Irrigation system including electronic independent observer integrated with fertigation system

Abstract

A monitoring system for an irrigation system that includes a nozzle and a product source that supports a product for mixing with water from a water source to which the irrigation system is operably coupled. The monitoring system comprises: a sensor (102, 1120) configured to generate a first electrical signal indicative of a travel speed and / or direction of travel of the irrigation system; a fluid pressure sensor (1170) configured to generate a second electrical signal indicative of a flow rate; a processor (220), a memory (230), and a variable speed pump (10) or valve (2800, 902). The memory (230) includes instructions that, when executed by the processor (220), cause the monitoring system to receive the first and second generated electrical signals, determine a rate of application of the irrigation fluid over the predetermined irrigation area based on the first and second electrical signals, and adjust a flow rate of the irrigation fluid through the at least one nozzle.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 325,798, filed on March 31, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present invention relates to an irrigation system, and more particularly to a structure and method for realizing integrated fertilization system control by using the irrigation system. Background Art

[0004] Over- or under-fertilization can occur when irrigation pivots slow down or speed up unexpectedly due to pivot failure, muddy fields or user error. Irrigation systems such as pivots, lateral move systems and drip systems fail an average of three times per 40 uses per year. These failures occur during critical growth stages and, in many cases, in the middle of a field. Today, nutrient injection is an open-loop process relative to actual pivot speed, which leads to an increased risk of misapplication. Summary of the invention

[0005] In order to fully apply fertilizers and mitigate the increased costs and other problems associated with irrigation system failures, the present disclosure details a solution that includes digitally observing the irrigation system during normal operation and setting parameters that control the flow of fertilizers. In order to observe operational anomalies, sensors can be added to the irrigation system to provide data for algorithm processing. These algorithms can be logic-based or analytical. In some cases, existing operational data (e.g., off-the-shelf) can be used. In some aspects, other data sources can be external to the system, such as weather, topographic maps, soil moisture, etc. from the National Oceanic and Atmospheric Administration (NOAA), or a combination thereof.

[0006] According to some aspects of the present disclosure, a monitoring system for an irrigation system operably coupled to a water source is provided. The irrigation system includes at least one nozzle and a product source that supports a product for mixing with water from the water source to form an irrigation fluid. The monitoring system includes: a sensor configured to generate a first electrical signal indicating a speed of travel of at least a portion of the irrigation system or a direction of travel of at least a portion of the irrigation system; a fluid pressure sensor configured to generate a second electrical signal indicating a flow rate of the irrigation fluid through the at least one nozzle; at least one of a variable speed pump or a valve operably coupled to the product source so that the product can be dispensed from the product source; a processor; and a memory. The memory includes instructions stored thereon that, when executed by the processor, cause the monitoring system to: receive first and second generated electrical signals; determine a rate of application of the irrigation fluid on a predetermined irrigation area based on the first and second electrical signals; and adjust the flow rate of the irrigation fluid through the at least one nozzle by actuating a valve and / or changing the speed of the variable speed pump based on the determined rate of application.

[0007] In one aspect of the present disclosure, the product may include nutrients, and thus the monitoring system is configured to determine the amount of nutrients applied to a predetermined irrigation area.

[0008] In another aspect of the present disclosure, a product source may be configured for product storage, product preservation, and / or product transportation.

[0009] In another aspect of the present disclosure, a fluid pressure sensor may be coupled to an end of a span of a pivot of an irrigation system.

[0010] In another aspect of the present disclosure, a fluid pressure sensor may be disposed proximate to at least one nozzle.

[0011] In one aspect of the present disclosure, at least one nozzle may be supported on a movable end gun.

[0012] In another aspect of the disclosure, at least a portion of the irrigation system may be a movable end gun such that the first electrical signal indicates a speed of travel of the movable end gun relative to a span of a pivot of the irrigation system or a direction of travel of the movable end gun relative to the span.

[0013] In another aspect of the present disclosure, when the instructions are executed, the monitoring system may also be caused to: determine an angular velocity of at least one nozzle and a time taken for at least one nozzle to advance and / or retract based on the first electrical signal; determine that at least one nozzle has pivoted more than a predetermined number of degrees without the at least one nozzle dispensing irrigation fluid; and provide an indication to a user that a location in a predetermined irrigation area is not fertilized with the product based on the determination.

[0014] In another aspect of the present disclosure, the nozzle is movably mounted on a pivot of the irrigation system.

[0015] In one aspect of the present disclosure, the monitoring system may further include an analysis engine configured to perform the determination. The analysis engine may include a machine learning model. The machine learning model may be based on a deep learning network, a classical machine learning model, or a combination thereof.

[0016] In another aspect of the present disclosure, a monitoring system for an irrigation system is presented. The irrigation system includes a movable end gun operably associated with a portion of the irrigation system. The monitoring system includes a sensor configured to be coupled to the movable end gun and configured to generate an electrical signal indicating movement and / or positioning of the movable end gun relative to the portion of the irrigation system over time; a product tank coupled to the irrigation system, the product tank configured to dispense product; a processor; a memory, and at least one of a variable speed pump or a valve, the variable speed pump or the valve being configured to control the flow rate of the product from the product tank to the movable end gun. The memory includes instructions stored thereon that, when executed by the processor, cause the system to: receive the generated electrical signal; determine a rate of application of the product over a predetermined area based on the electrical signal; and actuate the valve and / or change the speed of the variable speed pump based on the determined rate of application.

[0017] In yet another aspect of the present disclosure, when the instructions are executed, the monitoring system may also be caused to determine the angular velocity of the movable end gun and the time taken for the movable end gun to advance and / or retreat based on the electrical signal.

[0018] In another aspect of the present disclosure, when the instructions are executed, the monitoring system may also be caused to generate a report based on the determination.

[0019] In another aspect of the present disclosure, when the instructions are executed, the monitoring system may also determine whether the end gun is pivoted more than a predetermined degree when the end gun is not in a triggered state, and provide an indication to the user that the position is not fertilized based on the determination.

[0020] In another aspect of the present disclosure, the portion of the irrigation system may include at least one of a lateral drive, a water winch, and / or a pivot, wherein the movable end gun is movably mounted on the pivot.

[0021] In another aspect of the present disclosure, the monitoring system may further include an analysis engine configured to perform the determination.

[0022] In another aspect of the present disclosure, when the instructions are executed by the processor, the monitoring system may also receive data from at least one of a weather station, a field soil moisture sensor, a topographic map, a soil map, a temperature sensor, or a National Oceanic and Atmospheric Administration weather.

[0023] In another aspect of the present disclosure, the analysis engine may include a machine learning model. The machine learning model is based on a deep learning network, a classical machine learning model, or a combination thereof.

[0024] In another aspect of the present disclosure, the sensor may include at least one of an encoder, a magnetometer, a gyroscope, an accelerometer, a camera, a gesture sensor, a microphone, a laser rangefinder, a reed switch, a magnetic switch, a GPS, and / or an optical switch.

[0025] In another aspect of the present disclosure, a computer-implemented method for monitoring an irrigation system is presented. The irrigation system is operably coupled to a water source. The irrigation system includes at least one nozzle and a product source that supports a product for mixing with water from the water source to form an irrigation fluid. The method includes: receiving a first electrical signal generated by a sensor configured to generate a first electrical signal indicating a speed of travel of at least a portion of the irrigation system or a direction of travel of at least a portion of the irrigation system; receiving a second electrical signal generated by a fluid pressure sensor configured to generate a second electrical signal indicating a flow rate of the irrigation fluid through the at least one nozzle; determining a rate of application of the irrigation fluid over a predetermined irrigation area based on the first and second electrical signals; and adjusting the flow rate of the irrigation fluid through the at least one nozzle by at least one of: actuating a valve; or changing a speed of a variable speed pump based on the determined rate of application. The valve is operably coupled to the product source to enable the product to be dispensed from the product source. The variable speed pump is operably coupled to the product source to enable the product to be dispensed from the product source.

