CN115077906A

CN115077906A - Engine high-occurrence fault cause determination method, engine high-occurrence fault cause determination device, electronic equipment and medium

Info

Publication number: CN115077906A
Application number: CN202210657654.6A
Authority: CN
Inventors: 殷利航; 唐波
Original assignee: Weichai Power Co Ltd
Current assignee: Weichai Power Co Ltd
Priority date: 2022-06-10
Filing date: 2022-06-10
Publication date: 2022-09-20

Abstract

The invention discloses a method and a device for determining engine high-occurrence fault cause, electronic equipment and a medium. The method comprises the following steps: acquiring a current dispatching order, current engine basic information, a current engine maintenance report and a current engine sales file, and determining current engine fault information according to the current dispatching order; inputting current engine fault information, current engine basic information, a current engine maintenance report and a current engine sales file into a pre-trained engine high-occurrence fault cause determining model, and outputting a current engine high-occurrence fault cause and a corresponding fault probability; and determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability, and determining corresponding fault troubleshooting information of the parts according to the target engine high-occurrence fault cause. The engine high-occurrence fault cause diagnosis is efficiently and accurately realized.

Description

Method and device for determining engine high-occurrence fault cause, electronic device and medium

Technical Field

The invention relates to the technical field of engine fault diagnosis, in particular to a method and a device for determining engine high-incidence fault cause, electronic equipment and a medium.

Background

The engine fault diagnosis is researched in various directions of production and research, the engine fault diagnosis technology is deeply researched from both the aspects of mechanism and data, from the perspective of after-sales of enterprise products, a large amount of after-sales historical maintenance data are accumulated by enterprises, a maintenance worksheet has actual maintenance experiences from maintenance engineers for many years, and millions of historical maintenance data are worth mining.

The fault diagnosis based on data mainly uses sensor data and is applied to fault diagnosis of rotary machinery which is convenient for mounting a vibration sensor, but in an actual scene, many faults are difficult to diagnose by collecting signals through the sensor, the cost is high, the research result of academic circles is difficult to fall to the ground, and the fault diagnosis only stays on a theoretical level; meanwhile, maintenance engineers in each service station have different maintenance experiences, erroneous judgment exists, and the one-time fault maintenance success rate is to be improved.

Disclosure of Invention

The invention provides a method, a device, electronic equipment and a medium for determining a high-occurrence fault cause of an engine, and aims to solve the problems that actual engine fault maintenance data in the market are limited, deviation exists between the actual engine fault maintenance data and an engine mechanism, the high-occurrence fault cause of the engine is difficult to diagnose accurately, and the success rate of engine fault maintenance is low.

According to an aspect of the present invention, there is provided an engine high-occurrence failure cause determination method including:

acquiring a current dispatching order and a current engine sales file, and determining current engine basic information and current engine fault information according to the current dispatching order;

inputting the current engine fault information, the current engine basic information and the current engine sales file into a pre-trained engine high-occurrence fault cause determining model, and outputting a current engine high-occurrence fault cause and a corresponding fault probability;

and determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability, and determining corresponding part fault troubleshooting information according to the target engine high-occurrence fault cause.

Optionally, before inputting the current engine fault information, the current engine basic information, and the current engine sales file into a pre-trained engine high-incidence fault cause determination model, the method further includes:

preprocessing the current engine fault information, the current engine basic information and the current engine sales file, and performing feature extraction, type feature coding and dimensionless processing on the preprocessed current engine fault information, the preprocessed current engine basic information and the preprocessed current engine sales file;

wherein the preprocessing comprises canonical data types, outlier processing, and missing value completion.

Optionally, the method for determining the cause of the high-occurrence engine fault further includes:

preprocessing at least one group of historical dispatch lists, historical engine basic information, historical engine maintenance reports and historical engine sales files to obtain a model building data set;

inputting the model building data set into a pre-built engine high-occurrence fault cause determining model to obtain historical engine high-occurrence fault causes and corresponding fault probabilities;

retraining model parameters of the engine high-incidence failure cause determination model based on the historical engine high-incidence failure causes and corresponding failure probabilities and an expected engine high-incidence failure cause and corresponding failure probability.

acquiring a current engine maintenance report, and storing the current engine fault information, the current engine basic information and the current engine sales file to the model building data set;

and retraining the model parameters of the engine high-incidence fault cause determination model according to the updated model building data set.

if the fault description information does not exist in the current engine fault information, generating a necessary parameter missing error instruction, wherein the necessary parameter missing instruction is used for prompting that the current engine fault information has an error; or the like, or a combination thereof,

and if the fault description information contained in the current engine fault information is detected not to belong to a preset fault range, generating a fault description missing error instruction, wherein the fault description missing error instruction is used for prompting that the fault description information does not belong to the preset fault range.

