Heavy haul railway mechanical maintenance decision-making method, device, equipment and medium

Abstract

The invention relates to the technical field of railway safety detection, and provides a heavy haul railway mechanical maintenance decision-making method, device, equipment and medium, and the method comprises the steps: determining an operation state corresponding to a maintenance index on each track unit; calculating an index composite weight corresponding to each maintenance and repair index according to a detection index in the maintenance and repair indexes on each track unit; calculating a maintenance index of the maintenance indexes according to a detection index in the maintenance indexes and the index composite weight; performing priority clustering on the track units according to the maintenance indexes, extracting spatial distribution of all the track units in the track unit clusters with the same priority, and extracting interval track units corresponding to the track units in the track unit clusters according to the spatial distribution; and combining the track units in the spatial distribution and the spaced track units into track sections, and carrying out maintenance operation on the track sections according to the priorities corresponding to the track sections. The efficiency of heavy haul railway mechanical maintenance decision making can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of railway safety detection, and in particular to a heavy-load railway mechanized maintenance decision-making method, device, equipment and medium. Background Art

[0002] In recent years, heavy-haul railways have become the development trend of global railway freight due to their advantages of large transport volume and low cost. However, due to the repeated unloading and loading of heavy-haul trucks and the influence of complex natural environment, the interaction between trains and tracks has gradually intensified. The health of heavy-haul railway lines faces severe challenges. Therefore, the field of line maintenance and repair has attracted increasing attention. By formulating a scientific and reasonable large-scale machine maintenance operation plan, we can guide various repair and maintenance work of the line and ensure the safety and reliability of railway transportation.

[0003] Most of the existing railway line maintenance technologies are studied for passenger railway lines, and only consider the maintenance decisions of a certain type of large-scale machine operation, such as rail grinding or tamping. They cannot take into account the different large-scale machine operations, increase the cases of "over-repair" and "under-repair", and lead to slower mechanized maintenance, thus reducing the efficiency of mechanized maintenance decisions for heavy-load railways. Summary of the invention

[0004] In view of the above problems, embodiments of the present invention provide a heavy-haul railway mechanized maintenance decision-making method, device, equipment and medium.

[0005] In a first aspect, an embodiment of the present invention provides a heavy-haul railway mechanized maintenance decision-making method, comprising:

[0006] Determine the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold;

[0007] Calculating the index composite weight corresponding to each maintenance and repair index according to the detection index in the maintenance and repair index on each track unit;

[0008] When the operation state corresponding to the maintenance and repair indicator is the preset target state, the maintenance index of the maintenance and repair indicator is calculated according to the detection indicator in the maintenance and repair indicator and the composite weight of the indicator;

[0009] Priority clustering is performed on the track units according to the maintenance index to obtain a track unit cluster, and the spatial distribution of all track units in the track unit cluster with the same priority is extracted, and the interval track units corresponding to the track units in the track unit cluster are extracted according to the spatial distribution;

[0010] The track units in the spatial distribution and the interval track units are merged into a track segment according to a preset track unit interval threshold, and maintenance operations are performed on the track segment according to the priority corresponding to the track segment.

[0011] According to an embodiment of the present invention, determining the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold includes:

[0012] When any indicator value of the maintenance and repair indicators pre-acquired on each track unit is greater than the preset railway line indicator threshold, extract the first maintenance and repair indicator corresponding to the indicator value greater than the preset railway line indicator threshold, and extract the second maintenance and repair indicator corresponding to the indicator value less than or equal to the preset railway line indicator threshold;

[0013] Determine the operating state corresponding to the first maintenance and repair indicator as a preset first operating state, and determine the operating state corresponding to the second maintenance and repair indicator as a preset second operating state;

[0014] When all indicator values ​​of the maintenance and repair indicators pre-acquired on each track unit are less than or equal to the preset railway line indicator threshold, the operating state corresponding to all maintenance and repair indicators on each track unit is determined as the second operating state.

[0015] According to an embodiment of the present invention, the step of calculating the index composite weight corresponding to each maintenance and repair index according to the detection index in the maintenance and repair index on each track unit includes:

[0016] Normalize the detection indicators in the maintenance and repair indicators on each track unit to obtain the indicator normalization matrix corresponding to each maintenance and repair indicator;

[0017] The data distribution weight corresponding to each detection indicator in the maintenance and repair indicators is calculated according to the indicator value in the indicator normalization matrix, wherein the data distribution weight calculation formula is:

[0018]

[0019] in, is the data distribution weight of the jth detection index, α i ' j is the normalized value of the jth detection index of the ith track unit in the index normalization matrix, α′ kj is the normalized value of the jth detection indicator of the kth track unit in the indicator normalization matrix, m is the number of detection indicators, and n is the number of track units;

[0020] Obtaining the indicator score value of each detection indicator in the maintenance and repair indicator by the line company;

[0021] The line regulation weight of each detection indicator in the maintenance and repair indicator is calculated according to the indicator score value, wherein the line regulation weight calculation formula is:

[0022]

[0023] in, is the line regulation weight of the jth detection index, b qj The score given to the jth inspection indicator with reference to the qth line company, p is the number of line companies, and n is the number of track units;

[0024] The composite weight of each detection indicator in the maintenance and repair indicator is calculated according to the data distribution weight and the line regulation weight, wherein the composite weight calculation formula is as follows:

[0025]

[0026] Among them, w j is the composite weight of the jth detection index, is the data distribution weight of the jth detection index, is the line regulation weight of the jth detection index, and n is the number of track units.