[0026] Other aspects, features, and advantages will become apparent from the following description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various aspects of the present disclosure and, together with the general description of the present disclosure given above and the detailed description given below, serve to explain the principles of the present disclosure, in which:

[0028] Figure 1 is a schematic diagram of a monitoring or predictive maintenance system;

[0029] Figure 2 is configured for use Figure 1 Block diagram of the controller of the predictive maintenance system;

[0030] Figure 3 is configured for use Figure 1 Schematic diagram of the machine learning model of the predictive maintenance system;

[0031] Figure 4A An exemplary flow chart showing a typical farm operation;

[0032] Figure 4B An exemplary flow chart of farm operations including a predictive maintenance system according to the principles of the present disclosure is shown;

[0033] Figure 5 Shows Figure 1 Data science workflow for various models of the predictive maintenance system shown;

[0034] Figure 6-Figure 8 yes Figure 1 A schematic diagram of an example hardware interface and instrumentation for a predictive maintenance system;

[0035] Fig. 9 yes Figure 1 A perspective view of a portion of an exemplary pivot of a predictive maintenance system;

[0036] Fig.10 yes Figure 1 A perspective view of a portion of another exemplary pivot air compressor apparatus of a predictive maintenance system;

[0037] Fig.11A is a perspective view of an end gun assembly of a predictive maintenance system according to the principles of the present disclosure;

[0038] Fig. 11B yes Fig.11A A side view of the end gun assembly;

[0039] Figure 12A-12C is to use Fig.11A Example signals generated by a predictive maintenance system;

[0040] Fig.13A and Fig. 13B An exemplary flow chart of a predictive maintenance system including end gun monitoring according to the principles of the present disclosure is shown;

[0041] Fig.14 An exemplary data science workflow for a predictive maintenance system of the present disclosure is shown;

[0042] Figure 15-17 is an exemplary flow chart of a testing system of the predictive maintenance system of the present disclosure;

[0043] Fig.18 is an exemplary model for end gun performance prediction using a nine-degree-of-freedom inertial measurement unit;

[0044] Figure 19-21 is a high-level block diagram of a predictive maintenance system according to the present disclosure;

[0045] Fig. 22 According to the present disclosure Fig. 27 The state machine diagram of the system;

[0046] Fig.23 is a diagram of end gun quadrants in a field for determining the location of irrigation faults according to the present disclosure;

[0047] Fig.24 According to the present disclosure Figure 1 A diagram of an example gyro signal output of a predictive maintenance system;

[0048] Fig.25 According to the present disclosure Figure 1 A diagram of an example compass signal output of a predictive maintenance system;

[0049] Fig.26 According to the present disclosure Figure 1 A diagram of an example accelerometer signal output of a predictive maintenance system;

[0050] Fig. 27 yes Figure 1 A perspective view of an end gun of a predictive maintenance system with an end gun monitoring system installed thereon;

[0051] Fig.28 Shows Figure 1 Perspective view of a remote mounted booster pump system for a predictive maintenance system;

[0052] Fig.29 yes Figure 1 A perspective view of components of a control box of a fertilization system of a predictive maintenance system;

[0053] Fig.30 It communicates with the controller of the fertilization system Figure 1 Perspective of the predictive maintenance system gateway;

[0054] Fig.31 is a perspective view of the various parts of the fertilization system, showing the connection to Figure 1 Predictive maintenance of irrigation systems, fertigation systems, fertilization tanks and pumps; and

[0055] Fig.32 Shown for Figure 1 The control panel of the predictive maintenance system. DETAILED DESCRIPTION

[0056] Various aspects of the disclosed predictive maintenance system are described in detail with reference to the accompanying drawings, wherein the same reference numerals represent the same or corresponding elements in the multiple views. Directional terms such as top, bottom, etc. are used only for descriptive convenience and are not intended to limit the attached disclosure. In addition, as used herein, the term "on" includes being in an open or activated position, and the term "off" includes being in a closed or inactivated position.

[0057] In the following description, well-known functions or constructions are not described in detail to avoid obscuring the present disclosure in unnecessary detail.

[0058] Advantageously, the system of the present disclosure monitors various aspects of an irrigation system (e.g., the position and travel speed of a pivot of an irrigation system with an "independent observer" not directly involved in the control of the pivot) to determine the optimal output of a product tank so that a predetermined amount (e.g., volume) of product (e.g., nutrients) is applied to a predetermined area within a predetermined time (e.g., as specified by the farm operations team). As used herein, "independent observer" includes sensors and analysis that are not directly involved in the control of the pivot.

[0059] refer to Figure 1 and Figure 7-Figure 9 , a monitoring system 100 for an irrigation system (for agriculture, mining, etc.) is provided. Generally, the monitoring system 100 includes an irrigation system 106 and a controller 200, which is configured to execute instructions for controlling the operation of the monitoring system 100. The irrigation system 106 may include a pump 10 (e.g., a compressor or booster pump, see FIG. 11 ), a pivot 20, one or more towers 30, an end tower 40, a corner tower 50, an air compressor 60, and an end gun 70 (also known as a large gun, a large capacity gun, and / or a movable nozzle). The pump 10 may include one or more current sensors and a wireless communication device 104, which is configured to wirelessly transmit data (e.g., sensed current data) to the controller 200. The pivot 20 may include one or more sensors 102 and a wireless communication device 104, which is configured to wirelessly transmit data to the controller 200. Each tower 30, corner tower 50 and end tower 40 may include one or more sensors 102 and wireless communication devices 104, which are configured to wirelessly transmit data to controller 200. Wireless communication devices may include, for example, 3G, LTE, 4G, 5G, Bluetooth and / or Wi-Fi, etc. Sensor 102 may include at least one of a current sensor, a voltage sensor and / or a power sensor, which are configured to sense, for example, current, voltage and / or power, respectively. In some aspects, when as part of a system, these sensors 102 may measure the power transmission into the motor of the booster pump 10. The pump 10 may include a transmission line on the span, a contactor, and components for actuating the contactor, motor components including electrical components, mechanical components and pump components including impellers, inlets, outlets and / or pipes. In some aspects, the pump 10 may include a flow sensor (not shown) on the booster pump outlet.

[0060] In some aspects, the one or more sensors 102 may include any suitable sensor, such as an encoder (eg, an angle encoder), a pressure sensor, a flow meter, etc. or a combination thereof. An angle encoder may be in the form of a position sensor that measures the angular position of a rotating shaft.

[0061] In some aspects, one or more sensors may be connected (e.g., directly) and / or may be separate components that may be connected via a wide area network (WAN). In some aspects, one or more sensors may be aggregated in a cloud based on a provisioning setup. In some aspects, one or more sensors may include, for example, a low power wide area network technology (LPWAN) that may be long range (LoRa).

[0062] In some aspects, controller 200 may determine a change in the condition of at least one component based on a comparison of the generated signal to predetermined data.

[0063] The controller 200 is configured to receive data from the sensors 102 and from external data sources (e.g., weather station 82, field soil moisture sensor 86, terrain and soil map 88, temperature sensor 89, and / or National Oceanic and Atmospheric Administration (NOAA) weather 84) to make and / or refine a prediction indicating the status of at least one of the plurality of components of the irrigation system 106 (e.g., pivot 20, end gun 70, tower 30, etc.). The prediction enables the controller 200 to determine a change in the condition of at least one component and predict the fertilizer demand (e.g., volume / time) for a predetermined area (e.g., a cropping area or field requiring irrigation and / or fertilizer application) based on predetermined data (e.g., historical data). For example, the prediction may be based on comparing the determined change in the condition of at least one component of the irrigation system 106 with predetermined data. For example, the sensor 102 of the tower 30 (or pivot 20, or end gun 70, etc.) may sense the current consumption of the tower 30 (or pivot 20, or end gun 70, etc.). The controller 200 may then compare the sensed current draw to a predetermined current draw for the tower 30, which may be a baseline current draw, a historical current draw, and / or a typical current draw for the tower 30 or other towers. For a particular set of conditions (sunny day, dry soil, etc.), the controller may determine that the sensed current draw for the tower 30 is significantly higher than the predetermined current draw by a predetermined amount (e.g., about 30%). Based on this determination, the controller 200 may predict that the tower 30 is irrigating at a slower rate than normal. In another embodiment, the system may sense, via the sensor 102, that the current on the pump 10 is low, and therefore predict that the pump 10 is not pumping enough water. In an example, the topographic map identifies when the pivot 20 is tilted along a slope, thereby increasing the pressure at the end gun 70, which helps determine why the pressure is higher in that particular area and the rate at which fertilizer may need to be changed. In many aspects, the system may use the maintenance needs of the irrigation system to determine the amount of fertilizer required for an area (e.g., a field, a zone, a quadrant, etc.).

