Integrated performance comprehensive evaluation method and system for fire-fighting chemical protective clothing

Abstract

The invention relates to the technical field of safety protection equipment performance evaluation, in particular to an integrated performance comprehensive evaluation method for fire-fighting chemical protective clothing, which comprises the following steps of: firstly, constructing a primary evaluation index system containing protective performance, environmental adaptability and human body efficiency and a secondary evaluation index system corresponding to the primary evaluation index system; secondly, a DEMATEL method and an entropy weight method are adopted to calculate a subjective weight and an objective weight respectively, and an optimal combination weight is obtained through fusion of an improved game theory model; then, a cloud model is introduced to convert the qualitative indexes into quantitative cloud droplets, and a comprehensive evaluation cloud is generated; and finally, fusing multi-source information by using a DS evidence theory, processing index conflicts, and outputting comprehensive evaluation grades and adaptive disaster scene suggestions. By fusing expert experience and experimental data, the problems of fuzziness and randomness in evaluation are effectively solved, and accurate evaluation of the performance of the chemical protection equipment and actual combat type selection guidance are realized.

Description

Technical Field

[0001] This invention relates to the field of performance evaluation technology for safety protection equipment, specifically to an integrated performance evaluation method and system for chemical protective clothing used in fire fighting. Background Technology

[0002] When handling hazardous chemical accidents, firefighters must wear chemical protective suits and positive-pressure breathing apparatus. This integrated equipment is the last line of defense for the safety of rescue personnel. However, the performance evaluation of this type of equipment faces great complexity: on the one hand, there are numerous evaluation indicators, covering multiple dimensions such as chemical protection capability, physical and mechanical properties, thermal comfort, and ergonomics, and there are inherent contradictions between these indicators (for example, stronger protective performance often means thicker and heavier materials, leading to a decrease in thermal and moisture comfort and flexibility); on the other hand, existing evaluation methods are mostly limited to single performance tests and lack a comprehensive consideration of the integrated performance of the human-equipment-environment system.

[0003] In existing technologies, evaluation models for protective clothing mainly include subjective evaluation methods, objective evaluation methods, and some simple comprehensive evaluation methods. However, traditional weighting methods often separate subjective experience from objective data. Purely subjective weighting is easily influenced by expert personal preferences and lacks stability; purely objective weighting relies entirely on the degree of data dispersion and may ignore some important but relatively uniform key indicators; in multi-indicator evaluations, different data sources may give conflicting conclusions, and traditional linear weighting often masks this conflict, leading to distorted evaluation results.

[0004] Therefore, there is an urgent need for a comprehensive evaluation method that can scientifically integrate subjective and objective weights, effectively handle fuzzy and conflicting information, and directly guide practical selection. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an integrated performance evaluation method and system for chemical protective clothing used in firefighting. This method scientifically integrates expert experience and experimental data through an improved game theory-based weighting method, utilizes a cloud model to convert qualitative language into quantitative values, and introduces DS evidence theory to handle conflicts between multi-source information, ultimately outputting a comprehensive evaluation result that is adapted to the disaster level.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a comprehensive evaluation method for the integrated performance of chemical protective clothing for fire fighting, comprising the following steps:

[0007] Step S1: Construct an evaluation index system: For the integrated equipment of chemical protective clothing and positive pressure respirator, establish primary indicators including protective performance, environmental adaptability and ergonomics, and construct corresponding secondary indicators for each primary indicator.

[0008] Step S2: Calculate subjective weights: Obtain the scoring data of domain experts on the mutual influence relationship between the indicators in the evaluation index system, calculate the centrality of each indicator based on the DEMATEL method, and normalize it to obtain the subjective weight vector of each indicator.

[0009] Step S3: Calculate objective weights: Collect experimental test data of each secondary indicator under the evaluation index system for different samples, construct a data matrix and perform standardization processing, use the entropy weight method to calculate the entropy value and difference coefficient of each indicator, and then obtain the objective weight vector of each indicator.

