CN116186106A - Railway wagon fault diagnosis method, device and equipment - Google Patents
Railway wagon fault diagnosis method, device and equipment Download PDFInfo
- Publication number
- CN116186106A CN116186106A CN202211626952.5A CN202211626952A CN116186106A CN 116186106 A CN116186106 A CN 116186106A CN 202211626952 A CN202211626952 A CN 202211626952A CN 116186106 A CN116186106 A CN 116186106A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- railway
- freight car
- wagon
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physiology (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method, a device and equipment for diagnosing faults of a railway wagon, wherein the method comprises the following steps: acquiring historical maintenance data of the railway freight car from an external system, wherein the historical maintenance data of the railway freight car comprises fault mode data, freight car operation data and fault reason data; searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set; encoding historical maintenance data of the railway freight car and a frequent item set of a railway freight car fault mode based on a genetic algorithm to obtain an initial group; and sequentially performing selection operation, cross operation and mutation operation on the initial population to obtain an association rule set for truck fault diagnosis. The efficiency and the accuracy of the fault diagnosis of the railway freight car are improved, a set of efficient and accurate fault diagnosis modes are established for the railway freight car, faults can be quickly and accurately found and diagnosed, and the safety of railway freight is guaranteed.
Description
Technical Field
The embodiment of the invention relates to the technical field of railway freight, in particular to a method, a device and equipment for diagnosing faults of a railway freight car.
Background
The heavy load high speed is the main development direction of railway freight in China, and has achieved a long-term development. However, with the continuous increase of the running speed and the continuous increase of the bearing of the railway freight car, the fault occurrence probability of the railway freight car is gradually increased, and adverse effects on the running safety of the railway freight car, the quality and efficiency of railway transportation and the like are further generated, so that higher requirements are put forward on the aspects of safety, operation, overhaul and the like of the railway freight car. The railway freight car is an important link for ensuring the safety and smoothness of railway transportation by using maintenance work, and is an important component of railway transportation.
At present, a fault diagnosis mode of manual detection is often adopted in railway freight car operation maintenance work, and the fault diagnosis of the railway freight car is realized by prolonging the operation safety guarantee section of the railway freight car, and completing all steps according to maintenance rules through the periodic maintenance processes of station maintenance, section maintenance and factory maintenance. However, with the improvement of railway freight technology and actual demands, the railway is accelerated in a large area, the heavy-load transportation technology is changed, the transportation capacity of the railway freight car is continuously improved, and meanwhile, under the demands of intelligent railway freight car system and great improvement of performance, the components of the railway freight car are more complex, so that the fault diagnosis difficulty of the railway freight car is improved. The fault diagnosis of the railway freight car is completed within the limited technical detection operation time, and higher requirements are put forward on technical operation means and operation capacity of an online repair operation field of the railway freight car, and the existing fault diagnosis mode of manual detection cannot meet the current high-efficiency railway transportation requirement.
Disclosure of Invention
The embodiment of the invention provides a method, a device and equipment for diagnosing faults of a railway wagon, which are used for solving the problem that the existing manual detection fault diagnosis mode is low in efficiency.
In a first aspect, an embodiment of the present invention provides a method for diagnosing a rail wagon fault, including:
acquiring historical maintenance data of the railway freight car from an external system, wherein the historical maintenance data of the railway freight car comprises fault mode data, freight car operation data and fault reason data;
searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set;
encoding historical maintenance data of the railway freight car and a frequent item set of a railway freight car fault mode based on a genetic algorithm to obtain an initial group;
and sequentially performing selection operation, cross operation and mutation operation on the initial population to obtain an association rule set for truck fault diagnosis.
In one embodiment, the external system includes a truck administration management information system, a truck historian information system, and a truck status monitoring maintenance system, and obtaining rail truck historian maintenance data from the external system includes:
acquiring 5T early warning information, 5T fixed inspection resume information, bad truck information, additional truck information, train inspection truck running state ground safety monitoring system information, train inspection truck rolling bearing early fault acoustic diagnosis system information and platform truck buckling and closing information from a truck operation management information system;
Acquiring maintenance three accompanying data and implementation information of railway wagon station maintenance, section maintenance and factory maintenance from a wagon resume information system;
technical states, running tracks and passing information of the railway wagon train and the vehicles are obtained from the wagon state monitoring and maintaining system.
In one embodiment, prior to searching the failure mode dataset using the Apriori algorithm, the method further comprises performing at least one of the following on the rail wagon historical service data:
deleting historical maintenance data of the railway freight car with the data classification labels missing;
filling blank values in historical maintenance data of the railway freight car by adopting a preset default value or a preset calculation mode;
replacing numerical data in the historical maintenance data of the railway freight car by using a historical average value;
using the average value of the front and rear values of the current data to replace the value of the current data, and performing data smoothing on the historical maintenance data of the railway freight car;
the historical maintenance data of the rail wagons of the same type are divided into the same type;
deleting abnormal data in the historical maintenance data of the railway freight car;
performing data generalization on historical maintenance data of the railway freight car by using a concept layering method;
scaling historical maintenance data of the railway freight car and converting the historical maintenance data into a preset range;
And carrying out semantic recognition and unification on the vehicle number, the vehicle type, the fault digit, the fault code, the fault name, the component type, the component name, the component code, the replacement time, the starting time, the cut-off time, the characteristic parameter value of the component, the total mileage, the empty mileage and the heavy mileage by adopting the vehicle type unique code and the component unique code.
