Train system sensor layout method and device, whole train, equipment and medium

Abstract

The invention discloses a train system sensor layout method and device, a whole train, equipment and a medium, and relates to the technical field of computers.The train system sensor layout method comprises the steps that a train system is divided into a plurality of subunits; constructing a symbol directed graph model of each subunit based on the system behavior characteristics under the operation condition; obtaining a system initial symbol directed graph model according to the symbol directed graph model of each subunit; embedding the fault feature information under the operation condition into a system initial symbol directed graph model to obtain a system fault symbol directed graph model; determining a minimum sensor subset covering all target nodes to realize train system sensor layout optimization; the target node is a node used for representing the variable to be monitored in the system fault symbol directed graph model. Therefore, the problem that the number and positions of the sensors in a traditional layout are unreasonable is solved, cost waste caused by excessive redundant installation of the sensors is avoided, and comprehensive collection of the key state information of the train system is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a train system sensor layout method and device, a train whole vehicle, equipment and medium. BACKGROUND

[0002] At present, the sensor layout optimization research of the train brake air supply system is still in its infancy, and the sensor layout design in this field still mainly depends on human experience, continuing the initial setting mode. Specifically, the determination of the number and installation position of the sensors lacks a systematic method, resulting in significant defects in the layout. For example, the unreasonable installation position and improper number configuration of some sensors may not only cause redundancy waste, but also lead to the lack of key monitoring points, directly causing low fault detection rate and the failure to effectively collect necessary state information, thereby making it difficult to achieve accurate perception and fault positioning of the system running state. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a train system sensor layout method, device, train whole vehicle, equipment and medium, which solves the problem of unreasonable number and position of sensors in the traditional layout, avoids the cost waste caused by excessive redundant installation of sensors, and realizes the comprehensive collection of key state information of the train system. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a train system sensor layout method, comprising:

[0005] dividing the train system into a plurality of sub-units;

[0006] constructing a symbolic directed graph model of each sub-unit based on the system behavior characteristics under different operating conditions; wherein the system behavior characteristics represent the behavior characteristics of the train system when different components interact to achieve a preset function under different operating conditions;

[0007] obtaining a system initial symbolic directed graph model according to the symbolic directed graph model of each sub-unit;

[0008] determining the fault feature information under the operating condition, and embedding the fault feature information in the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model;

[0009] determining a minimum sensor subset covering all target nodes according to the monitoring range of each sensor in the sensor set to the target node, so as to realize the optimization of train system sensor layout; wherein the target node is a node in the system fault symbolic directed graph model for representing a to-be-monitored variable.

[0010] Optionally, the dividing the train system into a plurality of sub-units comprises:

[0011] Based on the differences in the roles of the components of the train system in physical structure layout, functional division, and control and signal interaction path, the train system is functionally divided to form a plurality of sub-units with relatively independent monitoring requirements and control boundaries.

[0012] Optionally, the system behavior characteristics include a signal transmission path, a gas transmission path, component control logic, and component response characteristics; wherein the signal transmission path represents the transmission trajectory of signals between components, the gas transmission path represents the flow path of gas between components, the component control logic represents the rules for components to perform actions according to input signals, and the component response characteristics represent the variation law of parameters of components after receiving excitation.

[0013] Optionally, the determining the fault feature information under the operating condition comprises:

[0014] Obtaining a preset fault set under the operating condition, and determining a fault vertex and a fault path under the operating condition according to the preset fault set; wherein the fault vertex is a node representing a fault source, and the fault path represents a propagation path formed by the fault vertex through the connection relationship between components.

[0015] Optionally, the embedding the fault feature information in the initial symbolic directed graph model of the system to obtain a system fault symbolic directed graph model comprises:

[0016] Mapping the fault vertex to the corresponding target node in the initial symbolic directed graph model of the system, so as to establish an association relationship between the fault vertex and the target node;

[0017] Converting the fault path into a directed edge in the initial symbolic directed graph model of the system, which extends from the fault vertex and along the connection relationship between components, to obtain a system fault symbolic directed graph model.

