A method, device, storage medium, and electronic equipment for predicting agricultural machinery maintenance.

Abstract

A method, apparatus, storage medium, and electronic device for predicting agricultural machinery maintenance are disclosed. This method mines agricultural machinery status based on a large amount of unlabeled data and predicts agricultural machinery accidents based on the mining results. The method includes establishing a maintenance time prediction model based on semi-supervised learning according to the working environment and maintenance requirements of the agricultural machinery to be predicted; acquiring the factory information, on-board sensor information, maintenance information, and repair information of the agricultural machinery to be predicted; and inputting the acquired information into the maintenance time prediction model to obtain the possible failure rate and time of equipment components of the agricultural machinery to be predicted, thus completing the prediction of maintenance time for different equipment components of the agricultural machinery to be predicted. The invention also provides an agricultural machinery maintenance prediction apparatus and a storage medium and electronic device used to execute the above-mentioned agricultural machinery maintenance prediction method during operation.

Description

Technical Field

[0001] This invention relates to vehicle device technology, and in particular to a method, device, storage medium, and electronic equipment for predicting the maintenance and repair of agricultural machinery. Background Technology

[0002] With the development of science and technology, the agricultural industrial structure is constantly being adjusted, and agricultural production output and efficiency are continuously improving. The promotion and implementation of the concept of agricultural modernization requires advanced agricultural machinery and equipment as backup support to achieve agricultural mechanization. The fundamental starting point of modern agricultural development is to adjust the agricultural structure, improve the quality and efficiency of agricultural production, and increase farmers' income. Developing agricultural mechanization technology and equipment is of paramount importance in modern agricultural development. At present, modern agricultural machinery and equipment are not merely replacing agricultural labor machinery, but are developing towards informatization and intelligence. Improving the ability to prevent and predict agricultural machinery accidents is an effective measure to avoid and reduce accidents. Existing agricultural machinery equipment lacks relevant methods for preventing and predicting agricultural machinery accidents. Often, a large amount of collected agricultural machinery data is unlabeled, and the classification ratio of labeled data varies greatly. Therefore, there is an urgent need for a device and method that can mine agricultural machinery status based on a large amount of unlabeled data and predict agricultural machinery accidents based on the mining results. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to address the above-mentioned deficiencies of the prior art by providing a method, device, storage medium and equipment for predicting agricultural machinery maintenance, so as to solve the problem of agricultural machinery failure caused by failure to maintain equipment and parts within the specified time limit.

[0004] To achieve the above objectives, this invention provides a method for predicting agricultural machinery maintenance, which involves mining agricultural machinery status based on a large amount of unlabeled data and predicting agricultural machinery accidents based on the mining results, including the following steps:

[0005] S100. Based on the working environment and maintenance requirements of the agricultural machinery to be predicted, establish a maintenance time prediction model based on semi-supervised learning.

[0006] S200: Obtain the factory information, on-board sensor information, maintenance information, and upkeep information of the agricultural machinery to be predicted; and

[0007] S300. Input the information obtained in step S200 into the maintenance time prediction model to obtain the possible failure rate and time of the equipment components of the agricultural machinery to be predicted, and complete the prediction of maintenance time for the equipment components of different agricultural machinery to be predicted.

[0008] The above-mentioned method for predicting agricultural machinery maintenance and repair further includes, in step S200:

[0009] S201. Obtain the factory information of agricultural machinery equipment parts, obtain the service life and suitable environmental parameters of each piece of equipment and part from the agricultural machinery equipment parts manufacturer, and enter them into the background database.

[0010] S202. Obtain agricultural machinery status information, including environmental data stored in the on-board sensors of the agricultural machinery to be predicted that affect maintenance time after the machinery leaves the factory, and store this data in the background database and maintenance time prediction model; and

[0011] S203. Obtain agricultural machinery repair information. Obtain agricultural machinery repair information through the agricultural machinery repair and maintenance platform, and enter it into the background database and maintenance time prediction model.

[0012] The above-mentioned method for predicting agricultural machinery maintenance and repair further includes, in step S100:

[0013] S101. Input the maintenance information, repair information and data from the vehicle sensor into a neural network that introduces noise data in multiple intermediate layers, and obtain the first noise output result of the first intermediate layer;

[0014] S102. The neural network is reconstructed using the first noise output result to obtain the second reconstruction output result of at least one second intermediate layer.

