Evaluation method, device and equipment for overhaul project approval of steel rail equipment, storage medium and program product

Abstract

The invention provides a rail equipment overhaul project approval evaluation method and device, equipment, a storage medium and a program product, and the method comprises the steps: inputting the state evaluation data of to-be-approved rail equipment into a rail equipment state evaluation model, and determining the state evaluation grade of the to-be-approved rail equipment; according to the historical project approval data set corresponding to each project approval steel rail device in the multiple project approval steel rail devices and the current project approval data set of the project approval steel rail device, the project approval early warning evaluation grade of the project approval steel rail device is determined; and according to the state evaluation grade and the project approval early warning evaluation grade, determining an overhaul project approval evaluation result of the to-be-approved steel rail equipment. The method can improve the assessment precision of overhaul project approval of the to-be-approved steel rail equipment to a certain extent. And meanwhile, more scientific and reasonable project establishment decision suggestions can be provided for project establishment personnel, so that the project establishment decision efficiency of the project establishment personnel is improved.

Description

Technical Field

[0001] This application relates to the field of technical upgrading and overhaul technology for rail equipment, specifically to an evaluation method, device, equipment, storage medium, and program product for the establishment of overhaul projects for rail equipment. Background Technology

[0002] Overhaul and maintenance of rail equipment (referred to as "overhaul") is one of the core tasks in railway maintenance. Its purpose is to ensure the safe and stable operation of railway lines through inspection, maintenance and repair of rail equipment.

[0003] In practical applications, the workflow for major overhaul of rail equipment typically includes project initiation, project approval, and maintenance personnel carrying out the overhaul. Therefore, the initiator usually needs to first assess the proposed major overhaul project to determine whether it is appropriate to proceed with the project.

[0004] However, current research on key technologies for initiating rail equipment overhaul projects is limited, and mature evaluation standards for such projects have not yet been established. This may result in a lack of theoretical basis for evaluating whether or not to initiate rail equipment overhaul projects. Consequently, the evaluation accuracy for rail equipment overhaul projects may be low, and the evaluation may fail to provide project initiation personnel with more scientific and reasonable decision-making suggestions.

[0005] It should be noted that the information disclosed in the background section of this application is intended only to enhance the understanding of the general background of this application, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] This application provides an evaluation method, apparatus, equipment, storage medium, and program product for the initiation of major overhaul projects for rail equipment, in order to solve the problem that the evaluation accuracy of major overhaul projects for rail equipment may be low due to the lack of mature evaluation standards.

[0007] In a first aspect, embodiments of this application provide an evaluation method for initiating a major overhaul project for rail equipment, including: The condition assessment data of the proposed rail equipment is input into the rail equipment condition assessment model to determine the condition assessment level of the proposed rail equipment. The condition assessment level is used to characterize the degree of damage to the proposed rail equipment. Based on the historical project approval dataset corresponding to each of the multiple approved rail equipment projects and the current project approval dataset of the proposed rail equipment project, the project approval early warning assessment level of the proposed rail equipment project is determined. The project approval early warning assessment level is used to characterize the urgency of the proposed equipment project project for major overhaul. Based on the status assessment level and the project establishment early warning assessment level, the project establishment assessment result for the proposed overhaul of the rail equipment is determined.

[0008] In one possible implementation, before inputting the condition assessment data of the proposed rail equipment into the rail equipment condition assessment model, the following is also included: Obtain a condition assessment dataset, which includes a condition assessment subset for each rail device. The rail devices are either approved or unapproved rail devices. Each condition assessment subset includes condition assessment data corresponding to the condition evaluation index of each rail device. Determine the first weight corresponding to each of the rail equipment condition evaluation indicators; Based on the first weight corresponding to each rail equipment condition evaluation index, each condition evaluation data in each condition evaluation subset is weighted to determine the weighted condition evaluation subset corresponding to each rail equipment, so as to obtain the weighted condition evaluation dataset. A rail equipment condition assessment model is trained based on each of the weighted condition assessment subsets.

[0009] In one possible implementation, obtaining the state assessment dataset includes: Acquire various types of rail equipment data, including basic rail equipment data, rail equipment defect data, and rail equipment overhaul data. Based on multi-source data fusion technology, data from various rail equipment are fused to determine a multi-source data fusion feature library. Based on the condition evaluation index of each rail equipment, the condition assessment dataset is obtained from the multi-source data fusion feature library.

[0010] In one possible implementation, determining the first weight corresponding to each of the rail equipment condition evaluation indicators includes: Based on the importance evaluation results of each rail equipment condition evaluation index by multiple experts, the second weight corresponding to each rail equipment condition evaluation index is determined by the analytic hierarchy process. Based on the state assessment dataset, the third weight corresponding to each of the rail equipment state assessment indicators is determined by the entropy weight method. Based on the second and third weights corresponding to each rail equipment condition evaluation index, the first weight corresponding to each rail equipment condition evaluation index is determined.

[0011] In one possible implementation, determining the first weight corresponding to each rail equipment condition evaluation index based on the second weight and the third weight corresponding to each rail equipment condition evaluation index includes: Based on the second weight, third weight, and weight adjustment coefficient corresponding to each rail equipment condition evaluation index, the first weight corresponding to each rail equipment condition evaluation index is determined.

[0012] In one possible implementation, determining the project approval early warning assessment level of the proposed rail equipment based on the historical project approval dataset corresponding to each of the multiple approved rail equipment projects and the current project approval dataset of the proposed rail equipment includes: Based on the historical project data set corresponding to each of the multiple approved rail equipment projects and the current project data set of the proposed rail equipment project, the similarity with each of the approved rail equipment projects is determined. Based on the similarity of each of the approved rail equipment projects, target similar rail equipment is determined; The project establishment early warning assessment level of the proposed rail equipment is determined based on the difference between the proposed establishment year and the historical establishment year of the target similar rail equipment.

[0013] In one possible implementation, each of the historical project datasets includes the equipment name, overhaul method, and mileage of the approved rail equipment; the current project dataset includes the equipment name, overhaul method, and mileage of the proposed rail equipment; and determining the similarity between the proposed rail equipment and the historical project dataset corresponding to each of the approved rail equipment and the current project dataset of the proposed rail equipment includes: Based on the equipment name corresponding to each of the multiple approved rail equipment projects and the equipment name of the proposed rail equipment project, determine the similarity with the equipment name corresponding to each of the approved rail equipment projects; Based on the overhaul method corresponding to each of the approved rail equipment projects and the overhaul method of the proposed rail equipment projects, determine the similarity with the overhaul method corresponding to each of the approved rail equipment projects; Based on the mileage corresponding to each of the approved rail equipment projects and the mileage of the proposed rail equipment projects, determine the proximity to the mileage corresponding to each of the approved rail equipment projects; Based on the similarity of equipment name, overhaul method, and mileage proximity of each of the approved rail equipment projects, the similarity of the rail equipment to the approved rail equipment project is determined.

