WO2013096716A1

WO2013096716A1 - Closed loop settings optimization using revenue metric

Info

Publication number: WO2013096716A1
Application number: PCT/US2012/071124
Authority: WO
Inventors: Christopher O'neil
Original assignee: Agco Corporation
Priority date: 2011-12-21
Filing date: 2012-12-21
Publication date: 2013-06-27
Also published as: GB201200425D0

Abstract

Systems and methods for real-time closed loop machine settings optimization are presented. The system can be configured to provide a real-time revenue/loss view of a field to identify underperforming machines whose revenue performance may be improved by adjusting settings for various machine parameters such as speed, engine revolutions, implement settings, and the like. Machine yield data can be provided to a remote fleet revenue assessment system (FRAS) that can be configured to determine a machine revenue metric, such as a revenue ratio, for a plurality of machines in a fleet. Machine revenue metrics can be aggregated to provide a fleet revenue metric to which machine revenue metrics can be compared to identify underperforming machines. By eliminating poor field artifacts, a determination can be made as to whether revenue may be increased by settings adjustments. An algorithm or look-up table can be used to optimize settings and determine the proper adjustments

Description

CLOSED LOOP SETTINGS OPTIMIZATION USING REVENUE METRIC

FIELD OF INVENTION

[0001] This invention pertains generally to methods and systems for supporting agricultural operations, and more particularly to adjusting machine settings.

BACKGROUND OF INVENTION

[0002] In the agricultural industry there is a continual effort to increase operator and machine productivity while decreasing operational costs. Accordingly, farmers have embraced larger and more technically advanced machinery, more precise farming techniques and more automated technology. Precision farming enables crop product to be applied under field-specific parameters to optimize and better predict yield based on the particular characteristics of the field.

Properly implemented, precision farming techniques can reduce product, operator and equipment costs. Similarly, automated guidance systems relying on geo-positioning satellites for accurate location data, and on user input for designated tasks, can reduce operator error and fatigue, further mitigating costs.

[0003] One important measure in considering the effectiveness of agricultural machinery and methods is the amount of revenue generated, particularly in comparison to production costs. Improved farming techniques and advanced technology mentioned above can boost this measure. However, revenue produced at a particular time can be a function of several factors, including, but not limited to machine condition, machine settings, field conditions, and weather conditions. In some instances poor field and/or crop conditions compel tolerance of reduced revenue. At other times, however, poor revenue production or profit can be attributable to less than optimal machine operation. In these situations, a reduced profit rate need not be grudgingly tolerated; as there are possibilities that revenue can be increased by improving machine operation. For example, machine speed, RPM, and other parameters can affect both harvested yield and operational costs. Accordingly, machine settings can be adjusted to improve the revenue ratio either by increasing the yield or decreasing operational costs. Typically, all machines in a fleet are initialized with the same settings prior to heading out to the fields for a work assignment. However, because different machines can be subject to different tasks, different environmental conditions, different repairs, etc. over their lifetimes, the expectation that all machines will perform equally well with identical settings is rather unrealistic. There is a need to recognize real-time opportunities to improve a machine's revenue ratio by adjustment of its settings.

SUMMARY OF INVENTION

[0004] Methods and systems for closed loop machine settings optimization using a revenue metric are presented. In an exemplary embodiment, a system can include a telemetry unit (TU) configured to receive and transmit machine data, and a fleet revenue assessment system (FRAS) configured to receive said machine data and determine a real-time revenue metric. In an example embodiment, an FRAS is part of a fleet management system at a remote location from the TU. The TU can be configured for communication with the fleet management system over a communications network, such as a cellular network. In an example system, the FRAS can be configured to receive data from a plurality of machines, and determine a revenue metric for each. The plurality of revenue metrics can be aggregated to provide a fleet average revenue metric. An example system can be configured to map one or more machine revenue metrics to provide a dynamic revenue/loss view of a field. A system can be configured to assess a revenue metric to determine whether an opportunity exists to increase machine or fleet revenue through adjustments to machine settings. A system can be configured to automatically adjust machine settings to improve the revenue metric.

[0005] An example FRAS system can comprise a machine revenue metric module (MRMM) configured to determine a revenue metric for one or more individual machines; a fleet revenue metric module (FRMM) configured to determine a fleet revenue metric based on machine revenue metrics; a revenue metric mapping module (RMMM) configured to map one or more revenue metrics; and a revenue metric assessment module (RMAM) configured to assess machine or fleet revenue metrics, and a machine settings adjustment module (MSAM) configured to determine and implement machine settings adjustments. In an example embodiment, a system of the invention can include a machine settings optimization module (MSOM) at the machine configured to cooperate with an MSAM to implement adjustments. [0006] A method of the invention can include: determining a machine revenue metric, determining a fleet revenue metric, mapping a revenue metric, assessing a revenue metric, and automatically adjusting machine settings based on a revenue metric.

BRIEF DESCRIPTION OF THE DRAWINGS

[0007] FIG. 1 A depicts an example system for fleet revenue ratio

determination.

[0008] FIG. 1 B depicts an example system of the invention.

[0009] FIG. 2 depicts an example system of the invention.

[0010] FIG. 3 depicts an example fleet revenue assessment system (FRAS)

[0011] FIG. 4A depicts an example machine record.

