A method, device, system and medium for handling oil pump failure

Abstract

The present application provides a method, device, system and medium for handling oil pump failures. By obtaining the operating parameters of the oil pump and identifying and processing the operating parameters, the operating condition characteristic parameters in the operating parameters are obtained; the operating condition characteristic parameters are analyzed and processed using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump; the fault characteristic parameters corresponding to the current operating condition are obtained from the operating parameters, and the fault characteristic parameters are analyzed and processed using a preconfigured two-stage BP neural network model to obtain the current fault of the oil pump and the type of fault, so as to perform corresponding handling measures on the fault according to the type of fault. The method provided by the present application can improve the efficiency and accuracy of the identification and processing of oil pump faults.

Description

Technical Field

[0001] The present application relates to the technical field of equipment fault diagnosis, and in particular to a method, device, system and medium for processing an oil pump fault. Background Art

[0002] Pipeline transportation is the preferred mode of oil transportation because of its economic efficiency, safety and convenience. The oil pump, as the "heart" of pipeline transportation, has complex mechanical structure, harsh working environment, and frequent debugging, which leads to frequent sudden failures of the oil pump. Centrifugal oil pumps are the most common oil pumps, and the failure forms are even more diverse, such as impeller wear, bearing wear, etc. When a fault is not discovered in time, it is very easy to cause the oil pump unit to shut down, the pipeline to stop transport, and even a series of safety accidents such as fire and explosion. Therefore, timely diagnosis of oil pump failures is very important for pipeline transportation.

[0003] In the prior art, the working condition and fault type of the oil pump are mainly detected at the same time. Usually, relevant technicians are required to manually analyze and integrate a large amount of operating data of the oil pump to form an oil pump fault information database, and the fault information database needs to be updated regularly by technicians. Based on this, when the oil pump is in an abnormal operating state, the abnormal state information is input into the fault information database for search and comparison to determine the corresponding working condition and fault type, and then execute the corresponding treatment measures.

[0004] However, the detection method of the oil pump in the prior art can only detect the failure of the oil pump when the oil pump is in an obviously abnormal operating state, which makes the oil pump problem not discovered in time and even causes a series of safety problems; in addition, with the accumulation of time, the data in the oil pump fault information database will gradually increase, and the oil pump operating parameters are varied, which makes the retrieval time-consuming, which makes the oil pump fault handling efficiency low; furthermore, the value ranges of the operating parameters corresponding to the oil pump fault and working condition are not much different, which makes the retrieval results inaccurate. Summary of the invention

[0005] The present application provides a method, device, system and medium for processing an oil pump failure, so as to solve the problem that the fault identification and processing in the prior art is not accurate enough and the efficiency is low.

[0006] In a first aspect, the present application provides a method for handling an oil pump failure, comprising:

[0007] Acquiring the operating parameters of the oil pump, and performing identification processing on the operating parameters to obtain the operating condition characteristic parameters in the operating parameters;

[0008] Analyzing and processing the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump;

[0009] Fault characteristic parameters corresponding to the current operating condition are obtained from the operating parameters, and the fault characteristic parameters are analyzed and processed using the preconfigured two-stage BP neural network model to obtain the current fault of the oil pump and the type of the fault, so as to perform corresponding processing measures on the fault according to the type of the fault.

[0010] In an optional specific implementation, the analyzing and processing the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump includes:

[0011] Using the preconfigured two-stage BP neural network model to process the inlet pressure and the outlet pressure in the operating condition characteristic parameters, and obtaining an operating condition mode output vector;

[0012] The matching degree between the working condition mode output vector and the pre-stored working condition ideal mode output vector is calculated, and the working condition corresponding to the working condition ideal mode output vector with the highest matching degree is used as the current operating condition of the oil pump.

[0013] In an optional specific implementation manner, the acquiring of the fault characteristic parameters corresponding to the current operating condition from the operating parameters, and the use of the preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters, to acquire the current fault of the oil pump and the type of the fault, and to perform corresponding processing measures on the fault according to the type of the fault, includes:

[0014] Acquire fault characteristic parameters corresponding to the current operating condition from the operating parameters, the fault characteristic parameters including: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, and oil seal differential pressure;

[0015] Analyzing and processing the fault characteristic parameters using the preconfigured two-stage BP neural network model to obtain a fault mode output vector;

[0016] Calculating the matching degree between the fault mode output vector and the pre-stored fault ideal mode output vector, and taking the fault corresponding to the fault ideal mode output vector with the highest matching degree as the current fault of the oil pump;

[0017] The type of fault corresponding to the fault is obtained from a pre-stored fault type database, and the processing measure corresponding to the type of fault is obtained, so as to execute the corresponding processing measure for the fault.