[0010] Step S4: Determine the combined weights: Construct a combined weighting model based on improved game theory, with the goal of minimizing the deviation between the combined weights and the subjective weight vector and the objective weight vector, solve for the optimal combined coefficients, and linearly fuse the subjective weight vector and the objective weight vector to obtain the final combined weights;

[0011] Step S5: Generate evaluation cloud: Set the evaluation set and its corresponding cloud model digital features, convert the indicator data of the object to be evaluated into cloud membership degree, and perform weighted aggregation of the evaluation clouds of each secondary indicator based on the combined weight to generate a comprehensive evaluation cloud of the primary indicator and the overall equipment.

[0012] Step S6, Multi-source information fusion and level determination: The comprehensive evaluation cloud is converted into a basic probability allocation function, and the Dempster synthesis rule of DS evidence theory is used to fuse multi-source evidence. The final evaluation level is determined according to the maximum probability after synthesis, and the disaster scenario suggestions are output in combination with the disaster database.

[0013] Preferably, in step S1, the secondary indicators of the protective performance include: the amount of chemical substance protection, the type of chemical substance protection, the protection time, the afterburning time, and the burn area.

[0014] The secondary indicators of environmental adaptability include: the degree of influence of temperature and humidity on air tightness, the degree of influence of temperature and humidity on liquid tightness, and the degree of influence of temperature pretreatment.

[0015] The secondary indicators of ergonomics include: equipment weight, limb flexibility, breathing resistance, and psychophysiological comfort under cyclical tasks.

[0016] Preferably, the specific process for calculating the subjective weight in step S2 is as follows:

[0017] Construct the direct influence matrix X:

[0018] ;

[0019] Where X ijThis indicates the degree of direct influence of the i-th indicator on the j-th indicator, and n represents the total number of evaluation indicators;

[0020] The direct influence matrix X is standardized to obtain matrix Y:

[0021] ;

[0022] Where Y represents the standardized direct influence matrix. This represents the sum of the elements in the i-th row;

[0023] Calculate the comprehensive influence matrix using the standardized direct influence matrix. ,in It is the identity matrix;

[0024] Calculate the impact of each indicator And the degree of influence :

[0025] ;

[0026] in Representation matrix The Middle Line number Column elements, Indicates the first The degree of combined influence of one indicator on all other indicators. Indicates the first The degree to which each indicator is affected by the combined influence of all other indicators;

[0027] Calculate centrality Subjective weights are obtained after normalization:

[0028] ;

[0029] in This represents the sum of the centralities of all indicators.

[0030] Preferably, the specific process for calculating the objective weight in step S3 is as follows:

[0031] Collect experimental data for each secondary indicator under different samples and construct the original data matrix:

[0032] ;

[0033] in Indicates the first The sample at the th The original values ​​of each indicator Indicates the number of samples. Indicates the total number of evaluation indicators;

[0034] Distinguish between positive and negative indicators, and standardize the collected experimental data. Positive indicators: Contrarian indicator: ;

[0035] in This represents the standardized data value. Indicates the first The maximum value of each indicator across all samples;

[0036] Calculate the entropy value of the j-th index. and specific gravity : ,if Then let and ;

[0037] Calculate the coefficient of difference Normalization yields objective weights .

[0038] Preferably, the specific process of constructing the combined weighting model in step S4 is as follows:

[0039] Construct the combined weight vector: ,in For subjective weight vectors, Let α and β be the objective weight vectors, and α and β be the linear combination coefficients. ;

[0040] Establish an optimization model to calculate and minimize the deviation between the combined weights and the subjective and objective weights:

[0041] ;

[0042] in Denotes the Euclidean norm. , ;

[0043] The optimal combination coefficients are obtained by solving and normalizing them, and then substituted into the combination weight formula to obtain the final combination weights.

[0044] Preferably, the process of generating the evaluation cloud in step S5 specifically includes:

[0045] Using a positive cloud generator, based on preset evaluation cloud parameters ( ) and the certainty of indicator data calculation, generating a result based on For the expectation, Normal random numbers with variance ,by For the expectation, Normal random numbers with variance The formula for certainty is: ;

[0046] Calculate the weighted overall evaluation cloud expectation and entropy ,in Let be the combined weight of the j-th indicator;

[0047] A comprehensive evaluation cloud map is generated based on the weighted cloud parameters.

