A monitoring system, monitoring method, device and medium for rail transit vehicles

Abstract

The present application provides a monitoring system, monitoring method, equipment and medium for rail transit vehicles. The vehicle operation status monitoring module displays the vehicle status information corresponding to the rail vehicle in the display interface; the vehicle maintenance status monitoring module evaluates the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle, and obtains the current maintenance status corresponding to each rail vehicle; the vehicle fault monitoring module classifies and counts the historical fault status information, and obtains multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category; the user login module provides the user with a login function of the login system that complies with the user's authority information according to the user's authority information. Through the system and method, high-efficiency and high-precision monitoring of rail transit vehicles is achieved.

Description

Technical Field

[0001] The present application relates to the field of rail transit technology, and in particular to a monitoring system, monitoring method, equipment and medium for rail transit vehicles. Background Art

[0002] With the rapid development of urban rail transit networks, the scale of rail transit vehicles continues to expand, and the traditional method of manual monitoring of rail vehicles is becoming increasingly difficult to adapt to the monitoring needs of large-scale intelligent vehicles.

[0003] The existing vehicle monitoring system has the following problems: it is difficult to achieve overall monitoring of vehicle operation and maintenance, and it is even more impossible to evaluate and analyze the vehicle maintenance progress and quality, technical capabilities, maintenance capabilities and maintenance quality; there is a lack of a fault monitoring module, and it is impossible to classify and count fault points and display them visually; there is a lack of a vehicle monitoring module, and it is impossible to comprehensively monitor the status of trains in mainline operation, making it difficult to achieve functions such as train positioning and train statistics. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a monitoring system, monitoring method, equipment and medium for rail transit vehicles. By evaluating and analyzing the progress and quality of vehicle maintenance through the vehicle maintenance status monitoring module, the overall situation of vehicle maintenance can be better controlled, maintenance efficiency can be improved, and maintenance costs can be reduced. Through the classification statistics and visual display functions of the vehicle fault monitoring module, vehicle abnormal status information can be grasped in a timely manner to better manage and maintain the vehicle. Through the train statistics function of the vehicle operation status monitoring module, the train status can be fully monitored, and key performance indicator information such as train basic information and train number information can be obtained.

[0005] In a first aspect, an embodiment of the present application provides a monitoring system for a rail transit vehicle, the monitoring system comprising a vehicle operation status monitoring module, a vehicle maintenance status monitoring module, a vehicle fault monitoring module and a user login module;

[0006] The vehicle operation status monitoring module is used to obtain the vehicle status information corresponding to the rail vehicle and display the vehicle status information corresponding to the rail vehicle in the display interface; wherein the vehicle status information includes the basic information of the rail vehicle, the train number information of the rail vehicle, the operation status information of the rail vehicle, the key performance indicators of the rail vehicle and the positioning information of the rail vehicle;

[0007] The vehicle maintenance status monitoring module is used to obtain the maintenance business data of the rail vehicle, and evaluate the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle;

[0008] The vehicle fault monitoring module is used to obtain historical fault status information of multiple faulty vehicles, classify and count the historical fault status information, obtain multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generate a vehicle fault statistics table based on the number of faults corresponding to each fault category;

[0009] The user login module is used to provide the user with a login function of a login system that complies with the user's authority information according to the user's authority information, so that the user logs in to the login system to view the vehicle monitoring information recorded in the login system.

[0010] Furthermore, the vehicle operation status monitoring module is also used for:

[0011] Acquiring real-time operation data of the rail vehicle;

[0012] Acquire multiple sensor data of rail vehicles, and build an abnormal state recognition model based on time domain characteristics and frequency domain characteristics of the multiple sensor data;

[0013] The characteristic sequence of the real-time operation data is input into the abnormal state recognition model to determine the abnormal state information of the rail vehicle.

[0014] Furthermore, when the vehicle fault monitoring module is used to classify and count the historical fault status information to obtain multiple fault categories corresponding to the historical fault status information, the vehicle fault monitoring module is also used to:

[0015] A CNN network is used to extract time domain features of the historical fault status information to identify multiple fault categories corresponding to the historical fault status information.

[0016] Furthermore, the rail transit vehicle monitoring system also includes an image recognition module and an intelligent voice question and answer module;

[0017] The image recognition module is used to obtain the vehicle equipment image taken by the user, and recognize the vehicle equipment image to determine the target vehicle-mounted equipment captured in the vehicle equipment image and the target rail vehicle to which the target vehicle-mounted equipment belongs;

[0018] The intelligent voice interactive question and answer module is used to obtain the user's question voice about the rail vehicle, convert the question voice into corresponding text information, and determine the answer information corresponding to the question voice based on the text information.

[0019] Furthermore, the rail transit vehicle monitoring system further includes an equipment state prediction module, wherein the equipment state prediction module is used to:

[0020] For each on-board device on the rail vehicle, obtaining historical status data of the on-board device;

[0021] Based on the historical status data, the LSTM neural network is used to perform time series data modeling to obtain a device status prediction model;

[0022] The current state data of the vehicle-mounted device is input into the device state prediction model to obtain the predicted state data of the vehicle-mounted device at the next time point.