[0018] In an optional specific implementation, the preconfigured two-stage BP neural network model includes:

[0019] Acquire a historical operating parameter data set of the oil pump, and perform normalization processing on the historical operating parameter data set to obtain a data set to be trained;

[0020] Inputting the training data set in the to-be-trained data set into the initial two-stage BP neural network model to obtain a trained two-stage BP neural network model;

[0021] Using the test data set in the training data set to test the trained two-stage BP neural network model to obtain a test result, and determine whether the test result is greater than or equal to a preset calibration value;

[0022] If yes, the trained two-stage BP neural network model is used as the preconfigured two-stage BP neural network model.

[0023] In an optional specific implementation, the method further includes:

[0024] If the test result is less than the preset calibration value, the training parameters in the trained two-stage BP neural network model are adjusted.

[0025] In a second aspect, the present application provides a device for processing an oil pump failure, comprising:

[0026] An acquisition module, used to acquire the operating parameters of the oil delivery pump, and perform identification processing on the operating parameters to acquire the operating condition characteristic parameters in the operating parameters;

[0027] A processing module, used to analyze and process the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump;

[0028] The processing module is also used to obtain fault characteristic parameters corresponding to the current operating conditions from the operating parameters, and use the preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters to obtain the current fault of the oil pump and the type of the fault, so as to perform corresponding processing measures on the fault according to the type of the fault.

[0029] In an optional specific implementation, the processing module is specifically used to:

[0030] Using the preconfigured two-stage BP neural network model to process the inlet pressure and the outlet pressure in the operating condition characteristic parameters, and obtaining an operating condition mode output vector;

[0031] The matching degree between the working condition mode output vector and the pre-stored working condition ideal mode output vector is calculated, and the working condition corresponding to the working condition ideal mode output vector with the highest matching degree is used as the current operating condition of the oil pump.

[0032] In an optional specific implementation, the processing module is specifically used to:

[0033] Acquire fault characteristic parameters corresponding to the current operating condition from the operating parameters, the fault characteristic parameters including: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, and oil seal differential pressure;

[0034] Analyzing and processing the fault characteristic parameters using the preconfigured two-stage BP neural network model to obtain a fault mode output vector;

[0035] Calculating the matching degree between the fault mode output vector and the pre-stored fault ideal mode output vector, and taking the fault corresponding to the fault ideal mode output vector with the highest matching degree as the current fault of the oil pump;

[0036] The type of fault corresponding to the fault is obtained from a pre-stored fault type database, and the processing measures corresponding to the type of fault are obtained.

[0037] In an optional specific implementation, the processing module is further used to:

[0038] Acquire a historical operating parameter data set of the oil pump, and perform normalization processing on the historical operating parameter data set to obtain a data set to be trained;

[0039] Inputting the training data set in the to-be-trained data set into the initial two-stage BP neural network model to obtain a trained two-stage BP neural network model;

[0040] Using the test data set in the training data set to test the trained two-stage BP neural network model to obtain a test result, and determine whether the test result is greater than or equal to a preset calibration value;

[0041] If yes, the trained two-stage BP neural network model is used as the preconfigured two-stage BP neural network model.

[0042] In an optional specific implementation, the processing module is further used to:

[0043] If the test result is less than the preset calibration value, the training parameters in the trained two-stage BP neural network model are adjusted.

[0044] In a third aspect, the present application provides a server, the server comprising: a processor, and a memory communicatively connected to the processor;

[0045] The memory stores computer-executable instructions;

[0046] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any of the preceding items.

[0047] In a fourth aspect, the present application provides a system for processing an oil pump failure, the processing system comprising: a server and an oil pump;

[0048] Among them, the processing device is carried or installed in the server, and the processing device is used to execute the method described in the previous item to process the operating parameters of the oil pump in real time or periodically to determine the current fault of the oil pump and the type of the fault, and perform corresponding processing measures on the fault according to the type of the fault.

[0049] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method described in any of the preceding items is implemented.

[0050] The present application provides a method, device, system and medium for handling oil pump faults, by obtaining the operating parameters of the oil pump, identifying and processing the operating parameters, and obtaining the operating condition characteristic parameters in the operating parameters; using a preconfigured two-stage BP neural network model to analyze and process the operating condition characteristic parameters, and obtaining the current operating condition of the oil pump; obtaining fault characteristic parameters corresponding to the current operating condition from the operating parameters, and using the preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters, and obtaining the current fault of the oil pump and the type of the fault, so as to perform corresponding handling measures on the fault according to the type of the fault. By utilizing the processing method provided in the present application, the operating condition type and fault type of the oil pump are classified and identified, which can avoid inaccurate identification when the operating condition type and fault type are highly similar. In addition, by analyzing the operating parameters of the oil pump, the operating condition characteristic parameters and fault characteristic parameters with a high correlation with the operating condition type and fault type are determined. Based on the operating condition characteristic parameters, the operating condition type of the oil pump is first determined, and then the fault of the oil pump and the fault type are determined based on the fault characteristic parameters under the working condition, thereby reducing the amount of data to be processed and improving data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0052] Figure 1 A schematic diagram of a method for handling oil pump failure provided in this application:

[0053] Figure 2 A schematic diagram of a method for handling an oil pump failure provided in the present application;

[0054] Figure 3 A schematic diagram of a method for handling an oil pump failure provided in the present application;

[0055] Figure 4 A schematic diagram of the structure of a device for processing oil pump failure provided in the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments made by ordinary technicians in this field under the enlightenment of the embodiments belong to the scope of protection of the present application.