[0014] In one possible implementation, determining the similarity of the rail equipment to each of the approved rail equipment projects based on the similarity of the equipment name, the similarity of the overhaul method, and the proximity of the mileage includes: For each of the approved rail equipment, the similarity of equipment name, the similarity of overhaul method, and the proximity of mileage are calculated by weighting the similarity of equipment name, the similarity of overhaul method, and the proximity of mileage according to the similarity weights corresponding to these factors, and then determining the similarity of the rail equipment to each of the approved rail equipment.

[0015] In one possible implementation, after determining the similarity of the rail equipment corresponding to each of the approved rail equipment projects, the method further includes: The similarity of each of the approved rail equipment projects is sorted in descending order to obtain the sorted sequence of approved rail equipment projects. From the sorted sequence of approved rail equipment projects, identify the top N potential rail equipment projects for approval, where N ≥ 1; Based on the difference between the proposed year of approval for the proposed rail equipment and the historical year of approval for each potential rail equipment, the project approval early warning assessment level corresponding to each potential rail equipment is determined.

[0016] Secondly, embodiments of this application provide an evaluation device for initiating major overhaul projects for rail equipment, comprising: The condition assessment level determination module is used to input the condition assessment data of the proposed rail equipment into the rail equipment condition assessment model to determine the condition assessment level of the proposed rail equipment. The condition assessment level is used to characterize the degree of damage of the proposed rail equipment. The project initiation early warning assessment level determination module is used to determine the project initiation early warning assessment level of the proposed rail equipment based on the historical project initiation dataset corresponding to each of the multiple approved rail equipment projects and the current project initiation dataset of the proposed rail equipment. The project initiation early warning assessment level is used to characterize the urgency of the proposed equipment to undergo major repair project initiation. The overhaul project evaluation result determination module is used to determine the overhaul project evaluation result of the proposed rail equipment based on the status evaluation level and the project establishment early warning evaluation level.

[0017] Thirdly, embodiments of this application provide an electronic device, including: processor; Memory; And a computer program, wherein the computer program is stored in the memory, and when the computer program is executed by the processor, causes the electronic device to perform the method described in any one of the first aspects.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of the first aspects.

[0019] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any one of the first aspects.

[0020] In this embodiment, the degree of damage to the proposed rail equipment is determined based on its condition assessment data. The urgency of initiating a major overhaul project for the proposed rail equipment is determined based on the historical project data set of each already approved rail equipment and the current project data set of the proposed rail equipment. Since the degree of damage and the urgency of initiating a major overhaul project for the proposed rail equipment effectively reflect the urgency of its need for overhaul, this method allows for a more accurate assessment of the proposed rail equipment's overhaul project initiation, thus improving the accuracy of the assessment. Furthermore, it provides project initiation personnel with more scientific and reasonable decision-making suggestions, thereby improving their efficiency in project initiation. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an evaluation method for initiating a major overhaul project for rail equipment, as provided in an embodiment of this application.

[0023] Figure 2 A flowchart illustrating another evaluation method for initiating a major overhaul project for rail equipment, provided in this application embodiment.

[0024] Figure 3 This is a schematic diagram illustrating a process for constructing a multi-source data fusion feature library, provided as an embodiment of this application.

[0025] Figure 4 A flowchart illustrating another evaluation method for initiating a major overhaul project for rail equipment, provided in this application embodiment.

[0026] Figure 5This is a schematic diagram of the structure of an evaluation device for the initiation of a major overhaul project for rail equipment, provided in an embodiment of this application.

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0029] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0030] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0032] Overhaul and maintenance of rail equipment (referred to as "overhaul") is one of the core tasks in railway maintenance. Its purpose is to ensure the safe and stable operation of railway lines through inspection, maintenance and repair of rail equipment.

[0033] In practical applications, the workflow for major overhaul of rail equipment typically includes project initiation, project approval, and maintenance personnel carrying out the overhaul. Therefore, the initiator usually needs to first assess the proposed major overhaul project to determine whether it is appropriate to proceed with the project.

[0034] However, there is currently limited research on key technologies for initiating rail equipment overhaul projects, and mature evaluation standards for such projects have not yet been established. This may result in a lack of theoretical basis for evaluating whether or not to initiate rail equipment overhaul projects. Consequently, the accuracy of these evaluations may be relatively low.

[0035] To address the aforementioned issues, this embodiment of the application determines the degree of damage to the proposed rail equipment based on its condition assessment data. Furthermore, it determines the urgency of initiating a major overhaul project for the proposed rail equipment based on the historical project data set of each already approved rail equipment and the current project data set of the proposed rail equipment. Since the degree of damage and the urgency of initiating a major overhaul project for the proposed rail equipment effectively reflect the urgency of its need for overhaul and remediation, this method allows for a more accurate determination of the project initiation assessment results, thus improving the accuracy of the project initiation assessment to some extent. Simultaneously, it provides project initiation personnel with more scientific and reasonable decision-making suggestions, thereby improving their project initiation efficiency.

[0036] Specifically, the following detailed description is provided in conjunction with the accompanying drawings and specific embodiments.

[0037] See Figure 1 This is a flowchart illustrating an evaluation method for initiating a major overhaul project for rail equipment, provided in an embodiment of this application. Figure 1 As shown, it mainly includes the following steps.

[0038] Step S101: Input the condition assessment data of the proposed rail equipment into the rail equipment condition assessment model to determine the condition assessment level of the proposed rail equipment.

[0039] It is understood that the proposed rail equipment is rail equipment for which a major overhaul project needs to be initiated. The condition assessment data for the proposed rail equipment includes data corresponding to the condition evaluation indicators of the rail equipment. Among them, the condition evaluation indicators of the rail equipment include, but are not limited to, the number of maintenance operations, maintenance time, number of overhaul operations, overhaul time, number of major overhaul project initiations, major overhaul project initiation time, and types of defects.

[0040] In this embodiment of the application, the condition assessment level of the proposed rail equipment is used to characterize the degree of damage to the proposed rail equipment. The condition assessment level reflects the equipment condition of the proposed rail equipment, and further, reflects the degree of damage to the proposed rail equipment.

[0041] Understandably, equipment status can generally be categorized into four types: healthy, alert, abnormal, and critical. When the equipment status of the proposed rail equipment is healthy, it can be considered undamaged; when the equipment status is alert, it can be considered slightly damaged; when the equipment status is abnormal, it can be considered damaged; and when the equipment status is critical, it can be considered severely damaged.

[0042] It should be noted that, in practical applications, those skilled in the art can also set other types of device states, and this application does not impose specific restrictions on this.

[0043] In one possible implementation, the condition assessment level of the proposed rail equipment is positively correlated with the degree of damage. It can be understood that the higher the condition assessment level of the proposed rail equipment, the more severe the damage and the greater the risk of potential safety hazards.

[0044] For example, the condition assessment levels are divided into Condition Assessment Level I, Condition Assessment Level II, Condition Assessment Level III, and Condition Assessment Level IV. When the condition assessment level of the proposed rail equipment is Condition Assessment Level I, the proposed rail equipment is in a healthy state, indicating that the proposed rail equipment is undamaged and there is no risk of safety hazards; when the condition assessment level of the proposed rail equipment is Condition Assessment Level II, the proposed rail equipment is in a state of caution, indicating that the proposed rail equipment is slightly damaged and there is a low-risk safety hazard; when the condition assessment level of the proposed rail equipment is Condition Assessment Level III, the proposed rail equipment is in an abnormal state, indicating that the proposed rail equipment is damaged and there is a high-risk safety hazard; when the condition assessment level of the proposed rail equipment is Condition Assessment Level IV, the proposed rail equipment is in a severe state, indicating that the proposed rail equipment is severely damaged and there is an extremely high-risk safety hazard.