In one embodiment, searching the failure mode dataset using an Apriori algorithm, forming a frequent item set for a rail wagon failure mode comprises:
initializing a fault mode data set, scanning a first data record in the fault mode data set, determining the number of data items of the data record currently scanned as the maximum number of data items, and creating a candidate set according to the maximum number of data items;
and sequentially scanning the next data record in the fault mode data set, if the number of data items of the data record which is currently scanned is smaller than or equal to the maximum number of data items, updating the candidate set, otherwise, updating the maximum number of data items to the number of data items of the data record which is currently scanned, creating a new candidate set according to the updated maximum number of data items until the last data record in the fault mode data set is scanned, and obtaining a frequent item set of the fault mode of the railway wagon.
In one embodiment, encoding the rail wagon historical maintenance data and the rail wagon failure mode frequent item set based on the genetic algorithm includes:
initializing population planning, crossover probability and variation probability in a genetic algorithm, wherein the population planning is initialized to be 300-500, the crossover probability is initialized to be 0.4-0.9, and the variation probability is initialized to be 0.01-0.1;
the fault characteristic values are divided into different grades, an integer array is adopted to encode a frequent item set of the railway wagon fault mode, a chromosome is used to represent an association rule, the association rule comprises a front part and a rear part, the front part comprises part codes and fault codes, and the rear part comprises fault characteristic value attribute information related to parts and faults.
In one embodiment, the fitness function employed in the genetic algorithm is determined according to the following expression:
Fitness＝S′/S；
wherein Fitness represents a Fitness function, S' represents the support degree of a new rule formed by genetic operation, and S represents a support degree threshold value given by a user.
In one embodiment, sequentially performing the selecting operation, the crossing operation, and the mutating operation on the initial population includes:
selecting an association rule with a fitness greater than 1 from the initial population;
Performing single-point cross operation on the selected association rule;
and randomly selecting variant individuals from the association rules after the cross operation by adopting preset variation probability to carry out variation.
In a second aspect, an embodiment of the present invention provides a railway wagon fault diagnosis apparatus, including:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring historical maintenance data of a railway wagon from an external system, and the historical maintenance data of the railway wagon comprises fault mode data, wagon operation data and fault reason data;
the searching module is used for searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set;
the coding module is used for coding the historical maintenance data of the railway freight car and the frequent item set of the fault mode of the railway freight car based on a genetic algorithm to obtain an initial group;
and the processing module is used for sequentially carrying out selection operation, cross operation and mutation operation on the initial group to obtain an association rule set for truck fault diagnosis.
In a third aspect, an embodiment of the present invention provides a rail wagon fault diagnosis apparatus, including:
at least one processor and memory;
the memory stores computer-executable instructions;
at least one processor executes computer-executable instructions stored in a memory, causing the at least one processor to perform the rail wagon fault diagnosis method of any of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium having stored therein computer executable instructions for implementing the rail wagon fault diagnosis method according to any of the first aspects when executed by a processor.
According to the railway wagon fault diagnosis method, device and equipment provided by the embodiment of the invention, the historical maintenance data of the railway wagon is obtained from an external system, and the historical maintenance data of the railway wagon comprises fault mode data, wagon operation data and fault reason data; searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set; encoding historical maintenance data of the railway freight car and a frequent item set of a railway freight car fault mode based on a genetic algorithm to obtain an initial group; and sequentially performing selection operation, cross operation and mutation operation on the initial population to obtain an association rule set for truck fault diagnosis. The efficiency and the accuracy of the fault diagnosis of the railway freight car are improved, a set of efficient and accurate fault diagnosis modes are established for the railway freight car, faults can be quickly and accurately found and diagnosed, and the safety of railway freight is guaranteed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow chart of a rail wagon fault diagnosis method provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a truck fault diagnosis association rule mining model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a railway wagon fault diagnosis device according to an embodiment of the present invention;
fig. 4 is a schematic structural view of a railway wagon fault diagnosis apparatus according to an embodiment of the present invention.
Specific embodiments of the present invention have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
The invention will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted, or replaced by other elements, materials, or methods in different situations. In some instances, some operations associated with the present application have not been shown or described in the specification to avoid obscuring the core portions of the present application, and may not be necessary for a person skilled in the art to describe in detail the relevant operations based on the description herein and the general knowledge of one skilled in the art.
Furthermore, the described features, operations, or characteristics of the description may be combined in any suitable manner in various embodiments. Also, various steps or acts in the method descriptions may be interchanged or modified in a manner apparent to those of ordinary skill in the art. Thus, the various orders in the description and drawings are for clarity of description of only certain embodiments, and are not meant to be required orders unless otherwise indicated.
The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning. The terms "coupled" and "connected," as used herein, are intended to encompass both direct and indirect coupling (coupling), unless otherwise indicated.
Although the existing manual detection fault diagnosis modes of station repair, section repair and factory repair according to the overhaul rules are low in efficiency, after the manual fault diagnosis and maintenance are carried out, various information in the fault diagnosis process, such as reasons, positions and repair methods of faults, is recorded, and the information can provide effective references for later fault diagnosis. However, as these historical data are numerous and cluttered and are stored and distributed in different databases, and as rail wagon systems become more complex, there is an increasing ambiguity between the symptoms and causes of the fault, and often no effective correlation between the fault and the characteristics causing the fault can be derived directly from these information. How to provide support for the fault diagnosis of rail wagons and the acquisition of effective repair plans based on these information is of great research importance.