[0023] Furthermore, the rail transit vehicle monitoring system further includes a maintenance plan determination module, wherein the maintenance plan determination module is used to:

[0024] Collect multi-source data, build a device association network map, and determine the correlation between each device time through node association analysis;

[0025] Obtain historical equipment failure information, use the Apriori algorithm to mine frequent equipment combinations, and determine the failure association rules;

[0026] The current faulty device is determined, and the associated devices associated with the current faulty device are determined based on the fault association rule, and the current faulty device is associated with the associated devices to generate a maintenance plan corresponding to the current faulty device.

[0027] Furthermore, the rail transit vehicle monitoring system further includes a data encryption module, and the data encryption module is used to:

[0028] The vehicle status information, the maintenance business data and the historical fault status information are encrypted using an encrypted HASH algorithm, and the encrypted vehicle status information, the encrypted maintenance business data and the encrypted historical fault status information are transmitted to a backend server for storage via blockchain.

[0029] In a second aspect, an embodiment of the present application further provides a monitoring method for a rail transit vehicle, the monitoring method being applied to a monitoring system for a rail transit vehicle, the monitoring system comprising a vehicle operation status monitoring module, a vehicle maintenance status monitoring module, a vehicle fault monitoring module and a user login module, the monitoring method comprising:

[0030] Control the vehicle operation status monitoring module to obtain vehicle status information corresponding to the rail vehicle, and display the vehicle status information corresponding to the rail vehicle in the display interface; wherein the vehicle status information includes rail vehicle basic information, rail vehicle train number information, rail vehicle operation status information, rail vehicle key performance indicators and rail vehicle positioning information;

[0031] Controlling the vehicle maintenance status monitoring module to obtain the maintenance business data of the rail vehicle, and evaluating the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle;

[0032] Controlling the vehicle fault monitoring module to obtain historical fault status information of multiple faulty vehicles, classifying and counting the historical fault status information, obtaining multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generating a vehicle fault statistics table based on the number of faults corresponding to each fault category;

[0033] The user login module is controlled to provide the user with a login function of a login system that complies with the user's authority information according to the user's authority information, so that the user logs in to the login system to view the vehicle monitoring information recorded in the login system.

[0034] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the rail transit vehicle monitoring method as described above are performed.

[0035] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for monitoring a rail transit vehicle are executed.

[0036] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A schematic diagram of the structure of a monitoring system for a rail transit vehicle provided in an embodiment of the present application;

[0039] Figure 2 A flow chart of a method for monitoring a rail transit vehicle provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0042] First, the application scenarios to which the present application is applicable are introduced. The present application can be applied in the field of rail transportation technology.

[0043] With the rapid development of urban rail transit networks, the scale of rail transit vehicles continues to expand, and the traditional method of manual monitoring of rail vehicles is becoming increasingly difficult to adapt to the monitoring needs of large-scale intelligent vehicles.

[0044] Research has found that the existing vehicle monitoring system has the following problems: it is difficult to achieve overall monitoring of vehicle operation and maintenance, and it is even more impossible to evaluate and analyze the vehicle maintenance progress and quality, technical capabilities, maintenance capabilities and maintenance quality; there is a lack of a fault monitoring module, and it is impossible to classify and count fault points and display them visually; there is a lack of a vehicle monitoring module, and it is impossible to comprehensively monitor the status of trains in mainline operation, making it difficult to achieve functions such as train positioning and train statistics.

[0045] Based on this, an embodiment of the present application provides a monitoring system for rail transit vehicles to achieve high-efficiency and high-precision monitoring of rail transit vehicles.

[0046] See also Figure 1 , Figure 1 This is a schematic diagram of the structure of a monitoring system for a rail transit vehicle provided in an embodiment of the present application. Figure 1 As shown in , the monitoring system 100 provided in the embodiment of the present application includes a vehicle operation status monitoring module 110 , a vehicle maintenance status monitoring module 120 , a vehicle fault monitoring module 130 and a user login module 140 .

[0047] The vehicle operation status monitoring module 110 is used to obtain vehicle status information corresponding to the rail vehicle and display the vehicle status information corresponding to the rail vehicle in a display interface.

[0048] The vehicle status information includes basic information of rail vehicles, train number information of rail vehicles, operation status information of rail vehicles, key performance indicators of rail vehicles and positioning information of rail vehicles.

[0049] Here, the vehicle operation status monitoring module 110 is mainly used to monitor the status of the rail vehicle. In specific implementation, the vehicle operation status monitoring module 110 obtains the vehicle status information corresponding to the rail vehicle, and displays the vehicle status information corresponding to the rail vehicle in the display interface. Specifically, the vehicle status information includes the basic information of the rail vehicle, the train number information of the rail vehicle, the operation status information of the rail vehicle, the key performance indicators of the rail vehicle and the positioning information of the rail vehicle. In this way, the functions of the rail vehicle positioning and key performance indicator monitoring of the vehicle operation status monitoring module 110 can meet the comprehensive monitoring of the rail vehicle status, and can also obtain basic information such as the basic information of the rail vehicle and the train number information.

