Large recreation facility hazard source identification and risk assessment method

Abstract

The invention discloses a large recreation facility hazard source identification and risk assessment method. The method comprises the following steps: firstly, identifying hazard sources of the large recreation facility to obtain a hazard source set; then, training according to the historical fault data of each hazard source in the hazard source set to obtain a risk level evaluation model corresponding to each hazard source; and finally, obtaining operation state data of the to-be-tested large recreation facility, performing one-to-one risk assessment by using the risk level assessment model of each hazard source, obtaining a risk level of each hazard source, and generating a risk assessment result of the large recreation facility. According to the invention, accurate identification and dynamic risk assessment of the hazard source are realized, and systematic and scientific technical support is provided for safety management of large recreation facilities.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment safety management and is a risk assessment method for characteristic equipment, and in particular relates to a hazard source identification and risk assessment method for large-scale amusement facilities. Background Art

[0002] As the scale of amusement facilities expands and their complexity increases, their safety management faces unprecedented challenges. The operation of these facilities involves multi-dimensional factors such as equipment structure, personnel operation and environmental conditions, and the potential sources of danger are numerous and highly dynamic. At present, the management and evaluation of hazard sources mostly rely on empirical judgment or static data analysis, lacking systematic and dynamic technical support. This traditional method is difficult to meet the safety protection needs of complex facilities in high-risk scenarios, resulting in incomplete identification of hazard sources and inaccurate risk assessment. Therefore, there is an urgent need for a dynamic hazard source identification and evaluation method based on modern data technology and risk management theory to improve the scientificity and efficiency of facility safety management. Summary of the invention

[0003] In order to solve the problems of incomplete hazard source identification, inaccurate risk assessment and insufficient dynamic update in the prior art, the present invention proposes a comprehensive hazard source identification and risk assessment method for super-large amusement facilities.

[0004] The technical solution of the present invention is as follows:

[0005] 1. A method for hazard identification and risk assessment of large-scale amusement facilities

[0006] S1: Identify the hazard sources of large amusement facilities and obtain a set of hazard sources;

[0007] S2: Train the risk level assessment model corresponding to each hazard source according to the historical failure data of each hazard source in the hazard source set;

[0008] S3: Obtain the operating status data of the large-scale amusement facility to be tested, use the risk level assessment model of each hazard source to assess the risks one by one, obtain the risk level of each hazard source, and then generate the risk assessment result of the large-scale amusement facility.

[0009] The S1 is specifically:

[0010] The HAZOP analysis method is used to identify equipment, personnel and environmental hazards in the accident case investigation reports of large-scale amusement facilities in previous years, and the first hazard source set is obtained; and the TRIZ failure analysis method is used to analyze the potential failure mechanism of equipment in large-scale amusement facilities, and the second hazard source set is obtained. After combining the first hazard source set and the second hazard source set and removing duplicates, the final hazard source set is obtained;

[0011] In S2, for each hazard source in the hazard source set, the training process of the risk level assessment model is as follows:

[0012] The historical fault data of the current hazardous source is obtained, and after data preprocessing and feature extraction of the historical fault data, the fault feature data is obtained, thereby obtaining a training data set; the SVM model is trained using the training data set to obtain a trained SVM model and use it as a risk level assessment model for the hazardous source.

[0013] In the SVM model, the radial basis function is used as the kernel function.

[0014] In the SVM model, the generated decision function value is converted into a risk value using the following formula:

[0015]

[0016] Among them, MinValue and MaxValue are the minimum decision function value and the maximum decision function value respectively;

[0017] If the risk value is less than or equal to the risk threshold, the risk source is a general hazard source, otherwise it is a major hazard source.

[0018] During the training process of the SVM model, a genetic algorithm is used to optimize the parameters of the model.

[0019] 2. A Hazard Identification and Risk Assessment System for Large-Scale Amusement Facilities

[0020] A hazard source identification unit is used to identify the hazard sources of large-scale amusement facilities and obtain a hazard source set;

[0021] A risk level assessment model generation unit is used to obtain a risk level assessment model corresponding to each hazard source according to historical failure data of each hazard source in the hazard source set;

[0022] The risk assessment unit of the amusement facility is used to obtain the operating status data of the large-scale amusement facility to be tested and use the risk level assessment model corresponding to each hazard source to assess the risks one by one, obtain the risk level of each hazard source, and then generate the risk assessment result of the large-scale amusement facility.

[0023] 3. A computer device

[0024] The device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for identifying and assessing the hazards of large amusement facilities are implemented.