According to the method, massive data assets in a truck application management information system, a truck resume information system and a truck state monitoring maintenance system (HCCBM) are fully utilized, data required by fault diagnosis are integrated and fused by means of data integration and data mining technology, massive fault data and railway truck part state data are integrated, association rules between truck faults and fault reasons are found in the massive data, an improved Apriori algorithm is utilized to search an association rule set, the efficiency and accuracy of association rule generation are optimized by means of a genetic algorithm of a heuristic intelligent algorithm, the problems of the efficiency and accuracy of association rule generation of truck faults and fault reasons are mainly solved, faults are found out rapidly and accurately, diagnosis is conducted, support is provided for railway truck fault diagnosis level improvement, and further safety of railway freight is guaranteed. The present application will be described in detail with reference to specific examples.
Fig. 1 is a flowchart of a rail wagon fault diagnosis method according to an embodiment of the present invention. As shown in fig. 1, the method for diagnosing a railway wagon fault provided in the present embodiment may include:
s101, acquiring historical maintenance data of the railway freight car from an external system, wherein the historical maintenance data of the railway freight car comprises fault mode data, freight car operation data and fault reason data.
The external systems in this embodiment may include a truck administration management information system, a truck biography information system, and a truck status monitoring maintenance system (HCCBM). Historical fault data, implementation method, technical state of the vehicle, running track and passing information of the railway wagon are all key basis for fault diagnosis of the running vehicle. In this embodiment, a data integration service (API) manner is adopted, and by acquiring historical fault data, semantic recognition and business penetration of different data of the heterogeneous information system are performed from a fault diagnosis dimension.
And according to the fault diagnosis requirement of the railway freight car, the required business data information is combed and identified. In particular, the obtaining of the rail wagon historical maintenance data from the external system may include: acquiring 5T early warning information, 5T fixed inspection history information, bad truck information, additional truck information, train inspection truck running state ground safety monitoring system information (TPDS), train inspection truck rolling bearing early fault acoustic diagnosis system information (TADS) and platform truck buckling and closing information from a truck operation management information system; acquiring maintenance three accompanying data and implementation information of railway wagon station maintenance, section maintenance and factory maintenance from a wagon resume information system; technical states, running tracks and passing information of the railway wagon train and the vehicles are obtained from the wagon state monitoring and maintaining system. It should be noted that 5T refers to a vehicle axle temperature intelligent detection system (Trace Hotbox Detection System, THDS), a truck operation state ground safety monitoring system (Truck Performance Detection System, TPDS), a rail side acoustic diagnostic system (Trackside Acoustic Detection System, TADS) for early failure of a rolling bearing of a railway truck, a truck wheel set size dynamic detection system (Trouble of Wheel Detection System, TWDS), and a railway truck operation failure dynamic image monitoring system (Trouble of moving Freight car Detection System, TFDS).
And through connection of the external data source system, information such as truck component faults, truck operation management, truck faults and operation rules and the like are acquired according to requirements, and success information is returned to the external system. And storing the involutory data into a database table for subsequent data mining and application service, and restarting retransmission service by a data source terminal if the data access fails. And checking and identifying the nonstandard data, converting the nonstandard data into qualified data through a data preprocessing service, and storing the qualified data into a database table.
In the embodiment, through combing the railway fault diagnosis service data information and designing the data integration service flow, the opening and access of the railway application management system, the truck resume system and the HCCBM system data link can be obtained, and the service data of truck fault data, operation data, history maintenance and the like are ensured to be communicated in terms of methods and mechanisms, so that the foundation of the association rule between the truck fault and the influence factors is provided. The truck fault mode data set, the fault reason data set and the data set combining the fault mode and the fault reason are formed through integration of an external system, so that the basis of truck fault diagnosis association rule mining is formed.
S102, searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set.
The Apriori algorithm is the most powerful algorithm for mining frequent item sets of boolean association rules. In this embodiment, the search of the frequent item set of the truck fault mode may use an improved Apriori algorithm, and after scanning the first data record in the truck fault mode data set, create a candidate set, sequentially scan the data records in the truck fault mode data set, update and create the candidate set until the frequent set of the truck fault mode is finally formed.
S103, encoding historical maintenance data of the railway freight car and a frequent item set of the fault mode of the railway freight car based on a genetic algorithm to obtain an initial group.
S104, sequentially performing selection operation, cross operation and mutation operation on the initial population to obtain an association rule set for truck fault diagnosis.
On the basis of obtaining a truck fault frequent item set through an improved Apriori algorithm, the frequent item set is encoded by means of a genetic algorithm, and an association rule set for truck fault diagnosis is obtained through selection, crossing and mutation operations.
Through integrating external system data, in the mass freight car operation management fault data and operation data, the association rule required by freight car fault diagnosis is searched and determined so as to form a strong association rule between freight car part faults and characteristic values thereof. Through the excavation of the truck fault diagnosis association rules, potential fault modes and possible reasons causing faults in the truck operation process can be identified and analyzed in advance, the quick completion of fault diagnosis work is facilitated, and support is provided for each repair Cheng Shixiu of the railway. Referring to fig. 2, the truck fault diagnosis association rule mining model is shown. The model is based on truck fault history data, takes the frequent item set search of fault modes and the generation of fault diagnosis association rules as keys, and takes the fault diagnosis feature data of the association rules between the mining fault modes and the fault occurrence causes as targets to energize railway truck fault diagnosis business. In the future, an artificial intelligent algorithm can be fused, and the prediction of the railway wagon faults can be realized through constructing a fault prediction model and analyzing and calculating big data.
The embodiment provides a railway wagon fault diagnosis method for accessing, processing and storing data related to a railway wagon in an external system by means of a data integration technology, constructing a railway wagon fault diagnosis association rule model, mining railway wagon fault association rules based on an improved Apriori algorithm and a genetic algorithm, and supporting each stage of repair and online repair of the railway wagon.
