Vehicle risk assessment method, storage medium and device

Abstract

The present disclosure relates to a vehicle risk assessment method, storage medium and device to improve the efficiency of vehicle risk assessment. The method comprises: obtaining a target assessment index of a target vehicle; determining the safety level corresponding to the target assessment index according to the correspondence between the preset assessment index and the safety level; determining the target risk type information of the target vehicle according to the safety level corresponding to the target assessment index and a preset risk assessment model, wherein the risk assessment model is a PSO-SVR model.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle safety technology, and in particular, to a vehicle risk assessment method, storage medium and device. Background Art

[0002] Rail transit is a mode of transportation in the transportation industry, with a large number of operating equipment of various types. In order to ensure the safety of passengers, trains and operating service personnel, it is crucial to adopt an effective safety risk assessment method and pre-analyze factors that may cause harm.

[0003] At present, the rail transit safety risk assessment method is mainly based on the risk assessment model built by GA-BP neural network. However, due to the numerous risk factors affecting rail transit safety, the risk assessment model built by GA-BP neural network requires a large amount of sample data for model training. If the sample data is insufficient, the assessment results of the risk assessment model will be inaccurate, which will further affect the safe operation of rail transit. Summary of the invention

[0004] The purpose of the present disclosure is to provide a vehicle risk assessment method, storage medium and device to solve the problem that the safety risk assessment method in the related art requires a large amount of sample data.

[0005] In order to achieve the above object, a first aspect of the present disclosure provides a vehicle risk assessment method, the method comprising:

[0006] Obtain target evaluation indicators for the target vehicle;

[0007] Determine the security level corresponding to the target evaluation indicator according to the corresponding relationship between the preset evaluation indicator and the security level;

[0008] The target risk type information of the target vehicle is determined according to the safety level corresponding to the target evaluation index and a preset risk evaluation model, wherein the risk evaluation model is a PSO-SVR model.

[0009] Optionally, the target evaluation index includes at least one of the following: an operating status index of the target vehicle, an operating environment index of the target vehicle, and a staff status index of the target vehicle.

[0010] Optionally, the operating status indicator of the target vehicle includes at least one of the following: data for characterizing the state of a speed pulse device, data for characterizing the state of a control system, data for characterizing the state of a transponder message transmission module, self-test data for characterizing the state of any system of the vehicle, the number of wheel spins, data for characterizing the state of a door, battery power, and data for characterizing the impact of a fire.

[0011] Optionally, determining the security level corresponding to the target evaluation indicator according to the correspondence between the preset evaluation indicator and the security level includes:

[0012] For the indicators of the data used to characterize the state of the speed pulse device, the data used to characterize the state of the control system, the data used to characterize the state of the transponder message transmission module, and the self-test data used to characterize the state of any system of the vehicle, the safety level corresponding to the indicator of the object characterized by failure is determined as the first safety level, and the safety level corresponding to the indicator of the object characterized by no failure is determined as the second safety level, and the safety guaranteed by the second safety level is higher than the safety guaranteed by the first safety level;

[0013] Determining the safety level corresponding to the number of wheel idling times according to the corresponding relationship between the preset evaluation index and the safety level, wherein the safety level corresponding to the number of wheel idling times is negatively correlated with the number of wheel idling times;

[0014] Determining the security level corresponding to the data used to characterize the door state according to the correspondence between the preset evaluation index and the security level, the door state including: normal door state, isolated door state, bypass door state, offline door state and faulty door state, and the security level corresponding to each state decreases in sequence;

[0015] Determine the safety level corresponding to the battery power according to the corresponding relationship between the preset evaluation index and the safety level, wherein the safety level corresponding to the battery power is positively correlated with the battery power;

[0016] The safety level corresponding to the data used to characterize the fire impact is determined according to the corresponding relationship between the preset evaluation index and the safety level, and the safety level corresponding to the data used to characterize the fire impact is negatively correlated with the fire impact.

