776results about "Railway vehicle testing" patented technology

The invention relates to the technical field of artificial intelligence and computer vision, discloses a subway key component fault detection method and system based on an AI visual large model, and aims to solve the problems of low detection precision, weak generalization ability, insufficient multi-mode understanding, poor real-time performance and lack of state evolution modeling in the prior art. The method comprises the following steps: acquiring images of key components through a multi-view industrial camera array, and performing distortion correction, illumination normalization and noise suppression; a pre-trained visual large model is utilized to extract deep space features, and modeling is carried out on a continuous frame feature sequence through bidirectional LSTM to capture a time sequence change trend. By introducing the large-scale visual large model and spatio-temporal joint modeling, the identification capability of tiny defects is improved, the discrimination stability is enhanced, high-precision and low-delay automatic detection is realized, the false alarm rate and the omission ratio are remarkably reduced, and the detection efficiency and the system maintainability are improved.

The invention provides the unsupervised learning-based fault diagnosis method and system for detecting wheel out of round, which belongs to the technical field of machine learning fault diagnosis. Characteristic signals of train wheels will be acquired. The pre-trained detection model is adopted to process the characteristic signals of the train wheels to be detected, so as to obtain the wheel roundness state results. As for the collected characteristic signals, the invention constructs a subway wheel out of round detection method based on unsupervised learning for collected characteristic signals, which are deployed to computer equipment capable of executing computer programs, inputting characteristic signal data collected by a subway wheel out of round monitoring device based on rail wayside response into the computer equipment to obtain the wheel roundness state.

The invention relates to the technical field of rail transit monitoring, and discloses a multi-sensor fusion rail transit electric passenger car bogie dynamic performance monitoring method. The method comprises the steps that multi-source heterogeneous sensing data such as bogie vibration acceleration time sequence signals, wheel-rail contact force distribution data, bearing temperature gradient data and structural strain field data are collected; analyzing the vibration signal to extract a frequency band energy feature vector, performing spatial gridding mapping on the contact force data to generate a distribution matrix, and performing time-space alignment fusion on the two to form a primary fusion feature set; positioning a bearing temperature anomaly region through a deep convolutional network, and generating a secondary fusion feature set in combination with a structural strain concentration coefficient; and inputting the two-stage feature set into a dynamic performance evaluation model, outputting a performance degradation index set of scores of axle box bearing wear degree, framework fatigue cumulant, wheel set tread damage and the like, generating a maintenance priority sequence and triggering a preventive maintenance instruction according to the performance degradation index set, and realizing accurate monitoring and efficient operation and maintenance management and control of the dynamic performance of the bogie.

The invention relates to the technical field of rail traffic monitoring, and discloses an urban rail vehicle driving analysis system based on digital twinning, which is characterized in that vehicle vibration and traction motor current signals are collected in real time through a vehicle-mounted sensing unit, and an edge feature extraction unit calculates energy ratio features of a predefined fault frequency band; the data transmission unit transmits the characteristic data and the working condition information to a digital twin platform, a digital fault tree model is arranged in the platform, and a cross-physical domain fault conduction path is analyzed and recognized through multi-source data coupling. Through combination of frequency band energy ratio characteristics and fault tree logical reasoning, electromechanical coupling fault risks which cannot be found by traditional isolated monitoring are effectively captured, meanwhile, a diagnosis threshold value is dynamically adjusted according to the wheel-rail adhesion state, and the diagnosis reliability under the complex working condition is improved.

The invention relates to the technical field of train data analysis, in particular to a data analysis method for train operation faults, which comprises the following steps: carrying out data fusion processing on train operation brake signals acquired by a vibration sensor, an acoustic emission sensor and a state detection device to generate multi-dimensional brake time sequence data; brake fusion features are generated from the multi-dimensional brake time sequence data through a cross-modal fusion model, and the cross-modal fusion model is constructed based on a gating feature interaction layer and a convolution feature extraction layer; and the brake fusion features are used to generate brake fault severity through a space-time joint model, the space-time joint model is constructed based on an improved LSTM architecture, and optimization training is carried out through a physics constraint loss function. According to the method, the accuracy and reliability of predictive fault diagnosis of the subway braking system are remarkably improved through the LSTM architecture of multi-modal data fusion, cross-modal feature modeling and physical constraint embedding on the train operation braking data detected beside the track and the detection data of the braking system.