[0048] Preferably, the specific steps in step S6 to output the adapted disaster scenario suggestion are as follows:

[0049] When the final score is greater than or equal to 85 points, the applicable scenario is determined to be a high-risk chemical disaster;

[0050] When the final score is between 70 and 84, the applicable scenario is determined to be a medium-risk chemical disaster.

[0051] When the final score is less than 70 points, the applicable scenario is determined to be a low-risk chemical disaster or a training scenario.

[0052] This invention also provides an integrated performance evaluation system for chemical protective clothing used in firefighting, comprising:

[0053] Weight Calculation Module: Includes subjective weight calculation unit, objective weight calculation unit and combined weight optimization unit, used to calculate and output the final combined weight of evaluation indicators based on DEMATEL method, entropy weight method and improved game theory model respectively;

[0054] Evaluation module: Used to receive the index data of the chemical protective clothing to be evaluated, combine the combined weights and preset cloud model parameters to generate a comprehensive evaluation cloud, and use DS evidence theory to fuse and generate the final evaluation result;

[0055] Disaster Level Comparison Module: This module stores a database that corresponds to disaster levels and performance requirements. It receives the evaluation results output by the evaluation module, compares them with the thresholds in the database, and outputs a disaster scenario level recommendation for the chemical protective clothing.

[0056] This invention provides an integrated performance evaluation method and system for chemical protective clothing used in firefighting. It has the following beneficial effects:

[0057] 1. This invention obtains subjective and objective weights through DEMATEL and entropy weight method respectively, and then integrates them through improved game theory. This not only reflects the experts' understanding of the inherent logical relationship of the indicators, but also retains the objective information of the data itself, thus overcoming the limitations of single weighting.

[0058] 2. This invention introduces cloud model theory and uses three numerical features—expectation, entropy, and hyperentropy—to realize the uncertainty conversion between qualitative concepts and quantitative values, effectively solving the problems of ambiguity and randomness in the evaluation process, such as good, relatively good, and poor linguistic values.

[0059] 3. This invention establishes a direct mapping relationship between scores and disaster levels, realizing intelligent processing of the entire process from data collection and weight calculation to scenario adaptation, providing a scientific basis for equipment selection, procurement, and practical application.

[0060] 4. By employing the DS evidence theory to fuse multi-source uncertain information, this invention can effectively handle conflicting evidence and improve the reliability of evaluation results. Attached Figure Description

[0061] Figure 1 This is an overall flowchart of the method of the present invention;

[0062] Figure 2 This is a schematic diagram of the functional module structure of the comprehensive evaluation system of the present invention;

[0063] Figure 3 A schematic diagram of the hardware structure of a computer device for executing the method of the present invention. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Example 1:

[0066] like Figure 1 As shown in the figure, this invention provides a method for comprehensive evaluation of the integrated performance of chemical protective clothing for fire fighting, and the specific steps are as follows:

[0067] Step S1: Construct an evaluation index system

[0068] A hierarchical evaluation index system was constructed for the integrated equipment of chemical protective suits and positive pressure respirators. The primary indicators include: protective performance, environmental adaptability, and ergonomics. The secondary indicators for protective performance include: the quantity of chemical substances protected, the type of chemical substances protected, the duration of protection, the afterburning time, and the burn area. The secondary indicators for environmental adaptability include: the degree of influence of temperature and humidity on airtightness, the degree of influence of temperature and humidity on liquid tightness, and the degree of influence of temperature pretreatment. The secondary indicators for ergonomics include: equipment weight, limb flexibility, breathing resistance, and psychological and physiological comfort under cyclical tasks.