Optionally, the determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability includes:

and sequencing the current engine high-occurrence-failure cause according to the failure probability, and sequentially selecting a set number of engine high-occurrence-failure causes as target engine high-occurrence-failure causes.

acquiring fault probability corresponding to the target engine high-occurrence fault initiating factor;

and feeding back the target engine high-occurrence failure cause, the failure probability corresponding to the target engine high-occurrence failure cause and the part failure troubleshooting information to a service terminal so as to display the target engine high-occurrence failure cause, the failure probability corresponding to the target engine high-occurrence failure cause and the part failure troubleshooting information on the service terminal.

According to another aspect of the present invention, there is provided an engine high-occurrence failure cause determination device including:

the information acquisition module is used for acquiring a current dispatching order and a current engine sales file, and determining current engine basic information and current engine fault information according to the current dispatching order;

the engine high-occurrence fault cause determination module is used for determining engine high-occurrence fault causes of the engine, and outputting the current engine high-occurrence fault causes and corresponding fault probabilities;

and the troubleshooting module is used for determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability and determining corresponding part fault troubleshooting information according to the target engine high-occurrence fault cause.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method for determining causes of high engine failure according to any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for determining the cause of high engine failure according to any one of the embodiments of the present invention when the computer instructions are executed.

According to the technical scheme of the embodiment of the invention, the current dispatching order, the current engine maintenance report and the current engine sales file are obtained, and the current engine basic information and the current engine fault information are determined according to the current dispatching order; inputting the current engine fault information, the current engine basic information and the current engine sales file into a pre-trained engine high-occurrence fault cause determining model, and outputting a current engine high-occurrence fault cause and a corresponding fault probability; and determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability, and determining corresponding part fault troubleshooting information according to the target engine high-occurrence fault cause. The method and the device solve the problems that in the market, actual engine fault maintenance data are limited, deviation exists between the actual engine fault maintenance data and an engine mechanism, and the engine high-occurrence fault cause is difficult to diagnose accurately, so that the success rate of engine fault maintenance is low, the more accurate engine high-occurrence fault cause determination model is formed based on market maintenance experience and the engine mechanism, the engine high-occurrence fault cause is diagnosed efficiently and accurately, meanwhile, the business explanatory performance of the accuracy rate of the engine high-occurrence fault cause determination model is achieved, and the prediction result of the engine high-occurrence fault cause determination model has the advantage of higher operability.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow chart of a method for determining the cause of a high-occurrence engine fault according to an embodiment of the present invention;

FIG. 2 is a schematic illustration of a broad table process suitable for use in accordance with an embodiment of the present invention;

FIG. 3 is a flowchart of a method for determining the cause of high engine failure according to a second embodiment of the present invention;

FIG. 4 is a diagram illustrating an implementation of specific results of variant one-hot encoding provided in accordance with an embodiment of the present invention;

FIG. 5 is a diagram illustrating a specific implementation result of tag encoding according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an engine high-incidence failure cause determination device according to a third embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device that implements the engine high-incidence failure cause determination method according to the embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of an engine high-occurrence-failure cause determination method according to an embodiment of the present invention, which is applicable to a situation where overall modeling and efficient and accurate diagnosis of an engine high-occurrence-failure cause are performed by fully mining characteristics such as engine failure influence factors in maintenance data for a large amount of historical maintenance data of an engine. As shown in fig. 1, the engine high-incidence failure cause determination method includes:

and S110, acquiring a current dispatching order and a current engine sales file, and determining current engine basic information and current engine fault information according to the current dispatching order.

The dispatching list is a data table which is generated when a user reports and repairs an engine fault and is used for recording fault conditions such as engine fault description and fault location and engine basic information such as an engine number. In this embodiment, the current dispatch list is the current dispatch list of the engine, and the current engine basic information and the current engine fault information can be obtained according to the current dispatch list.