[0018] Optionally, the determining a minimum sensor subset covering all the target nodes according to the monitoring range of each sensor in the sensor set to achieve train system sensor layout optimization comprises:

[0019] Marking each sensor in the sensor set as a candidate state;

[0020] According to the monitoring coverage relationship of each sensor to the target nodes, filtering out the sensor that can cover the most unmonitored target nodes from the sensors currently in the candidate state;

[0021] The screened sensors are marked as selected, and the target nodes covered by the sensors are marked as monitored. The above screening and marking steps are then repeated until all the target nodes are marked as monitored, thereby obtaining the minimum sensor subset.

[0022] Optionally, the process of obtaining the minimum sensor subset further includes:

[0023] A redundancy check is performed on any sensor in the minimum sensor subset. If all target nodes covered by the sensor are already covered by the remaining sensors, the sensor is removed from the subset.

[0024] In a second aspect, the present application discloses a train system sensor layout device, comprising:

[0025] A unit division module, used to divide the train system into multiple sub-units;

[0026] a model construction module for constructing, for different operating conditions, a symbolic directed graph model of each of the subunits based on the system behavior characteristics under the operating conditions; wherein the system behavior characteristics represent the behavior characteristics exhibited by the components of the train system when interacting with each other to achieve preset functions under the different operating conditions;

[0027] A system integration module, configured to obtain an initial symbolic directed graph model of the system according to the symbolic directed graph models of the subunits;

[0028] a fault embedding module, configured to determine fault characteristic information under the operating condition and embed the fault characteristic information into the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model;

[0029] The optimization layout module is used to determine the minimum sensor subset covering all target nodes based on the monitoring range of each sensor in the sensor set to the target node, so as to optimize the sensor layout of the train system; wherein the target node is the node used to represent the variable to be monitored in the directed graph model of the system fault symbol.

[0030] In a third aspect, the present application discloses a complete train, including a train system and a sensor set whose layout is optimized using the aforementioned method disclosed above.

[0031] In a fourth aspect, the present application discloses an electronic device, comprising:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the aforementioned disclosed train system sensor layout method.

[0034] In a fifth aspect, the present application discloses a computer readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the train system sensor layout method disclosed above.

[0035] It can be seen that the present application proposes a train system sensor layout method, which comprises: dividing a train system into a plurality of sub-units; for different operating conditions, constructing a signed directed graph model of each sub-unit based on system behavior characteristics under the operating conditions; wherein the system behavior characteristics represent the behavior characteristics of the train system when different components interact with each other to achieve a preset function under different operating conditions; obtaining a system initial signed directed graph model according to the signed directed graph model of each sub-unit; determining fault feature information under the operating conditions and embedding the fault feature information in the system initial signed directed graph model to obtain a system fault signed directed graph model; determining a minimum sensor subset covering all target nodes according to the monitoring range of each sensor in the sensor set to the target nodes, so as to realize train system sensor layout optimization; wherein the target nodes are nodes in the system fault signed directed graph model for representing variables to be monitored. It can be seen from the above that the present application first divides the train system into a plurality of sub-units, and constructs a signed directed graph model of each sub-unit based on system behavior characteristics under different operating conditions, then combines the signed directed graph model of each sub-unit to obtain a system initial signed directed graph model, and embeds fault feature information under the operating conditions in the system initial signed directed graph model to obtain a system fault signed directed graph model, so that the sensor layout is changed from the traditional experience-dependent mode to a scientific modeling method based on system behavior characteristics and fault feature information. Further, since the system fault signed directed graph model embeds fault characteristic information, the system fault signed directed graph model can accurately reflect the propagation path and influence range of the train system when a fault occurs under different operating conditions, further enabling the sensor layout to cover key fault nodes, solving the problem of unreasonable number and position of sensors caused by relying on human experience in traditional layout, thereby improving the fault detection rate. In addition, by determining the minimum sensor subset covering all target nodes, the cost waste caused by excessive redundant installation of sensors is avoided, so that the present application can realize comprehensive collection of key state information of the train system with the least number of sensors. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute a part of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0037] Figure 1 A train system sensor layout method flow chart disclosed by the present application;

[0038] Figure 2 A specific train system sensor layout method flow chart disclosed by the present application;

[0039] Figure 3 A specific train system sensor layout method flow chart disclosed by the present application;

[0040] Figure 4 A train system sensor layout device structure schematic diagram disclosed by the present application;

[0041] Figure 5 An electronic equipment structure diagram disclosed by the present application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0043] At present, the sensor layout optimization research of the train brake air supply system is still in the initial stage, and the sensor layout design in this field still mainly depends on human experience, continuing the initial setting mode. Specifically, the determination of the number and installation position of the sensors lacks a systematic method, resulting in significant defects in the layout. For example, the unreasonable installation position and improper number configuration of some sensors may cause waste of redundancy, and may also lead to the lack of key monitoring points, directly causing low fault detection rate, and the problem that necessary state information is not effectively collected, thereby making it difficult to realize accurate perception and fault positioning of the system running state.

[0044] Therefore, the embodiments of the present application propose a train system sensor layout scheme, which solves the problem of unreasonable number and position of sensors in the traditional layout, avoids the cost waste caused by excessive redundant installation of sensors, and realizes comprehensive collection of key state information of the train system.

[0045] The embodiment of the application discloses a train system sensor layout method, referring to Figure 1 as shown, comprising:

[0046] Step S11: dividing the train system into multiple sub-units.

[0047] In the embodiment, the train system is divided into multiple sub-units based on the architecture function of the train system. Specifically, based on the differences in the roles of each component of the train system in physical structure layout, functional division, and control and signal interaction path, the train system is functionally divided into multiple sub-units with relatively independent monitoring requirements and control boundaries. Taking the train brake air supply system as an example, according to the division principle of the physical structure and functional modules of the system, the system is divided into three core sub-units: air supply and air suspension unit, brake control and execution unit, and parking brake unit. Among them, the air supply and air suspension unit is used to provide air source for the brake system and adjust the suspension state, the brake control and execution unit is used to receive and execute brake instructions, and the parking brake unit realizes brake holding when the vehicle is parked to ensure the safety of the vehicle when it is stationary. From the perspective of physical structure layout, the air supply and air suspension unit integrates air supply equipment and air springs and other suspension devices, the brake control and execution unit contains physical components such as electro-pneumatic conversion valve and relay valve, and the parking brake unit is composed of independent structures such as parking brake cylinder; from the perspective of functional division, the air supply and air suspension unit is responsible for supplying compressed air to the brake system and adjusting the suspension state of the vehicle, the brake control and execution unit undertakes the function of receiving brake instructions and realizing brake execution through air pressure conversion, and the parking brake unit only executes the brake holding task when the vehicle is parked; from the perspective of control and signal interaction path, the air supply and air suspension unit exists in the air pressure transmission path (such as compressed air from the air compressor to the total air cylinder), the brake control and execution unit involves the conversion path of electrical signal to air pressure signal, and the parking brake unit realizes the holding of the brake state through mechanical linkage and electrical control. This division method based on physical structure, functional division and path role difference can disassemble the complex train system into sub-units with independent monitoring requirements, so that the application can be modeled and analyzed for each unit, thereby improving the accuracy of sensor layout.

[0048] Step S12: for different operating conditions, based on the system behavior characteristics under the operating conditions, a symbolic directed graph model of each sub-unit is constructed; wherein the system behavior characteristics represent the behavior characteristics of the train system when interacting between components to achieve the preset function under different operating conditions.

[0049] For different operating conditions, the signed directed graph model of each sub-unit is constructed based on the system behavior characteristics under the operating condition. The system behavior characteristics include signal transmission path, gas pressure transmission path, component control logic and component response characteristics. The signal transmission path represents the transmission trajectory of the signal between components, the gas pressure transmission path represents the flow path of the gas between components, the component control logic represents the rules of the component action according to the input signal, and the component response characteristics represent the variation law of the parameter of the component after receiving the excitation. Specifically, for different operating conditions, the components involved in the implementation of the function in the sub-unit are different, so there are differences in the construction of the signed directed graph (SDG) model of the sub-unit. Taking the train brake air supply system as an example, assuming that the operating conditions include normal braking and emergency braking, the target nodes (variable nodes, i.e. nodes corresponding to the monitored variables) of the SDG model of the sub-unit need to be adjusted according to the system behavior characteristics (signal transmission path, gas pressure transmission path, component control logic and component response characteristics) under different operating conditions. The monitored variables include electric air valve current, sensor reading, etc.

[0050] For normal braking, the brake control unit generates a command signal by calculation and transmits it to the electric air valve, which generates a pre-control pressure value CV1 according to the command signal and transmits it to the relay valve. The relay valve amplifies the flow of compressed air and transmits it to the brake cylinder, thereby ensuring the smoothness and stability of the braking process. Therefore, for normal braking, the variable nodes of the sub-unit SDG model are nodes related to the monitored variables such as electric air valve current and pre-control pressure value CV1 that implement the operating condition function.

[0051] For emergency braking, the loss of power of the emergency electromagnetic valve triggers the activation of the pneumatic passage, forming a communication path between the air-heavy valve and the relay valve. The air-heavy valve generates a final control pressure CV2 based on the load pressure feedback of the air suspension device, and transmits the final control pressure CV2 to the relay valve. Then, through the flow amplification effect of the relay valve, the brake cylinder is driven to perform emergency braking. Therefore, for emergency braking, the variable nodes of the brake control unit SDG model are nodes related to the monitored variables such as air suspension pressure, air-heavy valve output pressure, emergency electromagnetic valve state, etc. that are deeply coupled with the operating condition function.

[0052] In summary, when constructing the subunit SDG model, the variable nodes need to be dynamically adjusted according to the system behavior characteristics of different operating conditions, and the core basis includes: the signal transmission path under the operating condition (such as the transmission trajectory of the electric signal between the brake control unit and the electric air conversion valve), the control logic (such as the air path rule triggered by the electromagnetic valve power failure in emergency braking), the air pressure transmission path (such as the flow characteristics of compressed air from the relay valve to the brake cylinder), and the response characteristics of the key components (such as the mapping relationship between the electric air conversion valve current and the pre-control pressure). By analyzing the causal transmission chain of signals and pressures under each operating condition, combined with the working state of the core components (such as the electric air conversion valve, the light-heavy valve) in different modes (such as electric-gas conversion in normal braking, pure pneumatic response in emergency braking), the key variables affecting the function realization of the operating condition can be accurately identified. Thus, the subunit SDG model can reflect the behavior characteristics of the system under different operating modes, thereby improving the adaptability of the model to complex conditions and the accuracy of fault diagnosis.

[0053] Step S13: obtaining a system initial signed directed graph model according to the signed directed graph model of each subunit.

[0054] After obtaining the signed directed graph model of each subunit, the system initial signed directed graph model is obtained by combining the signed directed graph model of each subunit to obtain the system initial signed directed graph model.

[0055] Step S14: determining the fault feature information under the operating condition, and embedding the fault feature information in the system initial signed directed graph model to obtain a system fault signed directed graph model.

[0056] In this embodiment, the fault feature information under the operating condition is determined, including: obtaining a preset fault set under the operating condition, and determining a fault vertex and a fault path under the operating condition according to the preset fault set; wherein the fault vertex is a node representing a fault source, and the fault path represents a propagation path formed by the connection relationship between components. Further, the fault feature information is embedded in the system initial signed directed graph model to obtain a system fault signed directed graph model, including: mapping the fault vertex to the corresponding target node in the system initial signed directed graph model, so as to establish an association relationship between the fault vertex and the target node; and converting the fault path into a directed edge in the system initial signed directed graph model, which extends from the fault vertex and along the component connection relationship, to obtain a system fault signed directed graph model.

[0057] It should be noted that the preset fault set in the running condition includes historical typical faults in the running condition. It can be understood that, since the historical typical faults reflect the historical fault distribution of the system in the running condition, the fault vertex (i.e. the fault source node) determined based on the historical typical faults can correspond to the high-frequency fault components or parameters in the actual running, and the construction of the fault path is based on the physical connection relationship and the control logic between components, clearly presenting the propagation trajectory of the fault from the source node to other components. In this way, the model can not only effectively cover the main fault scenarios in the target condition, but also provide real and reliable fault propagation logic support for subsequent model-based fault observability analysis.

[0058] Step S15: determining a minimum sensor subset covering all the target nodes according to the monitoring range of each sensor in the sensor set to the target nodes, so as to realize train system sensor layout optimization; the target node is a node representing a to-be-monitored variable in the system fault symbol directed graph model.

[0059] In the embodiment, different sensors have different monitoring ranges for the target nodes, for example, a current sensor is used to monitor the target nodes such as an electric air conversion valve, and a pressure sensor is used to monitor the target nodes such as brake cylinder pressure and total air cylinder pressure. By using a minimum observation set algorithm based on a greedy strategy, a minimum sensor subset covering all the target nodes is determined from the sensor set in combination with the monitoring range of each sensor in the sensor set to the target nodes, so as to realize train system sensor layout optimization.

[0060] It can be seen that the present application proposes a train system sensor layout method, comprising: dividing the train system into a plurality of sub-units; for different operating conditions, constructing a symbolic directed graph model of each sub-unit based on the system behavior characteristics under the operating condition; wherein the system behavior characteristics represent the behavior characteristics of the train system under different operating conditions when each component interacts to achieve the preset function; obtaining a system initial symbolic directed graph model according to the symbolic directed graph model of each sub-unit; determining the fault feature information under the operating condition, and embedding the fault feature information in the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model; determining a minimum sensor subset covering all target nodes according to the monitoring range of each sensor in the sensor set to the target node, so as to realize train system sensor layout optimization; wherein the target node is a node in the system fault symbolic directed graph model for representing a to-be-monitored variable. As can be seen from the above, the present application first divides the train system into a plurality of sub-units, and constructs a symbolic directed graph model of each sub-unit based on the system behavior characteristics under different operating conditions, then combines the symbolic directed graph model of each sub-unit to obtain a system initial symbolic directed graph model, and embeds the fault feature information under the operating condition in the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model, so that the sensor layout is changed from the traditional experience-dependent mode to a scientific modeling method based on system behavior characteristics and fault feature information. Further, since the system fault symbolic directed graph model embeds the fault characteristic information, the system fault symbolic directed graph model can accurately reflect the propagation path and influence range of the train system under different operating conditions when a fault occurs, further enabling the sensor layout to cover the key nodes of the fault, solving the problem of unreasonable sensor quantity and position caused by relying on human experience in the traditional layout, thereby improving the fault detection rate. In addition, by determining the minimum sensor subset covering all target nodes, the cost waste caused by excessive redundant installation of sensors is avoided, so that the present application can realize comprehensive collection of key state information of the train system with the least number of sensors.

[0061] The embodiment of the present application discloses a specific train system sensor layout method. Compared with the previous embodiment, the step S15 is further described and optimized in the present embodiment. Referring to Figure 2 as shown, comprising:

[0062] Step S151: marking each sensor in the sensor set as a candidate state.

[0063] Step S152: according to the monitoring coverage relationship of each sensor to the target node, screening out the sensor that can cover the most unmonitored target nodes from the sensors currently in the candidate state.

[0064] Step S153: mark the selected sensor as selected state, and mark the target nodes covered by the sensor as monitored state, then repeat the above filtering and marking step until all the target nodes are marked as monitored state, and get the minimum sensor subset.

[0065] That is, first mark all the sensors in the sensor set as unselected state, and according to their monitoring coverage relationship with the target nodes, each time pick out the sensor that can cover the most unmonitored target nodes from the unselected sensors, and mark it as selected state, and mark the target nodes covered by the sensor as monitored state, then loop this step until all the target nodes are in the monitored state, and get the minimum sensor subset.

[0066] Figure 3 The algorithm flow is an attempt to determine the minimum sensor subset based on the greedy strategy, so as to realize the comprehensive monitoring of the target nodes. After the flow starts, first input the bipartite graph representing the relationship between the sensors and the target nodes (obtained according to the monitoring coverage relationship of each sensor with the target nodes), and the edges in the graph represent that the sensor can monitor the corresponding target node. Then, initialize the counter i=0, i is used to record the number of selected sensors. Then, select the sensor that is not marked and has the most unmarked edges (i.e. can monitor the most unmonitored target nodes), and mark it as selected state, and i=i+1. Then, mark all the target nodes that can be monitored by the sensor as monitored state. At this time, judge whether there are still unmonitored target nodes. If there are, delete the edges of the monitored target nodes pointing to the selected state sensor (indicating that these target nodes have been monitored, and there is no need to consider these connections), mark the edges of the monitored target nodes pointing to the unselected state sensor (which may need to be adjusted later), and then return to continue selecting the sensor; if not, check whether there are sensors without edges (i.e. cannot monitor any unmonitored target nodes). If there are, select and remove the mark of the sensor (i.e. do not select it into the final subset), i=i-1, and continue to check; if not, output the value of the counter i and all the marked (selected) sensors, and the flow ends.

[0067] In the embodiment, in the process of obtaining the minimum sensor subset, redundancy judgment is further performed on any sensor in the minimum sensor subset, and if all the target nodes covered by the sensor have been covered by the remaining sensors, the sensor is removed from the subset. Specifically, for any sensor in the minimum sensor subset, it is checked whether the target nodes covered by the sensor have been covered by other sensors; if the target nodes covered by the sensor have been covered by the other sensors, the sensor is removed from the minimum sensor subset. In this way, unnecessary hardware resources are reduced, and layout cost and system complexity are reduced.

[0068] Taking the sensor layout optimization of the brake air supply system of the CR400AF motor train unit as an example, two working conditions of normal braking and emergency braking are considered. First, the brake air supply system is divided into three sub-units of air supply and air suspension modules, brake control and execution modules, and parking brake modules, and a symbolic directed graph model of each sub-unit is constructed, and then the SDG model of the brake air supply system under the normal braking working condition and the emergency braking working condition is formed. Based on the greedy algorithm, the sensor layout scheme considering fault observability and fault distinguishability under the normal braking working condition and the emergency braking working condition is solved, and finally the final sensor layout scheme is determined. Specifically, the SDG observability algorithm (an algorithm based on a symbolic directed graph model for judging whether a sensor can monitor all fault vertices in the system) is used to determine that pressure sensors are arranged at nine places of the total air pressure, the auxiliary air cylinder pressure, the overflow valve output pressure, the pressure reducing valve output pressure, the bidirectional valve output, and the four axle brake cylinders; the SDG distinguishability algorithm (an algorithm for further judging whether a sensor layout can distinguish different fault paths or similar fault types on the basis of observability) is used to determine that pressure sensors are arranged at fifteen places of the emergency electromagnetic valve front and rear ends, the electric air conversion valve output, the air suspension pressure, the parking pressure reducing valve output end, the overflow valve output end, the pressure reducing valve output end, the double-pulse electromagnetic valve rear end, the bidirectional valve rear end, the total air pressure, the auxiliary air cylinder pressure, and the four axle brake cylinders. After the sensor layout is optimized by the SDG distinguishability algorithm, the fault observability rate is improved by about 16.28%, and the fault distinguishability rate is improved by about 37.21%.

[0069] Correspondingly, the embodiment of the application further discloses a train system sensor layout device, as shown in Figure 4 The device comprises:

[0070] A unit division module 11 is configured to divide the train system into a plurality of sub-units.

[0071] The model construction module 12 is configured to construct a symbolic directed graph model of each of the sub-units based on system behavior characteristics under different operating conditions, wherein the system behavior characteristics represent behaviors of the train system under different operating conditions when components interact with each other to achieve a preset function.

[0072] The system integration module 13 is configured to obtain a system initial symbolic directed graph model according to the symbolic directed graph models of the sub-units.

[0073] The fault embedding module 14 is configured to determine fault feature information under the operating conditions, and embed the fault feature information in the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model.

[0074] The optimization layout module 15 is configured to determine a minimum sensor subset covering all target nodes according to monitoring ranges of each sensor in a sensor set on the target nodes, so as to achieve train system sensor layout optimization, wherein the target nodes are nodes in the system fault symbolic directed graph model for representing variables to be monitored.

[0075] The above-mentioned modules can refer to the corresponding content disclosed in the foregoing embodiments for more specific working processes, which will not be described here again.