[0015] S103. Input the maintenance information, repair information, and vehicle sensor data into the neural network to obtain at least one second output result of a second intermediate layer and a first output result of a first intermediate layer; and

[0016] S104. Using the loss between the second output result and the second reconstructed output result, and the loss between the first output result and the first noise output result, the neural network is trained to obtain the maintenance time prediction model.

[0017] The above-mentioned method for predicting agricultural machinery maintenance and repair further includes, in step S100:

[0018] S105. Input the maintenance information, repair information, and data from the vehicle's sensors into the maintenance time prediction model to obtain the output of the neural network's output layer; and

[0019] S106. The neural network is trained using the loss between the output of the output layer and the labeled result to further improve the maintenance time prediction model.

[0020] The aforementioned methods for predicting agricultural machinery maintenance also include:

[0021] S400 will send maintenance alerts to users via push notifications, based on the predicted maintenance times for agricultural machinery.

[0022] To better achieve the above objectives, the present invention also provides an agricultural machinery maintenance prediction device, which includes a processor and an on-board sensor. The on-board sensor is connected to the processor and the agricultural machinery respectively. The processor uses the above-mentioned agricultural machinery maintenance prediction method to mine the status of agricultural machinery based on a large amount of unlabeled data, and makes agricultural machinery accident prevention prediction based on the mining results.

[0023] The aforementioned agricultural machinery maintenance prediction device includes a processor comprising a system setting module, a status monitoring module, a maintenance information module, a maintenance information module, and a viewing and display module. The maintenance information module stores historical maintenance information of agricultural machinery, and the maintenance information module stores historical maintenance information of agricultural machinery.

[0024] In the aforementioned agricultural machinery maintenance prediction device, the vehicle-mounted sensor is used to record environmental parameters that affect the maintenance time of agricultural machinery, and is connected to the agricultural machinery via a bus to obtain information on key components of the agricultural machinery. The vehicle-mounted sensor includes a data acquisition unit, a central processing unit, and a data network transmission unit. The environmental parameters and key component information of the agricultural machinery acquired by the data acquisition unit are processed by the central processing unit and then transmitted to the processor via the data network transmission unit.

[0025] To better achieve the above objectives, the present invention also provides a storage medium storing a computer program configured to execute the above-described agricultural machinery maintenance prediction method during runtime.

[0026] To better achieve the above objectives, the present invention also provides an electronic device, comprising:

[0027] Processor; and

[0028] Memory for storing the executable instructions of the processor;

[0029] The processor is configured to execute the above-described agricultural machinery maintenance prediction method by executing the executable instructions.

[0030] The technical effects of this invention are as follows:

[0031] This invention utilizes environmental parameters affecting agricultural machinery maintenance time transmitted by vehicle-mounted sensors, factory maintenance and repair information for agricultural machinery components, and user-uploaded agricultural machinery maintenance information. This effectively improves the accuracy of predicting agricultural machinery component failure times. Platform reminders for maintenance and repair can effectively save on maintenance costs and reduce operational risks. It solves the problems of existing technologies that cannot predict maintenance times in real time, thus compromising reliability during agricultural machinery operation; and the difficulty of unifying maintenance and repair information on a single platform for data querying and prediction due to the large number and variety of agricultural machinery models and brands. This avoids the need for separate simulation and prediction platforms for each type of agricultural machinery. It significantly reduces the probability of agricultural machinery components failing to undergo timely maintenance, improving safety during use and saving on simulation platform development costs. Furthermore, addressing the issue of a large amount of unlabeled data and inconsistent classification ratios among labeled data, this invention effectively utilizes a large amount of unlabeled data to train neural networks, improving the utilization rate of this large dataset.

[0032] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the present invention. Attached Figure Description

[0033] Figure 1 This is a flowchart of a maintenance prediction method according to an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram illustrating the working principle of an embodiment of the present invention;

[0035] Figure 3 This is a block diagram of a vehicle-mounted sensor structure according to an embodiment of the present invention;

[0036] Figure 4 The flowchart illustrates the establishment of a maintenance time prediction model according to an embodiment of the present invention.

