Method and system for detecting abnormal switch state of door system and rail vehicle

Abstract

The present invention provides a method, system, and rail vehicle for detecting abnormalities in the switch status of a vehicle door system. The method obtains door parameters, a lock position switch signal, a close position switch signal, and a control signal from the vehicle door system; utilizes a pretrained anomaly detection and prediction model to predict and determine, based on the acquired information, whether the state of the close position switch and the lock position switch of the vehicle door system is abnormal; and stores the prediction and judgment results. The present invention uses the model to determine whether the state of the close position switch and the lock position switch is abnormal. The judgment results are objective, enabling effective and timely detection of abnormalities in the close position switch and the lock position switch, reducing operating costs, eliminating unnecessary waste, and improving the reliability of vehicle door operation.

Description

Technical Field

[0001] The present invention belongs to the field of vehicle door detection technology, and specifically relates to a method and system for detecting abnormal switch states of a vehicle door system, and a rail vehicle. More specifically, it relates to a method and system for detecting abnormal switch states of a vehicle door system when the vehicle door system is in the fully closed or fully locked position, and a rail vehicle. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Doors play a vital role in urban rail transit equipment. During vehicle operation, the door system needs to be frequently opened and closed. Coupled with the influence of human factors during peak hours, door opening and closing failures often occur, leading to passenger removal incidents. According to operator statistics, the number of door system failures ranks first among all train systems, accounting for approximately 35% of the total failures. The close and lock switches occupy an important position in the door system and are one of the core components of the door system. Once an abnormality occurs, most of the abnormalities are sudden, and the signs of the abnormality cannot be discovered in advance through routine or planned repairs. Furthermore, once the number of switch operations reaches its theoretical lifespan, it can only be directly replaced, which easily leads to increased costs and unnecessary waste. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a method, system and rail vehicle for detecting abnormal switch status of a vehicle door system. The present invention uses a model to judge whether the status of the closed position switch and the locked position switch is abnormal. The judgment result is objective and can effectively and timely detect abnormalities of the closed position switch and the locked position switch, thereby reducing operating costs, eliminating unnecessary waste and improving the reliability of vehicle door operation.

[0005] According to some embodiments, the present invention adopts the following technical solutions:

[0006] A method for detecting abnormal switch status of a vehicle door system comprises the following steps:

[0007] Obtain door parameters, lock position switch signal, close position switch signal and control signal of the door system;

[0008] Using the pre-trained anomaly detection and prediction model, the system can predict whether the closed and locked positions of the door system are abnormal based on the acquired information.

[0009] Storing prediction and judgment results;

[0010] The construction process of the anomaly detection and prediction model includes constructing door switch component state evaluation parameters, extracting influencing factors of the evaluation parameters, establishing feature evaluation relationships, and obtaining the anomaly detection and prediction model based on the feature evaluation relationships.

[0011] As an optional implementation, the door parameters include the voltage, current and speed of the door motor; the control signal includes the trigger time, the door position and the control instruction.

[0012] As an optional implementation method, the specific process of constructing the door switch component status evaluation parameters includes: selecting the triggering number difference Fd if, triggering sequence difference Od if, triggering position difference Ld if, initial synchronization difference Sd if, and door opening and closing resistance characteristic difference Rd if when triggered of the closed position switch and the locked position switch on both sides of the door system as characteristic parameters for evaluating the door switch component status.

[0013] As an optional implementation method, the specific process of extracting the influencing factors of the evaluation parameters includes: extracting the right switch signal of the closed position, the left switch signal of the closed position, the right switch signal of the locked position, the left switch signal of the locked position, the time T ime, the door position L, the voltage U, current I and speed V of the door motor, and the control instructions for opening and closing the door.

[0014] As an optional implementation method, the specific process of establishing the feature evaluation relationship includes:

[0015] 1) Trigger count difference Fd if is used to reflect the difference in the number of times each close and lock switch operates. This function checks whether a switch has no operation or multiple operations, and whether the operation state of each switch changes only once during each door opening or closing process.