[0050] The vehicle maintenance status monitoring module 120 is used to obtain the maintenance business data of the rail vehicle, and evaluate the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle.

[0051] Here, the vehicle maintenance status monitoring module 120 is mainly used to comprehensively monitor the maintenance status of the rail vehicle. In the specific implementation, the vehicle maintenance status monitoring module 120 obtains the maintenance business data of the rail vehicle, and evaluates the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle. At the same time, the vehicle maintenance status monitoring module 120 realizes the overall monitoring of vehicle maintenance by integrating and cleaning the maintenance business data of the rail vehicle. Through data governance and data model calculation, the vehicle maintenance progress and maintenance quality are evaluated and analyzed, the overall situation of vehicle maintenance is controlled, maintenance resources are dynamically scheduled, maintenance efficiency is improved, and maintenance costs are reduced. Specifically, according to the embodiment provided by this application, the implementation process of evaluating the progress and quality of vehicle maintenance includes the following steps: first, the maintenance business data of the vehicle is collected, which may specifically include maintenance time, maintenance items, equipment use and personnel allocation data. Then, according to the maintenance plan and standardized maintenance process, key nodes and quality evaluation indicators are set. Compare the differences between maintenance data and planned progress and quality indicators to assess progress delays and quality compliance. Use the degree of progress delay to assess maintenance progress and the quality compliance rate to assess maintenance quality, so as to determine the current maintenance status of each rail vehicle.

[0052] According to the embodiments provided in the present application, data integration and cleaning are mainly achieved through the following steps: collecting data from multi-source heterogeneous systems and converting them into a unified format; repairing, smoothing, interpolating, and other processing of missing and abnormal data; applying ETL tools to extract data, transform integration, and load into the data warehouse; and improving data quality by using rules and expressions to identify and delete dirty data.

[0053] The vehicle fault monitoring module 130 is used to obtain historical fault status information of multiple faulty vehicles, classify and count the historical fault status information, obtain multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generate a vehicle fault statistics table based on the number of faults corresponding to each fault category.

[0054] Here, the vehicle fault monitoring module 130 is mainly used to perform statistical monitoring on the fault information of the faulty vehicle. In specific implementation, the vehicle fault monitoring module 130 obtains the historical fault status information of multiple faulty vehicles, classifies and counts the historical fault status information, obtains multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generates a vehicle fault statistics table based on the number of faults corresponding to each fault category. The vehicle fault monitoring module 130 can access the fault status information of the platform, and obtains multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category by counting the fault status information, and intuitively displays the number of faults corresponding to each fault category in a list, bar chart, pie chart or trend statistical chart. Through the classification statistics and visual display functions of the vehicle fault monitoring module 130, information statistics and analysis of daily operation and maintenance business can be supported. At the same time, the abnormal status information of the vehicle can be grasped in time to better manage and maintain the vehicle.

[0055] Specifically, the vehicle fault monitoring module 130 can classify the historical fault status information through the following steps to achieve fault classification: establish a classification system based on indicators such as fault code, system, and impact range; use decision trees, SVM and other algorithms to identify and classify fault patterns; count the number of faults of different categories and present them visually. Specifically, according to the embodiment provided by the present application, the implementation process of fault classification includes the following steps: design a classification system based on indicators such as fault code, system and impact range, such as function, location, severity and other categories. Then, collect and annotate a large amount of fault sample data. Use the decision tree algorithm to select branches according to the characteristics of the sample data to obtain fault classification rules. Use the SVM algorithm to find the optimal hyperplane and separate different faults. Verify the classification model and adjust the classification model parameters to improve the accuracy. Classify the historical fault status information and count the faults of different categories and their numbers. Finally, the classification results can be visualized using bar charts, pie charts, etc.

[0056] As an optional embodiment, when the vehicle fault monitoring module 130 is used to classify and count the historical fault status information to obtain multiple fault categories corresponding to the historical fault status information, the vehicle fault monitoring module 130 is further used to:

[0057] A CNN network is used to extract time domain features of the historical fault status information to identify multiple fault categories corresponding to the historical fault status information.

[0058] Here, the vehicle fault monitoring module 130 uses the CNN network to analyze the historical fault state information to identify the fault category. Specifically, the vehicle fault monitoring module 130 uses the CNN network to extract the time domain features of the historical fault state information to identify the multiple fault categories corresponding to the historical fault state information. As an example, the historical fault state information can be the on-board vibration sensor data of the rail vehicle engine in a fault state. The CNN network analyzes the on-board vibration sensor data, extracts the time domain features of the on-board vibration sensor data through convolution, and identifies the engine fault category. Specifically, as an example, the vehicle fault monitoring module 130 specifically trains the CNN network through the following steps: first, collect the vibration data of the engine of the faulty vehicle under various fault states as sample data, and then pre-process the sample data, including denoising, standardization, etc. Then construct a CNN network structure, including an input layer, a convolution layer, a pooling layer, and a fully connected layer. Use the sample data to iteratively train the constructed CNN network, and continuously adjust the parameters of the CNN network to reduce the loss function until the CNN network converges. Use test data to verify the detection effect of the CNN network.