According to the railway wagon fault diagnosis method provided by the embodiment, historical railway wagon maintenance data are obtained from an external system, wherein the historical railway wagon maintenance data comprise fault mode data, wagon operation data and fault reason data; searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set; encoding historical maintenance data of the railway freight car and a frequent item set of a railway freight car fault mode based on a genetic algorithm to obtain an initial group; and sequentially performing selection operation, cross operation and mutation operation on the initial population to obtain an association rule set for truck fault diagnosis. The efficiency and the accuracy of the fault diagnosis of the railway freight car are improved, a set of efficient and accurate fault diagnosis modes are established for the railway freight car, faults can be quickly and accurately found and diagnosed, and the safety of railway freight is guaranteed.
Based on the above embodiment, in order to further improve the efficiency and accuracy of the fault diagnosis of the railway wagon, preprocessing such as data cleaning, data transformation and data penetration needs to be performed on massive data acquired from an external system, so as to eliminate the problems of inconsistent data, irregular data, voice and the like in the massive data.
Data cleaning of mass data acquired from an external system may include, for example: incomplete data acquired from an external system, such as brake shoe wear, train passing information and the like, can be processed according to the importance and service attribute of the data. Specifically, when the data classification label is missing, the data is ignored; the null value can be obtained by default or by a calculation formula; historical averages may be used instead for numerical data. For the data with noise obtained from the external system, that is, the data may have errors and errors in the measurement process, specifically, may be: the box division method is to replace the current value according to the front and back values of the current data, so that the effect of smoothing the data, such as the wear thickness of a brake shoe of ten thousand kilometers, is achieved; clustering, namely dividing the data of the same type into the same type, and dividing abnormal data out and neglecting the record of the value; manual inspection may be used to remove certain values that are negative or that exceed conventional values that are judged to be abnormal, such as truck speed.
The data transformation of the mass data acquired from the external system may include, for example: when data representing the same business semantics obtained from a plurality of external data sources have different data types and expression forms, the data is processed by a data conversion mode. Specifically, a data generalization method can be adopted, when the data values are more, a conceptual layering method can be used for converting the data, such as the speed of a truck, and generalization can be carried out to low speed, medium speed and high speed; scaling the data according to a certain proportion by adopting a zero-mean value (z-score) and a specified range mode, so that the data are uniformly distributed in the specified range; attribute construction, to increase the effectiveness of subsequent data mining, new attributes are added to the original data, such as truck speed, increasing the rate of change of hour speed.
The data penetration of the mass data acquired from the external system may include, for example: the goods train has a plurality of components, and by using the vehicle type unique code and the component unique code which are unified in the whole way, the information such as the vehicle number, the vehicle type, the fault digit, the fault code, the fault name, the component type, the component name, the component code, the replacement time, the starting time, the cut-off time, the characteristic parameter value of the component, the total mileage, the empty mileage, the heavy mileage and the like can be semantically identified and unified. And on the basis, the comprehensive business information is fused, so that the fusion and communication of the multisource external system data are realized, and complete and timely railway wagon repair data information is formed.
In summary, in the method for diagnosing a rail wagon fault provided in the present embodiment, before searching the fault mode dataset by adopting the Apriori algorithm, at least one of the following operations is performed on the rail wagon historical maintenance data:
deleting historical maintenance data of the railway freight car with the data classification labels missing;
filling blank values in historical maintenance data of the railway freight car by adopting a preset default value or a preset calculation mode;
replacing numerical data in the historical maintenance data of the railway freight car by using a historical average value;
Using the average value of the front and rear values of the current data to replace the value of the current data, and performing data smoothing on the historical maintenance data of the railway freight car;
the historical maintenance data of the rail wagons of the same type are divided into the same type;
deleting abnormal data in the historical maintenance data of the railway freight car;
performing data generalization on historical maintenance data of the railway freight car by using a concept layering method;
scaling historical maintenance data of the railway freight car and converting the historical maintenance data into a preset range;
and carrying out semantic recognition and unification on the vehicle number, the vehicle type, the fault digit, the fault code, the fault name, the component type, the component name, the component code, the replacement time, the starting time, the cut-off time, the characteristic parameter value of the component, the total mileage, the empty mileage and the heavy mileage by adopting the vehicle type unique code and the component unique code.
How to search the failure mode dataset will be further described by specific embodiments to form a rail wagon failure mode frequent item set. The method specifically comprises the following steps:
step 1: initializing a truck fault mode data set, scanning data records subjected to service through truck operation management, obtaining the number of recorded data items, defaulting the number of the data items to the maximum number of the data items, and simultaneously creating a candidate set C of the number of the data records 1 ,C 2 ,...，C n The number of candidate sets is equal to the maximum number of data items.
Step 2: scanning the next record and obtaining the number of data items of the record, updating the original candidate set if the number of the data items is smaller than or equal to the maximum number of the items, otherwise, creating a new candidate set, updating the maximum number of the data items at the moment, and creating the new candidate set so that the number of the candidate sets is equal to the maximum number of the items at the moment.
Step 3: in the above step, each time a record is scanned, it is determined whether it is the last record of the truck failure mode dataset. And (3) after the last record is scanned, completing the process of searching the frequent set of the fault mode of the truck, otherwise, repeatedly executing the step (2), and directly completing the scanning of all records.