The invention relates to the technical field of damage identification, in particular to a structural defect identification method for brake shoe displacement and damage characteristics of a railway wagon, which comprises the following steps of: in the whole life cycle of the railway wagon, dividing a braking process into a plurality of stages, and performing hierarchical filing according to working condition types and service stages, constructing a brake shoe multi-working-condition structure response file; through longitudinal comparison along a time axis in the same working condition layer and transverse comparison among different working condition layers, screening out a brake shoe ectopic evolution mark and an initial brake shoe damage evolution mark which are sensitive to a structure state; encoding all evolution marks according to a spatial position, a working condition layer and a service stage to form a brake shoe ectopic and damage structure fingerprint sequence; and outputting an identification result including the structure defect type and the severity level, and generating a maintenance priority. According to the method, a space-time coupling mechanism of acoustic emission energy and temperature gradient is introduced to recognize early microcrack propagation, and the recognition sensitivity of recessive fatigue and complex damage modes is improved.

This application relates to the field of health monitoring in rail transit, and discloses a method, device, and system for monitoring the health of a bogie. The method includes: acquiring the stress on the surface of a predetermined location on the main body of a composite bogie when deformation occurs; the predetermined location includes key parts of the main body and areas where the main body and components are connected by fasteners; determining the degree of damage to the main body; and predicting the remaining life of the composite bogie based on the stress and the degree of damage. Therefore, the health monitoring method in this application, by acquiring the stress on the surface of a predetermined location on the main body of the composite bogie and determining the degree of damage to the bogie main body, and then predicting the remaining life of the composite bogie based on the degree of damage and the acquired stress, ensures the structural safety of the composite bogie and reduces maintenance costs.

The invention provides a rail vehicle collision test system, which relates to the technical field of rail vehicle collision tests and comprises a collision simulation device, a wall body, a test vehicle body and a data acquisition device. The test vehicle body is configured to move towards the wall body at a preset speed, and dummy passengers are carried in the test vehicle body. The collision simulation device comprises an energy absorption assembly and an adjusting assembly, the energy absorption assembly is installed on the wall and suitable for colliding with the test vehicle body, and the adjusting assembly is configured to respond to the crumple amount of the energy absorption assembly in the collision process and adjust the counter-acting force applied by the energy absorption assembly to the test vehicle body so as to simulate the collision process of the real vehicle with the energy absorption structure. The data acquisition device is arranged on the dummy passenger and is suitable for acquiring data information of secondary collision of the dummy passenger in the test vehicle body.

The invention provides a multi-modal intelligent diagnosis method and system for temperature vibration of a high-speed rail bearing based on a working condition spectrogram, and relates to the technical field of intelligent diagnosis, and the method comprises the steps: synchronously collecting vibration, temperature distribution and phase angle signals of a bearing, and extracting a self-adaptive reference baseline in combination with an operation working condition; and obtaining a temperature vibration joint sequence through phase alignment, calculating a thermal vibration coupling intensity spectrum, and comparing the thermal vibration coupling intensity spectrum with a baseline to obtain circumferential deviation distribution. And after dynamic threshold correction, mapping the over-limit phase interval into a fault space coordinate on the bearing raceway, and determining a fault type according to frequency spectrum characteristics. According to the invention, accurate space positioning and type identification of high-speed rail bearing faults are realized, and the adaptability and accuracy of diagnosis are improved.