[0059] The user login module 140 is used to provide the user with a login function of a login system that complies with the user's authority information according to the user's authority information, so that the user logs in to the login system to view the vehicle monitoring information recorded in the login system.

[0060] Here, the user login module 140 mainly provides a unified login management function for users. In specific implementation, the user login module 140 provides the user with a login function for a login system that meets the user's authority information according to the user's authority information, so that the user can log in to the login system to view the vehicle monitoring information recorded in the login system. In this way, the user login module 140 can facilitate users to quickly jump to a system that meets their authority to view their system information through the unified login management function.

[0061] Specifically, unified login management is achieved through the following steps: using the OAuth 2.0 protocol to implement single sign-on, so that different systems can share user authentication information; applying LDAP directory services to centrally manage user account information; using the Session synchronization mechanism to achieve seamless user access across systems; providing basic data maintenance functions to manage users, roles, permissions and other information.

[0062] As an optional embodiment, the vehicle running status monitoring module 110 is further used for:

[0063] Acquire real-time operation data of the rail vehicle; acquire multiple sensor data of the rail vehicle, and build an abnormal state recognition model based on the time domain characteristics and frequency domain characteristics of the multiple sensor data; input the feature sequence of the real-time operation data into the abnormal state recognition model to determine the abnormal condition information of the rail vehicle.

[0064] In view of the above three steps, in the specific implementation, the vehicle operation status monitoring module 110 obtains the real-time operation data of the rail vehicle. At the same time, multiple sensor data of the rail vehicle are obtained, and an abnormal state recognition model is constructed based on the time domain features and frequency domain features of the multiple sensor data. Here, the network structure of the abnormal state recognition model is an input layer, an LSTM layer, a fully connected layer and a Softmax output layer. Specifically, the vehicle operation status monitoring module 110 is also used to construct an abnormal state recognition model through the following steps: first, sample data of multiple sensors of the vehicle are collected, including normal state and abnormal state. Then, the characteristics of the sample data are analyzed to extract time domain statistical features, frequency domain features, etc. An abnormal state recognition model is constructed, and the model structure includes an input layer, an LSTM layer, a fully connected layer and a Softmax output layer. The abnormal state recognition model is iteratively trained using sample data, and the loss function is optimized to improve the accuracy. (5) The effect of the abnormal state recognition model is verified using a test data set. Features are extracted from the real-time operation data of multiple rail vehicles and input into the abnormal state recognition model to judge the abnormal state. The feature sequence of the real-time operation data of the rail vehicle is input into the abnormal state recognition model to determine the abnormal condition information of the rail vehicle. In this way, by analyzing a large amount of sensor data and applying deep learning algorithms to analyze vehicle operation data, abnormal conditions of rail vehicles can be identified, such as excessive engine temperature and excessive vibration.

[0065] As an optional embodiment, the rail transit vehicle monitoring system 100 also includes an image recognition module and an intelligent voice question and answer module.

[0066] The image recognition module is used to obtain a vehicle equipment image taken by a user, and recognize the vehicle equipment image to determine a target vehicle-mounted equipment captured in the vehicle equipment image and a target rail vehicle to which the target vehicle-mounted equipment belongs.

[0067] Here, the image recognition module is mainly used to identify the corresponding vehicle equipment according to the image taken by the user. In the specific implementation, the image recognition module obtains the vehicle equipment image taken by the user, and recognizes the vehicle equipment image to determine the target vehicle equipment captured in the vehicle equipment image and the target rail vehicle to which the target vehicle equipment belongs. In this way, the image recognition technology is applied to realize the intelligent identification and positioning of vehicle equipment.

[0068] The intelligent voice interactive question and answer module is used to obtain the user's question voice about the rail vehicle, convert the question voice into corresponding text information, and determine the answer information corresponding to the question voice based on the text information.

[0069] Here, the intelligent voice interactive question and answer module is mainly used to determine the corresponding answer information based on the voice input by the user. In the specific implementation, the intelligent voice interactive question and answer module obtains the user's question voice about the rail vehicle, and converts the question voice into corresponding text information, and determines the answer information corresponding to the question voice based on the text information. Here, Chatbot and natural language generation technology are used to realize intelligent voice interactive question and answer to assist users in solving common problems. Specifically, the GTC model is used to generate a long text description of vehicle failures and maintenance measures: input structured information such as vehicle model, fault code, maintenance record, etc. The GPT model learns text generation rules through training and generates corresponding natural language descriptions. Specifically, the text generation rules are learned through the following formula:

[0070] P(yt)=ΠiP(yi|y1,..,yi-1)

[0071] P(yt) represents the probability of word yt output at time t, which can be expressed as the product of conditional probabilities ΠiP(yi|y1,..,yi-1), that is, the product of the conditional probabilities of each previous word to the current word. Among them, yt represents the current word to be predicted, such as the 5th word to be predicted. P(yt) represents the probability of predicting word yt, and this probability should be maximized. Π represents the probability multiplication operation. i represents the position of the word, starting from 1 to the position t of the current word. yi represents the i-th word. y1,..,yi-1 represents from the first word to the i-1th word, that is, the first i-1 words. P(yi|y1,..,yi-1) represents the conditional probability of the i-th word yi under the condition of the first i-1 words. The above formula means: To predict the word yt at the current time t, I can regard it as considering the product of the conditional probabilities of each previous word to the current word yt. In other words, the probability of the current word depends on the influence of all previous words. In this way, the model learns the conditional dependency of all previous words on the current word. At the same time, a Transformer-based machine translation model can be developed to support multi-language interaction of users.