[0027] According to an embodiment of the present invention, the step of calculating the maintenance index of the maintenance index according to the detection index in the maintenance index and the composite weight of the index includes:

[0028] Extract each detection indicator corresponding to each maintenance and repair indicator;

[0029] The maintenance index of each maintenance and repair indicator is calculated according to the index value of each detection index and the index composite weight corresponding to each detection index. The calculation formula of the maintenance index of each maintenance and repair indicator is as follows:

[0030]

[0031] Among them, V f is the maintenance index of the fth maintenance index, Z fj is the index value of the jth detection index in the fth maintenance index, w fj is the composite weight of the jth detection indicator in the fth maintenance and repair indicator, and m is the number of detection indicators.

[0032] According to an embodiment of the present invention, the priority clustering of the track units according to the maintenance index to obtain the track unit clusters includes:

[0033] Calculate the similarity between the maintenance and repair indicators corresponding to each track unit;

[0034] Determine the cluster core point of each track unit according to the similarity, cluster each track unit according to the cluster core point, and return to the step of calculating the similarity between the maintenance and repair indicators corresponding to each track unit until a preset number of iterations is reached, and output an initial unit cluster;

[0035] The priority corresponding to the initial unit cluster is determined according to the maintenance index to obtain a track unit cluster.

[0036] According to an embodiment of the present invention, extracting the interval track unit corresponding to the track unit in the track unit cluster according to the spatial distribution includes:

[0037] Identifying track positions corresponding to all track units having the same priority in the spatial distribution;

[0038] Determine the unit position of the spacing unit corresponding to the track unit according to the track positions corresponding to all the track units;

[0039] The interval track unit corresponding to the track unit in the track unit cluster is extracted according to the unit position.

[0040] According to an embodiment of the present invention, merging the track units in the spatial distribution and the interval track units into a track segment according to a preset track unit interval threshold comprises:

[0041] Extracting the number of interval track units between any two track units with the same priority in the spatial distribution;

[0042] When the number of intervals is less than or equal to a preset track unit interval threshold, the any two track units and the interval track unit are merged into a track segment.

[0043] In a second aspect, an embodiment of the present invention provides a heavy-haul railway mechanized maintenance decision-making device, characterized in that it includes:

[0044] An operation status determination module, used to determine the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold;

[0045] An indicator composite weight calculation module, used to calculate the indicator composite weight corresponding to each maintenance and repair indicator according to the detection indicators in the maintenance and repair indicators on each track unit;

[0046] A maintenance index calculation module, used for calculating the maintenance index of the maintenance index according to the detection index in the maintenance index and the composite weight of the index when the operation state corresponding to the maintenance index is a preset target state;

[0047] A track unit clustering module, used for clustering the track units according to the maintenance index to obtain a track unit cluster, extracting the spatial distribution of all track units in the track unit cluster with the same priority, and extracting the interval track units corresponding to the track units in the track unit cluster according to the spatial distribution;

[0048] A track unit merging module is used to merge the track units in the spatial distribution and the interval track units into a track segment according to a preset track unit interval threshold, and perform maintenance operations on the track segment according to the priority corresponding to the track segment.

[0049] In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the multi-fuel cell system fan control method described in the above aspect.

[0050] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the heavy-haul railway mechanized maintenance decision-making method described in the above aspects.

[0051] Compared with the prior art, the above technical solution of the present invention has the following beneficial effects:

[0052] The embodiment of the present invention aims at a heavy-load railway line, establishes a heavy-load railway large-scale mechanized maintenance intelligent decision-making system, takes the heavy-load railway line section as the research object, conducts research on the maintenance and repair decisions of four large-scale machine operations of heavy-load railway line rail grinding, rail replacement, tamping and screening, constructs a heavy-load railway maintenance and repair index system, establishes a line maintenance and repair decision-making model, determines maintenance and repair decisions for different large-scale machine operations, judges whether the line section maintenance can be operated continuously, and decides the priority of large-scale machine operations in each line section, thereby improving decision-making efficiency and reducing maintenance and repair costs. Therefore, the heavy-load railway mechanized maintenance decision-making method, device, equipment and medium proposed by the present invention can solve the problem of low efficiency in making mechanized maintenance decisions for heavy-load railways. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A flowchart showing a heavy-haul railway mechanized maintenance decision-making method according to Embodiment 1 of the present invention is shown;

[0055] Figure 2 A schematic diagram showing the importance scores of various indicators in the first embodiment of the present invention;

[0056] Figure 3 A flowchart showing the maintenance and repair decision model algorithm of the first embodiment of the present invention is shown;

[0057] Figure 4 A functional module diagram of a heavy-haul railway mechanized maintenance decision-making device according to a third embodiment of the present invention is shown;

[0058] Figure 5 A schematic diagram of the composition structure of an electronic device for implementing the heavy-haul railway mechanized maintenance decision-making method according to the fourth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0059] The present disclosure is further described below in conjunction with the embodiments shown in the accompanying drawings.

[0060] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0061] This paper proposes a heavy-haul railway mechanized maintenance decision-making method based on safety detection technology. Based on clustering algorithm theory and combined with weight calculation method, a maintenance decision-making model is built to determine the types and priorities of large machine operations in each section of the line. Compared with traditional methods, heavy-haul railway mechanized maintenance decision-making technology is more efficient and reduces human subjectivity, and has great potential and application prospects in track safety detection and interpretation applications.

[0062] Embodiment 1

[0063] like Figure 1 As shown, the present invention proposes a heavy-haul railway mechanized maintenance decision-making method, comprising the following steps:

[0064] S1. Determine the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold.

[0065] In the embodiment of the present invention, the maintenance and repair indexes obtained in advance include four indexes: rail grinding index RGI, rail replacement index RRI, ballast cleaning index BCI and tamping index BTI. The rail grinding index is composed of five detection indicators, namely, rail profile (G), rail corrugation depth (RC), weld depression depth (RW), number of peeled blocks, abrasions, cracks, rust (ND) and preventive grinding cycle (M); the rail replacement index is composed of three detection indicators, namely, number of severely damaged rails (RF, including number of severely damaged rails, surface damage of rails and internal damage of rails). The track cleaning index is composed of six detection indicators, namely, track hardening degree (RH), track thickness (HB), track dirtiness (RS), track mudding length (LM), track freezing height (HF) and track overhaul cycle (M). The tamping index is composed of two detection indicators, namely, track geometry irregularity (T) and large-scale tamping maintenance cycle (t). Each detection indicator in each maintenance and repair indicator is the indicator value of each detection indicator data obtained in advance through simulation experiments.

[0066] Furthermore, based on the maintenance and repair indicators obtained in advance, it can be determined whether a certain track unit needs grinding, track replacement, screening and tamping. Therefore, it is necessary to analyze the large-scale machine operation status of the track unit to determine the large-scale machine operation required for a certain track unit.

[0067] In an embodiment of the present invention, the operation status refers to whether the maintenance and repair indicators corresponding to the track unit perform corresponding large-scale operations, wherein the first operation status is to perform corresponding large-scale operations, that is, state is Yes; the second operation status is not to perform corresponding large-scale operations, that is, state is No.

[0068] In an embodiment of the present invention, determining the operation state corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold includes:

[0069] When any indicator value of the maintenance and repair indicators pre-acquired on each track unit is greater than the preset railway line indicator threshold, extract the first maintenance and repair indicator corresponding to the indicator value greater than the preset railway line indicator threshold, and extract the second maintenance and repair indicator corresponding to the indicator value less than or equal to the preset railway line indicator threshold;

[0070] Determine the operating state corresponding to the first maintenance and repair indicator as a preset first operating state, and determine the operating state corresponding to the second maintenance and repair indicator as a preset second operating state;

[0071] When all indicator values ​​of the maintenance and repair indicators pre-acquired on each track unit are less than or equal to the preset railway line indicator threshold, the operating state corresponding to all maintenance and repair indicators on each track unit is determined as the second operating state.

[0072] In detail, the value of any indicator in a certain maintenance and repair index on each track unit is compared with the provisions of the railway line repair regulations. If the value of any indicator in a certain maintenance and repair index on each track unit exceeds the provisions of the railway line repair regulations, it indicates that the track unit needs to carry out corresponding large-scale machine operations. For example, if any one or more detection indicators of the rail profile (G), rail corrugation depth (RC), weld depression depth (RW), number of peeled blocks, abrasions, cracks, rust (ND) and preventive grinding cycle (M) in the rail grinding index RGI on a certain track unit exceed the provisions of the railway line repair regulations, it means that the track unit needs to carry out corresponding large-scale machine operations for rail grinding, that is, the rail grinding index RGI The operating state corresponding to the number is the first operating state, then the maintenance and repair index corresponding to the provisions of the railway line revision regulations on the track unit that exceeds the first maintenance and repair index, and the maintenance and repair index corresponding to the provisions of the railway line revision regulations that does not exceed the provisions of the railway line revision regulations is the second maintenance and repair index. For example, if the index value of any detection index among the rail grinding index RGI, the rail replacement index RRI and the ballast cleaning index BCI exceeds the provisions of the railway line revision regulations, the rail grinding index RGI, the rail replacement index RRI and the ballast cleaning index BCI are used as the first maintenance and repair index, and if the index value of any detection index of the tamping index BTI does not exceed the provisions of the railway line revision regulations, the tamping index BTI is used as the second maintenance and repair index.

[0073] Specifically, the operating state corresponding to the first maintenance and repair index is determined as the first operating state, and the operating state corresponding to the second maintenance and repair index is determined as the second operating state; and when the values ​​of various indicators in a certain maintenance and repair index in the track unit all comply with the provisions of the railway line repair regulations, it indicates that the track unit does not need to perform corresponding large-scale machine operations, such as the rail profile (G), rail corrugation depth (RC), weld depression depth (RW), number of peeled blocks, abrasions, cracks, rust (ND) and preventive grinding cycle (M) in the rail grinding index RGI all comply with the provisions of the railway line repair regulations, indicating that the track unit does not need to perform large-scale machine operations for grinding, and the operating state corresponding to the rail grinding index RGI is the second operating state, that is, state is No.

[0074] Further, is the operating state corresponding to each maintenance and repair indicator, the operating state corresponding to the rail grinding index RGI is state1, the operating state corresponding to the rail replacement index RRI is state2, the operating state corresponding to the ballast cleaning index BCI is state3 and the operating state corresponding to the tamping index BTI is state4, then state1 to state4 are all determined according to the provisions of the railway line repair regulations, then state1 to state4 can be the first operating state or the second operating state.

[0075] Furthermore, in order to take into account the data distribution characteristics of the index evaluation results of each unit and the requirements of the railway line repair rules, it is necessary to calculate the weight of each indicator in the four indexes to achieve weighted and normalized each detection indicator.

[0076] S2. Calculate the composite weight of each maintenance indicator according to the detection indicators in the maintenance indicators on each track unit.

