1261 results about "Rail transportation" patented technology

The invention discloses a railway freight train data acquisition method and system based on multi-sensor fusion, and relates to the technical field of railway transportation, and the method comprises the steps: detecting the operation state and position of a train in real time through wireless communication, and carrying out the self-inspection of each sensor when the train is detected to be about to enter a monitoring region; constructing a three-dimensional health state model of the train through three-dimensional reconstruction and synchronous positioning according to the comprehensive state data of the train; in combination with a three-dimensional health state model and a side cloud collaborative architecture, layered processing and dynamic optimization of train comprehensive state data are accelerated by using a quantum algorithm, and abnormal features are identified in real time; the abnormal features are analyzed through deep learning and a time sequence analysis algorithm, and alarm information is generated and fed back to the edge computing terminal; according to the method, the running state of the train and the cargo state data are deeply fused through the convolution operation of the three-dimensional health state model and the space-time diagram, so that the global perception capability of the data is improved.

The invention relates to the technical field of data processing, and provides a train dynamic scheduling method and a resource allocation system, through real-time acquisition and processing of heterogeneous data, generation of train priorities, and generation and verification execution of a scheduling scheme, fine management of a whole train scheduling process is realized, all steps cooperate with one another and are progressive layer by layer, and the scheduling efficiency is improved. Various complex factors in the train running process can be comprehensively considered, the limitation that a traditional dispatching mode depends on experience or a single index is changed, the scientificity, accuracy and timeliness of train dispatching decisions are remarkably improved, resources can be dynamically and efficiently allocated, train running arrangement can be optimized, and the train dispatching efficiency is improved. The transportation efficiency and the service quality are improved, and the ever-increasing diversified requirements of modern railway transportation are effectively met.

The invention provides a railway track periodical intelligent monitoring method based on the Internet of Things. The railway track periodical intelligent monitoring method comprises the steps that track geometric deformation data and track temperature distribution data are collected through sensing nodes deployed beside a track and on the track; extracting abnormal sections in the track geometric deformation data based on time window segmentation, and mapping the abnormal sections to a space grid of the track temperature distribution data to generate a deformation-temperature incidence matrix; calculating a track stress change gradient by combining the matrix and historical track temperature distribution data, and generating a track health degree evaluation index; and when the track health degree evaluation index meets a preset degradation condition, inputting the time sequence multi-source fusion data into a deep learning track state prediction module, and outputting a track failure risk level. According to the invention, the efficiency, accuracy and intelligent level of railway track monitoring can be improved, and the safety and reliability of railway transportation are guaranteed.

The invention provides a railway skylight scheme optimization method, device and equipment and a readable storage medium, and relates to the technical field of ordinary-speed railway transportation organizations, and the method comprises the steps: obtaining railway equipment information and train operation information, and determining a plurality of basic data; obtaining a plurality of dynamic skylights; constructing a collaborative optimization model based on the plurality of dynamic skylights and the plurality of basic data to obtain a multi-objective planning model; adjusting the basic data to obtain target data; and performing corresponding adjustment on the dynamic skylight based on the target data. According to the method, a train operation plan and dynamic skylight scheme collaborative optimization model is established by combining dynamically changing transportation requirements and equipment maintenance information, considering mutual influence between traffic flows and skylights and aiming at minimizing the total travel time and maintenance operation cost of a freight train, and solving is performed based on a Lagrange algorithm, so that the dynamic skylight scheme is optimized. Therefore, matching between the skylight and the line trafficability is ensured, reasonable application of track resources is achieved, and the skylight utilization rate is increased.

The invention provides a port operation optimization method based on big data and air rail transportation technology fusion, and belongs to the technical field of intelligent ports, and the method comprises the steps: obtaining port geographic data, setting a four-layer intelligent system, and collecting basic data based on the four-layer intelligent system; performing multi-modal data fusion processing on the basic data to obtain multi-modal fusion data, performing big data analysis based on the multi-modal fusion data, and constructing an intelligent decision model according to a big data analysis result; the dynamic scheduling of the air rail transport system is guided based on the output of the intelligent decision model, the dynamic scheduling is executed, the execution result is evaluated according to the real-time basic information obtained by the four-layer intelligent system, and then the port operation link is optimized according to the evaluation result; and designing a continuous learning mechanism based on an optimization result, and carrying out comprehensive optimization on the intelligent decision-making system and a port transportation link. And the port competitiveness is enhanced, and the data security and the autonomous controllable level are improved.