[0072] When applying the intelligent voice interactive question-and-answer module, develop an intelligent customer service robot based on deep learning to support multiple rounds of conversations to answer user questions. Use the Seq2Seq model and Attention mechanism to obtain the user's query intention and generate corresponding responses. Use transfer learning to pre-train the model on large-scale question-and-answer data, and then fine-tune it using vehicle system data. Build a knowledge graph to expand the knowledge scope of the intelligent voice interactive question-and-answer module, and continue to learn and improve. Specifically, build a vehicle fault knowledge graph, including nodes such as fault symptoms, location basis, and processing methods, input the fault phenomenon, and determine the cause and solution of the fault through knowledge graph reasoning.

[0073] In this way, through the image processing technology of the image recognition module and the intelligent voice interaction technology of the intelligent voice interaction question and answer module, users can interact using natural language, improving the system's usability and user experience, making the system smarter and more user-friendly.

[0074] As an optional embodiment, the rail transit vehicle monitoring system 100 further includes a device state prediction module, and the device state prediction module is used to:

[0075] For each on-board device on the rail vehicle, historical status data of the on-board device is obtained; based on the historical status data, time series data modeling is performed using an LSTM neural network to obtain a device status prediction model; the current status data of the on-board device is input into the device status prediction model to obtain the predicted status data of the on-board device at the next time point.

[0076] Here, the device state prediction module is mainly used to predict the predicted state data of the on-board device at the next time point based on the current state data of the on-board device. In specific implementation, for each on-board device on the rail vehicle, the device state prediction module obtains the historical state data of the on-board device. Based on the historical state data, the LSTM neural network is used to model the time series data to obtain the device state prediction model, and the current state data of the on-board device is input into the device state prediction model to obtain the predicted state data of the on-board device at the next time point. As an example, for example, the engine temperature data is modeled to predict the predicted temperature of the engine at the next time point:

[0077] ht=σ(Wxhxt+Whhht-1+bh)

[0078] yt=Whyht+by

[0079] Among them, ht represents the LSTM hidden layer state at time t, W represents the weight matrix, b represents the bias vector, xt represents the input at time t, ht-1 represents the hidden layer state at the previous moment, bh represents the bias vector, yt represents the output at time t, Why represents the weight matrix from the hidden layer to the output, and by represents the output bias vector.

[0080] As an optional embodiment, the monitoring system 100 further includes a maintenance plan determination module. Specifically, the maintenance plan determination module is used to:

[0081] Collect multi-source data, build an equipment association network map, and determine the time association relationship of each device through node association analysis; obtain historical equipment failure information, use the Apriori algorithm to mine frequent equipment combinations, and determine the failure association law; determine the current faulty device, determine the associated devices associated with the current faulty device based on the fault association law, and associate the current faulty device with the associated devices to generate a maintenance plan corresponding to the current faulty device.

[0082] For the above three steps, collect and associate multi-source data, such as component relationship data between each on-board equipment in multiple rail vehicles, establish a data warehouse, build an equipment association map, and determine the association relationship of each equipment time through node association analysis. Obtain historical equipment failure information, use the Apriori algorithm to mine frequent equipment combinations, and determine the fault association law. Determine the current faulty equipment, determine the associated equipment associated with the current faulty equipment based on the fault association law, and associate the current faulty equipment with the associated equipment to generate a maintenance plan corresponding to the current faulty equipment. For example, when the fault association law is that the transformer fault is frequently associated with the motor fault, when it is determined that the current faulty equipment is the motor, based on the fault association law, it is determined that the associated equipment associated with the motor is the transformer, and the maintenance plan at this time is to recommend a joint inspection of the transformer and the motor. In this way, the association rule algorithm is used to analyze the correlation of different vehicle and component faults, and according to the frequent component failure correlation, a maintenance plan for checking and repairing related components together is recommended.

[0083] As an optional embodiment, the monitoring system provided in the present application also includes a data analysis module. Here, the data analysis module is mainly used to analyze vehicle operation data and maintenance data to enhance data collection and analysis capabilities. Specifically, the data analysis module uses distributed computing frameworks such as Spark to analyze large-scale vehicle operation and maintenance data. Use convolutional neural networks to automatically learn and extract features from sensor data. For example, a 1-dimensional convolutional layer performs time series feature extraction: Hj = σ(bj + ΣiXi*Wij), where Xi is the input layer, Wij is the convolution kernel, and Hj is the feature map. Here, first, a centralized database for vehicle operation and maintenance data is established to collect massive vehicle fault data and maintenance data. Interactive data analysis is performed based on Spark SQL to facilitate the acquisition of maintenance suggestions, and a Spark Machine Learning pipeline is developed for batch pattern recognition, fault prediction, etc.