[0057] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0058] Pipeline transportation is the preferred mode of oil transportation for its economic efficiency, safety and convenience. The oil pump, as the "heart" of pipeline transportation, has complex mechanical structure, harsh working environment, and frequent debugging, which leads to frequent sudden failures of the oil pump. Centrifugal oil pumps are the most common oil pumps, and the failure forms are even more diverse, such as impeller wear, bearing wear, unit rotor imbalance, oil film vortex, etc. Fault diagnosis research on key components of oil pumps, timely detection of oil pump unit failures, prevention of oil pump shutdown, pipeline shutdown, and a series of safety accidents such as fire and explosion, thereby reducing or eliminating the impact of failures and improving their operating efficiency, has become a hot topic of concern for technicians in this field.

[0059] In the prior art, the detection of failures in key components of oil pumps is mainly carried out by relevant technicians manually retrieving the current working condition and failure type of the oil pump based on the previously established failure information database, and performing corresponding processing according to the identification and processing results, such as repair or replacement of parts.

[0060] However, in order to prevent the oil pump from malfunctioning, technicians in the prior art need to collect the operating parameters of the oil pump once within a preset time interval and match the operating parameters with a pre-established fault information database to determine whether a fault has occurred. If a fault has occurred, corresponding processing operations are performed according to the fault, and the oil pump cannot be detected in real time. In addition, due to the wide variety of operating parameters of the oil pump and the huge amount of data in the pre-established fault information database, the processing efficiency of the oil pump fault is not high, and it is easy to confuse the fault type under various working conditions, which leads to inaccurate processing results.

[0061] Based on the above technical problems, the technical concept of the present application is to realize a method for processing oil pump failure in real time with high identification accuracy and high processing efficiency.

[0062] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0063] Figure 1 A schematic diagram of a method for handling an oil pump failure provided in this application is shown in FIG. Figure 1 As shown, the method includes:

[0064] Step 101: Acquire the operating parameters of the oil delivery pump, perform identification processing on the operating parameters, and acquire the operating condition characteristic parameters in the operating parameters.

[0065] In this embodiment, the operating parameters of the oil pump can be collected in real time or periodically to prevent unpredictable consequences caused by a failure of the oil pump. Optionally, the operating parameters of the oil pump are collected using a supervisory control and data acquisition system (SCADA), and at least 20 operating parameters are collected, such as the operating status, which can be obtained by parameters such as inlet pressure, outlet pressure, motor current, motor stator temperature, bearing temperature (motor, pump), housing temperature, vibration (pump) drive end and non-drive end, and oil seal differential pressure.

[0066] In order to reduce the complexity of processing and improve the efficiency of fault handling, it is necessary to perform parameter optimization processing on the obtained operating parameters. Optionally, characteristic parameters related to the operating condition type are first selected from the operating parameters of the oil pump to identify the current operating condition of the oil pump.

[0067] Step 102: Analyze and process the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump.

[0068] In this embodiment, in order to accurately and efficiently handle the fault of the oil pump, a two-stage BP neural network model is pre-configured. The two-stage BP neural network model is used to implement hierarchical processing of the working conditions and faults of the oil pump, that is, first identify the current operating conditions of the oil pump, and then identify the fault of the oil pump, that is, the type of fault, but this embodiment is not limited to this neural network model.

[0069] Optionally, the inlet pressure and outlet pressure of the oil pump are identified from the current operating parameters of the oil pump, the operating condition characteristic parameters are input into a preconfigured BP neural network model for identification and processing, and an operating condition mode output vector related to the type of operating condition is obtained. The matching degree of the operating condition mode output vector and the operating condition ideal mode output vector is calculated, and then the operating condition ideal mode output vector with a high matching degree is selected as the current operating condition of the oil pump.

[0070] Step 103: Obtain fault characteristic parameters corresponding to the current operating conditions from the operating parameters, and use a preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters to obtain the current fault of the oil pump and the type of the fault, so as to perform corresponding processing measures on the fault according to the type of the fault.