The engine fault description is a standard description selected according to sensed engine fault performance when a user reports a repair when an engine fails.

The engine sales file is a file for recording engine sales information generated when the engine is first forcibly maintained. In this embodiment, the current engine sales profile is the current engine sales profile of the engine.

In this embodiment, in order to correlate the engine maintenance report, the current engine sales file, the current basic engine information, and the current engine failure information to generate a wide table for further analysis and processing, fig. 2 is a schematic processing diagram of the wide table provided by the embodiment of the present invention, as shown in fig. 2, the engine maintenance report may include information such as a dispatching order number, an engine number, and an accessory name, the engine sales file may include information such as an engine number, a date of delivery, and a device usage, the basic engine information may include information such as an engine number, an engine series, and a manufacturing plant, the dispatching order may include information such as a dispatching order number, a failure description, and a failure date, and further, it is known that variables for training engine high-incidence failure cause determination model characteristics may be preliminarily selected according to business logic, the information may specifically include a description of the failure, a family of engines, a model of an engine, a date of sale, a date of failure, a manufacturing plant, a host plant, etc.

It should be noted that the cleaning logic of the maintenance report is: selecting a maintenance report with a process approval state of 'accounted', 'to-be-accounted' or 'under-accounted' as a current engine maintenance report; selecting a sales file with an expired state or an effective state as a current engine sales file; the logic of completing the sales files, dispatching orders and basic engine information processing, which does not contain related fields of maintenance and correction in the fault description, is a maintenance report. In addition, when the engine is maintained for multiple times, the same engine is maintained for multiple times within 15 days of the same fault phenomenon, and only one engine with the latest date is taken as the fault date.

Specifically, with continued reference to fig. 2, the maintenance report is used as the master table, the dispatch list number is used as the association field, the association is made with the dispatch list, and the engine number is used to associate the basic engine information and the sales file.

And S120, inputting the current engine fault information, the current engine basic information and the current engine sales file into a pre-trained engine high-occurrence fault cause determining model, and outputting the current engine high-occurrence fault cause and the corresponding fault probability.

It is understood that before inputting the current engine fault information, the current engine basic information and the current engine sales file into the pre-trained engine high incidence fault cause determination model, the method further comprises: preprocessing the current engine fault information, the current engine basic information and the current engine sales file, and performing feature extraction, type feature coding and dimensionless processing on the preprocessed current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file; wherein the preprocessing comprises canonical data types, outlier processing, and missing value completion.

It should be noted that, during the preprocessing, it is necessary to determine whether there are problems of whether the data type is normal, abnormal values and missing values, and then perform corresponding preprocessing operations on the existing problems, for the current engine fault information, the current engine basic information and the current engine sales file. When the current engine fault information, the current engine basic information and the current engine sales file do not have the problems of irregular data types, abnormal values and missing values, preprocessing operation on the current engine fault information, the current engine basic information and the current engine sales file is not needed.

In this embodiment, the engine high-occurrence-failure cause determination model may adopt a classification model, for example, an SVM (Support Vector Machine) model, an XGBoost model (Gradient Boosting model), a deep learning model, and the like, where the deep learning model may be a deep neural network DNN model, a convolutional neural network CNN model, a bp (back propagation) neural network BPNN model, a probabilistic neural network PNN model, or may adopt a Machine learning model, and optionally, the engine high-occurrence-failure cause determination model adopts a random forest model.

On the basis, before inputting the current engine fault information, the current engine basic information and the current engine sales file into a pre-trained engine high-occurrence-failure cause determination model, the engine high-occurrence-failure cause determination model needs to be trained, and the method specifically includes: preprocessing at least one group of historical dispatch lists, historical engine basic information, historical engine maintenance reports and historical engine sales files to obtain a model building data set; inputting the model building data set into a pre-built engine high-occurrence fault cause determining model to obtain historical engine high-occurrence fault causes and corresponding fault probabilities; and adjusting the model parameters of the engine high-occurrence-failure-cause determination model based on the historical engine high-occurrence-failure causes and the corresponding failure probabilities and the expected engine high-occurrence-failure causes and the corresponding failure probabilities.