[0025] 4. A computer-readable storage medium

[0026] The medium stores a computer program, which, when executed by a processor, implements the steps of the method for identifying and assessing the hazards of large amusement facilities.

[0027] 5. A computer program product

[0028] The product includes a computer program / instruction, which, when executed by a processor, implements the steps of a method for identifying hazards and assessing risks of large-scale amusement facilities.

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

[0030] The present invention identifies the sources of danger covering equipment, personnel and environment, and combines them with risk assessment models to reveal potential risks from three dimensions: design, operation and environment, thereby significantly improving the safety of amusement facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is the overall flow chart of the present invention;

[0032] Figure 2 A flowchart for amusement risk classification. DETAILED DESCRIPTION

[0033] The specific implementation of the present invention is further described below in conjunction with the accompanying drawings and technical solutions.

[0034] The present invention proposes a method for identifying and assessing the hazards of large-scale amusement facilities. Figure 1 As shown, the specific steps include:

[0035] S1: Identify the hazard sources of large amusement facilities and obtain a set of hazard sources;

[0036] S1 is specifically:

[0037] The HAZOP analysis method is used to identify equipment, personnel and environmental hazards in the accident case investigation reports of large amusement facilities in previous years, and the first hazard source set is obtained; and the TRIZ failure analysis method is used to analyze the potential failure mechanism of equipment in large amusement facilities, and the second hazard source set is obtained. After combining and removing the first hazard source set and the second hazard source set, the final hazard source set is obtained; Among them, the HAZOP analysis method combines the guide words to systematically identify the hazard source, and comprehensively analyzes the potential risks in equipment design, operation procedures and human-computer interaction. The TRIZ failure analysis method explores the weak links of the system from the perspective of design defects and failure mechanisms and proposes optimization results.

[0038] The following is an example of combining HAZOP with guide words. Combining "Check weather conditions" in the node "Preparation before starting" in the startup step with the guide word "No / None", it can be obtained that the hazard source is that the manager did not confirm whether the weather conditions meet the requirements for the operation of the Ferris wheel. For example, stormy weather may cause the Ferris wheel to malfunction, such as the 8-level gale in Changsha, Hunan, which caused the structure to shake in November 2021. In addition, the temperature in the environment is also extremely important. For example, on May 23, 2020, the amusement facility "Ferris Flying Wheel" in a certain place suddenly malfunctioned, and more than a dozen passengers were suspended on the flying car at 90 degrees. According to the staff of the company involved, the track-side beam sensor was shut down due to the hot weather. In addition, the guide word "None" combined with the safety inspection may lead to undiscovered safety hazards in practice, such as damaged cabin door locks or safety railings; and the guide word "Other Than": using non-standard safety inspection procedures may miss key safety checkpoints. Specific safety measures include that work managers need to confirm daily whether the local environmental conditions meet the operating conditions of the equipment and whether the safety protection devices meet the requirements.

[0039] And an analysis example that introduces the TRIZ failure analysis method. From the perspective of "destroyers", possible risk sources such as track wear, insufficient structural strength, loose connection components, and electrical system failure are analyzed. This analysis method helps to deeply understand the potential mechanisms of failure, such as material fatigue, the impact of environmental erosion on mechanical properties, etc., thereby further revealing the weak links in system design.

[0040] Hazard sources are generally classified into general hazards and major hazards. The criteria for determining major hazards are: hazards that may cause serious consequences to equipment, personnel or the environment and occur frequently. Major hazards include instability of supporting structures, cable breakage, overload operation of key components, and damage to equipment performance due to extreme environmental conditions.

[0041] S2: Train the risk level assessment model corresponding to each hazard source according to the historical failure data of each hazard source in the hazard source set;

[0042] For each hazard source in the hazard source set, the training process of its risk level assessment model is as follows:

[0043] The historical fault data of the current hazardous source is obtained, and after data preprocessing and feature extraction of the historical fault data, the fault feature data is obtained, thereby obtaining a training data set; the SVM model is trained using the training data set to obtain a trained SVM model and use it as a risk level assessment model for the hazardous source.

[0044] S3: Obtain the operating status data of the large-scale amusement facility to be tested, use the risk level assessment model of each hazard source to assess the risks one by one, obtain the risk level of each hazard source, that is, general hazard source or major hazard source, and then generate the risk assessment result of the large-scale amusement facility.

[0045] For example, for the specific hazard source of roller coaster axle fracture, the generation process of the risk level assessment model is as follows:

[0046] 1) Data Collection

[0047] 1.1) Historical fault data: Collect historical events of shaft breakage during roller coaster operation, including the number of occurrences, time, environmental conditions, etc.

