Risk domain control method and system based on train formation operation risk cause analysis

Abstract

The invention provides a risk domain control method and system based on train formation operation risk cause analysis, belongs to the technical field of train operation control, and aims at sensing formation state information in real time and realizing adjacent train state information interaction based on a train-train communication technology. The method comprises the following steps of: constructing a risk situation propagation model by using a dynamic Bayesian network by taking low efficiency of a braking anti-skid system and communication link establishment failure among formation trains in abnormal weather as a risk source and taking formation train collision as an accident result, and performing sensitivity analysis and sorting on each risk node; a nonlinear vibration theory and a Rayleigh equation are used to describe vibration characteristics in risk situation changes and a microscopic evolution process thereof, a sensitivity weight value of a node having a maximum influence on a collision accident occurrence probability is used as a damping coefficient of the Rayleigh equation, and a relationship between a control variable and the damping coefficient is explored based on damping control. The risk domain is converged to an initial security state. According to the invention, risk domain control for train formation operation can be realized from a system-level perspective.

Description

Technical Field

[0001] The present invention relates to the technical field of train operation control, and in particular to a risk domain control method and system based on risk cause analysis of train formation operation. Background Art

[0002] The urban rail transit operation network has played an important role in alleviating traffic congestion and accelerating the process of carbon neutrality. However, with the development of urban rail transit network operations, the passenger flow-capacity mismatch caused by changes in passenger flow over time has gradually become apparent.

[0003] Drawing on the idea of ​​vehicle formation operation, German scholar U. Block first proposed the concept of virtual reconnection in 1999, hoping that through the formation method, freight trains can achieve extremely short running intervals without relying on physical couplers. It has been applied in my country's heavy-duty and urban rail transit. At the same time, integrating positioning, communication and control technologies, the virtual reconnection-fully automatic operation system not only improves the line operation efficiency, but also improves the overall automation level of the rail transit control system. With the compression of the running interval, compared with the traditional single-vehicle autonomous operation, when the train runs in the formation mode, it is affected by potential risks such as the equipment status, operating environment, personnel operation and organizational management form of multiple trains in the team. This means that the risk of any train may have a chain reaction on the formation. In addition, due to the close coupling relationship between trains, mutual cooperation, and frequent transmission of information and instructions, any potential risk will spread faster, wider and more difficult to control. If it is not intervened in time before the accident occurs, it is very easy to cause serious accidents, and even interfere with line operations on a large scale, seriously affecting the operation efficiency. Therefore, it is urgent to improve the risk prevention and control and safety management capabilities of train formation operation in the field of rail transit.

[0004] At present, the research on the operation mechanism of train formations has become mature, but the related operation safety research is relatively scattered, mainly focusing on risk analysis, or implicit in the constraints or fault tolerance in the interval control or optimization algorithm, and the risk analysis is disconnected from the prevention and control methods; and most of them are aimed at the operation of a single or several non-formation trains, focusing on the use of continuously developing safety analysis methods to call a large amount of manpower to investigate, review and analyze the entire process of the accident after the accident occurs. A complete timely safety management system for formation operation has not yet been formed, and there is a lack of in-depth research on timely safety management methods for formation operation and full-link risk prevention and control methods. Therefore, for the operation of rail transit train formations, based on the technical updates of precise positioning, vehicle-to-vehicle communication, etc., it is of great significance and application value to carry out research on risk cause analysis and active risk prevention and control methods, which can provide theoretical and technical support for the realization of safe, stable and efficient operation of train formations.

[0005] At present, there is no in-depth research in the existing technology on the risk domain control method based on the risk cause analysis of train formation operation. Summary of the invention

[0006] The object of the present invention is to provide a risk domain control method and system based on risk cause analysis of train formation operation, so as to solve at least one technical problem existing in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a risk domain control method based on risk cause analysis of train formation operation, comprising:

[0009] In view of the multi-factor and cumulative nature of risks during train formation operation, a risk situation propagation model is constructed with the low efficiency of the anti-skid braking system in abnormal weather and the high delay in communication between train formation cars as risk sources, and the collision between train formation cars as accident results.

[0010] The dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and the sensitivity of each node in the risk situation propagation model is analyzed and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of collision accidents.

[0011] Based on the applicability of the Rayleigh equation to describe the risk situation changes of the VC-FAO system, the risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation.

[0012] Based on the risk state equation and damping control, the amplitude of the limit cycle of the risk domain is derived by introducing control variables, so that the risk domain constructed by the limit cycle can be as small as possible or converge to the initial safe state.

[0013] Furthermore, a risk situation propagation model is constructed, including:

[0014] Based on the risk causes and accident consequences, a risk scenario is assumed: it is assumed that the automatic monitoring system issues formation instructions to two trains running in moving block mode through the area controller and trackside communication equipment; based on the risk scenario, the evolution process of risk-accident is deduced; the deduced evolution process of risk-accident is converted into a risk situation propagation model based on risk causal factors.

[0015] Furthermore, based on the risk scenarios, the evolution process of risk-accident was deduced, including: the two trains respectively confirmed and started the car-to-car communication equipment, but because the car-to-car communication equipment of the rear car was abnormally occupied and in abnormal weather, the car-to-car communication equipment of the front car had high latency, and the car-to-car communication link between the platoon workshop failed to be established; at the same time, the environmental monitoring system detected that the front car was slipping due to the influence of the track adhesion coefficient, reported to ZC and ATS, and set a temporary speed limit to implement braking; but due to the failure to establish the car-to-car communication link, the rear car could not obtain the changes in the running status of the front car in time, and still judged that it was running according to the predetermined trajectory, and accelerated to catch up according to the formation instruction, which led to a reduction in the running interval and the occurrence of a collision accident.

[0016] Furthermore, the risk nodes that have the greatest impact on the probability of a collision accident are determined, including:

[0017] The situation propagation model based on risk causal factors is transformed into DBN based on logical behavior and sequence, and the status monitoring data of the VC-FAO system is continuously input into the DBN model as evidence information;

[0018] Assuming that each node is independent of its parent node, the joint probability of all nodes is obtained by multiplying the conditional probability of each node;

[0019] It is assumed that each time node must satisfy the Markov assumption and the current state is only related to the previous state, so as to reduce the complexity of DBN and improve the analysis efficiency.