[0064] Data from external data sources can be used to improve model predictions. For example, by processing data such as higher power used by the motor of tower 30 (due to rain causing muddy fields), such processed data can be used to improve model predictions. Monitoring system 100 can display a map of the field, topography, soil type, etc. This helps the model account for changes in power usage. The predictions can be transmitted by controller 200 to user device 120 for display and / or further analysis.

[0065] In some aspects, the data and / or predictions may be processed by a data visualization system 110. Data visualization is a graphical representation of information and data. Using visualization elements such as charts, graphs, and maps, data visualization tools provide an accessible way to view and understand trends, outliers, and patterns in data.

[0066] In some aspects, monitoring system 100 can be implemented in the cloud. For example, Linux that can run Python scripts can be used to implement predictions.

[0067] Figure 2 The controller 200 is shown to include a processor 220 connected to a computer-readable storage medium or memory 230. The computer-readable storage medium or memory 230 can be a volatile type of memory (e.g., RAM), or a non-volatile type of memory (e.g., flash media, disk media, etc.). In some aspects of the present disclosure, the processor 220 can be another type of processor, such as a digital signal processor, a microprocessor, an ASIC, a graphics processing unit (GPU), a field programmable gate array (FPGA), or a central processing unit (CPU). In certain aspects of the present disclosure, network reasoning can also be accomplished in a system with weights implemented with memristors, chemical methods, or other reasoning calculations, as opposed to processors.

[0068] In some aspects of the present disclosure, the memory 230 may be a random access memory, a read-only memory, a disk memory, a solid-state memory, an optical disk memory, and / or other types of memory. In some aspects of the present disclosure, the memory 230 may be separate from the controller 200 and may communicate with the processor 220 via a communication bus of a circuit board and / or via a communication cable such as a serial ATA cable or other types of cables. The memory 230 includes computer-readable instructions that can be executed by the processor 220 to operate the controller 200. In other aspects of the present disclosure, the controller 200 may include a network interface 240 for communicating with other computers or servers. The storage device 210 may be used to store data.

[0069] The disclosed method may be executed on the controller 200 or on a user device, including, for example, a mobile device, an IoT device, or a server system.

[0070] In some aspects, an analytics engine (e.g., a machine learning model and / or classical analytics) may be configured to perform the determination.

[0071] Figure 3 A machine learning model 300 and data flow\storage\feedback of a pivot predictive maintenance system are shown. The machine learning model 300 may be hosted at the pivot 20 or in the cloud (e.g., a remote server). The machine learning model 300 may include one or more convolutional neural networks (CNNs).

[0072] In machine learning, convolutional neural networks (CNNs) are a class of artificial neural networks (ANNs) that are most commonly used to analyze visual images. The convolution aspect of CNNs involves applying matrix processing operations to local parts of an image, and the results of these operations (which may involve dozens of different parallel and serial calculations) are a collection of many features for training neural networks. CNNs typically include convolutional layers, activation function layers, and pooling (usually maximum pooling) layers to reduce dimensions without losing too many features. Additional information may be included in the operations that generate these features. Providing unique information that generates features that give neural network information can be used to ultimately provide a way to aggregate to distinguish different data input to the neural network. In some aspects, the machine learning model 300 may include a combination of one or more deep learning networks (e.g., CNNs) and classical machine learning models (e.g., SVMs, decision trees, etc.). For example, the machine learning model 300 may include two deep learning networks.

[0073] In some aspects, two labeling methods for training data can be used, one based on connection to a computerized maintenance system (CMMS) and the other based on user input. In some aspects, the user can be prompted to label the data, or the data can be provided manually (e.g., at the time of a service event).

[0074] As mentioned above, Figure 4A An exemplary flow chart of a typical farm operation 400a is shown. Typically, at step 410, pre-season maintenance is performed on the irrigation equipment. Next, at step 420, the irrigation equipment is used during the season. At step 440, if the equipment is determined to be damaged, it is sent for repair at step 430. At the end of the season (step 450), post-season maintenance is performed (step 460).

[0075] Figure 4B An exemplary flow chart 400b of farm operations including a monitoring system 100 in accordance with the principles of the present invention is shown. Typically, at step 410, pre-season maintenance is performed on irrigation equipment. Next, the monitoring system 100 predicts whether a particular irrigation equipment will require maintenance. If maintenance is predicted at step 415, then at step 430, the equipment is inspected and repaired. Next, at step 420, the irrigation equipment is used during the season. At step 440, if the equipment is determined to be damaged, then the equipment is sent for repair at step 430. At the end of the season (step 450), post-season maintenance is performed (step 460).

[0076] Figure 5 Shows that there is Figure 4B Data science workflow for various models of a predictive maintenance system shown.

[0077] The five models include an end gun prediction model 502, a tower drive prediction model 504, a sequencing prediction model 506, an air compression prediction model 508, and an electrical prediction model 510. These models may be implemented through logic and / or machine learning.

[0078] refer to Figure 5 and 18 , showing the end gun prediction model 502. The end gun prediction model can calculate the end gun 70 ( Figure 1 ) The number of times the bearing moves back and forth from left to right. The expected time for movement to the left and right can be based on pressure, bearing condition, tension, etc. or a combination thereof.

[0079] The end gun prediction model 502 may consider expected power based on directly measured soil moisture or inferred from weather data from a field or regional weather station, topographic maps, soil maps, motor RPM, gearbox ratios, tower weight, span weight, operating conditions, etc., or a combination thereof. The end gun 70 includes instrumentation that measures each cycle using proximity switches, encoders, capacitance, and / or an imaging system. Aspects of the monitoring system 100 may be mounted on the irrigation system 106 or mounted outside the irrigation system 106 (e.g., a moisture sensor records when water dispensed into the field is remotely splashed). If an electronic gun is used, energy usage and duty cycle may be used. In some aspects, one or more sensors may include any suitable sensor, such as an encoder (such as an angle), a pressure sensor, a flow meter, a magnetometer, a gyroscope, an accelerometer, a camera, a gesture sensor, a microphone, a laser rangefinder, a reed / magnetic / optical switch, etc., or a combination thereof. The end gun prediction model 502 may also include as input pump pressure, end gun model, end gun nozzle diameter, drive arm spring setting, diffuser type, flow measurement, drive arm spring K factor, drive arm balance, drive arm bearing condition, base bearing condition, base seal condition, drive arm alignment and / or mounting base stiffness ( Fig.18 ). The nozzle type can be inferred from the measured flow rate and the measured pressure. In some aspects, the end gun prediction model 502 ( Fig.18 ) can predict the frequency of drive arm impacts, the magnitude of acceleration at each drive arm impact, the forward angular velocity, the reverse angular velocity, the rate of change of forward or reverse heading, the time of each pass, and / or the time to flip the steering column. The model output can be used to further predict abnormal operation.

[0080] Abnormal operation of the end gun can also be based on the movement and / or positioning of the movable end gun 70 relative to the pivot 20 (and / or other parts of the irrigation system, such as lateral drives, water winches, etc.) over time. For example, the monitoring system 100 can monitor the drive arm frequency using accelerometers and / or gyroscopes, and / or the change in heading of the end gun 70 can be determined by a magnetometer. The end gun 70 can typically "open" about 15 degrees of rotation from when it is started to when it is stopped. The sensor 102 can sense that the end gun 70 has opened about 3 degrees of rotation, and the controller can determine that this is abnormal operation and that the end gun 70 may need maintenance. In some aspects, the logic for determining abnormal operation can be based on a sliding window of seconds, minutes, hours, days, and / or years. In some aspects, there is a travel end gun 70 without a span called a water winch. The disclosed technology is also applicable to water winches and lateral movement irrigation systems. In some aspects, the movable end gun 70 can be set on a water winch. In some examples, the water winch moves on tires, and in other examples, the end gun 70 is moved by a drive arm or a gear rotation powered by water flow. In an example, the water winch can be moved by another vehicle (such as a tractor or truck). In another example, the water winch can be pulled along the path by a flexible water pipe through a reel. In yet another example, the end gun 70 can be directly mounted on a truck to reduce dust in a mine, and / or to apply wastewater to a field. In another example, the end gun 70 may not be mounted on a pivot, but on a boom, and / or on the last conventional drive unit in a pivot irrigation system.