[0048] Equipment status data: shaft material, diameter, manufacturing process, service life, degree of wear, etc.

[0049] Operation parameter data: roller coaster speed, load, acceleration, operating frequency, etc.

[0050] Environmental factor data: temperature, humidity, corrosive environment, vibration, etc.

[0051] 1.2) Labeling

[0052] No fracture occurs (Y=0): indicates that the shaft has not fractured during operation and the risk is low.

[0053] Fracture occurs (Y=1): Indicates that the shaft breaks during operation, which is a high risk.

[0054] 2) Data preprocessing

[0055] Data cleaning: Process missing values ​​and outliers to ensure data integrity and accuracy.

[0056] 3) and feature extraction

[0057] 3.1) Feature Selection and Extraction

[0058] According to the factors affecting the risk of shaft fracture, the following characteristics are selected:

[0059] Material strength (X1): tensile strength, fatigue strength, etc. of the shaft material.

[0060] Stress level (X2): The maximum stress the shaft is subjected to during operation.

[0061] Fatigue Life (X3): The remaining fatigue life of the shaft at the current stress level.

[0062] Inspection frequency (X4): The frequency of non-destructive inspection of the shaft.

[0063] Defect Size (X5): The size of the crack or defect detected on the shaft.

[0064] Running time (X6): The total time or number of cycles that the axis has run.

[0065] Environmental corrosion grade (X7): The degree of corrosiveness of the environment in which the shaft is located.

[0066] 3.2) Feature normalization: Min-Max normalization of all features

[0067] 4) Build SVM model

[0068] 4.1) Dataset division: The data set is divided into a training set and a test set, for example, according to the ratio of 80% training and 20% testing. Table 1 is a partial data diagram of the training set, and Table 2 is a partial data diagram of the test set.

[0069] 4.2) Model training: The SVM model is trained using the training set data, and the radial basis function (RBF) is used as the kernel function.

[0070] 4.3) Parameter adjustment: Use genetic algorithm (GA) to perform grid search and select the best penalty parameter C and kernel parameter γ. Figure 2 As shown in the figure, the specific process is that first, GA initializes a set of candidate parameters (C, γ) and calculates its fitness function during the SVM training process. Then, through selection methods such as roulette or tournament, individuals with high fitness are selected for the next round of optimization. Subsequently, new individuals are generated by single-point crossover or uniform crossover, and the parameters are fine-tuned through mutation to increase the search diversity. For example, if the initial individual (C = 5, γ = 0.1) evolves to (C = 10, γ = 0.5), a better classification effect may be obtained. After multiple rounds of iterations, GA finally found the optimal parameters C* = 10, γ* = 0.5, which optimized the classification accuracy of SVM and improved the accuracy and reliability of risk assessment of amusement facilities. Therefore, the optimal parameters C = 10, γ = 0.5 are selected.

[0071] 4.4) Model testing: Use the test set data to evaluate the performance of the model and calculate the accuracy, precision, recall and F1 score. In the model evaluation results, the accuracy is 95%, the precision is 92%, the recall is 90%, and the F1 score is 91%.

[0072] Table 1 is a schematic diagram of some data of the training set

[0073]

[0074] Table 2 is a schematic diagram of some data of the test set

[0075]

[0076] In the SVM model, the decision function value is the distance from the sample to the classification hyperplane. The generated decision function value is converted into a risk value using the following formula:

[0077]

[0078] Among them, MinValue and MaxValue are the minimum decision function value and the maximum decision function value respectively;

[0079] If the risk value is less than or equal to the risk threshold, the risk threshold is 0.7, then the risk source is a general hazard source (i.e., low risk), otherwise it is a major hazard source (i.e., high risk). Table 3 is an example of the results of the test set.

[0080] Table 3 shows an example of the test set results.

[0081]

[0082] Here is an example of a roller coaster axis:

[0083] Material strength (X1): 0.65

[0084] Stress level (X2): 0.85

[0085] Fatigue life (X3): 0.55

[0086] Detection frequency (X4): 0.6

[0087] Defect size (X5): 0.3

[0088] Running time (X6): 0.7

[0089] Environmental corrosion level (X7): 0.5

[0090] Model predictions:

[0091] Decision function value: 0.78

[0092] Risk value: The calculated risk value is 0.82

[0093] Risk determination: Risk value 0.82 ≥ 0.7, determined as a major hazard source

[0094] Result interpretation:

[0095] High stress level: The shaft is subjected to high stress during operation (X2=0.85), which increases the risk of fracture.

[0096] Insufficient fatigue life: The remaining fatigue life is low (X3=0.55), which means that the shaft is closer to its fatigue limit.