[0016] 2) Trigger sequence difference, used to reflect whether the switch action sequence matches the design mechanism, and whether there is a wrong sequence in the triggering of the vehicle closing and locking in place;

[0017] 3) Trigger position difference, used to reflect whether each closed position and locked position switch is triggered when the door moves to the normal position;

[0018] 4) Preliminary synchronization difference, used to reflect whether the closed and locked switches on the left and right sides are triggered synchronously;

[0019] 5) The difference in the door opening and closing resistance characteristics when triggered is used to reflect the consistency of the door motor's driving torque during each opening and closing action. The driving torque is calculated based on the motor voltage, current and speed.

[0020] As an optional implementation method, based on the feature evaluation relationship, the specific process of obtaining the abnormality detection and prediction model includes calculating the trigger number difference, trigger position difference, trigger sequence difference, initial synchronization difference and door opening and closing resistance characteristic difference when triggering according to the vehicle door parameters, locked position switch signal, closed position switch signal and control signal, and making a comprehensive judgment on each feature. When any feature exceeds the set range or an error occurs, the output of the abnormality detection and prediction model is abnormal.

[0021] A vehicle door system switch state abnormality detection system, comprising:

[0022] A data acquisition module is configured to acquire door parameters, a lock position switch signal, a close position switch signal, and a control signal of the door system;

[0023] A switch component abnormality diagnosis module is configured to use a pre-trained abnormality detection and prediction model to predict whether the closed position switch and the locked position switch of the vehicle door system are abnormal based on the acquired information;

[0024] A data management module is configured to store prediction and judgment results;

[0025] The construction process of the anomaly detection and prediction model includes constructing door switch component state evaluation parameters, extracting influencing factors of the evaluation parameters, establishing feature evaluation relationships, and obtaining the anomaly detection and prediction model based on the feature evaluation relationships.

[0026] As an optional implementation, it also includes a data communication module for connecting to the vehicle network system to obtain the collected door parameters, locked position switch signal, closed position switch signal and control signal.

[0027] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0028] A rail transit vehicle comprises the above-mentioned electronic device or system.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention constructs an abnormal warning prediction model for the door closed and locked switches. The warning prediction model is constructed based on the characteristic parameters of the door system switch component status evaluation to accurately monitor and predict the performance status of the door system switch components, reduce the failure rate of the door switch components, and improve the reliability of the door operation.

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0033] Figure 1 is a flow chart of an embodiment;

[0034] Figure 2 Schematic diagram of an anomaly detection and prediction model according to an embodiment. DETAILED DESCRIPTION

[0035] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0037] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0038] In the absence of conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0039] Example 1

[0040] A method for detecting abnormal switch status of a vehicle door system comprises the following steps:

[0041] Obtain door parameters, lock position switch signal, close position switch signal and control signal of the door system;

[0042] Using the pre-trained anomaly detection and prediction model, the system can predict whether the closed and locked positions of the door system are abnormal based on the acquired information.

[0043] Storing prediction and judgment results;

[0044] The construction process of the anomaly detection and prediction model includes constructing door switch component state evaluation parameters, extracting influencing factors of the evaluation parameters, establishing feature evaluation relationships, and obtaining the anomaly detection and prediction model based on the feature evaluation relationships.

[0045] Among them, the door parameters, the locked position switch signal, the closed position switch signal and the control signal include the signal of the right closed position switch (for the convenience of description, referred to as DCSR below, the same below), the left closed position switch signal DCSL, the right locked position switch signal DLSR, the left locked position switch signal DLSL, the trigger time Time, the door position L, the voltage U, current I and speed V of the door motor, and the control instructions or control status of the door opening and door closing states.

[0046] The following is a detailed description of the construction process of the anomaly detection and prediction model.

[0047] like Figure 2 As shown, specifically including:

[0048] (1) Constructing door switch component status evaluation parameters

[0049] The door switches include the closed position switches (DCSR, DCSL) and the locked position switches (DLSR, DLSL). The difference in the number of triggers Fd if, the difference in the trigger sequence Od if, the difference in the trigger position Ld if, the difference in the initial synchronization Sd if, and the difference in the opening and closing resistance characteristics Rd if when triggering the left and right switches are selected as characteristic parameters for evaluating the status of the door switch components.

[0050] (2) Extract the influencing factors of the evaluation parameters and construct the feature evaluation relationship

[0051] Based on the characteristic parameters of door switch component status evaluation, the influencing factors are extracted, including the right switch (DCSR) in the closed position, the left switch (DCSL) in the closed position, the right switch (DLSR) in the locked position, the left switch (DLSL) in the locked position, time T ime, door position L, door motor voltage U, current I, speed V, door opening, and door closing.

[0052] Based on the door parameters, a feature evaluation relationship is constructed, which includes the following features:

[0053] (a) Trigger count difference Fd if: This feature reflects the difference in the number of DCSR, DCSL, DLSR, and DLSL actuations of the switches. It checks whether a switch has no actuation or multiple actuations. Specifically, it checks whether the actuation state of each switch changes only once during each door opening or closing process, that is, whether di ff(DCSR / DCSL / DLSR / DLSL) = 1 or -1 only occurs once.

[0054] (b) Trigger sequence difference Od if. This feature reflects whether the switch action sequence matches the design mechanism and checks whether there is a misorder in the triggering of the vehicle closing and locking positions. That is, during the door opening process, diff(DLSR) and diff(DLSL) act before diff(DCSR) and diff(DCSL); during the door closing process, diff(DCSR) and diff(DCSL) act before diff(DLSR) and diff(DLSL);

[0055] (c) Trigger position difference Ld if, which reflects whether each DCSR, DCSL, DLSR, and DLSL is triggered when the door moves to the normal position, that is, the door position parameters when the di ff(DCSR), di ff(DCSL), di ff(DLSR), and di ff(DLSL) states change.

[0056] In this embodiment, the mean Lmean and standard deviation Lstd of each switch trigger position under the normal door opening and closing state can be calculated, and Lmean±3*Lstd can be used as the evaluation standard;

[0057] (d) Preliminary synchronization difference Sd if: The difference in triggering time between DCSR and DCSL, and between DLSR and DLSL, reflects whether the left and right switches are triggered synchronously.

[0058] In this embodiment, the time between the triggering time of the left and right switches in the normal door opening and closing state can be calculated by diff(DCSR) -T diff(DCSL) 、T diff(DLSR) -T diff(DLSL) The mean Smean and standard deviation Sstd of the difference, and Smean±3*Sstd are used as the evaluation criteria;

[0059] (e) Door opening and closing resistance characteristic difference Rd if during triggering: This characteristic reflects the consistency of the driving torque of the door motor during each switch action.

[0060] In this embodiment, the mean Rmean and standard deviation Rstd of the motor torque (composed of the motor voltage, current, and speed) during each switching action may be calculated, and Rmean±3*Rstd may be used as the evaluation criterion.

[0061] Of course, in other embodiments, the evaluation criteria for the above features can be determined by setting a threshold range, etc. When the difference value exceeds the set value or the set range, the feature is considered abnormal.

[0062] (3) Construct a model for detecting abnormalities in the door closing and locking switches

[0063] Based on Fd if, Od if, Ld if, Sd if, and Rd if, a comprehensive model for detecting abnormalities in the close position and lock position switches is constructed to judge whether the states of the close position switches (DCSR and DCSL) and lock position switches (DLSR and DLSL) are abnormal during the door opening and closing process.

[0064] (2) Construct a model for detecting abnormalities in the door closing and locking switches

[0065] Based on the above features Fd if, Od if, Ld if, Sd if, and Rd if, a comprehensive model for detecting abnormalities in the close position and lock position switches is constructed. This model is used to judge whether the states of the close position switches (DCSR and DCSL) and lock position switches (DLSR and DLSL) are abnormal during the door opening and closing process.