[0081] Monitoring output parameters, such as timing, flow and / or pressure of the end gun 70, also helps to infer the health of the air compressor. In some aspects, abnormal operation can be further determined by water pressure and / or volume from the end gun 70.

[0082] For example, if a user (e.g., a farmer) applies too much pressure to the end gun 70, water and fertilizer may splash onto the crops, causing a dry ring. The pressure sensor may sense that the end gun pressure has dropped from a normal 71 psi to approximately 40 psi. The end gun prediction model 502 may predict system operating anomalies based on pressure measurements over a period of time. The pressure may be high initially and then drop by approximately 10 psi over the next hour. The farmer may have been operating at too high a pressure because the booster pump is frequently stopped and restarted. The restarting of the pump is very detrimental to the health of the irrigation system 106 because the pump may wear out electrical components before their rated life.

[0083] Electrical Instruments:

[0084] The system can also monitor contactors, commutator rings, motor windings, electrical connections and / or wiring faults. Monitoring electrical transients or power indicators such as THD, power factor, current balance can help infer the health of the electrical system.

[0085] Monitoring the temperature of the components listed above can also help infer electrical system health.

[0086] refer to Fig.11A , Fig. 11B and Figure 12A-12C , the removable end gun 70 supports an electronics housing 1110, which supports at least one sensor 1120, including an accelerometer, gyroscope, microphone, pressure sensor, flow sensor and / or magnetometer, which can be electrically connected to each other, a power source or battery 1130, a circuit 1140 (e.g., a controller), and / or a solar panel 1150. In some aspects, the sensor 1120 can be mounted above, below, and / or to the side of the end gun 70. In some aspects, the sensor 1120 can include a water quality sensor that measures, for example, iron, calcium, salt, and / or organic matter.

[0087] In some aspects, the magnetometer can determine the heading and / or typical travel of the end gun 70 (see Fig.15 and 16 ). For example, a typical range of travel for the end gun 70 may be from about 100 degrees to about 150 degrees of rotation. If the drive arm return spring 1210 changes due to a poor setup, or due to a branch pulling on it, the heading accuracy may be at least about 10 degrees. In other cases, the end gun 70 never changes direction, or may travel beyond 100 to 150 degrees.

[0088] The movable end gun 70 may also support an encoder assembly 1160 having an encoder 1162 and an encoder disk 1164 coupled to the electronics housing 1110. A pressure sensor 1170 is also coupled to the electronics housing 1110 to measure the pressure passing through the end gun 70 ( Fig.15 ) fluid flow pressure. The pressure can indicate the amount of water dispensed. In addition, a reed switch 1180 or other magnetic switch can be coupled to the movable end gun 70 and disposed on a support on the pivot 20 ( Figure 1 ) near the magnet 1190 on the ). It is understood that any disclosed electronic component can be electrically coupled to the circuit 140 (see Fig.13A and 13B). Notably, one or more of the accelerometer, gyroscope, magnetometer, encoder assembly, and / or any other suitable sensor is configured to generate an electrical signal indicating the movement and / or positioning (e.g., acceleration, velocity, distance, position, etc.) of the movable end gun 70 relative to the pivot 20 over time (seconds, minutes, hours, days, years, etc.). The controller 200 is configured to receive the electrical signal and determine whether the movable end gun requires maintenance based on the electrical signal. The controller 200 may send a signal and / or an alert indicating the health of the end gun and / or whether maintenance is required based on predetermined data or thresholds, which may be part of a database, program, and / or stored in a memory (e.g., supported on a circuit, in the cloud, on a network, on a server, etc.).

[0089] When mechanical problems occur at the end gun, the angular velocity may decrease. In addition, the ratio of forward time to backward time may become less balanced, with the time spent forward becoming much longer than the return speed.

[0090] Fig. 12A and Fig. 12B is to use Fig.11A Example signals generated by the predictive maintenance system during a single pass of the end gun from left to right. In some aspects, the end gun prediction model 502 can use ratios of factors such as total pass cycle (Tc), forward angular velocity (T1), reverse angular velocity (T2), forward revolutions (n), reverse revolutions (m), forward angular velocity, and / or reverse angular velocity to indicate the reduced health of the end gun. For example, a fully healthy end gun has a ratio of forward angular velocity to rearward angular velocity of 1. As the health of the end gun decreases, this ratio may begin to deviate from 1. In another example, during forward or rearward motion, the slope of the gyroscope signal over time can be proportional to the angular acceleration. This slope can be used by the end gun prediction model 502 to predict abnormal operation of the end gun. In some aspects, the angular velocity may decrease when there is a mechanical problem. In addition, the ratio of time forward and time backward may become less balanced, and the time spent forward will be much longer than the return speed.

[0091] refer to Fig.13A , Fig. 13B and Fig.14 , the disclosed predictive maintenance system may be in the form of an intelligent end gun for predictive maintenance of the end gun, and may operate using any suitable number or type of analytical and / or logical methods (such as control charts, machine learning ("ML") anomaly detection, parameter limit alarms, etc.). For example, the predictive maintenance system may predict abnormal behavior using a signal that fails to meet a given threshold associated with the free movement of the end gun 70, such as the peak rotation speed during the impact of the drive arm, or the time taken to complete a left-right-left cycle.

[0092] In various aspects, geolocation reports can be used as inputs to the ML model 300. For example, GPS can be used to determine wet and dry areas and train as a "digital twin" of the irrigation system as it moves through the field. The height of the end gun 70 (relative to the pivot) also helps predict expected pressure. Pressure signal analysis can be used as input to the ML model 300.

[0093] Fig.15 A flow chart of a testing system of the predictive maintenance system of the present disclosure is shown.

[0094] In some aspects, the disclosed predictive maintenance system can be a stand-alone system that can be selectively attached to or retrofitted to the end gun 70 , or in some aspects, the predictive maintenance system can be built directly into the end gun 70 .

[0095] Fig.17 A logic diagram of the disclosed technology is shown. The predictive maintenance system can look at various motion acceptance criteria (such as forward / backward angular velocity, ratio of forward to backward motion, angular range, time to trigger the detection rod, acceleration in the x / y / z / forward / backward directions and / or forward and backward heading changes). These movements are proportional to the water pressure. In some aspects, the slope of the accelerometer and / or gyroscope signal over time, and / or the waveform of the gyroscope and / or accelerometer over time can also be used to determine abnormal operation of the end gun.

[0096] In addition, the disclosed structure may include any suitable mechanical, electrical and / or chemical components for operating the disclosed pivot predictive maintenance system or components thereof. For example, such electrical components may include, for example, any suitable electrical and / or electromechanical and / or electrochemical circuits, which may include or be coupled to one or more printed circuit boards. As used herein, the term "controller" includes "processor," "digital processing device," and similar terms, and is used to refer to a microprocessor or a central processing unit (CPU). A CPU is an electronic circuit within a computer that executes the instructions of a computer program by performing basic arithmetic, logic, control, and input / output (I / O) operations specified by the instructions, and includes, by way of non-limiting example, a server computer. In some aspects, the controller includes an operating system configured to execute executable instructions. Those skilled in the art will recognize that, by way of non-limiting example, suitable server operating systems include: FreeBSD, OpenBSD, Linux, Mac OS X Windows and In some ways, the operating system is provided by cloud computing.

[0097] In some aspects, the term "controller" may be used to refer to devices that control the transfer of data from a computer or computing device to a peripheral or separate device, or vice versa, and / or mechanical and / or electromechanical devices (e.g., levers, knobs, etc.) that mechanically operate and / or actuate a peripheral or separate device.