[0084] As an optional embodiment, the monitoring system further includes a data encryption module, wherein the data encryption module is used to:

[0085] The vehicle status information, the maintenance business data and the historical fault status information are encrypted using an encrypted HASH algorithm, and the encrypted vehicle status information, the encrypted maintenance business data and the encrypted historical fault status information are transmitted to a backend server for storage via blockchain.

[0086] Here, this application takes into account the security of the system and data and introduces appropriate security measures. For example, encryption technology can be used to protect the transmission and storage of data, and multi-level identity authentication can be used to control the access rights of the system. Encrypt vehicle operation and maintenance data to ensure data security. At the same time, blockchain technology is used to confirm the ownership of vehicle operation and maintenance records to prevent tampering. Use blockchain and encrypted HASH algorithm to verify the entire life cycle of vehicle operation data and maintenance records. In the specific implementation, the data encryption module uses the encrypted HASH algorithm to encrypt the vehicle status information, maintenance business data and historical fault status information, and transmits the encrypted vehicle status information, encrypted maintenance business data and encrypted historical fault status information to the background server for storage through the blockchain.

[0087] Furthermore, this application uses the decentralized and tamper-proof characteristics of blockchain to design a blockchain storage solution for vehicle operation and maintenance data. A private alliance chain with vehicle computers and background servers as nodes is constructed. Vehicle operation data is recorded on the chain in the form of transactions. Each detection data is packaged into a block and the HASH value is calculated. After the nodes on the chain reach a consensus, it is written into the blockchain. The maintenance center, as a node on the chain, uploads the maintenance records. All records are anonymized to protect privacy. The encrypted H algorithm is used to ensure integrity for key operating parameters and events. Before sending data to the network, the on-board system uses the SHA-256 algorithm to calculate the HASH value. After receiving the data, the background recalculates the HASH value and compares the consistency to detect the integrity of the data during transmission. HMAC signatures are also performed on events that modify key parameters to prevent private data from being tampered with. When the vehicle is resold, blockchain technology is used to reliably track the vehicle's full life cycle operation data, including mileage, maintenance records, etc., to ensure data authenticity.

[0088] Furthermore, the monitoring system 100 provided in the present application also includes model compression technology. Specifically, taking the abnormal state recognition model in the above embodiment as an example, the quantization technology is used to binarize or multi-bit quantize the model parameters to reduce the computing and storage costs. Apply knowledge distillation technology, use a small student network to learn the knowledge of a large teacher network, and achieve model compression. Design compression activation functions, such as adaptive ReLU, to automatically select the appropriate negative semi-axis truncation point. Develop a simulated steel quenching algorithm to automatically find the optimal model compression solution through network structure adjustment. The above technology can effectively realize efficient model deployment from cloud to end, enabling complex deep learning systems to run on vehicle-mounted equipment. By compressing the model size, the storage and transmission costs are reduced, making it easy to embed into vehicle-mounted equipment.

[0089] At the same time, the monitoring system 110 provided in the embodiment of the present application combines the system with the Internet of Things technology, which can monitor the status and location of the vehicle in real time and automatically send warning information to maintenance personnel. In addition, the Internet of Things technology can also help the system manage and dispatch maintenance resources more effectively. Install sensors at key parts of the vehicle to monitor the vehicle's operating status in real time. Use networks such as NB-IoT to build a car network and collect real-time vehicle data. Use technologies such as RFID to identify spare parts to ensure that the correct accessories are used for maintenance.

[0090] The monitoring system provided in the embodiment of the present application can better control the overall situation of vehicle maintenance, improve maintenance efficiency, and reduce maintenance costs by evaluating and analyzing the vehicle maintenance progress and quality through the vehicle maintenance status monitoring module. Through the classification statistics and visual display functions of the vehicle fault monitoring module, the abnormal status information of the vehicle can be grasped in time to better manage and maintain the vehicle. Through the train statistics function of the vehicle operation status monitoring module, the train status can be fully monitored, and key performance indicator information such as basic train information and train number information can be obtained.

[0091] See also Figure 2 , Figure 2 The present invention provides a flow chart of a method for monitoring a rail transit vehicle. The monitoring method is applied to a monitoring system for a rail transit vehicle, and the monitoring system includes a vehicle operation status monitoring module, a vehicle maintenance status monitoring module, a vehicle fault monitoring module, and a user login module. Figure 2 As shown, the monitoring method includes:

[0092] S201, controlling the vehicle operation status monitoring module to obtain vehicle status information corresponding to the rail vehicle, and displaying the vehicle status information corresponding to the rail vehicle in a display interface; wherein the vehicle status information includes rail vehicle basic information, rail vehicle train number information, rail vehicle operation status information, rail vehicle key performance indicators and rail vehicle positioning information;

[0093] S202, controlling the vehicle maintenance status monitoring module to obtain the maintenance business data of the rail vehicle, and evaluating the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle;

[0094] S203, controlling the vehicle fault monitoring module to obtain historical fault status information of multiple faulty vehicles, classifying and counting the historical fault status information, obtaining multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generating a vehicle fault statistics table based on the number of faults corresponding to each fault category;

[0095] S204, controlling the user login module to provide the user with a login function of a login system that complies with the user's authority information according to the user's authority information, so that the user logs in to the login system to view the vehicle monitoring information recorded in the login system.

