CN114418239A - Method and device for predicting failure of held vehicle and operation machine - Google Patents
Method and device for predicting failure of held vehicle and operation machine Download PDFInfo
- Publication number
- CN114418239A CN114418239A CN202210152033.2A CN202210152033A CN114418239A CN 114418239 A CN114418239 A CN 114418239A CN 202210152033 A CN202210152033 A CN 202210152033A CN 114418239 A CN114418239 A CN 114418239A
- Authority
- CN
- China
- Prior art keywords
- fault
- sample
- holding
- data
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000000605 extraction Methods 0.000 claims description 42
- 238000004590 computer program Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 description 23
- 238000012423 maintenance Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 14
- 238000005070 sampling Methods 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000005553 drilling Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Control Of Transmission Device (AREA)
Abstract
The invention provides a method and a device for predicting a failure of a held vehicle and an operating machine, and relates to the technical field of engineering machinery, wherein the method comprises the following steps: acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period; inputting the target data into a car holding fault prediction model, and acquiring a prediction result of the car holding fault of the operation machine in a second time period output by the car holding fault prediction model; wherein, power operating mode data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the vehicle holding down fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of the engine of the sample operation machine in the first sample time period and whether the vehicle holding down fault occurs to the sample operation machine in the second sample time period. The method, the device and the operation machine for predicting the car holding failure can predict the car holding failure in advance, improve the practicability of the car holding failure prediction and effectively avoid the occurrence of the failure.
Description
Technical Field
The invention relates to the technical field of engineering machinery, in particular to a method and a device for predicting a failure of a held vehicle and an operation machine.
Background
The failure of holding the car refers to the failure that the engine in the operation machine rapidly drops in speed or stalls under the stress condition. Car holding faults can be caused by a number of reasons, for example: the engine power of the working machine is not matched with the main pump power in the hydraulic system, the air inflow of the engine is insufficient, the load is overlarge, an oil way is blocked, an air filter element is blocked, and the like. Frequent occurrence of a car holding fault may damage a transmission system in the working machine, affecting the service life of the working machine.
According to the existing vehicle holding fault prediction method, the vehicle holding fault of the working machine is considered to possibly occur under the condition that the speed of the engine is detected to drop in real time and the speed dropping value is larger than the speed threshold according to a predetermined speed threshold. However, based on the above conventional car holding fault prediction method, whether a car holding fault occurs is predicted, and often when it is determined that the speed of the engine detected in real time is reduced and the reduction value is greater than the above rotation speed threshold, the car holding fault of the working machine has occurred, it is difficult to reserve enough time to overhaul or control the working machine, and the practicability of predicting the car holding fault is not strong.
Disclosure of Invention
The invention provides a car holding fault prediction method, a car holding fault prediction device and an operation machine, which are used for solving the defect of poor practicability of the car holding fault prediction in the prior art and improving the practicability of the car holding fault prediction.
The invention provides a vehicle holding fault prediction method, which comprises the following steps:
acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period;
inputting the target data into a car holding fault prediction model, and obtaining a prediction result of the car holding fault of the working machine in a second time period output by the car holding fault prediction model;
wherein an end time of the first time period is earlier than a start time of the second time period; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the vehicle holding-down fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of the engine of the sample operation machine in a first sample time period and whether the vehicle holding-down fault occurs to the sample operation machine in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
According to the method for predicting the car holding fault, the target data are input into a car holding fault prediction model, and a prediction result of the car holding fault of the working machine in a second time period output by the car holding fault prediction model is obtained, and the method specifically comprises the following steps:
inputting the target data into the car holding fault prediction model, and obtaining the prediction result output by the car holding fault prediction model, wherein the prediction result indicates that the working machine cannot have car holding faults in the second time period;
the vehicle holding-down fault prediction model is used for acquiring first characteristic data corresponding to the target data, acquiring a first probability of vehicle holding-down fault of the working machine in the second time interval based on the first characteristic data, and outputting the prediction result when the first probability is not greater than a first preset value.
According to the method for predicting the car holding fault, the target data are input into a car holding fault prediction model, and a prediction result of the car holding fault of the working machine in a second time period output by the car holding fault prediction model is obtained, and the method specifically comprises the following steps:
inputting the target data into the car holding fault prediction model, and obtaining the prediction result output by the car holding fault prediction model, wherein the prediction result comprises a second probability of the car holding fault of the working machine in the second time period;
the vehicle holding back fault prediction model is used for acquiring first feature data corresponding to the target data, acquiring a first probability of the vehicle holding back fault of the working machine in the second time period based on the first feature data, acquiring second feature data corresponding to the target data under the condition that the first probability is larger than a first preset value, and acquiring a second probability of the vehicle holding back fault of the working machine in the second time period based on the second feature data.
According to the vehicle holding down fault prediction method provided by the invention, the vehicle holding down fault prediction model is used for respectively carrying out feature extraction on each type of power working condition data in the target data based on the rotating speed and the working gear in the target data, and acquiring feature data corresponding to each type of power working condition data as the first feature data.
According to the vehicle holding fault prediction method provided by the invention, the vehicle holding fault prediction model is used for obtaining the residual error and the decision coefficient of the target data as the second characteristic data.
According to the method for predicting the failure of the car holding, the prediction result further comprises the following steps: the risk level corresponding to the second probability.
The invention also provides a car holding fault prediction device, which comprises:
the data acquisition module is used for acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period;
the fault prediction module is used for inputting the target data into a vehicle holding fault prediction model and acquiring a prediction result of the vehicle holding fault of the operation machine in a second time period output by the vehicle holding fault prediction model;
wherein an end time of the first time period is earlier than a start time of the second time period; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the vehicle holding-down fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of the engine of the sample operation machine in a first sample time period and whether the vehicle holding-down fault occurs to the sample operation machine in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the vehicle holding fault prediction method is realized.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of suppressing a vehicle fault as described in any of the above.
The invention also provides a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements any of the above-mentioned methods for predicting a failure of a held vehicle.