The invention discloses an online detection device for a rack rail wheel, relates to the technical field of rail transit vehicles, and aims to solve the problem that the meshing relation between the rack rail wheel and a rack cannot be actually detected. The gear tooth structures of the detection rack and the line rack are consistent in specification; the propelling device is arranged on one side of the detection rack and used for driving the detection rack to move in the direction perpendicular to the extending direction of the detection rack; the pressing device is arranged on the other side of the detection rack, and the pressing device is used for providing pre-tightening force enabling the detection rack to reset in the direction perpendicular to the extending direction of the detection rack; through the arrangement, the actual meshing center distance between the rack rail wheel and the rack can be directly detected.

The present application relates to the technical field of sealing test, in particular to a railway clamp testing device, which comprises a testing table, a fixing mechanism arranged on the testing table, and an air pipe in communication with an internal air supply device of the testing table, one end of the air pipe being in communication with a connector; the connector comprises a pipe body, a distance sensor, and an adjusting piece, one end of the pipe body being rotatably provided with a connecting pipe, the pipe body being internally provided with a contraction part and a piston piece. In the railway clamp testing device, the piston plate and the contraction part are arranged to cooperate with each other in the pipe body, so that the piston plate can isolate the inside of the pipe body by moving in or out, and then the piston plate can automatically displace according to the change of air pressure, on the one hand, the driving of the connecting pipe is realized, and the number of times of twisting the connecting pipe is reduced, on the other hand, the piston plate can move according to the air leakage position, so that the air leakage position can be obtained according to the moving state, and whether the clamp leaks air can be quickly understood.

The invention discloses a train suspension system multi-physical quantity fusion health monitoring method and system, and the method comprises the steps: synchronously collecting flexible piezoresistance, triaxial acceleration and temperature signals, and achieving the cooperative calibration of multi-source signal cross attention alignment, residual optimization and physical perception through a DW-PC-CA calibration mechanism; tensor construction, lightweight tensor decomposition and physical constraint fusion optimization are carried out on the calibrated signal based on a PC-TD feature extraction method, and space, modal and time feature vectors with clear physical significance are extracted; the feature vectors are input into a pre-trained PhySTAGN model, and the model achieves accurate output of fault probability distribution and prediction uncertainty through a four-layer structure of input tensor preprocessing, space-time bidirectional interactive attention fusion, physical consistency regularization and health monitoring output. According to the method, the problems of multi-source signal misalignment, complex feature coupling and poor model interpretability are effectively solved, and the recognition accuracy of the health state of the suspension system and the system reliability are remarkably improved.

A bearing axial loading test device comprises a driving motor, an accompanying test bearing seat, an auxiliary bearing seat and an axial loading mechanism which are sequentially arranged from left to right. According to the utility model, the steps of the stepped shaft are adopted to position and place the bearing to be tested, the position precision and the dismounting efficiency of the bearing to be tested are improved, and the steps with different diameters are utilized to place the bearings to be tested with different models, so that the test range of the bearing axial loading test device is expanded; the one-way stepped shaft and the two-way stepped shaft form a clamped beam structure by using the accompanying test bearing seat and the auxiliary bearing seat, so that the stability of the stepped shafts under high-speed rotation is improved, the influence of high-speed rotation on the axial load of the to-be-tested bearing is avoided, and the test precision is improved; the separable roller bearing is adopted to reduce the resistance of the stepped shaft during axial movement, the placement cavity is defined by the accompanying test shaft and the auxiliary bearing to store lubricating oil, the lubricating oil is utilized to reduce the resistance of the bearing during relative movement of the inner ring and the outer ring, and the precision of the axial load output to the bearing to be tested is improved.

The invention relates to the field of subway fault analysis, in particular to a subway fault data analysis method based on a cloud platform, and the method comprises the steps: obtaining train operation difference parameters and noise characteristic difference parameters of all key monitoring points, so as to determine a monitoring difference state; determining a difference analysis strategy of each key monitoring point position according to the monitoring difference state; when abnormal defect analysis is carried out, a defect analysis mode is determined according to the noise period stability coefficient and the image gradient difference coefficient of the key monitoring point position; under the condition that abnormal defect analysis is completed, a monitoring compensation mode is determined according to the defect interference radiation coefficient of the key monitoring point position; when parameter optimization analysis is carried out, the setting mode of the point location anomaly coefficient is determined according to the noise anomaly frequency of the key monitoring point location and the operation interference proportion, whether the point location anomaly coefficient is adjusted or not is determined according to the coincident anomaly parameters, and the accuracy of the operation parameter optimization result is improved.