[0097] Large defect size: The detected defect size is large (X5 = 0.3) and may become the starting point of fracture.

[0098] Environmental corrosion: The corrosion level is high (X7=0.5), and the environment has an adverse effect on the material properties of the shaft.

[0099] Long running time: The shaft has been running for a long time (X6=0.7) and has accumulated more fatigue damage.

[0100] The present invention also proposes a large-scale amusement facility hazard source identification and risk assessment system, comprising:

[0101] A hazard source identification unit is used to identify the hazard sources of large-scale amusement facilities and obtain a hazard source set;

[0102] A risk level assessment model generation unit is used to obtain a risk level assessment model corresponding to each hazard source according to historical failure data of each hazard source in the hazard source set;

[0103] The risk assessment unit of the amusement facility is used to obtain the operating status data of the large-scale amusement facility to be tested and use the risk level assessment model corresponding to each hazard source to assess the risks one by one, obtain the risk level of each hazard source, and then generate the risk assessment result of the large-scale amusement facility.

[0104] The present invention also proposes a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for identifying and assessing the hazards of large amusement facilities are implemented.

[0105] The present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for identifying and assessing the hazards of large-scale amusement facilities are implemented.

[0106] The present invention also proposes a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a method for identifying and assessing the hazards of large-scale amusement facilities.

[0107] Finally, it should be noted that the above embodiments and explanations are only used to illustrate the technical solution of the present invention rather than to limit it. Those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope disclosed in the technical solution of the present invention, which should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for identifying and assessing the hazards of large-scale amusement facilities, characterized in that: The following steps are involved: S1: Identify the hazard sources of large amusement facilities and obtain a set of hazard sources; S2: Train the risk level assessment model corresponding to each hazard source according to the historical failure data of each hazard source in the hazard source set; S3: Obtain the operating status data of the large-scale amusement facility to be tested, use the risk level assessment model of each hazard source to assess the risks one by one, obtain the risk level of each hazard source, and then generate the risk assessment result of the large-scale amusement facility.

2. A large-scale amusement facility hazard source identification and risk assessment method according to claim 1, characterized in that: The S1 is specifically: The HAZOP analysis method is used to identify equipment, personnel and environmental hazards in the accident case investigation reports of large amusement facilities in previous years to obtain the first hazard source set; and the TRIZ failure analysis method is used to conduct a potential analysis of the equipment failure mechanism of large amusement facilities to obtain the second hazard source set. The first hazard source set and the second hazard source set are combined and deduplicated to obtain the final hazard source set.

3. A large-scale amusement facility hazard source identification and risk assessment method according to claim 1, characterized in that: In S2, for each hazard source in the hazard source set, the training process of the risk level assessment model is as follows: The historical fault data of the current hazardous source is obtained, and after data preprocessing and feature extraction of the historical fault data, the fault feature data is obtained, thereby obtaining a training data set; the SVM model is trained using the training data set to obtain a trained SVM model and use it as a risk level assessment model for the hazardous source.

4. A large-scale amusement facility hazard source identification and risk assessment method according to claim 3, characterized in that: In the SVM model, the radial basis function is used as the kernel function.

5. A large-scale amusement facility hazard source identification and risk assessment method according to claim 3, characterized in that: In the SVM model, the generated decision function value is converted into a risk value using the following formula: Among them, MinValue and MaxValue are the minimum decision function value and the maximum decision function value respectively; If the risk value is less than or equal to the risk threshold, the risk source is a general hazard source, otherwise it is a major hazard source.

6. A method for identifying and assessing the hazards of large-scale amusement facilities according to claim 3, characterized in that: During the training process of the SVM model, a genetic algorithm is used to optimize the parameters of the model.

7. A large-scale amusement facility hazard source identification and risk assessment system, characterized in that: include: A hazard source identification unit is used to identify the hazard sources of large-scale amusement facilities and obtain a hazard source set; A risk level assessment model generation unit is used to obtain a risk level assessment model corresponding to each hazard source according to historical failure data of each hazard source in the hazard source set; The risk assessment unit of the amusement facility is used to obtain the operating status data of the large-scale amusement facility to be tested and use the risk level assessment model corresponding to each hazard source to assess the risks one by one, obtain the risk level of each hazard source, and then generate the risk assessment result of the large-scale amusement facility.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a large-scale amusement facility hazard source identification and risk assessment method described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a large-scale amusement facility hazard source identification and risk assessment method described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of a large-scale amusement facility hazard source identification and risk assessment method described in any one of claims 1 to 6 are implemented.

Images