[0069] The specific testing standards for the secondary indicators are as follows: The type and duration of chemical substance protection are confirmed through laboratory penetration testing based on the list of chemical penetration test substances specified in the national standard GB24539-2025, taking into account their penetration performance level. For example, for acetone (a ketone), analytical grade or higher liquid acetone, through continuous contact with liquid chemicals, if the penetration time is greater than 120 minutes, it is recorded as "Class 1, Level 4," earning 4 points. There are 15 chemical categories in the national standard, with the highest level being Level 6 protection time, i.e., a maximum of 90 points. These are then converted to a percentage system. The afterflame time and burn area are confirmed based on the burning dummy test in the national standard GB8965.1-2020. For example, if a chemical protective suit experiences a 3-second flashover, no afterflame or a burn area less than 2% is the maximum score of 100 points; continuous afterflame or a burn area greater than 30% is recorded as 0 points. The effect of temperature and humidity on airtightness was investigated by testing the leakage rate of protective clothing under different temperature and humidity conditions in a temperature- and humidity-controlled environment chamber. The leakage rate at normal temperature and humidity was used as the standard leakage rate C. 标准 The experimental leakage rate C was obtained under high, low temperature and humidity conditions. 试验 The formula for calculating the rate of change in airtightness is as follows: The effect of temperature and humidity on liquid tightness was investigated by simulating chemical liquid splashing, recording the liquid penetration time under different temperatures and humidity levels, and calculating the liquid tightness retention rate. The calculation formula is as follows: T 试验 The osmosis time under normal temperature and humidity, T 标准 The penetration time under high, low temperature, and high humidity conditions was measured. The impact of temperature pretreatment was assessed by pretreating the protective suit at 60°C or -20°C for 48 hours, followed by airtightness and liquid tightness tests after returning to room temperature. The weight of the entire set of equipment was measured directly. Limb flexibility was measured using a goniometer to measure the wearer's joint range of motion during standard movements, and the time required to complete a series of standard movements was recorded. Breathing resistance was measured using a breathing resistance tester to simulate the human breathing curve, measuring inspiratory and expiratory resistance. The psychological and physiological comfort under cyclical tasks was assessed using a subjective psychological rating scale with five levels. Changes in heart rate, body temperature, and perspiration were monitored, referencing a physiological parameter threshold table (see Table 1). Within the danger range, 0-3 points were awarded; within the moderate alert range, 4-7 points; and within the safe range, 8-10 points. Taking a TK601 protective suit produced by a certain company as an example, with a subjective rating scale of level 3, after two task cycles, the heart rate was 140 beats / minute, the body temperature was 38.1℃, and the perspiration was 1.1 liters / hour, all within the moderate alert range. The subjective rating was 6 points, and the objective rating was 6 points. All scores were then converted to percentages.

[0070] Table 1 Physiological Parameter Threshold Table

[0071] physiological indicators Comfort / Safety Range (Rest / Light Activity) Discomfort / Alert Level (Moderate Intensity Labor) High-risk / dangerous areas (high-intensity / extreme labor) Heart rate 60-100 times / minute 110-150 beats / minute >180 beats / minute Core body temperature 36.5-37.5°C >38.0°C >39.5°C sweat volume 0.5-1.0 liters / hour 1.0-1.5 liters / hour >1.5 liters / hour

[0072] Step S2: Calculate subjective weights based on the DEMATEL method

[0073] Obtain expert ratings: Invite several experts in the field to score the degree of mutual influence between the indicators (0-4 points, 0 for no influence, 4 for extremely strong influence).

[0074] Construct the direct influence matrix X:

[0075] ;

[0076] Where x ij This indicates the degree of direct influence of the i-th indicator on the j-th indicator, and n represents the total number of evaluation indicators.

[0077] Standardization: Standardize the directly influential matrix X to obtain matrix Y:

[0078] ;

[0079] Where Y represents the standardized direct influence matrix. This represents the sum of the elements in the i-th row, with the denominator being the maximum sum among all rows.

[0080] Calculate the overall impact matrix T:

[0081] ,in It is the identity matrix. It is the inverse of the matrix.