The invention belongs to the technical field of railway transportation safety, provides a railway contact net carrier cable tension online monitoring and early warning method and system, and aims at solving the technical problems that in the prior art, capturing is not comprehensive, and different environments are difficult to adapt. Acquiring a tension data stream by using a context awareness technique; analyzing the tension data flow by using a hidden Markov model to obtain a preliminary analysis result, processing by using a neural network, generating an abnormal mode recognition result, performing risk assessment by using a Bayesian network algorithm and a digital twin technology to obtain a preliminary fault estimation probability, and predicting a target fault estimation probability in combination with multi-context sensing data; a self-adaptive control algorithm is used for generating an adjusted alarm threshold value, when the monitored tension value exceeds the adjusted alarm threshold value, early warning information is generated in time, and processing is carried out through the block chain technology to obtain target early warning information; according to the technical scheme provided by the invention, the monitoring and early warning capabilities of the railway overhead line system carrier cable are comprehensively improved.

The invention provides a high-precision railway map generation method and system based on one-way trajectory correction, and relates to the technical field of heavy haul railway transportation, and the method comprises the steps: collecting a continuous image sequence and spatial attitude data of a current train in a driving process at the same time; determining pose change data of the current train based on visual feature points in the continuous image sequence; performing synchronous positioning and map construction based on the pose change data and the spatial pose data to generate an initial electronic map; and based on mileage information and image positions corresponding to preset markers in the continuous image sequence, the mileage and the track of the current train in the initial electronic map are corrected, and a corresponding electronic map of the current train in the driving process is generated. According to the method and system provided by the invention, the generation efficiency and accuracy of the railway electronic map are improved.

The invention discloses a railway dispatching transportation intelligent system. The system comprises a data acquisition module, a data preprocessing module, an intelligent analysis and prediction module, a dynamic dispatching optimization module, a communication and data exchange module, a user interface and interaction module, a system performance monitoring and adaptive learning module, an emergency response module and an energy management module. The system can acquire multivariate data in a railway network in real time, perform deep mining on the data through the intelligent analysis and prediction module, and accurately predict conditions such as train operation delay and fault risk, so that a dispatcher can take measures in advance to avoid or reduce delay, thereby remarkably improving punctuality and efficiency of railway transportation, and improving the safety of railway transportation. The dynamic scheduling optimization module can dynamically adjust the train operation plan according to the prediction result and the actual operation condition, the flexible scheduling mode can utilize railway resources to the maximum extent, waiting and conflicts between trains are reduced, and the transportation efficiency is further improved.

The invention discloses an electric locomotive rail obstacle identification method, device and system and electronic equipment, and relates to the technical field of rail transit. The method comprises the following steps: acquiring geographic information along a track and current positioning information, acquiring current radar information to perform obstacle detection when a driving state is determined according to the current positioning information, and performing a first alarm and acquiring current video image information when a suspected obstacle is detected; performing time-space synchronization and data fusion on the current positioning information, the current radar information and the current video image information, and inputting the fused data, the locomotive running state data and the geographic information into a pre-established obstacle recognition model to recognize a suspected obstacle to obtain a recognition result; and determining a risk level according to the identification result, so that the electric locomotive gives a second alarm according to the risk level and takes countermeasures. According to the invention, multi-source data is acquired through various sensors, accurate identification of small targets is realized, and the safety of railway transportation is guaranteed.

The invention provides an air-railway combined transportation network passenger flow prediction method fusing LSTM and GNN. The method comprises the steps that firstly, a graph model of a user travel scheme interaction data set is established through a user portrait data set and a travel scheme record data set; then constructing a weight matrix as the input of the traffic prediction model; and predicting the future traffic of the air-railway combined transportation travel scheme by adopting a traffic prediction model based on a long-short-term memory network and a graph neural network. According to the method, the long-term dependency relationship in the time sequence data is captured by using the LSTM, and the graph structure between the travel schemes is constructed in combination with the GNN to process the spatial relationship data, so that the complex characteristics of the traffic change of the travel schemes can be captured more comprehensively. Simulation results show that the proposed method is superior to a single LSTM, GNN or SFM or other benchmark methods in indexes such as MSE, MAE, RMSE and MAPE.