[0077] In the embodiment of the present invention, the composite weight of the index refers to taking every 200m of the heavy-duty railway track as an evaluation unit, and calculating the weight based on the distribution characteristics of the unit index evaluation result data using the actual measurement data of each detection index, and calculating the partial weight based on the deviation of each detection index; The weight based on the railway line repair rules refers to the content of the maintenance regulations of different line companies, and scores the importance of each evaluation index respectively, so as to determine the partial weight of each detection index; Finally, the two parts of the weight are integrated to determine the composite weight of each detection index in the four maintenance and repair indexes.

[0078] In the embodiment of the present invention, the step of calculating the index composite weight corresponding to each maintenance index according to the detection index in the maintenance index on each track unit includes:

[0079] Normalize the detection indicators in the maintenance and repair indicators on each track unit to obtain the indicator normalization matrix corresponding to each maintenance and repair indicator;

[0080] The data distribution weight corresponding to each detection indicator in the maintenance and repair indicators is calculated according to the indicator value in the indicator normalization matrix, wherein the data distribution weight calculation formula is:

[0081]

[0082] in, is the data distribution weight of the jth detection index, α i ' j is the normalized value of the jth detection index of the ith track unit in the index normalization matrix, α′ kjis the normalized value of the jth detection indicator of the kth track unit in the indicator normalization matrix, m is the number of detection indicators, and n is the number of track units;

[0083] Obtaining the indicator score value of each detection indicator in the maintenance and repair indicator by the line company;

[0084] The line regulation weight of each detection indicator in the maintenance and repair indicator is calculated according to the indicator score value, wherein the line regulation weight calculation formula is:

[0085]

[0086] in, is the line regulation weight of the jth detection index, b qj The score given to the jth inspection indicator with reference to the qth line company, p is the number of line companies, and n is the number of track units;

[0087] The composite weight of each detection indicator in the maintenance and repair indicator is calculated according to the data distribution weight and the line regulation weight, wherein the composite weight calculation formula is as follows:

[0088]

[0089] Among them, w j is the composite weight of the jth detection index, is the data distribution weight of the jth detection index, is the line regulation weight of the jth detection index, and n is the number of track units.

[0090] In detail, every 200m track on the line is taken as an evaluation unit. Taking the calculation of the parameter weight of the rail grinding index expression as an example, assuming that the data of 5 detection indicators (G, RC, RW, ND, M) of several track evaluation units are known, the detection indicators in the rail grinding index are first normalized, including constructing a rail detection indicator evaluation matrix and normalizing each matrix value in the rail detection indicator evaluation matrix, so as to obtain the normalized matrix corresponding to the normalized rail grinding index, and calculate the data distribution weight corresponding to each detection indicator in the maintenance and repair indicator according to the indicator value in the indicator normalization matrix, that is, set is the weight of the jth detection index of the rail grinding index based on the distribution characteristics. The weight based on the data distribution characteristics is calculated based on the discrete degree of the measured values ​​of index j in all track units. In the first step, the standard value of the jth detection index of the first unit is set as the reference value, and the absolute value of the difference between the jth index value and the remaining track units is accumulated, that is, the deviation and D sumj , In the formula, α i' j is the normalized value of the jth detection index of the ith track unit, α′ kj is the normalized value of the jth detection index of the kth track unit (i or k = 1, 2, ..., n and i ≠ k; j = 1, 2, ..., m). Similarly, the first step is repeated to calculate the sum of the deviations of the detection indexes of all track units, and then the total deviation of the m indicators is calculated, that is, Finally, the weights of each detection index based on data distribution are calculated, that is,

[0091] Specifically, the weight of railway regulation depends on the maintenance regulations of different line companies. The relevant regulations of line companies are different. Therefore, it is necessary to fully consider not only the regulations of each inspection indicator in different companies, but also the track inspection frequency and maintenance difficulty corresponding to the indicator. Refer to the relevant maintenance regulations of p line companies, and score the importance of each indicator independently. The score range is 0 to 5, representing unimportant, slightly important, relatively important, important, very important and extremely important. Figure 3 As shown in the figure, it is a schematic diagram of the importance of each indicator, which represents the score of each company for each indicator, that is, b qj The weight of the jth inspection indicator based on the railway regulation is calculated based on the score specified by the qth line company, which refers to the score given to the jth inspection indicator by the qth line company. As shown below Integrate the scoring results of all line companies and calculate the weight of the jth detection indicator based on railway regulation revision

[0092] Furthermore, by integrating the weights based on data distribution characteristics and the weights based on railway line regulation, the composite weights of each detection index are calculated as follows: Thus, the composite weight of the index corresponding to each maintenance and repair index can be calculated by obtaining the inspection index in the maintenance and repair index, such as the composite weights corresponding to the rail profile (G), rail corrugation depth (RC), weld depression depth (RW), number of peeled blocks, abrasions, cracks, rust (ND) and preventive grinding cycle (M) in the rail grinding index. Similarly, each inspection index in the rail replacement index RRI, the ballast cleaning index BCI and the tamping index BTI corresponds to a composite weight.

[0093] Furthermore, based on the composite weight corresponding to the detection indicators in each index and the operating status corresponding to each index, the grinding index, track changing index, screening index and tamping index of each unit that needs to perform grinding, track changing, screening and tamping operations can be calculated. The larger the index, the more urgent the demand for this large-scale machine operation.

[0094] S3. When the operation state corresponding to the maintenance and repair indicator is a preset target state, the maintenance index of the maintenance and repair indicator is calculated according to the detection indicator in the maintenance and repair indicator and the composite weight of the indicator.

[0095] In the embodiment of the present invention, the target state is the first operating state. Only when the operating state corresponding to the maintenance and repair index is the first operating state, the corresponding maintenance index will be calculated. The larger the index is, the more urgent the demand for the large machine operation is.

[0096] In the embodiment of the present invention, the calculation of the maintenance index of the maintenance index according to the detection index in the maintenance index and the composite weight of the index includes:

[0097] Extract each detection indicator corresponding to each maintenance and repair indicator;

[0098] The maintenance index of each maintenance and repair indicator is calculated according to the index value of each detection index and the index composite weight corresponding to each detection index. The calculation formula of the maintenance index of each maintenance and repair indicator is as follows:

[0099]

[0100] Among them, V f is the maintenance index of the fth maintenance index, Z fj is the index value of the jth detection index in the fth maintenance index, w fj is the composite weight of the jth detection indicator in the fth maintenance and repair indicator, and m is the number of detection indicators.

[0101] In detail, the maintenance index of each maintenance index is obtained by weighting the index value of the detection index and the detection composite weight corresponding to the detection index. The maintenance indexes of the four indexes of rail grinding index RGI, rail replacement index RRI, ballast cleaning index BCI and tamping index BTI are calculated respectively. The maintenance index of rail grinding index RGI is RGI = A1(100-G) + A2R C +A3R W +A4N D +A5M, the maintenance index of the rail replacement index RRI is RRI = B1R F +B2W C +B3M, the maintenance index of the bed cleaning index BCI is BCI=C1R H +C2H B +C3R S +C4L M +C5H F+C6M, the maintenance index of the tamping index BTI is BTI=D1T+D2t, among which A1 to A5, B1 to B3, C1 to C6, D1 and D2 are the composite weights of the jth detection index in the fth maintenance and repair index, then A1 to A5 are the composite weights corresponding to each detection index in the rail grinding index RGI, B1 to B3 are the composite weights corresponding to each detection index in the rail replacement index RRI, C1 to C6 are the composite weights corresponding to each detection index in the ballast cleaning index BCI, D1 and D2 are the composite weights corresponding to each detection index in the tamping index BTI, so that each detection index is weightedly calculated to obtain the maintenance index of each maintenance and repair index.

[0102] Furthermore, the calculation results of the above four maintenance indexes can provide a scientific basis for the maintenance of heavy-haul railway lines, so as to formulate a reasonable production schedule. It is necessary to comprehensively consider the track unit status level and the spatial distribution of track defects, establish an intelligent decision-making model for heavy-haul railway line maintenance based on the k-means clustering algorithm, and determine the maintenance strategy of the line section, so as to improve the line maintenance efficiency, reduce the economic cost of maintenance, and ensure the good operation status of the line.

[0103] S4. Priority clustering is performed on the track units according to the maintenance index to obtain a track unit cluster, and the spatial distribution of all track units in the track unit cluster with the same priority is extracted, and the interval track units corresponding to the track units in the track unit cluster are extracted according to the spatial distribution.

[0104] In an embodiment of the present invention, the track unit cluster refers to a grouping of track units with the same priority, and the priority of the track unit is determined by the maintenance index. The larger the maintenance index corresponding to the track unit, the higher the priority of the track unit. The priority of the track unit cluster is divided into high priority, medium priority and low priority.

[0105] In the embodiment of the present invention, the priority clustering of the track units according to the maintenance index to obtain the track unit clusters includes:

[0106] Calculate the similarity between the maintenance and repair indicators corresponding to each track unit;

[0107] Determine the cluster core point of each track unit according to the similarity, cluster each track unit according to the cluster core point, and return to the step of calculating the similarity between the maintenance and repair indicators corresponding to each track unit until a preset number of iterations is reached, and output an initial unit cluster;

[0108] The priority corresponding to the initial unit cluster is determined according to the maintenance index to obtain a track unit cluster.

[0109] In detail, the rail grinding index, rail replacement index, ballast cleaning index and tamping index of each unit in the section are respectively input into the system for cluster analysis, so as to decide the operation priority of each track unit. The input of the maintenance intelligent decision model based on the k-means clustering algorithm is a certain evaluation index of the track unit, which is used to judge the similarity between units. The corresponding output is the decision result, that is, the priority level of each cluster that needs maintenance is determined, which is divided into high priority, medium priority and low priority. The mean of the maintenance index of the corresponding four indicators in the initial unit cluster is used to determine the priority. If the first initial unit cluster is the track unit corresponding to the rail grinding index, the mean of the rail grinding index of all track units is calculated. If the mean is large, the priority of the unit cluster corresponding to the rail grinding index is determined as high priority. In the k-means clustering algorithm, the core point is not directly found, but the center point (i.e., the centroid) of the cluster is found through an iterative process, and the data points are assigned to these clusters. First, k initial cluster center points are selected. Usually, k points in the data set can be randomly selected as the initial cluster center points, and each data point is assigned to the cluster where the cluster center point closest to it is located. For each cluster, the average value of all points (i.e., the new cluster center) is calculated as the center point of the cluster, and the cluster point search is repeated until the cluster center point no longer changes or the predetermined number of iterations is reached. Finally, k clusters are obtained, each cluster contains a group of data points, which are considered to be more similar to each other than the data points in other clusters.

[0110] Specifically, Figure 4 As shown in the figure, it is a flow chart of the maintenance decision model algorithm. First, the input of the maintenance intelligent decision model based on the k-means clustering algorithm is a certain evaluation index of the rail grinding index, rail replacement index, ballast cleaning index and tamping index of each unit in the section, and the similarity of each track unit of the input evaluation index is calculated. Then, based on the k-means clustering algorithm, the core points are found and clustered, and the similarity is continuously updated to find the core points until the iteration limit is reached, and the decision result is output.

[0111] Furthermore, railway maintenance and repair work is generally carried out in sections, and the degradation patterns and degrees of each track unit are different. It is difficult to make scientific and efficient decisions based on the status of a track unit. Therefore, the present invention expands the research scope of maintenance and repair from a single track unit to the track line section.

[0112] In an embodiment of the present invention, the spaced track unit refers to whether there is a spaced track unit between every two track units in a track unit cluster with the same priority, that is, to determine whether the two track units can operate continuously. If not, there is a spaced track unit between the two track units.

[0113] In an embodiment of the present invention, extracting the interval track unit corresponding to the track unit in the track unit cluster according to the spatial distribution includes:

[0114] Identifying track positions corresponding to all track units having the same priority in the spatial distribution;

[0115] Determine the unit position of the spacing unit corresponding to the track unit according to the track positions corresponding to all the track units;

[0116] The interval track unit corresponding to the track unit in the track unit cluster is extracted according to the unit position.

[0117] In detail, all track units in a track unit cluster with the same priority in space are identified, and the track positions of all track units in the track unit cluster with the same priority are determined, and whether there is a gap between the track units is judged based on the track positions. When there is a gap, it is necessary to determine the unit position corresponding to the gap unit, and then extract the gap unit between the tracks based on the unit position. For example, if the track positions corresponding to the track units with the same priority are 1, 2, 5, 7, and 9, there is a gap between track 2 and track 5, and the gap track units are track 3 and track 4.

[0118] Furthermore, an intelligent decision-making model for heavy-duty railway line maintenance was established based on the k-means clustering algorithm. In order to determine the priority of large-scale machine operations in each section to be maintained and whether they can operate continuously, it is necessary to expand the research scope of maintenance from a single track unit to the track line section, so as to take into account the spatial distribution characteristics of the disease.

[0119] S5. According to a preset track unit interval threshold, the track units in the spatial distribution and the interval track units are merged into a track segment, and maintenance operations are performed on the track segment according to the priority corresponding to the track segment.

[0120] In the embodiment of the present invention, the track section refers to merging track units that can perform continuous operations into one track line section, thereby improving the operating efficiency of the large machine and reducing the operating cost of the large machine.

[0121] In an embodiment of the present invention, the step of merging the track units in the spatial distribution and the interval track units into a track segment according to a preset track unit interval threshold comprises:

[0122] Extracting the number of interval track units between any two track units with the same priority in the spatial distribution;

[0123] When the number of intervals is less than or equal to a preset track unit interval threshold, the any two track units and the interval track unit are merged into a track segment.

[0124] In detail, determine whether each unit can operate continuously, considering the spatial distribution of all track units of a certain priority level. If the interval between two track units of the same priority level is less than or equal to 5 track units, then these 7 track units are merged into one track section, and it is deemed that all of them need to perform large-scale machine operations of this priority level. Similarly, determine the priority level of large-scale machine operations in different sections of the entire line, where the track unit interval threshold is an interval less than or equal to 5 track units.

[0125] Furthermore, the priority of the merged track sections is determined by the maintenance index, and maintenance work is performed on the high-priority track sections first, then on the medium-priority track sections, and finally on the low-priority track sections.

[0126] Embodiment 2

[0127] In order to better understand the present invention, a second embodiment is used below to further explain the standardization of detection indicators in the embodiment of the present invention.

[0128] In the embodiment of the present invention, the indicator normalization matrix refers to a matrix corresponding to the detection indicator obtained by normalizing the initial indicator constructed by each detection indicator.

[0129] In the embodiment of the present invention, the normalization processing of the detection indicators in the maintenance and repair indicators on each track unit to obtain the indicator normalization matrix corresponding to each maintenance and repair indicator includes:

[0130] Construct an initial indicator matrix according to each detection indicator in the maintenance and repair indicators on each track unit;

[0131] Normalizing each indicator value in the initial indicator matrix to obtain a normalized indicator value;

[0132] The initial indicator matrix is ​​normalized according to the normalized indicator value to obtain an indicator normalization matrix corresponding to each maintenance and repair indicator.

[0133] In detail, assuming that the data of five detection indicators (G, RC, RW, ND, M) of several track evaluation units are known, the rail detection indicator evaluation matrix is ​​constructed, that is, the initial indicator matrix is Where m and n are the number of detection indicators and the number of track units, respectively. To facilitate subsequent calculations, the above matrix is ​​transformed into After normalization processing, the normalized index value corresponding to each matrix value is obtained, and then the normalization calculation is performed through the benefit index and the cost index. If it is a benefit index, the larger the better, the calculation is performed as follows: If it is a cost-based indicator, the smaller the better, the calculation is as follows: Among them, max and min are the minimum and maximum values ​​of the detection index in all track units, respectively, so as to obtain the index normalization matrix corresponding to the rail detection index. Similarly, the index normalization matrix corresponding to the detection index of rail replacement index, ballast cleaning index and tamping index is obtained respectively.