That is, in the method for diagnosing a railway wagon fault provided in this embodiment, searching the fault mode data set by using Apriori algorithm on the basis of any one of the embodiments, the forming of the frequent item set of the railway wagon fault mode may specifically include: initializing a fault mode data set, scanning a first data record in the fault mode data set, determining the number of data items of the data record currently scanned as the maximum number of data items, and creating a candidate set according to the maximum number of data items; and sequentially scanning the next data record in the fault mode data set, if the number of data items of the data record which is currently scanned is smaller than or equal to the maximum number of data items, updating the candidate set, otherwise, updating the maximum number of data items to the number of data items of the data record which is currently scanned, creating a new candidate set according to the updated maximum number of data items until the last data record in the fault mode data set is scanned, and obtaining a frequent item set of the fault mode of the railway wagon.
The method has important significance for diagnosing the faults of the truck parts based on the association rule between the historical maintenance data mining fault mode and the fault reasons of the truck. According to the railway wagon fault diagnosis method provided by the embodiment, on the basis of any embodiment, on the basis of constructing a wagon fault diagnosis association rule mining model, an improved Apriori algorithm is designed and used for searching wagon fault frequent item sets, and the defects that the traditional algorithm is low in execution efficiency and a large number of candidate item sets can be generated are overcome.
How the historical maintenance data of the railway freight car and the frequent item sets of the fault modes of the railway freight car are encoded based on genetic algorithms will be further described by specific embodiments. The method specifically comprises the following steps: firstly, various parameters of a genetic algorithm are required to be initialized, and then, the method of integer data is adopted for encoding. The initialization parameters may specifically include: the railway freight car has more parts, frequent faults, and abundant historical faults and implementation data, so that the initialization group planning is selected from 300 to 500; meanwhile, in order to avoid the premature problem of the genetic algorithm, a strategy of a fixed value is adopted for the crossover probability and the mutation probability, the crossover probability is selected from 0.4 to 0.9 when the strategy is applied, and the mutation probability is selected from 0.01 to 0.1. The encoding process may specifically include: the method of dividing the fault characteristic value into different grades firstly and then adopting an integer array to encode is adopted, and meanwhile, one chromosome is expressed as a solution, which also represents an association rule. The association rule is divided into a front part and a rear part, wherein the front part comprises part codes and fault codes, the rear part comprises characteristic value attribute information related to the parts and faults, such as a characteristic value 1 (such as the wear thickness of a brake shoe), a characteristic value 2 (the running mileage), a characteristic value 3 (the total mileage) … … and a characteristic value n (the total running duration), and the association rules of different parts and faults are different.
The number of elements of the integer array corresponds to the number of fields in the transaction database, the elements of the integer array representing the attribute value of the field and 0 representing this attribute independent of other attributes. The individual codes of the transaction database are shown in table 1, and table 1 is a rule code.
TABLE 1
That is, in the method for diagnosing a railway wagon fault provided in this embodiment, the encoding of the historical maintenance data of the railway wagon and the frequent item set of the railway wagon fault mode based on the genetic algorithm may specifically include: initializing population planning, crossover probability and variation probability in a genetic algorithm, wherein the population planning is initialized to be 300-500, the crossover probability is initialized to be 0.4-0.9, and the variation probability is initialized to be 0.01-0.1; the fault characteristic values are divided into different grades, an integer array is adopted to encode a frequent item set of the railway wagon fault mode, a chromosome is used to represent an association rule, the association rule comprises a front part and a rear part, the front part comprises part codes and fault codes, and the rear part comprises fault characteristic value attribute information related to parts and faults.
According to the railway wagon fault diagnosis method, the heuristic intelligent genetic algorithm is led into the generation of the association rule, the design of a solution for causing the multi-dimensional reasons of wagon faults is solved by designing an integer array coding mode aiming at the generated wagon fault frequent item set, and reasonable selection intervals of the size of the initialized group, the variation probability and the cross probability are provided, so that the method is suitable for the generation of the wagon fault data association rule, and the accuracy and the efficiency of wagon fault diagnosis can be guaranteed.
The fitness function is the only interface between the genetic algorithm and the business application problem, and the construction of the fitness function directly influences the solving efficiency. In this embodiment, the support degree is used as a measure for the importance of the association rule, that is, the greater the support degree, the more important the association rule.
fitness(R i )＝S'/S
Wherein S' is the support of a new rule formed by genetic operation, and S is the support threshold value given by the user. R is R i R is the fault association rule of the ith truck i When the truck fault association rule meets the preset requirement, the fitness function value is larger than 1, otherwise, the rule is eliminated in the next generation of genetic variation.
That is, in the rail wagon fault diagnosis method provided in this embodiment on the basis of any one of the above embodiments, the fitness function adopted in the genetic algorithm is determined according to the following expression:
Fitness＝S′/S；
wherein Fitness represents a Fitness function, S' represents the support degree of a new rule formed by genetic operation, and S represents a support degree threshold value given by a user.
In the railway wagon fault diagnosis method provided by the embodiment, the ratio of the supporting degree to the threshold value of the supporting degree accepted by the user is innovatively used as the fitness, the defect that a large number of useless rules are generated by using the supporting degree and the confidence degree as the strong association rule judgment basis in the prior art is overcome, and the guarantee is provided for the wagon fault diagnosis accuracy and efficiency.