[0071] In this embodiment, after identifying the current operating condition of the oil pump, the fault of the oil pump and the type of fault will continue to be identified and processed. Optionally, fault characteristic parameters corresponding to the current operating condition are identified from the acquired operating parameters of the oil pump, such as: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, oil seal differential pressure and other parameters. These fault characteristic parameters are input into the two-stage BP neural network model for analysis and processing, and the fault mode output vector corresponding to the fault characteristic parameters is obtained. Similarly, the fault mode vector and the ideal fault mode vector are matched and calculated, and the fault ideal mode output vector with the largest matching degree is used as the current fault of the oil pump.

[0072] Then, the fault type corresponding to the current fault of the oil pump is searched in the pre-established fault type database, and the treatment measures corresponding to the fault type are obtained, such as replacement of parts or shutdown treatment.

[0073] Figure 2 The schematic diagram of the process of a method for processing an oil pump failure provided in this application is as follows. In summary, the principle of analyzing and processing an oil pump failure using a two-stage BP neural network model is as follows: Figure 2 As shown, Figure 2 201 and 202 respectively represent the operating condition identification stage and fault identification stage of the oil pump using a two-stage BP neural network.

[0074] In 201, the operating parameters 2001 are obtained, and after the current operating parameters are identified and processed, the operating condition characteristic parameters 2002, such as the inlet pressure and the outlet pressure, etc., can be obtained, and the obtained operating condition characteristic parameters 2002 are input into the two-stage BP neural network model 2003 for analysis and processing, and the current operating condition mode output vector 2004 of the oil pump is obtained, and the matching degree is calculated and the ideal mode output vector of the working condition with the highest matching degree is used as the current operating condition of the oil pump, and thus the processing step flows to 2005.

[0075] In 202, when it is known which operating state the oil pump is currently in, the fault characteristic parameters 2006 under the operating condition are obtained from the obtained operating parameters, and the fault characteristic parameters are input into the two-stage BP neural network model 2003 again for fault analysis and processing, the current fault mode output vector 2007 of the oil pump is obtained, the matching degree is calculated and the fault ideal mode output vector with the highest matching degree is taken as the current fault of the oil pump, and the fault type 2007 corresponding to the fault is determined in the corresponding fault type database.

[0076] Thus, the analysis and processing of the current operating conditions and faults of the oil pump are completed, and when it is determined that the current oil pump has a fault, corresponding processing measures are executed according to the type of the fault, such as prompting the user with corresponding processing suggestions, or shutting down the pump.

[0077] It should be noted that, in the specific implementation, the operating parameters of the oil pump obtained can be in the form of a table, and when performing operating condition and fault analysis and processing, the data required to be processed in the operating condition identification stage can be set. For example, the first and second columns of data in the table are the data required to be analyzed and processed in the operating condition identification stage, and the first to sixth columns of data in the table are the data required to be analyzed and processed in the fault identification stage.

[0078] In this embodiment, a method for processing an oil pump fault is provided, by obtaining the operating parameters of the oil pump, identifying and processing the operating parameters, obtaining the operating condition characteristic parameters in the operating parameters; using a preconfigured two-stage BP neural network model to analyze and process the operating condition characteristic parameters, obtaining the current operating condition of the oil pump; obtaining the fault characteristic parameters corresponding to the current operating condition from the operating parameters, and using a preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters, obtaining the current fault of the oil pump and the type of the fault, so as to perform corresponding processing measures on the fault according to the type of the fault. Compared with the prior art, the method provided in this embodiment can analyze and process the operating condition and fault of the oil pump in real time and in a graded manner, which can reduce the amount of data analyzed and processed to achieve the effect of improving efficiency, and at the same time, the operating condition and fault are processed separately to avoid the occurrence of a fault type of another operating condition under a certain operating condition, thereby improving the accuracy of the analysis of operating parameters with high similarity, and then improving the accuracy of the oil pump processing.

[0079] On the basis of the above-mentioned embodiment, this embodiment will specifically explain the specific processing steps for analyzing and processing the working condition and fault of the current operating state of the oil delivery pump.

[0080] First, the specific process of analyzing and processing the current operating conditions of the oil pump will be explained in detail. Specifically, the inlet pressure and outlet pressure in the operating condition characteristic parameters are processed using the pre-configured two-stage BP neural network model to obtain the operating condition mode output vector; the matching degree between the operating condition mode output vector and the pre-stored ideal operating condition mode output vector is calculated, and the operating condition corresponding to the ideal operating condition mode output vector with the highest matching degree is used as the current operating condition of the oil pump.

[0081] It should be noted that the operating conditions of the oil pump can be described by the inlet pressure, outlet pressure, motor current, motor stator temperature, bearing temperature (motor, pump), housing temperature, vibration (pump) drive end and non-drive end, and oil seal differential pressure. However, by using Failure Mode and Effect Analysis (FMEA) to analyze and process the operating parameters of the oil pump, compare the relevant parameters of the oil pump under different working conditions and different faults, and optimize the operating parameters of the oil pump according to the working condition characteristic parameters, the complexity of the model can be further reduced.