The engine maintenance report is a data table which is generated after the maintenance of the engine is finished and used for recording the fault condition of the engine, and the engine maintenance report comprises information such as the maintenance process and result of the engine, and cause parts related to the fault. In the present embodiment, the historical engine maintenance reports are engine maintenance reports generated by the engine over a past time.

It can be understood that research and development engineers and service related personnel regularly monitor data quality, reduce error judgment of after-sales maintenance, ensure data quality of maintenance reports and dispatch lists, explore according to new series, models and market feedback conditions of the engine, and update the high-occurrence fault and cause combination table in time, namely update the engine high-occurrence fault cause determination model.

In one embodiment, the engine high-incidence failure cause determination model is updated at any time, specifically: storing the current engine fault information, the current engine basic information and the current engine sales file to the model building data set; and adjusting the model parameters of the engine high-incidence fault cause determining model according to the updated model building data set.

In an embodiment, the engine high-incidence failure cause determination model is updated periodically, that is, the accuracy of the engine high-incidence failure cause determination model is continuously monitored, error records are analyzed, periodically, optionally, every 2 months, data of 2 years before the current time point are selected as a trained model building data set, the engine high-incidence failure cause determination model is retrained, and a new engine high-incidence failure cause determination model is deployed and applied to a recommended engine high-incidence failure cause troubleshooting method.

In order to solve the problem, in the embodiment, before model training is performed on the current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file, fault description standardization needs to be performed, and before the current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file are input into a pre-trained engine high-incidence fault cause determination model, whether fault description information exists in the current engine fault information or not is determined, and determining whether the existing fault description is a pre-stored fault range.

Specifically, if no fault description information exists in the current engine fault information, an error instruction lacking necessary parameters is generated, and the error instruction lacking necessary parameters is used for prompting that the current engine fault information has an error; or if the fault description information contained in the current engine fault information is detected not to belong to the preset fault range, generating a fault description missing error instruction, wherein the fault description missing error instruction is used for prompting that the fault description information does not belong to the preset fault range.

S130, determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability, and determining corresponding part fault troubleshooting information according to the target engine high-occurrence fault cause.

Specifically, the current engine high-occurrence-failure cause is sorted according to the failure probability, and a set number of engine high-occurrence-failure causes are sequentially selected as target engine high-occurrence-failure causes.

The number of the target engine high-incidence failure causes can be selected and set according to actual requirements, and the embodiment does not limit the number. Optionally, three engine high-occurrence fault cause pieces are sequentially selected as the target engine high-occurrence fault cause piece, and further, the three engine high-occurrence fault cause pieces with the largest fault probability corresponding to the current engine high-occurrence fault cause piece are selected as the target engine high-occurrence fault cause pieces.

In order to provide a maintenance guidance suggestion for a maintenance technician and allow the maintenance technician to view the failure probability corresponding to the target engine high-incidence failure cause at any time through a service terminal, in this embodiment, the failure probability corresponding to the target engine high-incidence failure cause is obtained, and then the target engine high-incidence failure cause, the failure probability corresponding to the target engine high-incidence failure cause, and the component troubleshooting information are fed back to the service terminal, so that the target engine high-incidence failure cause, the failure probability corresponding to the target engine high-incidence failure cause, and the component troubleshooting information are displayed on the service terminal.

According to the technical scheme of the embodiment of the invention, the current dispatching order and the current engine sales file are obtained, and the current engine basic information and the current engine fault information are determined according to the current dispatching order; inputting the current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file into a pre-trained engine high-occurrence fault cause determining model, and outputting a current engine high-occurrence fault cause and a corresponding fault probability; and determining a target engine high-occurrence fault cause according to the current engine high-occurrence fault cause and the corresponding fault probability, and determining corresponding part fault troubleshooting information according to the target engine high-occurrence fault cause. The problem that in the market, actual engine fault maintenance data are limited, deviation exists between the actual engine fault maintenance data and an engine mechanism, and diagnosis of engine high-occurrence fault cause parts is difficult to accurately carry out, so that the success rate of engine fault maintenance is low is solved.

Example two

Fig. 3 is a flowchart of a method for determining an engine high-occurrence-failure cause according to a second embodiment of the present invention, and an alternative implementation manner is provided on the basis of the second embodiment. As shown in fig. 2, the engine high-incidence failure cause determination method includes:

s310, obtaining a current dispatching order and a current engine sales file, and determining current engine basic information and current engine fault information according to the current dispatching order.