The quality of the genetic operator determines the searching capability and convergence of the algorithm to the fault diagnosis association rule, so that how to determine the selection operator, the crossover operator and the mutation operator has great influence on the whole genetic algorithm, and further has great influence on the efficiency and the accuracy of the fault diagnosis of the railway wagon. How the selection operator, the crossover operator and the mutation operator are determined will be described in detail in sequence. Selecting an operator: for truck fault association rules, two individuals with higher fitness are unlikely to generate an individual with high fitness, and two individuals with lower fitness are likely to reproduce an individual with high fitness, so roulette selection is not adopted in the embodiment, and association rules with fitness greater than 1 are adopted; crossover operator: the bit string of the integer array codes used in the method is not long, and the risk that a better mode is saved is not facilitated because the multi-point intersection influences the result of an individual is considered, so that a single-point intersection is adopted as a selection strategy of an intersection operator; mutation operator: in this embodiment, when determining the mutation algorithm, a mutation individual is randomly selected in the population with a certain mutation probability, and after the mutation, each position of the gene segment of the individual is mutated, and each gene of the gene segment sequentially takes a value within the allowable value range, so as to ensure that each attribute value exists after mutation.
That is, in the method for diagnosing a railway wagon fault according to any one of the embodiments, the selecting operation, the crossing operation and the mutation operation are sequentially performed on the initial group, including: selecting an association rule with a fitness greater than 1 from the initial population; performing single-point cross operation on the selected association rule; and randomly selecting variant individuals from the association rules after the cross operation by adopting preset variation probability to carry out variation.
Fig. 3 is a schematic structural diagram of a railway wagon fault diagnosis device according to an embodiment of the present invention. As shown in fig. 3, the railway wagon fault diagnosis apparatus 30 provided in the present embodiment may include: an acquisition module 301, a search module 302, an encoding module 303 and a processing module 304.
An acquisition module 301, configured to acquire rail wagon historical maintenance data from an external system, where the rail wagon historical maintenance data includes failure mode data, wagon operation data, and failure cause data;
the searching module 302 is configured to search the failure mode dataset by using an Apriori algorithm to form a frequent item set of the railway wagon failure mode;
the encoding module 303 is used for encoding historical maintenance data of the railway freight car and a frequent item set of a fault mode of the railway freight car based on a genetic algorithm to obtain an initial group;
And the processing module 304 is used for sequentially performing a selection operation, a cross operation and a mutation operation on the initial population to obtain an association rule set for truck fault diagnosis.
In an alternative embodiment, the external system includes a truck operation management information system, a truck history information system, and a truck status monitoring maintenance system, and the obtaining module 301 configured to obtain the historical maintenance data of the railway truck from the external system may specifically include:
acquiring 5T early warning information, 5T fixed inspection resume information, bad truck information, additional truck information, train inspection truck running state ground safety monitoring system information, train inspection truck rolling bearing early fault acoustic diagnosis system information and platform truck buckling and closing information from a truck operation management information system;
acquiring maintenance three accompanying data and implementation information of railway wagon station maintenance, section maintenance and factory maintenance from a wagon resume information system;
technical states, running tracks and passing information of the railway wagon train and the vehicles are obtained from the wagon state monitoring and maintaining system.
In an alternative embodiment, the rail wagon fault diagnosis device 30 may further comprise a preprocessing module (not shown in the figure) for performing at least one of the following operations on the rail wagon historical maintenance data before searching the fault mode data set using the Apriori algorithm:
Deleting historical maintenance data of the railway freight car with the data classification labels missing;
filling blank values in historical maintenance data of the railway freight car by adopting a preset default value or a preset calculation mode;
replacing numerical data in the historical maintenance data of the railway freight car by using a historical average value;
using the average value of the front and rear values of the current data to replace the value of the current data, and performing data smoothing on the historical maintenance data of the railway freight car;
the historical maintenance data of the rail wagons of the same type are divided into the same type;
deleting abnormal data in the historical maintenance data of the railway freight car;
performing data generalization on historical maintenance data of the railway freight car by using a concept layering method;
scaling historical maintenance data of the railway freight car and converting the historical maintenance data into a preset range;
and carrying out semantic recognition and unification on the vehicle number, the vehicle type, the fault digit, the fault code, the fault name, the component type, the component name, the component code, the replacement time, the starting time, the cut-off time, the characteristic parameter value of the component, the total mileage, the empty mileage and the heavy mileage by adopting the vehicle type unique code and the component unique code.
In an alternative embodiment, the searching module 302 is configured to search the failure mode dataset by using Apriori algorithm, and forming the frequent item set of the railway wagon failure mode may specifically include:
Initializing a fault mode data set, scanning a first data record in the fault mode data set, determining the number of data items of the data record currently scanned as the maximum number of data items, and creating a candidate set according to the maximum number of data items;
and sequentially scanning the next data record in the fault mode data set, if the number of data items of the data record which is currently scanned is smaller than or equal to the maximum number of data items, updating the candidate set, otherwise, updating the maximum number of data items to the number of data items of the data record which is currently scanned, creating a new candidate set according to the updated maximum number of data items until the last data record in the fault mode data set is scanned, and obtaining a frequent item set of the fault mode of the railway wagon.
In an alternative embodiment, the encoding module 303 is configured to encode the historical maintenance data of the railway freight car and the frequent item set of failure modes of the railway freight car based on a genetic algorithm may specifically include:
initializing population planning, crossover probability and variation probability in a genetic algorithm, wherein the population planning is initialized to be 300-500, the crossover probability is initialized to be 0.4-0.9, and the variation probability is initialized to be 0.01-0.1;
The fault characteristic values are divided into different grades, an integer array is adopted to encode a frequent item set of the railway wagon fault mode, a chromosome is used to represent an association rule, the association rule comprises a front part and a rear part, the front part comprises part codes and fault codes, and the rear part comprises fault characteristic value attribute information related to parts and faults.