The method, the device and the operation machine for predicting the suppressed vehicle fault, provided by the invention, are characterized in that target data comprising the rotating speed of an engine of the operation machine, a working gear, the oil return pressure of a hydraulic system, the pressure of a main pump and the current of the main pump in a first time period are obtained, the target data are input into a suppressed vehicle fault prediction model, a prediction result of the suppressed vehicle fault of the operation machine in a second time period output by the suppressed vehicle fault prediction model is obtained, the ending time of the first time period is earlier than the starting time of the second time period, the suppressed vehicle fault prediction model is constructed based on the rotating speed of the engine of a sample operation machine in the first time period, the working gear, the oil return pressure of the hydraulic system, the pressure of the main pump and the current of the main pump, and whether the suppressed vehicle fault of the sample operation machine occurs in the second sample time period, the ending time of the first sample time period is earlier than the starting time of the second sample time period, can carry out the prediction in advance to the trouble of holding back the car, can improve the practicality of the trouble prediction of holding back the car, through predicting the trouble of holding back the car in advance, can reserve sufficient time before the trouble of holding back the car takes place and overhaul and maintain operation machinery, can more effectually avoid the trouble of holding back the car emergence, can improve operation machinery's usability, can reduce the maintenance work volume, can reduce the maintenance cost.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is one of the flow diagrams of a method for predicting a stuck vehicle fault according to the present invention;
fig. 2 is a data schematic diagram of the rotating speed of the engine which is not subjected to data processing in the first period in the method for predicting the failure of the held vehicle provided by the invention;
fig. 3 is a data schematic diagram of the rotating speed of the engine after data processing in the first time period in the vehicle holding fault prediction method provided by the invention;
fig. 4 is a schematic structural diagram of a car holding fault prediction model in the car holding fault prediction method provided by the present invention;
fig. 5 is a data schematic diagram of a confidence interval corresponding to a second probability in the vehicle holding fault prediction method provided by the invention;
fig. 6 is a data schematic diagram of return oil pressure of a hydraulic system in target data in the method for predicting the failure of the held vehicle provided by the invention;
fig. 7 is a data schematic diagram of return oil pressure of a hydraulic system at a unit rotation speed in target data in the method for predicting a failure of a held vehicle provided by the invention;
fig. 8 is a data schematic diagram of second characteristic data in the method for predicting a stuck vehicle fault according to the present invention;
fig. 9 is a data schematic diagram of a second probability in the method for predicting a stuck vehicle fault according to the present invention;
fig. 10 is a schematic structural diagram of a car holding fault prediction device provided by the invention;
fig. 11 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
It should be noted that, based on the conventional intelligent diagnosis technology, the intelligent diagnosis technology for the trouble caused by the stuck car is less, and the intelligent diagnosis technology can be used for diagnosing parts such as an engine, a power head, and a bearing of the working machine, and judging whether the parts have the trouble.
Under the normal condition, according to a predetermined rotating speed threshold, under the condition that the engine rotating speed detected in real time is out of speed and the out-of-speed value is greater than the preset rotating speed threshold, it is considered that the work machine may have a trouble of holding down the vehicle, and at the moment, the load and the torque of the work machine can be controlled by adjusting the electric proportional valve current, the oil supply pressure of a main pump motor, the main pump voltage and the like in the hydraulic system of the work machine, so that the trouble of holding down the vehicle is avoided. However, for the car holding-down fault caused by the problems of oil circuit blockage, air filter core blockage and the like of the operation machine, the occurrence of the car holding-down fault is difficult to avoid by adjusting the current of the electro proportional valve, the oil supply pressure of the main pump motor, the voltage of the main pump and the like, so that the speed and the torque of the operation machine can be continuously kept in an unmatched state, and the operation machine is easily damaged. Therefore, for the trouble of holding the car caused by the problems of the oil circuit blockage of the operation machinery, the blockage of the air filter element and the like, the trouble of holding the car can be avoided only by timely overhauling the operation machinery and eliminating the problems of the oil circuit blockage of the operation machinery, the blockage of the air filter element and the like. However, frequent maintenance of the working machine not only affects the work efficiency of the working machine, but also requires a large amount of labor and maintenance costs.
The traditional vehicle holding-down fault prediction method judges whether the vehicle holding-down fault occurs to the operation machine or not based on the real-time detection of the rotating speed of the engine, when the speed of the engine detected in real time is determined to drop and the speed dropping value is greater than a preset rotating speed threshold value, the vehicle holding-down fault possibly occurs to the operation machine, enough time is difficult to reserve for overhauling or controlling the operation machine, the timeliness is poor, and the limitation is strong.
Therefore, the invention provides a method for predicting a failure of a held vehicle. The method for predicting the car holding failure can predict whether the car holding failure of the operation machine occurs in advance, so that enough time can be reserved for overhauling or controlling the operation machine, the damage of the operation machine caused by the car holding failure is avoided, the usability of the operation machine is improved, the maintenance workload is reduced, and the maintenance cost is reduced.
Fig. 1 is a schematic flow chart of a car holding fault prediction method provided by the invention. The method for predicting the failure of the held car of the present invention is described below with reference to fig. 1. As shown in fig. 1, the method includes: step 101, acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period; wherein the ending time of the first time interval is earlier than the starting time of the second time interval; the power condition data includes: the hydraulic system return pressure, the main pump pressure, and the main pump current.
Specifically, the first period is earlier than the second period and the first period does not intersect the second period. According to the method for predicting the vehicle holding failure, whether the vehicle holding failure occurs to the operation machine in the second time period can be predicted based on the working condition data of the operation machine in the first time period, and the prediction result of the vehicle holding failure occurring to the operation machine in the second time period is obtained.
Alternatively, the end time of the first period may be the start time of the second period. The duration of the first period may be the same as the duration of the second period. For example: the first time period can be 00:00 to 23:59 of 1/2022, and the second time period can be 00:00 to 23:59 of 1/2/2022, and based on the method for predicting the holding back fault, whether the holding back fault occurs in the operating machinery within 00:00 to 23:59 of 1/2/2022 can be predicted based on the working condition data of the operating machinery within 00:00 to 23:59 of 1/2022, and the prediction result of the holding back fault occurs in the operating machinery within 00:00 to 23:59 of 1/2/2022 can be obtained.
The method and the device have the advantages that the power working condition data capable of describing the power matching condition of the engine in the working process of the working machine can be acquired to be used for predicting the failure of the vehicle-holding-down state.
The power condition data may include, but is not limited to, a return pressure of the hydraulic system, a main pump pressure, and a main pump current.
It can be understood that the power condition data includes various different types of power condition data, and the return oil pressure of the hydraulic system, the main pump pressure and the main pump current are three different types of power condition data respectively.
The rotational speed of the engine of the work machine and the operating range of the work machine during the first period of time may be continuously obtained based on a controller of the work machine. For example: the rotation speed of the engine of the work machine and the current operating range (current range) of the work machine may be acquired at every preset sampling period in the first period.
The power condition data of the work machine during the first period may be continuously obtained in various ways, such as: the method comprises the steps that a main pump current of a hydraulic system of the working machine at a current gear is obtained every other preset sampling period within a first time period based on a controller of the working machine; and the return oil pressure of the hydraulic system and the main pump pressure of the working machine at the current gear can be obtained at intervals of the preset sampling period in the first period based on various sensors.