[0045] In practical applications, the condition assessment level of rail equipment to be approved can be determined using a rail equipment condition assessment model. However, the accuracy of the condition assessment level output by an untrained rail equipment condition assessment model may be low.

[0046] See Figure 2 This is a flowchart illustrating another evaluation method for initiating a major overhaul project for rail equipment, provided in an embodiment of this application. Figure 2 As shown, the embodiments of this application are in Figure 1 Based on the embodiment shown, steps S201-S204 are included before step S101.

[0047] Step S201: Obtain the state assessment dataset.

[0048] Understandably, the condition assessment dataset includes a condition assessment subset corresponding to each rail device. The rail devices are either those with approved projects or those without. Approved rail devices are those that have undergone major overhaul approval, while unapproved rail devices are those that have not undergone major overhaul approval.

[0049] In addition, each condition assessment subset includes condition assessment data corresponding to each rail equipment condition evaluation index.

[0050] In this embodiment of the application, the state evaluation dataset can be represented as an m x n matrix, i.e. Where m is the number of rail equipment; n is the number of rail equipment condition evaluation indicators; x ij Let be the condition assessment data corresponding to the condition evaluation indicators of the i-th rail equipment and the j-th rail equipment. Where l≤i≤m, l≤j≤n.

[0051] It is understandable that the i-th row represents the condition assessment subset of the i-th rail equipment. The j-th column represents the dataset of indicators corresponding to the j-th rail equipment condition evaluation indicator. .

[0052] In practical applications, various types of information, such as basic equipment information, defect information, and maintenance information, are typically distributed across multiple business systems, such as the railway engineering safety production management information system, the railway engineering management information system, the equipment asset management system, and the defect dynamic detection system. Moreover, this information may differ in format and type, exhibiting multi-source and multi-modal characteristics. Therefore, there may be instances where the condition assessment data for rail equipment is incomplete, resulting in lower accuracy of the trained rail equipment condition assessment model, which in turn may lead to lower accuracy in the assessment of rail equipment overhaul projects.

[0053] In one possible implementation, firstly, various types of rail equipment data are acquired, including basic data, defect data, and overhaul data. Then, based on multi-source data fusion technology, the various types of rail equipment data are fused to determine a multi-source data fusion feature library. Finally, based on the condition evaluation index of each rail equipment, a condition assessment dataset is obtained from the multi-source data fusion feature library.

[0054] For details, see Figure 3 This is a schematic diagram illustrating a process for constructing a multi-source data fusion feature library, provided in an embodiment of this application. Figure 3 As shown, the process of constructing a multi-source data fusion feature library specifically includes steps S301 to S305.

[0055] Step S301: Collect data from various rail equipment.

[0056] In practical applications, data from various rail equipment typically originates from different business systems. These systems provide a variety of data tables and project documents related to rail equipment. Examples include equipment attribute data tables, equipment maintenance data tables, equipment maintenance plan data tables, equipment defect data tables, equipment project initiation data tables, equipment fixed asset tables, equipment project initiation tables, equipment TQI data tables, equipment investment project documents, proposed plan documents, project initiation documents, feasibility study reports, implementation plans, and work completion and valuation documents. Therefore, to build a more complete multi-source data fusion feature library, it is usually necessary to first collect data for each type of rail equipment.

[0057] In this embodiment, the collected data on various rail equipment includes basic rail equipment data, rail equipment defect data, and rail equipment overhaul data. The basic rail equipment data includes attribute information for multiple rail equipment, such as equipment name, material type, equipment model, quantity, and railway bureau to which it belongs. The rail equipment defect data includes defect information for multiple rail equipment, such as equipment name, defect type, defect detection method, and repair method. The overhaul data for approved rail equipment includes maintenance information for multiple rail equipment, such as equipment name, maintenance time, and number of maintenance operations. It should be noted that defect types include, but are not limited to, rail corrugation, rail abrasion, and joint defects.

[0058] Step S302: Rail equipment data preprocessing.

[0059] In practical applications, various rail equipment data are characterized by multi-source and multi-modal nature. These multi-source, multi-modal rail equipment data often suffer from inconsistencies, incompleteness, and noise, which may hinder the establishment of correlations between different data sets. For example, unstructured text data from rail equipment overhaul and maintenance has a non-standardized data structure, making it difficult to establish correlations with structured text data.

[0060] In this embodiment of the application, the rail equipment data is preprocessed through operations such as data cleaning and data normalization to eliminate data noise and thus form a standardized data structure.

[0061] For unstructured text data of rail equipment, key fields of the rail equipment (such as equipment name, overhaul method, equipment quantity, unit of measurement, railway bureau, geographical location, etc.) are obtained, and a structured data dictionary is built based on the key fields.

[0062] In this embodiment of the application, by converting the unstructured text data of the rail equipment into a structured data dictionary, it is easier to establish the relationship between the unstructured text data and other structured text data, thereby obtaining more complete condition assessment data of the rail equipment.

[0063] Step S303: Obtain the rail equipment data entity.

[0064] In this embodiment of the application, after preprocessing the collected data of various rail equipment, the rail equipment data entities can be identified and extracted through a network model to establish the association between various rail equipment data.

[0065] Step S304: Establish the association between rail equipment entities.

[0066] In this embodiment of the application, data fusion operations such as entity parsing, primary and foreign key association analysis, entity similarity extraction, spatiotemporal association analysis and data standardization are performed on the extracted rail equipment data entities. By analyzing attributes and relationships, a strong association relationship of composite primary key (e.g., equipment name + equipment identification mark) is established to eliminate contradictions and ambiguities, making the rail equipment data more standardized.

[0067] The spatiotemporal correlation analysis primarily considers the spatiotemporal characteristics of rail equipment status-related data. This aims to integrate equipment status-related data from a spatiotemporal perspective, thereby establishing correlations between this data and other rail equipment data. Regarding the time dimension, correlation analysis can be performed on equipment status-related data within the same time period, or on equipment status-related data from different time periods within the same time period. Regarding the spatial dimension, correlation analysis can be performed on the spatial location of the railway line where the rail equipment is located, including the railway line name, railway line class, and mileage.

[0068] In this embodiment, after establishing associations among rail equipment data entities, a multi-source data fusion feature library can be obtained. Furthermore, based on each rail equipment condition evaluation index, a condition assessment dataset is extracted from the multi-source data fusion feature library.

[0069] Understandably, the multi-source data fusion feature library includes feature data extracted from various rail equipment data, such as rail equipment maintenance time, maintenance frequency, inspection time, inspection frequency, overhaul method, overhaul project initiation time, and defect type.