The invention discloses an intelligent field section management and control method and system suitable for urban rail transit, and belongs to the technical field of rail transit, and the technical key points comprise the steps: arranging various types of sensors for images, positions, states and the like in a field section key area, and collecting the operation, state and environment data of vehicles, equipment and infrastructures in real time; transmitting the collected data to a management and control center in real time through a wired and wireless combined communication network, so that the management and control center analyzes the received data in real time, identifies abnormity, predicts faults and generates a management and control instruction; according to the railway operation and maintenance management system, intelligent execution equipment such as a turnout point switch, a signal machine and vehicle maintenance equipment is automatically controlled according to a management and control instruction, intelligent coordinated management and control of vehicle entering and exiting, parking, maintenance and equipment operation are achieved, and the railway operation and maintenance management system is a highly complex and precise system. And safety, high efficiency and order of railway transportation are ensured.

The invention relates to the technical field of railway fault traceability, in particular to a railway fault traceability method and system based on a weighted path sorting algorithm, and the method comprises the steps: constructing a traceability knowledge graph according to historical fault data, equipment operation data and maintenance records of a railway system; and then a weighted path sorting algorithm is carried out on the traceability knowledge graph by combining a Bayesian network model, a random walk algorithm and an attention mechanism model, so that efficient and accurate railway safety fault traceability is realized, the safety and reliability of railway transportation are remarkably improved, and the method has a wide application prospect and a remarkable practical value.

The invention discloses a railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, and particularly relates to the technical field of high-speed railway signal system operation and maintenance, and the system comprises a data collection layer which is used for collecting data related to a railway vehicle-mounted ATP from a plurality of different data sources in real time; the data transmission layer adopts a reliable communication protocol to ensure that the data acquired from the data acquisition layer can be stably transmitted to the subsequent processing layer in real time; the data processing layer is used for cleaning, converting and fusing the transmitted data so as to improve the consistency and availability of the data; the intelligent analysis layer is used for carrying out intelligent analysis on the fused data; and the application layer provides a visual interface for operation and maintenance personnel and displays the analysis result and the operation and maintenance suggestions obtained by the intelligent analysis layer. According to the railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, the ATP operation and maintenance efficiency can be remarkably improved, the operation and maintenance cost is reduced, and safe and smooth railway transportation is guaranteed.

The invention discloses a virtual marshalling train distributed control method and system based on running track optimization, and the method comprises the steps: firstly, considering the resultant force in a train running process, and building a train simple substance point kinetic equation; secondly, in the virtual marshalling state, train operation conditions are divided according to the spatial position in combination with a train driving control strategy; thirdly, by means of the virtual marshalling technology, all train units in marshalling in the train running process are made to be consistent in speed, constraint conditions of safety protection distance and space-time safety protection are set, the train running energy consumption and comfort model is introduced into a multi-target hiking optimization algorithm, and the energy consumption and comfort of the train are optimized in combination with the constraint conditions; optimizing the running track according to the working condition state of the train; and finally, establishing a distributed self-adaptive sliding mode control law of the train according to the optimized running track. By optimizing the running track of the train, an accurate protection strategy is realized, and the control method established based on the optimized track can ensure stable running of the train while improving the railway transportation efficiency.

The invention discloses a mountain gravity energy storage system and method for continuous operation of multiple weight blocks. The mountain gravity energy storage system comprises an inclined rail, a cableway support, a truck, standardized weight blocks, a high-altitude automatic loading and unloading platform, a low-altitude automatic loading and unloading platform, a motor generator set, a transmission mechanism and a control system. Standardized weight blocks serve as weight carriers, charging and discharging of the energy storage system are achieved through mutual conversion of gravitational potential energy and electric energy of the standardized weight blocks, rail transportation and cable transportation modes are combined, an automatic weight loading and unloading platform is arranged, and the carrying capacity of the weight carriers can be increased on the basis that the system operation continuity is guaranteed; the power and the capacity of the energy storage system are improved, manual establishment of a sand warehouse or a complex transferring and stacking mechanism is avoided, the cost is reduced, and the energy circulation efficiency of the system is further improved.