After the rotational speed, the working gear and the power condition data of the engine of the working machine in the first time period are acquired, the rotational speed, the working gear and the power condition data of the engine of the working machine in the first time period can be directly used as target data.
Optionally, the sampling frequency of each sensor is different due to different types and types of the sensors for acquiring the power condition data of the working machine in the first period. In addition, because the working environment of the working machine is complex, the working machine can generate large amplitude vibration during working, so that the data acquired by each sensor has large noise, the signal-to-noise ratio is low, and the signal-to-noise ratio comprises a plurality of abnormal values and vacancy values. In order to improve the accuracy of the vehicle holding fault prediction, after the data of the rotating speed, the working gear and the power working condition of the engine of the working machine in the first time period are obtained, the data can be used as original data, and after the data processing is carried out on the original data, the original data after the data processing is used as target data.
The raw data can be processed based on mathematical statistics, linear interpolation, down-sampling and other manners. The specific data processing procedure is described by taking the example of data processing of the engine speed in the first period.
Fig. 2 is a data schematic diagram of the rotating speed of the engine which is not subjected to data processing in the first period in the method for predicting the failure of the car holding. As shown in fig. 2, the first time period is from 11/19/2019/08: 10:57 to 11/20/08: 10: 56/2019, and the engine speed that has not been subjected to data processing in the first time period has a large noise and has a plurality of abnormal values with large fluctuations.
After the abnormal value in the rotating speed of the engine which is not processed by data in the first period is identified by the mathematical statistics based method, the abnormal value can be replaced by a linear interpolation method.
After the abnormal value in the rotation speed of the engine which has not been subjected to the data processing in the first time period is replaced, the replaced abnormal value may be verified based on the prior knowledge, and in a case where the replaced abnormal value satisfies the verification, the replacement of the abnormal value is confirmed.
Fig. 3 is a data schematic diagram of the rotating speed of the engine after data processing in the first time period in the vehicle holding fault prediction method provided by the invention. As shown in fig. 3, the noise of the engine speed after data processing in the first period is small, and the engine speed after data processing in the first period may be used as the target data.
The sampling frequency of the engine speed, the working gear and the target working condition data can be unified.
The target data includes a correspondence relationship between the engine speed and the operating range of the work machine and the power condition data.
It should be noted that "first" and "second" in the embodiments of the present invention are used for distinguishing similar objects, and are not used for describing or indicating a specific order or sequence.
Specifically, before target data is input into the suppressing fault prediction model, and a prediction result of the suppressing fault of the working machine in a second time period output by the suppressing fault prediction model is obtained, the data of the rotating speed, the working gear and the power working condition of the engine of the sample working machine in a first sample time period can be obtained as sample data, whether the suppressing fault of the sample working machine occurs in the second sample time period is obtained as a sample label, and the suppressing fault prediction model is constructed based on the sample data and the sample label. Wherein the first sample period is earlier than the second sample period, and the first sample period does not intersect the second sample period.
Alternatively, 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.
It should be noted that the first sample period and the second sample period have a corresponding relationship with the first period and the second period, that is, the duration of the first period is the same as the duration of the first sample period, the duration of the second period is the same as the duration of the second sample period, and the duration of the interval between the first period and the second period is the same as the duration of the interval between the first sample period and the second sample period.
The sample work machine is a work machine in a normal operation state. The work machine described above is the same type and model as the sample work machine.
The sample data may be obtained by various methods, for example: the method comprises the steps that based on a controller of the sample working machine, the rotating speed of an engine of the sample working machine, the current working gear (current gear) of the sample working machine and the main pump current of a hydraulic system of the sample working machine under the current gear are obtained at intervals of a preset sampling period in a first sample period and are used as sample data; the return oil pressure of the hydraulic system and the main pump pressure of the sample working machine at the current gear can be obtained at intervals of a preset sampling period in the first sample period based on various sensors and used as sample data.
Whether the sample operation machine has a car holding fault in the second sample time period can be determined based on the prior data to serve as a sample label.
After the sample data and the sample label are obtained, a suppressed vehicle fault prediction model can be constructed based on the sample data and the sample label.
After the vehicle holding estimation prediction model is constructed, the target data can be input into the vehicle holding failure prediction model, and a prediction result of the vehicle holding failure of the working machine in the second time period output by the vehicle holding failure prediction model is obtained.
It should be noted that the prediction result may include that the vehicle holding fault occurs or does not occur in the work machine within the second time period; the prediction result may further include a probability and/or a risk level of the work machine having the stuck vehicle fault in the second time period; the prediction may further include a probability and/or a risk level of the work machine experiencing the stuck-at fault at the target time within the second time period. The prediction result is not particularly limited in the embodiment of the present invention.
The embodiment of the invention obtains the target data comprising the rotating speed of an engine of the working machine in a first period, a working gear, the oil return pressure of a hydraulic system, the pressure of a main pump and the current of the main pump, inputs the target data into a suppressed vehicle fault prediction model, obtains the prediction result of the suppressed vehicle fault of the working machine in a second period output by the suppressed vehicle fault prediction model, the ending time of the first period is earlier than the starting time of the second period, the suppressed vehicle fault prediction model is constructed based on the rotating speed of the engine of the sample working machine in the first sample period, the working gear, the oil return pressure of the hydraulic system, the pressure of the main pump and the current of the main pump, and whether the sample working machine has the suppressed vehicle fault in the second sample period, the ending time of the first sample period is earlier than the starting time of the second sample period, can predict the suppressed vehicle fault in advance, and can improve the practicability of the suppressed vehicle fault prediction, by predicting the trouble of the car being held back in advance, enough time can be reserved before the trouble of the car being held back occurs to overhaul and maintain the operation machine, the trouble of the car being held back can be effectively avoided, the usability of the operation machine can be improved, the maintenance workload can be reduced, and the maintenance cost can be reduced.
Based on the content of each embodiment, target data is input into the car holding fault prediction model, a prediction result output by the car holding fault prediction model is obtained, and the prediction result indicates that the working machine cannot have car holding faults in a second time period; the vehicle holding-down fault prediction model is used for obtaining first characteristic data corresponding to the target data, obtaining a first probability of the vehicle holding-down fault of the working machine in a second time interval based on the first characteristic data, and outputting a prediction result under the condition that the first probability is not greater than a first preset value.
Fig. 4 is a schematic structural diagram of a car holding fault prediction model in the car holding fault prediction method provided by the present invention. As shown in fig. 4, the vehicle holding fault prediction model includes: a first feature extraction layer and a first prediction layer.
Specifically, after the target data is obtained, the target data is input to a first feature extraction layer in the car holding fault prediction model, and first feature data corresponding to the target data output by the first feature extraction layer may be obtained.
The first feature extraction layer may be configured to perform first feature extraction on the target data, and acquire and output the first feature data.
