Method for evaluating safety resilience of dangerous chemical production enterprise based on comprehensive empowerment-clustering algorithm

Abstract

This invention, based on a comprehensive weighted clustering algorithm, describes a method for evaluating the safety resilience of hazardous chemical production enterprises, belonging to the field of safety assessment technology for chemical production enterprises. To address the problem of establishing a scientific and quantitative method for assessing the safety resilience of chemical production enterprises, this invention includes: collecting survey and statistical data from hazardous chemical production enterprises; constructing a safety resilience index system for hazardous chemical production enterprises, including a target layer, a criterion layer, and an element layer; calculating the weights corresponding to the evaluation grading indicators using a combination of subjective and objective methods (AHP-CRITIC); calculating a comprehensive score based on the survey and statistical data of hazardous chemical production enterprises and the weights corresponding to the evaluation grading indicators; and then using a K-means clustering algorithm for analysis to obtain the evaluation results of the safety resilience of hazardous chemical production enterprises based on the comprehensive weighted clustering algorithm. This invention provides a scientific basis for improving the quality and efficiency of enterprise safety management.

Description

Technical Field

[0001] This invention belongs to the field of safety assessment technology for chemical production enterprises, specifically involving a method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm. Background Technology

[0002] The hazardous chemicals industry is characterized by a wide variety and large quantity of hazardous materials, concentrated energy resources, complex production processes, harsh operating conditions, and high maintenance and repair difficulties. It is characterized by a concentration of risks, technologies, capital, and talent, making it the third highest-risk industry after the nuclear and aerospace industries. Accidents in the hazardous chemicals industry are characterized by their suddenness, wide impact, difficulty in rescue, and devastating consequences. Therefore, hazardous chemicals safety is of paramount importance for safe production, and there is an urgent need to establish scientific and quantifiable methods for assessing the safety resilience of chemical production enterprises. Summary of the Invention

[0003] The problem this invention aims to solve is to establish a scientific quantitative method for assessing the safety resilience of chemical production enterprises. It proposes a safety resilience evaluation method for hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm includes the following steps:

[0006] S1. Collect survey data and statistical data from hazardous chemical production enterprises;

[0007] S2. Construct a safety resilience indicator system for hazardous chemical production enterprises, including the target layer, criterion layer, and element layer;

[0008] S3. For the safety resilience index system of hazardous chemical production enterprises obtained in step S2, calculate the weights corresponding to the evaluation and grading indicators using the AHP-CRITIC subjective and objective combined method;

[0009] S4. Based on the survey data and statistical data of hazardous chemical production enterprises collected in step S1, calculate the comprehensive score according to the weights corresponding to the evaluation and grading indicators in step S3, and then use the K-means clustering algorithm for analysis to obtain the safety resilience evaluation results of hazardous chemical production enterprises based on the comprehensive weighting-clustering algorithm.

[0010] Furthermore, the specific implementation method of step S1 includes the following steps:

[0011] S1.1. Collect survey data on hazardous chemical production enterprises, including enterprise size, industrial structure, equipment operating years, automation control, proportion of investment in safety production expenses, safety culture construction, safety training plan formulation and implementation, occurrence of safety production accidents, emergency rescue personnel allocation, emergency rescue material allocation, number of emergency plan drills, whether the proportion of full-time safety production management personnel meets the standards, whether the proportion of registered safety engineers meets the standards, the proportion of chemical engineering majors among safety management personnel, and the proportion of personnel with high school education or above;

[0012] S1.2. Collect statistical data from hazardous chemical production enterprises;

[0013] The system collects information on whether a chemical plant is located within a chemical industrial park, the level of major hazard sources, the number of major hazard sources, the number of key monitored hazardous chemical processes, the number of key monitored hazardous chemicals, and the level of safety production standardization in the integrated service system for hazardous chemical registration.

[0014] The platform for monitoring and early warning of safety production risks of hazardous chemicals collects data on whether a digital system for monitoring and early warning of safety production risks and a dual prevention mechanism has been established, the number of times safety commitments were not made each month, the number of times alarms were not extinguished in a timely manner, the number of times the monthly average operating effect was medium or poor, the number of times the monthly average responsible person failed to perform their duties in a timely manner, and the number of major hidden dangers identified in the dual prevention mechanism system.