In an alternative embodiment, the fitness function employed in the genetic algorithm is determined according to the following expression:
Fitness＝S′/S；
wherein Fitness represents a Fitness function, S' represents the support degree of a new rule formed by genetic operation, and S represents a support degree threshold value given by a user.
In an alternative embodiment, the processing module 304 is configured to sequentially perform a selection operation, a crossover operation, and a mutation operation on the initial population may specifically include:
selecting an association rule with a fitness greater than 1 from the initial population;
performing single-point cross operation on the selected association rule;
and randomly selecting variant individuals from the association rules after the cross operation by adopting preset variation probability to carry out variation.
The embodiment of the invention also provides a rail wagon fault diagnosis, please refer to fig. 4, and the embodiment of the invention is only illustrated by taking fig. 4 as an example, and the invention is not limited thereto. Fig. 4 is a schematic structural view of a railway wagon fault diagnosis apparatus according to an embodiment of the present invention. As shown in fig. 4, the railway wagon fault diagnosis apparatus 40 provided in the present embodiment may include: memory 401, processor 402, and bus 403. Wherein the bus 403 is used to implement the connections between the elements.
The memory 401 stores a computer program, which when executed by the processor 402 can implement the technical solution of any of the above-mentioned method embodiments.
Wherein the memory 401 and the processor 402 are electrically connected directly or indirectly to enable transmission or interaction of data. For example, the elements may be electrically coupled to each other via one or more communication buses or signal lines, such as via bus 403. The memory 401 stores therein a computer program for implementing a railway wagon fault diagnosis method, including at least one software functional module which may be stored in the memory 401 in the form of software or firmware, and the processor 402 executes various functional applications and data processing by running the software program and the module stored in the memory 401.
The Memory 401 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory 401 is used for storing a program, and the processor 402 executes the program after receiving an execution instruction. Further, the software programs and modules within the memory 401 described above may also include an operating system, which may include various software components and/or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.
The processor 402 may be an integrated circuit chip with signal processing capabilities. The processor 402 may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), and the like. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. It will be appreciated that the configuration of fig. 4 is merely illustrative and may include more or fewer components than shown in fig. 4 or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware and/or software.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the technical solution of any of the method embodiments described above.
The various embodiments in this disclosure are described in a progressive manner, and identical and similar parts of the various embodiments are all referred to each other, and each embodiment is mainly described as different from other embodiments.
The scope of the present disclosure is not limited to the above-described embodiments, and it is apparent that various modifications and variations can be made to the present disclosure by those skilled in the art without departing from the scope and spirit of the disclosure. Such modifications and variations are intended to be included herein within the scope of the following claims and their equivalents.
Claims (10)
1. A railway wagon fault diagnosis method, characterized by comprising:
acquiring historical maintenance data of a railway wagon from an external system, wherein the historical maintenance data of the railway wagon comprises fault mode data, wagon operation data and fault reason data;
searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set;
encoding the historical maintenance data of the railway freight car and the frequent item set of the railway freight car fault mode based on a genetic algorithm to obtain an initial group;
and sequentially performing selection operation, cross operation and mutation operation on the initial population to obtain an association rule set for truck fault diagnosis.
2. The method of claim 1, wherein the external system includes a truck administration management information system, a truck history information system, and a truck status monitoring maintenance system, the obtaining rail truck history maintenance data from the external system comprising:
Acquiring 5T early warning information, 5T fixed inspection resume information, bad truck information, additional truck information, train inspection truck running state ground safety monitoring system information, train inspection truck rolling bearing early fault acoustic diagnosis system information and platform truck buckling and closing information from the truck operation management information system;
acquiring maintenance three accompanying data and implementation information of railway wagon station maintenance, section maintenance and factory maintenance from the wagon resume information system;
and acquiring technical states, running tracks and passing information of the train and the vehicle of the railway freight car from the freight car state monitoring and maintaining system.
3. The method of claim 1, wherein prior to searching the failure mode dataset using the Apriori algorithm, the method further comprises performing at least one of the following on the rail wagon historical service data:
deleting historical maintenance data of the railway freight car with the data classification labels missing;
filling blank values in historical maintenance data of the railway freight car by adopting a preset default value or a preset calculation mode;
replacing numerical data in the historical maintenance data of the railway freight car by using a historical average value;
using the average value of the front and rear values of the current data to replace the value of the current data, and performing data smoothing on the historical maintenance data of the railway freight car;
The historical maintenance data of the rail wagons of the same type are divided into the same type;
deleting abnormal data in the historical maintenance data of the railway freight car;
performing data generalization on historical maintenance data of the railway freight car by using a concept layering method;
scaling historical maintenance data of the railway freight car and converting the historical maintenance data into a preset range;
and carrying out semantic recognition and unification on the vehicle number, the vehicle type, the fault digit, the fault code, the fault name, the component type, the component name, the component code, the replacement time, the starting time, the cut-off time, the characteristic parameter value of the component, the total mileage, the empty mileage and the heavy mileage by adopting the vehicle type unique code and the component unique code.
4. The method of claim 1, wherein searching the failure mode dataset using an Apriori algorithm to form a frequent set of railway wagon failure modes comprises:
initializing a fault mode data set, scanning a first data record in the fault mode data set, determining the number of data items of the data record currently scanned as the maximum number of data items, and creating a candidate set according to the maximum number of data items;
and sequentially scanning the next data record in the fault mode data set, if the number of data items of the data record which is currently scanned is smaller than or equal to the maximum number of data items, updating the candidate set, otherwise, updating the maximum number of data items to the number of data items of the data record which is currently scanned, and creating a new candidate set according to the updated maximum number of data items until the last data record in the fault mode data set is scanned, so as to obtain a frequent item set of the railway wagon fault mode.