The invention relates to the technical field of low-temperature environment simulation and material characteristic test, in particular to a high-speed rail traction system fault diagnosis method based on electromagnetic parameter fusion, which is used for solving the problems of material electromagnetic characteristic test distortion and fault diagnosis algorithm verification deficiency in a high and cold environment. The method comprises the following steps: constructing a multi-physical field coupling test environment, simulating temperature cycle and humidity sudden change working conditions from-50 DEG C to + 80 DEG C, and synchronously acquiring dynamic parameters of resistivity, dielectric loss and magnetic conductivity; according to the method, the limitation of a traditional static test is broken through, the real representation of the material performance degradation rule is realized, a closed-loop verification system of laboratory and field data is constructed, and the performance of the material is verified. The accuracy and environmental adaptability of fault diagnosis in a high and cold environment are remarkably improved, and reliable guarantee is provided for safe operation of a traction system under an extreme working condition.

The invention discloses a pipeline air charging device and method, and relates to the technical field of vehicle detection and maintenance, the pipeline air charging device comprises a supporting seat, a positioning gland and a transition joint, the supporting seat is of a hook-shaped structure, and the supporting seat is provided with a clamping groove used for clamping a car coupler main blast pipe fixing seat; one end of the supporting seat is connected with a positioning gland, a transition connector is installed on the side, away from the supporting seat, of the positioning gland and used for being connected with an air charging pipeline, and the other side of the positioning gland is used for being in butt joint with a vehicle body air pipe. The supporting seat is designed according to the outer contour of the coupler, accurate, firm and reliable positioning is guaranteed, and the air charging efficiency can be improved.

Assemblies, systems, and methods for inspecting vehicles are disclosed. An assembly can comprise a first angled camera, a second angled camera, an upright camera, lights, and a housing configured to attach to a railway. The first angled camera can be oriented at least partially in a generally vertical direction and at least partially in a first horizontal direction, and directed to a first target region from a first viewpoint. The second angled camera can be oriented at least partially in the generally vertical direction and at least partially in a second horizontal direction, and directed to a second target region from a second viewpoint. The upright camera can be oriented substantially in a vertical direction, and configured to capture images of a third target region from a third viewpoint.

The utility model discloses a suspension type monorail vehicle bogie running-in test bench, comprising a support frame, a support platform, a running-in wheel set, a guide wheel backstop assembly and a loading assembly. Modularization and lightweight design is adopted, the whole bogie structure is placed, load loading is achieved, the guide wheel positioning function is achieved, and traction and running-in of a transmission system of the traction can be carried out.

A diagnosis device (1) is provided with a data generation unit (11), an approximate rotation speed acquisition unit (12), a rotation speed acquisition unit (13), and a diagnosis unit (14). The data generation unit (11) generates, from a vibration sensor signal output by a vibration sensor (92) for measuring the magnitudes of vibration of a subject appliance, spectrum data indicating the distribution of the per-frequency magnitudes of vibration of the subject appliance. The approximate rotation speed acquisition unit (12) obtains an approximate rotation speed, which is an approximate value of the rotation speed of a rotating body of the subject appliance. The rotation speed acquisition unit (13) acquires, as the rotation speed of the rotating body, a frequency corresponding to the peak of the spectrum data in a frequency band including the approximate rotation speed. The diagnosis unit (14) diagnoses the conditions of the subject appliance on the basis of the peak value of the peak of the spectrum data in the frequency band including the diagnosis subject frequency corresponding to the rotation speed acquired by the rotation speed acquisition unit (13).

The utility model belongs to the technical field of rail transit vehicle testing, and particularly relates to a rail transit vehicle axle fatigue testing device capable of applying axial force, which comprises a mounting seat, a sliding block is fixedly arranged on the lower surface of a base, the sliding block is arranged on a sliding rail in a sliding manner, and the sliding rail is fixed on the mounting seat. A transverse rod is connected between the two bases in a hinged mode, guide blocks are arranged on the upper surface and the lower surface of the transverse rod and arranged in sliding grooves in U-shaped blocks in a sliding mode, the U-shaped blocks are fixedly connected with the movable end of a hydraulic oil cylinder, the hydraulic oil cylinder is installed on a fixing base, and the fixing base is fixedly connected with the movable end of the hydraulic oil cylinder. And the fixed seat is fixedly mounted on the upper surface of the mounting seat. According to the utility model, the U-shaped block can be driven to move through the action of the hydraulic oil cylinder, the force is converted into the force for the transverse movement of the base through the matching of the chute and the guide block, and the base drives the synchronizing wheel to move, so that the axial force loading of the loading wheel and the axle is realized, and the fatigue test of the axle in a turning state is further completed.

The invention provides a detection method and system for an air supply system of a railway vehicle, a train, equipment and a medium, and can be applied to the technical field of railway vehicles. The method comprises the following steps: in response to determining that a to-be-detected vehicle is in a static state, determining a vehicle working condition of the to-be-detected vehicle according to a vehicle speed data set and a first main blast pipe pressure data set of the to-be-detected vehicle within a first preset time period; under the condition that the vehicle working condition represents that the to-be-detected vehicle is in the stable working condition, according to a wind using equipment data set of the to-be-detected vehicle in a second preset time period, the wind using equipment state of the to-be-detected vehicle is determined, and the second preset time period is after the first preset time period; and under the condition that the state of the air using equipment represents that the air using equipment of the to-be-detected vehicle does not work, determining an air tightness detection result aiming at the air supply system according to a second main air pipe pressure data set in a second preset time period.

The invention provides an impact test device and method for a brake disc of a high-speed train, and relates to the technical field of impact test equipment, the impact test device comprises a base, a brake disc to be detected is placed on a placement table, an impact seat falls under the action of gravity to impact the brake disc to be detected above the placement table, and a base plate is arranged below the base. A mounting base plate is mounted at the bottom end of the base plate, the base plate is fixedly mounted on the ground by means of the mounting base plate, a buffer unit is arranged between the base and the base plate, and when the impact seat impacts the placement table under the action of gravity, impact force can be removed by means of the buffer unit; the arc-shaped elastic piece, the damping part and the buffering rubber ball are matched with a multi-stage buffering structure of self-adaptive pressurization of the air cylinder, and graded unloading and energy dissipation can be carried out on instantaneous strong loads after impact.

This application provides a method, apparatus, device, and medium for determining the characteristic frequencies of dynamic response data of rail vehicles, relating to the field of rail vehicle technology. The method determines the resonant frequency band in the dynamic response based on the known excitation frequency of the operating line, and separates the dynamic response data according to the energy change rate of the resonant frequency band to obtain vehicle vibration response data, thereby determining the characteristic frequencies of target vehicle components. This overcomes the problems of existing technologies where fixed-band filtering cannot adapt to the differences in excitation characteristics of different lines, easily leads to insufficient interference filtering or over-filtering that mistakenly deletes effective information, and manual frequency selection relies on experience, is inefficient, and has subjective judgment errors, making it difficult to adapt to scenarios with large changes in rail vehicle speed and complex operating conditions. It can accurately eliminate line excitation interference, accurately extract the characteristic frequencies of vehicle components, and improve the accuracy and reliability of characteristic frequency identification.

The application relates to the technical field of railway vehicle detection, and discloses a bearing vibration detection and identification method based on an octave and a voting mechanism, which is characterized in that bearing detection of passing vehicles is completed through a bearing running-in test platform arranged on a railway site to form actual detection data; the bearing running-in test platform comprises a contact part used for directly contacting an outer ring of a measured bearing, an acceleration sensor and a microphone are arranged on the contact part; vibration acceleration data is formed through acceleration sensor detection of bearing vibration; sound pressure level data is formed through microphone detection of bearing vibration; and the vibration acceleration data and the sound pressure level data together form vibration transmission data. The application can more accurately complete bearing vibration detection and identification and can be applied to actual railway vehicle detection and identification.