[0082] Table 1 is a schematic table of FMEA analysis results provided in this application.

[0083] Table 1

[0084]

[0085] As shown in Table 1, the table shows the causes of failure of the oil pump subsystem, the impact of the failure, and the method of detecting the failure.

[0086] Table 2 is a schematic table of characteristic parameters corresponding to a type of working condition provided in this application.

[0087] Table 2

[0088]

[0089] As shown in Table 2, assuming that the operating conditions in this embodiment are OC1-ZC, OC2-ZC and OC3-ZC, and these three operating conditions are all normal operating conditions, it can be seen from Table 2 that the characteristic parameter value ranges corresponding to these three operating conditions are not much different. Therefore, when selecting characteristic parameters, characteristic parameters with greater differentiation should be selected to distinguish the types of operating conditions.

[0090] It should be noted that Table 1 and Table 2 provided in this embodiment are only examples, and there is no correlation between Table 1 and Table 2.

[0091] It can be seen from Table 2 that the inlet pressure and outlet pressure under different working conditions of the oil pump are quite different. Therefore, the inlet pressure and outlet pressure are selected as the characteristic parameters for identifying the working conditions of the oil pump.

[0092] More specifically, the inlet pressure value and the outlet pressure value in the obtained operating condition characteristic parameters are input into the preconfigured two-stage BP neural network model for analysis and processing to obtain the operating condition mode output vector corresponding to the current operating parameters, and the matching degree of the operating condition mode output vector and the preset operating condition ideal mode output vector is calculated. Optionally, the Pearson similarity formula can be used to calculate the matching degree, and the operating condition corresponding to the operating condition ideal mode output vector with the highest similarity to the operating condition mode output vector is used as the current operating condition of the oil pump.

[0093] Among them, the pre-stored ideal operating mode output vector is set by relevant technicians in this field based on experience, but is not limited to other specific implementation methods.

[0094] Furthermore, the specific process of how to analyze and handle the current operating failure of the oil pump will be explained in detail.

[0095] Specifically, fault characteristic parameters corresponding to the current operating conditions are obtained from the operating parameters, and the fault characteristic parameters include: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, and oil seal differential pressure; the fault characteristic parameters are analyzed and processed using a preconfigured two-stage BP neural network model to obtain a fault mode output vector; the matching degree between the fault mode output vector and the pre-stored fault ideal mode output vector is calculated, and the fault corresponding to the fault ideal mode output vector with the highest matching degree is used as the current fault of the oil pump.

[0096] In this embodiment, the fault handling method provided mainly distinguishes three situations under certain working conditions: normal working condition of the oil pump, abnormal condition of the motor and abnormal condition of the oil seal, and the parameters include inlet pressure, outlet pressure, motor current, motor stator temperature, bearing temperature (motor, pump), housing temperature, vibration (pump) drive end and non-drive end, and oil seal differential pressure, a total of ten groups, so appropriate characteristic parameters are selected for the two fault conditions of abnormal motor vibration and abnormal oil seal.

[0097] According to the method of selecting characteristic parameters corresponding to the working condition type, the fault characteristic parameters can be determined as: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, and oil seal differential pressure.

[0098] More specifically, the acquired fault characteristic parameters are input into a preconfigured two-stage BP neural network model for analysis and processing to obtain a fault mode output vector corresponding to the current operating parameters, and the fault mode output vector is matched with a preset fault ideal mode output vector. Optionally, the Pearson similarity formula can be used to calculate the matching degree, and the fault corresponding to the fault ideal mode output vector with the highest similarity to the fault mode output vector is taken as the current operating fault of the oil pump.

[0099] It should be noted that the pre-stored ideal fault mode output vector is set by relevant technicians in this field based on experience, but is not limited to other specific implementation methods.

[0100] Furthermore, the type of fault corresponding to the fault is obtained from a pre-stored fault type database, and the processing measure corresponding to the type of fault is obtained, so as to execute the corresponding processing measure for the fault.

[0101] In this embodiment, a fault type database is pre-stored to record faults related to the oil pump, fault types and corresponding treatment measures. The fault type database is implemented by relevant technicians in this field, but is not limited to other specific implementation methods.

[0102] In the pre-stored fault type database, the fault type corresponding to the current operating fault of the oil pump and the corresponding treatment measures are found.

[0103] In this embodiment, it is specifically explained how to select operating condition characteristic parameters and fault characteristic parameters, as well as the specific processing steps for obtaining the operating condition characteristic parameters and fault characteristic parameters, so as to analyze and process the operating condition and fault of the oil pump. Compared with the existing technology, the processing efficiency and accuracy can be improved.