[0082] Calculate the degree of influence and the degree of being influenced:

[0083] Impact degree of influence ;

[0084] in Represents the first element in matrix T. Line number Column elements, Indicates the first The degree of combined influence of one indicator on all other indicators. Indicates the first The degree to which an indicator is affected by the combined influence of all other indicators.

[0085] Calculate and normalize the centrality:

[0086] Centrality This indicates the importance of the indicator in the evaluation system; and the subjective weight is obtained after normalization. ,in This represents the sum of the centralities of all indicators.

[0087] Step S3: Calculate the objective weights based on the entropy weight method

[0088] Data Collection: Collect experimental data from m different samples under n indicators, and construct the original data matrix. ,in Indicates the first The sample at the th The original values ​​of each indicator Indicates the number of samples. Indicates the total number of evaluation indicators;

[0089] Data standardization:

[0090] For positive indicators (the higher the value, the better): ;

[0091] For reverse indicators (the smaller the value, the better): ;

[0092] in This represents the standardized data value. Indicates the first The maximum value of each indicator across all samples.

[0093] Calculate the entropy and weight:

[0094] Calculate the weight of the i-th sample under the j-th indicator: ;

[0095] Calculate the entropy value of the j-th index: ;

[0096] if Then let and .

[0097] Calculate the coefficient of difference Normalization yields objective weights .

[0098] Step S4: Determine the combined weights based on improved game theory

[0099] Construct the combined weight vector: ,in For subjective weight vectors, Let be the objective weight vector, α and β be the linear combination coefficients, and α and β > 0. .

[0100] Establish an optimization model:

[0101] Calculate and minimize the deviation between the combined weights and the subjective and objective weights:

[0102] ;

[0103] in Denotes the Euclidean norm. , Based on the properties of matrix differentiation, the problem is transformed into solving a system of linear equations for the optimal coefficients, as follows:

[0104] Establish constraints: ;

[0105] Will Substitute into the objective function:

[0106] ;

[0107] Will Substitute into the above equation and simplify: ;

[0108] Take the derivative and set it to zero: ;

[0109] Solving for the given information, we get: .

[0110] After solving for the optimal combination coefficients and normalizing them, we input them into the combination weight formula to obtain the final combination weights: .

[0111] Step S5: Generate Evaluation Cloud

[0112] Define the evaluation criteria set: Define the evaluation criteria set V = {Excellent, Good, Average, Poor, Poor}, and determine the corresponding cloud model digital features for each level. The specific parameters for the rating scale are shown in Table 2.

[0113] Table 2. Parameters of the comment set for each level

[0114] Comments Level Ex En He Difference 30 8 0.5 Poor 50 6 0.4 generally 65 4 0.3 good 80 3 0.2 excellent 90 2 0.1

[0115] Forward cloud generator:

[0116] Calculate the degree of certainty based on the indicator data x of the object to be evaluated and the parameters of the comment set cloud. , generate For the expectation, Normal random numbers with variance ,by For the expectation, Normal random numbers with variance .

[0117] Weighted aggregation:

[0118] Based on the combined weights, the evaluation clouds of each secondary indicator are weighted to generate a primary indicator cloud and an overall comprehensive evaluation cloud. The expected value of the overall evaluation cloud is... and entropy ,in Let be the combined weight of the j-th indicator.

[0119] Step S6: Multi-source information fusion and level determination

[0120] Evidence fusion: The membership degrees output by the comprehensive evaluation cloud are converted into basic probability assignment functions (BPA). The Dempster synthesis rule based on DS evidence theory is used to fuse subjective and objective evaluation results. ,in Indicates the degree of conflict.

[0121] Level determination and scene adaptation:

[0122] The final evaluation level is determined based on the highest probability after synthesis and mapped to a score. Recommendations are then output in conjunction with a disaster database, which includes disaster scenarios, case studies, and recommended scores.

[0123] When the final score is greater than or equal to 85 points, the applicable scenario is determined to be a high-risk chemical disaster, applicable to strong acid and alkali, highly toxic gas, flammable and explosive environments.

[0124] When the final score is between 70 and 84, the applicable scenario is determined to be a medium-risk chemical disaster, applicable to general industrial chemical leaks and low-concentration toxic gas environments.