[0134] The embodiment of the present invention aims at a heavy-load railway line, establishes a heavy-load railway large-scale mechanized maintenance intelligent decision-making system, takes the heavy-load railway line section as the research object, conducts research on the maintenance and repair decisions of four large-scale machine operations of heavy-load railway line rail grinding, rail replacement, tamping and screening, constructs a heavy-load railway maintenance and repair index system, establishes a line maintenance and repair decision-making model, determines maintenance and repair decisions for different large-scale machine operations, judges whether the line section maintenance can be operated continuously, and decides the priority of large-scale machine operations in each line section, thereby improving decision-making efficiency and reducing maintenance and repair costs. Therefore, the heavy-load railway mechanized maintenance decision-making method, device, equipment and medium proposed by the present invention can solve the problem of low efficiency in making mechanized maintenance decisions for heavy-load railways.

[0135] Embodiment 3

[0136] like Figure 4 As shown, this embodiment also provides a functional module diagram of a heavy-haul railway mechanized maintenance decision-making device.

[0137] The heavy-haul railway mechanized maintenance decision-making device 100 described in this embodiment can be installed in an electronic device. According to the functions to be implemented, the heavy-haul railway mechanized maintenance decision-making device 100 may include an operation status determination module 101, an index composite weight calculation module 102, a maintenance index calculation module 103, a track unit clustering module 104 and a track unit merging module 105. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0138] In this embodiment, the functions of each module / unit are as follows:

[0139] The operation status determination module 101 is used to determine the operation status corresponding to the maintenance and repair index on each track unit according to the index value of the maintenance and repair index pre-acquired on each track unit and the preset railway line index threshold;

[0140] The index composite weight calculation module 102 is used to calculate the index composite weight corresponding to each maintenance and repair index according to the detection index in the maintenance and repair index on each track unit;

[0141] The maintenance index calculation module 103 is used to calculate the maintenance index of the maintenance index according to the detection index in the maintenance index and the composite weight of the index when the operation state corresponding to the maintenance index is a preset target state;

[0142] The track unit clustering module 104 is used to perform priority clustering on the track units according to the maintenance index to obtain a track unit cluster, extract the spatial distribution of all track units in the track unit cluster with the same priority, and extract the interval track units corresponding to the track units in the track unit cluster according to the spatial distribution;

[0143] The track unit merging module 105 is used to merge the track units in the spatial distribution and the interval track units into a track segment according to a preset track unit interval threshold, and perform maintenance operations on the track segment according to the priority corresponding to the track segment.

[0144] In detail, each module described in the heavy-haul railway mechanized maintenance decision-making device 100 described in the embodiment of the present invention adopts the same technical means as the heavy-haul railway mechanized maintenance decision-making method described in Example 1 and Example 2 when used, and can produce the same technical effects, which will not be repeated here.

[0145] Embodiment 4

[0146] like Figure 5 As shown, this embodiment also provides a computer electronic device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a heavy-duty railway mechanized maintenance decision program.

[0147] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing a heavy-load railway mechanized maintenance decision program, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0148] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device, such as the code of the heavy-duty railway mechanized maintenance decision program, but also be used to temporarily store data that has been output or is to be output.

[0149] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0150] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0151] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0152] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0153] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0154] The heavy-haul railway mechanized maintenance decision program stored in the memory 11 in the electronic device is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0155] Determine the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold;

[0156] Calculating the index composite weight corresponding to each maintenance and repair index according to the detection index in the maintenance and repair index on each track unit;

[0157] When the operation state corresponding to the maintenance and repair indicator is the preset target state, the maintenance index of the maintenance and repair indicator is calculated according to the detection indicator in the maintenance and repair indicator and the composite weight of the indicator;

[0158] Priority clustering is performed on the track units according to the maintenance index to obtain a track unit cluster, and the spatial distribution of all track units in the track unit cluster with the same priority is extracted, and the interval track units corresponding to the track units in the track unit cluster are extracted according to the spatial distribution;

[0159] The track units in the spatial distribution and the interval track units are merged into a track segment according to a preset track unit interval threshold, and maintenance operations are performed on the track segment according to the priority corresponding to the track segment.

[0160] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0161] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0162] Embodiment 5

[0163] This embodiment provides a storage medium storing a computer program. When the computer program is executed by a processor, the steps of the heavy-haul railway mechanized maintenance decision-making method described above are implemented.

[0164] These program codes can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 The steps of a specified function in a process or multiple processes.

[0165] Storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of storage media can include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0166] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0167] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0169] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0170] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is not limited only according to the above description, and it is intended that all changes within the meaning and scope of equivalent elements within the scope of protection are included in the present invention.

[0171] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0172] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A heavy-haul railway mechanized maintenance decision-making method, characterized in that: The method comprises: Determine the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold; Calculating the index composite weight corresponding to each maintenance and repair index according to the detection index in the maintenance and repair index on each track unit; When the operation state corresponding to the maintenance and repair indicator is the preset target state, the maintenance index of the maintenance and repair indicator is calculated according to the detection indicator in the maintenance and repair indicator and the composite weight of the indicator; Priority clustering is performed on the track units according to the maintenance index to obtain a track unit cluster, and the spatial distribution of all track units in the track unit cluster with the same priority is extracted, and the interval track units corresponding to the track units in the track unit cluster are extracted according to the spatial distribution; The track units in the spatial distribution and the interval track units are merged into a track segment according to a preset track unit interval threshold, and maintenance operations are performed on the track segment according to the priority corresponding to the track segment.