[0037] Among them, the attached figures are labeled

[0038] 1 processor

[0039] 2 vehicle-mounted sensors

[0040] 21 Data Acquisition Unit

[0041] 22 Central Processing Units

[0042] 23 Data Network Transmission Unit

[0043] 3. Agricultural machinery

[0044] S100-S300 Steps Detailed Implementation

[0045] The structural and working principles of the present invention will be described in detail below with reference to the accompanying drawings:

[0046] See Figure 1 , Figure 1 This is a flowchart of a maintenance prediction method according to an embodiment of the present invention. The agricultural machinery maintenance prediction method of the present invention mines agricultural machinery status based on a large amount of unlabeled data, and predicts agricultural machinery accidents based on the mining results, including the following steps:

[0047] Step S100: Based on the working environment and maintenance requirements of the agricultural machinery 3 to be predicted, establish a maintenance time prediction model based on semi-supervised learning;

[0048] Step S200: Obtain the factory information, on-board sensor information, maintenance information, and upkeep information of the agricultural machinery 3 to be predicted; and

[0049] Step S300: The information obtained in step S200 can be manually uploaded and input into the maintenance time prediction model to obtain the possible failure rate and time of the equipment components of the agricultural machinery 3 to be predicted, and to complete the prediction of the maintenance time of different equipment components of the agricultural machinery 3 to be predicted.

[0050] In the absence of agricultural machinery maintenance information, the prediction result is based on the factory information of the components of Agricultural Machinery 3. When maintenance information of the same Agricultural Machinery 3 components is available, the prediction result is obtained through semi-supervised learning big data predictive analysis. In addition to the maintenance information of the same Agricultural Machinery 3 components, the environmental parameters affecting the maintenance time of agricultural machinery uploaded by vehicle-mounted sensor 2 are also crucial parameters in the big data prediction. After a failure occurs in Agricultural Machinery 3, a comparative analysis result is generated by comparing and analyzing the failure information and the predictive analysis result. The parameters in the failure trend prediction step are adjusted based on the comparative analysis result. Data can be dynamically updated via browser and mini-program access.

[0051] It may also include: step S400, sending the predicted results, such as the maintenance time of agricultural machinery, to the user as a maintenance warning via push notification.

[0052] The maintenance time prediction model is established based on semi-supervised learning and big data prediction analysis. It includes inputting user-uploaded maintenance and repair information, as well as data uploaded by vehicle-mounted sensor 2, into a neural network with multiple intermediate layers containing noise data to obtain the first noise output result of the first intermediate layer; reconstructing the neural network using the first noise output result to obtain the second reconstructed output result of at least one second intermediate layer; inputting user-uploaded maintenance and repair information, as well as data uploaded by vehicle-mounted sensor 2, into the neural network to obtain the second output result of at least one second intermediate layer and the first output result of the first intermediate layer; training the neural network using the loss between the second output result and the second reconstructed output result, and the loss between the first output result and the first noise output result; inputting user-uploaded maintenance and repair information, as well as data uploaded by vehicle-mounted sensor 2, into the neural network to obtain the output result of the output layer of the neural network; and training the neural network using the loss between the output result of the output layer and the labeled result to obtain the predicted maintenance time for agricultural machinery.

[0053] Step S200 further includes:

[0054] Step S201: Obtain the factory information of agricultural machinery equipment parts. Obtain the service life and suitable environmental parameters of each piece of equipment and part from the agricultural machinery equipment parts manufacturer and enter them into the background database.

[0055] Step S202: Obtain agricultural machinery status information. This involves acquiring environmental data stored in the on-board sensor 2 of the agricultural machinery 3 (to be predicted) that affects maintenance time after leaving the factory, through communication with the on-board sensor 2, and storing this data in the background database and maintenance time prediction model; and...

[0056] Step S203: Obtain agricultural machinery repair information. Agricultural machinery repair information can be obtained by users uploading repair information to the agricultural machinery repair and maintenance platform, and then entered into the background database and maintenance time prediction model.

[0057] It should be noted that the above steps are only a recommended order in this embodiment. Based on this invention, the execution order of obtaining agricultural machinery equipment parts manufacturing information, obtaining agricultural machinery status information, and obtaining user-uploaded agricultural machinery maintenance information can be set according to the actual situation.

[0058] See Figure 2 , Figure 2This is a schematic diagram illustrating the working principle of an embodiment of the present invention. The agricultural machinery maintenance prediction device of the present invention includes a processor 1 and an on-board sensor 2. The on-board sensor 2 is connected to the processor 1 and the agricultural machinery 3 respectively. The processor 1 uses the above-described agricultural machinery maintenance prediction method to mine the status of the agricultural machinery 3 based on a large amount of unlabeled data, and performs accident prevention prediction of the agricultural machinery 3 based on the mining results.