[0012] FIG. 4B depicts an example fleet record.

[0013] FIG. 5A depicts an example revenue metric mapping.

[0014] FIG. 5B depicts an example revenue metric mapping.

[0015] FIG. 6 depicts a flow diagram of an example method of the invention.

[0016] FIG. 7 depicts an example method of the invention.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0017] As required, example embodiments of the present invention are disclosed. The various embodiments are meant to be non-limiting examples of various ways of implementing the invention and it will be understood that the invention may be embodied in alternative forms. The present invention will be described more fully hereinafter with reference to the accompanying drawings in which like numerals represent like elements throughout the several figures, and in which example embodiments are shown. The figures are not necessarily to scale and some features may be exaggerated or minimized to show details of particular elements, while related elements may have been eliminated to prevent obscuring novel aspects. The specific structural and functional details disclosed herein should not be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present invention. For example, functions discussed in the context of being performed by a particular module or device may be performed by a different module or device, or combined, without departing from the scope of the claims.

[0018] Referring now to the figures, the present invention will be described in detail. Referring to FIG. 1 A, an example system 100 can include one or more agricultural machines, represented here by machines 102, 104, 106, equipped with a telemetry data unit (TU) 1 10. The TU 1 10 can be configured to provide machine data, such as machine identification, location, and state information, over a communications network 120 to a fleet management system (FMS) 130 equipped with a Fleet Revenue Assessment System (FRAS) 140. Using the received machine data, the FRAS 140 can be configured to determine a real-time revenue metric for each of the machines 102, 104, and 106 as well as a fleet average revenue for the plurality of machines. The example system 100 is configured to optimize machines settings through closed loop adjustment based on a revenue metric determined by the FRAS 140.

[0019] FIG. 1 B shows a block diagram 150 that can represent the system 100 for closed loop optimization of machine settings. Harvester settings at block 152 can be provided to a revenue metric determination block 154. Harvester settings can include the settings for such machine parameters as speed, engine revolutions, implement height and clearance distances, and the like. They can comprise actual current settings at a machine, or the standard settings typically applied to machine of a particular type. The revenue metric determination block 154 can also receive current yield and loss monitors from the plurality of machines in a fleet, represented by block 156 to determine a revenue metric such as a machine revenue ratio for each machine in a fleet, and a fleet average revenue ratio. Based on one or more revenue metrics, a determination can be made that settings for one or more parameters on an underperforming machine should be made. Block 158 represents the machine settings optimization process by which optimum settings for achieving an improved revenue metric are determined. Block 160 represents implementing the changes to machine settings, which can be performed through cooperation of the FMS 130 and the particular machine 102, 104, 106.

[0020] The agricultural machines 102, 104, 106 can be in the form of an agricultural vehicle, by way of example, but not limitation, a combine harvester configured to cut, thresh and winnow crop product. The machines 102, 104, 106 can be equipped with any of a variety of implements, such as a standard header, wheat header, corn header, etc., and can include a flight elevator for transporting grain up the feederhouse into the combine, and a crop bin for collection of winnowed product. The machines 102, 104, 106, and any attached implement, may be provided with a variety of sensors, actuators, hydraulics and other tools to monitor and control various machine and implement states. The TU 1 10 can be embodied as a unit configured to receive input from various machine sensors and tools, and transmit the machine data. In an example embodiment, the TU 1 10 can comprise a data recorder configured to receive and record apparatus data from a plurality of sources, coupled to a data transmitter configured to transmit apparatus data received at the data recorder to the FMS 130.

[0021] The TU 1 10 can be configured to provide apparatus/machine data to the FMS130 by any suitable means, by way of example, but not limitation, by communication over the communication network 120, which can include one or more networks, for example a local area network (LAN) and a wide area network (WAN). A wireless communications system, or a combination of wire line and wireless may be utilized to communicate apparatus data. Wireless can be defined as radio transmission via the airwaves. However, other transmission techniques including, but not limited to, infrared line of sight, cellular, microwave, satellite, packet radio, and spread spectrum radio can also be employed.

[0022] The FMS 130 can include one or more devices configured for communication over a communications network. For example, one or more computer servers coupled to a modem for communication capability can be included at the FMS 130. The FMS 130 can include one or more dedicated servers, such as an application server configured to process data associated with a particular software application, a verification server configured to determine whether a user is authorized to communicate with the FMS 130, as well as any other servers or other devices required to support a system for determining machine and fleet revenue metrics for a plurality of machines.

[0023] The FMS 130 can include the FRAS 140 for determining a revenue metric for each of the machines 102, 104, 106, using machine data transmitted by the TU 1 10. The FRAS 140 can include one or more components or modules that can comprise hardware, software, firmware or some combination thereof. In an example embodiment, a module can be embodied as an application executed at a computing device or server at the FMS 130. The FRAS 140 can be configured to determine an average revenue metric for the fleet, and further be configured to compare individual machine metrics to each other or to a fleet metric to determine whether adjustments to machine settings should be made to improve machine and overall fleet performance. The FRAS 140 can be configured to implement settings adjustments.