[0098] In some aspects, the controller includes a storage device and / or a memory device. The storage device and / or the memory device is one or more physical devices for temporarily or permanently storing data or programs. In some aspects, the controller includes volatile memory and requires power to maintain the stored information. In some aspects, the controller includes non-volatile memory and retains the stored information when it is not powered on. In some aspects, the non-volatile memory includes flash memory. In some aspects, the non-volatile memory includes dynamic random access memory (DRAM). In some aspects, the non-volatile memory includes ferroelectric random access memory (FRAM). In some aspects, the non-volatile memory includes phase change random access memory (PRAM). In some aspects, the controller is a storage device, including but not limited to CD-ROM, DVD, flash memory device, disk drive, tape drive, optical drive and cloud computing-based storage device. In various aspects, the storage device and / or the memory device is a combination of devices such as those disclosed herein.

[0099] In some aspects, the controller includes a display that sends visual information to the user. In many aspects, the display is a cathode ray tube (CRT). In various aspects, the display is a liquid crystal display (LCD). In some aspects, the display is a thin film transistor liquid crystal display (TFT-LCD). In some aspects, the display is an organic light emitting diode (OLED) display. In some aspects, the organic light emitting diode display is a passive matrix organic light emitting diode (PMOLED) or an active matrix organic light emitting diode (AMOLED) display. In some aspects, the display is a plasma display. In some aspects, the display is a video projector. In many aspects, the display is interactive (e.g., with a touch screen or sensor, such as a camera, a 3D sensor, a lidar, a radar, etc.), and user interactions / gestures / responses can be detected. In some aspects, the display is a combination of devices such as those disclosed herein.

[0100] The controller may include or be coupled to a server and / or a network. As used herein, the term "server" includes "computer server," "central server," "master server," and similar terms to indicate a computer or device on a network that manages a system, its components, and / or its resources. As used herein, the term "network" may include any network technology (including, for example, cellular data networks, wired networks, fiber optic networks, satellite networks, and / or IEEE 802.11a / b / g / n / ac wireless networks, etc.).

[0101] In many aspects, the controller can be coupled to a mesh network. As used herein, a "mesh network" is a network topology in which each node relays data for the network. All mesh nodes collaborate in the data distribution of the network. It can be applied to both wired and wireless networks. A wireless mesh network can be considered a "wireless ad hoc" network. Therefore, a wireless mesh network is closely related to a mobile ad hoc network (MANET). Although MANET is not limited to a specific mesh network topology, a wireless ad hoc network or MANET can adopt any form of network topology. A mesh network can use flooding or routing techniques to relay messages. With routing, a message jumps from one node to another along a path until it reaches its destination. To ensure that all paths are available, the network must allow continuous connectivity and must use self-healing algorithms such as shortest path bridging to self-reconfigure around disconnected paths. Self-healing allows routing-based networks to operate when nodes fail or connections become unreliable. Therefore, the network is usually very reliable because there are usually multiple paths between the source and destination in the network. This concept also applies to wired networks and software interactions. A mesh network in which all nodes are connected to each other is a fully connected network.

[0102] In some aspects, the controller may include one or more modules. As used herein, the term "module" and similar terms are used to refer to a self-contained hardware component of a central server, which in turn includes a software module. In software, a module is a part of a program. A program consists of one or more independently developed modules that can only be combined after the program is linked. A single module may contain one or several routines, or program segments that perform specific tasks.

[0103] As used herein, a controller includes a software module for managing various aspects and functions of the disclosed system or components thereof.

[0104] The disclosed structure may also utilize one or more controllers to receive various information and convert the received information to generate output. The controller may include any type of computing device, computing circuit, or any type of processor or processing circuit capable of executing a series of instructions stored in a memory. The controller may include multiple processors and / or multi-core central processing units (CPUs), and may include any type of processor (such as a microprocessor, a digital signal processor, a microcontroller, a programmable logic device (PLD), a field programmable gate array (FPGA), etc.). The controller may also include a memory storing data and / or instructions, which, when executed by one or more processors, causes one or more processors to execute one or more methods and / or algorithms.

[0105] Any method, program, algorithm or code described herein can be converted into a programming language or computer program, or expressed in a programming language or computer program. The terms "programming language" and "computer program" used herein each include any language for specifying instructions to a computer, and include (but are not limited to) the following languages ​​and their derivatives: assembly language, Basic language, batch file, BCPL, C, C +, C ++, Delphi, Fortran, Java, JavaScript, machine code, operating system command language, Pascal, Perl, PL1, scripting language, Visual Basic, the metalanguage of the program itself, and all first generation, second generation, third generation, fourth generation, fifth generation or further computer languages. Also included are databases and other data modes, and any other metalanguage. There is no difference between an interpreted language, a compiled language, or a language that is compiled and interpreted. There is no difference between the compiled version and the source code version of the program. Therefore, a reference to a program is a reference to any and all of these states, wherein a programming language can exist in more than one state (e.g., source code, compiled, object, or link). A reference to a program can include actual instructions and / or the intent of these instructions.

[0106] Machine learning (“ML”) models may be most effective for complex faults. However, basic logic can be used for simpler fault modes. Possible signals of abnormal operation may come from an increase in the energy required to move the irrigation system, a change in system speed, or a change in the order in which the towers move, end gun rotation frequency, or power quality indicators (e.g., phase balance, inrush current, power factor, THD). Since these vary with complex inference spaces, ML can help predict abnormal operation and simplify input from users and subject matter experts by giving simple labeling methods.

[0107] In some aspects, abnormal operation can be predicted by generating a data structure based on the received first set of sensor signals, the data structure being formatted to be processed by one or more layers of a machine learning model. The data structure may have one or more fields of structured data. Abnormal operation can also be predicted by processing data including a data structure by each of one or more layers of a machine learning model, the machine learning model having been trained to predict the likelihood that a particular device may require maintenance; and generating an output data structure by an output layer of the machine learning model. The output data structure may include one or more fields of structured data, the fields of which indicate the likelihood that a particular device component may require maintenance. Abnormal operation requirements can be further predicted by processing the output data structure to determine whether the data organized by one or more fields of the output data structure meets a predetermined threshold, wherein the output data structure includes one or more fields of structured data, the fields of which indicate the likelihood that a particular device component may require maintenance; and generating a prediction based on the output data of the machine learning model. The prediction includes abnormal operation. Training may include supervised learning.

[0108] The machine learning model can be trained based on observing where the end gun 70 opens, the speed at which the end gun 70 completes the left-right-left cycle, the peak gyroscope speed, the GPS coordinates at which the end gun 70 opens, the pressure at a given GPS location, and using it as a "digital twin" to set a baseline operation to compare with when in use. In some aspects, pressure transient data when the end gun 70 opens and closes can be used as input to the machine learning model for training. Pressure transient data can be used to identify valve operation problems that may cause the valve to be stuck in the open or closed position. In some aspects, the number of irrigated acres of a field can be automatically mapped to replace or supplement the current "marking" practice, through which irrigation team members carry laser rangefinders to drive around the field and place markers to create a field map that can be used to plant and manage the field. Looking at the pressure at the end of the pivot 20 and the end gun 70, the machine learning model can identify / predict potential problems in the water supply, well, well motor, span, VFD, filter, booster pump and / or other components of the pivot. Pressure transient measurements can be sensed using relatively high time resolution (<100 milliseconds). In some aspects, the user can configure the open and / or closed zones of the end gun 70. In some aspects, the end gun motion parameters and the pressure transients of the end gun valve pressure and / or the angle arm sequencing pressure can be used as inputs to the machine learning model. This reference observation can be used to implement position and / or well pressure based analysis to improve the sensitivity and accuracy of the system.

[0109] In some aspects, the controller 200 can monitor the valve 902 ( Fig. 9) receives the generated electrical signal. Valve 902 is configured to provide irrigation water. Sensor 102 can sense, for example, but not limited to, pressure transient data. Sensor 102 can sense pressure transient data that changes over time, and / or generate a synthetic waveform that changes over time. Controller 200 can determine whether valve 902 or one or more components thereof requires maintenance based on the electrical signal, and determine when valve 902 requires maintenance based on the electrical signal (e.g., a valve operation problem that may cause the valve to be stuck in an open or closed position). This determination can be performed by a machine learning model and / or a classical algorithm. Controller 200 can provide an alert to a user that valve 902 requires maintenance.

[0110] Although an irrigation system is used as an example, the disclosed systems and methods may be advantageously used in other environments, such as, but not limited to, dust management in mines and / or irrigation of turf on covered sports stadiums.