[0070] In this embodiment, by fusing multi-source, multi-modal rail equipment data, relevant data and relationships between related data can be extracted quickly and accurately. This allows for the extraction of more complete condition assessment data and historical project approval data of the rail equipment from a multi-source data fusion feature library with correlations, thereby improving the assessment accuracy of proposed rail equipment overhaul projects to a certain extent. Simultaneously, it reduces the time and workload for project approval personnel in data screening, improving their work efficiency.

[0071] Step S202: Determine the first weight corresponding to each rail equipment condition evaluation index.

[0072] In practical applications, when training a rail equipment condition assessment model, the level of attention given to different rail equipment condition evaluation indicators may vary. For example, when setting rail equipment condition evaluation indicators as "number of maintenance visits," "number of overhaul visits," "major overhaul project status," and "current defect type," the assessment of rail equipment condition may place greater emphasis on the "current defect type" indicator. Therefore, it is possible to differentiate the importance of rail equipment condition evaluation indicators by assigning corresponding weights to each indicator.

[0073] To distinguish it from other weights used later in this application, the weight used to weight the state evaluation data in the state evaluation dataset is referred to as the "first weight" in this embodiment. The specific details of "weighting the state evaluation data in the state evaluation dataset" will be described in detail below and will not be repeated here.

[0074] Currently, the Analytic Hierarchy Process (AHP) or the entropy weight method can be used to assign corresponding first weights to the rail equipment condition evaluation indicators. However, the AHP relies on expert experience to compare different rail equipment condition evaluation indicators pairwise to assign corresponding first weights, making it susceptible to the influence of personal subjective biases. The entropy weight method relies on the data corresponding to the rail equipment condition evaluation indicators to assign corresponding first weights, ignoring the mutual influence and correlation between indicators. Therefore, it may lead to inaccurate weight allocation and fail to fully reflect the actual situation of the evaluation indicators.

[0075] In this embodiment, the Analytic Hierarchy Process (AHP) and the entropy weight method can be combined to assign corresponding first weights to the rail equipment condition evaluation indicators. This process is specifically divided into three steps: AHP weighting, entropy weighting, and combined weighting. These three weighting processes will be described in detail below.

[0076] (1) Weighting by Analytic Hierarchy Process: Based on the evaluation results of the importance of each rail equipment status evaluation index by multiple experts, the second weight corresponding to each rail equipment status evaluation index is determined by Analytic Hierarchy Process.

[0077] In this embodiment of the application, multiple experts are selected to evaluate the importance of each rail equipment condition evaluation index, and the evaluation results of each expert on the importance of each rail equipment condition evaluation index are obtained.

[0078] Specifically, each expert compares all the rail equipment condition evaluation indicators pairwise. Based on preset scaling rules (e.g., the 1-5 scaling method or the 1-9 scaling method), an indicator judgment matrix corresponding to each expert is constructed. Where n represents the number of rail equipment condition evaluation indicators.

[0079] Understandable, A s n×n Let be the indicator judgment matrix corresponding to the s-th expert. Wherein, , l≤j≤n, l≤k≤n. This indicates the importance of the k-th rail equipment condition evaluation index determined by the s-th expert relative to the j-th rail equipment condition evaluation index.

[0080] In this embodiment of the application, when the indicator judgment matrix A corresponding to each expert is determined... s n×n Then, determine the judgment matrix A for each indicator. s n×n Corresponding weight vector This is to obtain the normalized weight value of each rail equipment condition evaluation index determined by each expert.

[0081] Among them, w s w is the weight vector corresponding to the s-th expert; s k Let be the normalized weight value corresponding to the k-th rail equipment condition evaluation index determined by the s-th expert.

[0082] Specifically, according to the formula Calculate w s k .in, Let A be the indicator judgment matrix corresponding to the s-th expert. s n×n The product of all elements in the k-th row.

[0083] In practical applications, after determining the weight vector corresponding to each expert, for each rail equipment condition evaluation index, the normalized weight value corresponding to that rail equipment condition evaluation index can be added to the weight vector of each expert to determine the second weight of each rail equipment condition evaluation index. To distinguish it from the "first weight" mentioned above, in this embodiment, the weight determined by the analytic hierarchy process is referred to as the "second weight".

[0084] However, this method does not take into account the expertise and influence of each expert in evaluating the importance of rail equipment condition indicators, which may result in lower scientific validity and reliability of the second weight allocation.

[0085] Therefore, in this embodiment, an expert evaluation weight is determined for each expert based on their evaluation authority. The expert evaluation weight is positively correlated with the expert's evaluation authority. It can be understood that the higher the expert's evaluation authority regarding the importance of each rail equipment condition evaluation indicator, the more reliable the expert's evaluation result for each rail equipment condition evaluation indicator, and the higher the corresponding expert evaluation weight.

[0086] In this embodiment of the application, after determining the expert evaluation weight for each expert, it can be done according to the formula: The second weight corresponding to each rail equipment condition evaluation index is determined. Let λ be the second weight corresponding to the k-th rail equipment condition evaluation index. s Let be the expert evaluation weight of the s-th expert.

[0087] For example, when five experts are selected to evaluate the importance of the rail equipment condition evaluation indicators, the evaluation weight for each expert can be set to 0.2. Of course, those skilled in the art can set other expert evaluation weights according to actual needs, and this application embodiment does not impose specific limitations on this.

[0088] In this embodiment, the professional level and influence of each expert in evaluating the importance of rail equipment condition evaluation indicators are fully considered, making the second weight assigned to each rail equipment condition evaluation indicator more scientific and reliable.

[0089] (2) Entropy weight method: Based on the state assessment dataset, the third weight corresponding to each rail equipment state evaluation index is determined by the entropy weight method.

[0090] To distinguish it from the "first weight" and "second weight" mentioned above, in this embodiment of the application, the weight determined by the entropy weight method is referred to as the "third weight".

[0091] In this embodiment of the application, according to the formula: Determine the entropy value corresponding to each rail equipment condition evaluation index.

[0092] Where, r j Let be the entropy value corresponding to the j-th rail equipment condition evaluation index; p ij For x ij The proportion of the index data corresponding to the j-th rail equipment condition evaluation index; x ij The condition assessment data corresponds to the condition evaluation indicators of the i-th approved rail equipment and the j-th rail equipment. Let Y be the index dataset corresponding to the j-th rail equipment condition evaluation index. j The sum of all data values ​​in the set, l≤t≤m.

[0093] In this embodiment of the application, after determining the entropy value corresponding to each rail equipment condition evaluation index, it can be calculated according to the formula: The third weight corresponding to each rail equipment condition evaluation index is determined. The third weight corresponds to the j-th rail equipment condition evaluation index; 1-r j Let be the information entropy redundancy corresponding to the j-th rail equipment condition evaluation index; This is the sum of the information entropy redundancy corresponding to each rail equipment condition evaluation index.

[0094] (3) Combination weighting: Based on the second and third weights corresponding to each rail equipment condition evaluation index, determine the first weight corresponding to each rail equipment condition evaluation index.

[0095] In practical applications, for each rail equipment condition evaluation index, after determining the corresponding second and third weights, the corresponding second and third weights can be added together to determine the corresponding first weight. However, the second and third weights may have different levels of importance and reliability. Simply adding the second and third weights together may not allow for flexible adjustment of their proportions, potentially leading to poor flexibility and applicability in calculating the first weight.