[0059] The processor 1 includes a system setting module, a data processing module, a status monitoring module, a maintenance information module, a repair information module, a maintenance information module, a configuration information module, and a viewing and display module. The maintenance information module stores historical maintenance information for agricultural machinery, and the maintenance information module stores historical maintenance information for agricultural machinery. The data processing module processes the acquired factory information of agricultural machinery components, the acquired status information of agricultural machinery, the acquired user-uploaded agricultural machinery maintenance information, and the agricultural machinery maintenance prediction results. The configuration information module records and maintains the maintenance prediction data and provides system design parameters and communication information formats for maintenance prediction analysis. The status monitoring module monitors environmental information uploaded by the onboard sensors 2 that affects agricultural machinery maintenance, so that the processor 1 can understand the status of the agricultural machinery 3. The maintenance information module includes a historical maintenance information module and a manually uploaded agricultural machinery maintenance information module, so that the processor 1 can understand the maintenance history information of the agricultural machinery 3. The manually uploaded agricultural machinery maintenance information is used to improve the agricultural machinery maintenance prediction and increase its accuracy. The maintenance information module includes a historical maintenance information module, an agricultural machinery maintenance prediction module, and a manually uploaded agricultural machinery maintenance information module. The agricultural machinery historical maintenance information module provides maintenance history information for agricultural machinery 3 through the platform. The agricultural machinery maintenance prediction module pushes maintenance reminders to users through the platform. The manual upload agricultural machinery maintenance information module allows users to upload agricultural machinery maintenance information through the platform to improve and update agricultural machinery maintenance predictions, increase the accuracy of agricultural machinery maintenance predictions, and improve the agricultural machinery historical maintenance information module.

[0060] See Figure 3 , Figure 3This is a structural block diagram of a vehicle-mounted sensor 2 according to an embodiment of the present invention. In this embodiment, the vehicle-mounted sensor 2 is used to record environmental parameters affecting the maintenance time of agricultural machinery, and is connected to the agricultural machinery 3 via a bus to obtain information on key components of the agricultural machinery. The vehicle-mounted sensor 2 includes a data acquisition unit 21, a central processing unit 22, and a data network transmission unit 23. The central processing unit 22 is connected to both the data acquisition unit 21 and the data network transmission unit 23. The environmental parameters and key component information of the agricultural machinery acquired by the data acquisition unit 21 are processed by the central processing unit 22 and then transmitted to the processor 1 via the data network transmission unit 23. The key component information of the agricultural machinery includes sensor content that needs to be detected, such as environmental parameters affecting the maintenance time of the agricultural machinery. The processor 1 determines and sends instructions to the vehicle-mounted sensor 2 to perform detection and calculation.

[0061] Specifically, the information uploaded by vehicle-mounted sensor 2 refers to the environmental parameters affecting the maintenance and repair time of agricultural machinery, collected by the vehicle-mounted sensor 2 installed on agricultural machinery 3, and uploaded to processor 1. The agricultural machinery equipment component information refers to the equipment component information of agricultural machinery 3 submitted to processor 1 during platform installation and registration. The agricultural machinery maintenance information refers to the agricultural machinery maintenance information submitted to processor 1. The agricultural machinery repair information refers to the agricultural machinery repair information submitted to processor 1. The agricultural machinery equipment component repair history information refers to all agricultural machinery repair information submitted to processor 1.

[0062] See Figure 4 , Figure 4 A flowchart illustrating the establishment of a maintenance time prediction model according to an embodiment of the present invention. Step S100 of this embodiment further includes:

[0063] Step S101: Input the maintenance information, repair information, and data from the vehicle sensor 2 into a neural network that introduces noise data in multiple intermediate layers, and obtain the first noise output result of the first intermediate layer;

[0064] Step S102: Use the first noise output result to reconstruct the neural network to obtain the second reconstruction output result of at least one second intermediate layer;

[0065] Step S103: Input the maintenance information, repair information, and data from the vehicle sensor 2 into the neural network to obtain at least one second output result of the second intermediate layer and a first output result of the first intermediate layer; and

[0066] Step S104: Using the loss between the second output result and the second reconstructed output result, and the loss between the first output result and the first noise output result, train the neural network to obtain the maintenance time prediction model.