[0017] Optionally, when the operating route of the target vehicle includes multiple operating intervals, obtaining the target evaluation index of the target vehicle includes obtaining multiple interval target evaluation indicators corresponding to the multiple operating intervals of the target vehicle; the interval target evaluation indicators include at least one of the following: an operating status index of the target vehicle, an operating environment index of the target vehicle, and a staff status index of the target vehicle; determining the safety level corresponding to the target evaluation index according to the correspondence between the preset evaluation index and the safety level includes: determining the safety level corresponding to each of the multiple interval target evaluation indicators according to the correspondence between the preset evaluation index and the safety level, and determining the safety level corresponding to the target evaluation indicator according to the multiple safety levels.

[0018] Optionally, the operating environment index of the target vehicle includes at least one of the following: road foreign object detection data, abnormal road occupancy data and climate data.

[0019] Optionally, the worker status indicator of the target vehicle includes at least one of the following: data for characterizing the fatigue state of the worker and data for characterizing the professional ability of the worker.

[0020] Optionally, the method further comprises:

[0021] After determining the target risk type information of the target vehicle, prompt information is generated according to the target risk type information.

[0022] The second aspect of the present disclosure further provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect above.

[0023] A third aspect of the present disclosure further provides a vehicle risk assessment device, comprising:

[0024] a memory having a computer program stored thereon;

[0025] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods described in the first aspect above.

[0026] Through the above technical solution, at least the following technical effects can be achieved:

[0027] By obtaining the target evaluation index of the target vehicle, and then determining the safety level corresponding to the target evaluation index according to the correspondence between the preset evaluation index and the safety level, and finally determining the target risk type information of the target vehicle according to the safety level corresponding to the target evaluation index and the preset risk assessment model, the risk assessment model is the PSO-SVR model. Since the PSO-SVR model can use a small amount of sample data for model training, it can obtain a risk assessment model that meets the accuracy requirements through model training when the sample data is insufficient, thereby improving the efficiency of vehicle risk assessment. In addition, through the trained risk assessment model, the risk assessment of the vehicle can be performed, thereby ensuring the safe operation of the vehicle.

[0028] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0030] Figure 1 is a flow chart of a vehicle risk assessment method provided by an embodiment of the present disclosure;

[0031] Figure 2 It is a schematic diagram of a vehicle risk assessment device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0033] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0034] It should be understood that the various steps described in the method implementation of the present disclosure may be performed in different orders and / or in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect. The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below.

[0035] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0036] Rail transit is a mode of transportation in the transportation industry, with a large number of operating equipment of various types. In order to ensure the safety of passengers, trains and operating service personnel, it is crucial to adopt an effective safety risk assessment method and pre-analyze factors that may cause harm.

[0037] At present, the selection of evaluation indicators for rail transit safety risk assessment methods is mainly based on the scenario of manned trains. However, due to the different operating rules and evaluation methods of manned trains and unmanned trains, the evaluation indicators of unmanned trains and the quantification methods of indicators are inconsistent. For example, manned trains need to evaluate the driver, while unmanned trains do not have a driver.

[0038] In addition, in the related technologies, the rail transit safety risk assessment method is mainly based on the risk assessment model built by the GA-BP neural network for risk assessment. However, due to the numerous risk factors that affect rail transit safety, the risk assessment model built by the GA-BP neural network requires a large amount of sample data for model training. If the sample data is insufficient, the assessment results of the risk assessment model will be inaccurate, and further affect the safe operation of rail transit.

[0039] In view of this, the present disclosure provides a vehicle risk assessment method, storage medium and device to solve the above technical problems.

[0040] Before describing the technical solution of the present invention in detail, the application scenarios of the technical solution of the present invention are described below.

[0041] The vehicle risk assessment method provided in the embodiments of the present disclosure can be applied to rail transit scenarios with drivers or to rail transit scenarios with unmanned trains. The present disclosure is illustrated by taking the rail transit scenario applied to unmanned trains as an example. In the present disclosure, the assessment indicators set for unmanned trains are set based on the research and analysis of the operating characteristics, operating rules, risk factors affecting operating safety of unmanned trains, and the experience of relevant practitioners.

[0042] The technical solution of the present disclosure is described in detail below with reference to embodiments.