[0096] Therefore, in one possible implementation, the proportion of weights determined by the analytic hierarchy process (AHP) and the entropy weight method can be allocated through a weight adjustment coefficient. For example, for each rail equipment condition evaluation index, the second weight determined by the AHP accounts for 0.2, and the third weight determined by the entropy weight method accounts for 0.8.

[0097] However, different rail equipment condition evaluation indicators differ fundamentally in terms of data characteristics and decision importance. Therefore, the importance assigned by the analytic hierarchy process (AHP) and the entropy weighting method may differ for each rail equipment condition evaluation indicator. Using the same weight adjustment coefficient for each rail equipment condition evaluation indicator may prevent the determination of a more accurate first weight for some indicators, potentially affecting the training accuracy of the rail equipment condition assessment model.

[0098] In one possible implementation, the first weight corresponding to each rail equipment condition evaluation index is determined based on the second weight, the third weight, and the weight adjustment coefficient corresponding to each rail equipment condition evaluation index.

[0099] Specifically, according to the formula: Calculate the first weight corresponding to each rail equipment condition evaluation index.

[0100] in, The first weight corresponds to the j-th rail equipment condition evaluation index; , Let be the weight adjustment coefficient corresponding to the j-th rail equipment condition evaluation index. Let be the standard deviation of all data elements in the index dataset corresponding to the j-th rail equipment condition evaluation index; The sum of the standard deviations corresponding to each rail equipment condition evaluation index; The second weight corresponds to the j-th rail equipment condition evaluation index; The third weight corresponds to the j-th rail equipment condition evaluation index.

[0101] In this embodiment of the application, by adjusting the weight adjustment coefficient corresponding to each rail equipment condition evaluation index, the proportion of the second weight and the third weight corresponding to each rail equipment condition evaluation index can be adjusted, so that each rail equipment condition evaluation index can adapt to its own data characteristics and decision importance, thereby improving the training accuracy of the rail equipment condition assessment model to a certain extent.

[0102] Step S203: Based on the first weight corresponding to each rail equipment condition evaluation index, weight each condition evaluation data in each condition evaluation subset to determine the weighted condition evaluation subset corresponding to each rail equipment, so as to obtain the weighted condition evaluation dataset.

[0103] As mentioned above, the condition assessment subset for each rail device includes condition assessment data corresponding to each rail device condition evaluation index. Therefore, based on the first weight corresponding to each rail device condition evaluation index, the condition assessment data corresponding to each rail device condition evaluation index in each condition assessment subset can be weighted to obtain a weighted condition assessment dataset.

[0104] In this embodiment of the application, the weighted state evaluation dataset can be represented as ,in, .

[0105] Understandable To evaluate x based on the first weight corresponding to the j-th rail equipment condition evaluation index ij Weighted state assessment data, x ij For state assessment dataset The condition assessment data corresponding to the condition evaluation indicators of the i-th rail equipment and the j-th rail equipment.

[0106] Step S204: Train the rail equipment condition assessment model based on each weighted condition assessment subset.

[0107] In this embodiment, a random forest algorithm is used to perform regression analysis on each weighted condition assessment subset to train the rail equipment condition assessment model. Furthermore, the condition assessment level of the proposed rail equipment can be evaluated using this model.

[0108] It is understandable that training a rail equipment condition assessment model using a weighted subset of condition assessment data can improve the accuracy of the model to some extent. Based on a more accurate rail equipment condition assessment model, a more precise condition assessment level can be determined for the proposed rail equipment.

[0109] Step S102: Based on the historical project approval dataset and the current project approval dataset of each of the multiple approved rail equipment projects, determine the project approval early warning assessment level of the proposed rail equipment.

[0110] In this embodiment, the historical project approval dataset corresponding to each approved rail equipment can be extracted from the multi-source data fusion feature library. It is understood that the historical project approval dataset corresponding to each approved rail equipment includes, but is not limited to, the equipment name, overhaul method, mileage, and historical project approval year of the approved rail equipment. The current project approval dataset for proposed rail equipment includes, but is not limited to, the equipment name, overhaul method, mileage, and proposed project approval year of the proposed rail equipment.

[0111] It should be noted that, due to the diverse types of defects and overhaul methods of rail equipment, there may be multiple corresponding historical project datasets for each approved rail equipment project.

[0112] In this embodiment, the project approval early warning assessment level for the proposed rail equipment is used to characterize the urgency of initiating a major overhaul project for the proposed equipment. Specifically, the project approval early warning assessment level is positively correlated with the difference between the proposed project approval year and the historical project approval year of the previous project. For ease of description, the difference between the proposed project approval year and the historical project approval year of the previous project is referred to as the "project approval year difference".

[0113] Understandably, the larger the difference in project initiation year, the longer the time since the last major overhaul of the proposed rail equipment, and the greater the potential damage to the proposed rail equipment. Therefore, the higher the urgency of needing to initiate another major overhaul project, the higher the project initiation early warning assessment level.

[0114] In this embodiment of the application, after determining the difference in the year of the proposed rail equipment project, the project early warning assessment level of the proposed rail equipment project can be determined from the correspondence between the difference in the year of the proposed project and the early warning assessment level.

[0115] For example, the difference in project approval year A < b1 and b1 < difference in project approval year B ≤ b2; the correspondence between the difference in project approval year and the project approval early warning assessment level is shown in Table 1. It can be understood that when the difference in project approval year corresponding to the proposed rail equipment project is A, since A < b1, the project approval early warning assessment level is determined to be Project Approval Early Warning Assessment Level I; similarly, when the difference in project approval year corresponding to the proposed rail equipment project is B, since b1 < difference in project approval year B ≤ b2, the project approval early warning assessment level is determined to be Project Approval Early Warning Assessment Level II; and so on. This embodiment of the application will not elaborate further on this.

[0116] Table 1:

[0117] It should be noted that the above table is only an exemplary illustration of the correspondence between the difference in project approval year and the project approval early warning assessment level. In practical applications, those skilled in the art can set other correspondences between the difference in project approval year and the project approval early warning assessment level, such as a curve or model of the correspondence between the difference in project approval year and the project approval early warning assessment level.

[0118] See Figure 4 This is a flowchart illustrating another evaluation method for initiating a major overhaul project for rail equipment, provided in an embodiment of this application. Figure 4 As shown, the embodiments of this application are in Figure 1Based on the embodiment shown, step S102 includes steps S401-S403.

[0119] Step S401: Based on the historical project data set corresponding to each of the multiple approved rail equipment projects and the current project data set of the proposed rail equipment project, determine the similarity between the rail equipment and the rail equipment corresponding to each approved rail equipment project.

[0120] In practical applications, the equipment name is usually the unique identifier of the proposed rail equipment. Generally, based on the equipment name of the proposed rail equipment, it is possible to identify the existing rail equipment that matches the proposed rail equipment from the historical project approval datasets corresponding to multiple existing rail equipment projects, thereby determining the project approval early warning assessment level of the proposed rail equipment.

