Method, device and operating machinery for predicting vehicle stalling failure

Abstract

The present invention provides a method, device and operating machinery for predicting a stalling fault, and relates to the technical field of engineering machinery. The method comprises: obtaining target data, the target data comprising the speed, working gear and power condition data of the engine of the operating machinery in a first time period; inputting the target data into a stalling fault prediction model, and obtaining the prediction result of the stalling fault of the operating machinery in a second time period output by the stalling fault prediction model; wherein the power condition data comprises: the return oil pressure, main pump pressure and main pump current of the hydraulic system; the stalling fault prediction model is constructed based on the speed, working gear and power condition data of the engine of the sample operating machinery in the first sample time period, and whether the stalling fault occurs in the sample operating machinery in the second sample time period. The stalling fault prediction method, device and operating machinery provided by the present invention can predict the stalling fault in advance, can improve the practicality of the stalling fault prediction, and can more effectively avoid the occurrence of the fault.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering machinery, and in particular to a method and device for predicting vehicle stalling failures and an operating machine. Background Art

[0002] A stalling failure refers to a failure in which the engine speed of an operating machine drops sharply or stalls when under stress. There are many reasons that may cause a stalling failure, such as: the engine power of the operating machine does not match the main pump power in the hydraulic system, insufficient engine air intake, excessive load, oil circuit blockage, and air filter blockage. Frequent stalling failures may damage the transmission system in the operating machine and affect the service life of the operating machine.

[0003] The existing engine stalling fault prediction method can be based on a predetermined speed threshold, and when the real-time detected engine speed drops and the speed drop value is greater than the speed threshold, it is considered that the operating machine may have an engine stalling fault. However, based on the above existing engine stalling fault prediction method, when predicting whether an engine stalling fault will occur, when it is determined that the real-time detected engine speed drops and the speed drop value is greater than the speed threshold, the operating machine has already had an engine stalling fault, and it is difficult to reserve enough time to repair or control the operating machine, and the practicality of predicting an engine stalling fault is not strong. Summary of the invention

[0004] The present invention provides a method, device and operating machine for predicting a vehicle stalling fault, which are used to solve the defect that the prediction of a vehicle stalling fault in the prior art is not very practical, and to improve the practicality of predicting a vehicle stalling fault.

[0005] The present invention provides a method for predicting a vehicle stalling fault, comprising:

[0006] Acquiring target data, wherein the target data includes the speed, working gear and power condition data of the engine of the working machine in the first period of time;

[0007] Inputting the target data into a vehicle holding failure prediction model to obtain a prediction result of a vehicle holding failure of the operating machine within a second period output by the vehicle holding failure prediction model;

[0008] Among them, the end time of the first time period is earlier than the start time of the second time period; the power operating condition data include: the return oil pressure, main pump pressure and main pump current of the hydraulic system; the engine stalling failure prediction model is constructed based on the engine speed, working gear and the power operating condition data of the sample operating machinery in the first sample time period, and whether the sample operating machinery has a engine stalling failure in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0009] According to a method for predicting a vehicle holding failure provided by the present invention, inputting the target data into a vehicle holding failure prediction model, and obtaining a prediction result of a vehicle holding failure of the operating machine within a second time period output by the vehicle holding failure prediction model, specifically includes:

[0010] Inputting the target data into the vehicle holding failure prediction model to obtain the prediction result output by the vehicle holding failure prediction model, wherein the prediction result indicates that the operating machine will not have a vehicle holding failure within the second time period;

[0011] Among them, the vehicle jam failure prediction model is used to obtain the first characteristic data corresponding to the target data, and based on the first characteristic data, obtain the first probability of the vehicle jam failure of the operating machinery in the second time period, and output the prediction result when the first probability is not greater than a first preset value.

[0012] According to a method for predicting a vehicle holding failure provided by the present invention, inputting the target data into a vehicle holding failure prediction model, and obtaining a prediction result of a vehicle holding failure of the operating machine within a second time period output by the vehicle holding failure prediction model, specifically includes:

[0013] Inputting the target data into the engine-holding failure prediction model to obtain the prediction result output by the engine-holding failure prediction model, wherein the prediction result includes a second probability of the engine-holding failure of the operating machine occurring within the second time period;

[0014] Among them, the vehicle jam failure prediction model is used to obtain the first characteristic data corresponding to the target data, and based on the first characteristic data, obtain the first probability of the operating machinery having a vehicle jam failure in the second time period; when the first probability is greater than a first preset value, obtain the second characteristic data corresponding to the target data, and based on the second characteristic data, obtain the second probability of the operating machinery having a vehicle jam failure in the second time period.

[0015] According to a method for predicting a vehicle stalling fault provided by the present invention, the vehicle stalling fault prediction model is used to extract features of each type of power operating condition data in the target data based on the speed and the working gear in the target data, and obtain feature data corresponding to each type of power operating condition data as the first feature data.

[0016] According to a vehicle stalling fault prediction method provided by the present invention, the vehicle stalling fault prediction model is used to obtain the residual and determination coefficient of the target data as the second feature data.

[0017] According to a vehicle stalling failure prediction method provided by the present invention, the prediction result further includes: a risk level corresponding to the second probability.

[0018] The present invention also provides a vehicle stalling fault prediction device, comprising:

[0019] A data acquisition module, used to acquire target data, wherein the target data includes the speed, working gear and power condition data of the engine of the working machine within a first period of time;

[0020] a fault prediction module, used for inputting the target data into a stalling fault prediction model, and obtaining a prediction result of a stalling fault of the operating machine within a second time period output by the stalling fault prediction model;

[0021] Among them, the end time of the first time period is earlier than the start time of the second time period; the power operating condition data include: the return oil pressure, main pump pressure and main pump current of the hydraulic system; the engine stalling failure prediction model is constructed based on the engine speed, working gear and the power operating condition data of the sample operating machinery in the first sample time period, and whether the sample operating machinery has a engine stalling failure in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0022] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned methods for predicting vehicle stalling failures is implemented.

[0023] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the vehicle stalling fault prediction method as described in any one of the above is implemented.

[0024] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, any of the above-mentioned vehicle stalling fault prediction methods is implemented.