2. The heavy-haul railway mechanized maintenance decision-making method according to claim 1, characterized in that: The step of determining the operation state corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold comprises: When any indicator value of the maintenance and repair indicators pre-acquired on each track unit is greater than the preset railway line indicator threshold, extract the first maintenance and repair indicator corresponding to the indicator value greater than the preset railway line indicator threshold, and extract the second maintenance and repair indicator corresponding to the indicator value less than or equal to the preset railway line indicator threshold; Determine the operating state corresponding to the first maintenance and repair indicator as a preset first operating state, and determine the operating state corresponding to the second maintenance and repair indicator as a preset second operating state; When all indicator values ​​of the maintenance and repair indicators pre-acquired on each track unit are less than or equal to the preset railway line indicator threshold, the operating state corresponding to all maintenance and repair indicators on each track unit is determined as the second operating state.

3. The heavy-haul railway mechanized maintenance decision-making method according to claim 1, characterized in that: The calculating the index composite weight corresponding to each maintenance and repair index according to the detection index in the maintenance and repair index on each track unit includes: Normalize the detection indicators in the maintenance and repair indicators on each track unit to obtain the indicator normalization matrix corresponding to each maintenance and repair indicator; The data distribution weight corresponding to each detection indicator in the maintenance and repair indicators is calculated according to the indicator value in the indicator normalization matrix, wherein the data distribution weight calculation formula is: in, is the data distribution weight of the jth detection index, α i ′ j is the normalized value of the jth detection index of the ith track unit in the index normalization matrix, α ′ kj is the normalized value of the jth detection indicator of the kth track unit in the indicator normalization matrix, m is the number of detection indicators, and n is the number of track units; Obtaining the indicator score value of each detection indicator in the maintenance and repair indicator by the line company; The line regulation weight of each detection indicator in the maintenance and repair indicator is calculated according to the indicator score value, wherein the line regulation weight calculation formula is: in, is the line regulation weight of the jth detection index, b qj The score given to the jth inspection indicator with reference to the qth line company, p is the number of line companies, and n is the number of track units; The composite weight of each detection indicator in the maintenance and repair indicator is calculated according to the data distribution weight and the line regulation weight, wherein the composite weight calculation formula is as follows: Among them, w j is the composite weight of the jth detection index, is the data distribution weight of the jth detection index, is the line regulation weight of the jth detection index, and n is the number of track units.

4. The heavy-haul railway mechanized maintenance decision-making method according to claim 1, characterized in that: The calculation of the maintenance index of the maintenance index according to the detection index in the maintenance index and the composite weight of the index includes: Extract each detection indicator corresponding to each maintenance and repair indicator; The maintenance index of each maintenance and repair indicator is calculated according to the index value of each detection index and the index composite weight corresponding to each detection index. The calculation formula of the maintenance index of each maintenance and repair indicator is as follows: Among them, V f is the maintenance index of the fth maintenance index, Z fj is the index value of the jth detection index in the fth maintenance index, w fj is the composite weight of the jth detection indicator in the fth maintenance and repair indicator, and m is the number of detection indicators.

5. The heavy-haul railway mechanized maintenance decision-making method according to claim 1, characterized in that: The step of clustering the track units according to the maintenance index to obtain a track unit cluster includes: Calculate the similarity between the maintenance and repair indicators corresponding to each track unit; Determine the cluster core point of each track unit according to the similarity, cluster each track unit according to the cluster core point, and return to the step of calculating the similarity between the maintenance and repair indicators corresponding to each track unit until a preset number of iterations is reached, and output an initial unit cluster; The priority corresponding to the initial unit cluster is determined according to the maintenance index to obtain a track unit cluster.

6. The heavy-haul railway mechanized maintenance decision-making method according to claim 1, characterized in that: The step of extracting the interval track units corresponding to the track units in the track unit cluster according to the spatial distribution includes: Identifying track positions corresponding to all track units having the same priority in the spatial distribution; Determine the unit position of the spacing unit corresponding to the track unit according to the track positions corresponding to all the track units; The interval track unit corresponding to the track unit in the track unit cluster is extracted according to the unit position.

7. The heavy-haul railway mechanized maintenance decision-making method according to claim 1, characterized in that: The step of merging the track units in the spatial distribution and the interval track units into a track segment according to a preset track unit interval threshold comprises: Extracting the number of interval track units between any two track units with the same priority in the spatial distribution; When the number of intervals is less than or equal to a preset track unit interval threshold, the any two track units and the interval track unit are merged into a track segment.

8. A heavy-haul railway mechanized maintenance decision-making device, characterized in that: The device comprises: An operation status determination module is used to determine the operation status corresponding to the maintenance and repair indicator on each track unit according to the indicator value of the maintenance and repair indicator pre-acquired on each track unit and the preset railway line indicator threshold; An indicator composite weight calculation module, used to calculate the indicator composite weight corresponding to each maintenance and repair indicator according to the detection indicators in the maintenance and repair indicators on each track unit; A maintenance index calculation module, used for calculating the maintenance index of the maintenance index according to the detection index in the maintenance index and the composite weight of the index when the operation state corresponding to the maintenance index is a preset target state; A track unit clustering module, used for clustering the track units according to the maintenance index to obtain a track unit cluster, extracting the spatial distribution of all track units in the track unit cluster with the same priority, and extracting the interval track units corresponding to the track units in the track unit cluster according to the spatial distribution; A track unit merging module is used to merge the track units in the spatial distribution and the interval track units into a track segment according to a preset track unit interval threshold, and perform maintenance operations on the track segment according to the priority corresponding to the track segment.

9. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the heavy-haul railway mechanized maintenance decision-making method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the heavy-haul railway mechanized maintenance decision-making method described in any one of claims 1 to 7 are implemented.

Images