S320, preprocessing the current engine fault information, the current engine basic information and the current engine sales file, and performing feature extraction, type feature coding and dimensionless processing on the preprocessed current engine fault information, the preprocessed current engine basic information, the preprocessed current engine maintenance report and the preprocessed current engine sales file.

In the embodiment, the engine fault descriptions recorded in the dispatch list are unified in standard, the engine high-frequency faults are counted according to the occurrence frequency of the engine fault descriptions, the cause with low occurrence frequency is filtered, optionally, a maintained TOP30 high-frequency fault and a corresponding cause combination (many-to-many) thereof are derived, and each engine fault description may be a fault condition represented by the same cause fault caused by different causes under different conditions.

The research and development engineer combines the engine fault diagnosis mechanism, the engine high-incidence fault and the corresponding cause thereof to screen, eliminates the maintenance scheme of the engine high-incidence fault of which the engine mechanism is unreasonably inferred, forms a screened engine high-incidence fault and cause combination table, and screens the engine maintenance report according to the table, namely, preprocesses the current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file.

The canonical data type is determined by removing symbols present in mileage and time and converting the two columns of total values to numbers.

The abnormal value processing is processing in which the sales date of the engine is recorded later than the trouble date, the sales date is corrected to the trouble date, and the production date is deleted from the record having the production date later than the trouble date as a missing value.

And missing value completion is to count missing value ratios of each column and each row in the information, and according to the missing value ratios and the feature types, the missing value completion is completed by using statistical values such as a median, a mode and the like.

It should be noted that, the preprocessing operation is performed on the current engine fault information, the current basic engine information, the current engine maintenance report and the current engine sales file, but not limited to completing each preprocessing operation, and the preprocessing is performed according to actual requirements.

S330, inputting the current engine fault information, the current engine basic information and the current engine sales file into a pre-trained engine high-occurrence fault cause determining model, and outputting the current engine high-occurrence fault cause and the corresponding fault probability.

It can be understood that, before inputting the current engine fault information, the current engine basic information, and the current engine sales profile into the pre-trained engine high-occurrence-failure-cause determination model, training the engine high-occurrence-failure-cause determination model specifically includes: preprocessing at least one group of historical dispatch lists, historical engine basic information, historical engine maintenance reports and historical engine sales files to obtain a model building data set; inputting the model building data set into a pre-built engine high-occurrence fault cause determining model to obtain historical engine high-occurrence fault causes and corresponding fault probabilities; and adjusting the model parameters of the engine high-occurrence-failure-cause determination model based on the historical engine high-occurrence-failure causes and the corresponding failure probabilities and the expected engine high-occurrence-failure causes and the corresponding failure probabilities.

In this embodiment, before training the engine high-occurrence-failure cause determination model, current engine failure information, current engine basic information, and a current engine sales file need to be constructed as features according to business logic, and type feature coding and dequantization of variables are performed, so as to subsequently generate a data set for model construction.

The method specifically comprises the following steps: and extracting the difference value from the failure date to the sale date as the running time of the engine, processing the production date as a type variable, and representing the influence of different production conditions to complete feature construction.

The type feature coding mode needs to consider the structure of a service scene and a subsequent model, a single dispatch list under a dispatch maintenance scene has one to four fault descriptions (fault description 1 to fault description 4), all the fault descriptions come from a unified list in case of multiple fault descriptions recorded in the same dispatch maintenance scene, and no matter which fault description appears, two coding modes are tried at present: one is variant one-hot coding, the unique fault descriptions appearing in all fault description related columns are used as a vocabulary, when the number of the fault descriptions appearing in the dispatching list is more than 1, the codes are set to 1 with the same number as the fault descriptions, a specific implementation result schematic diagram is shown in FIG. 4, and the other types of characteristics are spliced after conventional one-hot coding; the other way is that new features are generated by all fault description columns, unordered fault description word combinations are combined, then label coding is carried out together with other types of features, and a specific implementation result of the label coding is schematically shown in fig. 5.

It should be noted that the type feature coding may also be implemented as embedding (word 2 vec-like, matrix factorization) based on the improved one-hot coding.

The dimensionless processing is that the magnitude difference between the type characteristic variable and the quantity characteristic after the type characteristic coding is large, the magnitude of the type characteristic after the type characteristic coding is small, after the variant one-hot coding is used, the corresponding virtual variable is 0 or 1, after the second coding mode is used, the magnitude of the corresponding virtual variable is hundred, the mileage characteristic value can reach hundred thousand, the difference of the magnitude can generate adverse effect on the convergence of subsequent model training, the magnitude difference is processed by adopting a standardized mode, and the specific formula is as follows:

wherein, x' _ij Recording the value of the current feature after normalization processing; x is the number of _ih Recording the actual value of the current characteristic for the current time;

is the average of the current features; n is the number of records; i is the current record number; j represents the current feature.

Furthermore, the cause is subjected to label coding and serves as a target variable of model training.

For example, taking an implementation of a random forest model as an engine high-incidence fault cause determination model, taking a dispatching list number as a unit of data in a model building data set, and performing hierarchical random extraction according to causes, wherein 70% is used as a training set and 30% is used as a test set, preprocessing operations are calculated on the training set, and results are used for testing on the test set. When a plurality of causes exist in the same engine maintenance report, each cause is a record row, and the service accuracy of the plurality of causes is determined by only recommending the cause to be any cause in the maintenance report. Aiming at the data of the TOP30 engine high-incidence fault, the performance of the model on the test set is determined according to the engine high-incidence fault cause (the measurement indexes of the performance of the engine high-incidence fault cause determination model comprise recall, precision, F-1 and a user-defined index L1), the accuracy of the random forest model is the highest, and a random forest algorithm can be selected for modeling.

The main hyper-parameters in the random forest algorithm are the number n _ estimators of trees, the minimum sample number min _ samples _ leaf required by leaf nodes, the maximum depth max _ depth and the like, the hyper-parameters are adjusted, the performance of the hyper-parameters on a verification set is checked, the hyper-parameters with the best performance are selected to be combined, training is carried out on the whole data set (a combined training set, the verification set and a test set), and a final engine high-incidence failure cause determining model is generated.

On the basis, the current engine fault information, the current engine basic information and the current engine sales file can be stored in the model building data set, and the model parameters of the engine high-occurrence fault cause determination model are adjusted according to the updated model building data set, so that the engine high-occurrence fault cause determination model is adjusted in real time.

In an embodiment, the engine high-incidence failure cause determination model is periodically maintained and updated, that is, optionally, three months are selected as a model verification period in the engine high-incidence failure cause determination model verification period, the cause recommendation accuracy of the engine high-incidence failure cause determination model is monitored, the accuracy of the engine high-incidence failure cause determination model is continuously up to more than 85% according to a custom evaluation index L1, and the model is integrated into a service terminal used by a maintenance technician and subjected to dispatching and continuously monitored.

S340, sequencing the current engine high-occurrence-failure cause according to the failure probability, and sequentially selecting a set number of engine high-occurrence-failure causes as target engine high-occurrence-failure causes.

And S350, acquiring the fault probability corresponding to the target engine high-occurrence fault initiating element.

S360, feeding back the target engine high-occurrence failure cause, the failure probability corresponding to the target engine high-occurrence failure cause and the component failure troubleshooting information to a service terminal so as to display the target engine high-occurrence failure cause, the failure probability corresponding to the target engine high-occurrence failure cause and the component failure troubleshooting information on the service terminal.

According to the technical scheme of the embodiment of the invention, the establishment of the engine high-occurrence fault cause determining model based on fault information such as fault description and the like and engine basic information is realized, the engine mechanism knowledge of research and development engineers is integrated in data processing and model establishment, the diagnosis of the engine fault cause combining the engine mechanism and market feedback is realized, the class variable coding algorithm is modified aiming at the characteristic information of different combinations of engine fault descriptions under the condition of multiple engine fault descriptions, the accuracy index based on the dispatching list is constructed aiming at the phenomenon of multiple causes, and the business explanation of the accuracy of the engine high-occurrence fault cause determining model is realized.