5. The method of claim 1, wherein the encoding the rail wagon historical repair data and the rail wagon failure mode frequent item set based on a genetic algorithm comprises:
initializing population planning, cross probability and variation probability in a genetic algorithm, wherein the population planning is initialized to be 300-500, the cross probability is initialized to be 0.4-0.9, and the variation probability is initialized to be 0.01-0.1;
dividing fault characteristic values into different grades, adopting an integer array to encode a frequent item set of the railway wagon fault mode, and using a chromosome to represent an association rule, wherein the association rule comprises a front part and a back part, the front part comprises part codes and fault codes, and the back part comprises fault characteristic value attribute information related to parts and faults.
6. The method of claim 1, wherein the fitness function employed in the genetic algorithm is determined according to the following expression:
Fitness＝S′/S；
wherein Fitness represents a Fitness function, S' represents the support degree of a new rule formed by genetic operation, and S represents a support degree threshold value given by a user.
7. The method of claim 1, wherein sequentially performing the selecting, crossing and mutating operations on the initial population comprises:
selecting an association rule with a fitness greater than 1 from the initial population;
performing single-point cross operation on the selected association rule;
and randomly selecting variant individuals from the association rules after the cross operation by adopting preset variation probability to carry out variation.
8. A railway wagon fault diagnosis device, characterized by comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring historical maintenance data of a railway wagon from an external system, and the historical maintenance data of the railway wagon comprises fault mode data, wagon operation data and fault reason data;
the searching module is used for searching the fault mode data set by adopting an Apriori algorithm to form a railway wagon fault mode frequent item set;
the coding module is used for coding the historical maintenance data of the railway freight car and the frequent item set of the fault mode of the railway freight car based on a genetic algorithm to obtain an initial group;
and the processing module is used for sequentially carrying out selection operation, cross operation and mutation operation on the initial group to obtain an association rule set for truck fault diagnosis.
9. A railway wagon fault diagnosis apparatus, characterized by comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the rail wagon fault diagnosis method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein computer executable instructions for implementing the rail wagon fault diagnosis method according to any of claims 1-7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211626952.5A CN116186106A (en) | 2022-12-16 | 2022-12-16 | Railway wagon fault diagnosis method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211626952.5A CN116186106A (en) | 2022-12-16 | 2022-12-16 | Railway wagon fault diagnosis method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116186106A true CN116186106A (en) | 2023-05-30 |
Family
ID=86431718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211626952.5A Pending CN116186106A (en) | 2022-12-16 | 2022-12-16 | Railway wagon fault diagnosis method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116186106A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114352A (en) * | 2023-09-15 | 2023-11-24 | 北京阿帕科蓝科技有限公司 | Vehicle maintenance method, device, computer equipment and storage medium |
-
2022
- 2022-12-16 CN CN202211626952.5A patent/CN116186106A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114352A (en) * | 2023-09-15 | 2023-11-24 | 北京阿帕科蓝科技有限公司 | Vehicle maintenance method, device, computer equipment and storage medium |
| CN117114352B (en) * | 2023-09-15 | 2024-04-09 | 北京阿帕科蓝科技有限公司 | Vehicle maintenance method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8930305B2 (en) | Adaptive information processing systems, methods, and media for updating product documentation and knowledge base | |
| CN102765643B (en) | Elevator fault diagnosis and early-warning method based on data drive | |
| CN112085261B (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
| US20200134639A1 (en) | Homogeneous model of hetergeneous product lifecycle data | |
| CN103631788B (en) | Vehicle manufacture quality problems diagnostic system based on shared data bank | |
| CN109523316A (en) | The automation modeling method of commerce services model | |
| CN106161138A (en) | A kind of intelligence automatic gauge method and device | |
| CN103163877A (en) | Method and system for root cause analysis and quality monitoring of system-level faults | |
| CN116186106A (en) | Railway wagon fault diagnosis method, device and equipment | |
| Dimitrova et al. | An ontological approach for pathology assessment and diagnosis of tunnels | |
| CN111915026A (en) | Fault processing method and device, electronic equipment and storage medium | |
| CN112700185B (en) | Logistics route planning method and system based on bionic intelligent optimization | |
| Deng et al. | Analysis of failures and influence factors of critical infrastructures: a case of metro | |
| CN116579697A (en) | Cold chain full link data information management method, device, equipment and storage medium | |
| Ren et al. | A personalised operation and maintenance approach for complex products based on equipment portrait of product-service system | |
| Katreddi | Development of Machine Learning based approach to predict fuel consumption and maintenance cost of Heavy-Duty Vehicles using diesel and alternative fuels | |
| Chinta et al. | Optimal feature selection on Serial Cascaded deep learning for predictive maintenance system in automotive industry with fused optimization algorithm | |
| Ejlali et al. | Developing hybrid machine learning models to assign health score to railcar fleets for optimal decision making | |
| CN116664099A (en) | Unmanned mine car health management method based on nonparametric regression | |
| CN116384961A (en) | Predictive application method and system based on vehicle electronic and electric appliance fault prediction model | |
| Li et al. | Research on construction of crude set model of critical fault information for bus based on can-bus data | |
| CN116304620A (en) | Electronic and electrical appliance fault prediction method and system based on deep learning and data mining | |
| Makarova et al. | Improving the reliability of autonomous vehicles in a branded service system using big data | |
| Brunheroto et al. | Data analytics in fleet operations: A systematic literature review and workflow proposal | |
| CN111882219A (en) | Coal machine equipment asset management big data platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |