Method for Evaluating the Mitigation Effectiveness of UAV Operation Risks Based on Bayesian Network

Abstract

The present invention discloses a method for evaluating the risk mitigation effectiveness of UAV operations based on a Bayesian network, belonging to the technical field of UAV risk assessment, and comprising the following steps: obtaining a UAV operation accident report and identifying the risk factors in the UAV operation accident report; constructing an accident causal influence diagram according to the risk factors in the UAV operation accident report; constructing a Bayesian belief network according to the accident causal influence diagram; correspondingly adding mitigation measures to the risk factors in the Bayesian belief network, and obtaining the risk mitigation effectiveness of all mitigation measures for the occurrence of accidents by estimating and updating the probabilities of the risk factors and the occurrence of accidents. The present invention solves the problem that the evaluation of the risk mitigation effectiveness of UAV operations is not accurate and comprehensive enough.

Description

Technical Field

[0001] The present invention belongs to the technical field of UAV risk assessment, and particularly relates to a method for evaluating the risk mitigation effectiveness of UAV operations based on a Bayesian network. Background Art

[0002] The effectiveness evaluation of risk mitigation measures aims to verify whether the currently implemented measures have achieved the expected effects, and it can provide a basis for timely adjusting strategies to avoid risk accumulation caused by inefficient measures when the risk mitigation measures fail to reduce risks as scheduled.

[0003] The risk assessment of UAV operations can be divided into two methods: quantitative and qualitative. The qualitative risk assessment process enables UAV operators to conduct an initial risk assessment of their operation scenarios according to their processes, thus ensuring the safe operation of UAVs. However, the qualitative UAV risk assessment relies on subjective judgments and expert opinions, and different assessors may have different interpretations of risks, which are prone to deviations and limitations. Therefore, the qualitative assessment cannot accurately quantify risks, is difficult to accurately compare risks or determine the priority of risks, and moreover, due to different airspace operation conditions, the qualitative risk assessment may affect the accuracy of the final assessment results, thus possibly ultimately hindering the decision-making of UAVs and the allocation of airspace resources. The quantitative risk assessment of UAV operations is achieved through probability estimation, and at the same time, it allows the system to be analyzed in a more correct way. Most safety assessments are achieved through qualitative analysis, but such assessment methods have problems of being incomplete and inaccurate, and still require quantitative supplementary analysis. Summary of the Invention

[0004] Aiming at the above deficiencies in the prior art, the present invention provides a method for evaluating the risk mitigation effectiveness of UAV operations based on a Bayesian network, which solves the problem of inaccurate and incomplete evaluation of the risk mitigation effectiveness of UAV operations.

[0005] In order to achieve the above invention purpose, the technical solution adopted by the present invention is as follows:

[0006] A method for evaluating the risk mitigation effectiveness of UAV operations based on a Bayesian network provided by the present invention includes the following steps:

[0007] S1. Obtain the UAV operation accident report and identify the risk factors in the UAV operation accident report;

[0008] S2. Construct an accident causal influence diagram according to the risk factors in the UAV operation accident report;

[0009] S3. Construct a Bayesian belief network according to the accident causal influence diagram;

[0010] S4. Add corresponding mitigation measures to the risk factors in the Bayesian belief network, and obtain the risk mitigation effectiveness of all mitigation measures for accident occurrence by estimating and updating the probabilities of risk factors and accidents.

[0011] Further, the risk factors in the drone operation accident report include operation environment factors, operation factors, and facility and equipment factors.

[0012] Further, the S3 includes the following steps:

[0013] S31. Obtain the accident causal influence diagram;

[0014] S32. Construct a single-factor influence conditional probability model to calculate the conditional probability of a single risk factor in the accident causal influence diagram causing a drone operation accident;

[0015] S33. Based on the single-factor influence conditional probability model, construct a multi-factor influence conditional probability model to calculate the conditional probability of multiple risk factors causing a drone operation accident;

[0016] S34. According to the multi-factor influence conditional probability model, construct shape parameter optimization constraints and calculate the target first shape parameter and target second shape parameter;

[0017] S35. Based on the conditional probability of a single risk factor causing a drone operation accident, the conditional probability of multiple risk factors causing a drone operation accident, the target first shape parameter, and the target second shape parameter, complete the construction of the Bayesian belief network.

[0018] Further, the calculation expression of the single-factor influence conditional probability model in S32 is as follows:

[0019] ,

[0020] where, represents the conditional probability of an accident occurring in the case of the existence of a risk factor ; represents the joint probability of the accident and the risk factor occurring simultaneously, represents the probability of the risk factor occurring.

[0021] Further, the calculation expression of the multi-factor influence conditional probability model in S33 is as follows:

[0022] ,

[0023] , ​,

[0024] Among them, represents the conditional probability of an accident occurring when n risk factors exist simultaneously of, represents the first risk factor, represents the second risk factor, represents the nth risk factor, represents the ratio of the conditional probability of a multi-factor accident, represents the first shape parameter, represents the second shape parameter, represents the differentiation with respect to time t, represents the beta function with respect to the first shape parameter and the second shape parameter, represents the sum of the conditional probabilities of an accident occurring under the first n risk factors of, represents the sum of the conditional probabilities of an accident occurring under a total of m risk factors of, represents the gamma function, represents the value of the gamma function at the first shape parameter, represents the value of the gamma function at the second shape parameter, represents the value of the gamma function at the sum of the first shape parameter and the second shape parameter, where and are both greater than 0, m > n, and both m and n are positive integers.

[0025] Furthermore, the calculation expression of the shape parameter optimization constraint in S34 is as follows:

[0026] ,

[0027] ,

[0028] where min represents taking the minimum value, represents the estimated probability of a multi-factor accident, represents the true probability of a multi-factor accident, where k is a positive integer.

[0029] Furthermore, the Bayesian belief network is a directed acyclic graph composed of a set of links and probability distributions on several nodes; each of the nodes corresponds to the probability distribution of the accident occurrence state and the probability distributions of the occurrence states of each risk factor.

[0030] Furthermore, S4 includes the following steps:

[0031] S41. Use the probability distributions of the occurrence states of the risk factors corresponding to each node in the Bayesian belief network and the probability distribution of the accident occurrence state as the prior probability of the occurrence state of the risk factors and the prior probability of the accident occurrence state respectively;

[0032] S42. Set mitigation measures for the nodes corresponding to the risk factors in the Bayesian belief network to obtain a Bayesian network for evaluating mitigation effectiveness;

[0033] S43. Obtain other UAV accident cases caused by the risk factors corresponding to the mitigation measures, and based on the prior probability of the occurrence state of the risk factors, use the Bayesian belief network for evaluating mitigation effectiveness to estimate and update the probability distributions of the occurrence states of the risk factors and the probability distribution of the accident occurrence state along the link for the nodes corresponding to the risk factors, as the updated probability of the occurrence state of the risk factors and the updated probability of the accident occurrence state;

[0034] S44. Calculate the risk mitigation effectiveness of all mitigation measures for accident occurrence according to the updated probability of the accident occurrence state and the prior probability of the accident occurrence state.

[0035] Further, the calculation expression of the updated probability of the occurrence state of the risk factors in S43 is as follows:

[0036] ,

[0037] where, represents the updated probability of the occurrence state of the risk factor corresponding to the j-th node after the k-th mitigation measure is added, represents the likelihood of adding the k-th mitigation measure in the presence of the risk factor corresponding to the j-th node, represents the prior probability of the occurrence state of the risk factor corresponding to the j-th node, represents the probability of the occurrence of other UAV accident cases caused by the risk factor corresponding to the k-th mitigation measure, where k is a positive integer.

[0038] Further, the calculation expression of the risk mitigation effectiveness of all mitigation measures for accident occurrence is as follows:

[0039] ,

[0040] where, represents the risk mitigation effectiveness of all mitigation measures for accident occurrence, represents the updated probability of the accident occurrence state, represents the prior probability of the accident occurrence state.

[0041] The beneficial effects of the present invention are as follows: A method for evaluating the risk mitigation effectiveness of UAV operation based on Bayesian network provided by the present invention realizes a comprehensive analysis of accidents caused by risk factors during UAV operation through functional safety qualitative evaluation combined with quantitative analysis; the present invention constructs a Bayesian belief network to reflect the correlation mechanism between the occurrence probabilities of risk factors and between the occurrence probability of risk factors and the occurrence probability of accidents, quantifies the influence probability of each risk factor on the UAV operation accident risk, and analyzes the reduction degree of the risk of occurrence of risk factors and the risk of occurrence of accidents after adding mitigation measures based on the Bayesian belief network, and can accurately and comprehensively evaluate the risk mitigation effectiveness of the mitigation measures adopted by the UAV during operation in the airport terminal area.

[0042] Other advantages of the present invention will be analyzed in more detail in the subsequent embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a flowchart of the steps of a method for evaluating the risk mitigation effectiveness of UAV operation based on Bayesian network in an embodiment of the present invention.

[0045] Figure 2 It is a node schematic diagram of the Bayesian belief network in an embodiment of the present invention.

[0046] Figure 3 It is a schematic diagram of the probability distribution of the risk factors corresponding to each node and the occurrence of accidents in the Bayesian belief network in an embodiment of the present invention.

[0047] Figure 4 It is a node schematic diagram of the Bayesian network for evaluating mitigation effectiveness in an embodiment of the present invention.

[0048] Figure 5 It is a schematic diagram of the updated probability distribution of the risk factors corresponding to each node and the occurrence of accidents in the Bayesian network for evaluating mitigation effectiveness after adding mitigation measures in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Usually, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0050] As Figure 1 shown, in an embodiment of the present invention, the present invention provides a method for evaluating the effectiveness of mitigating the operation risks of unmanned aerial vehicles based on a Bayesian network, including the following steps:

[0051] S1. Obtain the unmanned aerial vehicle operation accident report and identify the risk factors in the unmanned aerial vehicle operation accident report;

[0052] In this solution, the unmanned aerial vehicle operation accident report includes the accident report of the unmanned aerial vehicle operating near the airport terminal area and the accident report in the database provided by the unmanned aerial vehicle accident website as a supplement; the unmanned aerial vehicle accident report includes the scenario of a single accident case or a composite scenario containing the common risk factors in multiple accident cases.

[0053] The risk factors in the unmanned aerial vehicle operation accident report include operation environment factors, operation factors, and facility and equipment factors.

[0054] In this solution, the operation environment factors include weather condition factors, airspace factors, obstacle factors, bird strike factors, etc.; the human factors include operation error factors, violation of airspace regulations factors, technical deficiency factors, etc.; the facility and equipment factors include electromagnetic interference factors, remote communication failure factors, brake system failure factors, flight control system failure factors, navigation ability failure factors, power shortage factors, etc.

[0055] S2. Construct an accident causal influence diagram according to the risk factors in the unmanned aerial vehicle operation accident report;

[0056] In this solution, the accident causal influence diagram is used to depict the interaction between each risk factor and the corresponding accident, and provides a basis for constructing a Bayesian belief network.

[0057] S3. Construct a Bayesian belief network according to the accident causal influence diagram;

[0058] In this scheme, the Bayesian belief network is used to simulate the complex interaction of risk factors that lead to accidents in drone aviation systems. The Bayesian belief network is suitable for decomposing the occurrence of accidents into a series of relatively simple risk factors through probabilistic reasoning to solve the complex joint probability distribution problem, thereby solving the problem of lack of drone operation data and uncertainty.

[0059] The S3 comprises the following steps:

[0060] S31. Obtaining an accident causal impact diagram;

[0061] In this embodiment, the accident report of drone aviation safety and the ASN database are combined to estimate the prior probability and conditional probability of the risk factors. Since the number of accidents reported in the ASN database is limited, the data cannot cover the probability of all different types of events or all accidents. Therefore, the conditional probability derived only by the data in the database may make the result inaccurate. Therefore, this solution provides a conditional probability calculation model to calculate the conditional probability affected by multiple risk factors. ASN, Aviation Safety Network is a professional website in the field of aviation safety and an important source of information in the field of aviation safety. The ASN database contains a lot of detailed information on aviation accidents, aircraft failures, hijacking incidents, etc., aiming to provide a comprehensive and reliable information platform for the public, airlines, regulators and researchers.

[0062] S32. Construct a single factor influence conditional probability model to calculate the conditional probability that a single risk factor in the accident causal influence diagram leads to a UAV operation accident;

[0063] The calculation expression of the single factor influence conditional probability model in S32 is as follows:

[0064] ,

[0065] in, Indicates the presence of risk factors Accidents The conditional probability of Indicates an accident and risk factors The joint probability of simultaneous occurrence, Indicates risk factors Probability of occurrence.

[0066] In this scenario, accidents and risk factors Joint probability of simultaneous occurrence and risk factors Probability of occurrence All of them can be obtained through the data in the ASN accident database.

[0067] In this embodiment, the single - factor influence conditional probability model can quantify the influence of a single risk factor on the occurrence of UAV operation accidents. Taking the UAV out - of - control operation accident as an example, this accident may be caused by multiple risk factors, such as brake system failure factor, electromagnetic interference factor, flight control system failure factor, remote communication failure factor, etc. Using the single - factor influence conditional probability model to separately focus on the conditional probability of the brake system failure factor on the UAV out - of - control operation accident, the corresponding calculation expression is as follows:

[0068] ,

[0069] where, represents the probability of an out - of - control operation accident occurring under the brake system failure factor, represents the joint probability of an out - of - control operation accident and the brake system failure factor occurring simultaneously, represents the probability of the brake system failure factor occurring.

[0070] S33. Based on the single - factor influence conditional probability model, construct a multi - factor influence conditional probability model to calculate the conditional probability of multiple risk factors causing UAV operation accidents;

[0071] The calculation expression of the multi - factor influence conditional probability model in S33 is as follows:

[0072] ,

[0073] , ,

[0074] where, represents the conditional probability of an accident occurring when n risk factors exist simultaneously ; represents the first risk factor, represents the second risk factor, represents the nth risk factor, represents the multi - factor accident conditional probability ratio, represents the first shape parameter, represents the second shape parameter, represents taking the differential with respect to time t, represents the beta function with respect to the first shape parameter and the second shape parameter, represents the sum of the conditional probabilities of an accident occurring under the first n risk factors ; represents the sum of the conditional probabilities of an accident occurring under the total m risk factors ; represents the gamma function, represents the value of the gamma function at the first shape parameter, represents the value of the gamma function at the second shape parameter, represents the value of the gamma function at the sum of the first shape parameter and the second shape parameter, where and are both greater than 0, m > n, and both m and n are positive integers.

[0075] In this embodiment, since each risk factor is independent of each other, each risk factor may cause an accident to occur to varying degrees, and the risk factors are not mutually exclusive. Therefore, when an accident is caused by multiple risk factors, it is necessary to satisfy: (1) when the number of risk factors of the accident increases, the probability of the accident occurring increases; (2) the impact of each risk factor on the occurrence of the accident should be considered within the conditional probability; (3) the situation of the accident occurring needs to be compatible with special situations at the same time. The beta distribution selected in this solution can meet the above requirements. By using the cumulative distribution function of the beta distribution as a non-linear function, defined on the interval [0, 1], the probability density is controlled by the first shape function and the second shape function.

[0076] S34. According to the multi-factor influence conditional probability model, construct shape parameter optimization constraints, and calculate to obtain the target first shape parameter and the target second shape parameter;

[0077] The calculation expression of the shape parameter optimization constraints in S34 is as follows:

[0078] ,

[0079] ,

[0080] where min represents taking the minimum value, represents the multi-factor accident estimated probability, represents the multi-factor accident true probability, where k is a positive integer.

[0081] In this embodiment, the values of the target first shape parameter and the target second shape parameter optimized by the shape parameter optimization constraints are 0.92797 and 0.14121 respectively, and the error variance between the multi-factor accident estimated probability and the multi-factor accident true probability fitted based on the target first shape parameter and the target second shape parameter is 3.56608×10 -7 , which indicates that the Beta function fits well with the observed conditional probability. The simulation results also show that the values of the cumulative distribution function of the beta function almost completely match the data points of the multi-factor accident estimated probability.

[0082] S35. Based on the conditional probability of a UAV operation accident caused by a single risk factor, the conditional probability of a UAV operation accident caused by multiple risk factors, the target first shape parameter, and the target second shape parameter, construct a Bayesian belief network.

[0083] In this solution, the Bayesian belief network represents UAV operation accidents and risk factors as a series of random variables and the dependencies between the random variables through probability modeling.

[0084] The Bayesian belief network is a directed acyclic graph composed of a set of links and probability distributions on several nodes; each of the nodes corresponds to the probability distribution of the accident occurrence state and the probability distribution of the occurrence states of each risk factor.

[0085] As Figure 2 shown, by way of example, the Bayesian belief network constructed in this embodiment includes: an accident occurrence node, an other aircraft in airspace node, a system component failure node, a pilot error node, an insufficient operation technical level node, an obstacle node, an extreme weather node, a bird strike node, a power shortage node, a remote communication failure node, a flight control system failure node, an electromagnetic interference node, a brake system failure node, and an illegal intrusion node;

[0086] The other aircraft in airspace node, the illegal intrusion node, and the insufficient operation technical level node all point to the accident occurrence node; the obstacle node points to the system component failure node; the extreme weather node points to the system component failure node and the operation system failure node respectively; the bird strike node points to the system component failure node; the power shortage node points to the operation system failure node and the flight control system failure node respectively; the remote communication failure node, the flight control system failure node, the electromagnetic interference node, and the brake system failure node all point to the operation system failure node; the system component failure node and the operation system failure node both point to the accident occurrence node; the pilot error node points to the operation system failure node and the accident occurrence node respectively.

[0087] S4. Corresponding mitigation measures are added to the risk factors in the Bayesian belief network, and by estimating and updating the probabilities of the risk factors and the occurrence of accidents, the risk mitigation effectiveness of all mitigation measures for the occurrence of accidents is obtained.

[0088] The S4 includes the following steps:

[0089] S41. The probability distributions of the occurrence states of the risk factors corresponding to each node in the Bayesian belief network and the probability distribution of the accident occurrence state are respectively used as the prior probability of the occurrence state of the risk factor and the prior probability of the accident occurrence state;

[0090] As Figure 3As shown in the figure, in this embodiment, by way of example, the probability of the YES state of an accident occurring in the Bayesian belief network is 38%, and the probability of the NO state of an accident occurring is 62%. The probability of the YES state of the occurrence of risk factors of other aircraft in the airspace is 32%, and the probability of the NO state of the occurrence of risk factors of other aircraft in the airspace is 68%. Among them, the YES state is the state that may occur, and the NO state is the state that cannot occur.

[0091] S42. Set mitigation measures for the nodes corresponding to the risk factors in the Bayesian belief network to obtain a Bayesian network for evaluating mitigation effectiveness;

[0092] As Figure 4 shown in the figure, in this embodiment, five corresponding risk mitigation measures are formulated for the risk factors that cause UAV accidents: The first measure M1 is to use a four-dimensional meteorological data system to provide weather information for ATM decision-making and help decision-makers judge whether the operation is safe; the second measure M2 is to use a detection and collision avoidance system, which can effectively replace the environmental perception ability of manned aircraft; the third measure M3 is to set up a geofence system to prevent the terminal area from being invaded by UAVs; the fourth measure M4 is to set up an electromagnetic protection system to prevent UAVs from losing control due to electromagnetic interference; the fifth measure M5 is to set up an automatic emergency braking system to make the UAV stop urgently or hover urgently when it loses control to avoid accidents.

[0093] S43. Obtain other UAV accident cases caused by the risk factors corresponding to the mitigation measures, and based on the prior probability of the occurrence state of the risk factors, use the Bayesian belief network for evaluating mitigation effectiveness to estimate and update the probability distribution of the occurrence state of the risk factors and the probability distribution of the accident occurrence state along the link for the nodes corresponding to the risk factors, as the updated probability of the occurrence state of the risk factors and the updated probability of the accident occurrence state;

[0094] As Figure 5 shown in the figure, by way of example, in this solution, five mitigation measures are added to the Bayesian belief network, and this is used as evidence for causal inference to predict the change in the accident occurrence probability. For example, after the UAV is equipped with a detection and collision avoidance device, it can effectively avoid the approach of other aircraft and obstacles in the airspace, which means that the probability of the YES state of the occurrence of risk factors corresponding to the nodes of other aircraft in the airspace and the obstacle nodes will be estimated and updated to 0%, and it affects the probability distribution of the occurrence state of the risk factors corresponding to the backward nodes and the probability distribution of the accident occurrence state. Finally, the probability of the YES state of the accident occurrence in this example is reduced to 20%. By using the Bayesian belief network for evaluating mitigation effectiveness to estimate and update the probability distribution of the occurrence state of the risk factors and the probability distribution of the accident occurrence state after adding the mitigation measures, it effectively reveals the degree of backward verification influence of the UAV accident case on the target node.

[0095] The calculation expression for the updated probability of the occurrence status of risk factors in S43 is as follows:

[0096] ,

[0097] where, represents the updated probability of the occurrence status of the risk factor corresponding to the j-th node after the k-th mitigation measure is added, represents the likelihood of adding the k-th mitigation measure in the case of the risk factor corresponding to the j-th node existing, represents the prior probability of the occurrence status of the risk factor corresponding to the j-th node, represents the probability of other UAV accident cases caused by the risk factor corresponding to the k-th mitigation measure, where k is a positive integer. In this solution, the updated probability of the accident occurrence status can be estimated and updated backward based on the updated probability of the occurrence status of the risk factor.

[0098] S44. Calculate the risk mitigation effectiveness of all mitigation measures for the accident occurrence based on the updated probability of the accident occurrence status and the prior probability of the accident occurrence status.

[0099] The calculation expression for the risk mitigation effectiveness of all mitigation measures for the accident occurrence is as follows:

[0100] ,

[0101] where, represents the risk mitigation effectiveness of all mitigation measures for the accident occurrence, represents the updated probability of the accident occurrence status, represents the prior probability of the accident occurrence status.

[0102] In this solution, based on the UAV operation accident report and the risk factors in the report, an accident causal influence diagram and a Bayesian belief network are constructed, and through the analysis of adding mitigation measures, a comprehensive qualitative and quantitative analysis of the risk mitigation effectiveness of UAV operation risks is realized, and the risk mitigation effectiveness of the mitigation measures adopted by UAVs in the airport terminal area operation can be accurately and comprehensively evaluated.

[0103] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network, characterized in that: The steps include: S1. Obtain UAV operation accident reports and identify the risk factors in the UAV operation accident reports; S2. Construct an accident cause-effect impact diagram based on the risk factors in the UAV operation accident report; S3. Construct a Bayesian belief network based on the accident causal impact diagram; S4. Add mitigation measures to the corresponding risk factors in the Bayesian belief network, and obtain the risk mitigation effectiveness of all mitigation measures for the occurrence of accidents by estimating and updating the risk factors and the probability of accidents. The S4 comprises the following steps: S41, corresponding the probability distribution of the hazardous factor occurrence state and the probability distribution of the accident occurrence state corresponding to each node in the Bayesian belief network as the prior probability of the hazardous factor occurrence state and the prior probability of the accident occurrence state; S42, setting mitigation measures to nodes corresponding to risk factors in the Bayesian belief network to obtain a mitigation effectiveness evaluation Bayesian network; S43. Obtain other drone accident cases caused by the risk factors corresponding to the mitigation measures, and based on the prior probability of the risk factor occurrence state, use the mitigation effectiveness evaluation Bayesian belief network to estimate and update the risk factor occurrence state probability distribution and accident occurrence state probability distribution along the link for the nodes corresponding to the risk factor, as the risk factor occurrence state update probability and accident occurrence state update probability; S44. Based on the updated probability of the accident occurrence state and the prior probability of the accident occurrence state, the risk mitigation effectiveness of all mitigation measures for the accident occurrence is calculated.

2. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 1 is characterized in that: The risk factors in the UAV operation accident report include operating environment factors, operation factors and facility and equipment factors.

3. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 1 is characterized in that: The S3 comprises the following steps: S31. Obtaining an accident causal impact diagram; S32. Construct a single factor influence conditional probability model to calculate the conditional probability that a single risk factor in the accident causal influence diagram leads to a UAV operation accident; S33. Based on the single-factor influence conditional probability model, a multi-factor influence conditional probability model is constructed to calculate the conditional probability of multiple dangerous factors leading to UAV operation accidents; S34, constructing shape parameter optimization constraints according to a multi-factor influence conditional probability model, and calculating a target first shape parameter and a target second shape parameter; S35. Based on the conditional probability of a single hazardous factor leading to a UAV operation accident, the conditional probability of multiple hazardous factors leading to a UAV operation accident, the target first shape parameter and the target second shape parameter, the construction of the Bayesian belief network is completed.

4. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 3 is characterized in that: The calculation expression of the single factor influence conditional probability model in S32 is as follows: ， in, Indicates the presence of risk factors Accidents The conditional probability of Indicates an accident and risk factors The joint probability of simultaneous occurrence, Indicates risk factors Probability of occurrence.

5. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 3 is characterized in that: The calculation expression of the multi-factor influence conditional probability model in S33 is as follows: ， ， ， in, Indicates simultaneous existence n Accidents occur when there are multiple risk factors The conditional probability of Indicates the first risk factor, Indicates the second risk factor, Indicates n risk factors, represents the conditional probability ratio of multi-factor accidents, represents the first shape parameter, represents the second shape parameter, Indicates time t Find the differential, represents the beta function with respect to the first shape parameter and the second shape parameter, Before n Accidents caused by risk factors The sum of the conditional probabilities of Indicates the total m Accidents caused by risk factors The sum of the conditional probabilities of represents the gamma function, represents the value of the gamma function at the first shape parameter, represents the value of the gamma function at the second shape parameter, represents the value of the gamma function at the sum of the first shape parameter and the second shape parameter, where and are greater than 0, m > n , m and n All are positive integers.

6. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 3 is characterized in that: The calculation expression of the shape parameter optimization constraint in S34 is as follows: ， ， in, min Indicates taking the minimum value, represents the estimated probability of multi-factor accidents, represents the true probability of multi-factor accidents, where k Is a positive integer.

7. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 3 is characterized in that: The Bayesian belief network is a directed acyclic graph consisting of a set of links and probability distributions on a number of nodes; each of the nodes corresponds to the probability distribution of the accident occurrence state and the probability distribution of the occurrence state of each risk factor.

8. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 1 is characterized in that: The calculation expression of the probability of updating the state of the risk factor in S43 is as follows: ， in, Indicates k After the mitigation measures were added j The probability of state update of the risk factor corresponding to each node, Indicates the existence of j If the risk factor corresponding to the node is k The likelihood of a mitigation measure, Indicates j The prior probability of the occurrence state of the risk factor corresponding to each node is Indicates k The probability of other drone accident cases caused by the risk factors corresponding to the mitigation measures, among which, k Is a positive integer.

9. The method for evaluating the effectiveness of UAV operation risk mitigation based on Bayesian network according to claim 1, characterized in that: The calculation expression of the risk mitigation effectiveness of all the mitigation measures for accidents is as follows: ， in, It indicates the risk mitigation effectiveness of all mitigation measures for accidents. represents the probability of updating the accident status. Represents the prior probability of the accident occurrence state.

Images