[0067] This may also include:

[0068] Step S105: Input the maintenance information, repair information, and data from the vehicle sensor 2 into the maintenance time prediction model to obtain the output result of the neural network output layer; and

[0069] Step S106: Train the neural network using the loss between the output of the output layer and the labeled result to further improve the maintenance time prediction model.

[0070] In this embodiment, the processor 1 uses the agricultural machinery equipment component information, agricultural machinery maintenance information, agricultural machinery repair information, and environmental information affecting the agricultural machinery maintenance time uploaded by the vehicle-mounted sensor 2 recorded during installation and registration as the input source for agricultural machinery maintenance prediction. The processor 1 inputs the data into a neural network that introduces noise data in several intermediate layers. The several intermediate layers include a first intermediate layer and at least one second intermediate layer. The processor 1 obtains the first noise output result of the first intermediate layer.

[0071] The data includes unlabeled data and labeled user data. Specifically, for the agricultural machinery maintenance system, a large amount of unlabeled data acquired by the vehicle-mounted sensor 2 represents environmental data of agricultural machinery in normal conditions. The labeled data includes data acquired by the vehicle-mounted sensor 2 when the agricultural machinery malfunctions or requires maintenance, as well as maintenance information uploaded by users. The ratio of unlabeled to labeled data can be very large, making it impossible to directly train the neural network. Therefore, a semi-supervised learning method for predicting maintenance time is used to train the neural network based on the above data.

[0072] These data are input into a neural network, where noise data is introduced into several intermediate layers to perturb the feature data obtained by each intermediate layer. Each intermediate layer includes a first intermediate layer and at least one second intermediate layer, with the first intermediate layer being the one that receives the least amount of data from the neural network. The data is then input into the neural network with the noise data introduced into several intermediate layers, and the first noisy output result of the first intermediate layer is obtained.

[0073] The neural network is reconstructed using the first noise output to obtain a second reconstructed output from at least one second intermediate layer. This at least one second intermediate layer can be multiple adjacent second intermediate layers, or multiple second intermediate layers with layer gaps between them. During reconstruction, several second reconstructed outputs from adjacent second intermediate layers can be obtained.

[0074] The user-uploaded maintenance and repair information, along with data uploaded by the vehicle-mounted sensor 2, are input into a neural network to obtain a second output result of at least one second intermediate layer and a first output result of the first intermediate layer. Alternatively, data can be input into a neural network that does not introduce noise to obtain a corresponding second output result of at least one second intermediate layer and a first intermediate result of the first intermediate layer.

[0075] The neural network is trained using the loss between the second output and the second reconstructed output, and the loss between the first output and the first noisy output. By using these losses, the weight parameters of each intermediate layer in the neural network can be updated, ensuring that the second reconstructed output is as close as possible to the second output, and the first noisy output is as close as possible to the first output, thus guaranteeing the correct training direction of the neural network.

[0076] By inputting user-uploaded maintenance and repair information, as well as data uploaded by vehicle-mounted sensor 2, into the neural network, the output of the neural network's output layer is obtained. The loss between the output of the output layer and the labeled results is then used to train the neural network. This primarily targets data with labeled results. By inputting this data into the neural network, the output of the neural network's output layer is obtained. Using the loss between the output of the output layer and the labeled results, the weight parameters of the output layer in the neural network can be updated, making the output result as close as possible to the labeled result, thereby completing the training of the neural network.

[0077] Processor 1 sends the predicted maintenance times for agricultural machinery components to PC and mobile platforms such as WeChat mini-programs. Upon receiving the data, the platforms send maintenance reminders to the user and also provide a simplified maintenance plan.

[0078] Based on the same inventive concept, the present invention also provides a storage medium and an electronic device, wherein the storage medium stores a computer program configured to execute the above-described agricultural machinery maintenance prediction method during runtime. The electronic device includes: a processor 1; and a memory for storing executable instructions of the processor 1; wherein the processor 1 is configured to execute the above-described agricultural machinery maintenance prediction method by executing the executable instructions.

[0079] In this invention, when agricultural machinery 3 is in use, the environmental parameter information affecting the maintenance time of agricultural machinery, the maintenance age information of agricultural machinery equipment parts, and the maintenance information of agricultural machinery uploaded by users can be transmitted through the vehicle-mounted sensor 2. This can effectively improve the accuracy of predicting the failure time of agricultural machinery equipment parts, remind users to carry out timely maintenance of agricultural machinery, effectively save agricultural machinery maintenance costs and reduce the risk of using agricultural machinery 3 through agricultural machinery maintenance prediction.