[0111] In one aspect of the invention, the disclosed algorithm can be trained using supervised learning. Supervised learning is a machine learning task of learning a function that maps an input to an output based on example input-output pairs. The ML model infers a function from labeled training data consisting of a set of training samples. In supervised learning, each example is a pair consisting of an input object (usually a vector) and a desired output value (also called a supervisory signal). The supervised learning algorithm analyzes the training data and produces an inferred function that can be used to map new examples. In various embodiments, the algorithm can correctly determine the class labels of unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way.

[0112] In various embodiments, a neural network may be trained using training data, which may include, for example, different soil conditions or different component characteristics (e.g., current, voltage, pressure, load, etc.). The algorithm may analyze the training data and generate an inference function that may allow the algorithm to identify component failures or health changes based on generalizations developed by the algorithm from the training data. In various embodiments, training may include at least one of supervised training, unsupervised training, and / or reinforcement learning.

[0113] In some aspects, the user can initiate a training phase while watching the operation to simplify the setup of each unique end gun and pivot combination, as pressures and flows may vary. When the end gun is deemed to be operating properly, the user can open a training window that will then be used to calibrate or train the analytics for future anomaly detection. For example, Linux(R) that can run Python(R) scripts can be used to implement predictions. In some aspects, the analytics can also be performed in the sensor using a platform such as Tensor Flow(R) lite.

[0114] In various embodiments, the neural network may include, for example, a three-layer temporal convolutional network with residual connections, wherein each layer may include three parallel convolutions, wherein the number of kernels and dilations increases from bottom to top, and wherein the number of convolution filters increases from bottom to top. It is contemplated that a greater or lesser number of layers may be used. It is also contemplated that a greater or lesser number of kernels and dilations may be used.

[0115] In some aspects, the disclosed monitoring system can be a stand-alone system that can be selectively coupled or retrofitted to an end gun, or in certain aspects, the monitoring system 100 can be built directly into the end gun.

[0116] like Figure 19-21 As shown, a condition based monitoring (CBM) system is also provided in the form of an end gun testing system for testing the end gun to determine the health of the end gun.

[0117] The system generally includes a first cloud server (e.g., Xintian Farm Cloud), which includes an interface for the system, a device cloud (e.g., Particle Cloud) configured for communication between connected devices and the system, and a firmware server configured to push firmware updates to components of the system. The system device may include a cellular-enabled microcontroller (e.g., Particle Boron) and a CBM module. The cellular-enabled microcontroller includes a cellular receiver / transmitter, a wireless receiver / transmitter (e.g., Bluetooth and / or WIFI), a power management function, a firmware update function, a watchdog function, a power management integrated circuit (PMIC), a power-on self-test (POST) function, a universal asynchronous receiver / transmitter (UART), and a general purpose IO (GPIO). The cellular-enabled microcontroller communicates with a state-based monitor module (CBM module), which is configured to process signals from sensors. For example, the CBM module can sample sensor signals at a rate of 1125KHz. When the CBM module determines that one or more operations are completed, the CBM module notifies the system through the cellular-enabled microcontroller.

[0118] refer to Fig. 20, shows a high-level block diagram of the CBM module. The functions performed by the CBM module include signal processing, sensor calibration, power management, end gun operation report, end gun health alarm, end gun characterization, watchdog, boot loader, and state machine. The CBM module typically includes a microcontroller (e.g., an STM32 microcontroller), a regulator, one or more UARTs, analog and / or digital inputs and outputs, a programming header (e.g., SWD and / or JTAG), a status LED (e.g., status LED blue, error LED red), flash memory, a collision sensor, and an inertial measurement unit (IMU). The application firmware and boot loader firmware run on the microcontroller. The CBM module can be powered by an external power supply and / or a battery. An IMU is an electronic device that uses a combination of accelerometers, gyroscopes, and / or magnetometers to measure and report the specific force, angular velocity, and sometimes the orientation of an object.

[0119] Signal processing functions include, for example, detecting when the end gun is activated and / or deactivated, determining the number of degrees (forward and reverse degrees) that the end gun has traveled based on an onboard compass, detecting average peak forward and / or reverse angular velocity based on an onboard gyroscope, determining average forward and reverse times, determining forward and reverse time ratios, determining when to trigger the reverse lever of the end gun (e.g., to notify the system if the unit is hung and taking too long to reverse direction), and how often the arm is driven forward and / or reverse based on an accelerometer and / or gyroscope.

[0120] In some aspects, the triangulated cellular location of the CBM module can be used to determine the end gun geographic location, speed, position, minimum and maximum observed locations, and other relevant information. Cellular location data comes from a variety of sources, including cell phone towers, global positioning system (GPS) signals, and Bluetooth beacons. For example, the cellular location of the CBM module can be determined using cell site location information because cellular devices connect their users to telecommunications and Internet networks through cellular towers with known locations.

[0121] The CBM module can generate an operation report based on the processed sensor signals and can upload the report to the system through the cellular-enabled microcontroller. The operation report can include, for example, the total angle of travel, the number of passes, the average pass angle of travel, and / or the average drive arm period.

[0122] refer to Fig.21 , shows a schematic diagram of firmware. The firmware may include, for example, peripheral device drivers (eg, SPI, I2C, UART, and / or QUADSPI), device drivers, and applications.

[0123] refer to Fig. 22, shows a state machine of a CBM system. A state machine is a behavioral model that includes a finite number of states. Based on the current state and a given input, the state machine performs state transitions. The state machine may include at least the following states: startup (e.g., power on), boot loading, initialization, application recovery, idle, monitoring, sensor calibration, end gun characterization, fault, hardware test, monitoring, and / or sleep.

[0124] When the CBM module is initially powered on, the state machine starts in the Startup state. Next, the CBM module enters the Boot Loading state. In the Boot Loading state, the bootloader firmware loads the application firmware into the working memory. The bootloader firmware may include the ability to update the firmware, determine whether the application is normal (e.g., a corrupted and / or erroneous application), or load the application firmware. The bootloader firmware may determine whether the application firmware is compatible with the hardware.

[0125] When in the bootloading state, if the CBM module receives a predetermined command (e.g., "0xAAFFAAFF"), the CBM module may enter the flash state (e.g., firmware update mode). In this state, the CBM module may receive a firmware update and then reset after updating the application firmware.

[0126] If the application firmware is running normally (eg, there is no corrupted and / or erroneous application) and no flash command is received, the application firmware is loaded and the initialization state is entered. In the initialization state, the CBM module sets up the sensors and communicates with the memory.

[0127] If initialization is performed correctly, the Idle state begins. In the Idle state, typically the CBM module reads sensor data and processes sensor data to generate a run report. While in the Idle state, the CBM module may poll / interrogate the IMU to get the latest heading and / or temperature from the device. In the Idle state, for example, if the gyroscope activity exceeds approximately 10 degrees per second for approximately one minute, the CBM module enters the Monitor state, in which various sensors are monitored.

[0128] When in the monitoring state, for example, if the gyroscope (e.g., the z-axis gyroscope) is less than about 5 degrees / second for about one minute, the CBM module exits the monitoring state and re-enters the idle state. When transitioning to the monitoring state, the CBM module will issue an end end gun start event. Once exiting the monitoring state, the CBM module will issue an end end gun stop event. When exiting the monitoring state, the CBM module can send an operation report to the first cloud server. In the monitoring state, the CBM module can determine based on the sensor that one or more end guns have failed, and can report the failure to the first cloud server.

[0129] The CBM module may include a command line interface (CLI) that enables a user computing device (e.g., a mobile device, tablet, desktop computer, and / or laptop) connected to the CBM module via a UART (e.g., via RS485 and / or Bluetooth) to send commands to the CBM module to enter various states from an idle state. For example, the CLI command "CAL" causes the CBM module to enter a sensor calibration state. In the sensor calibration state, the system may allow calibration of sensors and sensor data. In addition, if a TBS sensor fault is detected during the monitoring state, the CBM module may enter a self-recovery channel and re-enter an idle state. The fault may be based on the total degree of end gun travel, the number of passes, the average degree of travel, the average drive arm period, the average peak gyro output per drive arm impact, the average peak accelerometer amplitude per drive arm impact, the average forward and reverse time ratio, the total time of the end gun open state, the number of faults reported during operation, the triangulation unit position, the minimum heading, and / or the maximum heading. For example, the CLI command "HWtest" causes the CBM module to enter a hardware test state. In the Hardware Test state, the CBM module tests the connected hardware. For example, the CLI command "Press enter twice" causes the CBM module to enter the Monitor state. For example, the CLI command "CHAR" causes the CBM module to enter the End Gun Characterization state. In the End Gun Characterization state, the CBM module is able to characterize and score the characterization of the connected hardware. For example, the CLI command "SLP" causes the CBM module to enter the Sleep state.