EXAMPLE III

Fig. 6 is a schematic structural diagram of an engine high-incidence failure cause determination device according to a third embodiment of the present invention. As shown in fig. 6, the engine high-incidence failure cause determination device includes:

the information acquisition module 610 is used for acquiring a current dispatch list and a current engine sales file, and determining current engine basic information and current engine fault information according to the current dispatch list;

a cause output module 620, configured to perform inputting the current engine fault information, the current engine basic information, and the current engine sales file into a pre-trained engine high-occurrence fault cause determination model, and output a current engine high-occurrence fault cause and a corresponding fault probability;

and the troubleshooting module 630 is configured to determine a target engine high-occurrence failure cause according to the current engine high-occurrence failure cause and the corresponding failure probability, and determine corresponding component troubleshooting information according to the target engine high-occurrence failure cause.

Optionally, the engine high-incidence failure cause determination device further includes:

preprocessing the current engine fault information, the current engine basic information and the current engine sales file, and performing feature extraction, type feature coding and dimensionless processing on the preprocessed current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file;

storing the current engine fault information, the current engine basic information and the current engine sales file to the model building data set;

if the fault description information does not exist in the current engine fault information, generating a necessary parameter missing error instruction, wherein the necessary parameter missing instruction is used for prompting that the current engine fault information has an error; or the like, or, alternatively,

acquiring the fault probability corresponding to the target engine high-occurrence fault initiating element;

The engine high-occurrence-failure cause determining device provided by the embodiment of the invention can execute the engine high-occurrence-failure cause determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the engine high-occurrence-failure cause determining method.

Example four

FIG. 7 illustrates a schematic structural diagram of an electronic device 710 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 7, the electronic device 710 includes at least one processor 711, and a memory communicatively connected to the at least one processor 711, such as a Read Only Memory (ROM)712, a Random Access Memory (RAM)713, and the like, wherein the memory stores computer programs executable by the at least one processor, and the processor 711 may perform various suitable actions and processes according to the computer programs stored in the Read Only Memory (ROM)712 or the computer programs loaded from the storage unit 718 into the Random Access Memory (RAM) 713. In the RAM 713, various programs and data required for the operation of the electronic device 710 can also be stored. The processor 711, ROM712, and RAM 713 are connected to each other by a bus 714. An input/output (I/O) interface 715 is also connected to bus 714.

A number of components in the electronic device 710 are connected to the I/O interface 715, including: an input unit 716 such as a keyboard, a mouse, or the like; an output unit 717 such as various types of displays, speakers, and the like; a storage unit 718 such as a magnetic disk, optical disk, or the like; and a communication unit 719 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 719 allows the electronic device 710 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 711 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the processor 711 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The processor 711 performs the various methods and processes described above, such as the engine high incidence failure cause determination method.

In some embodiments, the engine high incidence failure cause determination method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 718. In some embodiments, some or all of the computer program may be loaded and/or installed onto the electronic device 710 via the ROM712 and/or the communication unit 719. When the computer program is loaded into RAM 713 and executed by processor 711, one or more of the steps of the engine high incidence failure cause determination method described above may be performed. Alternatively, in other embodiments, the processor 711 may be configured to perform the engine high incidence failure cause determination method by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining the cause of a high-occurrence engine fault, comprising:

2. The engine high incidence failure cause determination method according to claim 1, further comprising, before inputting the current engine failure information, the current engine basic information, and the current engine sales profile into a pre-trained engine high incidence failure cause determination model:

3. The engine high-occurrence failure cause determination method according to claim 1, characterized by further comprising:

4. The engine high-occurrence failure cause determination method according to claim 3, characterized by further comprising:

acquiring a current engine maintenance report, and storing the current engine fault information, the current engine basic information, the current engine maintenance report and the current engine sales file to the model building data set;

5. The engine high incidence failure cause determination method according to claim 1, further comprising, before inputting the current engine failure information, the current engine basic information, and the current engine sales profile into a pre-trained engine high incidence failure cause determination model:

6. The engine high-occurrence failure cause determination method according to claim 1, wherein the determining a target engine high-occurrence failure cause from the current engine high-occurrence failure cause and the corresponding failure probability comprises:

7. The engine high-occurrence failure cause determination method according to claim 1, characterized by further comprising:

8. An engine high-incidence failure cause determination device, characterized by comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the engine high incidence failure cause determination method of any one of claims 1 to 7.

10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions for causing a processor to implement the method for determining the cause of engine high incidence failure according to any one of claims 1-7 when executed.