[0096] Furthermore, the monitoring method further comprises:

[0097] Controlling the vehicle operation status monitoring module to obtain real-time operation data of the rail vehicle;

[0098] Controlling the vehicle operation status monitoring module to obtain multiple sensor data of the rail vehicle, and constructing an abnormal state recognition model based on the time domain characteristics and frequency domain characteristics of the multiple sensor data;

[0099] The vehicle operation status monitoring module is controlled to input the feature sequence of the real-time operation data into the abnormal state recognition model to determine the abnormal state information of the rail vehicle.

[0100] Furthermore, the vehicle fault monitoring module is controlled to classify and count the historical fault status information to obtain multiple fault categories corresponding to the historical fault status information, including:

[0101] The vehicle fault monitoring module is controlled to use a CNN network to perform time domain feature extraction on the historical fault status information to identify multiple fault categories corresponding to the historical fault status information.

[0102] Furthermore, the rail transit vehicle monitoring system further includes an image recognition module and an intelligent voice question-answering module, and the control method further includes:

[0103] Controlling the image recognition module to obtain the vehicle equipment image taken by the user, and recognize the vehicle equipment image to determine the target vehicle-mounted equipment captured in the vehicle equipment image and the target rail vehicle to which the target vehicle-mounted equipment belongs;

[0104] The intelligent voice interactive question-and-answer module is controlled to obtain a user's voice question about the rail vehicle, and the voice question is converted into corresponding text information, and answer information corresponding to the voice question is determined based on the text information.

[0105] Furthermore, the rail transit vehicle monitoring system further includes a device state prediction module, and the monitoring method further includes:

[0106] Controlling the device status prediction module to obtain historical status data of each on-board device on the rail vehicle;

[0107] Control the device state prediction module to perform time series data modeling using an LSTM neural network based on the historical state data to obtain a device state prediction model;

[0108] The device state prediction module is controlled to input the current state data of the vehicle-mounted device into the device state prediction model to obtain the predicted state data of the vehicle-mounted device at the next time point.

[0109] Furthermore, the rail transit vehicle monitoring system further includes a maintenance plan determination module, and the establishment method further includes:

[0110] Control the maintenance plan determination module to collect multi-source data, construct a device association network map, and determine the association relationship of each device time through node association analysis;

[0111] Control the maintenance plan determination module to obtain historical equipment failure information, use the Apriori algorithm to mine frequent equipment combinations, and determine the failure association rules;

[0112] The maintenance plan determination module is controlled to determine the current faulty device, determine the associated devices associated with the current faulty device based on the fault association rule, and associate the current faulty device with the associated devices to generate a maintenance plan corresponding to the current faulty device.

[0113] Furthermore, the rail transit vehicle monitoring system further includes a data encryption module, and the monitoring method further includes:

[0114] The data encryption module uses an encrypted HASH algorithm to encrypt the vehicle status information, the maintenance business data and the historical fault status information, and transmits the encrypted vehicle status information, the encrypted maintenance business data and the encrypted historical fault status information to a background server for storage through blockchain.

[0115] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown in , the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0116] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 2 The specific implementation of the steps of the method in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0117] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 2 The specific implementation of the steps of the method in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0118] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0119] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0122] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0123] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0124] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A monitoring system for rail transit vehicles, characterized in that: The monitoring system includes a vehicle operation status monitoring module, a vehicle maintenance status monitoring module, a vehicle fault monitoring module and a user login module; The vehicle operation status monitoring module is used to obtain the vehicle status information corresponding to the rail vehicle and display the vehicle status information corresponding to the rail vehicle in the display interface; wherein the vehicle status information includes the basic information of the rail vehicle, the train number information of the rail vehicle, the operation status information of the rail vehicle, the key performance indicators of the rail vehicle and the positioning information of the rail vehicle; The vehicle running status monitoring module is also used for: Acquiring real-time operation data of the rail vehicle; Acquire multiple sensor data of rail vehicles, and build an abnormal state recognition model based on time domain characteristics and frequency domain characteristics of the multiple sensor data; Inputting the characteristic sequence of the real-time operation data into the abnormal state recognition model to determine the abnormal state information of the rail vehicle; The vehicle maintenance status monitoring module is used to obtain the maintenance business data of the rail vehicle, and evaluate the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle; The vehicle fault monitoring module is used to obtain historical fault status information of multiple faulty vehicles, classify and count the historical fault status information, obtain multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generate a vehicle fault statistics table based on the number of faults corresponding to each fault category; The user login module is used to provide the user with a login function that conforms to the user's authority information, so that the user can log in to the login system and view the vehicle monitoring information recorded in the login system. The rail transit vehicle monitoring system further includes an equipment state prediction module, wherein the equipment state prediction module is used to: For each on-board device on the rail vehicle, obtaining historical status data of the on-board device; Based on the historical status data, the LSTM neural network is used to perform time series data modeling to obtain a device status prediction model; Inputting the current state data of the vehicle-mounted device into the device state prediction model to obtain the predicted state data of the vehicle-mounted device at the next time point; The rail transit vehicle monitoring system further includes a maintenance plan determination module, wherein the maintenance plan determination module is used to: Collect multi-source data, build a device association network map, and determine the correlation between each device time through node association analysis; Obtain historical equipment failure information, use the Apriori algorithm to mine frequent equipment combinations, and determine the failure association rules; The current faulty device is determined, and the associated devices associated with the current faulty device are determined based on the fault association rule, and the current faulty device is associated with the associated devices to generate a maintenance plan corresponding to the current faulty device.