[0130] Fig.23is a schematic diagram of end gun areas (e.g., four quadrants) for determining the location of irrigation failures. In some aspects, one or more end guns can be located in four quadrants of a field that also uses a center pivot irrigation system. Although four quadrants are used as an example, any number of end gun areas are considered to be within the scope of the present disclosure. End guns can be used to irrigate corners (e.g., quadrants) of a field that are missed by a center pivot irrigation system. A center pivot irrigation system typically takes two full days to go around a field. For example, if the equipment fails and the user does not notice that a corner is not irrigated on a hot summer day, the crops in that corner may die. Therefore, the method and system for real-time missed corner detection of the present disclosure helps avoid these situations by detecting corners (e.g., quadrants) that are not irrigated and reporting them to the user. In addition to not being irrigated, sometimes the end gun 70 insists on being "on" when it should be "off", which can be dangerous to families and motorists in the area. In some aspects, for example, each quadrant can include two end guns equipped with a CBM module. The CBM module may include a compass (e.g., a magnetometer) configured to determine the minimum and maximum observed headings of two end guns (e.g., a first end gun and a second end gun). For example, if the first end gun has a minimum observed heading of the southwest and the second end gun has a maximum observed heading of the northeast, the controller 200 may determine that the first end gun and the second end gun are located in quadrant 4. The first end gun of a quadrant may have a relationship with the first end gun of the next or previous quadrant, wherein they are offset in direction by approximately 90 degrees. For example, the first end gun of quadrant 4 may have a minimum observable position of the southwest, and the first end gun of quadrant 1 may have a minimum observable position of the northwest. In some aspects, the CBM module may include a GPS, and / or use cellular location triangulation to set a geo-fence to determine in which quadrant the end gun is located. For example, based on the GPS coordinates, the controller 200 may determine that the end gun is in quadrant 2. The method may monitor a trigger "on" event to determine whether the end gun has been triggered to irrigate the field. The controller 200 may determine that the determined quadrant is not irrigated based on the quadrant and whether a triggering event is detected. In some aspects, the user may receive a report or indication (e.g., a text message, email, etc.) that the determined quadrant is not being irrigated. For example, the controller 200 may detect a trigger event for an end gun. The controller 200 may also detect that this particular end gun is in Quadrant 1. The controller 200 will determine that Quadrant 1 is being irrigated. Next, the controller 200 may detect that the next end gun has no trigger event, and based on the GPS location of the end gun, it is in Quadrant 2. The controller 200 will determine that Quadrant 2 may not have been irrigated, and will generate a report to alert the user so that the user can check the end gun for a possible device failure. For example, in the end gun area, the end gun 70 may be "turned on" in a random location around 360 degrees, not operated in another corner, and / or in some cases, always "turned on".

[0131] It is contemplated that a movable end gun may be operably connected to the pivot, such as as part of the system, but separate from the pivot. For example, in some less capital-intensive farms, the pivot may not have an end gun, but rather the end gun may be placed in a fixed position at a corner of a field. The end gun may include a fixed gun sprayer set in an appropriate position on a tripod or quadripod. Although an end gun is shown, other types of nozzles are also contemplated.

[0132] refer to Fig.24 , showing Figure 1 Figure 2 shows an example gyro signal output of a monitoring system. For example, if an end gun requires maintenance, data from the gyro may provide an indication such as a forward / reverse time ratio that is higher than an end gun that does not require maintenance.

[0133] refer to Fig.25 , showing Figure 1 Graph of example compass signal output of a monitoring system. For example, if the end gun is hard to flip the reverse mechanism, there may be a slope change in the output data from the compass (e.g., a magnetometer).

[0134] refer to Fig.26 , showing Figure 1 Figure 2 is a graph of example accelerometer signal outputs of a monitoring system. For example, if an end gun requires maintenance, data from the accelerometer may provide an indication such as a forward to reverse time ratio that is higher than an end gun that does not require maintenance.

[0135] refer to Figure 27-Figure 32 The end gun 70 may include an end gun monitoring system that includes any number and / or type of sensors (e.g., Figure 1 Sensors 102 are shown, for example, pressure sensors for determining water flow rate and / or motion detection sensors for determining movement (e.g., angular movement) of the end gun 70 relative to the irrigation system. In some aspects, the sensors can include any suitable sensors for monitoring various aspects of the irrigation system / end gun, such as encoders (e.g., angle encoders), pressure sensors, flow meters, etc. or combinations thereof. The angle encoder can be in the form of a position sensor that measures the angular position of a rotating shaft.

[0136] The fertilization system 3000 generally includes a product storage tank 3810 (e.g., a fertilizer tank, Fig.31 ), booster pump system and control box 2900 ( Fig.29 ), the booster pump system includes a booster pump 10 ( Fig.28 ) valve 2800. Product storage tank 3810 ( Fig.31 ) is configured to distribute fertilizer. Although fertilizer is used as an example, pesticides, herbicides, preservatives and / or any suitable product applied with water may be used.

[0137] like Fig.28 As shown, valve 2800 is configured to control the flow rate of water and / or fertilizer to end gun 70.

[0138] refer to Fig.29 The control box 2900 of the fertilization system 3000 is configured to communicate with the booster pump 10 and / or the valve 2800 of the fertilization system 3000 to control the product storage tank 3810 ( Fig.31 ) in the fertilizer. The booster pump may include a variable speed drive to control the flow rate of the product. The control box 2900 may include a variable frequency drive and a programmable logic controller (PLC) 3030 (e.g., controller 200) for a pump that is configured to regulate the fertilization rate. Although fertilizer is given as an example, the product may include any substance that can be injected into an irrigation system that may require a specified uniformity of volume per acre. These substances may include, for example, organic nutrients, chemical nutrients, pesticides, fungicides, herbicides, and / or fumigants.

[0139] refer to Fig.30 , and product storage tank 3810( Fig.31 )'s PLC 3030 enables wired and / or wireless communication between components of the irrigation system and / or fertilization system 3000.

[0140] refer to Fig.31 , product storage tank 3810 and pump 10 (e.g., compressor or booster pump) are connected to Figure 1 The irrigation system 106. The product storage tank 3810 is coupled to Figure 1 The control valve 2800 is configured to control the flow rate of fertilizer from the product tank 3810 to the movable end gun 70, and the product tank 3810 can be coupled to the irrigation system 106. Although a product tank is discussed, the product source can include any form of product storage or preservation, transportation or other source.

[0141] Fig.32 Shows the integration Figure 29-Figure 31 Fertilization system and Figure 1 The control panel can be used to input and / or control the parameters of the fertilization and / or irrigation system.

[0142] In some aspects, the controller 200 can receive an electrical signal generated from a sensor 102 configured to be coupled to a movable end gun of the irrigation system 106. The sensor 102 is configured to generate an electrical signal indicating the movement and / or positioning of the movable end gun 70 relative to a portion of the irrigation system 106 over time. The controller 200 can determine a rate of application of the product over a predetermined area based on the electrical signal. The controller 200 can actuate a control valve 2800 and / or change the speed of a variable speed pump based on the determined rate of application to control the flow rate of the product (e.g., fertilizer). In some aspects, the travel speed and / or flow rate of the irrigation system 106 (or a portion of the irrigation system) can be used to determine the rate of application. For example, the monitoring system 100 can include a sensor 102 and a fluid pressure sensor 1170, the sensor 102 is configured to be coupled to one or more nozzles and is configured to generate a first electrical signal indicating the travel speed or direction of the irrigation system 106 over time, and the fluid pressure sensor 1170 is configured to generate a second electrical signal indicating the flow rate. In some aspects, the sensor 102, 1170 can be coupled to the end of the pivot 20, which can include coupling to a nozzle (e.g., end gun 70). The end of the pivot 20 is typically located near the last nozzle. Near is defined as at least about 75% of the distance from the water source to the irrigation system 106. For example, the end of the pivot 20 can be located at or beyond the last nozzle.