[0025] The method, device and operating machine for predicting a stalling fault provided by the present invention obtain target data including the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the operating machine in a first time period, input the above target data into a stalling fault prediction model, obtain the prediction result of the stalling fault of the operating machine in a second time period output by the stalling fault prediction model, the end time of the first time period is earlier than the start time of the second time period, the stalling fault prediction model is constructed based on the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the sample operating machine in the first sample time period, and whether the stalling fault occurs in the sample operating machine in the second sample time period, the end time of the first sample time period is earlier than the start time of the second sample time period, the stalling fault can be predicted in advance, the practicality of the stalling fault prediction can be improved, by predicting the stalling fault in advance, sufficient time can be reserved for inspection and maintenance of the operating machine before the stalling fault occurs, the occurrence of the stalling fault can be avoided more effectively, the availability of the operating machine can be improved, the maintenance workload can be reduced, and the maintenance cost can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 This is one of the flow charts of the method for predicting vehicle stalling failure provided by the present invention;

[0028] Figure 2 It is a data schematic diagram of the engine speed that has not been processed in the first period of time in the method for predicting the vehicle stalling fault provided by the present invention;

[0029] Figure 3 It is a data schematic diagram of the engine speed after data processing in the first period of time in the method for predicting vehicle stalling failure provided by the present invention;

[0030] Figure 4 It is a structural schematic diagram of a vehicle stalling fault prediction model in the vehicle stalling fault prediction method provided by the present invention;

[0031] Figure 5 It is a data schematic diagram of the confidence interval corresponding to the second probability in the vehicle holding failure prediction method provided by the present invention;

[0032] Figure 6 It is a data schematic diagram of the oil return pressure of the hydraulic system in the target data in the vehicle holding failure prediction method provided by the present invention;

[0033] Figure 7 It is a data schematic diagram of the return oil pressure of the hydraulic system at a unit speed in the target data in the vehicle stalling fault prediction method provided by the present invention;

[0034] Figure 8 It is a data schematic diagram of the second characteristic data in the vehicle stalling fault prediction method provided by the present invention;

[0035] Fig. 9 It is a data schematic diagram of the second probability in the vehicle holding failure prediction method provided by the present invention;

[0036] Fig.10 It is a structural schematic diagram of the vehicle stalling fault prediction device provided by the present invention;

[0037] Fig.11 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] In the description of the invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] It should be noted that based on traditional intelligent diagnostic technology, it is possible to diagnose the engine, power head, bearings and other components of the operating machinery to determine whether the above components have failed. However, there are fewer intelligent diagnostic technologies for engine stalling failures.

[0041] Under normal circumstances, according to the predetermined speed threshold, when the real-time detected engine speed drops and the speed drop value is greater than the preset speed threshold, it is considered that the operating machinery may have a stalling fault. At this time, the electric proportional valve current, the main pump motor oil supply pressure and the main pump voltage in the hydraulic system of the operating machinery can be adjusted to control the load and torque of the operating machinery to avoid the stalling fault. However, for the stalling fault caused by the oil circuit blockage and air filter blockage of the operating machinery, it is difficult to avoid the stalling fault by adjusting the electric proportional valve current, the main pump motor oil supply pressure and the main pump voltage, so that the speed and torque of the operating machinery will continue to remain in a mismatched state, which is easy to cause damage to the operating machinery. Therefore, for the stalling fault caused by the oil circuit blockage and air filter blockage of the operating machinery, the only way to avoid the stalling fault is to timely repair the operating machinery and eliminate the problems of oil circuit blockage and air filter blockage of the operating machinery. However, frequent maintenance of the operating machinery not only affects the working efficiency of the operating machinery, but also requires a lot of manpower and maintenance costs.

[0042] The traditional method of predicting a stalling failure is based on real-time detection of the engine speed to determine whether the operating machinery has a stalling failure. When it is determined that the real-time detected engine speed has dropped and the speed drop value is greater than the preset speed threshold, the operating machinery may have a stalling failure. It is difficult to reserve enough time to repair or control the operating machinery, and the timeliness is poor and has strong limitations.

[0043] Therefore, the present invention provides a method for predicting a stalling failure. Based on the method for predicting a stalling failure provided by the present invention, it is possible to predict in advance whether a working machine will have a stalling failure, so that sufficient time can be reserved for maintenance or control of the working machine, thereby avoiding damage to the working machine caused by the stalling failure, improving the availability of the working machine, reducing maintenance workload, and reducing maintenance costs.

[0044] Figure 1 2 is a flow chart of the method for predicting vehicle stalling failure provided by the present invention. Figure 1 The method for predicting vehicle stalling failure of the present invention is described below. Figure 1 As shown, the method includes: step 101, obtaining target data, the target data including the engine speed, working gear and power condition data of the operating machinery in a first time period; wherein the end time of the first time period is earlier than the start time of the second time period; the power condition data includes: the return oil pressure, main pump pressure and main pump current of the hydraulic system.

[0045] Specifically, the first time period is earlier than the second time period and the first time period does not overlap with the second time period. Based on the method for predicting a stalling fault provided by the present invention, it is possible to predict whether a stalling fault occurs in the operating machinery in the second time period based on the working condition data of the operating machinery in the first time period, and obtain a prediction result of whether a stalling fault occurs in the operating machinery in the second time period.

[0046] Optionally, the end time of the first time period may be the start time of the second time period. The duration of the first time period may be the same as the duration of the second time period. For example, the first time period may be from 00:00 to 23:59 on January 1, 2022, and the second time period may be from 00:00 to 23:59 on January 2, 2022. Based on the method for predicting a vehicle holding failure provided by the present invention, it is possible to predict whether a vehicle holding failure occurs in the operating machinery from 00:00 to 23:59 on January 1, 2022 based on the operating condition data of the operating machinery from 00:00 to 23:59 on January 1, 2022, and obtain a prediction result of a vehicle holding failure in the operating machinery from 00:00 to 23:59 on January 2, 2022.

[0047] It is understandable that the engine stalling failure is mainly caused by power mismatch during the operation of the engine. Therefore, in the embodiment of the present invention, power operating condition data that can describe the engine power matching situation of the operating machinery during the operation process can be obtained for engine stalling failure prediction.

[0048] The power operating condition data may include but is not limited to the return oil pressure, main pump pressure and main pump current of the hydraulic system.

[0049] It can be understood that the power operating condition data includes a plurality of different types of power operating condition data, and the return oil pressure, main pump pressure and main pump current of the hydraulic system are three different types of power operating condition data respectively.

[0050] The engine speed and the working gear of the working machine can be continuously obtained based on the controller of the working machine in the first period. For example, the engine speed and the current working gear (current gear) of the working machine can be obtained every preset sampling period in the first period.

[0051] The power operating condition data of the operating machinery during the first time period can be continuously obtained in a variety of ways. For example, based on the controller of the operating machinery, the main pump current of the hydraulic system of the operating machinery in the current gear position can be obtained every the above-mentioned preset sampling period during the first time period; based on various sensors, the return oil pressure and main pump pressure of the hydraulic system of the operating machinery in the above-mentioned current gear position can be obtained every the above-mentioned preset sampling period during the first time period.

[0052] After obtaining the data on the engine speed, working gear and power condition of the operating machine in the first period of time, the data on the engine speed, working gear and power condition of the operating machine in the first period of time can be directly used as target data.

[0053] Optionally, due to the different types and models of sensors used to obtain the power condition data of the operating machinery in the first time period, the sampling frequency of each sensor is also different. In addition, due to the complex working environment of the operating machinery, the operating machinery will generate a large amplitude of vibration when operating, causing the data collected by the above sensors to have a large noise, a low signal-to-noise ratio and include more abnormal values ​​and vacancy values. In order to improve the accuracy of the prediction of the vehicle stalling fault, after obtaining the engine speed, working gear and power condition data of the operating machinery in the first time period, the above data can be used as the original data, and after the above original data is processed, the original data after data processing is used as the target data.

[0054] The raw data may be processed based on mathematical statistics, linear interpolation, downsampling, etc. The specific data processing process is described by taking the data processing of the engine speed in the first period as an example.

[0055] Figure 2 1 is a schematic diagram of the data of the engine speed that has not been processed in the first period of time in the method for predicting the vehicle stalling fault provided by the present invention. Figure 2 As shown, the first period is from 08:10:57 on November 19, 2019 to 08:10:56 on November 20, 2019. The speed noise of the engine that has not been processed during the first period is relatively large, and there are multiple abnormal values ​​with large fluctuations.

[0056] After the abnormal values ​​in the rotation speed of the engine that has not been processed in the first period of time are identified based on the mathematical statistics method, the abnormal values ​​can be replaced by the linear interpolation method.

[0057] After replacing the abnormal value in the rotation speed of the engine that has not been data processed in the first time period, the replaced abnormal value can be verified based on prior knowledge, and the replacement of the abnormal value is confirmed when the replaced abnormal value meets the verification.

[0058] Figure 3 FIG. 1 is a data diagram of the engine speed after data processing in the first period of time in the method for predicting a vehicle stalling fault provided by the present invention. Figure 3 As shown, the engine speed noise after data processing in the first time period is relatively small, and the engine speed after data processing in the first time period can be used as target data.

[0059] The engine speed, working gear and power condition data of the operating machinery in the first period may also be downsampled to unify the sampling frequencies of the engine speed, working gear and target condition data.

[0060] It should be noted that the engine speed and working gear of the working machine in the target data have a corresponding relationship with the power operating condition data.

[0061] It should be noted that, in the embodiments of the present invention, “first” and “second” are used to distinguish similar objects rather than to describe or indicate a specific order or sequence.

[0062] Step 102: Input the target data into the engine stalling failure prediction model to obtain the prediction result of the engine stalling failure of the operating machinery in the second time period output by the engine stalling failure prediction model; wherein the engine stalling failure prediction model is constructed based on the engine speed, working gear and power condition data of the sample operating machinery in the first sample time period, and whether the engine stalling failure occurs in the sample operating machinery in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0063] Specifically, before inputting the target data into the engine holding failure prediction model and obtaining the prediction result of the engine holding failure of the operating machine in the second period output by the engine holding failure prediction model, the engine speed, working gear and power condition data of the sample operating machine in the first sample period can be obtained as sample data, and whether the engine holding failure of the sample operating machine in the second sample period occurs as a sample label, and the engine holding failure prediction model is constructed based on the above sample data and sample labels. Among them, the first sample period is earlier than the second sample period, and the first sample period does not overlap with the second sample period.

[0064] Optionally, the end time of the first sample period may be the start time of the second sample period. The duration of the first sample period may be the same as the duration of the second sample period.

[0065] It should be noted that the first sample time period and the second sample time period have a corresponding relationship with the first time period and the second time period, that is, the length of the first time period is the same as the length of the first sample time period, the length of the second time period is the same as the length of the second sample time period, and the length of the interval between the first time period and the second time period is the same as the length of the interval between the first sample time period and the second sample time period.

[0066] It should be noted that the sample operating machine is an operating machine in a normal working state. The operating machine described above is of the same type and model as the sample operating machine.

[0067] The above-mentioned sample data can be obtained through a variety of methods. For example, based on the controller of the sample working machine, the engine speed of the sample working machine, the current working gear (current gear) of the sample working machine and the main pump current of the hydraulic system of the sample working machine in the above-mentioned current gear can be obtained as sample data every preset sampling period within the first sample time period; based on various sensors, the return oil pressure and the main pump pressure of the hydraulic system of the sample working machine in the above-mentioned current gear can be obtained as sample data every preset sampling period within the first sample time period.

[0068] Whether a vehicle stalling failure occurs in the sample operating machinery during the second sample period can be determined based on the prior data as a sample label.

[0069] After obtaining the sample data and the sample labels, a vehicle holding failure prediction model may be constructed based on the sample data and the sample labels.

[0070] After the engine stall estimation prediction model is constructed, the target data can be input into the engine stall fault prediction model to obtain the prediction result of the engine stall fault occurring in the operating machinery within the second time period output by the engine stall fault prediction model.

[0071] It should be noted that the above prediction result may include whether the operating machine will have a stalling failure or not in the second time period; the above prediction result may also include the probability and / or risk level of the operating machine having a stalling failure in the second time period; the above prediction result may also include the probability and / or risk level of the operating machine having a stalling failure at the target time in the second time period. The above prediction result is not specifically limited in the embodiments of the present invention.

[0072] The embodiment of the present invention obtains target data including the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the working machinery in a first time period, inputs the above target data into the engine stalling fault prediction model, and obtains the prediction result of the engine stalling fault of the working machinery in the second time period output by the engine stalling fault prediction model. The end time of the first time period is earlier than the start time of the second time period. The engine stalling fault prediction model is constructed based on the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the sample working machinery in the first sample time period, and whether the engine stalling fault occurs in the sample working machinery in the second sample time period. The end time of the first sample time period is earlier than the start time of the second sample time period. The engine stalling fault can be predicted in advance, and the practicality of the engine stalling fault prediction can be improved. By predicting the engine stalling fault in advance, sufficient time can be reserved for inspection and maintenance of the working machinery before the engine stalling fault occurs, which can more effectively avoid the occurrence of the engine stalling fault, improve the availability of the working machinery, reduce the maintenance workload, and reduce the maintenance cost.

[0073] Based on the contents of the above-mentioned embodiments, the target data is input into the vehicle holding failure prediction model to obtain a prediction result output by the vehicle holding failure prediction model, and the prediction result indicates that the operating machinery will not have a vehicle holding failure within the second time period; wherein the vehicle holding failure prediction model is used to obtain first characteristic data corresponding to the target data, and based on the first characteristic data, obtain a first probability of a vehicle holding failure occurring in the operating machinery within the second time period, and output a prediction result when the first probability is not greater than a first preset value.

[0074] Figure 4 FIG. 1 is a schematic diagram of the structure of the vehicle stalling fault prediction model in the vehicle stalling fault prediction method provided by the present invention. Figure 4 As shown, the vehicle stalling fault prediction model includes: a first feature extraction layer and a first prediction layer.

[0075] Specifically, after acquiring the target data, the target data is input into the first feature extraction layer in the vehicle holding fault prediction model, and the first feature data corresponding to the target data output by the first feature extraction layer can be acquired.

[0076] The first feature extraction layer can be used to perform a first feature extraction on the target data, and obtain and output the above-mentioned first feature data.

[0077] After obtaining the first characteristic data, the first characteristic data may be input into the first prediction layer to obtain a prediction result output by the first prediction layer indicating that the operating machine will not have a vehicle stalling failure within the second time period.

[0078] It should be noted that before inputting the first feature data into the first prediction layer in the vehicle holding fault prediction model, the first prediction layer can be trained based on the above sample data and sample labels to obtain a trained first prediction layer.

[0079] Specifically, by performing a first feature extraction on the sample data, first sample feature data corresponding to the sample data can be obtained.

[0080] Optionally, the sample data may be input into a first feature extraction layer to obtain first sample feature data corresponding to the sample data output by the first feature extraction layer.

[0081] Based on prior knowledge and whether the sample operating machinery has a stalling failure in the second sample period, a first sample probability of the sample operating machinery having a stalling failure in the second sample period can be obtained. For example, if the sample operating machinery has not a stalling failure in the second sample period, the above first sample probability is 0.

[0082] Based on prior knowledge, the threshold range of each type of power operating condition data when a vehicle stalling failure occurs and the contribution of each type of power operating condition data to the occurrence of the vehicle stalling failure can also be determined as training parameters for training the first prediction layer.

[0083] Based on the above training parameters, the first sample feature data and the first sample probability, the first prediction layer may be trained to obtain a trained first prediction layer.

[0084] After the trained first prediction layer is obtained, the first feature data may be input into the trained first prediction layer.

[0085] The first prediction layer can obtain the first probability of the operating machinery having a stalling failure in the second time period based on the first feature data. If the first probability is not greater than the preset probability threshold, the first prediction layer can determine that the possibility of the operating machinery having a stalling failure in the second time period is small, and the first prediction layer can output a prediction result indicating that the operating machinery will not have a stalling failure in the second time period, and then obtain the prediction result output by the stalling failure prediction model indicating that the operating machinery will not have a stalling failure in the second time period.

[0086] Optionally, the prediction result output by the engine jam failure prediction model may also include a first probability of an engine jam failure occurring in the operating machinery within the second time period.

[0087] The embodiment of the present invention inputs target data into a vehicle holding failure prediction model, and the vehicle holding failure prediction model performs a first feature extraction on the target data to obtain a first probability of a vehicle holding failure occurring in the operating machinery within a second time period. When it is determined that the first probability is not greater than a first preset value, a prediction result indicating that the operating machinery will not have a vehicle holding failure within the second time period is output, thereby enabling the prediction result of the vehicle holding failure to be obtained more efficiently and accurately when the operating machinery is in a normal state.

[0088] Based on the contents of the above-mentioned embodiments, the target data is input into the vehicle holding failure prediction model to obtain the prediction result of the vehicle holding failure prediction model outputting the vehicle holding failure prediction model, and the prediction result includes the second probability of the vehicle holding failure occurring in the operating machinery in the second time period; wherein the vehicle holding failure prediction model is used to obtain the first characteristic data corresponding to the target data, and based on the first characteristic data, obtain the first probability of the vehicle holding failure occurring in the operating machinery in the second time period; when the first probability is greater than the first preset value, obtain the second characteristic data corresponding to the target data, and based on the second characteristic data, obtain the second probability of the vehicle holding failure occurring in the operating machinery in the second time period.

[0089] like Figure 4 As shown, the vehicle stalling fault prediction model also includes: a second feature extraction layer and a second prediction layer.

[0090] Specifically, the target data is input into the first feature extraction layer, and after the first feature data corresponding to the target data output by the first feature extraction layer is obtained, the first feature data is input into the trained first prediction layer.

[0091] The first prediction layer can obtain the first probability of the operating machine having a stalling failure in the second time period based on the first feature data. If the first probability is greater than the first preset value, the first prediction layer can determine that the operating machine has a greater probability of having a stalling failure in the second time period, and the first prediction layer can call the second feature extraction layer and input the target data into the second feature extraction layer.

[0092] The second feature extraction layer can perform a second feature extraction on the target data, and obtain and output second feature data corresponding to the target data.

[0093] The second feature data is input into the second prediction layer to obtain a prediction result output by the second prediction layer, wherein the prediction result includes a probability of a stalling failure of the operating machinery within the second time period.

[0094] It should be noted that, before the second feature data is input into the second prediction layer, the second prediction layer may be trained based on the sample data and the sample labels to obtain a trained second prediction layer.

[0095] Specifically, by performing a second feature extraction on the sample data, second sample feature data corresponding to the sample data can be obtained.

[0096] Optionally, the sample data may be input into a second feature extraction layer to obtain second sample feature data corresponding to the sample data output by the first feature extraction layer.

[0097] A second sample probability of the sample operating machine having a stalling failure in the second sample period can be obtained based on prior knowledge and whether the sample operating machine has a stalling failure in the second sample period. The second sample probability can be the same as the first sample probability.

[0098] Based on the second sample feature data and the second sample probability, the second prediction layer may be trained to obtain a trained second prediction layer.

[0099] After the trained second prediction layer is obtained, the second feature data may be input into the second prediction layer.

[0100] The second prediction layer can obtain the second probability of the operating machinery having a jamming failure within the second time period based on the second characteristic data as a prediction result of the operating machinery having a jamming failure within the second time period, and then the second prediction layer can obtain the prediction result output including the jamming failure of the operating machinery within the second time period.

[0101] It should be noted that the second probability may be the average probability of a stuck machine failure in the second period, for example, the probability of a stuck machine failure in the second period is 85%; the second probability may also be the probability of a stuck machine failure at a target moment in the second period, wherein the time interval between any two adjacent target moments may be a preset time length. The second probability is not specifically limited in the embodiments of the present invention.

[0102] It should be noted that, based on the prior knowledge and the time when the sample operating machinery has a stalling failure within the second sample period, a confidence interval of the second sample probability can also be obtained.

[0103] Correspondingly, based on the second sample feature data, the second sample probability and the confidence interval of the second sample probability, the second prediction layer is trained. After the trained second prediction layer is obtained, the second feature data is input into the second prediction layer. The second prediction layer can obtain the second probability and the confidence interval corresponding to the second probability based on the second feature data.

[0104] Figure 5 : is a data schematic diagram of the confidence interval corresponding to the second probability in the vehicle stalling fault prediction method provided by the present invention. Figure 5 As shown, when the confidence interval is 0.5, the second probability is 85%.

[0105] The embodiment of the present invention inputs target data into a vehicle holding failure prediction model, and the vehicle holding failure prediction model performs a first feature extraction on the target data to obtain a first probability of a vehicle holding failure occurring in the operating machinery within the second time period. When it is determined that the above-mentioned first probability is greater than the first preset value, second feature data corresponding to the target data is obtained based on the target data, and a second probability of a vehicle holding failure occurring in the operating machinery within the second time period is obtained based on the second feature data as a prediction result of a vehicle holding failure occurring in the operating machinery within the second time period. When it is initially predicted that there is a high possibility that a vehicle holding failure will occur in the operating machinery within the second time period, the vehicle holding failure occurring in the operating machinery within the second time period can be further predicted, and in particular, vehicle holding failures caused by oil circuit blockage, air filter blockage and other problems in the operating machinery can be predicted in advance. The prediction result of the vehicle holding failure occurring in the operating machinery within the second time period can be obtained more intuitively, and more targeted measures can be taken based on the above-mentioned prediction results to more effectively avoid the occurrence of vehicle holding failures, reduce maintenance workload, and reduce maintenance cost investment.

[0106] Based on the contents of the above embodiments, the vehicle stalling fault prediction model is used to extract features of each type of power operating condition data in the target data based on the speed and working gear in the target data, and obtain feature data corresponding to each type of power operating condition data as the first feature data.

[0107] Specifically, after the target data is input into the first feature extraction layer, the first feature extraction layer can perform feature extraction on each type of power condition data based on the engine speed and working gear in the target data, so that each type of power condition data can be quantified into feature data, and the feature data corresponding to each type of power condition data is obtained as the first feature data corresponding to the target data. For example, the first feature extraction layer can perform feature extraction on the engine speed of the working machine in the target data, and obtain the feature data corresponding to the engine speed in the target data as the first feature data.

[0108] Optionally, for any type of power condition data, the first feature extraction layer can perform feature extraction on the power condition data of this type at each working gear, and obtain feature data corresponding to the power condition data of this type at each working gear as feature data corresponding to the power condition data of this type. For example: the first feature extraction layer can perform feature extraction on the engine speed of the operating machinery at the first working gear in the target data, and obtain feature data corresponding to the engine speed at the first working gear in the target data as feature data corresponding to the engine speed in the target data.

[0109] The first feature extraction layer can perform feature extraction on any type of power condition data of the working machinery in any working gear in the target data in the following manner, specifically including: the first feature extraction layer can obtain the ratio between the power condition data of this type in the working gear in the target data and the speed of the corresponding engine, obtain the power condition data of this type at a unit speed in the working gear in the first time period, based on the power condition data of this type at a unit speed in the working gear in the first time period and the power condition data of this type in the working gear, feature extraction can be performed on the power condition data of this type in the working gear by a numerical calculation method, and the power condition data of this type at a unit speed in the working gear in the first time period and the power condition data of this type in the working gear are quantified into feature data corresponding to the power condition data of this type in the working gear, as feature data corresponding to the power condition data of this type.

[0110] Figure 6 It is a data schematic diagram of the return oil pressure of the hydraulic system in the target data in the vehicle stalling fault prediction method provided by the present invention. Figure 7 It is a data schematic diagram of the return oil pressure of the hydraulic system at a unit speed in the target data in the method for predicting a vehicle stalling fault provided by the present invention. The first feature extraction layer can obtain the ratio between the return oil pressure of the hydraulic system in the target data and the corresponding engine speed, and obtain the return oil pressure of the hydraulic system at a unit speed in the target data.

[0111] The first feature extraction layer can quantify the return oil pressure of the hydraulic system at unit speed in the target data into feature data [0.0182, 0.0184, 0.0180, 0.00006] corresponding to the return oil pressure of the hydraulic system based on the return oil pressure of the hydraulic system at unit speed in the target data.

[0112] The engine stalling fault prediction model in the embodiment of the present invention is based on the engine speed and working gear of the operating machinery in the first time period in the target data, and extracts features of each type of power operating condition data in the target data, and obtains the feature data corresponding to each type of power operating condition data as the first feature data corresponding to the target data. It can more accurately and efficiently obtain the features of the target data, and then more accurately infer the operating status of the operating machinery in the first time period based on the features of the target data, providing a data basis for more accurate prediction results of the engine stalling fault.

[0113] Based on the contents of the above embodiments, the vehicle holding failure prediction model is used to obtain the residual and determination coefficient of the target data as the second feature data.

[0114] It can be understood that the sample operating machine is in normal working condition, so the power system of the sample operating machine satisfies the speed characteristic curve, and the regression algorithm can be used to obtain the regression model of the engine speed of the sample operating machine and the power operating condition data of the sample operating machine in the first sample period.

[0115] After obtaining the above regression model, a second feature extraction layer may be constructed based on the above regression model.

[0116] After the first prediction layer inputs the target data into the constructed second feature extraction layer, the second feature extraction layer can perform a second feature extraction on the target data based on the target data and the above-mentioned regression model, and obtain the residual and determination coefficient of the target data as the second feature data corresponding to the target data, and then obtain the second feature data output by the second feature extraction layer.

[0117] Figure 8 It is a data schematic diagram of the second characteristic data in the vehicle holding failure prediction method provided by the present invention. Figure 8 Figure (a) is a schematic diagram of the residual of the target data. Figure 8 Figure (b) in the figure is a schematic diagram of the determination coefficient of the target data. Figure 8 As shown, there are large fluctuation points in Figure (a) and Figure (b), indicating that at the above fluctuation points, the power operating condition data of the operating machinery deviates greatly from the speed characteristic curve of the power system of the sample operating machinery, and the operating machinery may have a stalling failure at the time when the above fluctuation points are located.

[0118] It should be noted that the coefficient of determination represents the numerical characteristics of the relationship between a random variable and multiple random variables. It is a statistical indicator used to reflect the reliability of the regression model in explaining the changes in the dependent variable. It is generally represented by the symbol "R".

[0119] Fig. 9 1 is a data diagram of the probability of a stalling failure of an operating machine in the second period of time in the stalling failure prediction method provided by the present invention. Fig. 9 As shown, the solid line is the actual value of the engine speed of the operating machinery in the second time period, and the dotted line is the predicted value of the engine speed of the operating machinery in the second time period. The fluctuation point where the predicted value fluctuates greatly indicates that the probability of the operating machinery having a stalling failure is higher at the moment of the fluctuation point.

[0120] The vehicle holding failure prediction model in the embodiment of the present invention obtains the residual and determination coefficient of the target data as the second feature data corresponding to the target data, which can improve the interpretability, computational efficiency and accuracy of the vehicle holding failure prediction model, reduce the false alarm rate of the vehicle holding failure prediction model, and can more accurately and efficiently predict the vehicle holding failure in advance.

[0121] Based on the contents of the above embodiments, the prediction result further includes: a risk level corresponding to the second probability.

[0122] Optionally, the second feature data is input into the trained second prediction layer, and the second prediction layer can obtain a second probability of a stalling failure of the operating machine in the second time period and a confidence interval of the second probability based on the second feature data. The second prediction layer can determine the risk level of a stalling failure of the operating machine in the second time period based on the second probability and the confidence interval of the second probability.

[0123] Optionally, the second feature data is input into the trained second prediction layer, and the second prediction layer can obtain the second probability of the operating machinery having a stalling failure in the second period based on the second feature data, and the second prediction layer can determine the risk level of the operating machinery having a stalling failure in the second period based on the second probability and the second preset value. For example: the second preset value can include 80%, 60%, 40% and 20%, if the second probability is greater than 80%, the risk level is determined to be high risk, if the second probability is greater than 60%, the risk level is determined to be medium-high risk, if the second probability is greater than 40%, the risk level is determined to be medium risk, if the second probability is greater than 20%, the risk level is determined to be medium-low risk, and if the second probability is less than 20%, the risk level is determined to be low risk.

[0124] It should be noted that the risk level of the operating machinery's vehicle holding failure during the second period can be the average risk level of the operating machinery's vehicle holding failure during the second period, for example: the risk level of the operating machinery's vehicle holding failure during the second period is medium-high risk; the risk level of the operating machinery's vehicle holding failure during the second period can also be the risk level of the operating machinery's vehicle holding failure at a target moment during the second period, wherein the time interval between any two adjacent target moments can be a preset duration. In the embodiment of the present invention, the risk level of the operating machinery's vehicle holding failure during the second period is not specifically limited.

[0125] Based on the risk level of the operating machinery's engine jam during the second time period, targeted measures can be taken to avoid engine jams in the operating machinery. For example, if the risk level of the operating machinery's engine jam during the second time period is high, the operating machinery needs to be shut down for maintenance, with a focus on detecting whether the operating machinery has oil circuit blockages, air filter blockages, etc.

[0126] The embodiment of the present invention obtains the second probability of a vehicle jamming failure of the operating machinery within the second time period based on the second characteristic data through the vehicle jamming failure prediction model, and then obtains the risk level of the vehicle jamming failure of the operating machinery within the second time period based on the above second probability, thereby outputting a prediction result including the above risk level. The prediction result of the vehicle jamming failure of the operating machinery within the second time period can be displayed more flexibly and intuitively, and more targeted measures can be taken based on the risk level included in the above prediction result to avoid the occurrence of vehicle jamming failure, reduce maintenance workload, and reduce maintenance cost investment.

[0127] Based on the contents of the above embodiments, whether the sample operating machinery has a vehicle holding failure within the second sample time period is determined based on the time when the vehicle holding failure occurs in the sample operating machinery within the second sample time period. If the sample operating machinery has not had a vehicle holding failure within the second sample time period, the time when the vehicle holding failure occurs in the sample operating machinery within the second sample time period is empty; the second probability includes: the probability of the operating machinery having a vehicle holding failure at the target time within the second time period.

[0128] Specifically, based on the time when the sample operating machinery has a stalling failure in the second sample period and prior knowledge, the sample probability of the stalling failure occurring at the sample time in the second sample period can be obtained, wherein the time intervals between any two adjacent sample times are equal. For example: if the stalling failure does not occur at a certain sample time, the probability of the sample operating machinery having a stalling failure at the sample time is 0; if the stalling failure occurs at a certain sample time, the probability of the sample operating machinery having a stalling failure at the sample time is 100%.

[0129] Based on the second sample feature data and the sample probability of the vehicle holding failure occurring at the sample time within the second sample period, the second prediction layer may be trained to obtain a trained second prediction layer.

[0130] The second feature data is input into the trained second prediction layer to obtain the second probability output by the second prediction layer. The second probability may include the probability of the operating machine having a stalling failure at the target moment in the second period, wherein the time interval between any two adjacent target moments may be a preset time length. For example, the probability of the operating machine having a stalling failure at the first target moment in the second period is 1%, the probability of the operating machine having a stalling failure at the second target moment is 2%, ..., and the probability of the operating machine having a stalling failure at the target moment in the Nth target period is 85%.

[0131] The second prediction layer in the embodiment of the present invention obtains the second probability of the operating machinery having a jamming failure within the second time period based on the second characteristic data. The above second probability includes the probability of the operating machinery having a jamming failure at the target time within the second time period. The prediction results of the operating machinery having a jamming failure within the second time period can be obtained more accurately and intuitively, and in particular, the jamming failures caused by oil circuit blockage, air filter blockage and other problems in the operating machinery can be predicted in advance. More targeted measures can be taken based on the above prediction results, which can more effectively avoid the occurrence of jamming failures.

[0132] Fig.10 This is a schematic diagram of the structure of the vehicle stalling fault prediction device provided by the present invention. Fig.10 The vehicle holding fault prediction device provided by the present invention is described. The vehicle holding fault prediction device described below and the vehicle holding fault prediction method provided by the present invention described above can be referred to each other. Fig.10 As shown, the device includes: a data acquisition module 1001 and a fault prediction module 1002.

[0133] The data acquisition module 1001 is used to acquire target data, where the target data includes the speed, working gear and power condition data of the engine of the working machine in the first time period.

[0134] The fault prediction module 1002 is used to input the target data into the engine-holding fault prediction model, and obtain the prediction result of the engine-holding fault occurring in the operating machinery within the second time period output by the engine-holding fault prediction model.

[0135] Among them, the end time of the first time period is earlier than the start time of the second time period; the power operating condition data include: the return oil pressure of the hydraulic system, the main pump pressure and the main pump current; the engine stalling failure prediction model is based on the engine speed, working gear and power operating condition data of the sample operating machinery in the first sample time period, and whether the sample operating machinery has a engine stalling failure in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0136] Specifically, the data acquisition module 1001 and the fault prediction module 1002 are electrically connected.

[0137] The data acquisition module 1001 can continuously acquire the power operating condition data of the operating machinery during the first time period in a variety of ways. For example, based on the controller of the operating machinery, the main pump current of the hydraulic system of the operating machinery in the current gear position can be acquired every preset sampling period during the first time period. The return oil pressure and main pump pressure of the hydraulic system of the operating machinery in the current gear position can be acquired every preset sampling period during the first time period based on various sensors.

[0138] After the data acquisition module 1001 acquires the engine speed, working gear and power condition data of the operating machine in the first period, the engine speed, working gear and power condition data of the operating machine in the first period can be directly used as target data.

[0139] In order to improve the accuracy of vehicle stalling failure prediction, after the data acquisition module 1001 acquires the engine speed, working gear and power operating condition data of the operating machinery in the first time period, the above data can be used as original data, and after data processing of the above original data, the processed original data can be used as target data.

[0140] The fault prediction module 1002 may input the target data into the stalling fault prediction model to obtain the prediction result of the stalling fault of the operating machinery within the second time period output by the stalling fault prediction model.

[0141] Optionally, the fault prediction module 1002 can be specifically used to input the target data into the vehicle holding fault prediction model to obtain the prediction result output by the vehicle holding fault prediction model, and the prediction result indicates that the vehicle holding fault will not occur in the operating machinery within the second time period; wherein the vehicle holding fault prediction model is used to obtain the first characteristic data corresponding to the target data, and based on the first characteristic data, obtain the first probability of the vehicle holding fault occurring in the operating machinery within the second time period, and output the prediction result when the first probability is not greater than the first preset value.

[0142] Optionally, the fault prediction module 1002 can be specifically used to input the target data into the vehicle holding fault prediction model to obtain the prediction result output by the vehicle holding fault prediction model, the prediction result including the second probability of the vehicle holding fault occurring in the operating machinery within the second time period; wherein, the vehicle holding fault prediction model is used to obtain the first characteristic data corresponding to the target data, and based on the first characteristic data, obtain the first probability of the vehicle holding fault occurring in the operating machinery within the second time period, and when the first probability is greater than a first preset value, obtain the second characteristic data corresponding to the target data, and based on the second characteristic data, obtain the second probability of the vehicle holding fault occurring in the operating machinery within the second time period.

[0143] The embodiment of the present invention obtains target data including the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the working machinery in a first time period, inputs the above target data into the engine stalling fault prediction model, and obtains the prediction result of the engine stalling fault of the working machinery in the second time period output by the engine stalling fault prediction model. The end time of the first time period is earlier than the start time of the second time period. The engine stalling fault prediction model is constructed based on the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the sample working machinery in the first sample time period, and whether the engine stalling fault occurs in the sample working machinery in the second sample time period. The end time of the first sample time period is earlier than the start time of the second sample time period. The engine stalling fault can be predicted in advance, and the practicality of the engine stalling fault prediction can be improved. By predicting the engine stalling fault in advance, sufficient time can be reserved for inspection and maintenance of the working machinery before the engine stalling fault occurs, which can more effectively avoid the occurrence of the engine stalling fault, improve the availability of the working machinery, reduce the maintenance workload, and reduce the maintenance cost.

[0144] Based on the contents of the above embodiments, a working machine includes the vehicle stalling failure prediction device as described above.

[0145] Specifically, the operating machinery may include pile-driving machinery, excavators, vehicles, etc. Among them, pile-driving machinery refers to the operating machinery used for drilling, piling, and sinking piles in various pile foundation constructions, such as pile drivers, vibrating pile sinkers, cast-in-place pile drilling machines, and rotary drilling rigs.

[0146] The operating machine includes the above-mentioned engine-holding fault prediction device, which can predict the engine-holding fault in advance, especially the engine-holding fault caused by oil circuit blockage, air filter blockage and other problems in the operating machine, thereby improving the practicality of engine-holding fault prediction. The structure and specific working process of the engine-holding fault prediction device can refer to the contents of the above-mentioned embodiments, and will not be repeated in the embodiments of the present invention.

[0147] The embodiment of the present invention obtains target data including the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the working machinery in a first time period, inputs the above target data into the engine stalling fault prediction model, and obtains the prediction result of the engine stalling fault of the working machinery in the second time period output by the engine stalling fault prediction model. The end time of the first time period is earlier than the start time of the second time period. The engine stalling fault prediction model is constructed based on the engine speed, working gear, return oil pressure of the hydraulic system, main pump pressure and main pump current of the sample working machinery in the first sample time period, and whether the engine stalling fault occurs in the sample working machinery in the second sample time period. The end time of the first sample time period is earlier than the start time of the second sample time period. The engine stalling fault can be predicted in advance, and the practicality of the engine stalling fault prediction can be improved. By predicting the engine stalling fault in advance, sufficient time can be reserved for inspection and maintenance of the working machinery before the engine stalling fault occurs, which can more effectively avoid the occurrence of the engine stalling fault, improve the availability of the working machinery, reduce the maintenance workload, and reduce the maintenance cost.

[0148] Fig.11 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.11 As shown, the electronic device may include: a processor (processor) 1110, a communication interface (Communications Interface) 1120, a memory (memory) 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140. Processor 1110 can call logic instructions in memory 1130 to execute a stalling fault prediction method, which includes: obtaining target data, the target data including the engine speed, working gear and power condition data of the operating machinery in a first time period; inputting the target data into a stalling fault prediction model, and obtaining a prediction result of a stalling fault of the operating machinery in a second time period output by the stalling fault prediction model; wherein the end time of the first time period is earlier than the start time of the second time period; the power condition data includes: the return oil pressure of the hydraulic system, the main pump pressure and the main pump current; the stalling fault prediction model is constructed based on the engine speed, working gear and power condition data of the sample operating machinery in the first sample time period, and whether the sample operating machinery has a stalling fault in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0149] In addition, the logic instructions in the above-mentioned memory 1130 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0150] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the engine stalling fault prediction method provided by the above-mentioned methods, which includes: obtaining target data, the target data including the engine speed, working gear and power condition data of the operating machinery in a first time period; inputting the target data into a engine stalling fault prediction model, and obtaining the prediction result of the engine stalling fault of the operating machinery in a second time period output by the engine stalling fault prediction model; wherein the end time of the first time period is earlier than the start time of the second time period; the power condition data includes: the return oil pressure of the hydraulic system, the main pump pressure and the main pump current; the engine stalling fault prediction model is constructed based on the engine speed, working gear and power condition data of the sample operating machinery in the first sample time period, and whether the sample operating machinery has a engine stalling fault in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0151] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the engine stalling fault prediction method provided by the above-mentioned methods, the method comprising: obtaining target data, the target data comprising the engine speed, working gear and power condition data of the operating machinery in a first time period; inputting the target data into a engine stalling fault prediction model, and obtaining a prediction result of an engine stalling fault occurring in the operating machinery in a second time period output by the engine stalling fault prediction model; wherein the end time of the first time period is earlier than the start time of the second time period; the power condition data comprises: the return oil pressure of the hydraulic system, the main pump pressure and the main pump current; the engine stalling fault prediction model is constructed based on the engine speed, working gear and power condition data of the sample operating machinery in the first sample time period, and whether the sample operating machinery has an engine stalling fault in the second sample time period; the end time of the first sample time period is earlier than the start time of the second sample time period.

[0152] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting a vehicle stalling fault, characterized in that: include: Acquiring target data, wherein the target data includes the speed, working gear and power condition data of the engine of the working machine in the first period of time; Inputting the target data into a vehicle holding failure prediction model to obtain a prediction result of a vehicle holding failure of the operating machine within a second period output by the vehicle holding failure prediction model; The end time of the first period is earlier than the start time of the second period; the power condition data includes: the return oil pressure, the main pump pressure and the main pump current of the hydraulic system; the engine stall fault prediction model is constructed based on the engine speed, the working gear and the power condition data of the sample operating machinery in the first sample period, and whether the engine stall fault occurs in the sample operating machinery in the second sample period; the end time of the first sample period is earlier than the start time of the second sample period; The step of inputting the target data into a vehicle holding failure prediction model and obtaining a prediction result of a vehicle holding failure of the operating machine within a second period output by the vehicle holding failure prediction model specifically includes: Inputting the target data into the vehicle holding failure prediction model to obtain the prediction result output by the vehicle holding failure prediction model, wherein the prediction result indicates that the operating machine will not have a vehicle holding failure within the second time period; The vehicle stalling failure prediction model is used to obtain first characteristic data corresponding to the target data, and based on the first characteristic data, obtain a first probability of the vehicle stalling failure of the operating machine in the second time period, and output the prediction result when the first probability is not greater than a first preset value; The vehicle stalling fault prediction model is used to extract features of each type of power operating condition data in the target data based on the speed and the working gear in the target data, and obtain feature data corresponding to each type of power operating condition data as the first feature data; The step of inputting the target data into a vehicle holding failure prediction model and obtaining a prediction result of a vehicle holding failure of the operating machine within a second period output by the vehicle holding failure prediction model specifically includes: Inputting the target data into the engine-holding failure prediction model to obtain the prediction result output by the engine-holding failure prediction model, wherein the prediction result includes a second probability of the engine-holding failure of the operating machine occurring within the second time period; The vehicle stalling failure prediction model is used to obtain first characteristic data corresponding to the target data, and based on the first characteristic data, obtain a first probability of the vehicle stalling failure of the operating machine in the second time period, and when the first probability is greater than a first preset value, obtain second characteristic data corresponding to the target data, and based on the second characteristic data, obtain a second probability of the vehicle stalling failure of the operating machine in the second time period; The vehicle stalling fault prediction model is used to obtain the residual and determination coefficient of the target data as the second feature data; Whether the sample operating machine has a stalling fault during the second sample period is determined based on the time when the sample operating machine has a stalling fault during the second sample period; The second probability includes: a probability of the operating machine having a stalling failure at a target time within the second time period.

2. The method for predicting vehicle stalling failure according to claim 1, characterized in that: The prediction result also includes: a risk level corresponding to the second probability.

3. A vehicle stalling fault prediction device, characterized in that: include: A data acquisition module, used to acquire target data, wherein the target data includes the speed, working gear and power condition data of the engine of the working machine within a first period of time; a fault prediction module, used for inputting the target data into a stalling fault prediction model, and obtaining a prediction result of a stalling fault of the operating machine within a second time period output by the stalling fault prediction model; The end time of the first period is earlier than the start time of the second period; the power condition data includes: the return oil pressure, the main pump pressure and the main pump current of the hydraulic system; the engine stall fault prediction model is constructed based on the engine speed, the working gear and the power condition data of the sample operating machinery in the first sample period, and whether the engine stall fault occurs in the sample operating machinery in the second sample period; the end time of the first sample period is earlier than the start time of the second sample period; The fault prediction module inputs the target data into a vehicle holding fault prediction model, and obtains a prediction result of a vehicle holding fault of the operating machine within a second period output by the vehicle holding fault prediction model, specifically including: Inputting the target data into the vehicle holding failure prediction model to obtain the prediction result output by the vehicle holding failure prediction model, wherein the prediction result indicates that the operating machine will not have a vehicle holding failure within the second time period; The vehicle stalling failure prediction model is used to obtain first characteristic data corresponding to the target data, and based on the first characteristic data, obtain a first probability of the vehicle stalling failure of the operating machine in the second time period, and output the prediction result when the first probability is not greater than a first preset value; The vehicle stalling fault prediction model is used to extract features of each type of power operating condition data in the target data based on the speed and the working gear in the target data, and obtain feature data corresponding to each type of power operating condition data as the first feature data; The fault prediction module inputs the target data into a vehicle holding fault prediction model, and obtains a prediction result of a vehicle holding fault of the operating machine within a second period output by the vehicle holding fault prediction model, specifically including: Inputting the target data into the engine-holding failure prediction model to obtain the prediction result output by the engine-holding failure prediction model, wherein the prediction result includes a second probability of the engine-holding failure of the operating machine occurring within the second time period; The vehicle stalling failure prediction model is used to obtain first characteristic data corresponding to the target data, and based on the first characteristic data, obtain a first probability of the vehicle stalling failure of the operating machine in the second time period, and when the first probability is greater than a first preset value, obtain second characteristic data corresponding to the target data, and based on the second characteristic data, obtain a second probability of the vehicle stalling failure of the operating machine in the second time period; The vehicle stalling fault prediction model is used to obtain the residual and determination coefficient of the target data as the second feature data; Whether the sample operating machine has a stalling fault during the second sample period is determined based on the time when the sample operating machine has a stalling fault during the second sample period; The second probability includes: a probability of the operating machine having a stalling failure at a target time within the second time period.

4. A working machine, characterized in that: include: The vehicle stalling failure prediction device as claimed in claim 3.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the vehicle stalling fault prediction method as claimed in claim 1 or 2 is implemented.

Images