[0125] When the final score is less than 70 points, the applicable scenario is determined to be a low-risk chemical disaster or training scenario. It is recommended to use it only for auxiliary rescue or daily training, and it is strictly forbidden to enter the core pollution area.

[0126] Example 2:

[0127] like Figure 2 As shown, this embodiment of the invention also provides an integrated performance evaluation system for chemical protective clothing used in firefighting, comprising:

[0128] The weight calculation module includes a subjective weight calculation unit (executing the DEMATEL algorithm), an objective weight calculation unit (executing the entropy weight method), and a combined weight optimization unit (executing the improved game theory model). This module is responsible for outputting scientific evaluation index weights.

[0129] Evaluation module: It receives the index data of the chemical protective clothing to be evaluated (including laboratory test report data and expert scoring data) input by the user, combines the combined weights output by the weight module, generates an evaluation cloud using a cloud generator, and finally generates a quantitative score and qualitative grade through DS evidence theory algorithm.

[0130] Disaster Level Comparison Module: Internally stores a disaster level-performance requirement database. This module receives the output from the evaluation module and, through threshold comparison (such as an 85-point threshold), automatically outputs practical scenario recommendations (high / medium / low risk) for the chemical protective suit.

[0131] Example 3:

[0132] like Figure 3 As shown, this embodiment of the invention provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the method steps in Embodiment 1 described above. The device may be a PC, server, or mobile terminal with evaluation software installed. The computer program stored in the memory implements the method steps in Embodiment 1 when executed by the processor.

[0133] Example 4:

[0134] This invention uses a TK601 chemical protective suit from a certain company as an example for evaluation. The specific steps are as follows:

[0135] Step S1:

[0136] For the acquisition of raw data, taking a certain company's TK601 chemical protective suit as an example, the experimental data has been converted to a percentage system, and the reference sample data comes from the experimental protective suit data.

[0137] Secondary indicators Sample 1 (TK601) Sample 2 (Reference Sample 1) Sample 3 (Reference Sample 2) Chemical protection comprehensive 88.9 94.4 83.3 Afterburning duration 86.7 83.3 50 Burn area 86.7 83.3 60 Temperature, humidity, and airtightness 88 85 80 Temperature, humidity, and liquid tightness 85 82 75 Temperature pretreatment 93 90 85 Equipment weight 60 70 50 Physical flexibility 70 80 60 breathing resistance 65 75 60 Psychological and physiological comfort 60 80 70

[0138] Step S2:

[0139] Five experts were invited to score the degree of mutual influence of the 10 indicators (0-4 points), and the average value was used to construct a matrix: And standardize the process: ;

[0140] ;

[0141] Calculate the overall impact matrix: ;

[0142] ;

[0143] Calculate the impact and affectedness of each indicator: .

[0144] Taking indicator 1 as an example:

[0145] ;

[0146] Normalization yields subjective weights:

[0147] ;

[0148]

[0149] Subjective weight vector:

[0150] ;

[0151] Step S3:

[0152] Construct the original data matrix:

[0153] ;

[0154] standardization:

[0155] Positive indicators: ;

[0156] Contrarian indicator: ;

[0157] .

[0158]

[0159]

[0160] .

[0161] Calculate the entropy value of the j-th index. and specific gravity :

[0162] ;

[0163]

[0164] ,

[0165] ,

[0166] ,

[0167] ,

[0168] ,

[0169] Normalization yields objective weights ;

[0170] Objective weight .

[0171] Step S4:

[0172] Combined weights ;

[0173] Taking indicator 1 as an example:

[0174] ;

[0175] Overall weighting:

[0176] .