After the first characteristic data is obtained, the first characteristic data may be input into a first prediction layer, and a prediction result output by the first prediction layer and indicating that the work machine does not have a stuck-behind fault in a second time period may be obtained.
It should be noted that before the first feature data is input into the first prediction layer in the car holding fault prediction model, the first prediction layer may be trained based on the sample data and the sample label, so as to obtain the trained first prediction layer.
Specifically, the first time of feature extraction is performed on the sample data, so that first sample feature data corresponding to the sample data can be obtained.
Optionally, the sample data may be input into the first feature extraction layer, and first sample feature data corresponding to the sample data output by the first feature extraction layer may be acquired.
Based on the priori knowledge and whether the sample operation machine has the car holding fault in the second sample period, a first sample probability of the sample operation machine having the car holding fault in the second sample period can be obtained, for example: and if the sample operation machine does not have the car holding fault in the second sample time period, the first sample probability is 0.
And determining the threshold range of each type of power working condition data when the car holding fault occurs and the contribution degree of each type of power working condition data to the car holding fault based on the priori knowledge, and taking the threshold range and the contribution degree as training parameters for training the first prediction layer.
Based on the training parameters, the first sample feature data and the first sample probability, the first prediction layer can be trained to obtain a trained first prediction layer.
After the trained first prediction layer is obtained, first feature data may be input into the trained first prediction layer.
The first prediction layer may obtain a first probability of the work machine having the stuck-car fault in the second time period based on the first characteristic data. If the first probability is not greater than the preset probability threshold, the first prediction layer may determine that the possibility that the operation machine has the car holding fault in the second time period is low, and the first prediction layer may output a prediction result indicating that the operation machine does not have the car holding fault in the second time period, so as to obtain the prediction result indicating that the operation machine does not have the car holding fault in the second time period, which is output by the car holding fault prediction model.
Optionally, the prediction result output by the vehicle holding fault prediction model may further include a first probability of the vehicle holding fault occurring in the work machine in the second time period.
According to the embodiment of the invention, the target data is input into the car holding fault prediction model, the car holding fault prediction model carries out first feature extraction on the target data to obtain the first probability of the car holding fault of the operation machine in the second time interval, and under the condition that the first probability is not larger than the first preset value, the prediction result indicating that the car holding fault of the operation machine cannot occur in the second time interval is output, so that the prediction result of the car holding fault can be obtained more efficiently and more accurately under the condition that the operation machine is in a normal state.
Based on the content of each embodiment, inputting the target data into the car holding fault prediction model, and obtaining a prediction result of the car holding fault of the working machine in the second time period output by the car holding fault prediction model, specifically including: inputting the target data into a car holding fault prediction model, and acquiring a prediction result output by the car holding fault prediction model, wherein the prediction result comprises a second probability of the car holding fault of the operation machine in a second time period; the vehicle holding-down fault prediction model is used for obtaining first characteristic data corresponding to target data, obtaining a first probability of the vehicle holding-down fault of the operation machine in a second time interval based on the first characteristic data, obtaining second characteristic data corresponding to the target data under the condition that the first probability is larger than a first preset value, and obtaining a second probability of the vehicle holding-down fault of the operation machine in the second time interval based on the second characteristic data.
As shown in fig. 4, the vehicle holding fault prediction model further includes: a second feature extraction layer and a second prediction layer.
Specifically, target data is input into a first feature extraction layer, and after first feature data corresponding to the target data output by the first feature extraction layer is obtained, the first feature data is input into a trained first prediction layer.
The first prediction layer may obtain a first probability of the work machine having the stuck-car fault in the second time period based on the first characteristic data. If the first probability is greater than the first preset value, the first prediction layer may determine that the possibility of the vehicle holding fault of the working machine is high in the second time period, and the first prediction layer may call the second feature extraction layer and input the target data into the second feature extraction layer.
The second feature extraction layer may perform second feature extraction on the target data, and obtain and output second feature data corresponding to the target data.
And inputting the second characteristic data into a second prediction layer, and obtaining a prediction result output by the second prediction layer, wherein the prediction result comprises the probability of the work machine generating the holding fault in a second time period.
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 label to obtain a trained second prediction layer.
Specifically, the second time of feature extraction is performed on the sample data, so that second sample feature data corresponding to the sample data can be obtained.
Optionally, the sample data may be input into a second feature extraction layer, and second sample feature data corresponding to the sample data output by the first feature extraction layer may be acquired.
The second sample probability of the car holding fault of the sample operation machine in the second sample time period can be obtained based on the priori knowledge and whether the car holding fault of the sample operation machine occurs in the second sample time period. The second sample probability may be the same as the first sample probability.
Based on the second sample feature data and the second sample probability, a second prediction layer can be trained, and the trained second prediction layer is obtained.
After the trained second prediction layer is obtained, second feature data may be input into the second prediction layer.
The second prediction layer may obtain, based on the second feature data, a second probability of the occurrence of the vehicle holding failure of the work machine in the second time period, as a prediction result of the occurrence of the vehicle holding failure of the work machine in the second time period, and may further obtain a prediction result output by the second prediction layer and including the occurrence of the vehicle holding failure of the work machine in the second time period.
The second probability may be an average probability of the work machine having the stuck vehicle fault in the second time period, for example: the probability of the vehicle holding fault of the working machine in the second time interval is 85 percent; the second probability may also be a probability of the occurrence of the holding fault of the work machine at the target time within the second time period, where a time interval between any two adjacent target times may be a preset time length. The second probability is not particularly limited in the embodiment of the present invention.
It should be noted that, the confidence interval of the second sample probability may also be obtained based on the priori knowledge and the time when the sample operation machine has a stuck-car fault in the second sample time period.
Accordingly, after the second prediction layer is trained based on the second sample feature data, the second sample probability, and the confidence interval of the second sample probability, the second feature data is input to the second prediction layer, and the second prediction layer may acquire the second probability and the confidence interval corresponding to the second probability based on the second feature data.
Fig. 5 is a data schematic diagram of a confidence interval corresponding to a second probability in the car holding fault prediction method provided by the invention. As shown in fig. 5, the second probability is 85% when the confidence interval is 0.5.
The embodiment of the invention inputs the target data into the suppressing fault prediction model, the suppressing fault prediction model carries out first feature extraction on the target data to obtain the first probability of the suppressing fault of the working machine in the second time interval, under the condition that the first probability is larger than the first preset value, the second feature data corresponding to the target data is obtained based on the target data, the second probability of the suppressing fault of the working machine in the second time interval is obtained based on the second feature data to be used as the prediction result of the suppressing fault of the working machine in the second time interval, the suppressing fault of the working machine in the second time interval can be further predicted under the condition that the probability of the suppressing fault of the working machine in the second time interval is predicted for the first time, particularly, the suppressing fault caused by the problems of oil circuit blockage, air filter core blockage and the like in the working machine can be predicted in advance, the method and the device can more visually acquire the prediction result of the vehicle holding-down fault of the operation machine in the second time period, can perform more targeted measures based on the prediction result, more effectively avoid the vehicle holding-down fault, reduce the maintenance workload and reduce the maintenance cost investment.