[0104] Figure 3 This is a schematic diagram of a method for troubleshooting an oil pump provided in this application. Based on the above-mentioned embodiment, this embodiment specifically describes the specific processing steps of pre-configuring a two-stage BP neural network model, such as Figure 3 As shown:

[0105] Step 301: Acquire a historical operating parameter data set of an oil pump, and normalize the historical operating parameter data set to obtain a data set to be trained.

[0106] In this embodiment, in order to obtain the ability to analyze and process the working conditions and faults of the oil pump in a graded manner, it is necessary to obtain a historical operating parameter data set of the oil pump for training the initial two-stage BP neural network model to obtain a preconfigured two-stage BP neural network model.

[0107] Specifically, the acquired historical operating parameter data set of the oil pump may be normalized to obtain a data set to be trained, and the data set to be trained may be divided into a training data set and a test data set according to a preset ratio.

[0108] Step 302: Input the training data set in the to-be-trained data set into the initial two-stage BP neural network model to obtain the trained two-stage BP neural network model.

[0109] Specifically, the initial two-stage BP neural network model needs to be trained twice, firstly, the first training is performed on the working condition type analysis and processing, and then the second training is performed on the fault analysis and processing.

[0110] Exemplarily, it is assumed that the data set to be trained includes: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, oil seal differential pressure, ideal operating mode output vector and ideal fault mode output vector, and the training data set exists in the form of a table, and the training parameters are marked as the first to sixth columns.

[0111] During the first training, the first column and the second category of the training data set in the training data set and the parameters corresponding to the ideal working mode output vector are used. The second training uses the first to sixth columns of the training data set in the training data set and the parameters corresponding to the ideal fault mode output vector.

[0112] Furthermore, a trained two-stage BP neural network model is obtained.

[0113] Step 303: Use the test data set in the training data set to test the trained two-stage BP neural network model to obtain a test result.

[0114] Specifically, the trained two-stage BP neural network model is tested using the test data set in the training data set.

[0115] Then, the trained two-stage BP neural network model is subjected to a first test of operating condition analysis and a second test of fault analysis.

[0116] More specifically, the actual mode output vector of the working condition of the first test and the actual mode output vector of the fault of the second test are obtained. The actual mode output vector of the working condition of the first test is matched with the ideal mode output vector of the working condition in the test data set, and the actual mode output vector of the fault of the second test is matched with the ideal mode output vector of the fault in the test data set to obtain the calculation result of the matching degree.

[0117] Step 304 , determine whether the test result is greater than or equal to a preset calibration value, if so, execute step 305 ; otherwise, execute step 306 .

[0118] Specifically, the matching result of step 303 is analyzed to determine whether the matching result corresponding to the first test result and the matching result of the second test reach a preset calibration value, such as 90%. The preset calibration value is implemented by relevant technical personnel, but is not limited to other specific implementation methods.

[0119] Optionally, if both test results reach 90%, step 305 is executed; if one of the two test results does not reach the standard, step 306 is executed.

[0120] Step 305: Use the trained two-stage BP neural network model as a preconfigured two-stage BP neural network model.

[0121] Step 306: Adjust the training parameters in the trained two-stage BP neural network model.

[0122] Specifically, when both test results reach 90%, it means that the accuracy of the current trained two-stage BP neural network model reaches the standard for oil pump operating conditions and fault analysis and processing, and the trained two-stage BP neural network model will be used as the preconfigured two-stage BP neural network model.

[0123] If the test result does not reach 90%, it means that the accuracy of the currently trained two-level BP neural network model is not enough, and the parameters such as learning rate, number of iterations and weight value can be adjusted. Optionally, the range of parameters such as learning rate, number of iterations and weight value is randomly selected, and the learning rate, number of iterations and weight value corresponding to the maximum matching degree are used as the adjusted parameters.

[0124] In this embodiment, the specific processing steps of how to obtain the preconfigured two-stage BP neural network model are specifically explained. The preconfigured two-stage BP neural network model can be used to analyze and process the working conditions and faults of the oil pump respectively, thereby improving the accuracy of the analysis and processing of the working conditions and faults of the oil pump.

[0125] Figure 4 A schematic diagram of a structure of a processing device for an oil pump failure provided in this application is shown in FIG. Figure 4 As shown, the processing device 40 includes: an acquisition module 41 and a processing module 42.

[0126] Among them, 42 obtains the operating parameters of the oil pump, identifies and processes the operating parameters, and obtains the operating condition characteristic parameters in the operating parameters; the processing module 42 is used to use the preconfigured two-stage BP neural network model to analyze and process the operating condition characteristic parameters to obtain the current operating condition of the oil pump; the processing module 42 is also used to obtain the fault characteristic parameters corresponding to the current operating condition from the operating parameters, and use the preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters to obtain the current fault of the oil pump and the type of fault, so as to perform corresponding processing measures on the fault according to the type of fault.