[0066] Specifically, in this embodiment, if any feature exceeds a set threshold / standard, or an anomaly exists, the anomaly detection model determines that an anomaly exists, and records the anomaly and the anomaly feature.

[0067] Of course, in other embodiments, the priority of each feature indicator can also be set. When the priority is higher than the set priority, if any related feature exceeds the set threshold / standard, or there is an anomaly, the model determines that there is an anomaly. When the priority is lower than the set priority, the model determines that there is an anomaly only if more than two features exceed the set threshold / standard, or there is an anomaly.

[0068] It can be changed or set according to the accuracy requirements of anomaly detection, etc.

[0069] Example 2

[0070] A rail vehicle door system lock and close position switch state abnormality detection system includes a communication and data preprocessing module, a switch component abnormality diagnosis module and a data management module, wherein:

[0071] Communication and data preprocessing module: mainly responsible for communicating with the vehicle network system, collecting door-related data, and transmitting it to the switch abnormality diagnosis module.

[0072] The collected parameters include: door motor voltage, current, speed, door position, time and position, DCSL, DCSR, DLSL, DLSR signals, etc.

[0073] Switch component abnormality diagnosis module: responsible for analyzing and processing the collected door-related parameters, calling the closed-position switch and locked-position switch abnormality detection and prediction model to realize the abnormal detection and prediction of the closed-position switch and locked-position switch status of the door.

[0074] Data management module: responsible for storing original data and diagnostic prediction result data, and sending the diagnostic prediction results to the vehicle network system.

[0075] like Figure 1 As shown, the system communicates with the vehicle network and collects parameters such as the door motor voltage, current, speed, position, time, left close position switch DCSL, right close position switch DCSR, left lock position switch DLSL, and right lock position switch DLSR;

[0076] Transmitting relevant parameters to the switch component abnormality diagnosis module via wired or wireless means;

[0077] The switch component abnormality diagnosis module calls the closed position switch and locked position switch abnormality detection and prediction model to detect whether the closed position switch and locked position switch of the vehicle door system are abnormal;

[0078] Push the diagnosis and prediction results, and store and manage the received raw data and processed result data.

[0079] Example 3

[0080] A rail transit vehicle includes the system provided in the second embodiment or adopts the method provided in the first embodiment.

[0081] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0085] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made by those skilled in the art that fall within the spirit and principles of the present invention and do not require creative effort are intended to be within the scope of protection of the present invention.

Claims

1. A method for detecting abnormal switch status of a vehicle door system, characterized in that: The following steps are involved: Obtain door parameters, lock position switch signal, close position switch signal and control signal of the door system; Using the pre-trained anomaly detection and prediction model, the system can predict whether the closed and locked positions of the door system are abnormal based on the acquired information. Storing prediction and judgment results; The process of constructing the anomaly detection and prediction model includes constructing door switch component state evaluation parameters, extracting influencing factors of the evaluation parameters, establishing feature evaluation relationships, and obtaining the anomaly detection and prediction model based on the feature evaluation relationships; The specific process of constructing the door switch component status evaluation parameters includes: selecting the triggering number difference Fdif, triggering sequence difference Odif, triggering position difference Ldif, initial synchronization difference Sdif, and the door opening and closing resistance characteristic difference Rdif when triggered of the closed and locked switches on both sides of the door system as characteristic parameters for evaluating the door switch component status; The specific process of establishing feature judgment relationship includes: 1) Trigger count difference Fdif is used to reflect the difference in the number of actions of each closed and locked switch, to check whether a switch has no action or multiple actions, and whether the action state of each switch changes only once during each door opening or closing process; 2) Trigger sequence differences, used to reflect whether the switch action sequence matches the design mechanism, and to check whether there is a mismatch in the triggering sequence of the vehicle closing and locking positions; 3) Trigger position difference, used to reflect whether each closed position and locked position switch is triggered when the door moves to the normal position; 4) Preliminary synchronization difference, used to indicate whether the closed and locked positions on the left and right sides are triggered synchronously; 5) The difference in the door opening and closing resistance characteristics when triggered is used to reflect the consistency of the door motor's driving torque during each opening and closing action. The driving torque is calculated based on the motor voltage, current, and speed.

2. A method for detecting abnormal switch status of a vehicle door system according to claim 1, characterized in that: The door parameters include the voltage, current and speed of the door motor; the control signal includes the trigger time, door position and control instructions.

3. The method for detecting abnormal switch status of a vehicle door system according to claim 1, wherein: The specific process of extracting the influencing factors of the evaluation parameters includes: extracting the right switch signal of the closed position, the left switch signal of the closed position, the right switch signal of the locked position, the left switch signal of the locked position, the time Time, the door position L, the voltage U, current I and speed V of the door motor, and the control instructions for opening and closing the door.

4. The method for detecting abnormal switch status of a vehicle door system according to claim 1, wherein: Based on the feature evaluation relationship, the specific process of obtaining the anomaly detection and prediction model includes calculating the trigger number difference, trigger position difference, trigger sequence difference, initial synchronization difference and door opening and closing resistance characteristic difference when triggering based on the vehicle door parameters, locked switch signal, closed switch signal and control signal, and making a comprehensive judgment on each feature. When any feature exceeds the set range or an error occurs, the output of the anomaly detection and prediction model is abnormal.

5. A door system switch state abnormality detection system, characterized in that: include: A data acquisition module is configured to acquire door parameters, a lock position switch signal, a close position switch signal, and a control signal of the door system; A switch component abnormality diagnosis module is configured to use a pre-trained abnormality detection and prediction model to predict whether the closed position switch and the locked position switch of the vehicle door system are abnormal based on the acquired information; A data management module is configured to store prediction and judgment results; The process of constructing the anomaly detection and prediction model includes constructing door switch component state evaluation parameters, extracting influencing factors of the evaluation parameters, establishing feature evaluation relationships, and obtaining the anomaly detection and prediction model based on the feature evaluation relationships; The specific process of constructing the door switch component status evaluation parameters includes: selecting the triggering number difference Fdif, triggering sequence difference Odif, triggering position difference Ldif, initial synchronization difference Sdif, and the door opening and closing resistance characteristic difference Rdif when triggered of the closed and locked switches on both sides of the door system as characteristic parameters for evaluating the door switch component status; The specific process of establishing feature judgment relationship includes: 1) Trigger count difference Fdif is used to reflect the difference in the number of actions of each closed and locked switch, to check whether a switch has no action or multiple actions, and whether the action state of each switch changes only once during each door opening or closing process; 2) Trigger sequence differences, used to reflect whether the switch action sequence matches the design mechanism, and to check whether there is a mismatch in the triggering sequence of the vehicle closing and locking positions; 3) Trigger position difference, used to reflect whether each closed position and locked position switch is triggered when the door moves to the normal position; 4) Preliminary synchronization difference, used to indicate whether the closed and locked positions on the left and right sides are triggered synchronously; 5) The difference in the door opening and closing resistance characteristics when triggered is used to reflect the consistency of the door motor's driving torque during each opening and closing action. The driving torque is calculated based on the motor voltage, current, and speed.

6. A vehicle door system switch state abnormality detection system as claimed in claim 5, characterized in that: It also includes a data communication module for connecting to the vehicle network system to obtain the collected door parameters, locked position switch signal, closed position switch signal and control signal.

7. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the steps of the method according to any one of claims 1 to 4 are completed when the computer instructions are executed by the processor.

8. A rail transit vehicle, characterized in that: The device comprises a processor that performs the steps of the method according to any one of claims 1 to 4, or comprises the system according to claims 5 and 6, or comprises the electronic device according to claim 7.

Images