[0024] FIG. 2 shows an example operating environment 200 that can be associated with the system 100 and includes a TU 210, one or more sensors 212 a...n, a positioning system 214, a processor 216, and an electronic control unit (ECU) 218. A data acquisition module (DAM) 222 can be included for

coordinating and/or controlling TU 210 operation. A machine optimization module (MSOM) 220 can be provided for cooperating with the FMS 130 to automatically adjust machine settings. [0025] The TU 210 can be configured to receive data from a plurality of sensors 212a..n, as well as other input associated with the agricultural machine 102. In an example embodiment, a sensor 212a can be positioned at a crop bin and configured to provide information regarding the weight or volume of harvested crop collected. By way of example, but not limitation, a sensor 212b can be positioned at a supply container, and configured to provide data representing the volume of consumable product remaining. As a further example, a sensor 212c can provide input associated with the state of a power take-off (PTO) on the agricultural machine 102. The type and location of sensors can vary in accordance with the type of agricultural machine, tool and/or implement. The sensors 212a-n can comprise mechanical or electrical sensors as well as electronic assemblies or modules. Further non-limiting examples include sensors that measure the height of an implement, machine speed, ignition state, and the like.

[0026] It is further contemplated that, in addition to receiving data captured by the sensors 212a-n, the TU 210 can receive status data from various subsystems or modules at the machine 102. In an illustrative example, the TU 210 can receive data from an electronic control unit (ECU) 218 configured to control various aspects of an apparatus or an implement. As described in U.S. Patent Application No. 12/648,985 entitled " Auto-Detection of a Field in Fleet

Management" filed on December 29, 2009 by Schmidt et al., which is

incorporated herein in its entirety by reference, the ECU 218 can be embodied as an autosteer system such as the Auto-Guide™ system manufactured by AGCO® of Duluth, GA. The TU 210 can be configured to receive information from the ECU 218 regarding current machine and implement state. For example, vehicle speed, rpm and direction can be provided by the Auto-Guide system, as well as information regarding the type of implement attached and its current setting position, such as raised or lowered, engaged or unengaged.

[0027] In an example embodiment, the TU 210 can be configured to receive data directly from various sensors or systems. For example, the components of the example operating environment 200 can be configured to form nodes for a controller area network (CAN) bus that provides serial communication capability between nodes, or, alternatively, can be communicatively coupled by other means. In a further example embodiment, input from various sensors/systems can be received at the processor 216, configured to control and coordinate operation of and interaction among various machine apparatus and components, and provided to the TU 210 in a compatible format.

[0028] The TU 210 can comprise a data receiver 202, a data recorder 204 and a data transmitter 206. The data recorder 204 can be configured to record data received at the TU 210. The data transmitter 206 can be configured to transmit data recorded at the data recorder 202. In an example embodiment, the data transmitter 206 can be configured to transmit to the FMS 130 over the

communication network 120.

[0029] By way of example, but not limitation, TU 210 data acquisition and transmission, such as commencement and termination of data recording, the type of data recorded, and the intervals at which apparatus data is received and transmitted to the FMS 130, can be controlled by the DAM 222, which can comprise hardware, software, firmware or some combination thereof. For example, the DAM 222 can be in the form of an application executed at the processor unit 216. In a further example embodiment, the DAM 212 can be embodied as a dedicated device such as, but not limited to, a microprocessor configured to control the TU 210 operation.

[0030] The positioning system 214 can be configured to provide a geographical location for the machine 102. In an example embodiment, the positioning system 214 can include a global positioning system (GPS) or global navigation satellite system (GNSS) receiver configured to receive satellite signals and determine a geographical location therefrom, as known in the art. Input from the positioning system 214 can be used to provide location data, as well as velocity data.

[0031] In an example embodiment, the MSOM 220 can be configured to cooperate with the FRAS 140 to automatically adjust settings at a machine. For example, the MSOM 220 can be configured to adjust settings based on a prompt received from the FRAS 140. The MSOM 220 can comprise a look-up table or an algorithm to determine the machine parameters to be adjusted, such as rpm, speed, etc and the adjustments to be made. In an alternative embodiment, the FRAS 140 can be configured to determine the machine adjustments and provide them to a machine, for example over the network 120. Adjustment

communications can be received at the TU 210, and provided to the processor 216 and/or MSOM 220 for decoding and formatting so that the signals required to implement the adjustments can be provided to the proper control units at the machine, for example via the CAN bus 235. AGCO Europe provides a feature called "Constant Flow" which ensures the same volume of material is flowing through the machine. This means that the Constant Flow is an embodiment of MSOM. Constant Flow software module will alter the engine RPM, Machine Speed, Rotor speed, concave settings, sieve etc to maintain a constant flow of material. Thus if a section of land is momentarily filled with less dense crop the machine speeds up and the slows down when the field becomes more dense with crop. This invention is stating that when multiple machines are in an area, they can communicate the field effects so that the Constant Flow feature can predict when it will make its adjustments before actually entering the portion of the field. Currently the CF must wait for several meters before its sensors are able to detect that the land has dropped /increase in crop density, so the communication between machine reduces this inefficiency of adjustment. The first machine does experience the delay in making the adjustment, but the remaining machines can be updated in advance of arriving at that section of the field.

[0032] In an exemplary embodiment, the FMS 130 can be embodied as an FMS 330 depicted in FIG. 3. The FMS 330 can comprise a central computing device (CCD) 332, a database 338 coupled to the CCD 332, and a fleet operations subsystem (FRAS) 340 coupled to the CCD 332 and the database 338. The CCD 332 can comprise a processor 334, a memory 336 that can comprise read-only memory (ROM) for computing capabilities and random access memory (RAM), a removable disc (not shown), and/or other devices with data storage capabilities, and a communications modem (not shown) for communications capabilities. By way of example, but not limitation, the CCD 332 can be implemented using a personal computer, a network computer, a mainframe, or microcomputer-based workstation. The database 338 can be configured to store data in various structured arrangements, for example in various accessible records. The database 338 can be embodied as a separate data storage device or as part of the memory 336 resident at the CCD 332. In an exemplary embodiment, records can be indexed and maintained by machine, fleet, and/or operator.

[0033] The FRAS 340 can include one or more modules configured to perform various revenue assessment related functions. Each module can be embodied as hardware, software, firmware or some combination thereof. By way of example, but not limitation, a module can be associated with a dedicated processing device. In a further example embodiment, a module can be configured to interact with the processor 334. By way of example, but not limitation, a module can be in the form of an application executed at the processor 334. In an example embodiment, a module can be embodied as an application service configured to cooperate with an application executed onboard the machines 102, 104, 106. In yet a further example embodiment, one or more modules shown at the FRAS 340 can instead reside at the machine itself and be configured to interact with an onboard computer or processor, such as the processor 216 or other modules in the environment 200. [0034] As shown in FIG. 3, the exannple FRAS 340 can include a machine revenue metric module (MRMM) 342, a fleet revenue metric module (FRMM) 344, a revenue metric mapping module (RMMM) 346, and a revenue metric assessment module (RMAM) 348. The MRMM 342 can be configured to determine a metric or measure/quantifier of machine income or revenue. For example, the MRMM 342 can be configured to determine total revenue, net profit or loss, or some other measure or quantifier of yield or revenue to provide a revenue metric. In an example embodiment, the MRMM 342 is configured to determine a revenue ratio, defined as revenue divided by costs associated with its production. The MRMM 342 can be configured to receive machine data associated with a particular machine and determine in real-time the potential revenue produced by the machine. For example, the MRMM 342 can receive machine data pertaining to the type and weight of machine yield, i.e. the harvested crop collected in a crop bin at the machine. By way of example, crop type can be input by an operator through a user interface at the machine 102, and subsequently identified in TU 210 transmissions to the FMS 330.

Alternatively, implement data such as header type can be provided by the ECU 218 to the TU 210, which can in turn transmit it to the FMS 330, where it can be used to determine crop type. For example, a standard header can be associated with cereal grains, a wheat header associated with wheat, a corn header, associated with corn, a flex platform associated with soybeans, etc. To determine the revenue associated with the harvested crop, the MRMM 342 can be configured to determine a real-time crop unit price, for example, the MRMM 342 can be configured to obtain current commodity pricing from the internet via a modem (not shown)at the CCD 332. In an example embodiment, the MMRM 342 can use the real-time unit price and the machine yield to determine the revenue generated by the machine.

[0035] The MRMM 342 can be configured to determine a cost associated with generating its projected revenue. Several factors can be considered in the cost determination; by way of example, but not limitation, operator hourly wage, number of operator work hours, fuel consumption, and fuel unit cost. In an example embodiment, the number of operator work hours can be determined from a machine start time and current time. For example, the positioning system 214 can include a date/time stamp in its location calculations which can begin at engine start-up. The TU 210 can transmit date and time data with machine location data to the FMS 330. The MRMM 342 can use the initial time stamp of the day and the most recent time stamp to determine the number of hours worked. Operator wage can be provided by a fleet manager and stored at the FMS 330, for example at the database 338. Fuel consumption can be

determined by the difference between the amount of fuel in the machine tank at the beginning of the job, and the current amount of fuel. For example, the TU 210 can receive initial fuel tank data from a sensor at the machine fuel tank, or from the ECU 218, when an operator starts up the machine. The initial fuel level can be transmitted by the TU 210 to the FMS 330 where it can be stored, for example at the database 338 in a format retrievable by the MRMM 342. At a predetermined time or time interval, for example as determined by the DAM 222, subsequent fuel levels can be detected and provided to the TU 210 for transmission to the FMS 330. Using initial and current fuel levels, machine fuel consumption can be determined.

[0036] Fuel cost can be determined in a variety of ways. By way of example, but not limitation, a fleet manager can provide actual fuel cost information via user input to the CCD 332, an average fuel cost per gallon can be provided by user input to the CCD 332, or the MRMM 342 can be configured to retrieve spot market price of fuel from an internet source. The MRMM 342 can be configured to use fuel unit price and fuel consumption to determine fuel cost. If desired, other costs, such as prorated insurance costs, maintenance costs, and the like can be provided to the FMS 330 by a user and stored, for example at the database 338. The MRMM 342 can be configured to retrieve the costs and include them in the machine cost determination. A machine revenue ratio can be determined by dividing projected revenue by cost.

[0037] As discussed above, the MRMM 342 can be configured to determine a machine revenue ratio; however, it is contemplated that other performance measures or quantifiers can be determined. For example, the MRMM 342 can be configured to determine machine profit or loss by subtracting machine costs from revenue produced by the machine.

[0038] The MRMM 342 can be configured to determine revenue, costs, and revenue ratios for a plurality of machines in a fleet. Each machine can provide its current location to the FMS 330 via TU 210 transmission of location data that can be provided by the positioning system 214. Current machine location can be stored at the database 338 in a machine record that can also include the machine revenue ratio determined at the MRMM 346.

[0039] FIG. 4A shows an example 400 of machine record that can be maintained at the database 338. In an example system, machine identity can be provided in the header of TU 210 messages to the FMS 330 so that machine data contained therein can be associated with the proper machine. Time can be expressed in column 402. In the example record 400, for illustrative purposes time is represented by to (an initial time), t1 , t2, etc. however, it is understood that actual times can be recorded so that time differences between initial and current times can be determined. Machine location coordinates can be expressed in terms of latitude and longitude in column 404, coordinates typically provided by GPS systems. The example 400 can further include a column 406 in which the field in which the machine is located can be identified. Fields can be defined by predetermined parameters, such as longitude and latitude

coordinates, at the FMS 330. For example, a user can provide field parameters at the CCD 332 via a user input device. The MRMM 342, or other module or application at the FMS 330 can be configured to use machine location coordinates and field parameter coordinates to identify the field in which the machine is currently located. The yield for a particular machine as a function of time can be recorded in column 408. For example, yield can be recorded in units of weight that can be used as a basis for calculating current revenue.

Although not shown as part of the record 400, it is understood that revenue and any other related parameter can also be included in the record 400. The cost associated with producing the revenue can be recorded in column 410. Column 412 can include the revenue metric determined for each machine.

[0040] The FRMM 344 can be configured to determine an average revenue metric for a fleet based on a plurality of individual machine revenue metrics. In an example embodiment, the FRMM 344 can be configured to determine an average fleet revenue ratio. In some cases a fleet can be spread out over a geographical area having a variety of fields, crops, and field conditions, while at other times, a fleet may be assigned to a more limited and homogenous area. To determine an average fleet metric based on similar fields and conditions, the FRMM 344 can be configured to use one or more predetermined criteria for selecting the machines to be included in the determination of the average revenue metric. By way of example, but not limitation, predetermined criteria can include: 1 ) selecting only those machines harvesting the same crop; 2) selecting only those machines working in the same field; 3) selecting only those machines within a predetermined radius of a predetermined location; 4) selecting only those machines producing at least a minimum yield; 5) selecting only those machines having yield/revenue within a certain percentage of a median yield/revenue, etc. After selecting machines that satisfy the predetermined criteria, should there be any designated, the FRMM 344 can determine an average metric by any of a variety of methods. In an example embodiment, an average value is determined by averaging the individual revenue ratios of the selected machines. The FRMM 344 can be configured to maintain a fleet revenue record, for example at the database 338. [0041] FIG. 4B shows a non-limiting example 420 of a fleet revenue record. The record can be compiled at a particular time, indicated in column 422.

Column 424 identifies the individual machines in the fleet. The location coordinates of each machine can be indicated in column 426, and the field that each is working in column 428. Machine location and field can be obtained from the machine record 400. The machine revenue metric for each machine, for example, the machine revenue ratio, can be provided in column 430. The average fleet revenue metric, for example, the average fleet revenue ratio, can be listed in column 432.

[0042] In an example embodiment, the RMMM 346 can be configured to map a revenue metric, or a comparison of revenue metrics, as a function of time and location to determine the nominal revenue potential at a field. FIG. 5A shows a mapping 500 of machine revenue ratio for machines A-F in Field 1 at time t1 . For example, the machines A-F can be mapped based on the locations and MRMs provided in columns 426, 430 respectively of the fleet record 420. A statistical mapping can be used to identify those machines having lower than average revenue production. Referring to FIG. 5A, machine F has the lowest revenue ratio of the six fleet machines. In an example embodiment, the RMMM 346 can be configured to compare each individual machine revenue metric with the fleet metric, and map the comparison, (which can be referred to as a comparison metric) allowing a machine to be compared to other machines and a fleet average in real time. FIG. 5B shows a mapping 520 of comparison metrics, here comparison or machine revenue ratio with fleet revenue ratio, for machines A-F in Field 1 at time t1 . In the case where a machine enters a field after all other machines have left, and thus has no real-time counterparts present, its revenue metric can be compared to the most recent fleet revenue metric for machines in that field. The comparison between machine and fleet metrics can be expressed as a percentage that is plotted by location to indicate profitable and non-profitable areas of the field, and identify underperforming machines. In an example embodiment, predetermined criteria, which can be the same or different from the predetermined criteria used at the FRMM 344, can be used to select the machine revenue ratios to be compared to the fleet average ratio. For example, a statistical mapping of the comparison of revenue ratios of all machines in the same field with the fleet average can be provided. The comparison between machine revenue ratio and fleet average revenue ratio for each machine can be stored at the database 338 as part of the machine record, as depicted in column 434 of the record 420 shown in FIG. 4B. It can also be stored in column 414 of the machine record 400. As shown in FIG. 5B, the machine F has a machine comparison metric lower than the other fleet machines. The 0.89 value indicates that the current revenue ratio of machine F is only 89% of the fleet average, indicating that it is underperforming in comparison with the other machines. The RMMM 346 can be configured to map revenue metrics other than revenue ratio as well. For example, the RMMM 346 can provide a statistical mapping of individual machine yields or revenues by location, or average fleet revenue by location and/or time. [0043] The RMAM 348 can be configured to assess a revenue metric. Values for machine, fleet, and comparison metrics can be considered along with predetermined evaluation criteria in this assessment. The RMAM 348 can be configured to retrieve information from machine and fleet records at the database 338 to perform this evaluation. Predetermined criteria can include minimum expected values for a particular revenue metric, maximum time periods for lower than expected values, minimum expected fleet metrics for a field, etc. The RMAM 348 can be configured to provide determination as to whether an opportunity exists to increase revenue by altering machine operation, either by adjusting machine settings or altering machine instructions or tasks. For example, if machine revenue ratio is less than 90% of the fleet average for longer than 10 minutes, the RMAM 348 can determine that machine settings for the particular machine need to be adjusted.

[0044] In an example embodiment, the MSAM 350 can be configured to determine how machine settings are to be adjusted. The MSAM 350 can include a look-up table of optimized adjusted values for particular parameters, such as speed, rpm, header parameters and the like. In an example embodiment, the MSAM 350 can comprise an algorithm to adjust settings based on current machine settings/states. By way of example, an algorithm can include changing a setting to a first value if current machine speed and rpm satisfy a first set of conditions, and changing a setting to a second value of current machine speed and rpm satisfy a second set of conditions. Changes can be implemented via control signals transmitted to the TU 210 over the network 120, which can then be provided to the appropriate control node via the CAN bus 235 to adjust machine and implement settings such as machine speed, machine rpm, implement height, conveyor speed, header drum speed, clearance distances, etc.

[0045] In an example embodiment, the FMS 330 can be configured to cooperate with the MSOM 220 at a machine. For example, the FMS 330 can be configured to provide a signal via the network 120 to a machine identified as a candidate for settings adjustments. The signal can include the adjustments to be made, or can provide notice to the MSOM 220 to determine and adjust settings. Via the CAN bus 235, the signal can be provided to the appropriate modules, by way of example, but not limitation, the PROC 216 and MSOM 220 to implement adjustments.

[0046] The FRAS 340 can be configured to provide a report pertaining to revenue metric to a user. In an example embodiment, a mapping can be presented to a fleet manager as a visual display, by way of example, but not limitation, at a display device coupled to the CCD 332 at the FMS 330, or as a download to a personal computing or communication device. In an exemplary embodiment, the FRAS 340 can be configured to cooperate with one or more applications to provide a visual display of the mapping as a function of time and location, either at a display device coupled to the FMS 300 or at a remote display device. By way of example, but not limitation, revenue or machine/fleet revenue metric comparisons can be superimposed on an image of the field being worked. A report can also be in the form of text provided to a fleet manager or an operator. As another example, an audio report can be provided by way of telephone. A report can comprise a notice that a machine or fleet revenue is below an expected value, or an advisory message to check machine equipment and settings for possible adjustments. In a further embodiment, a report can include an alert to a fleet manager that the fleet revenue metric of a field is below desired levels, giving a fleet manager the opportunity to change fleet

assignments to better utilize fleet resources. In an example embodiment, a report can include notice of automatic settings adjustments for the machine.

[0047] FIG. 6 shows a flow diagram of an example method 600 that can be practiced as part of a fleet revenue metric determination process. The method can begin in response to the satisfaction of a triggering condition, such as, but not limited to, key ON, engine ignition, or operator input, at which a machine can begin telemetry communication with the FMS 330, for example via the network 120. At block 602, machine data can be provided to the FMS 330. In an example embodiment, the DAM 222 can trigger activation of the various sensors 212a..n to provide input to the TU 210. In a further embodiment, sensors 212a..n can be configured to provide input to the TU 210 independent of the DAM 222. In an exemplary embodiment, a communications bus communicatively couples the TU 210 and the sensors 212a...n, the positioning system 214, the ECU 218 and the processor 216. By way of example, but not limitation, a controller area network (CAN) bus can provide connectivity between the TU 210 and the sensors

212a..n. In an example embodiment, the sensors 212a..n can be coupled to the TU 210 via wireless transmission, direct coupling or other communicative means. An example method can include receiving machine data at the processor 216, at which it can be formatted for compatibility with the TU 210 and/or the FMS 330 and then provided to the TU 210. The TU 210 can be configured to receive sensor input continuously, or at designated intervals, for example at intervals controlled by the DAM 222. Machine data can include real-time machine yield data. For example, the crop bin sensor 212a can provide data characterizing the weight of harvested crop product at the crop bin. Machine data can also include current machine location. For example, the positioning system 214 can determine machine location from satellite signals as known in the art, and provide location coordinates to the TU 210 via the CAN bus 235, along with a date/time stamp.