[0127] Optionally, the processing module 42 is specifically configured to:

[0128] The inlet pressure and outlet pressure in the operating condition characteristic parameters are processed using a pre-configured two-stage BP neural network model to obtain an operating condition mode output vector;

[0129] The matching degree between the working condition mode output vector and the pre-stored working condition ideal mode output vector is calculated, and the working condition corresponding to the working condition ideal mode output vector with the highest matching degree is used as the current operating condition of the oil pump.

[0130] Optionally, the processing module 42 is specifically configured to:

[0131] Obtain fault characteristic parameters corresponding to the current operating conditions from the operating parameters, the characteristic parameters including: inlet pressure, outlet pressure, motor stator temperature, vibration (pump) drive end and non-drive end parameters, and oil seal differential pressure;

[0132] The pre-configured two-stage BP neural network model is used to analyze and process the fault characteristic parameters to obtain the fault mode output vector;

[0133] Calculate the matching degree between the fault mode output vector and the pre-stored fault ideal mode output vector, and take the fault corresponding to the fault ideal mode output vector with the highest matching degree as the current fault of the oil pump;

[0134] The type of fault corresponding to the fault is obtained from a pre-stored fault type database, and the processing measures corresponding to the type of fault are obtained.

[0135] Optionally, the processing module 42 is further configured to:

[0136] Obtain a historical operating parameter data set of the oil pump, and normalize the historical operating parameter data set to obtain a data set to be trained;

[0137] Inputting the training data set in the to-be-trained data set into the initial two-stage BP neural network model to obtain a trained BP neural network model;

[0138] The trained BP neural network model is tested using the test data set in the training data set to obtain the test result, and determine whether the test result is greater than or equal to the preset calibration value;

[0139] If yes, the trained BP neural network model is used as the preconfigured two-stage BP neural network model.

[0140] Optionally, the processing module 42 is further configured to:

[0141] If the test result is less than the preset calibration value, the training parameters in the trained BP neural network model are adjusted.

[0142] The processing device provided in the embodiment of the present application can execute the technical solution shown in the above method implementation. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0143] This embodiment provides a processing device for oil pump failure, wherein the acquisition module is used to acquire the operating parameters of the oil pump, identify and process the operating parameters, and acquire the operating condition characteristic parameters in the operating parameters; the processing module is used to analyze and process the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to acquire the current operating condition of the oil pump; the processing module is also used to acquire the fault characteristic parameters corresponding to the current operating condition from the operating parameters, and analyze and process the fault characteristic parameters using a preconfigured two-stage BP neural network model to acquire the current fault of the oil pump and the type of fault, so as to perform corresponding processing measures on the fault according to the type of fault. Compared with the prior art, the processing device provided by the present application executes the processing method provided by the present application, which can improve the processing efficiency and accuracy of the operating condition and fault of the oil pump.

[0144] The embodiment of the present application also provides a server, which includes: a processor and a memory connected to the processor in communication, wherein the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method mentioned in the above embodiment.

[0145] The embodiment of the present application also provides a system for processing oil pump failure, the processing system comprising: a server and an oil pump. The server carries or houses a processing device, and uses the processing device to execute the method mentioned in the previous embodiment to process the operating parameters of the oil pump in real time or periodically to determine the current fault of the oil pump and the type of the fault, and execute corresponding processing measures for the fault according to the type of the fault.

[0146] An embodiment of the present application also provides a computer-readable storage medium on which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the technical solution provided by any of the aforementioned embodiments is implemented.

[0147] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the technical solution provided by any of the aforementioned method embodiments when the computer program is executed by a processor.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for handling oil pump failure, characterized in that: include: Acquire the operating parameters of the oil pump, perform identification processing on the operating parameters, and acquire the operating condition characteristic parameters from the operating parameters, wherein the operating condition characteristic parameters have different value ranges under different operating conditions; Analyzing and processing the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump; Fault characteristic parameters corresponding to the current operating condition are obtained from the operating parameters, and the fault characteristic parameters are analyzed and processed using the preconfigured two-stage BP neural network model to obtain the current fault of the oil pump and the type of the fault, so as to perform corresponding processing measures on the fault according to the type of the fault.

2. The method according to claim 1, characterized in that The method of analyzing and processing the operating condition characteristic parameters by using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump includes: Using the preconfigured two-stage BP neural network model to process the inlet pressure and the outlet pressure in the operating condition characteristic parameters, and obtaining an operating condition mode output vector; The matching degree between the working condition mode output vector and the pre-stored working condition ideal mode output vector is calculated, and the working condition corresponding to the working condition ideal mode output vector with the highest matching degree is used as the current operating condition of the oil pump.

3. The method according to claim 1, characterized in that The method of acquiring the fault characteristic parameters corresponding to the current operating condition from the operating parameters, and analyzing and processing the fault characteristic parameters using the preconfigured two-stage BP neural network model to acquire the current fault of the oil pump and the type of the fault, and executing corresponding processing measures for the fault according to the type of the fault, includes: Acquire fault characteristic parameters corresponding to the current operating condition from the operating parameters, the fault characteristic parameters including: inlet pressure, outlet pressure, motor stator temperature, vibration pump drive end and non-drive end parameters, and oil seal differential pressure; Analyzing and processing the fault characteristic parameters using the preconfigured two-stage BP neural network model to obtain a fault mode output vector; Calculating the matching degree between the fault mode output vector and the pre-stored fault ideal mode output vector, and taking the fault corresponding to the fault ideal mode output vector with the highest matching degree as the current fault of the oil pump; The type of fault corresponding to the fault is obtained from a pre-stored fault type database, and the processing measure corresponding to the type of fault is obtained, so as to execute the corresponding processing measure for the fault.

4. The method according to any one of claims 1 to 3, characterized in that: The preconfigured two-stage BP neural network model includes: Acquire a historical operating parameter data set of the oil pump, and perform normalization processing on the historical operating parameter data set to obtain a data set to be trained; Inputting the training data set in the to-be-trained data set into the initial two-stage BP neural network model to obtain a trained two-stage BP neural network model; Using the test data set in the training data set to test the trained two-stage BP neural network model to obtain a test result, and determine whether the test result is greater than or equal to a preset calibration value; If yes, the trained two-stage BP neural network model is used as the preconfigured two-stage BP neural network model.

5. The method according to claim 4, characterized in that The method further comprises: If the test result is less than the preset calibration value, the training parameters in the trained two-stage BP neural network model are adjusted.

6. A device for handling oil pump failure, characterized in that: include: An acquisition module is used to acquire the operating parameters of the oil delivery pump, identify and process the operating parameters, and acquire operating condition characteristic parameters from the operating parameters, wherein the operating condition characteristic parameters have different value ranges under different operating conditions; A processing module, used to analyze and process the operating condition characteristic parameters using a preconfigured two-stage BP neural network model to obtain the current operating condition of the oil pump; The processing module is also used to obtain fault characteristic parameters corresponding to the current operating conditions from the operating parameters, and use the preconfigured two-stage BP neural network model to analyze and process the fault characteristic parameters to obtain the current fault of the oil pump and the type of the fault, so as to perform corresponding processing measures on the fault according to the type of the fault.

7. The device according to claim 6, characterized in that The processing module is specifically used for: Using the preconfigured two-stage BP neural network model to process the inlet pressure and the outlet pressure in the operating condition characteristic parameters, and obtaining an operating condition mode output vector; The matching degree between the working condition mode output vector and the pre-stored working condition ideal mode output vector is calculated, and the working condition corresponding to the working condition ideal mode output vector with the highest matching degree is used as the current operating condition of the oil pump.

8. The device according to claim 6, characterized in that The processing module is specifically used for: Acquire fault characteristic parameters corresponding to the current operating condition from the operating parameters, the fault characteristic parameters including: inlet pressure, outlet pressure, motor stator temperature, vibration pump drive end and non-drive end parameters, and oil seal differential pressure; Analyzing and processing the fault characteristic parameters using the preconfigured two-stage BP neural network model to obtain a fault mode output vector; Calculating the matching degree between the fault mode output vector and the pre-stored fault ideal mode output vector, and taking the fault corresponding to the fault ideal mode output vector with the highest matching degree as the current fault of the oil pump; The type of fault corresponding to the fault is obtained from a pre-stored fault type database, and the processing measures corresponding to the type of fault are obtained.

9. The device according to any one of claims 6 to 8, characterized in that: The processing module is further used for: Acquire a historical operating parameter data set of the oil pump, and perform normalization processing on the historical operating parameter data set to obtain a data set to be trained; Inputting the training data set in the to-be-trained data set into the initial two-stage BP neural network model to obtain a trained two-stage BP neural network model; Using the test data set in the training data set to test the trained two-stage BP neural network model to obtain a test result, and determine whether the test result is greater than or equal to a preset calibration value; If yes, the trained two-stage BP neural network model is used as the preconfigured two-stage BP neural network model.

10. The device according to claim 9, characterized in that The processing module is further used for: If the test result is less than the preset calibration value, the training parameters in the trained two-stage BP neural network model are adjusted.

11. A server, characterized in that: The server comprises: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

12. A system for processing oil pump failure, characterized in that: The processing system includes: a server and an oil pump; Wherein, the server carries or houses a processing device, and utilizes the processing device to execute the method described in any one of claims 1 to 5, processes the operating parameters of the oil pump in real time or periodically to determine the current fault of the oil pump and the type of the fault, and executes corresponding processing measures for the fault according to the type of the fault.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1 to 5 is implemented.

Images