[0015] Furthermore, the specific implementation method of step S2 includes the following steps:

[0016] S2.1. Construct the target layer as an evaluation and grading index for assessing the safety resilience of hazardous chemical production enterprises;

[0017] S2.2. Construct a criteria layer, including enterprise basic resilience, inherent risk resilience, safety management resilience, emergency response resilience, personnel capability resilience, and monitoring and early warning resilience;

[0018] S2.3. Select corresponding indicator elements for each criterion layer, and classify each indicator element into levels I-IV according to its degree range from low to high;

[0019] The key indicators of a company's fundamental resilience include company size, industrial structure, years of operation of its facilities, whether it is located in a chemical industrial park, and automation control.

[0020] The indicators of inherent risk resilience include the level of major hazard sources, the number of major hazard sources, the number of key monitored hazardous chemical processes, and the number of key monitored hazardous chemicals;

[0021] The indicators of safety management resilience include the level of safety production standardization, the proportion of safety production expenditure, the development of safety culture, the formulation and implementation of safety training plans, and the occurrence of safety production accidents.

[0022] The indicators of emergency response resilience include the availability of emergency rescue personnel, the availability of emergency and fire protection resources, and the number of emergency response drills.

[0023] The indicators of personnel capability resilience include whether the proportion of full-time safety production management personnel meets the standards, whether the proportion of registered safety engineers meets the standards, the proportion of safety management personnel with chemical engineering backgrounds, and the proportion of personnel with high school diplomas or above.

[0024] The indicators for monitoring and early warning resilience include whether a digital system for monitoring and early warning of safety production risks and a dual prevention mechanism has been established, the number of times safety commitments were not made each month, the number of times alarms were not extinguished in a timely manner, the number of times the average monthly operating effect was medium or poor, the average number of times the responsible person failed to perform their duties in a timely manner each month, and the number of major hidden dangers identified in the dual prevention mechanism system.

[0025] Furthermore, the specific implementation method of step S3 includes the following steps:

[0026] S3.1. Establish the subjective assignment method (AHP): Invite 8 experts in related fields to fill out a questionnaire, compare each indicator in pairs, score the indicators according to their relative importance, and obtain the relative weight of each indicator after normalization. Finally, use the consistency ratio (CR) value to test the rationality of the weights. It is generally believed that if the CR value is less than 0.1, the judgment matrix satisfies the consistency test.

[0027] S3.2. Establish the objective assignment method CRITIC;

[0028] S3.2.1. Standardize each collected indicator element, and then calculate the standard deviation of each indicator;

[0029] S3.2.2. Calculate the correlation matrix r between the indicators using the Pearson correlation coefficient;

[0030] S3.2.3. Calculate the conflict resolution index. The calculation formula is as follows:

[0031]

[0032] in, For the conflict index of the j-th index element, Let be the correlation coefficient between the j-th indicator element and the k-th indicator element, where k is any one of m, and m is the total number of indicator elements;

[0033] S3.2.4. Calculate the total information content based on the standard deviation and conflict index, let I. j The information content contained in the j-th indicator is expressed as:

[0034] ;

[0035] Then calculate the weight W of the objective assignment method for the j-th indicator element. j *for:

[0036] ;

[0037] S3.3. Based on the weights obtained from the objective and subjective weighting methods, the weight W of the j-th indicator is obtained by combining them. j for:

[0038]

[0039] Where W' is the weight obtained by the AHP method; α is the preference coefficient, and α is 0.5.

[0040] Furthermore, the specific implementation method of step S4 includes the following steps:

[0041] S4.1. Calculate the overall score using the following formula:

[0042]

[0043] Where M is the overall score, and C j Let be the dimensionless value of the j-th index;

[0044] S4.2. When the M value of each enterprise is clustered into 2-7 clusters, different classification results are obtained. The mean square error within each cluster is used as the index to evaluate the clustering effect. The optimal number of clusters K is set to 4.

