Method and system for identifying track risks based on big data analysis

A method for identifying track risks based on big data analysis, comprising:

• determining the track to be inspected and its track image data, and obtaining the location information of each station on the track to be inspected;
• based on the location information of each station, segmenting the track to be inspected and obtaining the segmented track;
• inputting the track image data corresponding to the segmented tracks into a track detection model, and output the detection results corresponding to the segmented tracks;
• wherein the track detection model includes a YOLO model and an SVM classifier connected in series;
• based on the detection results, obtaining environmental data of the segmented track, inputting it into a track damage prediction model, and outputting the corresponding damage prediction results;
• wherein the track damage prediction model includes an RF model;
• based on the detection results, obtaining the path signal corresponding to the segmented track, inputting it into the track fault diagnosis model, and outputting the corresponding fault diagnosis result;
• wherein the track fault diagnosis model includes a BP neural network model;
• based on the detection results, the damage prediction results, and the fault diagnosis results, planning the path of the track to be inspected and obtaining the corresponding inspection path;
• based on the inspection path, dispatching investigation personnel to investigate the track to be inspected;
• wherein the training process of the track detection model includes:
• step S11, obtaining training orbit image data and its first label;
• wherein the first label includes damage, deformation, and normal;
• step S12, selecting the training track image data corresponding to any segmented track and inputting it into the YOLO model along with the corresponding first label to obtain the initial training detection result;
• step S13, inputting the initial training detection results into the SVM classifier to obtain the training detection results;
• wherein the training detection results are divided into to be inspected and normal;
• the pending investigation includes training deformation detection results and training damage detection results;
• the normal result refers to the normal training and detection results;
• step S14, based on the training detection results, calculating the corresponding loss function;
• step S15, repeating the steps S12 to S14 until the loss function corresponding to all segmented tracks is obtained;
• step S16, calculating the final loss function based on all the aforementioned loss functions;
• based on the final loss function, adjusting the weight parameters of the track detection model to complete the training of the track detection model;
• wherein the training process of the track damage prediction model includes:
• step S21, obtaining the historical environmental parameters and their second labels corresponding to the training deformation detection results;
• wherein the historical environmental parameters include historical temperature data and historical humidity data;
• and the second label is damage and normal;
• step S22, inputting the training deformation detection results, historical environmental parameters, and their second labels into the RF model, and outputting the corresponding damage prediction results;
• step S23, calculate the mean square error loss function based on the damage prediction results;
• step S24, based on the mean square error loss function, adjusting the parameters of the track damage prediction model to complete the training of the track damage prediction model;
• wherein the training process of the track fault diagnosis model includes:
• step S31, obtaining training path signal data and its third label;
• wherein the training path signal data is divided into training path signals corresponding to the training deformation detection results, training path signals corresponding to the training damage detection results, and training path signals corresponding to the training normal detection results;
• the third tag includes line faults and line non faults corresponding to the track, namely signal fault points and signal non fault points;
• step S32, inputting the training path signal data and its third label into the BP neural network model, and outputting the corresponding training fault diagnosis result;
• step S33, based on the training fault diagnosis results, calculating the corresponding cross entropy loss function;
• step S34, based on the cross entropy loss function, adjusting the weight parameters of the BP neural network model using back propagation algorithm and gradient descent algorithm to complete the training of the track fault diagnosis model;
• wherein the training fault diagnosis results include training signal fault points and training signal non fault points;
• based on the detection results, risk probability data, and diagnosis results, performing path planning on the track to be inspected to obtain the corresponding inspection path, which includes:
• setting a damage threshold and divide the damage prediction results into high-risk damage prediction results and low-risk damage prediction results based on the damage threshold;
• taking the track corresponding to the detection result of ‘to be inspected’, the damage prediction result of ‘high-risk damage prediction result’, and the diagnosis result of ‘signal fault point’ as the first priority node;
• wherein the second priority node is the track corresponding to the detection result being to be inspected, the damage prediction result being a high-risk damage prediction result, and the diagnosis result being a non signal fault point, as well as the detection result being to be inspected, the damage prediction result being a low-risk damage prediction result, and the diagnosis result being a signal fault point;
• taking the track corresponding to the detection result of ‘to be inspected’, the damage prediction result of ‘low-risk damage prediction result’, and the diagnosis result of ‘non signal fault point’ as the third priority node;
• obtaining the location information of the first to third priority nodes;
• calculating the distance between the first priority node and the site;
• and based on the distance, determining the station with the shortest distance between each first priority node, and obtaining the location relationship map between the first priority node and the station;
• and
• based on the location relationship graph, the second priority node, the third priority node, and the location information of each station, using the greedy ant colony algorithm to plan the path of the track to be inspected and obtain the inspection path.