[0177] Step S5:

[0178] Determine the evaluation level table for the cloud platform:

[0179] Comments Level Ex En He Difference 30 8 0.5 Poor 50 6 0.4 generally 65 4 0.3 good 80 3 0.2 excellent 90 2 0.1

[0180] The indicator data of the sample TK601 to be evaluated:

[0181] ;

[0182] Calculate the expected score for the overall cloud evaluation:

[0183]

[0184] Calculate the degree of certainty for each indicator at each level. For each indicator and each evaluation level, use the cloud model to calculate the degree of certainty:

[0185] Generate random entropy values ;

[0186] Calculate the degree of certainty: ;

[0187] Calculation of the certainty of index 1:

[0188] For excellence: ;

[0189] Good: ;

[0190] For general: Similarly, calculate other levels.

[0191] The subjective evaluation cloud certainty is obtained by weighted aggregation: ;

[0192] Subjective weighted certainty ;

[0193] Objective weighted certainty .

[0194] Step S6:

[0195] Converting to the Mass function of the DS evidence theory, and normalizing the subjective and objective certainty, we obtain the Mass function:

[0196] ;

[0197] subjective ,

[0198] objective ;

[0199] The probability distributions for each level were obtained by Dempster synthesis.

[0200] ,in Indicates the degree of conflict.

[0201] Denominator: .

[0202] ;

[0203] ;

[0204] ;

[0205] ;

[0206] .

[0207] The weighted average of the scores corresponding to each level is calculated:

[0208] .

[0209] This indicates that the fire-fighting chemical protective clothing (TK601 type) has a good rating and is suitable for medium-hazard chemical disaster environments. Its applicable scenarios include general industrial chemical leaks and low-concentration toxic gas environments. Due to its average ergonomics (60-70 points), it is recommended that single use not exceed 4 hours. However, its chemical protection performance is excellent (88.9 points) and its environmental adaptability is good (88.7 points).

[0210] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A comprehensive evaluation method for the integrated performance of chemical protective clothing for firefighting, characterized in that, Includes the following steps: Step S1: Construct an evaluation index system: For the integrated equipment of chemical protective clothing and positive pressure respirator, establish primary indicators including protective performance, environmental adaptability and ergonomics, and construct corresponding secondary indicators for each primary indicator. Step S2: Calculate subjective weights: Obtain the scoring data of domain experts on the mutual influence relationship between the indicators in the evaluation index system, calculate the centrality of each indicator based on the DEMATEL method, and normalize it to obtain the subjective weight vector of each indicator. Step S3: Calculate objective weights: Collect experimental test data of each secondary indicator under the evaluation index system for different samples, construct a data matrix and perform standardization processing, use the entropy weight method to calculate the entropy value and difference coefficient of each indicator, and then obtain the objective weight vector of each indicator. Step S4: Determine the combined weights: Construct a combined weighting model based on improved game theory, with the goal of minimizing the deviation between the combined weights and the subjective weight vector and the objective weight vector, solve for the optimal combined coefficients, and linearly fuse the subjective weight vector and the objective weight vector to obtain the final combined weights; Step S5: Generate evaluation cloud: Set the evaluation set and its corresponding cloud model digital features, convert the indicator data of the object to be evaluated into cloud membership degree, and perform weighted aggregation of the evaluation clouds of each secondary indicator based on the combined weight to generate a comprehensive evaluation cloud of the primary indicator and the overall equipment. Step S6, Multi-source information fusion and level determination: The comprehensive evaluation cloud is converted into a basic probability allocation function, and the Dempster synthesis rule of DS evidence theory is used to fuse multi-source evidence. The final evaluation level is determined according to the maximum probability after synthesis, and the disaster scenario suggestions are output in combination with the disaster database.

2. The integrated performance evaluation method for chemical protective clothing for firefighting according to claim 1, characterized in that, In step S1, the secondary indicators of the protective performance include: the amount of chemical substance protection, the type of chemical substance protection, the protection time, the afterburning time, and the burn area. The secondary indicators of environmental adaptability include: the degree of influence of temperature and humidity on air tightness, the degree of influence of temperature and humidity on liquid tightness, and the degree of influence of temperature pretreatment. The secondary indicators of ergonomics include: equipment weight, limb flexibility, breathing resistance, and psychophysiological comfort under cyclical tasks.

3. The integrated performance evaluation method for chemical protective clothing for firefighting according to claim 1, characterized in that, The specific process for calculating the subjective weight in step S2 is as follows: Construct the direct influence matrix X: ； Where x ij This indicates the degree of direct influence of the i-th indicator on the j-th indicator, and n represents the total number of evaluation indicators; The direct influence matrix X is standardized to obtain matrix Y: ； Where Y represents the standardized direct influence matrix. This represents the sum of the elements in the i-th row; Calculate the comprehensive influence matrix using the standardized direct influence matrix. ,in It is the identity matrix; Calculate the impact of each indicator And the degree of influence : ； in Representation matrix The Middle Line number Column elements, Indicates the first The degree of combined influence of one indicator on all other indicators. Indicates the first The degree to which each indicator is affected by the combined influence of all other indicators; Calculate centrality Subjective weights are obtained after normalization: ； in This represents the sum of the centralities of all indicators.

4. The integrated performance evaluation method for chemical protective clothing for firefighting according to claim 1, characterized in that, The specific process for calculating the objective weight in step S3 is as follows: Collect experimental data for each secondary indicator under different samples and construct the original data matrix: ； in Indicates the first The sample at the th The original values ​​of each indicator Indicates the number of samples. Indicates the total number of evaluation indicators; Distinguish between positive and negative indicators, and standardize the collected experimental data. Positive indicators: Contrarian indicator: ; in This represents the standardized data value. Indicates the first The maximum value of each indicator across all samples; Calculate the entropy value of the j-th index. and specific gravity : ,if Then let and ; Calculate the coefficient of difference Normalization yields objective weights .

5. The integrated performance evaluation method for chemical protective clothing for fire fighting according to claim 1, characterized in that, The specific process of constructing the combined weighting model in step S4 is as follows: Construct the combined weight vector: ,in For subjective weight vectors, Let be the objective weight vector, α and β be the linear combination coefficients, and α and β >

0. ; Establish an optimization model to calculate and minimize the deviation between the combined weights and the subjective and objective weights: ； in Denotes the Euclidean norm. , ; The optimal combination coefficients are obtained by solving and normalizing them, and then substituted into the combination weight formula to obtain the final combination weights.

6. The integrated performance evaluation method for chemical protective clothing for firefighting according to claim 1, characterized in that, The process of generating the evaluation cloud in step S5 is as follows: Using a positive cloud generator, based on preset evaluation cloud parameters ( ) and the certainty of indicator data calculation, generating a result based on For the expectation, Normal random numbers with variance ,by For the expectation, Normal random numbers with variance The formula for certainty is: ; Calculate the weighted overall evaluation cloud expectation and entropy ,in Let be the combined weight of the j-th indicator.

7. The integrated performance evaluation method for chemical protective clothing for fire fighting according to claim 1, characterized in that, The specific steps for outputting the adapted disaster scenario suggestions in step S6 are as follows: When the final score is greater than or equal to 85 points, the applicable scenario is determined to be a high-risk chemical disaster; When the final score is between 70 and 84, the applicable scenario is determined to be a medium-risk chemical disaster. When the final score is less than 70 points, the applicable scenario is determined to be a low-risk chemical disaster or a training scenario.

8. An integrated performance evaluation system for chemical protective clothing used in firefighting, used to perform the method as described in any one of claims 1 to 7, characterized in that, The system includes: Weight Calculation Module: Includes subjective weight calculation unit, objective weight calculation unit and combined weight optimization unit, used to calculate and output the final combined weight of evaluation indicators based on DEMATEL method, entropy weight method and improved game theory model respectively; Evaluation module: Used to receive the index data of the chemical protective clothing to be evaluated, combine the combined weights and preset cloud model parameters to generate a comprehensive evaluation cloud, and use DS evidence theory to fuse and generate the final evaluation result; Disaster Level Comparison Module: This module stores a database that corresponds to disaster levels and performance requirements. It receives the evaluation results output by the evaluation module, compares them with the thresholds in the database, and outputs a disaster scenario level recommendation for the chemical protective clothing.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images