The embodiment of the invention provides a multi-system rail transit junction streamline optimization method and device, and the method comprises the steps: carrying out the three-dimensional modeling of a multi-system rail transit junction, and obtaining a transportation junction model; dividing the transportation junction model into a plurality of digital blocks according to geographic information, facility layout information, passenger flow data and operation data of the multi-system rail transportation junction; according to passenger flow and logistics demands among different digital blocks, determining a connection relationship among the different digital blocks; according to the method, a streamline path is determined based on a connection relationship between different digital blocks, a streamline operation condition is simulated, a preset optimization target is taken as a target function, the streamline path is optimized, an optimized streamline is obtained, and the operation efficiency of the hub is effectively improved through division of the digital blocks in the hub and optimization of streamline organizations and stream nodes between the blocks; the travel time of passengers is shortened, and the passenger satisfaction is improved.

The invention relates to the technical field of railway transportation safety monitoring, and discloses a railway operation environment intelligent monitoring and risk assessment system, which comprises a railway environment multi-source data acquisition module, a track potential safety hazard detection module and a risk assessment and processing unit, and is also provided with a data fusion and preprocessing module. The acquisition module acquires various types of environmental data in real time, the detection module accurately identifies hidden danger track sections, and the risk assessment and processing unit analyzes hidden danger influences, assesses risk levels and formulates strategies. And the data fusion and preprocessing module improves the data quality. The beneficial effects are obvious, and hidden dangers can be comprehensively monitored in real time and accurately positioned; risks are scientifically evaluated, and coping strategies are reasonably formulated; data processing is optimized, and a reliable decision basis is provided; the operation and maintenance cost is reduced and the operation efficiency is improved; the device adapts to complex environments, guarantees safe development of railways, and meets safe operation requirements of railways.

Disclosed in the present invention are a locomotive number tracking method and system. The locomotive number tracking method comprises: handling a shunting route of a locomotive number and acquiring station yard signal device representation information; acquiring the running direction of the locomotive number on the basis of the station yard signal device representation information; acquiring an auxiliary tracking data set on the basis of a station yard signal device logic diagram and the running direction of the locomotive number, the auxiliary tracking data set comprising the locomotive number, a signal machine, and a route locking section; when the state of a track section in the shunting route changes, acquiring track section representation information; and matching the track section representation information with the auxiliary tracking data set to search for a locomotive number movement starting signal device and target signal device so as to track the locomotive number. The present invention can improve the accuracy and reliability of locomotive number tracking and point reporting, thereby improving railway transportation working efficiency.

The invention provides a railway automatic goods yard loading and unloading operation method, and relates to the technical field of railway goods yards, and the method is characterized in that a railway automatic goods yard goods loading and unloading operation system comprises a loading and unloading machine tool positioning system, a goods positioning system and a loading and unloading machine tool management system; the railway freight yard is provided with a freight car loading and unloading operation area, a warehouse operation area and a railway freight car loading and unloading operation area, and goods are loaded and unloaded in different areas. The loading and unloading machine tool management system controls the loading and unloading machine tools to carry out truck unloading operation and truck loading operation in the truck loading and unloading area, carry out warehousing operation and ex-warehouse operation in the warehousing operation area and carry out railway loading operation and railway unloading operation in the railway loading and unloading area. According to the method, rapid loading and unloading, efficient stacking and intelligent management of goods can be achieved, and the efficiency and competitiveness of railway transportation are improved; meanwhile, labor cost can be reduced, operation risks are reduced, and the automation degree of the railway freight yard is improved.

The invention discloses a ballastless track concrete bonding interface mechanical state testing method, belongs to the technical field of track traffic engineering, and realizes a multi-field coupling loading test on a ballastless track interlayer test piece by constructing an interlayer mechanical testing device comprising a servo loading mechanism, a DIC technology and finite element mechanical analysis. A high-speed camera is adopted to synchronously record the whole process of interlayer interface damage, an interface stress distribution cloud picture is obtained in combination with a distributed strain patch, and a load-displacement curve and interlayer slippage data are synchronously collected. A refined finite element model containing a cohesion unit is established based on measured data, and iterative fitting of a simulation result and test data is achieved by dynamically adjusting interface damage parameters. According to the method, the limitation of a traditional single-point stress test is broken through, space-time multi-scale analysis of interlayer mechanical behaviors is achieved, the technical problems that an interlayer interface failure mechanism is not clear and simulation model parameters are difficult to calibrate are solved, and a novel test is provided for durability evaluation of a ballastless track structure.