[0020] Assuming that each temporal node is stable within a single time slice, its conditional probability does not change;

[0021] Based on the assumptions, a DBN risk situation propagation model is constructed, and the status of each risk node in the network is continuously calculated to achieve dynamic Bayesian network visualization update of the probability of collision accidents in train formation operation scenarios.

[0022] Furthermore, since the parameters of each node in DBN will change over time, it is necessary to dynamically add evidence nodes at different times, while considering the situation changes in adjacent time slices, and then calculate the sensitivity weight of each risk node in DBN, and sort the risk nodes with the greatest impact on the probability of train formation collision accidents and their sensitivity weight values.

[0023] Furthermore, based on the applicability of the Rayleigh equation to describe the changes in the risk situation of the VC-FAO system, a risk state equation for the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of a collision accident is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation, including: using nonlinear vibration theory and the Rayleigh equation to describe the vibration characteristics and its microscopic evolution process during the change of the risk situation of the VC-FAO system, and constructing the risk state equation based on this; considering that the phase plane technology can intuitively observe the relationship between state variables and the changes of state variables over time; converting the risk state equation into a first-order differential equation containing only state variables ; The system damping term in the equation is negative when it is small; but when it is large enough, it is positive, which means that when using the Rayleigh equation to describe the change of the system risk state, there is a moment when the damping term changes rapidly from positive to negative or vice versa, that is, there is a mutation; using the Reynolds construction method, the zero-slope isocline in the phase plane can be obtained, which proves that the Rayleigh equation is also applicable to describing the risk situation changes of the VC-FAO system while satisfying the sharp mutation, and after a period of time, its phase trajectory will maintain periodic motion; in addition, since each point in the phase trajectory contains the risk state of the system at the current moment and the changing trend of the risk state, it can constitute the system risk domain.

[0024] Furthermore, based on the risk state equation and damping control, by introducing control variables, the amplitude of the risk domain limit cycle is derived, so that the risk domain constructed by the limit cycle is as small as possible or converges to the initial safe state, including: introducing a risk control function into the risk state equation based on damping control, introducing small parameters, and using the multi-scale method to obtain the spatial approximate solution of the risk control function; for the original time phase, different time scales are used to synthesize it; the limit cycle amplitude of the risk domain when the Rayleigh equation describes the change of the system risk situation is obtained, and by adjusting the relationship between the control variable and the damping coefficient of the Rayleigh equation, the risk domain of the platoon can be controlled from a system level perspective.

[0025] In a second aspect, the present invention provides a risk domain control system based on risk cause analysis of train formation operation, comprising:

[0026] The construction module is used to construct a risk situation propagation model based on the multi-factor and cumulative nature of risks during train formation operation, with low efficiency of the anti-skid braking system in abnormal weather and high communication delay between train formation cars as risk sources, and collision between train formation cars as accident results;

[0027] The sorting module is used to simulate the occurrence process of risk scenarios using a dynamic Bayesian network, perform sensitivity analysis on each node in the risk situation propagation model and sort them according to their sensitivity, and determine the risk nodes that have the greatest impact on the probability of collision accidents;

[0028] The deduction module is used to deduce the risk situation change of the VC-FAO system, construct the risk state equation of the VC-FAO system, and use the sensitivity weight value of the node with the greatest impact on the probability of collision accidents as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation;

[0029] The control module is used to integrate the risk state equation and damping control from the system level to realize the control of the risk domain of the platoon. By introducing control variables, the amplitude of the limit cycle of the risk domain is derived to make the risk domain constructed by the limit cycle as small as possible or converge to the initial safe state.

[0030] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the risk domain control method based on the risk cause analysis of train formation operation as described in the first aspect is implemented.

[0031] In a fourth aspect, the present invention provides a computer device comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the risk domain control method based on the risk cause analysis of train formation operation as described in the first aspect.

[0032] In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the risk domain control method based on the risk cause analysis of train formation operation as described in the first aspect.

[0033] The invention has the following beneficial effects: based on multi-sensor fusion technology, multi-dimensional running state information of trains is perceived in real time, and based on vehicle-to-vehicle communication technology, real-time interaction of adjacent train state information is realized; in view of the multi-factor and cumulative nature of risks occurring during train formation operation, a risk situation propagation model is constructed with low efficiency of braking anti-skid system under abnormal weather conditions and failure to establish communication link between formation workshops as risk sources, and collision between formation workshops as accident results; based on the evolution process of risk-accident, DBN is used to simulate the occurrence process of risk scenarios, and sensitivity analysis and ranking of each risk node are performed; in view of the fact that the risk situation of train formation operation is constantly changing, nonlinear vibration theory and Rayleigh equation are used to describe the vibration characteristics and micro-evolution process of the VC-FAO system during the risk situation change process, and a risk state equation is constructed based on this, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation; based on the derivation of the limit cycle amplitude of the risk domain, the relationship between the control variable and the damping coefficient of the Rayleigh equation is explored, so that the limit cycle amplitude is as small as possible, and the risk domain converges to the initial safe state. The present invention can realize risk domain control for train formation operation from a system-level perspective, reduce the dependence of risk research on accident data or expert knowledge, and provide guarantee for the intelligent, reliable and safe operation of flexible train formations.

[0034] Additional advantages of the present invention will be more clearly given in the following description or learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0036] Figure 1 The present invention is a schematic diagram of a specific process of the risk domain control method based on the risk cause analysis of train formation operation according to an embodiment of the present invention.

[0037] Figure 2 These are the various internal and external risks that may exist during the single-vehicle autonomous operation and multi-vehicle collaborative platoon operation described in the embodiments of the present invention.

[0038] Figure 3 This is the risk situation propagation model based on risk causal factors described in an embodiment of the present invention.

[0039] Figure 4 This is the evolution process of risk-accident during train formation operation described in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below by the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0041] It should be understood by those skilled in the art that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs.

[0042] It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have a meaning consistent with that in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless as defined herein.

[0043] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. Different embodiments or examples described in this specification and features of different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

[0045] To facilitate understanding of the present invention, the present invention is further explained below with reference to specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0046] Those skilled in the art should understand that the drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily necessary for implementing the present invention.

[0047] Example 1

[0048] In this embodiment 1, a risk domain control system based on the cause analysis of train formation operation risk is first provided, including: a construction module, which is used to construct a risk situation propagation model based on the multi-factor and cumulative nature of the risk occurrence when the train formation is running, with the low efficiency of the braking anti-skid system in abnormal weather and the high delay of the communication between the formation workshop and the formation train as the risk source, and the collision of the formation train as the accident result; a sorting module, which is used to simulate the occurrence process of the risk scenario by using a dynamic Bayesian network, perform sensitivity analysis on each node in the risk situation propagation model and sort them according to their sensitivity, and determine the risk node with the greatest impact on the probability of collision accident; a deduction module, which is used to deduce the change of the risk situation of the VC-FAO system, construct the risk state equation of the VC-FAO system, and use the sensitivity weight value of the node with the greatest impact on the probability of collision accident as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation; a control module, which is used to control the risk domain of the formation train from the system level by combining the risk state equation and the damping control, and derive the amplitude of the risk domain limit cycle by introducing the control variable, so that the risk domain constructed by the limit cycle is as small as possible or converges to the initial safe state.

[0049] In this embodiment, the above-mentioned system is used to implement a risk domain control method based on the cause analysis of train formation operation risks, including: in view of the multi-factor and cumulative nature of the risk occurrence during train formation operation, the low efficiency of the braking anti-skid system under abnormal weather conditions and the high delay in communication between the formation workshops are used as risk sources, and the collision between the formation workshops is used as the accident result to construct a risk situation propagation model; a dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and the sensitivity of each node in the risk situation propagation model is analyzed and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of collision accidents; based on the applicability of the Rayleigh equation to describe the change of the risk situation of the VC-FAO system, a risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node with the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation; based on the risk state equation and damping control, the amplitude of the risk domain limit cycle is derived by introducing control variables, so that the risk domain constructed by the limit cycle is as small as possible or converges to the initial safe state.

[0050] In this embodiment, in view of the multi-factor and cumulative nature of risks occurring during train formation operation, the low efficiency of the braking anti-skid system in abnormal weather and the high delay in communication between trains in the formation are taken as risk sources, and the collision between trains in the formation is taken as the accident result. A risk situation propagation model is constructed, including: based on the risk causes and accident results, assuming risk scenarios: assuming that the automatic monitoring system issues formation instructions to two trains operating in the moving block mode through the regional controller and the trackside communication equipment; based on the risk scenarios, the evolution process of risk-accident is deduced; and the deduced evolution process of risk-accident is converted into a risk situation propagation model based on risk causal factors. Specifically, it includes: based on the risk causes and accident results, assume the risk scenario: in order to improve the line operation efficiency, assume that the automatic monitoring system issues formation instructions to two trains running in mobile block mode through the regional controller and the trackside communication equipment; deduce the evolution process of risk-accident: the two trains confirm and start the car-to-car communication equipment respectively, but because the car-to-car communication equipment of the rear car is abnormally occupied and in abnormal weather, the car-to-car communication equipment of the front car has high latency, and the car-to-car communication link between the formation workshop fails to be established; at the same time, the environmental monitoring system detects that the front car is slipping due to the adhesion coefficient of the rail surface, reports to ZC and ATS, and sets a temporary speed limit to implement braking; but due to the failure to establish the car-to-car communication link, the rear car cannot obtain the change in the running status of the front car in time, and still judges that it is running according to the predetermined trajectory, and accelerates to catch up according to the formation instruction, which leads to a reduction in the running interval and the occurrence of a collision accident. The above risk-accident evolution process is converted into a risk situation propagation model based on risk cause factors, such as Figure 3 shown.

[0051] In this embodiment, a dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and sensitivity analysis is performed on each node in the DBN and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of a collision accident, including: converting a situation propagation model based on risk causal factors into a DBN based on logical behavior and sequence, and continuously inputting the status monitoring data of the VC-FAO system into the DBN model as evidence information; assuming that each node is independent of its parent node, and multiplying the conditional probability of each node to obtain the joint probability of all nodes; assuming that each temporal node must meet the Markov assumption, and the current state is only related to the previous state, so as to reduce the complexity of the DBN and improve the analysis efficiency; assuming that each temporal node is stable within a single time slice, and its conditional probability does not change; constructing a DBN risk situation propagation model based on the assumption, performing continuous probability calculation on the state of each risk node in the network, and realizing the dynamic Bayesian network visualization update of the probability of a collision accident in the train formation operation scenario.

[0052] Specifically, the situation propagation model based on risk causal factors is transformed into DBN based on logical behavior and sequence, and the status monitoring data of the VC-FAO system is continuously input into the DBN model as evidence information.

[0053] Assuming that each node is independent of its parent node, the joint probability of all nodes can be obtained by multiplying the conditional probabilities of each node:

[0054]

[0055] Assuming that each time node needs to satisfy the Markov assumption, the current state is only related to the previous state, as shown in formula (2), in order to reduce the complexity of DBN and improve the analysis efficiency.

[0056]

[0057] Assuming that each temporal node is stable within a single time slice, its conditional probability does not change.

[0058]

[0059] Based on the assumption, a DBN risk situation propagation model is constructed, and the state of each risk node in the network is continuously calculated to achieve dynamic Bayesian network visualization update of the probability of collision accidents in the train formation operation scenario. However, since the parameters of each DBN node will change over time, it is necessary to dynamically add evidence nodes at different times, while considering the situation changes in adjacent time slices, which is defined as:

[0060]

[0061] Then, the sensitivity weight of each risk node in DBN can be calculated, and the risk nodes with the greatest impact on the probability of train formation collision accidents and their sensitivity weight values ​​μ can be obtained by sorting. max .

[0062] In this embodiment, based on the applicability of the Rayleigh equation to describe the risk situation changes of the VC-FAO system, a risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of a collision accident is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation, including: using nonlinear vibration theory and the Rayleigh equation to describe the vibration characteristics and its microscopic evolution process during the change of the risk situation of the VC-FAO system, and constructing the risk state equation based on this; considering that the phase plane technology can intuitively observe the relationship between state variables and the change of state variables over time; converting the risk state equation into a first-order differential equation containing only state variables The system damping term in the equation is negative when it is small, but positive when it is large enough. This means that when the Rayleigh equation is used to describe the change of the system risk state, there is a moment when the damping term changes rapidly from positive to negative or vice versa, that is, there is a mutation. The zero-slope isocline in the phase plane can be obtained by using the Reynolds construction method, which proves that the Rayleigh equation is also applicable to describing the risk situation change of the VC-FAO system while satisfying the sharp mutation, and after a period of time, its phase trajectory will maintain periodic motion. In addition, since each point in the phase trajectory contains the risk state of the system at the current moment and the changing trend of the risk state, it can constitute the system risk domain.

[0063] Specifically, the nonlinear vibration theory and Rayleigh equation are used to describe the vibration characteristics and micro-evolution process of the VC-FAO system risk situation change process, and the risk state equation is constructed based on this.

[0064]

[0065] Considering the phase plane technology, we can intuitively observe the relationship between state variables and the change of state variables over time; let y = dx / dt, and convert it into a first-order differential equation containing only state variables (x, y):

[0066]

[0067] The second term of the Rayleigh equation is the system damping term. When it is small, this damping term is negative; but when it is large enough, this damping term is positive; this means that when using the Rayleigh equation to describe the change of the system risk state, there is a moment when the damping term changes rapidly from positive to negative or vice versa, that is, there is a mutation. Using the Reynolds construction method, let dx / dt = 0, and you can get the zero slope isocline in the phase plane (x, y).

[0068] x==μ max y-μ max y 3(7)

[0069] It can be proved that the Rayleigh equation is also applicable to describing the risk situation changes of the VC-FAO system while satisfying the sharp mutation, and after a period of time, its phase trajectory will maintain periodic motion; in addition, since each point in the phase trajectory contains the risk state of the system at the current moment and the changing trend of the risk state, it can constitute the system risk domain.

[0070] In this embodiment, since the size of the limit cycle depends on the amplitude of the limit cycle, based on the risk state equation and damping control, by introducing control variables into it, the amplitude of the risk domain limit cycle is derived, so that the risk domain constructed by the limit cycle is as small as possible or converges to the initial safe state, including: introducing a risk control function into the risk state equation based on damping control, introducing small parameters, and using a multi-scale method to obtain a spatial approximate solution of the risk control function; for the original time phase, using different time scales to synthesize it; deriving the limit cycle amplitude of the risk domain when the Rayleigh equation describes the change of the system risk situation, and by adjusting the relationship between the control variable and the damping coefficient of the Rayleigh equation, the risk domain of the platoon can be controlled from a system level perspective.

[0071] Specifically, based on damping control, the risk control function is introduced into equation (5):

[0072]

[0073] Introducing small parameters and using the multi-scale method, we assume that the spatial approximate solution of equation (8) is:

[0074] x(t,ε)=x0(T0,T1)+εx1(T0,T1) (9)

[0075] The original time phase can be synthesized using different time scales; furthermore, by introducing the operator The derivative of the time variable is expressed as:

[0076]

[0077] Substituting equation (9) and equation (10) into equation (8), we can obtain:

[0078]

[0079] By simplifying and comparing the powers of various orders, we can get:

[0080]

[0081] Due to the zero-order term, the Euler formula is used to expand the complex number form, as shown in formula (13), and it is substituted into formula (11) ε 1The right side of the equation is:

[0082]

[0083] Due to the existence of the Yongnian term, in order to eliminate the resonance phenomenon and ensure that the result does not diverge, let:

[0084]

[0085] Combined with Euler's formula, A(T1) is expressed by formula (16), and it is substituted into formula (15) to obtain:

[0086]

[0087] Based on this, we can get the limit cycle amplitude of the risk domain when the Rayleigh equation describes the change of system risk situation: By adjusting the relationship between the control variable and the damping coefficient of the Rayleigh equation, the risk domain of the platoon can be controlled from a system-level perspective.

[0088] Example 2

[0089] In this embodiment 2, a risk domain control method based on train formation operation risk cause analysis is provided, comprising the following steps:

[0090] Based on multi-sensor fusion technology, multi-dimensional running status information of trains is perceived in real time, and train-to-train communication is established between trains in the train formation, so as to realize real-time interaction of status information between adjacent trains;

[0091] In view of the higher requirements for reliability and safety put forward by autonomous perception of train operation status, data and command transmission and interaction, and platoon collaborative decision-making and control, we conduct in-depth analysis of various internal and external risks that may exist in the autonomous operation of a single vehicle and the coordinated operation of multiple vehicles in platooning;

[0092] In view of the multi-factor and cumulative nature of risks during train formation operation, a risk situation propagation model is constructed with the low efficiency of the anti-skid braking system in abnormal weather and the failure to establish communication links between train formation workshops as risk sources, and the collision between train formation workshops as accident results.

[0093] Based on the evolution process of risk-accident, Dynamic Bayesian Networks (DBN) is used to simulate the occurrence process of the above risk scenarios, and the sensitivity analysis and ranking of each risk node in the dynamic Bayesian network are carried out to determine the risk node with the greatest impact on the probability of collision accidents.

[0094] In view of the fact that the risk situation of train formation operation is constantly changing, the nonlinear vibration theory and Rayleigh equation are used to describe the vibration characteristics and micro-evolution process of the risk situation change of the Virtual Coupling-Fully Automatic Operation (VC-FAO) system. Based on this, the risk state equation is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation.

[0095] Since it satisfies self-excited oscillation, its phase trajectory will present a stable limit cycle after a period of time, constituting the system risk domain; if no intervention is made, the risk domain of the system will not change, the risk and its risk resistance will be balanced, and it will continue to be in a high-risk state; based on damping control, by introducing control variables into the risk state equation, the amplitude of the risk domain limit cycle is derived.

[0096] Based on the amplitude of the limit cycle in the risk domain, the relationship between the control variable and the damping coefficient of the Rayleigh equation is explored to make the amplitude of the limit cycle as small as possible and the risk domain converges to the initial safe state, thereby realizing risk domain control for train formation operation from a system-level perspective.

[0097] In this embodiment, based on multi-sensor fusion technology, multi-dimensional running status information of trains is perceived in real time, and vehicle-to-vehicle communication is established between trains running in formation, specifically including:

[0098] Utilizing data from multiple sensors such as Beidou, inertial navigation, speed sensors, transponders, lidar and cameras, and supported by vehicle-to-vehicle / vehicle-ground networking, the train operation status information is solved in real time based on the train positioning perception algorithm based on multi-sensor information fusion; the train operation environment information is obtained through a collaborative perception method of the train operation environment based on information interaction, to achieve high-precision positioning and continuous perception of the train operation status, and provide perception and communication technology support for train tracking interval control and train group operation planning adjustment in formation mode, thereby ensuring safe and efficient collaborative operation control of trains in formation mode.

[0099] The operation speed is high and the relative distance is small in the formation mode. While improving the flexibility and operation efficiency of the formation, it also faces various risks from inside and outside the formation, such as Figure 2 In-depth analysis of the various risks that may exist in the autonomous operation of a single vehicle and the coordinated operation of multiple vehicles in formation, specifically:

[0100] The characteristics of the risk analysis process should take into account the main elements that constitute the system and its environment, including equipment, capabilities, procedures and personnel. Specifically, they can be divided into internal risks caused by internal elements of the system or equipment and their temporal and spatial changes, such as traction brake system failure, communication delay or interruption, etc., and external risks caused by external environmental interference and other elements and their temporal and spatial changes, such as extreme weather impacts, foreign body intrusion, etc. The occurrence of any risk may cause changes in system status, equipment failure, failure, etc., which will reduce the reliability of the system and make it unable to operate in normal or pre-defined operating modes. If active repairs, maintenance or timely corrections to the system status are not carried out, it will have a direct impact on the safety of the system. In serious cases, it may even cause systemic or functional safety accidents, and even interfere with line operations on a large scale, seriously affecting operating efficiency.

[0101] Taking the low efficiency of the anti-skid braking system in abnormal weather and the failure to establish the communication link between the platooning vehicles as the risk sources and the collision as the accident result, a risk situation propagation model is constructed. Specifically, it includes:

[0102] In order to improve the line operation efficiency, it is assumed that the Automatic Train Supervision (ATS) issues formation instructions to two trains running in mobile block mode through the zone controller (ZC) and the trackside communication equipment; the two trains confirm and start the car-to-car communication equipment respectively, but because the car-to-car communication equipment of the rear car is abnormally occupied and in abnormal weather, the car-to-car communication equipment of the front car has high latency, and the car-to-car communication link between the formation workshop fails to be established; at the same time, the environmental monitoring system detects that the front car is slipping due to the adhesion coefficient of the rail surface, reports to ZC and ATS, and sets a temporary speed limit to implement braking; but due to the failure of the car-to-car communication link to be established, the rear car cannot obtain the change of the running status of the front car in time, and still judges that it is running according to the predetermined trajectory, and accelerates to catch up according to the formation instruction, which leads to a decrease in the running interval and the occurrence of a collision accident. The risk evolution process is transformed into a risk situation propagation model based on risk causal factors, such as Figure 3 shown.

[0103] Based on the risk-causing scenarios and the risk-accident evolution process, the dynamic Bayesian network is used to simulate the risk scenario process, and the sensitivity analysis and ranking of each risk node are performed to determine the risk node with the greatest impact on the probability of collision accidents, including:

[0104] Due to the different operating environments and the low reliability of system components, deviations from the expected operating status may occur. The control system that enables the train formation to be implemented can be divided into a component layer consisting of software and hardware equipment, environment, personnel, etc., a subsystem layer consisting of a single vehicle, and a system layer consisting of the entire formation. The functions of each layer correspond to them. The physical structure of the system is based on components, and the realization of system functions also benefits from the ability of each component to perform its own functions, such as Figure 4 shown.

[0105] When the system is in the operation stage, with the emergence of risk sources and the development of their trends, component failures may occur, which may lead to single-vehicle functional failures at the subsystem level in the system functional structure, and then the formation operation may be blocked at the system level. If there is no preventive and control measures, functional failures of varying degrees at all levels in the functional structure may lead to the occurrence of critical safety incidents, and serious accidents may occur.

[0106] DBN is an extension of Bayesian network with time dimension t. Based on the logical behavior and sequence of each risk node, the situation propagation model based on risk causal factors is transformed into DBN. The status monitoring data of VC-FAO system is continuously input into DBN model as evidence information. It is assumed that:

[0107] Assumption 1: Each node is independent of its parent node, and the joint probability of all nodes can be obtained by multiplying the conditional probabilities of each node:

[0108]

[0109] In the formula, x i represents each risk node; P is the conditional probability distribution; Pa(x i ) is the parent node, and when it is an empty set, it means x i is the root node, and P(x i |Pa(x i ) is its prior probability.

[0110] Assumption 2: Each time node must satisfy the Markov assumption condition, and the current state is only related to the previous state, as shown in formula (2), in order to reduce the complexity of DBN and improve the analysis efficiency.

[0111]

[0112] In the formula, X t represents the set of child nodes at time t; P(X t+1 ) is the joint probability of each risk node at time t+Δt.

[0113] Assumption 3: Each temporal node is stable within a single time slice, and its conditional probability does not change.

[0114]

[0115] In the formula, and Represent the parent node sets at time t and time t+Δt respectively.

[0116] Based on this, a DBN risk situation propagation model can be constructed to continuously calculate the probability of each risk node in the network, and realize the dynamic Bayesian network visualization update of the probability of collision accidents in the train formation operation scenario. However, since the parameters of each DBN node will change over time, it is necessary to dynamically add evidence nodes at different times, while considering the situation changes in adjacent time slices, which is defined as:

[0117]

[0118] In the formula, T is the total number of time slices, t is the time slice to which the target node belongs, is the i-th node, e j is the i-th evidence node.

[0119] The probability of a train formation collision is taken as the target node, the node probability when the train does not collide is set as the prior probability, and the evidence is the node probability when a collision occurs, that is, the posterior probability. Then, the sensitivity weight of each risk node in the DBN can be calculated using formula (4), and the risk nodes with the greatest impact on the probability of a train formation collision accident and their sensitivity weight values ​​μ are obtained by sorting. max .

[0120] The nonlinear vibration theory and Rayleigh equation are used to describe the vibration characteristics and micro-evolution process of the VC-FAO system risk situation change process, and based on this, the risk state equation is constructed. The sensitivity weight value μ of the risk node with the greatest impact on the probability of train formation collision accident obtained in claim 5 is max As the damping coefficient of the Rayleigh equation, it describes the change process of the risk situation. Specifically, it includes:

[0121] Differential equations are usually used to describe the vibration characteristics of complex systems and to analyze the stability, resonance, and energy transfer characteristics of the system. Since the risk is constantly changing and will accumulate with the changes in the spatiotemporal running state of the platoon, the risk state of the system at time t can be described by dx / dt, and the risk state of the system at time t can be described by dx / dt. 2 x / dt 2 Describe the risk situation changes, and then analyze the vibration characteristics of the system risk situation changes;

[0122] The Rayleigh equation, such as equation (5), has the advantage of describing complex nonlinear systems while satisfying the order of the risk state equation of the VC-FAO system. Therefore, it is necessary to first prove the applicability of the Rayleigh equation for describing the risk situation change process of the VC-FAO system;

[0123]

[0124] Considering the phase plane technology, we can intuitively observe the relationship between state variables and the change of state variables over time; let y = dx / dt, the equation can be converted into a first-order differential equation containing only state variables (x, y):

[0125]

[0126] The second term of the Rayleigh equation is the system damping term. When it is small, this damping term is negative; but when it is large enough, this damping term is positive; this means that when using the Rayleigh equation to describe the change of the system risk state, there is a moment when the damping term changes rapidly from positive to negative or vice versa, that is, there is a mutation. Using the Reynolds construction method, let dx / dt = 0, and you can get the zero slope isocline in the phase plane (x, y), as shown in equation (7), which proves that the Rayleigh equation is also applicable to describing the risk situation changes of the VC-FAO system while satisfying the sharp mutation.

[0127] x==μ max y-μ max y 3 (7)

[0128] The zero-slope isocline in the y direction occurs in the first and third quadrants near the origin, and the phase points diverge outward; but far from the origin, the zero-slope isocline in the y direction occurs in the second and fourth quadrants, and the phase points shrink inward. Therefore, these two phase points with opposite directions must tend to a stable limit cycle, which further indicates that when the Rayleigh equation is used to describe the risk state change process of the VC-FAO system, it satisfies self-excited vibration, and its phase trajectory will maintain periodic motion after a period of time; in addition, since each point in the phase trajectory contains the risk state of the system at the current moment and the change trend of the risk state, it can constitute the system risk domain.

[0129] Based on the constructed risk state equation and damping control, the amplitude of the risk domain limit cycle is derived by introducing control variables; specifically:

[0130] With the accumulation of changes in the spatiotemporal operating state, the system risk situation is far away from the initial safe state and shows an overall upward trend; and after a certain period of time, the system risk situation presents a stable limit cycle; if no intervention is made, the risk domain of the system will not change, the risk and its risk resistance will be balanced, and the system will continue to be in a high-risk state, which is contrary to the principle of rail transit safety first. It is urgent to control the risk domain so that the area formed by its limit cycle is as small as possible or converges to the initial safe state, and the size of the limit cycle depends on the amplitude of the limit cycle; therefore, based on damping control, the risk control function is introduced in equation (5):

[0131]

[0132] In the formula, κ is the control variable.

[0133] First, a small parameter ε is introduced, and the multi-scale method is used to assume that the spatial approximate solution of equation (8) is:

[0134] x(t,ε)=x0(T0,T1)+εx1(T0,T1) (9)

[0135] Where, T n =ε n t(n=0,1) is the time scale.

[0136] The original time phase can be synthesized using different time scales; furthermore, by introducing the operator Transform formula (8) into:

[0137]

[0138] By simplifying and comparing the powers of various orders, we can get:

[0139]

[0140] Since the zero-order term x0 = αcost, the complex number form converted by Euler's formula is:

[0141]

[0142] In the formula, A(T1) does not include the T0 term, and its amplitude is a slow-varying process; Substituting it into formula (11) ε 1 The right side of the equation is:

[0143]

[0144] Where cc represents all conjugate terms.

[0145] Due to the existence of the Yongnian term, in order to eliminate the resonance phenomenon and ensure that the result does not diverge, let:

[0146]

[0147] In addition, A(T1) can be expressed as:

[0148]

[0149] Where, α and β are real functions of time scale T1;

[0150] Furthermore, formula (14) can be transformed into:

[0151]

[0152] Based on this, the limit cycle amplitude of the risk domain when the Rayleigh equation describes the change of system risk situation can be obtained:

[0153]

[0154] Based on the amplitude of the risk domain limit cycle obtained by the above derivation, adjust the control variable κ and the Rayleigh equation damping coefficient μ max The relationship between them can be used to control the risk domain of platooning vehicles from a system-level perspective. The specific implementation process of damping control based on the Rayleigh equation is as follows: Figure 1 shown.

[0155] Example 3

[0156] In this embodiment 3, a risk domain control method based on the risk cause analysis of train formation operation is provided to realize the initial exploration of the timely safety concept from identification, deduction to control in the field of rail transit. The risk domain control method based on the risk cause analysis of train formation operation includes:

[0157] Based on multi-sensor fusion technology, multi-dimensional operating status information of high-speed trains is perceived in real time, and vehicle-to-vehicle communication is established between trains running in virtual multiple-unit formations.

[0158] In-depth analysis of the various internal and external risks that may exist in the autonomous operation of a single vehicle and the coordinated operation of multiple vehicles in formation;

[0159] Taking the low efficiency of the anti-skid braking system under abnormal weather conditions and the failure to establish communication links between platooning vehicles as risk sources and the occurrence of collisions as accident results, a risk situation propagation model based on risk causal factors is constructed.

[0160] Based on the logical behavior and order of each risk node in the risk cause scenario, the situation propagation model based on risk cause factors is transformed into DBN. The status monitoring data of the VC-FAO system is continuously input into the DBN model as evidence information. It is assumed that each node is independent of its parent node, and the joint probability of all nodes can be obtained by multiplying the conditional probability of each node, which is specifically expressed as:

[0161]

[0162] Furthermore, it is assumed that each time node needs to satisfy the Markov assumption condition, and the current state is only related to the previous state, in order to reduce the complexity of DBN and improve the analysis efficiency, which is specifically expressed as:

[0163] P(X t+1 |X 0 ,X 1 ,…,X t )=P(X t+1 |X t )

[0164] Furthermore, assuming that each temporal node is stable within a single time slice, its conditional probability does not change, which can be specifically expressed as:

[0165]

[0166] Based on this, a DBN risk situation propagation model is constructed to continuously calculate the probability of each risk node in the network, and realize the DBN visualization update of the probability of collision accidents in the train formation operation scenario. Combined with the evolution process of risk-accident, DBN is used to simulate the process of risk scenario occurrence, and sensitivity analysis and sorting of each risk node are performed to determine the risk node with the greatest impact on the probability of collision accidents. The specific expression is:

[0167]

[0168] Furthermore, the nonlinear vibration theory and Rayleigh equation are used to describe the vibration characteristics and micro-evolution process of the VC-FAO system during the risk situation change process, and the risk state equation is constructed based on this. The sensitivity weight value μ of the risk node that has the greatest impact on the probability of train formation collision accidents is max As the damping coefficient of the Rayleigh equation, it describes the change process of the risk situation. It is specifically expressed as:

[0169]

[0170] As the changes in the spatiotemporal operation state accumulate, the system risk situation moves away from the initial safe state and shows an overall upward trend; and after a certain period of time, the system risk situation presents a stable limit cycle; the purpose of using the Rayleigh equation to control the risk domain of the VC-FAO system is to make the area formed by its limit cycle as small as possible or converge to the initial safe state (0,0), and the size of the limit cycle depends on the amplitude of the limit cycle; therefore, the risk control function is introduced based on damping control, which is specifically expressed as:

[0171]

[0172] Furthermore, the multi-scale method is used to solve the amplitude of the risk domain limit cycle when the Rayleigh equation is used to describe the change of system risk situation, which is specifically expressed as:

[0173]

[0174] Based on this, adjust the control variable κ and the Rayleigh equation damping coefficient μ max The relationship between them makes the limit cycle amplitude of the risk domain as small as possible, that is, the risk domain converges to the initial safe state (0,0) as much as possible, and then the risk domain of the platooning is controlled from the perspective of the system level.

[0175] Example 4

[0176] This embodiment 4 provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the risk domain control method based on the risk cause analysis of train formation operation as described above is implemented. The method includes:

[0177] In view of the multi-factor and cumulative nature of risks during train formation operation, a risk situation propagation model is constructed with the low efficiency of the anti-skid braking system in abnormal weather and the high delay in communication between train formation cars as risk sources, and the collision between train formation cars as accident results.

[0178] The dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and the sensitivity of each node in the risk situation propagation model is analyzed and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of collision accidents.

[0179] Based on the applicability of the Rayleigh equation to describe the risk situation changes of the VC-FAO system, the risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation.

[0180] Based on the risk state equation and damping control, the amplitude of the limit cycle of the risk domain is derived by introducing control variables, so that the risk domain constructed by the limit cycle can be as small as possible or converge to the initial safe state.

[0181] Example 5

[0182] This embodiment 5 provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, the processor calls the program instructions to execute the risk domain control method based on the risk cause analysis of train formation operation as described above, the method comprising:

[0183] In view of the multi-factor and cumulative nature of risks during train formation operation, a risk situation propagation model is constructed with the low efficiency of the anti-skid braking system in abnormal weather and the high delay in communication between train formation cars as risk sources, and the collision between train formation cars as accident results.

[0184] The dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and the sensitivity of each node in the risk situation propagation model is analyzed and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of collision accidents.

[0185] Based on the applicability of the Rayleigh equation to describe the risk situation changes of the VC-FAO system, the risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation.

[0186] Based on the risk state equation and damping control, the amplitude of the limit cycle of the risk domain is derived by introducing control variables, so that the risk domain constructed by the limit cycle can be as small as possible or converge to the initial safe state.

[0187] Example 6

[0188] This embodiment 6 provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for implementing the risk domain control method based on the risk cause analysis of train formation operation as described above, the method comprising:

[0189] In view of the multi-factor and cumulative nature of risks during train formation operation, a risk situation propagation model is constructed with the low efficiency of the anti-skid braking system in abnormal weather and the high delay in communication between train formation cars as risk sources, and the collision between train formation cars as accident results.

[0190] The dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and the sensitivity of each node in the risk situation propagation model is analyzed and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of collision accidents.

[0191] Based on the applicability of the Rayleigh equation to describe the risk situation changes of the VC-FAO system, the risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation.

[0192] Based on the risk state equation and damping control, the amplitude of the limit cycle of the risk domain is derived by introducing control variables, so that the risk domain constructed by the limit cycle can be as small as possible or converge to the initial safe state.

[0193] In summary, the risk domain control method based on train formation operation risk cause analysis is described in an embodiment of the present invention. Based on multi-sensor fusion technology, multi-dimensional running status information of trains is perceived in real time, and real-time interaction of adjacent train status information is achieved based on vehicle-to-vehicle communication technology. In view of the multi-factor and cumulative nature of risks during train formation operation, the low efficiency of the anti-skid braking system in abnormal weather and the failure to establish communication links between trains are taken as risk sources, and the collision between trains in formation is taken as the accident result, and a risk situation propagation model is constructed. Based on the evolution process of risk-accident, DBN is used to simulate the occurrence process of risk scenarios, and sensitivity analysis and ranking of each risk node are performed to determine the risk node with the greatest impact on the probability of collision accidents. In view of the fact that the risk situation of train formation operation is constantly changing, the nonlinear vibration theory and Rayleigh equation are used to describe the vibration characteristics and micro-evolution process of the VC-FAO system during the risk situation change process, and the risk state equation is constructed based on this, and the sensitivity weight value of the node with the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation. Based on the derivation of the limit cycle amplitude of the risk domain, the relationship between the control variable and the damping coefficient of the Rayleigh equation is explored to make the limit cycle amplitude as small as possible and the risk domain converges to the initial safe state. The present invention can realize risk domain control for train formation operation from a system-level perspective, reduce the dependence of risk research on accident data or expert knowledge, and provide guarantee for the intelligent, reliable and safe operation of flexible train formations.

[0194] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0195] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0196] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0197] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0198] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative work on the basis of the technical solution disclosed in the present invention should be included in the scope of protection of the present invention.

Claims

1. A risk domain control method based on risk cause analysis of train formation operation, characterized in that: include: In view of the multi-factor and cumulative nature of risks during train formation operation, a risk situation propagation model is constructed with the low efficiency of the anti-skid braking system in abnormal weather and the high delay in communication between train formation cars as risk sources, and the collision between train formation cars as accident results. The dynamic Bayesian network is used to simulate the occurrence process of risk scenarios, and the sensitivity of each node in the risk situation propagation model is analyzed and sorted according to its sensitivity to determine the risk node with the greatest impact on the probability of collision accidents. Based on the applicability of the Rayleigh equation to describe the risk situation changes of the VC-FAO system, the risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of collision accidents is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation. Based on the risk state equation and damping control, the amplitude of the limit cycle of the risk domain is derived by introducing control variables, so that the risk domain constructed by the limit cycle can be as small as possible or converge to the initial safe state.

2. The risk domain control method based on train formation operation risk cause analysis according to claim 1 is characterized in that: Construct a risk situation communication model, including: Based on the risk causes and accident consequences, a risk scenario is assumed: it is assumed that the automatic monitoring system issues formation instructions to two trains running in moving block mode through the area controller and trackside communication equipment; based on the risk scenario, the evolution process of risk-accident is deduced; the deduced evolution process of risk-accident is converted into a risk situation propagation model based on risk causal factors.

3. The risk domain control method based on train formation operation risk cause analysis according to claim 2 is characterized in that: Based on the risk scenario, the evolution process of risk-accident is simulated, including: the two trains confirm and start the car-to-car communication equipment respectively, but the car-to-car communication equipment of the front car has high delay due to the abnormal occupation of the car-to-car communication equipment of the rear car and in abnormal weather conditions, and the car-to-car communication link between the platoon workshop fails to be established; at the same time, the environmental monitoring system detects that the front car is slipping due to the influence of the track adhesion coefficient, reports to ZC and ATS, and sets a temporary speed limit to implement braking; but due to the failure to establish the car-to-car communication link, the rear car cannot obtain the changes in the running status of the front car in time, and still judges that it is running according to the predetermined trajectory, and accelerates to catch up according to the formation instruction, which leads to a reduction in the running interval and the occurrence of a collision accident.

4. The risk domain control method based on train formation operation risk cause analysis according to claim 1 is characterized in that: Identify the risk nodes that have the greatest impact on the probability of a collision accident, including: The situation propagation model based on risk causal factors is transformed into DBN based on logical behavior and sequence, and the status monitoring data of the VC-FAO system is continuously input into the DBN model as evidence information; Assuming that each node is independent of its parent node, the joint probability of all nodes is obtained by multiplying the conditional probability of each node; It is assumed that each time node must satisfy the Markov assumption and the current state is only related to the previous state, so as to reduce the complexity of DBN and improve the analysis efficiency. Assuming that each temporal node is stable within a single time slice, its conditional probability does not change; Based on the assumptions, a DBN risk situation propagation model is constructed, and the status of each risk node in the network is continuously calculated to achieve dynamic Bayesian network visualization update of the probability of collision accidents in train formation operation scenarios.

5. The risk domain control method based on train formation operation risk cause analysis according to claim 4 is characterized in that: Since the parameters of each node in DBN will change over time, it is necessary to dynamically add evidence nodes at different times and consider the situation changes in adjacent time slices. Then, the sensitivity weight of each risk node in DBN can be calculated, and the risk nodes with the greatest impact on the probability of train formation collision accidents and their sensitivity weight values ​​can be sorted.

6. The risk domain control method based on train formation operation risk cause analysis according to claim 1 is characterized in that: Based on the applicability of the Rayleigh equation to describe the changes in the risk situation of the VC-FAO system, the risk state equation of the VC-FAO system is constructed, and the sensitivity weight value of the node that has the greatest impact on the probability of a collision accident is used as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation, including: using nonlinear vibration theory and the Rayleigh equation to describe the vibration characteristics and its microscopic evolution process during the change of the risk situation of the VC-FAO system, and constructing the risk state equation based on this; considering that the phase plane technology can intuitively observe the relationship between state variables and the changes of state variables over time; converting the risk state equation into a first-order differential equation containing only state variables; formula The system damping term in the process is negative when it is small, but positive when it is large enough. This means that when using the Rayleigh equation to describe the change of the system risk state, there is a moment when the damping term changes rapidly from positive to negative or vice versa, that is, there is a mutation. Using the Reynolds construction method, the zero-slope isocline in the phase plane can be obtained, which proves that the Rayleigh equation is also applicable to describing the risk situation changes of the VC-FAO system while satisfying the sharp mutation, and after a period of time, its phase trajectory will maintain periodic motion. In addition, since each point in the phase trajectory contains the risk state of the system at the current moment and the changing trend of the risk state, it can constitute the system risk domain.

7. The risk domain control method based on train formation operation risk cause analysis according to claim 1 is characterized in that: Based on the risk state equation and damping control, by introducing control variables, the amplitude of the limit cycle of the risk domain is derived, so that the risk domain constructed by the limit cycle is as small as possible or converges to the initial safe state, including: introducing a risk control function into the risk state equation based on damping control, introducing small parameters, and using the multi-scale method to obtain the spatial approximate solution of the risk control function; for the original time phase, different time scales are used to synthesize it; the limit cycle amplitude of the risk domain when the Rayleigh equation describes the change of the system risk situation is obtained, and by adjusting the relationship between the control variable and the damping coefficient of the Rayleigh equation, the risk domain of the platoon can be controlled from a system level perspective.

8. A risk domain control system based on risk cause analysis of train formation operation, characterized in that: include: The construction module is used to construct a risk situation propagation model based on the multi-factor and cumulative nature of risks during train formation operation, with low efficiency of the anti-skid braking system in abnormal weather and high communication delay between train formation cars as risk sources, and collision between train formation cars as accident results; The sorting module is used to simulate the occurrence process of risk scenarios using a dynamic Bayesian network, perform sensitivity analysis on each node in the risk situation propagation model and sort them according to their sensitivity, and determine the risk nodes that have the greatest impact on the probability of collision accidents; The deduction module is used to deduce the risk situation change of the VC-FAO system, construct the risk state equation of the VC-FAO system, and use the sensitivity weight value of the node with the greatest impact on the probability of collision accidents as the damping coefficient of the Rayleigh equation to describe the change process of the risk situation; The control module is used to integrate the risk state equation and damping control from the system level to realize the control of the risk domain of the platoon. By introducing control variables, the amplitude of the limit cycle of the risk domain is derived to make the risk domain constructed by the limit cycle as small as possible or converge to the initial safe state.

9. A computer device, characterized in that: It includes a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the risk domain control method based on train formation operation risk cause analysis as described in any one of claims 1-7.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the risk domain control method based on the risk cause analysis of train formation operation as described in any one of claims 1-7.

Images