[0080] Of course, the present invention may have other various embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art can make various corresponding changes and modifications according to the present invention, but these corresponding changes and modifications should all fall within the protection scope of the appended claims.

Claims

1. A method for predicting agricultural machinery maintenance, characterized in that, Based on a large amount of unlabeled data, the status of agricultural machinery is mined, and agricultural machinery accident prevention and prediction are carried out based on the mining results, including the following steps: S100. Based on the working environment and maintenance requirements of the agricultural machinery to be predicted, establish a maintenance time prediction model based on semi-supervised learning. S200: Obtain the factory information, vehicle sensor information, maintenance information, and upkeep information of the agricultural machinery to be predicted; as well as S300. Input the information obtained in step S200 into the maintenance time prediction model to obtain the possible failure rate and time of the equipment components of the agricultural machinery to be predicted, and complete the prediction of maintenance time for the equipment components of different agricultural machinery to be predicted. Step S200 further includes: S201. Obtain the factory information of agricultural machinery equipment parts, obtain the service life and suitable environmental parameters of each piece of equipment and part from the agricultural machinery equipment parts manufacturer, and enter them into the background database. S202. Obtain agricultural machinery status information, including environmental data stored in the on-board sensors of the agricultural machinery to be predicted that affect maintenance time after the machinery leaves the factory, and store this data in the background database and maintenance time prediction model; and S203. Obtain agricultural machinery repair information. Obtain agricultural machinery repair information through the agricultural machinery repair and maintenance platform, and enter it into the background database and maintenance time prediction model. Step S100 further includes: S101. Input the maintenance information, repair information and data from the vehicle sensor into a neural network that introduces noise data in multiple intermediate layers, and obtain the first noise output result of the first intermediate layer; S102. The neural network is reconstructed using the first noise output result to obtain the second reconstruction output result of at least one second intermediate layer. S103. Input the maintenance information, repair information, and vehicle sensor data into the neural network to obtain at least one second output result of a second intermediate layer and a first output result of a first intermediate layer; and S104. Using the loss between the second output result and the second reconstructed output result, and the loss between the first output result and the first noise output result, the neural network is trained to obtain the maintenance time prediction model.

2. The agricultural machinery maintenance prediction method as described in claim 1, characterized in that, Step S100 also includes: S105. Input the maintenance information, repair information, and data from the vehicle's sensors into the maintenance time prediction model to obtain the output of the neural network's output layer; and S106. The neural network is trained using the loss between the output of the output layer and the labeled result to further improve the maintenance time prediction model.

3. The agricultural machinery maintenance prediction method as described in claim 1 or 2, characterized in that, Also includes: S400 will send maintenance alerts to users via push notifications, based on the predicted maintenance times for agricultural machinery.

4. A predictive device for agricultural machinery maintenance, characterized in that, The system includes a processor and vehicle-mounted sensors, which are connected to the processor and the agricultural machinery respectively. The processor uses the agricultural machinery maintenance prediction method according to any one of claims 1-3 to mine the status of agricultural machinery based on a large amount of unlabeled data and to predict agricultural machinery accidents based on the mining results.

5. The agricultural machinery maintenance prediction device as described in claim 4, characterized in that, The processor includes a system setting module, a status monitoring module, a maintenance information module, a maintenance information module, and a viewing and display module. The maintenance information module stores historical maintenance information of agricultural machinery, and the maintenance information module stores historical maintenance information of agricultural machinery.

6. The agricultural machinery maintenance prediction device as described in claim 4, characterized in that, The vehicle-mounted sensor is used to record environmental parameters that affect the maintenance time of agricultural machinery, and is connected to the agricultural machinery via a bus to obtain information on key components of the agricultural machinery. The vehicle-mounted sensor includes a data acquisition unit, a central processing unit, and a data network transmission unit. The environmental parameters and key component information of the agricultural machinery acquired by the data acquisition unit are processed by the central processing unit and then transmitted to the processor through the data network transmission unit.

7. A storage medium, characterized in that, The storage medium stores a computer program, which is configured to execute the agricultural machinery maintenance prediction method according to any one of claims 1-3 when it runs.

8. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the agricultural machinery maintenance prediction method according to any one of claims 1-3 by executing the executable instructions.

Images