The invention discloses a turnout switch machine fault diagnosis and prediction model method based on artificial intelligence. The method comprises the following steps: step 1, data acquisition; step 2, data preprocessing; step 3, feature extraction; step 4, model training; 5, verifying the model; 6, deploying the model; step 7, fault diagnosis and prediction; an artificial intelligence algorithm is introduced to automatically analyze data and identify faults, safe operation of equipment is ensured, instant fault response is realized through real-time monitoring and rapid data processing, the equipment safety is improved, an automatic modeling tool is adopted to simplify the construction process, non-professional personnel operation is facilitated, system deployment is accelerated, and the system reliability is improved. The method combines expert experience and data driving to form a hybrid model, improves the adaptability and accuracy of the model, integrates multi-sensor data to form a unified monitoring platform, enhances the comprehensiveness and accuracy of fault diagnosis, and provides powerful guarantee for the safety and efficiency of railway transportation.

According to the train fault remote early warning method and system based on artificial intelligence, the multi-dimensional state path vectors in the target train operation data are accurately extracted and fused to generate the first train state characteristic spectrum, and comprehensive and accurate representation of the train operation state is achieved. In combination with prior early warning guiding knowledge data, the method effectively guides a train fault early warning decision model to perform accurate early warning decision on target train operation data by using an interactive focusing feature analysis technology. And by introducing the first feature flow control parameter to optimize the interactive focusing feature data, a more targeted target guidance knowledge vector is generated, and the accuracy and reliability of fault early warning are further improved. Finally, the train fault early warning knowledge points can be remotely generated in real time, powerful technical guarantee is provided for safe operation of the train, the occurrence rate and the influence range of train faults are remarkably reduced, and the safety and the efficiency of railway transportation are improved.

The invention relates to the technical field of intelligent scheduling, in particular to a railway vehicle intelligent scheduling and monitoring system which comprises a data acquisition module, a data processing module, an intelligent scheduling module, a priority adjustment module, a scheduling scheme generation module and a visualization module. The data acquisition module acquires multi-source data related to train operation in real time through a sensor and monitoring equipment, the data processing module performs preprocessing and feature extraction on the multi-source data, the intelligent scheduling module generates a preliminary scheduling scheme by adopting an intelligent algorithm based on the extracted feature data, the priority adjustment module performs priority adjustment, and the scheduling module performs scheduling according to the preliminary scheduling scheme. The scheduling scheme is ensured to adapt to real-time demand changes, the scheduling scheme generation module generates a complete train scheduling scheme, and the visualization module displays the scheduling scheme to a dispatcher and an administrator through a graphical interface; according to the method, through real-time dynamic scheduling and simulation optimization, the operation efficiency and safety of railway transportation are improved, delay is reduced, and the satisfaction degree of passengers is improved.

The utility model provides a steel plate seat frame and a railway transport vehicle, and relates to the technical field of steel plate transportation, the steel plate seat frame provided by the utility model comprises a seat frame body, a first upright post and a second upright post, the extending directions of the first stand column and the second stand column in the using state are both configured to be parallel to the thickness direction of the steel plate. The first stand column is in sliding fit with the seat frame body in the first direction and is in rotating fit with the seat frame body around the first direction, and the first stand column is used for limiting the position of the steel plate in the first direction. A limiting structure used for limiting or releasing limiting of the position of the first stand column relative to the seat frame body is arranged between the first stand column and the seat frame body. The second stand column is detachably connected with the seat frame body and used for limiting the position of the steel plate in the second direction. The steel plate seat frame can prevent steel plates from damaging a transport vehicle in the transportation process, and meanwhile has the advantage of being convenient to store.

The invention discloses a method for measuring the toughness of a high-speed railway transportation network, and relates to the technical field of railway transportation networks. Comprising the following steps: respectively establishing a high-speed railway tense service network in a normal state and a high-speed railway tense service network under interference, and determining the instantaneous performance of the high-speed railway transportation network in the normal state and the instantaneous performance of the high-speed railway transportation network in the interference state; and determining the optimal network toughness of the high-speed railway transportation network according to the instantaneous performance in the normal state and the instantaneous performance in the interference state. According to the method, the instantaneous performance is measured and calculated on the smaller time granularity, the change rule of the instantaneous performance along with time can be effectively observed, the measurement and calculation precision of the network toughness is improved, and the method has more guiding significance for formulating a recovery strategy.

The invention discloses an intelligent transportation scheduling system and method for the rail transit equipment industry, and the system comprises a data collection module, a transportation module, a scheduling module and an output module, and the data collection module is used for collecting the related information of railway transportation; the transportation module is used for detecting parameter indexes of railway transportation; the scheduling module analyzes problems generated when the cargoes arrive at different unloading places; the output module is used for transmitting the planning information to transfer personnel at a loading site; the cargo batching module is used for enabling cargos at different delivery sites to arrive at unloading sites at different time; the scheduling analysis sub-module obtains an adjustment scheme beneficial to reducing the unloading pressure of the unloading places according to the stacking degrees of different unloading places; the loading evaluation module enables more unloading sites to execute an adjustment scheme to the maximum extent under the condition that the normal warehouse storage capacity of the shipping sites is guaranteed, the goods problems of the shipping sites and the unloading sites are considered, and the method has the advantages of being high in design transportation efficiency and high in transportation resource utilization rate.

The invention relates to the technical field of rail transit, and provides a virtual marshalling train operation adjustment method, device and equipment and a storage medium, and the method comprises the steps: obtaining a current train operation plan and train operation information, and generating marshalling information according to the train operation plan and the train operation information; the specific marshalling information comprises marshalling intervals and marshalling operation plans of the target trains in the marshalling fleet; when the target train arrives at a first target station, sending the marshalling information to the target train; the first target station is a previous parking station of the marshalling interval in the advancing direction of the target train; and the target train performs virtual marshalling in the marshalling interval according to the marshalling information, and operates according to the marshalling operation plan after completing the virtual marshalling. Automatic adjustment of train operation is achieved by automatically generating marshalling information, the requirement for efficient operation of the train is met, and marshalling flexibility and line operation capacity are improved.

The invention relates to the technical field of train transportation, in particular to a train timetable and speed curve optimization method and device and a storage medium, and the method comprises the steps: obtaining the attribute information of a train and each operation interval of the train; by taking the minimum energy consumption as a target and taking the interval speed limit and punctuality operation of each operation interval as constraints, calculating to obtain an initial speed curve and an initial train timetable corresponding to each operation interval of each train; calculating traction network loss corresponding to each train under the same power supply arm according to the traction network equivalent model; and optimizing an initial speed curve and an initial train timetable by taking minimization of the sum of traction network loss of the trains under the whole line and maximization of overlapping time and on-time operation of traction and braking stages among the trains as targets. The optimization method disclosed by the invention has remarkable beneficial effects in the aspects of improving the energy utilization efficiency, improving the train operation efficiency, reliability and punctuality rate, promoting the sustainable development of a railway transportation system and the like.

The invention provides a railway safety protection system, which comprises a laser correlation detection module formed by a laser transmitting end and a laser receiving end symmetrically arranged on two sides of a railway opening and used for generating a plurality of groups of laser grating networks and monitoring a light beam shielding event in real time; the intelligent analysis module is used for identifying the type of an intrusion target according to the shielding signal of the laser grating network and analyzing a target movement track to filter false triggering; the alarm linkage module is used for triggering a sound-light alarm after the invasion is confirmed, closing a railway barrier gate and sending alarm information to a control center; the monitoring integration module is used for being linked with a video monitoring system to call the high-definition image of the intrusion area and assisting in judgment through AI image recognition; and the environment self-adaption module is used for integrating a temperature and humidity sensor and a wind speed sensor to dynamically adjust a laser sensitivity threshold value to adapt to environment change. Personnel invasion at the railway crossing of the thermal power plant is monitored through a laser correlation technology, so that unauthorized personnel or vehicles are prevented from entering a railway transportation area of the thermal power plant, and the operation safety of the thermal power plant is guaranteed.

The invention provides an asynchronous federal learning system and method for a turnout switch machine fault diagnosis model. The system comprises the following steps: acquiring mechanical vibration signals at three positions of a speed reducer shell, a contact seat and an actuating rod of a switch machine by using a mechanical vibration sensor; information fusion of the vibration signals of the three point locations is carried out; a lightweight dual-scale neural network model; an asynchronous federated learning process resistant to time delay and packet loss; and an asynchronous federated learning system structure. An asynchronous federal learning process resistant to time delay and packet loss is adopted, communication delay and the remaining receiving time of single uploading of an edge computing unit are fully utilized, and the extra computing time for fusion after all units are uploaded is shortened; the asynchronous federated learning system structure clarifies the hierarchical relationship and specification of federated learning of point switch fault diagnosis in a railway system. Distributed training of the switch machine fault diagnosis model is realized, and reliable guarantee is provided for railway transportation safety.