[0121] However, the types of defects and overhaul methods of the proposed rail equipment are diverse. Therefore, the number of proposed rail equipment projects may vary. Consequently, simply identifying existing rail equipment projects that match the proposed project based on equipment name may not be sufficient to pinpoint the most similar existing rail equipment. This could lead to inaccurate assessments of the project's early warning level.

[0122] As mentioned above, each historical project dataset includes the equipment name, overhaul method, and mileage of the approved rail equipment, while the current project dataset includes the equipment name, overhaul method, and mileage of the proposed rail equipment.

[0123] Therefore, in this embodiment, the similarity between the proposed rail equipment and each existing rail equipment can be determined by the similarity in equipment name, overhaul method, and mileage proximity. This allows for the identification of the existing rail equipment most similar to the proposed rail equipment. The calculation process for the similarity in equipment name, overhaul method, mileage proximity, and rail equipment similarity between the proposed rail equipment and each existing rail equipment will be described in detail below.

[0124] (1) Calculation of equipment name similarity: Based on the equipment name corresponding to each of the multiple approved rail equipment projects and the equipment name of the proposed rail equipment project, determine the similarity of the equipment name with each approved rail equipment project.

[0125] Specifically, it can be determined according to the formula: The similarity of equipment names between each approved and proposed rail equipment project is calculated using the Levenshtein algorithm.

[0126] Among them, S name_iLet Lev(u) be the similarity of the names of the i-th approved rail equipment and the proposed rail equipment; i ,v) is the string u i Levenshtein distance between string u and string v; i The string represents the name of the i-th approved rail equipment; string v represents the name of the proposed rail equipment; |u i | represents the string u i The length of string v; |v| represents the length of string v.

[0127] In this application embodiment, the greater the similarity between the names of the approved rail equipment and the proposed rail equipment, the more similar the approved rail equipment and the proposed rail equipment are.

[0128] (2) Calculation of overhaul method similarity: Based on the overhaul method corresponding to each approved rail equipment and the overhaul method of the proposed rail equipment, determine the similarity with the overhaul method corresponding to each approved rail equipment.

[0129] Specifically, it can be determined according to the formula: The similarity of overhaul methods for each approved and proposed rail equipment was calculated using the Levenshtein algorithm.

[0130] Among them, S process_i Let Lev(i) represent the similarity of overhaul methods between the i-th approved and proposed rail equipment projects; (h) is a string Levenshtein distance between string h and string h; string The string represents the overhaul method corresponding to the i-th approved rail equipment project; the string h represents the overhaul method corresponding to the proposed rail equipment project. Represents a string The length of string h; |h| represents the length of string h.

[0131] Additionally, if the strings corresponding to the overhaul methods of the i-th approved rail equipment and the proposed rail equipment are exactly the same, the score for complete consistency with the i-th approved rail equipment is 1; otherwise, it is 0.

[0132] In the embodiments of this application, the greater the similarity between the overhaul methods of the approved rail equipment and the proposed rail equipment, the more similar the approved rail equipment and the proposed rail equipment are.

[0133] (3) Mileage proximity calculation: Based on the mileage corresponding to each approved rail equipment and the mileage of the proposed rail equipment, determine the mileage proximity to each approved rail equipment.

[0134] Specifically, it can be determined according to the formula: The mileage proximity of each approved and proposed rail equipment project is calculated using the Haversine algorithm.

[0135] Where, f(d) i ) represents the mileage proximity of the i-th approved and proposed rail equipment projects; d is the distance attenuation coefficient; i Let represent the geographical distance between the i-th approved rail equipment and the proposed rail equipment.

[0136] In this embodiment of the application, the greater the mileage proximity between the approved rail equipment and the proposed rail equipment, the closer the actual distance between the approved rail equipment and the proposed rail equipment.

[0137] (4) Calculation of similarity of rail equipment: Based on the similarity of equipment name, overhaul method and mileage of each approved rail equipment, determine the similarity of rail equipment to each approved rail equipment.

[0138] In practical applications, for each approved and proposed rail equipment, the similarity of equipment name, overhaul method, and mileage can be calculated by adding the similarity of equipment name, overhaul method, and mileage to the corresponding approved rail equipment, thereby determining the corresponding rail equipment similarity.

[0139] In this embodiment, the similarity between approved and proposed rail equipment is calculated by combining the similarity of equipment names, overhaul methods, and mileage proximity. This allows for a more accurate identification of the approved rail equipment most similar to the proposed rail equipment. Based on this more accurate assessment of the most similar approved rail equipment, a more precise project approval early warning level for the proposed rail equipment can be determined.

[0140] However, equipment name similarity, overhaul method similarity, and mileage proximity may have different levels of importance and reliability. The method described above for calculating rail equipment similarity may not be flexible enough to adjust the proportions of equipment name similarity, overhaul method similarity, and mileage proximity, potentially resulting in poor flexibility and applicability in calculating rail equipment similarity.

[0141] In one possible implementation, for each approved rail equipment, the similarity of equipment name, overhaul method, and mileage proximity is calculated by weighting the similarity of equipment name, overhaul method, and mileage proximity according to the similarity weights corresponding to these factors, thus determining the rail equipment similarity to each approved rail equipment.

[0142] Specifically, according to the formula: Calculate the similarity of rail equipment with each approved and proposed rail equipment project.

[0143] Among them, SimScore i The similarity between the i-th approved rail equipment and the proposed rail equipment is calculated. The similarity weights are the equipment name similarities between the i-th approved rail equipment and the proposed rail equipment. Let be the similarity weight corresponding to the similarity of the overhaul methods of the i-th approved rail equipment and the proposed rail equipment. Let be the similarity weight corresponding to the mileage proximity of the i-th approved rail equipment and the proposed rail equipment.

[0144] In this embodiment, since equipment name similarity can reflect the uniqueness of approved rail equipment, a relatively high similarity weight is usually given to equipment name similarity. The same similarity weight is given to overhaul method similarity and mileage proximity. For example, .

[0145] Of course, those skilled in the art can set other similarity weights according to actual needs, and the embodiments of this application do not impose specific limitations on this.

[0146] In this embodiment of the application, by setting corresponding similarity weights for equipment name similarity, overhaul method similarity, and mileage proximity, the proportions of equipment name similarity, overhaul method similarity, and mileage proximity can be flexibly adjusted, thereby improving the flexibility and applicability of calculating rail equipment similarity to a certain extent.

[0147] Step S402: Determine the target similar rail equipment based on the similarity of the rail equipment corresponding to each approved rail equipment project.

[0148] In this embodiment of the application, after determining the similarity between each approved and proposed rail equipment, the approved rail equipment with the highest similarity is identified as the target similar rail equipment. It can be understood that the target similar rail equipment is the rail equipment most similar to the proposed rail equipment.

[0149] Step S403: Determine the early warning assessment level of the proposed rail equipment project based on the difference between the proposed project approval year and the historical project approval year of similar rail equipment.

[0150] In this embodiment of the application, after identifying the target similar rail equipment, the corresponding historical project approval year can be determined from the historical project approval dataset corresponding to the target similar rail equipment. It can be understood that the historical project approval year corresponding to the target similar rail equipment can be considered as the historical project approval year of the last time the proposed rail equipment was approved.