[0045] Then, based on the comprehensive score M, the K-means clustering algorithm was used in SPSS software for analysis. The number of clusters K=4 was selected, and the process was iterated 10 times. Enterprises in each cluster were classified into levels I to IV according to their scores, and the safety resilience evaluation results of hazardous chemical production enterprises based on the comprehensive weighted clustering algorithm were obtained.

[0046] The beneficial effects of this invention are:

[0047] The present invention describes a method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm. The resilience evaluation grading model constructed by combining subjective and objective weighting based on the AHP method and the CRITIC method can make up for the shortcomings of subjective methods being not objective and effective enough, and objective methods being unable to take into account the influence of subjective consciousness. The comprehensive weight obtained has high reliability.

[0048] This invention presents a method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighted clustering algorithm. It utilizes K-means clustering for scientific classification and determines the optimal number of clusters using the elbow method, thereby categorizing the safety resilience of hazardous chemical production enterprises into four levels. Case studies demonstrate the feasibility of this method. This model provides hazardous chemical production enterprises with a feasible evaluation and grading scheme that offers intuitive results and a simplified calculation process, providing important reference for the formulation of management plans for chemical enterprises and offering a scientific basis for improving the quality and efficiency of enterprise safety management. Attached Figure Description

[0049] Figure 1 This is a flowchart of a method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm, as described in this invention.

[0050] Figure 2 This is the curve showing the variation of the intra-class mean square error of the present invention with the value of K;

[0051] Figure 3 This is a cluster visualization diagram of hazardous chemical production enterprises according to the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention; that is, the described specific embodiments are merely a part of the embodiments of the invention, and not all of them. The components of the specific embodiments of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations, and the invention may also have other embodiments.

[0053] Therefore, the following detailed description of specific embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected specific embodiments of the invention. All other specific embodiments obtained by those skilled in the art based on these specific embodiments without inventive effort are within the scope of protection of this invention.

[0054] To further understand the invention's content, features, and effects, the following specific embodiments are provided, along with accompanying drawings. Figure 1 - Appendix Figure 3 Detailed explanation is as follows:

[0055] Example 1:

[0056] A method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm includes the following steps:

[0057] S1. Collect survey data and statistical data from hazardous chemical production enterprises;

[0058] Furthermore, the specific implementation method of step S1 includes the following steps:

[0059] S1.1. Collect survey data on hazardous chemical production enterprises, including enterprise size, industrial structure, equipment operating years, automation control, proportion of investment in safety production expenses, safety culture construction, safety training plan formulation and implementation, occurrence of safety production accidents, emergency rescue personnel allocation, emergency rescue material allocation, number of emergency plan drills, whether the proportion of full-time safety production management personnel meets the standards, whether the proportion of registered safety engineers meets the standards, the proportion of chemical engineering majors among safety management personnel, and the proportion of personnel with high school education or above;

[0060] S1.2. Collect statistical data from hazardous chemical production enterprises;

[0061] The system collects information on whether a chemical plant is located within a chemical industrial park, the level of major hazard sources, the number of major hazard sources, the number of key monitored hazardous chemical processes, the number of key monitored hazardous chemicals, and the level of safety production standardization in the integrated service system for hazardous chemical registration.

[0062] The platform for monitoring and early warning of safety production risks of hazardous chemicals collects data on whether a digital system for monitoring and early warning of safety production risks and a dual prevention mechanism has been established, the number of times safety commitments were not made each month, the number of times alarms were not extinguished in a timely manner, the number of times the monthly average operating effect was medium or poor, the number of times the monthly average responsible person failed to perform their duties in a timely manner, and the number of major hidden dangers identified in the dual prevention mechanism system.

