A method and system for automatic allocation of rail transit defects based on support vector machine
By applying support vector machine technology in rail transit defect processing, automatic defect allocation is realized, the problem of low manual allocation efficiency is solved, and processing efficiency and safety are improved.
Patent Information
- Application Number
- CN202210615614.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-01
- Publication Date
- 2025-04-04
- Estimated Expiration
- 2042-06-01
AI Technical Summary
The existing rail transit defect handling technology relies on manual allocation, resulting in low efficiency and high cost, making it difficult to eliminate safety hazards in a timely manner according to the degree of impact.
Using machine learning technology based on support vector machine, the defect identification model and the processing personnel evaluation model are used to automatically associate and match the pending defects and processing personnel to achieve automatic allocation of defects.
This improves the efficiency of defect handling, reduces labor costs, ensures that defects are handled in a timely manner according to the severity, and reduces safety hazards.
Smart Images
Figure CN115018099B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent operation and maintenance of rail transit, and in particular to a method and system for automatically allocating rail transit defects based on a support vector machine. Background Art
[0002] The rail transit (railway and urban rail transit) industry has played an extremely important role in the development of the national economy and the process of urbanization, and has become one of the fastest-growing industries in my country. Rail transit is closed and independent, which makes it very safe. However, due to the large volume of rail transit and the high scientific and technological content of the equipment, once a failure occurs, it often has a great impact and serious consequences. Therefore, the handling of defects in rail transit operation and maintenance has become an important means to eliminate safety hazards.
[0003] Rail transit operating units usually have strict defect handling procedures and are equipped with a defect management information system for unified management of defect handling procedures. The allocation of defects still relies mainly on manual allocation by department and level in the management system. There are a large number of defects, which is prone to allocation errors and delays in defect handling. In addition, manual allocation can only rely on the defect level to subjectively determine the processing priority. There is a lack of intelligent determination of the processing order of a large number of defects of the same level, making it difficult to eliminate safety hazards according to the degree of impact when time and manpower are limited. Summary of the invention
[0004] In view of the problems of high labor cost and low efficiency in existing defect handling technologies, the present invention provides a method for automatic defect allocation in rail transit based on support vector machine. The present invention adopts machine learning technology to quantify the severity of defects and the ability of handling personnel, and then realizes automatic association and matching, realizes automatic defect allocation processing, and improves processing efficiency.
[0005] The present invention is achieved through the following technical solutions:
[0006] A method for automatic allocation of rail transit defects based on support vector machine, comprising:
[0007] Obtain line maintenance or inspection information;
[0008] Get the list of pending defects;
[0009] The defect recognition model is used to calculate the severity and ranking of defects to be processed;
[0010] The defect handling personnel assessment model is used to calculate the handling personnel capability assessment score list;
[0011] Establish a matching relationship between the defects to be processed and the maintenance items or inspection items;
[0012] Determine the order of processing defects at the same location based on the order of defects to be processed;
[0013] Determine the person who will handle the defect based on the severity of the defect to be handled and the ability assessment score of the person who will handle the defect;
[0014] According to the matching relationship, processing sequence and processing personnel, the defects to be merged and processed, their processing sequence and processing personnel are automatically added to the maintenance items or inspection items.
[0015] As a preferred embodiment, the method of the present invention further comprises:
[0016] Establish support vector analysis model;
[0017] Acquire processed historical data, and process the historical data to obtain training sample data, wherein the training sample data includes defect recognition training sample data and personnel capability assessment training sample data;
[0018] The support vector analysis model is trained using the training sample data to obtain a defect recognition model and a defect handling personnel evaluation model.
[0019] As a preferred embodiment, the defect recognition model construction process of the present invention specifically includes:
[0020] Processing historical defect data in the historical data to obtain defect recognition training sample data;
[0021] The support vector analysis model is trained using the defect recognition training sample data to obtain a defect recognition model.
[0022] As a preferred embodiment, the defect recognition training sample data of the present invention includes the cause of the defect, the defect level, the defect location, the duration of the defect, the person who handles the defect, the defect handling cycle, the number of times the defect handling fails, the parts affected by the defect, and the weight of the parts.
[0023] As a preferred embodiment, the defect handling personnel evaluation model construction process of the present invention specifically includes:
[0024] Processing the historical defect processing data in the historical data to obtain personnel capability assessment training sample data;
[0025] The support vector analysis model is trained using the personnel capability assessment training sample data to obtain a defect handling personnel assessment model.
[0026] As a preferred embodiment, the personnel capability assessment training sample data of the present invention includes a quantitative value of defect severity, defect level, defect handler, defect handling cycle, and number of defect handling failures.
[0027] As a preferred embodiment, the present invention determines the order of processing defects at the same position according to the order of defects to be processed, specifically: for defects to be processed at the same position, the higher the level, the higher the priority;
[0028] And / or, the processing personnel are determined based on the matching of the severity of the defect to be processed and the processing personnel's ability assessment score, specifically, the processing personnel are determined according to the preset rules, and the preset rules specifically include:
[0029] Processors can handle defects at their corresponding level as well as defects below their corresponding level.
[0030] As a preferred embodiment, the maintenance or inspection information of the present invention includes the maintenance / inspection date, location information and person in charge;
[0031] And / or, the list of defects to be processed includes defect discovery time, defect level, and defect location.
[0032] In a second aspect, the present invention proposes a rail transit defect automatic allocation system based on a support vector machine, comprising:
[0033] Defect recognition module, which uses historical defect data to train a defect recognition model;
[0034] The defect handling personnel evaluation module uses historical defect data to train the defect handling personnel evaluation model;
[0035] The allocation module is used to obtain line maintenance information or inspection information, as well as the list of defects to be processed;
[0036] The allocation module also uses the defect recognition model to calculate the severity of defects to be processed and the order of defects to be processed, and uses the defect handling personnel evaluation model to calculate a list of handling personnel capability evaluation scores;
[0037] The allocation module also determines the matching relationship between defects and maintenance items or inspection items, the order of defect processing, and the processing personnel based on the information of defects to be processed, maintenance items or inspection items, the severity of defects to be processed and the order of defects to be processed, and the list of processing personnel's ability assessment scores, thereby automatically adding merged defects and their processing order and processing personnel to the maintenance items or inspection items.
[0038] In a third aspect, the present invention proposes a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method of the present invention when executing the computer program.
[0039] The present invention has the following advantages and beneficial effects:
[0040] 1. The present invention uses a support vector machine to construct an automatic defect severity identification model, performs accurate automatic quantification of the severity of defects to be processed, and sorts the defect processing. At the same time, a support vector machine is used to construct a defect processing personnel capability assessment model, which automatically matches the corresponding severity of defect processing according to the personnel capability, thereby improving the defect processing effect and reducing safety hazards.
[0041] 2. The present invention quantitatively characterizes the severity of defects and personnel capabilities based on the above model, realizes the matching and merging of defects with maintenance plans or inspection plans, realizes the automatic allocation of defects, and improves processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:
[0043] Figure 1 The figure is a schematic diagram of a method flow of an embodiment of the present invention.
[0044] Figure 2 A schematic diagram of the defect recognition model construction process according to an embodiment of the present invention.
[0045] Figure 3 The figure is a schematic diagram of the defect handling personnel evaluation model construction process according to an embodiment of the present invention.
[0046] Figure 4 Schematic diagram of the computer device structure according to an embodiment of the present invention.
[0047] Figure 5 4 is a system principle block diagram of an embodiment of the present invention.
[0048] Marks and corresponding parts names in the attached drawings:
[0049] 10-defect identification module, 11-first data acquisition unit, 12-first model training unit, 20-defect handling personnel evaluation module, 21-second data acquisition unit, 22-second model training unit, 30-allocation module, 31-third data acquisition unit, 32-calculation unit, 33-rule base, 34-matching unit, 35-output unit. DETAILED DESCRIPTION
[0050] Hereinafter, the term "include" or "may include" used in various embodiments of the present invention indicates the presence of the invented function, operation or element, and does not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present invention, the terms "include", "have" and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.
[0051] In various embodiments of the present invention, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.
[0052] The expressions (such as "first", "second", etc.) used in various embodiments of the present invention may modify the various constituent elements in various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing an element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of various embodiments of the present invention, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.
[0053] It should be noted that if it is described that one component element is “connected” to another component element, the first component element may be directly connected to the second component element, and a third component element may be “connected” between the first component element and the second component element. Conversely, when one component element is “directly connected” to another component element, it can be understood that there is no third component element between the first component element and the second component element.
[0054] The terms used in various embodiments of the present invention are only used for the purpose of describing specific embodiments and are not intended to limit various embodiments of the present invention. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meaning generally understood by those of ordinary skill in the art to which the various embodiments of the present invention belong. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in various embodiments of the present invention.
[0055] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.
[0056] Example 1
[0057] The existing defect relationship information system mainly relies on manual allocation in the management system, which has high labor costs and low efficiency. At the same time, it is difficult to eliminate safety hazards according to the degree of impact when time and manpower are limited, and the reliability is low. In view of this, this embodiment proposes a method for automatic allocation of rail transit defects based on support vector machines, which provides more accurate and objective allocation and management, and improves the ability to eliminate safety hazards during rail transit operation and maintenance.
[0058] like Figure 1 As shown, the method of this embodiment specifically includes the following steps:
[0059] Step S1, obtaining line maintenance plan or inspection plan information, and list information of defects to be processed.
[0060] In this embodiment, the maintenance plan or inspection plan information obtained includes the maintenance / inspection date, location information, and person in charge; the pending defect list information obtained includes the defect discovery time, defect level, and defect location.
[0061] Step S2: using the defect recognition model to calculate the severity of the defects to be processed and their ranking.
[0062] The defect recognition model of this embodiment is constructed using a support vector machine. Figure 2 As shown, including:
[0063] Step S21, obtaining the processed historical defect data, which is a list of defect data that has been processed and cancelled.
[0064] Step S22, establish a support vector analysis model for defect processing events. The model uses historical defect processing data as training data, extracts the defect level, existence duration, processing cycle, number of failed processing, parts affected by the defect, and weight of parts as features of each historical defect, and uses kernel techniques and soft margin maximization to establish a nonlinear support vector machine for the training data, learns a nonlinear classifier, and outputs a defect severity classification, with multiple classifications corresponding to different scores.
[0065] Step S23: Process the historical defect data to obtain training sample data.
[0066] In this embodiment, in order to ensure the accuracy of the model output, the training sample data needs to contain accurate and complete input features, so the historical defect data is processed to determine the input features, which include the cause of the defect, the defect level, the defect location, the duration of the defect, the person who handles the defect, the defect handling cycle, the number of times the defect handling fails, the parts affected by the defect, and the weight of the parts.
[0067] Step S24: training the support vector analysis model of the defect processing event using the training sample data to obtain a defect recognition model.
[0068] In this embodiment, the defect data to be processed is input into the defect recognition model obtained in the above steps S21-S24 to calculate the quantified severity value corresponding to the defect to be processed. The defect data to be processed in this embodiment is processed in the same way as the above historical defect data to obtain the input features.
[0069] The priority ranking of the defects to be processed is obtained according to the severity quantification value or defect level of the defects to be processed. The higher the severity quantification value or the higher the defect level or the higher the defect level, the higher the processing priority.
[0070] In this embodiment, defect levels are divided according to the severity of the defects. The defect levels can be set from level one to level three, where level one corresponds to the most serious defect, and the severity of defects from level one to level three decreases in sequence; in another preferred embodiment, more levels are also supported to support user business demands.
[0071] Step S3, using the defect handling personnel evaluation model to calculate the handling personnel capability evaluation score list.
[0072] The defect handling personnel evaluation model of this embodiment is constructed using a support vector machine. Figure 3 As shown, including:
[0073] Step S31, obtaining the processed historical defect data. The historical defect data is a list of defect data that has been processed and cancelled, and must include the defect processing personnel information.
[0074] Step S32, establish a support vector analysis model for defect handling personnel capability assessment. The model uses the historical defect handling data that has been handled by the defect handling personnel as training data, extracts the defect level, existence duration, processing cycle, number of failed processing, parts affected by the defects, and weight of parts of each historical defect of the personnel as features, and uses the kernel technique and soft margin maximization to establish a nonlinear support vector machine for the training data, learns a nonlinear classifier, and outputs the processing personnel processing capability classification, and multiple classifications correspond to different processing capability scores.
[0075] Step S33: Process the historical defect data to obtain training sample data.
[0076] To ensure the accuracy of the model output, the training sample data needs to contain accurate and complete input features. Therefore, this embodiment processes the historical defect data to determine the input features. The input features include the quantitative value of the defect severity, defect level, defect handler, defect handling cycle, and the number of times the defect handling fails.
[0077] Step S34: Use the training sample data to train the support vector analysis model for defect handling personnel evaluation to obtain a defect handling personnel evaluation model.
[0078] In this embodiment, the defect data to be processed is input into the defect handling personnel evaluation model obtained in the above steps S31-S34 to calculate the defect handling personnel capability evaluation score, and the defect handling personnel capability evaluation score determines the processing capability level of the processing personnel. In this embodiment, the defect data to be processed is processed in the same way as the above historical defect data to obtain the input features.
[0079] In this embodiment, the number of processing capability level divisions is the same as the number of defect level divisions, so the processing capability level is divided into level one to level three according to the capability evaluation score. Level one corresponds to the strongest processing capability, and the levels decrease in sequence. When the defect level increases, the level of the processing personnel increases accordingly. There is a corresponding relationship between the processing capability level and the capability evaluation score. The higher the capability evaluation score, the higher the processing capability level.
[0080] Step S4, establishing a matching relationship between the defects to be processed and the maintenance items or inspection items at the same location.
[0081] This embodiment uses the rule that the location of the defect to be processed is close to the working location of a maintenance item or inspection item, and establishes a many-to-one relationship between the defect to be processed and the maintenance item or inspection item, that is, the same maintenance item or inspection item is associated with multiple defects to be processed with similar locations.
[0082] Step S5, the defects to be processed at the same position are sorted and given a processing order.
[0083] Step S6, for defects to be processed at the same location, match the severity of the defects to be processed with the competence assessment score of the processing personnel to determine the processing personnel.
[0084] Step S6 of this embodiment is specifically as follows:
[0085] According to the severity of the defects to be processed, the order of processing defects in the same position is given, and defects with higher severity are processed first;
[0086] Personnel with level 1 processing capability can handle level 1 defects and below, and so on, personnel with level 2 processing capability can handle level 2 defects and below. For example, taking level 3 pending defects (i.e., the pending defects are level 1 to level 3) as an example, pending defects are matched with personnel in the order of level 1 to level 3, and level 1 defects are matched with level 1 processing personnel. If the available working hours of the same person on the same day are fully booked, the processing personnel of the same level will be replaced, and the personnel allocation from level 1 to level 3 will be completed in sequence.
[0087] Step S7, based on the matching relationship, processing sequence and processing personnel, automatically add the defects to be merged and processed to the maintenance items or inspection items (for example, automatically add note information to the maintenance items or inspection items, and the note information contains information about the defects to be processed), and automatically add the defect processing personnel and the defect processing sequence.
[0088] This embodiment also provides a computer device for executing the above method of this embodiment.
[0089] Specific as Figure 4 As shown, the computer device includes a processor, an internal memory and a system bus; various device components including the internal memory and the processor are connected to the system bus. The processor is a piece of hardware used to execute computer program instructions through basic arithmetic and logical operations in the computer system. The internal memory is a physical device used to temporarily or permanently store computer programs or data (for example, program status information). The system bus can be any of the following types of bus structures, including a memory bus or a storage controller, a peripheral bus, and a local bus. The processor and the internal memory can communicate data through the system bus. The internal memory includes a read-only memory (ROM) or a flash memory (not shown in the figure), and a random access memory (RAM), and RAM usually refers to the main memory loaded with the operating system and computer programs.
[0090] Computer devices generally include an external storage device. The external storage device can be selected from a variety of computer-readable media, which refers to any available media that can be accessed by the computer device, including both removable and fixed media. For example, computer-readable media include, but are not limited to, flash memory (micro SD card), CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic tape cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by the computer device.
[0091] Computer devices can be logically connected to one or more network terminals in a network environment. Network terminals can be personal computers, servers, routers, smart phones, tablets, or other public network nodes. Computer devices are connected to network terminals through network interfaces (local area network LAN interfaces). Local area network (LAN) refers to a network of computers interconnected within a limited area, such as a home, school, computer laboratory, or office building using network media. WiFi and twisted pair cabling Ethernet are the two most commonly used technologies for building LANs.
[0092] It should be noted that other computer systems including more or fewer subsystems than a computer device may also be suitable for the invention.
[0093] As described in detail above, the computer device applicable to the present embodiment can perform the specified operations of the method for automatically allocating rail transit defects based on a support vector machine. The computer device performs these operations in the form of software instructions running on a computer-readable medium by a processor. These software instructions can be read into the memory from a storage device or from another device through a local area network interface. The software instructions stored in the memory enable the processor to execute the above-mentioned method for processing group member information. In addition, the present invention can also be implemented by hardware circuits or hardware circuits combined with software instructions. Therefore, the implementation of this embodiment is not limited to any specific combination of hardware circuits and software.
[0094] Example 2
[0095] This embodiment proposes a rail transit defect automatic allocation system based on support vector machine.
[0096] like Figure 5 As shown, the automatic allocation system of this embodiment includes a defect identification module 10 , a defect handling personnel assessment module 20 , and an allocation module 30 .
[0097] The defect recognition module 10 of this embodiment further includes a first data acquisition unit 11 and a first model training unit 12 .
[0098] The first data acquisition unit 11 acquires the processed historical defect data; the first model training unit 12 establishes a support vector analysis model for defect handling events, and establishes input features based on the historical defect data, the input features including but not limited to the defect cause, defect level, defect location, defect existence duration, defect handler, defect handling cycle, number of defect handling failures, components affected by the defect, and weights of components; the above-mentioned support vector analysis model is trained using the above-mentioned features to obtain a defect recognition model.
[0099] The defect handling personnel assessment module 20 further includes a second data acquisition unit 21 and a second model training unit 22 .
[0100] The second data acquisition unit 21 acquires processed historical defect data, including defect handlers; the second model training unit 22 establishes an evaluation model based on a support vector machine, establishes input features based on the historical defect data, and the input features include a quantitative value of defect severity, defect level, defect handler, defect handling cycle, and number of defect handling failures; the features are used to train the above-mentioned evaluation model to obtain a defect handler evaluation model.
[0101] The allocation module 30 further includes a third data acquisition unit 31 , a calculation unit 32 , a rule base 33 , a matching unit 34 and an output unit 35 .
[0102] The third data acquisition unit 31 acquires the line maintenance plan and inspection plan information, including the maintenance / inspection date, location information, and person in charge; and acquires the list of defects to be processed, including the defect discovery time, defect level, and defect location.
[0103] The calculation unit 32 calculates the severity and ranking of the defects to be processed using the defect recognition model; and calculates a list of evaluation scores of the processing personnel's ability using the defect processing personnel evaluation model.
[0104] In this embodiment, the defect recognition model is used to calculate and obtain a quantitative value of the severity corresponding to the defect to be processed, wherein the higher the quantitative value, the higher the defect level and the higher the processing priority. Based on this, the defects to be processed are sorted according to severity or level.
[0105] The rule base 33 establishes allocation rules according to the severity of defects and the evaluation scores of the processing personnel's abilities.
[0106] In this embodiment, the allocation rule is specifically:
[0107] According to the severity of the defects to be processed, the order of processing defects in the same position is given, and defects with higher severity are processed first;
[0108] Personnel with level 1 processing capability can handle level 1 defects and below, and so on, personnel with level 2 processing capability can handle level 2 defects and below. For example, taking level 3 pending defects (i.e., the pending defects are level 1 to level 3) as an example, pending defects are matched with personnel in the order of level 1 to level 3, and level 1 defects are matched with level 1 processing personnel. If the available working hours of the same person on the same day are fully booked, the processing personnel of the same level will be replaced, and the personnel allocation from level 1 to level 3 will be completed in sequence.
[0109] The matching unit 34 automatically schedules the maintenance and inspection staff according to the allocation rules established in the rule base, and provides the automatic matching results of the personnel who will execute the maintenance or inspection work plan for the day. The automatic matching results include the matching relationship between the defects to be processed and the maintenance items / inspection items, the processing order of the defects to be processed, and the matching relationship between the defects to be processed and the processing personnel.
[0110] The output unit 35 automatically assigns defects to processing personnel and determines the combined processing maintenance items / inspection items and the processing date based on the matching relationship between defects and maintenance / inspections, the defect processing order, and the matching relationship between defects and processing personnel.
[0111] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for automatic allocation of rail transit defects based on support vector machine, characterized in that: include: Obtain line maintenance or inspection information; Get the list of pending defects; The defect recognition model is used to calculate the severity and ranking of defects to be processed; The defect handling personnel assessment model is used to calculate the handling personnel capability assessment score list; Establish a matching relationship between the defects to be processed and the maintenance items or inspection items at the same location, that is, establish a many-to-one relationship between all the defects to be processed and the maintenance items or inspection items at the same location; For defects to be processed at the same location, the order of processing the defects at the same location is determined according to the order of defects to be processed; For defects to be processed at the same location, the processing personnel are determined based on the severity of the defects to be processed and the ability assessment score of the processing personnel; According to the matching relationship, processing sequence and processing personnel, the defects and their processing sequence and processing personnel are automatically added to the maintenance items or inspection items for combined processing; and further comprising: Establish support vector analysis model; Acquire processed historical data, and process the historical data to obtain training sample data, wherein the training sample data includes defect recognition training sample data and personnel capability assessment training sample data; The support vector analysis model is trained using the training sample data to obtain a defect recognition model and a defect handling personnel evaluation model respectively; the defect recognition model construction process specifically includes: Processing historical defect data in the historical data to obtain defect recognition training sample data; The support vector analysis model is trained using the defect recognition training sample data to obtain a defect recognition model; the defect recognition training sample data includes defect cause, defect level, defect location, defect existence duration, defect handler, defect handling cycle, number of defect handling failures, components affected by defects, and weights of components; the defect handling personnel evaluation model construction process specifically includes: Processing the historical defect processing data in the historical data to obtain personnel capability assessment training sample data; The support vector analysis model is trained using the personnel capability assessment training sample data to obtain a defect handling personnel assessment model; the personnel capability assessment training sample data includes a quantitative value of defect severity, defect level, defect handler, defect handling cycle, and number of defect handling failures.
2. The method for automatic rail transit defect allocation based on support vector machine according to claim 1 is characterized in that: The order of processing defects at the same location is determined based on the order of defects to be processed. Specifically, for defects to be processed at the same location, the higher the level, the higher the priority. And / or, the processing personnel are determined based on the matching of the severity of the defect to be processed and the processing personnel's ability assessment score, specifically, the processing personnel are determined according to the preset rules, and the preset rules specifically include: Processors can handle defects at their corresponding level as well as defects below their corresponding level.
3. The method for automatic rail transit defect allocation based on support vector machine according to claim 1, characterized in that: The inspection or patrol information includes the inspection / patrol date, location information and person in charge; And / or, the list of defects to be processed includes defect discovery time, defect level, and defect location.
4. A rail transit defect automatic allocation system based on support vector machine, characterized in that: include: A defect recognition module (10) is used to train a defect recognition model using historical defect data; A defect handling personnel evaluation module (20) is used to train a defect handling personnel evaluation model using historical defect data; The allocation module (30) is used to obtain line maintenance information or inspection information, and information on a list of defects to be processed; The allocation module (30) further uses the defect recognition model to calculate the severity of the defects to be processed and the ranking of the defects to be processed, and uses the defect handling personnel evaluation model to calculate a list of handling personnel capability evaluation scores; The allocation module (30) further determines the matching relationship between defects and maintenance items or inspection items, the defect processing sequence and the processing personnel based on the information of the defects to be processed, the maintenance items or inspection items, the severity of the defects to be processed and the ranking of the defects to be processed, and the list of the processing personnel's ability evaluation scores, so as to automatically add the defects to be processed in combination and their processing sequence and processing personnel to the maintenance items or inspection items, specifically including: establishing a matching relationship between the defects to be processed and the maintenance items or inspection items at the same position, that is, establishing a many-to-one relationship between all the defects to be processed at the same position and the maintenance items or inspection items; determining the processing sequence of the defects at the same position according to the ranking of the defects to be processed; matching the defects to be processed at the same position according to the severity of the defects to be processed and the processing personnel's ability evaluation scores to determine the processing personnel; automatically adding the defects to be processed in combination and their processing sequence and processing personnel to the maintenance items or inspection items according to the matching relationship, processing sequence and processing personnel; The defect recognition module (10) further comprises a first data acquisition unit (11) and a first model training unit (12); wherein the first data acquisition unit (11) acquires processed historical defect data; the first model training unit (12) establishes a support vector machine analysis model for defect processing events, processes the historical defect data to obtain defect recognition training sample data, and uses the defect recognition training sample data to train the support vector machine analysis model to obtain a defect recognition model; wherein the defect recognition training sample data comprises defect cause, defect level, defect location, defect existence time, defect handler, defect processing cycle, number of defect processing failures, components affected by the defect, and weights of components; The defect handling personnel assessment module (20) further comprises a second data acquisition unit (21) and a second model training unit (22); wherein the second data acquisition unit (21) acquires processed historical defect data; the second model training unit (22) establishes a support vector machine assessment model, processes the historical defect data, obtains personnel capability assessment training sample data, and uses the personnel capability assessment training sample data to train the support vector machine assessment model, to obtain a defect handling personnel assessment model; wherein the personnel capability assessment training sample data comprises a quantitative value of defect severity, defect grade, defect handler, defect handling cycle, and number of defect handling failures.
5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.
Citation Information
Patent Citations
Railway tunnel detection method
CN109278053A
Industrial control equipment maintenance scheduling system and method
CN111080140A