[0151] Furthermore, based on the difference between the proposed year of approval for the proposed rail equipment project and the historical year of approval in the previous approval process, the project approval early warning assessment level for the proposed rail equipment project can be determined. The relevant content regarding "determining the project approval early warning assessment level for the proposed rail equipment project" in this application embodiment can be found in the description of step S102, and will not be repeated here for the sake of brevity.

[0152] To improve the work efficiency of project initiation personnel, once the similarity between the proposed rail equipment and each already approved rail equipment is determined, it is possible to assess the project initiation early warning level for some or all of the already approved rail equipment.

[0153] Specifically, after step S401, the method further includes: sorting the similarity of each approved rail equipment in descending order to obtain a sorted sequence of approved rail equipment; identifying the top N potential approved rail equipment in the sorted sequence, where N≥1; and determining the project approval early warning assessment level corresponding to each potential approved rail equipment based on the difference between the proposed approval year of the proposed rail equipment and the historical approval year of each potential approved rail equipment.

[0154] In this embodiment, the sorted sequence of approved rail equipment includes multiple approved rail equipment projects. The similarity of these multiple approved rail equipment projects is arranged in descending order. The first N approved rail equipment projects in the sorted sequence are selected as potential approved rail equipment projects.

[0155] Understandably, the similarity between potential rail equipment projects and those proposed for approval is relatively high compared to the similarity between non-potential rail equipment and those proposed for approval. This increases the likelihood that potential rail equipment projects will require further major overhaul approval. Therefore, a project approval early warning assessment level can be conducted for potential rail equipment projects with a relatively high degree of similarity to those proposed for approval.

[0156] In this embodiment of the application, for each potential rail equipment project, the corresponding historical project approval year is determined from the historical project approval dataset of the potential rail equipment. The proposed project approval year of the proposed rail equipment is subtracted from the corresponding historical project approval year of the potential rail equipment to determine the difference in project approval year for the potential rail equipment.

[0157] Furthermore, the project establishment early warning assessment level for potential rail equipment projects is determined by analyzing the relationship between the difference in project establishment year and the project establishment early warning assessment level. The relevant content regarding "determining the project establishment early warning assessment level for potential rail equipment projects" in this application embodiment can be found in the description of step S102, and will not be repeated here for the sake of brevity.

[0158] In this embodiment, only potential rail equipment projects with a relatively high degree of similarity to the proposed rail equipment are assessed for project approval early warning level. Since project approval personnel do not need to assess the project approval early warning level for every piece of already approved rail equipment, they can promptly identify those projects that may require further major repairs, thus improving their work efficiency. Furthermore, this allows maintenance personnel to promptly carry out major repairs on potential rail equipment with high project approval early warning levels, thereby ensuring the safe and stable operation of railway lines to a certain extent.

[0159] Step S103: Determine the project assessment results for the overhaul of the proposed rail equipment based on the status assessment level and the project establishment early warning assessment level.

[0160] In this embodiment of the application, after determining the status assessment level and project establishment early warning assessment level of the proposed rail equipment, the project establishment assessment result of the proposed rail equipment can be determined from the correspondence between the status assessment level, the project establishment early warning assessment level and the project establishment assessment result of the overhaul.

[0161] For example, the correspondence between the condition assessment level, the project approval warning assessment level, and the overhaul project approval result is shown in Table 2. When the condition assessment level of the proposed rail equipment is both Condition Assessment Level I and Project Approval Warning Assessment Level I, it indicates that the overhaul project approval result for the proposed rail equipment is not recommended. When the condition assessment level of the proposed rail equipment is both Condition Assessment Level II and Project Approval Warning Assessment Level I, it indicates that the overhaul project approval result for the proposed rail equipment is not recommended. And so on. This embodiment of the application will not elaborate further.

[0162] Table 2:

[0163] It should be noted that the above table is only an exemplary illustration of the correspondence between the status assessment level, the project establishment early warning assessment level, and the overhaul project establishment assessment result. In practical applications, those skilled in the art can set other correspondences between the status assessment level, the project establishment early warning assessment level, and the overhaul project establishment assessment result, such as a correspondence curve or a correspondence model between the status assessment level, the project establishment early warning assessment level, and the overhaul project establishment assessment result.

[0164] In this embodiment, the degree of damage to the proposed rail equipment is determined based on its condition assessment data. The urgency of initiating a major overhaul project for the proposed rail equipment is determined based on the historical project data set of each already approved rail equipment and the current project data set of the proposed rail equipment. Since the degree of damage and the urgency of initiating a major overhaul project for the proposed rail equipment effectively reflect the urgency of its need for overhaul, this method allows for a more accurate assessment of the proposed rail equipment's overhaul project initiation, thus improving the accuracy of the assessment. Furthermore, it provides project initiation personnel with more scientific and reasonable decision-making suggestions, thereby improving their efficiency in project initiation.

[0165] Corresponding to the above method embodiments, this application also provides an evaluation device for the establishment of a major overhaul project for rail equipment.

[0166] See Figure 5 This is a structural schematic diagram of an evaluation device for initiating a major overhaul project for rail equipment, provided in an embodiment of this application. Figure 5 As shown, the evaluation device 500 for the overhaul project of rail equipment includes: a status evaluation level determination module 501, a project establishment early warning evaluation level determination module 502, and an overhaul project establishment evaluation result determination module 503.

[0167] Specifically, the condition assessment level determination module 501 is used to input the condition assessment data of the proposed rail equipment into the rail equipment condition assessment model to determine the condition assessment level of the proposed rail equipment. The condition assessment level is used to characterize the degree of damage to the proposed rail equipment.

[0168] The project establishment early warning assessment level determination module 502 is used to determine the project establishment early warning assessment level of the proposed rail equipment based on the historical project establishment dataset corresponding to each of the multiple approved rail equipment projects and the current project establishment dataset of the proposed rail equipment. The project establishment early warning assessment level is used to characterize the urgency of the proposed equipment to undergo major repair project establishment.

[0169] The overhaul project evaluation result determination module 503 is used to determine the overhaul project evaluation result of the proposed rail equipment based on the condition evaluation level and the project establishment early warning evaluation level.

[0170] For details regarding the specific content involved in the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, these details will not be repeated here.

[0171] Corresponding to the above embodiments, this application also provides an electronic device.

[0172] See Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 600 may include a processor 601, a memory 602, and a communication unit 603. These components communicate via one or more buses. Those skilled in the art will understand that the electronic device structure shown in the figures does not constitute a limitation on the embodiments of this application. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0173] The communication unit 603 is used to establish a communication channel, thereby enabling the electronic device to communicate with other devices.

[0174] The processor 601 serves as the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes software programs and / or modules stored in the memory 602, and calls data stored in the memory to perform various functions and / or process data. The processor may be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 601 may consist only of a central processing unit (CPU). In this embodiment, the CPU may have a single processing core or include multiple processing cores.

[0175] Memory 602 is used to store the execution instructions of processor 1001. Memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0176] When the execution instructions in memory 602 are executed by processor 601, the electronic device 600 is able to perform some or all of the steps in the above method embodiments.