[0143] In some aspects, the control valve 2800 can also be adjusted based on product characteristics. Figure 5 ) and / or an analysis engine (e.g., a machine learning model and / or classical analysis) can be configured to perform the determination. The controller 200 can determine the uniformity of the product applied over a predetermined area. The controller 200 can actuate a valve and / or change the speed of a variable speed pump based on the determined uniformity. For example, the processor can control the nutrients applied per acre. Nutrient units per acre are provided as an example, however, other units are also contemplated.

[0144] In some aspects, the irrigation system 106 and the fertilization system 3000 can be connected directly or indirectly via a physical and / or wireless connection. In some aspects, the controller 200 can use dealer specifications, manufacturer specifications, and / or farm calibration reports for each pivot 20. The training data set collected from the end gun monitor can record, store, and / or monitor the correct operation of the pivot and can be used to determine the flow rate and / or application rate of fertilizer.

[0145] The disclosed technology provides the benefit of reporting actual travel speed and / or flow rate (inferred or directly measured) back to the product tank 3810 (e.g., a fertilizer tank), which can compensate the distribution rate to maximize uniformity of nutrients per acre.

[0146] It will be appreciated that fixation of any component of the disclosed device may be achieved using known fixation techniques such as welding, crimping, gluing, fastening, and the like.

[0147] Those skilled in the art will appreciate that the structures and methods specifically described herein and shown in the accompanying drawings are non-restrictive exemplary aspects, and the specification, disclosure, and drawings should only be interpreted as examples of specific aspects. Therefore, it should be understood that the present disclosure is not limited to the precise aspects described, and that those skilled in the art can implement various other changes and modifications without departing from the scope or spirit of the present disclosure. In addition, it is foreseeable that, without departing from the scope of the present disclosure, the elements and features shown or described in conjunction with an exemplary aspect can be combined with the elements and features of another exemplary aspect, and such modifications and variations are also intended to be included within the scope of the present disclosure. In fact, any combination of any disclosed elements and features is within the scope of the present disclosure. Therefore, the subject matter of the present disclosure is not limited by the content that has been specifically shown and described.

Claims

1. A monitoring system for an irrigation system, the irrigation system operably coupled to a water source, the irrigation system comprising at least one nozzle and a product source, the product source supporting a product for mixing with water from the water source to form an irrigation fluid, the monitoring system comprising: a sensor configured to generate a first electrical signal indicative of a speed of travel of at least a portion of the irrigation system or a direction of travel of at least a portion of the irrigation system; a fluid pressure sensor configured to generate a second electrical signal indicative of a flow rate of irrigation fluid through the at least one nozzle; at least one of a variable speed pump or a valve operably coupled to a product source to enable product to be dispensed from the product source; processor; as well as A memory including instructions stored thereon that, when executed by a processor, cause the monitoring system to: receiving first and second generated electrical signals; determining a rate of application of the irrigation fluid over a predetermined irrigation area based on the first and second electrical signals; as well as The flow rate of the irrigation fluid through the at least one nozzle is adjusted by at least one of the following: actuate a valve; or The speed of the variable speed pump is varied based on the determined applied rate.

2. The monitoring system according to claim 1, wherein: The product includes a nutrient such that the monitoring system is configured to determine an amount of the nutrient to be applied to a predetermined irrigation area.

3. The monitoring system according to claim 1, wherein: The product source is configured for product storage, product preservation, or product transportation.

4. The monitoring system according to claim 1, wherein: The fluid pressure sensor is coupled to an end of a span of a pivot of the irrigation system.

5. The monitoring system according to claim 4, wherein: The fluid pressure sensor is disposed near at least one nozzle.

6. The monitoring system according to claim 5, wherein: The at least one nozzle is supported on a movable end gun.

7. The monitoring system according to claim 6, wherein: At least a portion of the irrigation system is a movable lance, such that the first electrical signal indicates a speed of travel of the movable lance relative to a span of a pivot of the irrigation system or a direction of travel of the movable lance relative to the span.

8. The monitoring system according to claim 1, wherein: When the instructions are executed, the monitoring system is further caused to: determining an angular velocity of the at least one nozzle and a time taken for the at least one nozzle to advance and / or retreat based on the first electrical signal; determining that the at least one nozzle is pivoted beyond a predetermined degree without the at least one nozzle dispensing irrigation fluid; as well as Based on the determination, an indication is provided to the user that locations within the predetermined irrigation area are not fertilized with the product.

9. The monitoring system according to claim 1, wherein: The nozzle is movably mounted on a pivot of the irrigation system.

10. The monitoring system of claim 1, further comprising an analysis engine configured to perform the determination, wherein: The analysis engine includes a machine learning model, wherein the machine learning model is based on a deep learning network, a classical machine learning model, or a combination thereof.

11. A monitoring system for an irrigation system, the irrigation system including a movable end gun operably associated with a portion of the irrigation system, the monitoring system comprising: a sensor configured to be coupled to the movable end lance and configured to generate an electrical signal indicative of movement and / or positioning of the movable end lance relative to a portion of the irrigation system over time; a product tank coupled to the irrigation system, the product tank configured to dispense a product; at least one of a variable speed pump or a valve configured to control a flow rate of product from the product storage tank to the movable end gun; processor; as well as a memory including instructions stored thereon that, when executed by a processor, cause the system to: receiving the generated electrical signal; determining a rate at which the product is applied to a predetermined area based on the electrical signal; as well as At least one of actuating a valve or changing a speed of a variable speed pump based on the determined applied rate.

12. The monitoring system according to claim 11, wherein: When the instructions are executed, the monitoring system is further caused to determine the angular velocity of the movable end gun and the time taken for the movable end gun to advance and / or retreat based on the electrical signal.

13. The monitoring system according to claim 12, wherein: The instructions, when executed, further cause the monitoring system to generate a report based on the determination.

14. The monitoring system according to claim 12, wherein: When the instructions are executed, the monitoring system: determining whether the end gun is pivoted beyond a predetermined degree without the end gun being in a triggered state; as well as An indication is provided to a user that the location is not fertilized based on the determination.

15. The monitoring system according to claim 11, wherein: The portion of the irrigation system includes at least one of a lateral drive, a water winch, or a pivot, wherein the movable end gun is movably mounted on the pivot.

16. The monitoring system of claim 11, further comprising an analysis engine configured to perform the determination.

17. The monitoring system according to claim 16, wherein: The instructions, when executed by the processor, further cause the monitoring system to receive data from at least one of a weather station, a field soil moisture sensor, a topographic map, a soil map, a temperature sensor, or a National Oceanic and Atmospheric Administration weather.

18. The monitoring system according to claim 16, wherein: The analysis engine includes a machine learning model, wherein the machine learning model is based on a deep learning network, a classical machine learning model, or a combination thereof.

19. The monitoring system according to claim 11, wherein: The sensor includes at least one of an encoder, a magnetometer, a gyroscope, an accelerometer, a camera, a gesture sensor, a microphone, a laser rangefinder, a reed switch, a magnetic switch, a GPS, or an optical switch.

20. A computer-implemented method for monitoring an irrigation system, the irrigation system operably coupled to a water source, the irrigation system comprising at least one nozzle and a product source, the product source supporting a product for mixing with water from the water source to form an irrigation fluid, the method comprising: receiving a first electrical signal generated by a sensor configured to generate a first electrical signal indicative of a speed of travel of at least a portion of the irrigation system or a direction of travel of at least a portion of the irrigation system; receiving a second electrical signal generated by a fluid pressure sensor configured to generate a second electrical signal indicative of a flow rate of irrigation fluid through the at least one nozzle; determining a rate of application of the irrigation fluid over a predetermined irrigation area based on the first and second electrical signals; as well as The flow rate of the irrigation fluid through the at least one nozzle is adjusted by at least one of the following: actuating a valve operably coupled to a product source to enable product to be dispensed from the product source; or A speed of a variable speed pump operably coupled to a product source is varied based on the determined applied rate to enable product to be dispensed from the product source.

Images