[0076] It can be seen that the application provides a train system sensor layout method, which comprises the following steps: dividing a train system into a plurality of sub-units; constructing a symbolic directed graph model of each sub-unit based on system behavior characteristics under different operating conditions; wherein the system behavior characteristics represent the behavior characteristics of the train system when different components interact with each other to achieve a preset function under different operating conditions; obtaining a system initial symbolic directed graph model according to the symbolic directed graph model of each sub-unit; determining fault feature information under the operating conditions, and embedding the fault feature information in the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model; determining a minimum sensor subset covering all target nodes according to the monitoring range of each sensor in a sensor set to the target nodes, so as to realize train system sensor layout optimization; wherein the target nodes are nodes in the system fault symbolic directed graph model for representing variables to be monitored. As can be seen from the above, the train system is first divided into a plurality of sub-units, and the symbolic directed graph model of each sub-unit is constructed based on the system behavior characteristics under different operating conditions, then the symbolic directed graph models of the sub-units are combined to obtain a system initial symbolic directed graph model, and the fault feature information under the operating conditions is embedded in the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model, so that the sensor layout is changed from the traditional experience-dependent mode to a scientific modeling method based on system behavior characteristics and fault feature information. Further, since the system fault symbolic directed graph model embeds fault characteristic information, the system fault symbolic directed graph model can accurately reflect the propagation path and influence range of the train system under different operating conditions when a fault occurs, further enabling the sensor layout to cover the key nodes of the fault, solving the problem of unreasonable number and position of sensors caused by relying on human experience in the traditional layout, thereby improving the fault detection rate. In addition, by determining the minimum sensor subset covering all target nodes, the cost waste caused by excessive redundant installation of sensors is avoided, so that the application can realize comprehensive collection of key state information of the train system with the least number of sensors.

[0077] Further, the application embodiment also provides a train vehicle, which comprises a train system and a sensor set optimized by the method disclosed above.

[0078] Further, the application embodiment also provides an electronic device. Figure 5 FIG. 1 is a structural diagram of an electronic device 20 according to an exemplary embodiment, and the content in the figure should not be considered as any limitation on the use range of the application.

[0079] Figure 5A structural schematic diagram of an electronic device 20 is provided in the embodiments of the present application. The electronic device 20 can specifically include at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26 and a communication bus 27. The memory 22 is configured to store a computer program, and the processor 21 is configured to load and execute the computer program to implement the related steps in the train system sensor layout method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the embodiments of the present application can be specifically an electronic computer.

[0080] In the embodiments of the present application, the power supply 26 is configured to provide working voltage for each hardware device on the electronic device 20, the communication interface 25 is capable of creating a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 25 can be any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein. The input / output interface 24 is configured to obtain external input data or output data to the outside, and the specific interface type can be selected according to the specific application needs, which is not specifically limited herein.

[0081] In addition, the memory 22 as a carrier for resource storage can be a read-only memory, a random access memory, a magnetic disk or an optical disk, and the resources stored thereon can include a computer program 221, and the storage mode can be temporary storage or permanent storage. In addition to the computer program capable of completing the train system sensor layout method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 221 can further include a computer program capable of completing other specific work.

[0082] Further, the embodiments of the present application further disclose a computer readable storage medium for storing a computer program, wherein the computer program is executed by a processor to implement the train system sensor layout method disclosed above.

[0083] The specific steps of the method can refer to the corresponding contents disclosed in the foregoing embodiments, which will not be repeated here.

[0084] The embodiments in the present application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts of each embodiment can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can refer to the method part.

[0085] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality, without referring to a specific sequence of operations for implementing the functions. The order of various illustrative blocks, modules, circuits, and steps may be re-arranged or otherwise implemented without departing from the spirit of the application, which is defined by the appended claims.

[0086] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0087] Finally, it should be noted that the terms "first", "second", and the like, herein do not denote any order, quantity, combination, or importance, but rather are used to distinguish one element from another, and are more especially used for the purpose of distinction from other elements in the specification. Also, the terms "comprise", "include" or "contain" or any other variant thereof are intended to encompass non-exclusive inclusions, such that processes, methods, articles, or apparatuses that comprise, include, or contain a list of elements are not limited to those elements, but can include other elements not expressly listed or inherent to such processes, methods, articles, or apparatuses. Without further limitation, an element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0088] The above provides a train system sensor layout method, device, train, equipment and medium, the principle and implementation mode of the application are described in the text by applying specific examples, the above example is only used to help understand the method and core idea of the application; At the same time, for those skilled in the art, according to the idea of the application, the specific implementation mode and application range will be changed; In view of the above, the content of the specification should not be understood as the limitation of the application.

Claims

1. A train system sensor layout method, characterized in that: include: Divide the train system into multiple subunits; For different operating conditions, based on the system behavior characteristics under the operating conditions, a symbolic directed graph model of each subunit is constructed; wherein the system behavior characteristics represent the behavior characteristics exhibited by the components of the train system when interacting with each other to achieve preset functions under the different operating conditions; Obtaining an initial symbolic directed graph model of the system according to the symbolic directed graph model of each of the subunits; Determining fault characteristic information under the operating condition, and embedding the fault characteristic information into the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model; Based on the monitoring range of each sensor in the sensor set on the target node, a minimum sensor subset covering all the target nodes is determined to achieve sensor layout optimization of the train system; wherein, the target node is a node used to represent the variable to be monitored in the system fault symbol directed graph model.

2. The train system sensor layout method according to claim 1, characterized in that: The train system is divided into multiple sub-units, including: Based on the differences in the physical structure layout, functional division, and control and signal interaction paths of the various components of the train system, the train system is divided into functional areas to form multiple sub-units with relatively independent monitoring requirements and control boundaries.

3. The train system sensor layout method according to claim 1, characterized in that: The system behavior characteristics include signal transmission path, air pressure transmission path, component control logic and component response characteristics; wherein, the signal transmission path represents the transmission trajectory of the signal between components, the air pressure transmission path represents the flow path of the gas between components, the component control logic represents the rules for the component to perform actions based on the input signal, and the component response characteristics represent the change rules of the parameters after the component receives stimulation.

4. The train system sensor layout method according to claim 1, characterized in that: The determining of the fault characteristic information under the operating condition includes: Obtain a preset fault set under the operating condition, and determine the fault vertex and fault path under the operating condition based on the preset fault set; wherein the fault vertex is a node representing the source of the fault, and the fault path represents a propagation path formed by the fault vertex through the connection relationship between components.

5. The train system sensor layout method according to claim 4, characterized in that: The method of embedding the fault feature information in the system initial symbol directed graph model to obtain a system fault symbol directed graph model includes: Mapping the fault vertex to the corresponding target node in the system initial symbolic directed graph model, so as to establish an association relationship between the fault vertex and the target node; The fault path is converted into a directed edge in the system initial symbolic directed graph model, starting from the fault vertex and extending along the component connection relationship, so as to obtain a system fault symbolic directed graph model.

6. The train system sensor layout method according to any one of claims 1 to 5, characterized in that: The step of determining a minimum sensor subset covering all target nodes based on the monitoring range of each sensor in the sensor set to the target node, so as to optimize the sensor layout of the train system, includes: Marking each sensor in the sensor set as a pending state; According to the monitoring coverage relationship of each sensor on the target node, the sensor that can cover the most unmonitored target nodes is selected from the sensors currently in the waiting state; The screened sensors are marked as selected, and the target nodes covered by the sensors are marked as monitored. The above screening and marking steps are then repeated until all the target nodes are marked as monitored, thereby obtaining the minimum sensor subset.

7. The train system sensor layout method according to claim 6, characterized in that: The process of obtaining the minimum sensor subset further includes: A redundancy check is performed on any sensor in the minimum sensor subset. If all target nodes covered by the sensor are already covered by the remaining sensors, the sensor is removed from the subset.

8. A train system sensor layout device, characterized in that: include: A unit division module, used to divide the train system into multiple sub-units; a model construction module for constructing, for different operating conditions, a symbolic directed graph model of each of the subunits based on the system behavior characteristics under the operating conditions; wherein the system behavior characteristics represent the behavior characteristics exhibited by the components of the train system when interacting with each other to achieve preset functions under the different operating conditions; A system integration module, configured to obtain an initial symbolic directed graph model of the system according to the symbolic directed graph models of the subunits; a fault embedding module, configured to determine fault characteristic information under the operating condition and embed the fault characteristic information into the system initial symbolic directed graph model to obtain a system fault symbolic directed graph model; The optimization layout module is used to determine the minimum sensor subset covering all target nodes based on the monitoring range of each sensor in the sensor set to the target node, so as to optimize the sensor layout of the train system; wherein the target node is the node used to represent the variable to be monitored in the directed graph model of the system fault symbol.

9. A complete train, characterized in that: The invention comprises a train system and a sensor set whose layout is optimized by the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the train system sensor layout method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that Used to store a computer program; wherein, when the computer program is executed by a processor, the train system sensor layout method according to any one of claims 1 to 7 is implemented.

Images