[0177] Corresponding to the above embodiments, this application also provides a computer-readable storage medium, wherein the computer-readable storage medium may store a program, wherein when the program runs, it can control the device where the computer-readable storage medium is located to execute some or all of the steps in the above method embodiments. In specific implementation, the computer-readable storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0178] Corresponding to the above embodiments, this application also provides a computer program product containing executable instructions that, when executed on a computer, cause the computer to perform some or all of the steps in the above method embodiments.

[0179] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0180] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0181] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0182] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0183] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

Claims

1. An evaluation method for initiating major overhaul projects for rail equipment, characterized in that, include: The condition assessment data of the proposed rail equipment is input into the rail equipment condition assessment model to determine the condition assessment level of the proposed rail equipment. The condition assessment level is used to characterize the degree of damage to the proposed rail equipment. Based on the historical project approval dataset corresponding to each of the multiple approved rail equipment projects and the current project approval dataset of the proposed rail equipment project, the project approval early warning assessment level of the proposed rail equipment project is determined. The project approval early warning assessment level is used to characterize the urgency of the proposed equipment project project for major overhaul. Based on the status assessment level and the project establishment early warning assessment level, the project establishment assessment result for the proposed overhaul of the rail equipment is determined.

2. The method according to claim 1, characterized in that, Before inputting the condition assessment data of the proposed rail equipment into the rail equipment condition assessment model, the following steps are also included: Obtain a condition assessment dataset, which includes a condition assessment subset for each rail device. The rail devices are either approved rail devices or unapproved rail devices. Each condition assessment subset includes condition assessment data corresponding to the condition evaluation index of each rail device. Determine the first weight corresponding to each of the rail equipment condition evaluation indicators; Based on the first weight corresponding to each rail equipment condition evaluation index, each condition evaluation data in each condition evaluation subset is weighted to determine the weighted condition evaluation subset corresponding to each rail equipment, so as to obtain the weighted condition evaluation dataset. A rail equipment condition assessment model is trained based on each of the weighted condition assessment subsets.

3. The method according to claim 2, characterized in that, The acquisition of the state assessment dataset includes: Acquire various types of rail equipment data, including basic rail equipment data, rail equipment defect data, and rail equipment overhaul data. Based on multi-source data fusion technology, data from various rail equipment are fused to determine a multi-source data fusion feature library. Based on the condition evaluation index of each rail equipment, the condition assessment dataset is obtained from the multi-source data fusion feature library.

4. The method according to claim 2, characterized in that, The determination of the first weight corresponding to each of the rail equipment condition evaluation indicators includes: Based on the importance evaluation results of each rail equipment condition evaluation index by multiple experts, the second weight corresponding to each rail equipment condition evaluation index is determined by the analytic hierarchy process. Based on the state assessment dataset, the third weight corresponding to each of the rail equipment state assessment indicators is determined by the entropy weight method. Based on the second and third weights corresponding to each rail equipment condition evaluation index, the first weight corresponding to each rail equipment condition evaluation index is determined.

5. The method according to claim 4, characterized in that, The step of determining the first weight corresponding to each rail equipment condition evaluation index based on the second weight and the third weight corresponding to each rail equipment condition evaluation index includes: Based on the second weight, third weight, and weight adjustment coefficient corresponding to each rail equipment condition evaluation index, the first weight corresponding to each rail equipment condition evaluation index is determined.

6. The method according to claim 1, characterized in that, The step of determining the project approval early warning assessment level of the proposed rail equipment based on the historical project approval dataset corresponding to each of the multiple approved rail equipment projects and the current project approval dataset of the proposed rail equipment includes: Based on the historical project data set corresponding to each of the multiple approved rail equipment projects and the current project data set of the proposed rail equipment project, the similarity with each of the approved rail equipment projects is determined. Based on the similarity of each of the approved rail equipment projects, target similar rail equipment is determined; The project establishment early warning assessment level of the proposed rail equipment is determined based on the difference between the proposed establishment year and the historical establishment year of the target similar rail equipment.

7. The method according to claim 6, characterized in that, Each historical project dataset includes the equipment name, overhaul method, and mileage of the approved rail equipment. The current project dataset includes the equipment name, overhaul method, and mileage of the proposed rail equipment. Determining the similarity between each approved rail equipment and its corresponding historical project dataset and the proposed rail equipment, based on the proposed historical project dataset and the current project dataset, includes: Based on the equipment name corresponding to each of the multiple approved rail equipment projects and the equipment name of the proposed rail equipment project, determine the similarity with the equipment name corresponding to each of the approved rail equipment projects; Based on the overhaul method corresponding to each of the approved rail equipment projects and the overhaul method of the proposed rail equipment projects, determine the similarity with the overhaul method corresponding to each of the approved rail equipment projects; Based on the mileage corresponding to each of the approved rail equipment projects and the mileage of the proposed rail equipment projects, determine the proximity to the mileage corresponding to each of the approved rail equipment projects; Based on the similarity of equipment name, overhaul method, and mileage proximity of each of the approved rail equipment projects, the similarity of the rail equipment to the approved rail equipment project is determined.

8. The method according to claim 7, characterized in that, The step of determining the similarity of rail equipment to each of the approved rail equipment projects based on the similarity of equipment name, overhaul method, and mileage proximity includes: For each of the approved rail equipment, the similarity of equipment name, the similarity of overhaul method, and the proximity of mileage are calculated by weighting the similarity of equipment name, the similarity of overhaul method, and the proximity of mileage according to the similarity weights corresponding to these factors, and then determining the similarity of the rail equipment to each of the approved rail equipment.

9. The method according to claim 6, characterized in that, After determining the similarity of the rail equipment corresponding to each of the approved rail equipment projects, the method further includes: The similarity of each of the approved rail equipment projects is sorted in descending order to obtain the sorted sequence of approved rail equipment projects. From the sorted sequence of approved rail equipment projects, identify the top N potential rail equipment projects for approval, where N ≥ 1; Based on the difference between the proposed year of approval for the proposed rail equipment and the historical year of approval for each potential rail equipment, the project approval early warning assessment level corresponding to each potential rail equipment is determined.

10. An evaluation device for the initiation of major overhaul projects for rail equipment, characterized in that, include: The condition assessment level determination module is used to input the condition assessment data of the proposed rail equipment into the rail equipment condition assessment model to determine the condition assessment level of the proposed rail equipment. The condition assessment level is used to characterize the degree of damage of the proposed rail equipment. The project initiation early warning assessment level determination module is used to determine the project initiation early warning assessment level of the proposed rail equipment based on the historical project initiation dataset corresponding to each of the multiple approved rail equipment projects and the current project initiation dataset of the proposed rail equipment. The project initiation early warning assessment level is used to characterize the urgency of the proposed equipment to undergo major repair project initiation. The overhaul project evaluation result determination module is used to determine the overhaul project evaluation result of the proposed rail equipment based on the status evaluation level and the project establishment early warning evaluation level.

11. An electronic device, characterized in that, include: processor; Memory; And a computer program, wherein the computer program is stored in the memory, and when the computer program is executed by the processor, causes the electronic device to perform the method of any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 9.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 9.

Images