[0048] Machine data can be recorded at the TU 210 as data points that include machine identification data, data from a plurality sensors and various

components in the TU 210 operating environment, date and time, and any other relevant information that can be used by the FMS 300 to determine machine and fleet revenue metrics. In an exemplary embodiment, the DAM 222 comprising hardware, software, firmware or some combination thereof, can control the acquisition and transmission of apparatus data by the TU 210. By way of example, but not limitation, the DAM 222 can be in the form of software executed at the processor 216. In an exemplary embodiment, prior to transmitting machine data, a cooperative initialization and authorization process can be performed. The initialization communications can comprise service request, machine identification and/or operator identification, verification, configuration, or authorization messages, and/or other messages consistent with FMS 330 partitioning and communication protocols. Machine data can be transmitted by the TU 210 to the FMS 330 via the network 120. In an exemplary embodiment the communications network 120 comprises a cellular network, and the machine data comprises current yield information, such as, but not limited to, crop type and weight.

[0049] At block 604, machine adjustments can be received. As discussed previously herein, the machine 102 can receive adjustments determined by the FRAS 140, which can be implemented by the processor 216 and/or the MSOM 220. In a further embodiment, the machine 102 can receive a signal

recommending adjustments, which can serve as a prompt for the MSOM 220 to determine and implement actual settings adjustments. In yet a further embodiment, the machine 102 can receive machine and fleet revenue metrics, perform an assessment to determine whether adjustments should be made, and should the determination be in the affirmative, determine and implement the actual adjustments. For example of the fuel consumption of the fleet of machines in a particular section of the field is exceeded by one machine, then a setting can be sent to the machine operator to reduce RPM. The example of Constant Flow would be applicable here. I once heard a fleet manager complain that when his machines are transporting from one field to another that one or two of the machines will be delayed because the operator is taking a break. The FRAS could detect this and send a notice to the operator that their transportation time expectation is below the norm for the fleet. [0050] FIG. 7 shows an example method 700 that can be practiced in a fleet revenue determination process. At block 702, machine data can be received at the FMS 130. For example, machine crop yield data, such as 50 kg of wheat, can be received at the FMS 130 via the network 120. At block 704, a machine revenue metric can be determined, for example, a machine revenue ratio can be determined. The MRMM 342 can obtain market spot pricing for the crop, for example from the internet through a modem (not shown) at the CCD 332 .

Obtaining a dollar/bushel price, and using the appropriate conversion factor to convert kg of crop to bushels of crop the MRMM 342 can determine the revenue expected from the current machine yield.

[0051] The MRMM 342 can further determine the cost of producing the expected machine revenue. In an example embodiment, operator cost can determined by multiplying hourly wage and hours worked. As stated previously above, operator wage rate can be stored at the database 338. Hours worked can be determined from the difference between initial transmission time stamp and most recent time stamp. Fuel cost can be determined by multiplying price per gallon of fuel and the number of gallons of fuel consumed, which can be derived from initial and current fuel tank sensor data. If desired, additional costs, such as insurance costs, and the like can be stored at the database 338 for retrieval by the MMRM 342. The MRMM 342 can determine a machine revenue ratio by dividing expected revenue by the determined costs.

[0052] At block 706, a fleet revenue metric can be determined. By way of example, the FRMM 344 can determine an average fleet revenue ratio. In accordance with any predetermined criteria, individual machine revenue ratios can be selected and averaged to provide an average fleet revenue ratio. For example, machine revenue ratios and other relevant information such as machine location, can be retrieved from machine records stored at the database 338 for use in this determination.

[0053] At block 708, a mapping of a revenue metric can be performed at the RMMM 346. For example, individual machine revenue ratio can be mapped by time and machine location, as shown in mapping 500 (FIG. 5A). As another example, a comparison of machine revenue ratio and fleet revenue ratio, can be mapped by time and location. Each machine ratio can be divided by the fleet average revenue ratio to provide a machine revenue comparison metric. The machine revenue comparison metric can be mapped by location to provide a view of fleet revenue production for a field, as shown by the mapping 520 (FIG. 5B). The machine revenue comparison metric can be stored in column 434 of the fleet record 420. Data from the fleet record 420 and machine record can be used in the mapping process.

[0054] As a further example, a fleet revenue metric can be mapped by field location, for instance machine metrics for machines in a first portion of a field can be aggregated to provide a fleet metric for that portion of the field, while machines in a different section of the field can be aggregated to provide a fleet metric for the different section. The fleet metrics for the different sections can be mapped to show fleet metrics over the field. [0055] At block 710, a revenue metric can be assessed. In an example embodiment, the RMAM 348 can use predetermined adjustment criteria or conditions, machine revenue metrics and fleet revenue metrics for this

assessment. For example, the machine revenue metric and machine

comparison metrics listed in columns listed in columns 412, 414 of the machine record 400, or listed in columns 430, 434 respectively can be user predetermined criteria can include predetermined thresholds, predetermined time periods for which thresholds are exceeded or failed, and the like. An assessment can include a determination as to whether an opportunity exists to improve a revenue metric by altering machine or fleet operation. For example, if the machine revenue comparison metric is 10% below the average for 10 minutes or longer, a determination can be made to adjust machine settings.

[0056] At block 712, adjustments to machine settings can be performed to improve a revenue metric. For example, the MSAM 350 can determine adjusted values for one or more machine parameters and provide them to the machine 102 via the network 120.

[0057] At block 714, a report can be provided based on a revenue metric. For example, the mapping 520 can be provided to a fleet manager. Alternatively, a message that one or more machines has a poor revenue metric can be provided, or a notice that one or more adjustments have been made to a machine's settings.

[0058] Systems and methods for closed looped optimization of machine settings based on a revenue metric are presented. A revenue metric can be any measure or quantifier of revenue, including, but not limited to total revenue, profit, loss, total yield, average revenue, average yield, or revenue ratio. Individual machine metrics can be determined, as well as a fleet metric. A system can determine a machine metric for each of a plurality of machines in a fleet. A fleet metric can be determined by the aggregation of a plurality of machine metrics. In an example embodiment, a plurality of machine metrics can be averaged to provide a fleet metric, and the individual machine metrics can be compared to the fleet metric.

[0059] A system of the invention can be configured to map a revenue metric or a comparison between a machine and a fleet revenue metric to provide a dynamic revenue/loss view of the field. The revenue metric map can be used to more robustly recognize opportunities to improve the revenue metric and eliminate poor field condition artifacts. By way of example, but not limitation, a revenue metric map can display machine revenue metrics, such as machine revenue ratios, fleet revenue metrics, such as a fleet average revenue ratio, or a comparison between machine metrics and a fleet metric, such as a comparison of machine revenue ratio with a fleet revenue ratio. The mapping can help identify those machines whose subpar performance is likely caused by poor field conditions, as well as machines whose unsatisfactory performance is likely to be the result of non-optimal machine operation.

[0060] Based on an assessment of one or more revenue metrics, a

determination can be made as to whether a particular machine's settings should be adjusted. A system of the invention can automatically change a machine's parameters, such as speed, rpm, header settings, etc. In an example

embodiment a look-up table or an algorithm can be used to determine what types of adjustments should be made to optimize performance. A central fleet management system can cooperate with a machine over a communications network to implement the adjustments.

[0061] A system can provide a report based on one or more revenue metrics. For example, a dynamic revenue view of a field can be provided to a fleet manager in real time. In an example embodiment, , if an individual machine revenue ratio falls too far below the fleet average, but it is working under similar field conditions, an alert to that effect can be sent to an operator or fleet manager. A dynamic revenue metric mapping or view of a field can also be used to determine when harvesting a field or portion of a field is no longer profitable. For example, if an average fleet revenue metric indicates a loss, or an

unacceptable profit margin, a decision can be made by an operator or fleet manager to spend less time on the field, abandon a portion of it, or begin a new task.

[0062] Although the invention has been described with reference to non-limiting example embodiments illustrated in the attached drawings, it is noted that equivalents may be employed and substitutions made herein without departing from the scope of the invention as recited in the appended claims. For example disclosed methods may be practiced in varying order and steps may be added or deleted without departing from the scope of the invention. In addition functions described as performed by a particular apparatus or module may be performed by a separate or different module or apparatus, or combined at a single module or apparatus. System elements disclosed as separate can be combined or reconfigured as will occur to those skilled in the art.

Claims

CLAIMS What is claimed:

1 . A system, comprising:

a telemetry unit configured to receive and transmit machine data; and

a fleet revenue assessment system (FRAS) communicatively coupled to said telemetry unit and configured to adjust machine settings based on a revenue metric.

2. The system of claim 1 , wherein said revenue metric comprises a machine revenue ratio.

3. The system of claim 1 , wherein said adjustment is based on a comparison of a machine revenue ratio with a fleet revenue ratio.

4. The system of claim 3, wherein said fleet revenue ratio comprises an aggregation of a plurality of said machine revenue ratios for a plurality of machines.

5. The system of claim 1 , wherein said FRAS comprises:

a machine revenue metric module configured to determine a machine revenue metric for a particular machine;

a fleet revenue metric module configured to aggregate said revenue metrics for a plurality of said machines to provide a fleet revenue metric; an assessment module configured to compare at least one of said machine and fleet revenue metrics to one or more predetermined criteria; and

a machine settings adjustment module to adjust one or more parameter settings for said machine.

6. The system of claim 5, wherein said parameters include speed, engine revolutions, and implement height.

7. The system of claim 1 , configured to adjust settings for a plurality of different machines.

8. A method, comprising:

receiving fleet revenue monitors;

receiving machine settings;

receiving machine location;

determining a revenue metric; and

adjusting machine settings to improve said revenue metric.

9. The method of claim 8, wherein said revenue metric comprises a comparison of a machine revenue ratio with a fleet revenue ratio.

10. The method of claim 8, wherein said adjusting machine settings comprises automatically adjusting said settings at a remote machine.

1 1 . The method of claim 8, wherein said determining a revenue metric comprises determining a machine revenue metric.

12. The method of claim 1 1 , wherein said determining a revenue metric further comprises determining a fleet revenue metric.

13. The method of claim 1 1 , further comprising mapping said revenue metric as a function of time and location.

14. The method of claim 9, wherein said determining a revenue metric comprises determining a machine metric for a plurality of machines in a fleet.

15. A method comprising:

providing machine yield data;

providing machine location data; and

r eceiving machine settings adjustments.