2. The monitoring system according to claim 1, characterized in that: When the vehicle fault monitoring module is used to classify and count the historical fault status information to obtain multiple fault categories corresponding to the historical fault status information, the vehicle fault monitoring module is also used to: A CNN network is used to extract time domain features of the historical fault status information to identify multiple fault categories corresponding to the historical fault status information.

3. The monitoring system according to claim 1, characterized in that: The rail transit vehicle monitoring system also includes an image recognition module and an intelligent voice question and answer module; The image recognition module is used to obtain the vehicle equipment image taken by the user, and recognize the vehicle equipment image to determine the target vehicle-mounted equipment captured in the vehicle equipment image and the target rail vehicle to which the target vehicle-mounted equipment belongs; The intelligent voice interactive question and answer module is used to obtain the user's question voice about the rail vehicle, convert the question voice into corresponding text information, and determine the answer information corresponding to the question voice based on the text information.

4. The monitoring system according to claim 1, characterized in that: The rail transit vehicle monitoring system further includes a data encryption module, which is used to: The vehicle status information, the maintenance business data and the historical fault status information are encrypted using an encrypted HASH algorithm, and the encrypted vehicle status information, the encrypted maintenance business data and the encrypted historical fault status information are transmitted to a backend server for storage via blockchain.

5. A method for monitoring a rail transit vehicle, characterized in that: The monitoring method is applied to the monitoring system of the rail transit vehicle according to any one of claims 1 to 4, the monitoring system comprising a vehicle operation status monitoring module, a vehicle maintenance status monitoring module, a vehicle fault monitoring module and a user login module, and the monitoring method comprises: Control the vehicle operation status monitoring module to obtain vehicle status information corresponding to the rail vehicle, and display the vehicle status information corresponding to the rail vehicle in the display interface; wherein the vehicle status information includes rail vehicle basic information, rail vehicle train number information, rail vehicle operation status information, rail vehicle key performance indicators and rail vehicle positioning information; Controlling the vehicle maintenance status monitoring module to obtain the maintenance business data of the rail vehicle, and evaluating the maintenance progress and maintenance quality of the rail vehicle based on the maintenance business data of the rail vehicle to obtain the current maintenance status corresponding to each rail vehicle; Controlling the vehicle fault monitoring module to obtain historical fault status information of multiple faulty vehicles, classifying and counting the historical fault status information, obtaining multiple fault categories corresponding to the historical fault status information and the number of faults corresponding to each fault category, and generating a vehicle fault statistics table based on the number of faults corresponding to each fault category; Control the user login module to provide the user with a login function of a login system that complies with the user's authority information according to the user's authority information, so that the user logs in to the login system to view the vehicle monitoring information recorded in the login system; The monitoring method further comprises: Controlling the vehicle operation status monitoring module to obtain real-time operation data of the rail vehicle; Controlling the vehicle operation status monitoring module to obtain multiple sensor data of the rail vehicle, and constructing an abnormal state recognition model based on the time domain characteristics and frequency domain characteristics of the multiple sensor data; Controlling the vehicle operation status monitoring module to input the feature sequence of the real-time operation data into the abnormal state recognition model to determine the abnormal state information of the rail vehicle; The rail transit vehicle monitoring system further includes a device state prediction module, and the monitoring method further includes: Controlling the device status prediction module to obtain historical status data of each on-board device on the rail vehicle; Control the device state prediction module to perform time series data modeling using an LSTM neural network based on the historical state data to obtain a device state prediction model; Controlling the device state prediction module to input the current state data of the vehicle-mounted device into the device state prediction model to obtain the predicted state data of the vehicle-mounted device at the next time point; The rail transit vehicle monitoring system further includes a maintenance plan determination module, and the maintenance plan determination module further includes: Control the maintenance plan determination module to collect multi-source data, construct a device association network map, and determine the association relationship of each device time through node association analysis; Control the maintenance plan determination module to obtain historical equipment failure information, use the Apriori algorithm to mine frequent equipment combinations, and determine the failure association rules; The maintenance plan determination module is controlled to determine the current faulty device, determine the associated devices associated with the current faulty device based on the fault association rule, and associate the current faulty device with the associated devices to generate a maintenance plan corresponding to the current faulty device.

6. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the rail transit vehicle monitoring method as described in claim 5.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring a rail transit vehicle as claimed in claim 5 are executed.

Images