The invention relates, among other things, to a method for measuring the condition of wheels, wheelsets and / or brake systems of railway vehicles (200) by generating condition data (CDs). According to the invention, a measuring device (10) temporarily attached to a first mounting interface (211) of a first railway vehicle (200) during maintenance and / or inspection determines the condition by measuring, generating one or more first condition data (CDs).

The utility model discloses a shielding door state monitoring device, which relates to the technical field of monitoring devices and comprises a moving mechanism, the moving mechanism comprises a guide rail, an adjusting screw and a motor, the outer wall of the adjusting screw is sleeved with a mounting seat in a threaded manner, one end of the mounting seat is fixedly provided with a mounting plate, and the motor drives the adjusting screw to rotate. A plurality of positioning rods are fixedly mounted at one end of the mounting plate, and the outer walls of the positioning rods are slidably sleeved with a mounting box; through mutual cooperation of an audible and visual alarm, a door state acquisition module, a signal processing and analysis module, a control module, a power supply management module and a moving mechanism, when the state of the shielding door is abnormal, a motor and the audible and visual alarm work, the moving mechanism drives the audible and visual alarm to vertically move upwards, the warning effect of the audible and visual alarm is improved, and the safety of the shielding door is improved. And when no abnormal condition exists, the equipment is hidden at a low position, so that the probability that the equipment is damaged by mistaken touch is reduced, and the applicability is high.

The embodiment of the present application relates to the technical field of railway transportation safety, and discloses a calibrating device for the force of a coupler of a railway train. The calibrating device comprises a fixing frame, an actuator assembly and a fixing mechanism. The fixing frame is used for fixing the actuator assembly. One end of the actuator assembly is fixedly connected with the fixing frame, and the other end acts on the coupler to apply a load force to the coupler. The fixing mechanism is located below the actuator assembly and is used for fixing the coupler. The technical scheme provided by the present application solves the problems that the calibrating work of the coupler under various complex loads is difficult to be realized in the prior art, and the calibration of the coupler is difficult to be objectively and accurately completed. The calibrating work of the coupler under various complex loads can be realized, so that the calibration of the coupler can be objectively and accurately completed.

A method and a device for diagnosing a defect in a pantograph of a railway vehicle and calculating its remaining service life are disclosed. The method may include setting a status value for diagnosing the pantograph, building a database with indexes for diagnosing the pantograph, comparing a detected index with a reference index, and storing a defect code of the pantograph if the detected index is greater than the reference index in the database.The status value can refer to the pressure of an actuator when the pantograph is raised before the rail vehicle is in motion, to the actuator pressure while the rail vehicle is in motion, to the number of arcing occurrences or the duration of arcing events while the rail vehicle is in motion, to an insulation resistance while the rail vehicle is in motion, or to the wear amount of a main wear slider. Furthermore, the device configured to carry out the method is disclosed.

The invention discloses an intelligent submission inspection method and system for a subway bogie. The system comprises a control mechanism, and an upper visual acquisition module, a first collaborative robot, a truss manipulator, a riding wheel transportation device, a seventh-axis robot, a second collaborative robot and a lower visual acquisition module which are connected with the control mechanism; the riding wheel transportation device carries wheels and accurately transfers the bogie; a first collaborative robot is arranged on a truss manipulator above the ground, and the first collaborative robot is connected with an upper visual module and is used for photographing the upper part, front, back, left and right parts of the bogie to collect images; a second collaborative robot is arranged on a seventh-axis robot in a pit below the ground level, and a visual module is arranged on the second collaborative robot and used for photographing the bottom of the bogie to collect images. Feeding and robot photographing are combined on one set of mechanism, the problem that a single feeding mechanism can occupy the photographing space is solved, the cost of the feeding mechanism is greatly reduced, the visual detection range is expanded, and mutual operation does not interfere with each other.