[0063] S2. Construct a safety resilience indicator system for hazardous chemical production enterprises, including the target layer, criterion layer, and element layer;

[0064] Furthermore, the specific implementation method of step S2 includes the following steps:

[0065] S2.1. Construct the target layer as an evaluation and grading index for assessing the safety resilience of hazardous chemical production enterprises;

[0066] S2.2. Construct a criteria layer, including enterprise basic resilience, inherent risk resilience, safety management resilience, emergency response resilience, personnel capability resilience, and monitoring and early warning resilience;

[0067] S2.3. Select corresponding indicator elements for each criterion layer, and classify each indicator element into levels I-IV according to its degree range from low to high;

[0068] The key indicators of a company's fundamental resilience include company size, industrial structure, years of operation of its facilities, whether it is located within a chemical industrial park, and automation control; as shown in Table 1:

[0069] Table 1

[0070]

[0071] The indicators of inherent risk resilience include the level of major hazard sources, the number of major hazard sources, the number of key monitored hazardous chemical processes, and the number of key monitored hazardous chemicals; as shown in Table 2:

[0072] Table 2

[0073]

[0074] The key indicators of safety management resilience include the level of safety production standardization, the proportion of safety production expenditure, safety culture development, the formulation and implementation of safety training plans, and the occurrence of safety production accidents; as shown in Table 3:

[0075] Table 3

[0076]

[0077] The indicators of emergency response resilience include the availability of emergency rescue personnel, the level of emergency and fire protection resources, and the number of emergency response drills; as shown in Table 4:

[0078] Table 4

[0079]

[0080] The indicators of personnel resilience include whether the proportion of full-time safety production management personnel meets the standards, whether the proportion of registered safety engineers meets the standards, the proportion of safety management personnel with chemical engineering backgrounds, and the proportion of personnel with high school diplomas or above; as shown in Table 5:

[0081] Table 5

[0082]

[0083] The indicators for monitoring and early warning resilience include whether a digital system for monitoring and early warning of safety production risks and a dual prevention mechanism has been established, the number of times safety commitments were not fulfilled each month, the number of times alarms were not extinguished in a timely manner, the number of times the monthly average operational effectiveness was rated as medium or poor, the number of times the monthly average responsible person failed to perform their duties in a timely manner, and the number of major hidden dangers identified in the dual prevention mechanism system; as shown in Table 6:

[0084] Table 6

[0085]

[0086] S3. For the safety resilience index system of hazardous chemical production enterprises obtained in step S2, calculate the weights corresponding to the evaluation and grading indicators using the AHP-CRITIC subjective and objective combined method;

[0087] Furthermore, the specific implementation method of step S3 includes the following steps:

[0088] S3.1. Establish the subjective assignment method (AHP): Invite 8 experts in related fields to fill out a questionnaire, compare each indicator in pairs, score the indicators according to their relative importance, and obtain the relative weight of each indicator after normalization. Finally, use the consistency ratio (CR) value to test the rationality of the weights. It is generally believed that if the CR value is less than 0.1, the judgment matrix satisfies the consistency test.

[0089] S3.2. Establish the objective assignment method CRITIC;

[0090] S3.2.1. Standardize each collected indicator element, and then calculate the standard deviation of each indicator;

[0091] Furthermore, the calculation formula for the standardized processing method is as follows:

[0092]

[0093] Where, x ij This is the original data, x ij 'This is standardized data;'

[0094] Calculate the standard deviation of each indicator:

[0095]

[0096] Where m is the number of research subjects. This is the mean of the j-th indicator. This indicator is the variability indicator; a larger value means a larger weight.

[0097] S3.2.2. Calculate the correlation matrix r between the indicators using the Pearson correlation coefficient. The calculation formula is as follows:

[0098] ;

[0099] S3.2.3. Calculate the conflict resolution index. The calculation formula is as follows:

[0100]

[0101] in, For the conflict index of the j-th index element, Let be the correlation coefficient between the j-th indicator element and the k-th indicator element, where k is any one of m, and m is the total number of indicator elements;

[0102] S3.2.4. Calculate the total information content based on the standard deviation and conflict index, let I.j The information content contained in the j-th indicator is expressed as:

[0103] ;

[0104] Then calculate the weight W of the objective assignment method for the j-th indicator element. j *for:

[0105] ;

[0106] S3.3. Based on the weights obtained from the objective and subjective weighting methods, the weight W of the j-th indicator is obtained by combining them. j for:

[0107]

[0108] Where W' is the weight obtained by the AHP method; α is the preference coefficient, and α is 0.5.

[0109] Furthermore, the weights of each indicator are shown in Table 7:

[0110] Table 7

[0111]

[0112] S4. Based on the survey data and statistical data of hazardous chemical production enterprises collected in step S1, calculate the comprehensive score according to the weights corresponding to the evaluation and grading indicators in step S3, and then use the K-means clustering algorithm for analysis to obtain the safety resilience evaluation results of hazardous chemical production enterprises based on the comprehensive weighting-clustering algorithm.

[0113] Furthermore, the specific implementation method of step S4 includes the following steps:

[0114] S4.1. Calculate the overall score using the following formula:

[0115]

[0116] Where M is the overall score, and C j Let be the dimensionless value of the j-th index;

[0117] S4.2. When the M value of each enterprise is clustered into 2-7 clusters, different classification results are obtained. The mean square error within each cluster is used as the index to evaluate the clustering effect. The optimal number of clusters K is set to 4.

[0118] Then, based on the comprehensive score M, the K-means clustering algorithm was used in SPSS software for analysis. The number of clusters K=4 was selected, and the process was iterated 10 times. Enterprises in each cluster were classified into levels I to IV according to their scores, and the safety resilience evaluation results of hazardous chemical production enterprises based on the comprehensive weighted clustering algorithm were obtained.

[0119] Furthermore, safety resilience assessments were conducted on 50 chemical manufacturing companies, and the results are shown in Table 8:

[0120] Table 8

[0121]

[0122] The 50 categorized companies were then visualized and analyzed, with dots representing Level I companies, squares representing Level II companies, diamonds representing Level III companies, and triangles representing Level IV companies. The clustering visualization is shown below. Figure 3 As shown.

[0123] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0124] Although this application has been described above with reference to specific embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of this application. In particular, as long as there is no structural conflict, the features in the specific embodiments disclosed in this application can be combined with each other in any way. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, this application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighted clustering algorithm, characterized in that, Includes the following steps: S1. Collect survey data and statistical data from hazardous chemical production enterprises; S2. Construct a safety resilience indicator system for hazardous chemical production enterprises, including the target layer, criterion layer, and element layer; S3. For the safety resilience index system of hazardous chemical production enterprises obtained in step S2, calculate the weights corresponding to the evaluation and grading indicators using the AHP-CRITIC subjective and objective combined method; S4. Based on the survey data and statistical data of hazardous chemical production enterprises collected in step S1, calculate the comprehensive score according to the weights corresponding to the evaluation and grading indicators in step S3, and then use the K-means clustering algorithm for analysis to obtain the safety resilience evaluation results of hazardous chemical production enterprises based on the comprehensive weighting-clustering algorithm.

2. The method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighted clustering algorithm according to claim 1, characterized in that, The specific implementation method of step S1 includes the following steps: S1.

1. Collect survey data on hazardous chemical production enterprises, including enterprise size, industrial structure, equipment operating years, automation control, proportion of investment in safety production expenses, safety culture construction, safety training plan formulation and implementation, occurrence of safety production accidents, emergency rescue personnel allocation, emergency rescue material allocation, number of emergency plan drills, whether the proportion of full-time safety production management personnel meets the standards, whether the proportion of registered safety engineers meets the standards, the proportion of chemical engineering majors among safety management personnel, and the proportion of personnel with high school education or above; S1.

2. Collect statistical data from hazardous chemical production enterprises; The system collects information on whether a chemical plant is located within a chemical industrial park, the level of major hazard sources, the number of major hazard sources, the number of key monitored hazardous chemical processes, the number of key monitored hazardous chemicals, and the level of safety production standardization in the integrated service system for hazardous chemical registration. The platform for monitoring and early warning of safety production risks of hazardous chemicals collects data on whether a digital system for monitoring and early warning of safety production risks and a dual prevention mechanism has been established, the number of times safety commitments were not made each month, the number of times alarms were not extinguished in a timely manner, the number of times the monthly average operating effect was medium or poor, the number of times the monthly average responsible person failed to perform their duties in a timely manner, and the number of major hidden dangers identified in the dual prevention mechanism system.

3. The method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighted clustering algorithm according to claim 2, characterized in that, The specific implementation method of step S2 includes the following steps: S2.

1. Construct the target layer as an evaluation and grading index for assessing the safety resilience of hazardous chemical production enterprises; S2.

2. Construct a criteria layer, including basic corporate resilience, inherent risk resilience, safety management resilience, emergency response resilience, personnel capability resilience, and monitoring and early warning resilience; S2.

3. Select corresponding indicator elements for each criterion layer, and classify each indicator element into levels I-IV according to its degree range from low to high; The key indicators of a company's fundamental resilience include company size, industrial structure, years of operation of its facilities, whether it is located in a chemical industrial park, and automation control. The indicators of inherent risk resilience include the level of major hazard sources, the number of major hazard sources, the number of key monitored hazardous chemical processes, and the number of key monitored hazardous chemicals; The indicators of safety management resilience include the level of safety production standardization, the proportion of safety production expenditure, the development of safety culture, the formulation and implementation of safety training plans, and the occurrence of safety production accidents. The indicators of emergency response resilience include the availability of emergency rescue personnel, the availability of emergency and fire protection resources, and the number of emergency response drills. The indicators of personnel capability resilience include whether the proportion of full-time safety production management personnel meets the standards, whether the proportion of registered safety engineers meets the standards, the proportion of safety management personnel with chemical engineering backgrounds, and the proportion of personnel with high school diplomas or above. The indicators for monitoring and early warning resilience include whether a digital system for monitoring and early warning of safety production risks and a dual prevention mechanism has been established, the number of times safety commitments were not made each month, the number of times alarms were not extinguished in a timely manner, the number of times the average monthly operating effect was medium or poor, the average number of times the responsible person failed to perform their duties in a timely manner each month, and the number of major hidden dangers identified in the dual prevention mechanism system.

4. The method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm according to claim 3, characterized in that, The specific implementation method of step S3 includes the following steps: S3.

1. Establish the subjective assignment method (AHP): Invite 8 experts in related fields to fill out a questionnaire, compare each indicator in pairs, score the indicators according to their relative importance, and obtain the relative weight of each indicator after normalization. Finally, use the consistency ratio (CR) value to test the rationality of the weights. It is generally believed that if the CR value is less than 0.1, the judgment matrix satisfies the consistency test. S3.

2. Establish the objective assignment method CRITIC; S3.2.

1. Standardize each collected indicator element, and then calculate the standard deviation of each indicator element; S3.2.

2. Calculate the correlation matrix r between the indicators using the Pearson correlation coefficient; S3.2.

3. Calculate the conflict resolution index. The calculation formula is as follows: in, For the conflict resolution indicator of the j-th indicator element, Let be the correlation coefficient between the j-th indicator element and the k-th indicator element, where k is any one of m, and m is the total number of indicator elements; S3.2.

4. Calculate the comprehensive information quantity according to the standard deviation and the conflict index, set I j The information quantity contained by the jth index is expressed as: ； Then the weight W of the objective evaluation method of the jth index element is calculated j * is: ； S3.

3. Based on the weights obtained from the objective and subjective weighting methods, the weight W of the j-th indicator is obtained by combining them. j for: Where W' is the weight obtained by the AHP method; α is the preference coefficient, and α is 0.

5.

5. The method for evaluating the safety resilience of hazardous chemical production enterprises based on a comprehensive weighting-clustering algorithm according to claim 4, characterized in that, The specific implementation method of step S4 includes the following steps: S4.

1. Calculate the overall score using the following formula: Where M is the overall score, and C j Let be the dimensionless value of the j-th index; S4.

2. When the M value of each enterprise is clustered into 2-7 clusters, different classification results are obtained. The mean square error within each cluster is used as the index to evaluate the clustering effect. The optimal number of clusters K is set to 4. Then, based on the comprehensive score M, the K-means clustering algorithm was used in SPSS software for analysis. The number of clusters K=4 was selected, and the process was iterated 10 times. Enterprises in each cluster were classified into levels I to IV according to their scores, and the safety resilience evaluation results of hazardous chemical production enterprises based on the comprehensive weighted clustering algorithm were obtained.

Images