Based on the content of each embodiment, the suppressed vehicle fault prediction model is used for respectively performing feature extraction on each type of power working condition data in the target data based on the rotating speed and the working gear in the target data, and acquiring feature data corresponding to each type of power working condition data as first feature data.
Specifically, after the target data is input into the first feature extraction layer, the first feature extraction layer may perform feature extraction on each type of power condition data based on the rotation speed and the operating range of the engine in the target data, so that each type of power condition data may be quantized into feature data, and the feature data corresponding to each type of power condition data is acquired as the first feature data corresponding to the target data. For example: the first feature extraction layer may perform feature extraction on the rotation speed of the engine of the work machine in the target data, and acquire feature data corresponding to the rotation speed of the engine in the target data as first feature data.
Optionally, for any type of power condition data, the first feature extraction layer may perform feature extraction on the type of power condition data at each operating gear, and obtain feature data corresponding to the type of power condition data at each operating gear as feature data corresponding to the type of power condition data. For example: the first feature extraction layer can perform feature extraction on the rotating speed of the engine of the working machine in the first working gear in the target data, and obtain feature data corresponding to the rotating speed of the engine in the first working gear in the target data as feature data corresponding to the rotating speed of the engine in the target data.
The first feature extraction layer can extract features of any type of power condition data of the working machine in any working gear in the target data in the following mode, and specifically comprises the following steps: the first feature extraction layer can obtain a ratio of the type of power condition data under the working gear in the target data to a corresponding rotating speed of the engine, obtain the type of power condition data under the unit rotating speed of the working gear in a first period, perform feature extraction on the type of power condition data under the working gear based on the type of power condition data under the unit rotating speed of the working gear and the type of power condition data under the working gear in the first period by a numerical calculation method, quantize the type of power condition data under the unit rotating speed of the working gear and the type of power condition data under the working gear in the first period into feature data corresponding to the type of power condition data under the working gear, and use the feature data as the feature data corresponding to the type of power condition data.
Fig. 6 is a data schematic diagram of return oil pressure of a hydraulic system in target data in the method for predicting the failure of the held vehicle provided by the invention. Fig. 7 is a data schematic diagram of return oil pressure of the hydraulic system at a unit rotation speed in the target data in the vehicle holding fault prediction method provided by the invention. The first feature extraction layer may obtain a ratio between the oil return pressure of the hydraulic system in the target data and the rotation speed of the corresponding engine, and obtain the oil return pressure of the hydraulic system at a unit rotation speed in the target data.
The first feature extraction layer may quantize the oil return pressure of the hydraulic system at the unit rotation speed in the target data to feature data [0.0182,0.0184,0.0180,0.00006] corresponding to the oil return pressure of the hydraulic system, based on the oil return pressure of the hydraulic system at the unit rotation speed in the target data.
According to the method and the device for predicting the holding-down fault, the model for predicting the holding-down fault extracts the characteristics of each type of power working condition data in the target data respectively based on the rotating speed and the working gear of the engine of the working machine in the first time period in the target data, obtains the characteristic data corresponding to each type of power working condition data as the first characteristic data corresponding to the target data, can obtain the characteristics of the target data more accurately and efficiently, further can accurately infer the running state of the working machine in the first time period based on the characteristics of the target data, and provides a data basis for accurately obtaining the prediction result of the holding-down fault.
Based on the content of each embodiment, the car holding fault prediction model is used for acquiring a residual error and a decision coefficient of the target data as second feature data.
It can be appreciated that the sample work machine is in a normal operating state, and therefore the power system of the sample work machine satisfies the speed characteristic curve, and a regression model of the rotational speed of the engine of the sample work machine and the power condition data of the sample work machine in the first sample period can be obtained using a regression algorithm.
After obtaining the regression model, a second feature extraction layer may be constructed based on the regression model.
After the first prediction layer inputs the target data into the constructed second feature extraction layer, the second feature extraction layer may perform second feature extraction on the target data based on the target data and the regression model to obtain a residual error and a decision coefficient of the target data, which are used as second feature data corresponding to the target data, and may further obtain second feature data output by the second feature extraction layer.
Fig. 8 is a data schematic diagram of second characteristic data in the method for predicting a stuck vehicle fault according to the present invention. Fig. 8 (a) is a schematic diagram of the residual of the target data, and fig. 8 (b) is a schematic diagram of the determination coefficient of the target data. As shown in fig. 8, the large fluctuation points in the graphs (a) and (b) indicate that the deviation between the power behavior data of the working machine and the speed characteristic curve of the power system of the sample working machine is large at the fluctuation points, and the holding fault of the working machine may occur at the moment of the fluctuation points.
It should be noted that, the determination coefficient, which is a numerical feature representing the relationship between one random variable and a plurality of random variables, is used to reflect a statistical index indicating the reliability of the regression model for describing the variation of the dependent variable, and is generally denoted by the symbol "R".
Fig. 9 is a data schematic diagram of the probability of the vehicle holding fault of the working machine in the second time period in the vehicle holding fault prediction method provided by the present invention. As shown in fig. 9, the solid line represents an actual value of the rotation speed of the engine of the work machine in the second period, the dotted line represents a predicted value of the rotation speed of the engine of the work machine in the second period, and the predicted value represents a fluctuation point where a large fluctuation occurs, which indicates that the probability of the occurrence of the stuck-up failure of the work machine at the time of the fluctuation point is high.
The car holding fault prediction model in the embodiment of the invention obtains the residual error and the decision coefficient of the target data as the second characteristic data corresponding to the target data, so that the interpretability, the calculation efficiency and the accuracy of the car holding fault prediction model can be improved, the false alarm rate of the car holding fault prediction model is reduced, and the car holding fault can be predicted in advance more accurately and efficiently.
Based on the content of the foregoing embodiments, the predicting a result further includes: the second probability corresponds to a risk level.
Optionally, the second feature data is input into a trained second prediction layer, and the second prediction layer may obtain, based on the second feature data, a second probability of the work machine having the stuck-car fault in a second time period and a confidence interval of the second probability. And the second prediction layer can determine the risk level of the work machine with the stuck vehicle fault in the second time period based on the second probability and the confidence interval of the second probability.