[0043] The present disclosure provides a method for assessing vehicle risk. Figure 1 As shown, the method includes:

[0044] S101, obtaining target evaluation indicators of a target vehicle.

[0045] S102: Determine the security level corresponding to the target evaluation indicator according to the corresponding relationship between the preset evaluation indicator and the security level.

[0046] S103. Determine target risk type information of the target vehicle according to the safety level corresponding to the target evaluation index and a preset risk evaluation model, wherein the risk evaluation model is a PSO (Partical Swarm Optimization)-SVR (Support Vector Machine) model.

[0047] By adopting the above method, the target evaluation index of the target vehicle is obtained, and then the safety level corresponding to the target evaluation index is determined according to the corresponding relationship between the preset evaluation index and the safety level. Finally, the target risk type information of the target vehicle is determined according to the safety level corresponding to the target evaluation index and the preset risk assessment model, wherein the risk assessment model is the PSO-SVR model. Since the PSO-SVR model can use a small amount of sample data for model training, it can obtain a risk assessment model that meets the accuracy requirements through model training when the sample data is insufficient, thereby improving the efficiency of vehicle risk assessment. In addition, through the trained risk assessment model, the risk assessment of the vehicle can be performed, thereby ensuring the safe operation of the vehicle.

[0048] In order to enable those skilled in the art to better understand the vehicle risk assessment method provided by the present disclosure, the above steps are described in detail with examples below.

[0049] In a possible manner, the target evaluation index includes at least one of the following: an operating state index of the target vehicle, an operating environment index of the target vehicle, and a staff state index of the target vehicle.

[0050] For example, based on the operation characteristics, operation rules, research and analysis of risk factors affecting operation safety of unmanned trains and the experience of relevant practitioners, selecting evaluation indicators from the operation status of the vehicle, the operation environment of the vehicle and the status of the vehicle's staff can more comprehensively evaluate the safety risks of the vehicle. It should be understood that in actual applications, the evaluation indicators can also include more or fewer categories of indicators according to actual demand targets, and this disclosure does not specifically limit this.

[0051] In a possible manner, the operating status indicator of the target vehicle includes at least one of the following: data for characterizing the status of a speed pulse device, data for characterizing the status of a control system, data for characterizing the status of a transponder message transmission module, self-test data for characterizing the status of any system of the vehicle, the number of wheel spins, data for characterizing the status of a door, battery power, and data for characterizing the impact of a fire.

[0052] In a possible manner, according to the correspondence between the preset evaluation index and the safety level, the safety level corresponding to the target evaluation index can be determined as follows: for the indexes of data used to characterize the state of the speed pulse device, data used to characterize the state of the control system, data used to characterize the state of the transponder message transmission module, and self-test data used to characterize the state of any system of the vehicle, the safety level corresponding to the index of the object characterized by the failure is determined as the first safety level, and the safety level corresponding to the index of the object characterized by the failure is determined as the second safety level, and the safety guaranteed by the second safety level is higher than the safety guaranteed by the first safety level. The safety level corresponding to the number of wheel idling is determined according to the correspondence between the preset evaluation index and the safety level, wherein the safety level corresponding to the number of wheel idling is negatively correlated with the number of wheel idling. The safety level corresponding to the data used to characterize the door state is determined according to the correspondence between the preset evaluation index and the safety level, wherein the door state includes: normal door state, isolated door state, bypass door state, offline door state, and faulty door state, and the safety level corresponding to each state decreases in sequence. The safety level corresponding to the battery power is determined according to the correspondence between the preset evaluation index and the safety level, wherein the safety level corresponding to the battery power is positively correlated with the battery power. The safety level corresponding to the data used to characterize the fire impact is determined according to the corresponding relationship between the preset evaluation index and the safety level, wherein the safety level corresponding to the data used to characterize the fire impact is negatively correlated with the fire impact.

[0053] For example, the safety level is identified by a score. For example, the safety level is divided into 0 to 10 points, and the larger the score, the higher the safety level, and the corresponding safety is also higher. For the indicators of data used to characterize the state of the speed pulse device, data used to characterize the state of the control system (TCMS communication state), data used to characterize the state of the transponder message transmission module (BTM), and self-test data used to characterize the state of any system of the vehicle, the safety level corresponding to the indicator of the object being characterized is determined to be 0 points (first safety level), and the safety level corresponding to the indicator of the object being characterized is not faulty is determined to be 10 points (second safety level).

[0054] Among them, for the indicator of the self-test data used to characterize the status of any system of the vehicle, if the self-test status of any system is self-test failure, the safety level corresponding to the indicator is determined to be 0 points, otherwise the safety level corresponding to the indicator is determined to be 10 points.

[0055] For example, for the safety level corresponding to the number of wheel spins, the corresponding safety level can be determined according to the number of wheel spins within a period (e.g., 500ms). The safety level corresponding to the number of wheel spins is negatively correlated with the number of wheel spins. For specific classification, please refer to Table 1 below.

[0056] Wheel spin times [0,1) [1,2) [2,4) [4,5) (5,+∞) Safety level (points) 9 7 5 2 1

[0057] Table 1

[0058] Furthermore, the safety levels corresponding to the number of wheel idling times in multiple cycles during the operation of the vehicle may be accumulated and averaged, and the average value of the obtained safety levels may be used as the safety level corresponding to the number of wheel idling times during the operation of the vehicle.

[0059] For example, for the security level corresponding to the data used to characterize the door status, the specific classification can be referred to the following Table 2.

[0060] Door status normal isolation bypass Offline Fault Safety level (points) 9 6 5 4 2

[0061] Table 2

[0062] For example, for the safety level corresponding to the battery power, the specific classification can refer to the following Table 3, where the safety level corresponding to the battery power is positively correlated with the battery power.

[0063]

[0064] Table 3

[0065] For example, for the safety level corresponding to the fire impact degree, the specific classification can refer to the following Table 4, where the safety level corresponding to the data used to characterize the fire impact degree is negatively correlated with the fire impact degree.

[0066] Fire impact big Larger generally Small none Safety level (points) 9 7 5 3 1

[0067] Table 4

[0068] Among them, the fire impact can be determined by the impact of the fire alarm or fire situation on the operational safety of the vehicle. Generally speaking, when the fire alarm sends out an alarm message or a fire occurs in the vehicle, the relevant technical personnel will evaluate the impact of the fire alarm or fire situation on the operational safety of the vehicle and upload the corresponding evaluation results to the corresponding management system. Therefore, the fire impact can be used to quantitatively analyze the safety level.

[0069] In a possible manner, the operating environment indicator of the target vehicle includes at least one of the following: road foreign object detection data, abnormal road occupancy data, and climate data.

[0070] For example, the safety level corresponding to the road foreign object detection data is determined according to the correspondence between the preset evaluation index and the safety level, wherein the safety level corresponding to the road foreign object detection data can be divided according to the distance between the foreign object and the vehicle in the road foreign object detection data, and the specific division can refer to the following Table 5. In addition, when there are multiple foreign objects during operation, the average value of the safety levels corresponding to the multiple road foreign object detection data can be taken as the safety level corresponding to the evaluation index during the entire operation.

[0071]

[0072] Table 5

[0073] For example, the safety level corresponding to the abnormal road occupancy data is determined according to the correspondence between the preset evaluation index and the safety level, wherein the safety level corresponding to the abnormal road occupancy data can be divided according to the duration of the road (track) being occupied in the abnormal road occupancy data, and the specific division can refer to the following Table 6. In addition, in the case where there are multiple occupied roads during the operation process, the average value of the safety levels corresponding to the multiple abnormal road occupancy data can be taken as the safety level corresponding to the evaluation index during the entire operation process.

[0074]

[0075] Table 6

[0076] For example, the safety level corresponding to the climate data is determined according to the correspondence between the preset evaluation index and the safety level, wherein the safety level corresponding to the climate data can be divided according to the impact of the climate (such as wind, snow, rain or other extreme weather) on the operational safety of the vehicle, and the specific division can refer to the following Table 7. Among them, the impact of the climate on the operational safety of the vehicle can be an evaluation result obtained by relevant technical personnel evaluating the impact of the climate conditions encountered during the operation of the vehicle on the operational safety of the vehicle, or it can be a relationship between the climate and the degree of impact of the climate on the operational safety of the vehicle obtained based on historical climate conditions, and then the corresponding impact degree is obtained through the weather data obtained during the operation, and then a quantitative analysis of the safety level is performed.

[0077]

[0078] Table 7

[0079] In a possible manner, the worker status indicator of the target vehicle includes at least one of the following: data used to characterize the worker's fatigue status and data used to characterize the worker's professional ability. The worker includes security personnel and dispatch personnel.

[0080] For example, according to the correspondence between the preset evaluation index and the security level, the security level corresponding to the data used to characterize the fatigue state of the staff is determined, wherein the security level corresponding to the data used to characterize the fatigue state of the staff can be divided according to the fatigue work rate in the data used to characterize the fatigue state of the staff, and the specific division can refer to the following Table 8. Among them, the fatigue work rate of the staff = (total number of staff / number of fatigued staff) × 100%. The fatigued staff can be analyzed by face recognition technology or obtained according to the work schedule record, and the present disclosure does not limit this.

[0081]

[0082] Table 8

[0083] For example, according to the correspondence between the preset evaluation index and the safety level, the safety level corresponding to the data used to characterize the professional ability of the staff is determined, wherein the safety level corresponding to the data used to characterize the professional ability of the staff can be divided according to the professional skills assessment level, emergency handling ability assessment level and safety awareness assessment level in the data used to characterize the professional ability of the staff. The specific division can refer to the following Table 9. Among them, each assessment level can be obtained by assessing the staff, and the present disclosure does not limit this. In addition, if there are multiple staff members, the average value of the safety levels corresponding to the multiple staff members can be taken as the safety level of the evaluation index. It is also possible to set corresponding weights to calculate the safety level according to the impact of different staff members' positions on the operational safety of the vehicle, and the present disclosure does not limit this.

[0084]

[0085] Table 9

[0086] In a possible manner, when the running route of the target vehicle includes multiple running intervals, obtaining the target evaluation index of the target vehicle includes obtaining multiple interval target evaluation indexes corresponding to the multiple running intervals of the target vehicle; the interval target evaluation index includes at least one of the following: the running state index of the target vehicle, the running environment index of the target vehicle, and the staff state index of the target vehicle. According to the correspondence between the preset evaluation index and the safety level, determining the safety level corresponding to the target evaluation index can be: according to the correspondence between the preset evaluation index and the safety level, determining the safety level corresponding to each of the multiple interval target evaluation indexes, and determining the safety level corresponding to the target evaluation index according to the multiple safety levels.

[0087] Among them, the indicators included in the operating status indicators of the target vehicle of the interval target evaluation index are consistent with the indicators included in the operating status indicators of the target vehicle of the target evaluation index, the indicators included in the operating environment indicators of the target vehicle of the interval target evaluation index are consistent with the indicators included in the operating environment indicators of the target vehicle of the target evaluation index, and the indicators included in the staff status indicators of the target vehicle of the interval target evaluation index are consistent with the indicators included in the staff status indicators of the target vehicle of the target evaluation index, and the present disclosure will not repeat them here.

[0088] For example, in an embodiment of the present disclosure, the vehicle's route is divided into logical intervals. The vehicle's route can be divided into intervals based on the running time, for example, every 10 minutes, or based on the running mileage, for example, every 500 meters. The lengths of the running intervals can be consistent or inconsistent, and the present disclosure does not make any specific limitations on this.

[0089] Furthermore, according to the correspondence between the preset evaluation indicators and the security levels, the security levels corresponding to the multiple interval target evaluation indicators are determined, and then the security level corresponding to the target evaluation indicator is determined according to the multiple security levels.

[0090] For example, taking the data used to characterize the state of the speed pulse device, the data used to characterize the state of the control system, and the data used to characterize the state of the transponder message transmission module in the operating state index of the target vehicle as an example, the safety levels corresponding to the speed pulse device, the control system (TCMS), and the transponder message transmission module are determined by the following calculation formula:

[0091]

[0092]

[0093]

[0094] Among them, Score pulse Indicates the safety level corresponding to the speed pulse device, Score TCMS Indicates the safety level of the control system (TCMS), Score BTM Indicates the security level corresponding to the transponder message transmission module (BTM), Indicates the interval safety level of the speed pulse device corresponding to the mth operating interval, It indicates the interval safety level of the control system (TCMS) corresponding to the mth operating interval, Indicates the interval security level corresponding to the mth operating interval of the transponder message transmission module (BTM), len mIndicates the length of the operating interval (duration or mileage). Then the average value of the interval safety level corresponding to each operating interval is used as the safety level corresponding to the evaluation indicator during the entire operation process. Other methods for determining the safety level corresponding to the target evaluation indicator based on the interval target evaluation indicator can refer to the above method, and this disclosure will not be repeated here.

[0095] It is worth noting that the safety level of different operating intervals has different impacts on the safety level of the entire operating line. For example, the time or location of failure of the speed pulse device, control system (TCMS) and transponder message transmission module is different, and the impact on vehicle operation safety is inconsistent. The impact of a vehicle failure at the start time or start position on operation safety is usually greater than the impact of a failure at the end time or end position on operation safety. Therefore, it is also possible to set corresponding weights for different operating intervals according to their impact on vehicle operation safety, and then calculate the average value as the safety level corresponding to the evaluation index in the entire operating line.

[0096] Furthermore, after determining the safety level corresponding to the target evaluation indicator based on the corresponding relationship between the above-mentioned preset evaluation indicators and safety levels, the safety level corresponding to the target evaluation indicator is input into a preset risk assessment model to obtain target risk type information of the target vehicle.

[0097] For example, the target risk type information of the target vehicle may be determined according to the following PSO-SVR model algorithm:

[0098] f(x i )=ω T Φ(x i )+b

[0099] Among them, f(x i ) represents the predicted safety level obtained by the preset risk assessment model based on the input safety level, x i represents the security level corresponding to the target evaluation index, ω represents the weight vector, T represents the transposition, Φ(x i ) represents the mapping function, and b represents the bias term.

[0100] It should be noted that x iIt includes at least one of the following: the safety level corresponding to the data used to characterize the state of the speed pulse device, the safety level corresponding to the data used to characterize the state of the control system, the safety level corresponding to the data used to characterize the state of the transponder message transmission module, the safety level corresponding to the self-test data used to characterize the state of any system of the vehicle, the safety level corresponding to the number of wheel idling, the safety level corresponding to the data used to characterize the state of the door, the safety level corresponding to the battery power, the safety level corresponding to the data used to characterize the impact of fire, the safety level corresponding to the road foreign object detection data, the safety level corresponding to the abnormal road occupancy data, the safety level corresponding to the climate data, the safety level corresponding to the data used to characterize the fatigue state of the staff and the safety level corresponding to the data used to characterize the professional ability of the staff.

[0101] Finally, risk type information is obtained based on the output predicted security level. For example, the output predicted security level can be used as risk type information, i.e., the first security level, the second security level, etc., or corresponding risk type information can be set for the security level, and then, for example, the first security level corresponds to serious, the second security level corresponds to minor, and so on. The present disclosure does not limit this.

[0102] It is worth noting that the risk assessment model in the disclosed embodiment is a PSO-SVR (Particle Swarm Optimization Algorithm-Support Vector Regression) model, that is, the parameters of the risk assessment model are determined using the particle swarm optimization algorithm (PSO). Since the particle swarm algorithm can perform iterative training based on a small amount of sample data, the particles in the particle swarm (parameters of the risk assessment model) are continuously optimized, and then the optimal particles are output as the parameters of the risk assessment model when the number of iterations or accuracy requirements are met. Therefore, a risk assessment model that meets the accuracy requirements can be obtained through the particle swarm algorithm when sample data is insufficient. In addition, through the trained risk assessment model, the risk assessment of the vehicle can be performed to ensure the safe operation of the vehicle. Among them, the objective function of the particle swarm optimization algorithm is:

[0103]

[0104] Wherein, mind(C,ε,γ) represents the objective function, C represents the error penalty parameter of the risk assessment model, ε represents the insensitive loss parameter of the risk assessment model, γ represents the Gaussian kernel function parameter of the risk assessment model, N represents the number of sample data, and y represents the number of sample data. i represents the reference safety level in the sample data, f(x i ) represents the predicted safety level obtained by the risk assessment model based on the sample data. The iterative process of the particle swarm optimization algorithm can be referred to in the relevant technology, and the present disclosure will not repeat it here.

[0105] In a possible manner, the method further includes: after determining the target risk type information of the target vehicle, generating prompt information according to the target risk type information.

[0106] For example, different prompt information is generated according to different target risk type information, for example, when the target risk type information is "first safety level", prompt information "first safety level warning" is generated, or when the target risk type information is "serious", prompt information "serious warning" is generated, etc., which is not limited in the present disclosure. The staff can learn that the vehicle has risks according to different prompt information, and thus take measures to avoid the risks, such as evacuating passengers, arranging maintenance personnel for inspection, etc., which is not limited in the present disclosure.

[0107] In addition, the execution subject of the vehicle risk assessment method in the embodiment of the present disclosure may be a vehicle, an electronic device or a management system on the vehicle, or a background system for assessing vehicle safety, etc., and the present disclosure does not limit this. In addition, the target assessment index of the vehicle is obtained from the system or device where the corresponding assessment object is located, or the detection system or detection device for the corresponding assessment object, and the present disclosure does not limit this.

[0108] It should be noted that the evaluation indicators, corresponding quantitative analysis, corresponding calculation formulas and objective functions provided in the embodiments of the present disclosure can be adjusted according to relevant regulations of the transportation industry and the needs for safety assessment during the specific implementation process.

[0109] Based on the same inventive concept, an embodiment of the present disclosure also provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the vehicle risk assessment method are implemented.

[0110] Based on the same inventive concept, the embodiment of the present disclosure also provides a vehicle risk assessment device, including:

[0111] a memory having a computer program stored thereon;

[0112] A processor is used to execute the computer program in the memory to implement the steps of the above-mentioned vehicle risk assessment method.

[0113] Figure 2 2 is a block diagram of a vehicle risk assessment device 200 according to an exemplary embodiment. Figure 2The vehicle risk assessment device 200 includes a processor 222, which may be one or more, and a memory 232 for storing a computer program executable by the processor 222. The computer program stored in the memory 232 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 222 may be configured to execute the computer program to perform the above-mentioned vehicle risk assessment method.

[0114] In addition, the vehicle risk assessment device 200 may further include a power supply component 226 and a communication component 250. The power supply component 226 may be configured to perform power management of the vehicle risk assessment device 200, and the communication component 250 may be configured to implement communication of the vehicle risk assessment device 200, for example, wired or wireless communication. In addition, the vehicle risk assessment device 200 may further include an input / output (I / O) interface 258. The vehicle risk assessment device 200 may operate based on an operating system stored in the memory 232, such as Windows Server 200. TM , Mac OS X TM , Unix TM , Linux TM etc.

[0115] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned vehicle risk assessment method are implemented. For example, the non-transitory computer-readable storage medium can be the above-mentioned memory 232 including program instructions, and the above-mentioned program instructions can be executed by the processor 222 of the vehicle risk assessment device 200 to complete the above-mentioned vehicle risk assessment method.

[0116] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above-mentioned vehicle risk assessment method when executed by the programmable device.

[0117] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0118] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0119] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A vehicle risk assessment method, characterized in that: Applied in a rail transit scenario of an unmanned train, the method includes: Obtain target evaluation indicators for the target vehicle; Determine the security level corresponding to the target evaluation indicator according to the corresponding relationship between the preset evaluation indicator and the security level; Determining target risk type information of the target vehicle according to the safety level corresponding to the target evaluation index and a preset risk evaluation model, wherein the risk evaluation model is a PSO-SVR model; When the operation route of the target vehicle includes multiple operation intervals, the obtaining of the target evaluation index of the target vehicle includes obtaining multiple interval target evaluation indexes corresponding to the multiple operation intervals of the target vehicle; the interval target evaluation index includes a staff status index of the target vehicle, or at least one of the operation status index of the target vehicle and the operation environment index of the target vehicle and the staff status index of the target vehicle; the staff status index of the target vehicle includes at least one of the following: data for characterizing the fatigue state of the staff and data for characterizing the professional ability of the staff; Determining the security level corresponding to the target evaluation indicator according to the correspondence between the preset evaluation indicator and the security level includes: According to the correspondence between the preset evaluation index and the safety level, the safety level corresponding to each of the multiple interval target evaluation indicators is determined, and according to the influence of different operating intervals on the vehicle operation safety, corresponding weights are set for different operating intervals to obtain weight values ​​corresponding to different operating intervals; according to the weight values ​​corresponding to the different operating intervals, the average value of the safety levels corresponding to each of the multiple interval target evaluation indicators is calculated, and the average value is determined as the safety level corresponding to the target evaluation indicator; The step of determining the security level corresponding to each of the plurality of interval target evaluation indicators according to the correspondence between the preset evaluation indicators and the security level comprises: Determine the safety level corresponding to the data used to characterize the fatigue state of the staff member according to the correspondence between the preset evaluation index and the safety level, wherein the safety level corresponding to the data used to characterize the fatigue state of the staff member is divided according to the fatigue work rate of the data used to characterize the fatigue state of the staff member, or According to the correspondence between preset evaluation indicators and security levels, the security level corresponding to the data used to characterize the professional ability of the staff is determined, wherein the security level corresponding to the data used to characterize the professional ability of the staff is divided by the professional skill assessment level, emergency response capability assessment level and safety awareness assessment level in the data used to characterize the professional ability of the staff.

2. The method according to claim 1, characterized in that The operating status index of the target vehicle includes at least one of the following: data for characterizing the status of a speed pulse device, data for characterizing the status of a control system, data for characterizing the status of a transponder message transmission module, self-test data for characterizing the status of any system of the vehicle, the number of wheel idling times, data for characterizing the status of a door, battery power, and data for characterizing the impact of a fire.

3. The method according to claim 2, characterized in that Determining the security level corresponding to the target evaluation indicator according to the correspondence between the preset evaluation indicator and the security level includes: For the indicators of the data used to characterize the state of the speed pulse device, the data used to characterize the state of the control system, the data used to characterize the state of the transponder message transmission module, and the self-test data used to characterize the state of any system of the vehicle, the safety level corresponding to the indicator of the object characterized by failure is determined as the first safety level, and the safety level corresponding to the indicator of the object characterized by no failure is determined as the second safety level, and the safety guaranteed by the second safety level is higher than the safety guaranteed by the first safety level; Determining the safety level corresponding to the number of wheel idling times according to the corresponding relationship between the preset evaluation index and the safety level, wherein the safety level corresponding to the number of wheel idling times is negatively correlated with the number of wheel idling times; Determining the security level corresponding to the data used to characterize the door state according to the correspondence between the preset evaluation index and the security level, the door state including: normal door state, isolated door state, bypass door state, offline door state and faulty door state, and the security level corresponding to each state decreases in sequence; Determine the safety level corresponding to the battery power according to the corresponding relationship between the preset evaluation index and the safety level, wherein the safety level corresponding to the battery power is positively correlated with the battery power; The safety level corresponding to the data used to characterize the fire impact is determined according to the corresponding relationship between the preset evaluation index and the safety level, and the safety level corresponding to the data used to characterize the fire impact is negatively correlated with the fire impact.

4. The method according to claim 1, characterized in that: The operating environment index of the target vehicle includes at least one of the following: road foreign object detection data, road abnormal occupancy data and climate data.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: After determining the target risk type information of the target vehicle, prompt information is generated according to the target risk type information.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

7. A vehicle risk assessment device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images