CN114996258A - Contact network fault diagnosis method based on data warehouse - Google Patents
Contact network fault diagnosis method based on data warehouse Download PDFInfo
- Publication number
- CN114996258A CN114996258A CN202210718355.9A CN202210718355A CN114996258A CN 114996258 A CN114996258 A CN 114996258A CN 202210718355 A CN202210718355 A CN 202210718355A CN 114996258 A CN114996258 A CN 114996258A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- real
- contact network
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003745 diagnosis Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 50
- 238000011897 real-time detection Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims description 46
- 238000010606 normalization Methods 0.000 claims description 25
- 230000009467 reduction Effects 0.000 claims description 19
- 238000013145 classification model Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000013480 data collection Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 4
- 230000003068 static effect Effects 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000012880 independent component analysis Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G06F16/21—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
- 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
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of rail transit fault detection, in particular to a data warehouse-based contact network fault diagnosis method, which comprises the following steps: acquiring corresponding characteristic data of the contact network in various states based on historical detection data of the contact network, and acquiring steady-state characteristic data in a steady-state; performing contrast clustering to obtain corresponding fault characteristic data in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data; and acquiring real-time detection data of the contact network and corresponding real-time characteristic data, comparing through a data warehouse, and outputting an identification result. On the basis of a data warehouse, various types of data such as dynamic and static detection, fault defects, inherent attributes, part inspection, external environments and the like of the contact network are unified to carry out comprehensive analysis on the contact network, so that comprehensive storage and utilization of various data types are realized, and the precision of fault diagnosis and positioning is improved.
Description
Technical Field
The invention relates to the technical field of rail transit fault detection, in particular to a data warehouse-based contact network fault diagnosis method.
Background
The contact network system is an important component of a subway traction power supply system, and generates a large amount of data in the business processes of daily operation, detection, maintenance and the like, and the data is the basis of intelligent operation and maintenance of the contact network. Therefore, it is necessary to comprehensively analyze and deeply mine these data in order to be able to serve these data for the fault Prediction and Health Management (PHM) of the catenary, thereby facilitating the transition from regular maintenance to state maintenance of the catenary.
At present, fault diagnosis and health assessment of subway overhead contact systems are mainly based on single-type data such as detection data or fault data of the overhead contact systems, for example, performance degradation assessment and residual life estimation are performed on the overhead contact systems by using dynamic and static detection data, and operation reliability of overhead contact system supporting devices is assessed based on event-type part fault data. Although the single data can evaluate the performance or fault probability of different aspects of the contact network to a certain extent, fault diagnosis and positioning cannot be carried out. The contact network is a complex system, only single type data is adopted, the relevance among different types of data is ignored, various types of data such as dynamic and static detection, fault defects, inherent attributes, part inspection and external environment of the contact network are not unified from the global angle to carry out comprehensive analysis, and fault diagnosis on the contact network is difficult to carry out comprehensively and accurately. In addition, the contact network data is usually dispersed in different service systems, and has the problems of different structures, inconsistent naming, containing of bad data, repeated content and the like, the content of different data sources is difficult to be effectively utilized, the efficiency of fault diagnosis of the contact rail system is not improved, the type of the fault can not be accurately diagnosed, and the accurate position information of the fault can not be obtained.
Disclosure of Invention
The invention provides a data warehouse-based catenary fault diagnosis method, which is used for overcoming the defects in the prior art and improving the fault diagnosis and positioning precision.
The invention provides a data warehouse-based contact network fault diagnosis method, which comprises the following steps:
acquiring characteristic data respectively corresponding to the contact network in various states based on historical detection data of the contact network, and acquiring steady-state characteristic data of the contact network in a steady-state;
comparing and clustering the characteristic data in multiple states with the steady-state characteristic data to obtain corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse, and judging whether a fault exists;
and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
The method comprises the following steps of obtaining characteristic data corresponding to the contact network in various states respectively, obtaining steady-state characteristic data of the contact network in a steady state, and specifically comprising the following steps:
acquiring historical detection data of a contact network;
carrying out normalization processing on the historical detection data, and converting various types of historical detection data into data with a numerical value between [0 and 1 ];
and performing dimension reduction processing on the data after the normalization processing to obtain characteristic data in various states.
Wherein, obtain the real-time detection data and the real-time characteristic data that correspond of contact net, include:
acquiring real-time detection data of a contact network;
carrying out normalization processing on the real-time detection data, and converting various real-time detection data into data with a numerical value between [0,1 ];
and performing dimension reduction processing on the normalized data to obtain characteristic data corresponding to various real-time detection data.
Further, before the normalization processing is performed on the detection data, the method includes:
comparing each type of detection data with a corresponding threshold, wherein the corresponding detection data higher than or equal to the threshold are unavailable data, eliminating the unavailable data, and replacing the unavailable data with the detection data lower than the threshold;
and carrying out noise reduction processing on various monitoring data.
Specifically, various types of feature data and corresponding states of a data warehouse are used as samples to input a state classification model for training, real-time detection data detected in real time are subjected to normalization processing and dimension reduction processing to obtain real-time feature data, and the real-time features are input into the trained state classification model;
and judging whether a fault exists or not through the trained state classification model, and if the fault exists, outputting a corresponding fault type.
Specifically, the detection data of the overhead contact system is fluctuation continuous data based on the line mileage or the geographic position information;
and if the fault exists, acquiring original real-time detection data corresponding to the characteristic data, and outputting the fault position according to the line mileage or the geographical position information in the original real-time detection data.
The invention also provides a data warehouse-based contact network fault diagnosis system, which comprises a data collection module, a data processing module, a feature extraction module, a data comparison module, a data warehouse and a fault diagnosis and positioning module, wherein:
the data collection module is used for acquiring various detection parameters of the contact network;
the data processing module is used for carrying out normalization processing on various detection parameters;
the characteristic extraction module is used for acquiring characteristic data respectively corresponding to the contact network in various states and acquiring steady-state characteristic data of the contact network in a steady state based on the data processed by the data processing module in a normalization mode;
the data comparison module is used for carrying out comparison clustering on the characteristic data in various states and the steady-state characteristic data, acquiring corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
the fault diagnosis and positioning module is used for acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse and judging whether a fault exists or not; and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
The present invention also provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above fault diagnosis methods when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the fault diagnosis method as described in any one of the above.
The invention provides a data warehouse-based contact network fault diagnosis method, which has the following technical effects:
(1) various cleaning and conversion operations are carried out on different data, and the data are organized together according to a certain rule to form a data warehouse, so that the data mining efficiency is effectively improved, and the comprehensive storage and utilization of various data types are realized;
(2) various fault characteristics of the subway overhead line system are integrated into a data warehouse by adopting a dimensionality reduction algorithm, and fault diagnosis and positioning of the subway overhead line system are realized through fault characteristic comparison;
(3) on the basis of a data warehouse, various types of data such as dynamic and static detection, fault defects, inherent attributes, part inspection, external environments and the like of the contact network are unified to carry out comprehensive analysis on the contact network, and the precision of fault diagnosis and positioning is improved.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a contact network fault diagnosis method based on a data warehouse, provided by the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
In one embodiment, as shown in fig. 1, the present invention provides a method for diagnosing a fault of a contact network based on a data warehouse, which sequentially includes the steps of: the method comprises the following steps of data collection, data processing, characteristic data extraction, data comparison, fault diagnosis and positioning, and specifically comprises the following steps:
acquiring historical detection data of the overhead line system by data collection;
preprocessing historical detection data;
after the characteristic data are extracted, acquiring characteristic data respectively corresponding to the contact network in various states, and acquiring steady-state characteristic data of the contact network in a steady state;
comparing and clustering the characteristic data in multiple states with the steady-state characteristic data to obtain corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
acquiring real-time detection data and corresponding real-time characteristic data of a contact network, comparing the real-time characteristic data with the characteristic data in the data warehouse, and judging whether a fault exists or not;
and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
Specifically, in the data collection step, the data of the overhead line system is collected based on the route mileage or the geographic position information; the parameters include but are not limited to contact force, lead height, pull-out value, hard point, net pressure, arcing, current, image and the like, and the corresponding data are the actual detection data of the parameters;
specifically, response data at each node position is collected through a sensor in a contact network, and the response data comprises but is not limited to numerical values of parameters such as contact force, lead height, pull-out value, hard point, network pressure and arcing; the type of data herein is by way of example only, and not by way of limitation;
the method comprises the following steps of obtaining characteristic data corresponding to the contact network in various states respectively, obtaining steady-state characteristic data of the contact network in a steady state, and specifically comprising the following steps:
acquiring historical detection data of a contact network;
carrying out normalization processing on the historical detection data, and converting various types of historical detection data into data with a numerical value between [0 and 1 ];
and performing dimension reduction on the data after the normalization processing to obtain characteristic data in various states.
Wherein, acquire the real-time detection data and the real-time characteristic data that correspond of contact net, include:
acquiring real-time detection data of a contact network;
carrying out normalization processing on the real-time detection data, and converting various real-time detection data into data with a numerical value between [0,1 ];
and performing dimension reduction processing on the normalized data to obtain characteristic data corresponding to various real-time detection data.
Specifically, due to the fact that the working environment of the contact network and equipment thereof is severe, data such as network voltage, contact network current, insulator leakage current and images are often interfered by factors such as vibration, strong electric field and illumination, and certain noise exists in detected data; due to technical reasons or human factors, omission possibly exists in the data acquisition process and the data uploading process of the sensor, and data loss can be caused; since the detection data related to the catenary is fluctuation continuous data based on the route mileage or geographic position information, and each data is in one-to-one correspondence with the sampling position, time and frequency, if the data is missing, inaccuracy of subsequent data processing and analysis may be caused.
Therefore, the unusable data needs to be removed, the missing data needs to be supplemented, noise interference is eliminated, and therefore before normalization processing is performed on the detection data, the data needs to be cleaned, and the method specifically comprises the following steps:
comparing each type of detection data with a corresponding threshold, wherein the corresponding detection data higher than or equal to the threshold are unavailable data, eliminating the unavailable data, and replacing the unavailable data with the detection data lower than the threshold; carrying out noise reduction processing on various monitoring data;
optionally, the various types of detection data may be compared with empirical values of word categories, for example, the voltage and current output by the sensor exceed or fall below the accuracy range of the sensor, and the value of the acceleration exceeds the threshold value measured by the sensor, which indicates that the value measured by the sensor is wrong, and similar data is regarded as unusable data;
optionally, the unusable data is removed, and then the missing value is completed, which may be completed by the following method: mean interpolation, homogeneous mean interpolation, modeling prediction, high-dimensional mapping, multiple interpolation, maximum likelihood estimation, compressed sensing, matrix complementation and the like; the examples are given herein by way of illustration of embodiments of the invention and not by way of further limitation;
specifically, the normalization processing of the data includes:
respectively carrying out normalization processing on the data collected in the step one by adopting a maximum and minimum normalization method to obtain the data with the size of [0,1]]Data of (X-X) in (b), Y ═ X min )/(X max -X min ) Wherein X and Y are values before and after normalization, respectively max ，X min Are respectivelyMaximum and minimum values of the data set.
Further, after the above steps, feature extraction is performed, including:
and (3) data dimension reduction treatment:
performing dimensionality reduction processing on the data obtained in the step to obtain characteristic data of various different states;
by inputting historical detection data or real-time measurement data, such as contact force, lead height, pull-out value, hard point, net pressure, arcing and the like;
calculating by a data dimension reduction method, and outputting a plurality of parameter-fused principal component data, such as geometric component data, smoothness component data, current component data and the like, wherein the data is fused state characteristic data; for example, for a fault state caused by current abnormality, current-related data such as current data and network voltage are used as characteristic data corresponding to the current abnormality state;
specifically, the data dimension reduction method comprises an Independent Component Analysis (ICA), a Principal Component Analysis (PCA), low variance filtering, high correlation filtering, a particle swarm optimization algorithm, a genetic algorithm and the like, reduces the data dimension, and simultaneously retains the characteristics of the data to the maximum extent; the present invention is described herein as an example of a process, and should not be considered as limiting;
the data volume of the overall parameters is reduced through dimension reduction processing, the time complexity and the space complexity of the parameters are reduced, calculation is facilitated, effective information extraction and useless information rejection are facilitated to achieve data screening, and feature selection and feature extraction are facilitated.
Further, data comparison is carried out, feature data are extracted, the contact network detection data of the contact network in various fault states obtained through the data dimension reduction processing are compared with the steady-state feature data and clustered, and the mapping relation between the fault type and the corresponding feature data is output, so that a data warehouse is formed;
it should be noted that the Data Warehouse (DW) is a theme-oriented, integrated, non-volatile, time-varying Data set that provides decision support for management personnel. Data can be extracted from different operation type business systems through a data warehouse, then various cleaning and conversion operations are carried out on the data, and finally the data are organized together according to certain rules. It is noted that an integrated, normative data warehouse environment can effectively improve the efficiency and accuracy of data mining;
specifically, various types of feature data and corresponding states of a data warehouse are used as samples to input a state classification model for training, real-time detection data detected in real time are subjected to normalization processing and dimension reduction processing to obtain real-time feature data, and the real-time features are input into the trained state classification model;
and judging whether a fault exists or not through the trained state classification model, and if so, outputting a corresponding fault type.
Specifically, the detection data of the overhead contact system is fluctuation continuous data based on the line mileage or the geographic position information;
if the fault exists, acquiring original real-time detection data corresponding to the characteristic data, and calculating the fault position of the subway overhead line system according to the position information and the mileage data according to the line mileage or the geographic position information in the original real-time detection data;
optionally, training various state feature data of the data warehouse by using an algorithm model such as a Support Vector Machine (SVM) and a random forest to obtain a state classification model, and then inputting feature data obtained by processing and feature extraction of actually measured data into the trained state classification model for state recognition.
On the other hand, the catenary fault diagnosis system based on the data warehouse provided by the invention can be referred to the catenary fault diagnosis method correspondingly, and specifically comprises a data collection module, a data processing module, a feature extraction module, a data comparison module, a data warehouse and a fault diagnosis and positioning module, wherein:
the data collection module is used for acquiring various detection parameters of the contact network;
the data processing module is used for carrying out normalization processing on various detection parameters;
the characteristic extraction module is used for acquiring characteristic data respectively corresponding to the contact network in various states and acquiring steady-state characteristic data of the contact network in a steady state based on the data processed by the data processing module in a normalization mode;
the data comparison module is used for carrying out comparison clustering on the characteristic data in various states and the steady-state characteristic data, acquiring corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
the fault diagnosis and positioning module is used for acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse and judging whether a fault exists or not; and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
In another aspect, the present invention also provides an electronic device, which may include: the system comprises a processor (processor), a communication interface (communication interface), a memory (memory) and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus. The processor can call logic instructions in the memory to execute the data warehouse-based contact network fault diagnosis method, which comprises the following steps:
acquiring characteristic data respectively corresponding to the contact network in various states based on historical detection data of the contact network, and acquiring steady-state characteristic data of the contact network in a steady state;
comparing and clustering the characteristic data in multiple states with the steady-state characteristic data to obtain corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse, and judging whether a fault exists;
and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the data warehouse-based catenary fault diagnosis method provided by the above methods, including the steps of:
acquiring characteristic data respectively corresponding to the contact network in various states based on historical detection data of the contact network, and acquiring steady-state characteristic data of the contact network in a steady state;
comparing and clustering the characteristic data in multiple states with the steady-state characteristic data to obtain corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse, and judging whether a fault exists;
and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
In still another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the method for diagnosing the fault of the overhead contact system based on the data warehouse, provided by the method, including the steps of:
acquiring characteristic data respectively corresponding to the contact network in various states based on historical detection data of the contact network, and acquiring steady-state characteristic data of the contact network in a steady state;
comparing and clustering the characteristic data in multiple states with the steady-state characteristic data to obtain corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse, and judging whether a fault exists;
and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A contact network fault diagnosis method based on a data warehouse is characterized by comprising the following steps:
acquiring characteristic data respectively corresponding to the contact network in various states based on historical detection data of the contact network, and acquiring steady-state characteristic data of the contact network in a steady state;
comparing and clustering the characteristic data in multiple states with the steady-state characteristic data to obtain corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse, and judging whether a fault exists;
and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
2. The data warehouse-based catenary fault diagnosis method according to claim 1, wherein the acquiring of the characteristic data corresponding to the catenary in various states respectively and the acquiring of the steady-state characteristic data of the catenary in a steady-state specifically comprises:
acquiring historical detection data of a contact network;
carrying out normalization processing on the historical detection data, and converting various types of historical detection data into data with a numerical value between [0 and 1 ];
and performing dimension reduction processing on the data after the normalization processing to obtain characteristic data in various states.
3. The data warehouse-based catenary fault diagnosis method according to claim 1, wherein the acquiring of real-time detection data and corresponding real-time characteristic data of a catenary comprises:
acquiring real-time detection data of a contact network;
carrying out normalization processing on the real-time detection data, and converting various real-time detection data into data with a numerical value between [0,1 ];
and performing dimension reduction processing on the normalized data to obtain characteristic data corresponding to various real-time detection data.
4. The data warehouse-based catenary fault diagnosis method according to claim 2 or 3, characterized in that before the normalization processing, the method comprises:
comparing each type of detection data with a corresponding threshold, wherein the corresponding detection data higher than or equal to the threshold are unavailable data, eliminating the unavailable data, and replacing the unavailable data with the detection data lower than the threshold;
and carrying out noise reduction processing on various monitoring data.
5. The data warehouse-based catenary fault diagnosis method according to claim 3, characterized in that various types of feature data and corresponding states of the data warehouse are used as sample input state classification models for training, real-time feature data is obtained after normalization processing and dimension reduction processing are performed on real-time detection data detected in real time, and the real-time features are input into the trained state classification models;
and judging whether a fault exists or not through the trained state classification model, and if so, outputting a corresponding fault type.
6. The data warehouse-based catenary fault diagnosis method of claim 2 or 3, characterized in that the detection data of the catenary is fluctuation continuous data based on route mileage or geographic position information;
and if the fault exists, acquiring original real-time detection data corresponding to the characteristic data, and outputting the fault position according to the line mileage or the geographical position information in the original real-time detection data.
7. The utility model provides a contact net fault diagnosis system based on data warehouse, its characterized in that, includes data collection module, data processing module, feature extraction module, data contrast module, data warehouse and failure diagnosis and orientation module, wherein:
the data collection module is used for acquiring various detection parameters of the contact network;
the data processing module is used for carrying out normalization processing on various detection parameters;
the characteristic extraction module is used for acquiring characteristic data respectively corresponding to the contact network in various states based on the data processed by the data processing module in a normalization mode, and acquiring steady-state characteristic data of the contact network in a steady-state;
the data comparison module is used for carrying out comparison clustering on the characteristic data in various states and the steady-state characteristic data, acquiring corresponding fault characteristic data of the contact network in each fault state, and generating a data warehouse according to each fault state and the corresponding fault characteristic data;
the fault diagnosis and positioning module is used for acquiring real-time detection data of a contact network and corresponding real-time characteristic data, comparing the real-time characteristic data with the characteristic data in the data warehouse and judging whether a fault exists or not; and if the fault exists, outputting the fault type, and acquiring the fault position according to the corresponding real-time detection data.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the catenary fault diagnosis method according to any one of claims 1 to 6 when executing the program.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the catenary fault diagnosis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210718355.9A CN114996258A (en) | 2022-06-23 | 2022-06-23 | Contact network fault diagnosis method based on data warehouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210718355.9A CN114996258A (en) | 2022-06-23 | 2022-06-23 | Contact network fault diagnosis method based on data warehouse |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114996258A true CN114996258A (en) | 2022-09-02 |
Family
ID=83037581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210718355.9A Pending CN114996258A (en) | 2022-06-23 | 2022-06-23 | Contact network fault diagnosis method based on data warehouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114996258A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116519021A (en) * | 2023-06-29 | 2023-08-01 | 西北工业大学 | Inertial navigation system fault diagnosis method, system and equipment |
| CN117454262A (en) * | 2023-12-22 | 2024-01-26 | 华东交通大学 | Contact network fault identification method, system, storage medium and electronic equipment |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN109683058A (en) * | 2018-12-24 | 2019-04-26 | 天津凯发电气股份有限公司 | A kind of urban rail transit contact network method for comprehensive detection based on big data |
| CN110161343A (en) * | 2019-06-12 | 2019-08-23 | 中南大学 | A kind of non-intrusion type real-time dynamic monitoring method of intelligence train exterior power receiving device |
| KR20200052461A (en) * | 2018-10-31 | 2020-05-15 | 한국철도기술연구원 | Apparatus and method for predicting train fault |
| CN111204363A (en) * | 2020-04-23 | 2020-05-29 | 湖南中车时代通信信号有限公司 | Fault diagnosis early warning and state evaluation method, device and system for traction system |
| CN111260822A (en) * | 2019-12-31 | 2020-06-09 | 杭州安脉盛智能技术有限公司 | Rail transit vehicle health state analysis method and terminal based on big data |
| CN112362368A (en) * | 2021-01-14 | 2021-02-12 | 西门子交通技术(北京)有限公司 | Fault diagnosis method, device and system for train traction motor and readable medium |
| CN112749744A (en) * | 2021-01-08 | 2021-05-04 | 中南大学 | Bayesian network rail passenger car traction system fault diagnosis method and system based on observation module |
| CA3162702A1 (en) * | 2019-11-25 | 2021-06-03 | Envision Digital International Pte. Ltd. | Method and apparatus for detecting fault, method and apparatus for training model, and device and storage medium |
| CN112906915A (en) * | 2021-01-22 | 2021-06-04 | 江苏安狮智能技术有限公司 | Rail transit system fault diagnosis method based on deep learning |
| CN112949715A (en) * | 2013-12-31 | 2021-06-11 | 北京泰乐德信息技术有限公司 | SVM (support vector machine) -based rail transit fault diagnosis method |
| CN113466597A (en) * | 2021-07-19 | 2021-10-01 | 江苏金鑫信息技术有限公司 | Intelligent detection method for equipment state of rail transit power supply system |
| CN113657258A (en) * | 2021-08-16 | 2021-11-16 | 前景智能交通科技(苏州)有限公司 | Contact network fault identification system and method based on image processing |
| CN114021621A (en) * | 2021-10-13 | 2022-02-08 | 北京和利时系统集成有限公司 | Fault diagnosis method, system, storage medium and edge computing device |
| CN114021602A (en) * | 2021-10-14 | 2022-02-08 | 北京和利时系统集成有限公司 | Method and system for processing data in point switch fault diagnosis model |
| CN114463151A (en) * | 2021-12-21 | 2022-05-10 | 南京康尼机电股份有限公司 | Sub-health diagnosis method for rail vehicle door system |
-
2022
- 2022-06-23 CN CN202210718355.9A patent/CN114996258A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949715A (en) * | 2013-12-31 | 2021-06-11 | 北京泰乐德信息技术有限公司 | SVM (support vector machine) -based rail transit fault diagnosis method |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| KR20200052461A (en) * | 2018-10-31 | 2020-05-15 | 한국철도기술연구원 | Apparatus and method for predicting train fault |
| CN109683058A (en) * | 2018-12-24 | 2019-04-26 | 天津凯发电气股份有限公司 | A kind of urban rail transit contact network method for comprehensive detection based on big data |
| CN110161343A (en) * | 2019-06-12 | 2019-08-23 | 中南大学 | A kind of non-intrusion type real-time dynamic monitoring method of intelligence train exterior power receiving device |
| CA3162702A1 (en) * | 2019-11-25 | 2021-06-03 | Envision Digital International Pte. Ltd. | Method and apparatus for detecting fault, method and apparatus for training model, and device and storage medium |
| CN111260822A (en) * | 2019-12-31 | 2020-06-09 | 杭州安脉盛智能技术有限公司 | Rail transit vehicle health state analysis method and terminal based on big data |
| CN111204363A (en) * | 2020-04-23 | 2020-05-29 | 湖南中车时代通信信号有限公司 | Fault diagnosis early warning and state evaluation method, device and system for traction system |
| CN112749744A (en) * | 2021-01-08 | 2021-05-04 | 中南大学 | Bayesian network rail passenger car traction system fault diagnosis method and system based on observation module |
| CN112362368A (en) * | 2021-01-14 | 2021-02-12 | 西门子交通技术(北京)有限公司 | Fault diagnosis method, device and system for train traction motor and readable medium |
| CN112906915A (en) * | 2021-01-22 | 2021-06-04 | 江苏安狮智能技术有限公司 | Rail transit system fault diagnosis method based on deep learning |
| CN113466597A (en) * | 2021-07-19 | 2021-10-01 | 江苏金鑫信息技术有限公司 | Intelligent detection method for equipment state of rail transit power supply system |
| CN113657258A (en) * | 2021-08-16 | 2021-11-16 | 前景智能交通科技(苏州)有限公司 | Contact network fault identification system and method based on image processing |
| CN114021621A (en) * | 2021-10-13 | 2022-02-08 | 北京和利时系统集成有限公司 | Fault diagnosis method, system, storage medium and edge computing device |
| CN114021602A (en) * | 2021-10-14 | 2022-02-08 | 北京和利时系统集成有限公司 | Method and system for processing data in point switch fault diagnosis model |
| CN114463151A (en) * | 2021-12-21 | 2022-05-10 | 南京康尼机电股份有限公司 | Sub-health diagnosis method for rail vehicle door system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116519021A (en) * | 2023-06-29 | 2023-08-01 | 西北工业大学 | Inertial navigation system fault diagnosis method, system and equipment |
| CN116519021B (en) * | 2023-06-29 | 2023-09-15 | 西北工业大学 | Inertial navigation system fault diagnosis method, system and equipment |
| CN117454262A (en) * | 2023-12-22 | 2024-01-26 | 华东交通大学 | Contact network fault identification method, system, storage medium and electronic equipment |
| CN117454262B (en) * | 2023-12-22 | 2024-03-22 | 华东交通大学 | Contact network fault identification method, system, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114996258A (en) | Contact network fault diagnosis method based on data warehouse | |
| US8868985B2 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
| EP2333629A1 (en) | Error detection method and system | |
| CN112949715A (en) | SVM (support vector machine) -based rail transit fault diagnosis method | |
| CN110225107B (en) | Cable comprehensive detection system | |
| CN108765189B (en) | Open type partial discharge big data management system based on intelligent diagnosis algorithm | |
| CN105675038A (en) | Device for predicting faults of instruments | |
| EP1958034B1 (en) | Use of sequential clustering for instance selection in machine condition monitoring | |
| CN116552306B (en) | Monitoring system and method for direct current pile | |
| CN111967620A (en) | Photovoltaic module diagnosis method, device, equipment and readable storage medium | |
| CN112418065A (en) | Equipment operation state identification method, device, equipment and storage medium | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN116089218A (en) | Dynamic baseline alarm method and system based on Kubernetes historical data and trend analysis | |
| CN113157536A (en) | Alarm analysis method, device, equipment and storage medium | |
| CN112560940A (en) | Power utilization abnormity detection method, device, equipment and storage medium | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN116739829A (en) | Big data-based power data analysis method, system and medium | |
| CN117110794A (en) | Intelligent diagnosis system and method for cable faults | |
| CN113704389A (en) | Data evaluation method and device, computer equipment and storage medium | |
| CN115409367A (en) | Intelligent power grid health state assessment method and system based on Internet of things | |
| CN115115585A (en) | Cable fault diagnosis method and system and readable storage medium | |
| JP6641056B1 (en) | Device abnormality diagnosis method and device abnormality diagnosis system | |
| CN117194049B (en) | Cloud host intelligent behavior analysis method and system based on machine learning algorithm | |
| CN117368598B (en) | Electric energy quality monitoring method and device | |
| CN116381419B (en) | Transmission line fault processing method, device, computer equipment and storage medium |
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 |