Optionally, the second feature data is input into a trained second prediction layer, the second prediction layer may obtain a second probability of the vehicle holding fault of the work machine in a second time period based on the second feature data, and the second prediction layer may determine a risk level of the vehicle holding fault of the work machine in the second time period based on the second probability and a second preset value. For example: the second preset value may include 80%, 60%, 40%, and 20%, and 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 is determined but each level is medium low risk, and if the second probability is less than 20%, the risk level is determined to be low risk.
It should be noted that the risk level of the work machine with the stuck-car fault in the second time period may be an average risk level of the work machine with the stuck-car fault in the second time period, for example: the risk level of the work machine with the failure of the car holding in the second time interval is the medium-high risk; the risk level of the vehicle holding fault of the working machine in the second time period may also be the risk level of the vehicle holding fault of the working machine at the target time in the second time period, wherein the time interval between any two adjacent target times may be a preset time length. In the embodiment of the present invention, the risk level of the work machine having the stuck vehicle fault in the second time period is not specifically limited.
Based on the risk level of the car holding fault of the operation machine in the second acquired time period, specific measures can be taken to avoid the car holding fault of the operation machine, for example: and under the condition that the risk level of the work machine with the car holding fault is high risk in the second time period, the work machine needs to be stopped and overhauled, and whether the work machine is blocked by an oil path or not, and an air filter core is blocked or not is mainly detected.
According to the embodiment of the invention, after the second probability of the car holding fault of the operation machine in the second time period is obtained through the car holding fault prediction model based on the second characteristic data, the risk level of the car holding fault of the operation machine in the second time period is obtained based on the second probability, so that the prediction result comprising the risk level is output, the prediction result of the car holding fault of the operation machine in the second time period can be displayed more flexibly and more intuitively, more targeted measures can be carried out based on the risk level included by the prediction result, the occurrence of the car holding fault is avoided, the maintenance workload can be reduced, and the maintenance cost investment can be reduced.
Based on the content of each embodiment, whether the car holding fault occurs to the sample operation machine in the second sample time period is determined based on the time when the car holding fault occurs to the sample operation machine in the second sample time period, and under the condition that the car holding fault does not occur to the sample operation machine in the second sample time period, the time when the car holding fault occurs to the sample operation machine in the second sample time period is empty; a second probability comprising: and the probability of the occurrence of the holding fault of the working machine at the target moment in the second time period.
Specifically, based on the time and prior knowledge of the occurrence of the car holding fault of the sample operation machine in the second sample period, the sample probability of the occurrence of the car holding fault of the sample time in the second sample period can be obtained, wherein the time intervals of any two adjacent sample times are equal. For example: if the car holding fault does not occur at a certain sample moment, the probability of the car holding fault occurring in the sample operation machine at the sample moment is 0; and if the car holding fault occurs at a certain sample moment, the probability of the car holding fault occurring in the sample operation machine at the sample moment is 100%.
And training the second prediction layer based on the second sample characteristic data and the sample probability of the car holding fault at the sample moment in the second sample time period to obtain the trained second prediction layer.
And inputting the second feature data into the trained second prediction layer, so as to obtain a second probability output by the second prediction layer, where the second probability may include a probability of the operation machine being subjected to the holding fault at a target time within a second time period, and a time interval between any two adjacent target times may be a preset time duration. For example: the probability of the vehicle holding fault of the working machine at the first target moment in the second time interval is 1%, the probability of the vehicle holding fault of the working machine at the second target moment is 2%, …, and the probability of the vehicle holding fault of the working machine at the target moment in the Nth target time interval is 85%.
The second prediction layer in the embodiment of the invention obtains the second probability of the vehicle holding down fault of the operation machine in the second time period based on the second characteristic data, the second probability comprises the probability of the vehicle holding down fault of the operation machine at the target moment in the second time period, the prediction result of the vehicle holding down fault of the operation machine in the second time period can be more accurately and more intuitively obtained, particularly, the vehicle holding down fault caused by the problems of oil circuit blockage, air filter core blockage and the like in the operation machine can be predicted in advance, more targeted measures can be taken based on the prediction result, and the vehicle holding down fault can be more effectively avoided.
Fig. 10 is a schematic structural diagram of a car holding fault prediction device provided by the invention. The car hold-down fault prediction device provided by the invention is described below with reference to fig. 10, and the car hold-down fault prediction device described below and the car hold-down fault prediction method provided by the invention described above may be referred to correspondingly. As shown in fig. 10, the apparatus includes: a data acquisition module 1001 and a failure prediction module 1002.
The data acquisition module 1001 is configured to acquire target data, where the target data includes a rotational speed, a work gear, and power condition data of an engine of the work machine during a first time period.
And the fault prediction module 1002 is configured to input the target data into the vehicle holding fault prediction model, and obtain a prediction result of the vehicle holding fault of the work machine in a second time period output by the vehicle holding fault prediction model.
Wherein the ending time of the first time interval is earlier than the starting time of the second time interval; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the method comprises the steps that a car holding fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of an engine of a sample operation machine in a first sample time period and whether the sample operation machine has car holding faults in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
Specifically, the data acquisition module 1001 and the failure prediction module 1002 are electrically connected.
The data acquisition module 1001 may continuously acquire the power condition data of the work machine in the first period of time in various manners, such as: the method comprises the steps that a main pump current of a hydraulic system of the working machine at a current gear is obtained every other preset sampling period within a first time period based on a controller of the working machine; and the return oil pressure of the hydraulic system and the main pump pressure of the working machine at the current gear can be obtained at intervals of the preset sampling period in the first period based on various sensors.
After the data acquisition module 1001 acquires the rotational speed, the operating range, and the power condition data of the engine of the work machine in the first period, the rotational speed, the operating range, and the power condition data of the engine of the work machine in the first period may be directly used as the target data.
In order to improve the accuracy of the vehicle holding fault prediction, after the data acquisition module 1001 acquires the data of the rotation speed, the working gear and the power condition of the engine of the work machine in the first time period, the data may be used as original data, and after the data processing is performed on the original data, the original data after the data processing is used as target data.
The fault prediction module 1002 may input the target data into the hold-down fault prediction model, and obtain a prediction result of the work machine having the hold-down fault in the second time period output by the hold-down fault prediction model.
Optionally, the fault prediction module 1002 may be specifically configured to input the target data into the hold-down fault prediction model, and obtain a prediction result output by the hold-down fault prediction model, where the prediction result indicates that the work machine does not have a hold-down fault in the second time period; the vehicle holding-down fault prediction model is used for obtaining first characteristic data corresponding to the target data, obtaining a first probability of the vehicle holding-down fault of the working machine in a second time interval based on the first characteristic data, and outputting a prediction result under the condition that the first probability is not greater than a first preset value.
Optionally, the fault prediction module 1002 may be specifically configured to input the target data into the hold-down fault prediction model, and obtain a prediction result output by the hold-down fault prediction model, where the prediction result includes a second probability that the work machine has a hold-down fault in a second time period; the vehicle holding-down fault prediction model is used for obtaining first characteristic data corresponding to target data, obtaining a first probability of the vehicle holding-down fault of the operation machine in a second time interval based on the first characteristic data, obtaining second characteristic data corresponding to the target data under the condition that the first probability is larger than a first preset value, and obtaining a second probability of the vehicle holding-down fault of the operation machine in the second time interval based on the second characteristic data.
The embodiment of the invention obtains the target data comprising the rotating speed of an engine of the working machine in a first period, a working gear, the oil return pressure of a hydraulic system, the pressure of a main pump and the current of the main pump, inputs the target data into a suppressed vehicle fault prediction model, obtains the prediction result of the suppressed vehicle fault of the working machine in a second period output by the suppressed vehicle fault prediction model, the ending time of the first period is earlier than the starting time of the second period, the suppressed vehicle fault prediction model is constructed based on the rotating speed of the engine of the sample working machine in the first sample period, the working gear, the oil return pressure of the hydraulic system, the pressure of the main pump and the current of the main pump, and whether the sample working machine has the suppressed vehicle fault in the second sample period, the ending time of the first sample period is earlier than the starting time of the second sample period, can predict the suppressed vehicle fault in advance, and can improve the practicability of the suppressed vehicle fault prediction, by predicting the trouble of the car being held back in advance, enough time can be reserved before the trouble of the car being held back occurs to overhaul and maintain the operation machine, the trouble of the car being held back can be effectively avoided, the usability of the operation machine can be improved, the maintenance workload can be reduced, and the maintenance cost can be reduced.
Based on the content of the foregoing embodiments, a work machine includes the aforementioned sticking trouble prediction device.
Specifically, the work machine may include a piling machine, an excavator, an automobile, and the like. The piling machinery refers to a working machine for drilling, piling and sinking piles in various pile foundation constructions, such as a pile driver, a vibration pile sinking machine, a cast-in-place pile drilling machine and a rotary drilling rig.
The operation machine comprises the device for predicting the failure of the suppressed vehicle, the failure of the suppressed vehicle can be predicted in advance, particularly the failure of the suppressed vehicle caused by the problems of oil circuit blockage, air filter core blockage and the like in the operation machine can be predicted in advance, and therefore the practicability of the prediction of the failure of the suppressed vehicle can be improved. The structure and the specific working process of the car holding fault prediction device can be referred to the contents of the above embodiments, and are not described in detail in the embodiments of the present invention.
The embodiment of the invention obtains the target data comprising the rotating speed of an engine of the working machine in a first period, a working gear, the oil return pressure of a hydraulic system, the pressure of a main pump and the current of the main pump, inputs the target data into a suppressed vehicle fault prediction model, obtains the prediction result of the suppressed vehicle fault of the working machine in a second period output by the suppressed vehicle fault prediction model, the ending time of the first period is earlier than the starting time of the second period, the suppressed vehicle fault prediction model is constructed based on the rotating speed of the engine of the sample working machine in the first sample period, the working gear, the oil return pressure of the hydraulic system, the pressure of the main pump and the current of the main pump, and whether the sample working machine has the suppressed vehicle fault in the second sample period, the ending time of the first sample period is earlier than the starting time of the second sample period, can predict the suppressed vehicle fault in advance, and can improve the practicability of the suppressed vehicle fault prediction, by predicting the trouble of the car being held back in advance, enough time can be reserved before the trouble of the car being held back occurs to overhaul and maintain the operation machine, the trouble of the car being held back can be effectively avoided, the usability of the operation machine can be improved, the maintenance workload can be reduced, and the maintenance cost can be reduced.
Fig. 11 illustrates a physical structure diagram of an electronic device, and as shown in fig. 11, 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 via the communication bus 1140. The processor 1110 may invoke logic instructions in the memory 1130 to perform a hold fault prediction method comprising: acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period; inputting the target data into a car holding fault prediction model, and acquiring a prediction result of the car holding fault of the operation machine in a second time period output by the car holding fault prediction model; wherein the ending time of the first time interval is earlier than the starting time of the second time interval; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the method comprises the steps that a car holding fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of an engine of a sample operation machine in a first sample time period and whether the sample operation machine has car holding faults in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
In addition, the logic instructions in the memory 1130 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, where the computer program product includes a computer program, the computer program may be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, a computer can execute the method for predicting a stuck vehicle fault provided by the above methods, where the method includes: acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period; inputting the target data into a car holding fault prediction model, and acquiring a prediction result of the car holding fault of the operation machine in a second time period output by the car holding fault prediction model; wherein the ending time of the first time interval is earlier than the starting time of the second time interval; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the method comprises the steps that a car holding fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of an engine of a sample operation machine in a first sample time period and whether the sample operation machine has car holding faults in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, is implemented to perform the method for predicting a stuck vehicle fault provided by the above methods, the method including: acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period; inputting the target data into a car holding fault prediction model, and acquiring a prediction result of the car holding fault of the operation machine in a second time period output by the car holding fault prediction model; wherein the ending time of the first time interval is earlier than the starting time of the second time interval; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the method comprises the steps that a car holding fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of an engine of a sample operation machine in a first sample time period and whether the sample operation machine has car holding faults in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A vehicle holding fault prediction method is characterized by comprising the following steps:
acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period;
inputting the target data into a car holding fault prediction model, and obtaining a prediction result of the car holding fault of the working machine in a second time period output by the car holding fault prediction model;
wherein an end time of the first time period is earlier than a start time of the second time period; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the vehicle holding-down fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of the engine of the sample operation machine in a first sample time period and whether the vehicle holding-down fault occurs to the sample operation machine in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
2. The method for predicting a hold-down fault according to claim 1, wherein the step of inputting the target data into a hold-down fault prediction model to obtain a prediction result of the work machine having the hold-down fault in a second time period output by the hold-down fault prediction model specifically comprises:
inputting the target data into the car holding fault prediction model, and obtaining the prediction result output by the car holding fault prediction model, wherein the prediction result indicates that the working machine cannot have car holding faults in the second time period;
the vehicle holding-down fault prediction model is used for acquiring first characteristic data corresponding to the target data, acquiring a first probability of vehicle holding-down fault of the working machine in the second time interval based on the first characteristic data, and outputting the prediction result when the first probability is not greater than a first preset value.
3. The method for predicting a hold-down fault according to claim 1, wherein the step of inputting the target data into a hold-down fault prediction model to obtain a prediction result of the work machine having the hold-down fault in a second time period output by the hold-down fault prediction model specifically comprises:
inputting the target data into the car holding fault prediction model, and obtaining the prediction result output by the car holding fault prediction model, wherein the prediction result comprises a second probability of the car holding fault of the working machine in the second time period;
the vehicle holding back fault prediction model is used for acquiring first feature data corresponding to the target data, acquiring a first probability of the vehicle holding back fault of the working machine in the second time period based on the first feature data, acquiring second feature data corresponding to the target data under the condition that the first probability is larger than a first preset value, and acquiring a second probability of the vehicle holding back fault of the working machine in the second time period based on the second feature data.
4. The vehicle holding failure prediction method according to claim 2, wherein the vehicle holding failure prediction model is configured to perform feature extraction on each type of power operating condition data in the target data respectively based on the rotation 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.
5. The car holding fault prediction method according to claim 3, wherein the car holding fault prediction model is used for obtaining a residual error and a decision coefficient of the target data as the second feature data.
6. The method for predicting a car holding fault according to claim 3, wherein the prediction result further comprises: the risk level corresponding to the second probability.
7. The hold-down fault prediction method according to claim 3, wherein whether the sample work machine has a hold-down fault in the second sample period is determined based on a time when the sample work machine has the hold-down fault in the second sample period;
the second probability comprises: and the probability of the occurrence of the holding fault of the working machine at the target moment in the second time interval.
8. A car holding failure prediction device is characterized by comprising:
the data acquisition module is used for acquiring target data, wherein the target data comprises the rotating speed, the working gear and the power working condition data of an engine of the working machine in a first time period;
the fault prediction module is used for inputting the target data into a vehicle holding fault prediction model and acquiring a prediction result of the vehicle holding fault of the operation machine in a second time period output by the vehicle holding fault prediction model;
wherein an end time of the first time period is earlier than a start time of the second time period; the power condition data includes: the oil return pressure of the hydraulic system, the main pump pressure and the main pump current; the vehicle holding-down fault prediction model is constructed based on the rotating speed, the working gear and the power working condition data of the engine of the sample operation machine in a first sample time period and whether the vehicle holding-down fault occurs to the sample operation machine in a second sample time period; the end time of the first sample period is earlier than the start time of the second sample period.
9. A work machine, comprising: the hold-down fault prediction device of claim 8.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of suppressing a vehicle fault according to any of claims 1 to 7 when executing the program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210152033.2A CN114418239A (en) | 2022-02-18 | 2022-02-18 | Method and device for predicting failure of held vehicle and operation machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210152033.2A CN114418239A (en) | 2022-02-18 | 2022-02-18 | Method and device for predicting failure of held vehicle and operation machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114418239A true CN114418239A (en) | 2022-04-29 |
Family
ID=81260811
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210152033.2A Pending CN114418239A (en) | 2022-02-18 | 2022-02-18 | Method and device for predicting failure of held vehicle and operation machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114418239A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101540009A (en) * | 2008-03-17 | 2009-09-23 | 大叶大学 | Method for predicting facility and equipment failure |
WO2019062462A1 (en) * | 2017-09-30 | 2019-04-04 | Oppo广东移动通信有限公司 | Application control method and apparatus, storage medium and electronic device |
CN112816898A (en) * | 2021-01-26 | 2021-05-18 | 三一重工股份有限公司 | Battery failure prediction method and device, electronic equipment and storage medium |
CN112906969A (en) * | 2021-03-01 | 2021-06-04 | 三一重工股份有限公司 | Engine fault prediction method, engine fault prediction device, electronic equipment and storage medium |
CN112924205A (en) * | 2021-01-27 | 2021-06-08 | 上海三一重机股份有限公司 | Method and device for diagnosing faults of working machine, working machine and electronic equipment |
-
2022
- 2022-02-18 CN CN202210152033.2A patent/CN114418239A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101540009A (en) * | 2008-03-17 | 2009-09-23 | 大叶大学 | Method for predicting facility and equipment failure |
WO2019062462A1 (en) * | 2017-09-30 | 2019-04-04 | Oppo广东移动通信有限公司 | Application control method and apparatus, storage medium and electronic device |
CN112816898A (en) * | 2021-01-26 | 2021-05-18 | 三一重工股份有限公司 | Battery failure prediction method and device, electronic equipment and storage medium |
CN112924205A (en) * | 2021-01-27 | 2021-06-08 | 上海三一重机股份有限公司 | Method and device for diagnosing faults of working machine, working machine and electronic equipment |
CN112906969A (en) * | 2021-03-01 | 2021-06-04 | 三一重工股份有限公司 | Engine fault prediction method, engine fault prediction device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2011252963B2 (en) | Predictive analysis for remote machine monitoring | |
CN108181105B (en) | Rolling bearing fault pre-diagnosis method and system based on logistic regression and J divergence | |
CN109083756B (en) | Engine air inlet fault detection method and device | |
KR102206737B1 (en) | Method and system for fault diagnosis of pump-turbines based on machine learning | |
CN112254972B (en) | Excavator oil temperature early warning method and device, server and excavator | |
CN115712268A (en) | Fault early warning system for automatic electronic product auxiliary material laminating device | |
CN112975983B (en) | Method and device for correcting boom of working machine | |
KR20210031179A (en) | System for predicting engine failure using big data | |
CN114323664A (en) | Method for detecting abnormal gas vibration of gas turbine | |
CN116665421A (en) | Early warning processing method and device for mechanical equipment and computer readable storage medium | |
US20110153035A1 (en) | Sensor Failure Detection System And Method | |
CN114418239A (en) | Method and device for predicting failure of held vehicle and operation machine | |
CN112964470A (en) | Method for detecting early failure of rolling bearing based on bearing health index | |
CN117435883A (en) | Method and system for predicting equipment faults based on digital twinning | |
WO2023160300A1 (en) | Structural part remaining service life prediction method and device, and operation machine | |
CN113955149B (en) | Health diagnosis method and device for motor system | |
CN111766514A (en) | Data analysis method for equipment detection points | |
CN114322446B (en) | Cooling system fault early warning method and device, cooling system and working machine | |
CN114418238A (en) | Oil temperature abnormity prediction method and device and working machine | |
CN114578269A (en) | Motor rotor winding turn-to-turn short circuit detection system and method | |
CN111439223A (en) | Method and device for identifying lifting of car hopper | |
CN117725513B (en) | AUV propeller real-time reliability evaluation system and method | |
AU2015200309B2 (en) | Predicting failure of a mining machine | |
CN117469152B (en) | Fluid pump abnormality detection method, fluid pump abnormality detection device, electronic device, and storage medium | |
CN112326255B (en) | Engine remote health monitoring system and monitoring method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |