Construction method and system of process safety management grading evaluation model

Abstract

The invention relates to the technical field of information processing, in particular to a construction method and system for a process safety management grading evaluation model, and the method comprises the steps: S1, collecting evaluation data; step S2, processing the evaluation data; s3, constructing an operation model and a state model according to the evaluation data of the previous evaluation period; s4, obtaining an enterprise operation security level and an enterprise state security level according to the operation model and the state model; s5, setting a weight parameter matrix according to historical grading evaluation data; s6, performing grading evaluation on enterprise process safety management according to the weight parameter matrix; s7, performing specific correction on the screening process of the historical grading evaluation data of the enterprise; and S8, performing universality correction on the screening process of the historical grading evaluation data. According to the method, the process safety management grading evaluation efficiency is improved by improving the application range of process safety management grading evaluation and refining information analysis.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method and system for constructing a process safety management grading evaluation model. Background Art

[0002] Process safety management grading and evaluation is an important means to prevent and reduce production accidents. Through process safety management grading and evaluation, enterprises can have a clearer understanding of the safety status of each link in the process and provide a basis for decision-making in the production process. The country has clear regulatory requirements for process safety management. Enterprises need to conduct regular evaluations of their own process safety status to ensure compliance with relevant regulatory requirements. Through process safety management grading and evaluation, enterprises can demonstrate their own process safety management level. Enterprises need to continuously improve their own process safety management level based on the evaluation results. Enterprises should attach great importance to process safety management grading and evaluation to ensure its effective implementation.

[0003] Chinese patent publication number: CN106094747B discloses a modeling method for a multi-resolution plant safety model of a petrochemical enterprise, including: (1) establishing a multi-level plant topology model; (2) establishing a mapping relationship between adjacent levels of the multi-level plant topology model; (3) constructing a node information set model, a hazard source information set model, and an accident risk information set model in each level of the topology model; (4) establishing a mapping relationship between each information set model in each level of the topology model and performing risk assessment to form a multi-level risk assessment information set model; (5) according to the node geographic location information in each level of the topology model, each information set model is associated with the multi-level plant topology model to form a multi-resolution plant safety model. However, this scheme does not classify the data and adjust the weight parameters of each type of data, and this scheme is not suitable for process safety management grading evaluation of multiple objects. Summary of the invention

[0004] To this end, the present invention provides a method and system for constructing a process safety management grading evaluation model, so as to overcome the problem of low efficiency of grading evaluation caused by few applicable objects and insufficiently detailed information analysis when chemical enterprises conduct process safety management grading evaluation in the prior art.

[0005] To achieve the above objectives, on the one hand, the present invention provides a method for constructing a process safety management grading evaluation model, comprising:

[0006] Step S1, collecting the equipment working hours, equipment maintenance time intervals, safety facility status, number of personnel wearing safety masks, standing areas for personnel not wearing masks, and standing time for personnel not wearing masks within the evaluation period to obtain evaluation data;

[0007] Step S2, processing the evaluation data;

[0008] Step S3, constructing an operation model and a state model based on the evaluation data of the previous evaluation cycle;

[0009] Step S4, obtaining the enterprise operation security level and the enterprise state security level according to the operation model and the state model;

[0010] Step S5, setting the weight parameter matrix according to the historical rating evaluation data;

[0011] Step S6, grading and evaluating the enterprise's process safety management according to the weight parameter matrix;

[0012] Step S7, specifically modifying the screening process of the enterprise's historical rating evaluation data according to the number of failures of the enterprise's process equipment in the current evaluation period;

[0013] Step S8, making universal corrections to the screening process of historical rating evaluation data according to the rating evaluation specific correction times.

[0014] Furthermore, in step S2, when processing the evaluation data, the life t2 of each device is obtained, the device working parameter T is calculated according to the device working time t1, T=t1 / t2 is set, the personnel wearing ratio p is calculated according to the number of personnel wearing safely n and the total number of people in the current working area n0, p=n / n0 is set, the personnel wearing ratio p is compared with the preset personnel wearing ratio p0, and the personnel wearing situation is judged according to the comparison result, wherein:

[0015] When p≥p0, it is judged that the person's wearing condition is normal;

[0016] When p<p0, it is determined that the wearing condition of the personnel is abnormal, and the adjustment coefficient v is set, 0.87<v<0.98, and the safety facility coverage rate u is adjusted according to the adjustment coefficient v. The adjusted safety facility coverage rate is uv, and uv=v×u is set.

[0017] Furthermore, in step S2, the process of judging the wearing status of the person is modified according to the standing area of ​​the person not wearing the wearer, wherein:

[0018] When the area where the non-wearing person stands is a first-level dangerous area, the standing time i of the non-wearing person is compared with the first preset standing time i 1, where:

[0019] If i≤i 1, the judgment process of the personnel wearing condition is not corrected;

[0020] If i>i 1, the judgment process of the wearing condition of the personnel is corrected, and the correction coefficient J is set, 1.02<J<1.2, and the preset wearing proportion p0 of the personnel in the judgment process of the wearing condition of the personnel is corrected. The corrected preset wearing proportion of the personnel is pj0, and pj0=J×p0 is set. When pj0>1, pj0 takes the value of 1;

[0021] When the area where the person who does not wear the mask stands is a secondary dangerous area, the standing time i of the person who does not wear the mask is compared with the second preset standing time i2, where:

[0022] If i≤i2, the judgment process of the wearing condition of the personnel will not be corrected;

[0023] If i>i2, the judgment process of the wearing condition of the personnel is corrected, and the correction coefficient J is set, 1.01<J<1.15, and the preset personnel wearing ratio p0 in the judgment process of the wearing condition of the personnel is corrected. The corrected preset personnel wearing ratio is pj0, and pj0=J×p0 is set. When pj0>1, pj0 takes the value of 1;

[0024] When the area where people who are not wearing the device are standing is a safe area, the judgment process of the person wearing the device is not corrected;

[0025] The equipment operating parameters and equipment maintenance time intervals are taken as operation data, and the safety facility status and safety facility coverage rate are taken as status data.

[0026] Furthermore, in step S3, when constructing the operation model and the state model, the operation model is constructed according to the safety facility status of the previous evaluation cycle and the operation safety level corresponding to the safety facility status, and the state model is constructed according to the state data of the previous evaluation cycle and the state safety level corresponding to the state data.

[0027] Furthermore, in step S4, the evaluation data of the current evaluation cycle is input into the operation model and the state model, and the enterprise operation safety level and the enterprise state safety level are output respectively.

[0028] Furthermore, in the step S5, when setting the weight parameter matrix, the weight parameter matrix is ​​initialized, and the weight parameter matrix is ​​set to [w1, w2, w3], w1 is the weight parameter of the enterprise operation safety level, w2 is the weight parameter of the enterprise status safety level, w3 is the weight parameter of the enterprise average process safety level, and w1+w2+w3=1;

[0029] The weight parameter matrix is ​​trained according to the historical grading evaluation data, and when the accuracy reaches the preset accuracy, the weight parameter matrix is ​​output.

[0030] Furthermore, in step S5, the number of enterprise process equipment failures y in each historical evaluation period is compared with the preset average standard enterprise process equipment failure number y0, and the historical grading evaluation data is screened according to the comparison result, wherein:

[0031] When y≤y0, the grading evaluation data of the historical evaluation period is selected as the historical grading evaluation data;

[0032] When y>y0, the rating evaluation data of the historical evaluation period is not selected as the historical rating evaluation data.

[0033] Furthermore, in step S6, when the enterprise process safety management is graded and evaluated, the enterprise process safety level H is calculated based on the enterprise operation safety level a, the enterprise status safety level b, the enterprise average process safety level c and the weight parameter matrix, and H=a×w1+b×w2+c×w3 is set, and the enterprise process safety level is used as the grading rating result.

[0034] Furthermore, in step S7, the number of enterprise process equipment failures y1 in the current evaluation cycle is compared with the number of enterprise process equipment failures y10 of the preset level standard, and the specific correction is determined according to the comparison result, wherein:

[0035] When y1≤y10, it is determined that no specificity correction is performed;

[0036] When y1>y10, it is determined that specificity correction is performed and the specificity correction coefficient r1 is set to r1=0.85+e -0.5×(y1-y10)-2 , e is the base of the natural logarithm, and the preset average standard enterprise process equipment failure number y0 in the screening process of the historical grading evaluation data of the enterprise is specifically corrected according to the specific correction coefficient r1. The preset average standard enterprise process equipment failure number after specific correction is yr10, and yr10=r1×y0 is set;

[0037] The specific correction times m of the grading evaluation are compared with the preset specific correction times m0 of the grading evaluation, and the universal correction is judged according to the comparison result, where:

[0038] When m≤m0, it is determined that no universal correction is performed;

[0039] When m>m0, it is determined that universal correction is performed and the universal correction coefficient r2 is set, and r2=0.9+e -0.7×(m-m0)-2.5 , e is the base of the natural logarithm. According to the universal correction coefficient r2, the preset average standard number of enterprise process equipment failures y0 in the screening process of historical grading evaluation data is universally corrected. The preset average standard number of enterprise process equipment failures yr20 after universal correction is set as yr20=r2×y0.

[0040] On the other hand, the present invention also provides a system for constructing a process safety management grading evaluation model, comprising:

[0041] The data collection module is used to collect the equipment working hours, equipment maintenance time intervals, safety facility status, number of personnel wearing safety masks, standing areas of personnel not wearing masks, and standing time of personnel not wearing masks within the evaluation period to obtain evaluation data;

[0042] A data processing module, used to process the evaluation data;

[0043] Model building module, used to build operation model and status model based on the evaluation data of the previous evaluation cycle;

[0044] An operation status evaluation module is used to obtain the enterprise operation safety level and enterprise status safety level according to the operation model and the status model;

[0045] A weight parameter setting module is used to set the weight parameter matrix according to historical rating evaluation data;

[0046] The grading and evaluation module is used to grade and evaluate the enterprise's process safety management according to the weight parameter matrix;

[0047] A specific correction module is used to perform specific correction on the screening process of the enterprise's historical rating evaluation data according to the number of failures of the enterprise's process equipment in the current evaluation cycle;

[0048] The universal correction module is used to make universal corrections to the screening process of historical grading evaluation data according to the number of specific corrections of the grading evaluation.

[0049] Compared with the prior art, the beneficial effects of the present invention are that the method collects evaluation data through step S1 so as to perform a process safety management grading evaluation based on the evaluation data, the method processes the evaluation data through step S2 to classify the data for subsequent model building, the method builds an operation model and a state model according to the evaluation data of the previous evaluation cycle through step S3 to classify and analyze the data according to the operation model and the state model, the method obtains the enterprise operation safety level and the enterprise state safety level according to the operation model and the state model through step S4 so as to perform a grading evaluation on the process safety management according to the enterprise operation safety level and the enterprise state safety level, and the method obtains the enterprise operation safety level and the enterprise state safety level according to the operation safety level and the enterprise state safety level according to the operation safety level and the state safety level, and the method obtains the enterprise operation safety level and the ... The weight parameter matrix is ​​set according to the historical grading and evaluation data and step S6 is passed to grade and evaluate the enterprise's process safety management according to the weight parameter matrix, so as to accurately grade and evaluate the enterprise's process safety management. The process safety management grading and evaluation is expanded to be applicable to enterprises through the weight parameter matrix, thereby improving the efficiency of the process safety management grading and evaluation. The method specifically corrects the screening process of the enterprise's historical grading and evaluation data through step S7 to improve the accuracy of the enterprise's process safety management grading and evaluation. The method universally corrects the screening process of the historical grading and evaluation data through step S8 to improve the accuracy of the process safety management grading and evaluation of each enterprise, and further improves the efficiency of the process safety management grading and evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a method for constructing a process safety management grading evaluation model in this embodiment;

[0051] Figure 2 This is a schematic diagram of the structure of the system for constructing the process safety management grading and evaluation model of this embodiment. DETAILED DESCRIPTION

[0052] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0054] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] See also Figure 1 As shown, it is a flow chart of a method for constructing a process safety management grading evaluation model in this embodiment, and the method includes:

[0056] Step S1, collecting the equipment working hours, equipment maintenance time intervals, safety facility status, number of personnel wearing safety masks, standing areas for personnel not wearing masks, and standing time for personnel not wearing masks within the evaluation period to obtain evaluation data;

[0057] Step S2, processing the evaluation data;

[0058] Step S3, constructing an operation model and a state model based on the evaluation data of the previous evaluation cycle;

[0059] Step S4, obtaining the enterprise operation security level and the enterprise state security level according to the operation model and the state model;

[0060] Step S5, setting the weight parameter matrix according to the historical rating evaluation data;

[0061] Step S6, grading and evaluating the enterprise's process safety management according to the weight parameter matrix;

[0062] Step S7, specifically modifying the screening process of the enterprise's historical rating evaluation data according to the number of failures of the enterprise's process equipment in the current evaluation period;

[0063] Step S8, making universal corrections to the screening process of historical rating evaluation data according to the rating evaluation specific correction times.

[0064] Specifically, the method is set in a system for process safety management of an enterprise, and the process safety management of the enterprise is graded and evaluated by constructing a process safety management grading evaluation model, classifying data, and adjusting weight parameters of various types of data so that the process safety management grading evaluation model is suitable for process safety management grading evaluation of multiple objects, thereby improving the efficiency of process safety management grading evaluation. The method collects evaluation data through step S1 to facilitate process safety management grading evaluation based on the evaluation data. The method processes the evaluation data through step S2 to classify the data for subsequent model construction. The method constructs an operation model and a state model according to the evaluation data of the previous evaluation cycle through step S3 to classify and analyze the data according to the operation model and the state model. The method obtains the enterprise operation safety level and the enterprise according to the operation model and the state model through step S4. The method sets the weight parameter matrix according to the historical grading and evaluation data through step S5, and grading and evaluating the enterprise process safety management according to the weight parameter matrix through step S6, so as to accurately grade and evaluate the enterprise process safety management. The process safety management grading and evaluation is applicable to the enterprise through the weight parameter matrix, thereby improving the efficiency of the process safety management grading and evaluation. The method specifically corrects the screening process of the historical grading and evaluation data of the enterprise through step S7, so as to improve the accuracy of the process safety management grading and evaluation of the enterprise. The method universally corrects the screening process of the historical grading and evaluation data through step S8, so as to improve the accuracy of the process safety management grading and evaluation of each enterprise, and further improves the efficiency of the process safety management grading and evaluation.

[0065] Specifically, in step S1, the evaluation cycle refers to the preset time interval for the process safety management grading evaluation of the enterprise. For example, if the evaluation cycle is set to one week, the process safety management grading evaluation of the enterprise is performed every other week. The equipment working time refers to the cumulative time that the equipment is in operation. Step S1 collects the equipment working time through the equipment work log. The equipment maintenance time interval refers to the interval between the two equipment maintenance time points closest in time. Step S1 collects the equipment maintenance time interval through the equipment work log. The safety facility status refers to the safety facilities set up by the enterprise for dangerous situations caused by safety failures, such as fire hydrants, fire extinguishers and gas masks. Step S1 sets the safety facility status according to the normal use of the safety facilities, wherein:

[0066] When the safety facilities can be used normally, the safety facility status is set to normal, and the safety facility status parameter is 1;

[0067] When there are facilities in the safety facilities that cannot be used normally, the safety facility status is set to abnormal, and the safety facility status parameter is 0;

[0068] The present embodiment does not limit the method for obtaining the normal use of the safety facilities. Those skilled in the art can freely set it according to the actual situation, and only need to meet the need to reflect the use of the safety facilities. For example, through the Internet of Things, smart sensors can be set in each safety facility to obtain the normal use of the safety facilities through sensor data. The number of people wearing safety equipment refers to the number of people wearing safety equipment in the working area of ​​the enterprise, such as the number of people wearing safety helmets. The present embodiment does not limit the method for collecting the number of people wearing safety equipment. Those skilled in the art can freely set it according to the actual situation, and only need to meet the need to accurately obtain the number of people wearing safety equipment. For example, the number of people wearing safety equipment can be collected through the temperature data of the temperature sensor set on the safety equipment. The standing area for people who do not wear safety equipment refers to the position area where people who do not wear safety equipment stand in the working area of ​​the enterprise. The step S1 collects the standing area for people who do not wear safety equipment through the camera set in the working area of ​​the enterprise. The standing time for people who do not wear safety equipment refers to the standing time for people who do not wear safety equipment in the working area of ​​the enterprise. The step S1 processes the image obtained by the camera in the working area of ​​the enterprise to obtain the standing time of people who do not wear safety equipment in the working area of ​​the enterprise.

[0069] Specifically, in step S2, when processing the evaluation data, the life t2 of each device is obtained, the device working parameter T is calculated according to the device working time t1, T=t1 / t2 is set, the personnel wearing ratio p is calculated according to the number of personnel wearing safely n and the total number of people in the current working area n0, p=n / n0 is set, the personnel wearing ratio p is compared with the preset personnel wearing ratio p0, and the personnel wearing situation is judged according to the comparison result, wherein:

[0070] When p≥p0, it is judged that the person's wearing condition is normal;

[0071] When p<p0, it is determined that the wearing condition of the personnel is abnormal, and the adjustment coefficient v is set, 0.87<v<0.98, and the safety facility coverage rate u is adjusted according to the adjustment coefficient v. The adjusted safety facility coverage rate is uv, and uv=v×u is set;

[0072] The judgment process of the wearing status of personnel is modified according to the standing area of ​​non-wearing personnel, including:

[0073] When the area where the non-wearing person stands is a first-level dangerous area, the standing time i of the non-wearing person is compared with the first preset standing time i 1, where:

[0074] If i≤i 1, the judgment process of the personnel wearing condition is not corrected;

[0075] If i>i 1, the judgment process of the wearing condition of the personnel is corrected, and the correction coefficient J is set, 1.02<J<1.2, and the preset wearing proportion p0 of the personnel in the judgment process of the wearing condition of the personnel is corrected. The corrected preset wearing proportion of the personnel is pj0, and pj0=J×p0 is set. When pj0>1, pj0 takes the value of 1;

[0076] When the area where the person who does not wear the mask stands is a secondary dangerous area, the standing time i of the person who does not wear the mask is compared with the second preset standing time i2, where:

[0077] If i≤i2, the judgment process of the wearing condition of the personnel will not be corrected;

[0078] If i>i2, the judgment process of the wearing condition of the personnel is corrected, and the correction coefficient J is set, 1.01<J<1.15, and the preset personnel wearing ratio p0 in the judgment process of the wearing condition of the personnel is corrected. The corrected preset personnel wearing ratio is pj0, and pj0=J×p0 is set. When pj0>1, pj0 takes the value of 1;

[0079] When the area where people who are not wearing the device are standing is a safe area, the judgment process of the person wearing the device is not corrected;

[0080] The equipment operating parameters and equipment maintenance time intervals are taken as operation data, and the safety facility status and safety facility coverage rate are taken as status data.

[0081] Specifically, the life of each device refers to the length of time that the enterprise's production process equipment can work normally. Step S2 obtains the life of each device by reading the attributes of the enterprise's production process equipment. The safety facility coverage rate refers to the degree of radiation of the setting location of the safety facility to the enterprise's work area. The total number of people in the current work area refers to the total number of people in the enterprise's work area at the current time. This embodiment does not limit the method for obtaining the total number of people in the current work area. Technical personnel in this field can freely set it according to actual conditions, and only need to meet the accurate acquisition requirements of the total number of people in the current work area. For example, the total number of people in the current work area of ​​the enterprise can be collected through the camera in the enterprise's work area. The preset personnel wearing ratio refers to a preset value that reflects the abnormal wearing situation of the personnel. For example, the preset personnel wearing ratio can be set to 95%. The preferred value of the adjustment coefficient in this embodiment is v=0.92. The enterprise work area refers to the area where the enterprise conducts production activities. The enterprise work area is divided according to the dangerousness of the production activities to obtain the first-level dangerous area, the second-level dangerous area and the safe area. This embodiment does not limit the division method of the enterprise work area. Domain technicians can freely set it according to actual conditions, and only need to meet the needs of distinguishing dangerous areas. For example, the area within the preset safety distance from the radioactive equipment can be set as a first-level dangerous area, the area within the preset safety distance from the dangerous gas equipment can be set as a second-level dangerous area, and other enterprise work areas are safe areas. This embodiment does not limit the way of safety facility coverage. Technical personnel in this field can freely set it according to actual conditions. For example, the area within the preset use distance of the safety facility can be set as the safety facility coverage area, and the safety facility coverage areas can be combined to obtain the total area covered by the safety facilities. The total area of ​​the safety facility coverage is divided by the area of ​​the enterprise work area to obtain the safety facility coverage rate. The first preset standing time refers to the preset time value that needs to be corrected for the judgment process of the personnel wearing situation when the standing area of ​​the non-wearing personnel is the first-level dangerous area, such as it can be set to 10 minutes. The second preset standing time refers to the preset time value that needs to be corrected for the judgment process of the personnel wearing situation when the standing area of ​​the non-wearing personnel is the second-level dangerous area, such as it can be set to 30 minutes, 0<i 1<i2.

[0082] Specifically, in step S3, when constructing the operation model and the state model, the operation model is constructed according to the safety facility status of the previous evaluation cycle and the operation safety level corresponding to the safety facility status, and the state model is constructed according to the state data of the previous evaluation cycle and the state safety level corresponding to the state data.

[0083] It can be understood that this embodiment does not limit the construction method of the operation model and the state model. It only needs to meet the accurate output requirements of the operation model and the state model for the enterprise operation safety level and the enterprise state safety level. For example, it can be set to obtain the safety facility status and the operation safety level corresponding to the safety facility status at each moment in the previous evaluation cycle, and use them as the operation model construction data, and set 70% of the operation model construction data as the operation model training set, and 30% of the operation model construction data as the operation model test set. The operation model training set is input into the neural network model for training, and the trained neural network model is tested according to the operation model test set. When the accuracy of the test result reaches 95%, the neural network model is output as the operation model, and the state data and the state safety level corresponding to the state data at each moment in the previous evaluation cycle are obtained, and used as the state model construction data, and 70% of the state model construction data is set as the state model training set, and 30% of the state model construction data is set as the state model test set. The state model training set is input into the neural network model for training, and the trained neural network model is tested according to the operation model test set. When the accuracy of the test result reaches 95%, the neural network model is output as the state model.

[0084] Specifically, in step S4, the evaluation data of the current evaluation cycle is input into the operation model and the state model, and the enterprise operation safety level and the enterprise state safety level are output respectively.

[0085] Specifically, in step S5, when setting the weight parameter matrix, the weight parameter matrix is ​​initialized and set to [w1, w2, w3], where w1 is the weight parameter of the enterprise operation safety level, w2 is the weight parameter of the enterprise status safety level, and w3 is the weight parameter of the enterprise average process safety level, w1+w2+w3=1;

[0086] The weight parameter matrix is ​​trained according to the historical grading evaluation data, and when the accuracy reaches the preset accuracy, the weight parameter matrix is ​​output.

[0087] Specifically, in this embodiment, the initial values ​​of the weight parameter matrix are set to w1=0.5, w2=0.5, w3=0. The historical rating evaluation data refers to the enterprise operation safety level, enterprise status safety level and enterprise process safety level of each historical evaluation period. The enterprise average process safety level refers to the sum of the enterprise process safety levels of each historical evaluation period divided by the total number of historical evaluation periods. This embodiment does not limit the training method of the weight parameter matrix. Technical personnel in this field can freely set it according to actual conditions. It only needs to meet the model calculation requirements of the enterprise process safety level. For example, the weight parameter matrix can be trained by the back propagation algorithm combined with the gradient descent method. The accuracy refers to the ratio of the number of times the test results of the weight parameter matrix are consistent with the enterprise process safety level of each historical evaluation period to the total number of tests when testing the training results of the weight parameter matrix. The preset accuracy refers to the preset accuracy of the training results of the weight parameter matrix reaching the output standard. For example, the preset accuracy can be set to 93%.

[0088] Specifically, in step S5, the number of enterprise process equipment failures y in each historical evaluation period is compared with the preset average standard enterprise process equipment failure number y0, and the historical grading evaluation data is screened according to the comparison result, wherein:

[0089] When y≤y0, the grading evaluation data of the historical evaluation period is selected as the historical grading evaluation data;

[0090] When y>y0, the rating evaluation data of the historical evaluation period is not selected as the historical rating evaluation data.

[0091] Specifically, the number of enterprise process equipment failures in each historical evaluation cycle refers to the number of times the enterprise process equipment fails in each historical evaluation cycle. The preset average standard number of enterprise process equipment failures refers to the preset value of the number of failures that reflects that the graded evaluation data of the historical evaluation cycle is not suitable as historical graded evaluation data. For example, the preset average standard number of enterprise process equipment failures can be set to 5 times.

[0092] Specifically, in step S6, when the enterprise process safety management is graded and evaluated, the enterprise process safety level H is calculated based on the enterprise operation safety level a, the enterprise status safety level b, the enterprise average process safety level c and the weight parameter matrix, and H=a×w1+b×w2+c×w3 is set, and the enterprise process safety level is used as the graded rating result.

[0093] Specifically, in step S7, the number of enterprise process equipment failures y1 in the current evaluation cycle is compared with the number of enterprise process equipment failures y10 of the preset level standard, and the specific correction is determined according to the comparison result, wherein:

[0094] When y1≤y10, it is determined that no specificity correction is performed;

[0095] When y1>y10, it is determined that specificity correction is performed and the specificity correction coefficient r1 is set to r1=0.85+e -0.5×(y1-y10)-2 , e is the base of the natural logarithm. According to the specific correction coefficient r1, the preset average standard number of enterprise process equipment failures y0 in the screening process of the historical rating evaluation data of the enterprise is specifically corrected. The preset average standard number of enterprise process equipment failures after specific correction is yr10, and yr10=r1×y0 is set.

[0096] Specifically, the number of enterprise process equipment failures in the current evaluation cycle refers to the number of times the enterprise process equipment fails within the current evaluation cycle. Step S7 obtains the number of enterprise process equipment failures through the enterprise process equipment log. The preset level standard number of enterprise process equipment failures refers to the preset value of the number of enterprise process equipment failures corresponding to the enterprise process safety level of the enterprise. For example, when the enterprise process safety level of the enterprise is level 3, the preset level standard number of enterprise process equipment failures is 5 times; when the enterprise process safety level of the enterprise is level 1, the preset level standard number of enterprise process equipment failures is 2 times. The specific correction refers to the situation where the number of enterprise process equipment failures y in the current evaluation cycle of the enterprise is greater than the preset level standard number of enterprise process equipment failures, and only the preset average standard number of enterprise process equipment failures y0 of the enterprise is corrected.

[0097] Specifically, in step S8, the number of specific corrections m for the grading evaluation is compared with the preset number of specific corrections m0 for the grading evaluation, and the universal correction is judged according to the comparison result, wherein:

[0098] When m≤m0, it is determined that no universal correction is performed;

[0099] When m>m0, it is determined that universal correction is performed and the universal correction coefficient r2 is set, and r2=0.9+e -0.7×(m-m0)-2.5 , e is the base of the natural logarithm. According to the universal correction coefficient r2, the preset average standard number of enterprise process equipment failures y0 in the screening process of historical grading evaluation data is universally corrected. The preset average standard number of enterprise process equipment failures yr20 after universal correction is set as yr20=r2×y0.

[0100] Specifically, the number of specific corrections for graded evaluation refers to the total number of specific corrections performed by each enterprise, the preset number of specific corrections for graded evaluation refers to a preset value reflecting the number of corrections required for universal corrections, such as 30 times, and the universal correction refers to the situation where the preset average standard number of enterprise process equipment failures for each enterprise is corrected when the total number of specific corrections performed by each enterprise is greater than the preset number of specific corrections for graded evaluation.

[0101] See also Figure 2 As shown, it is a schematic diagram of the structure of the system for constructing the process safety management grading evaluation model of this embodiment, and the system includes:

[0102] The data collection module is used to collect the equipment working hours, equipment maintenance time intervals, safety facility status, number of personnel wearing safety masks, standing areas of personnel not wearing masks, and standing time of personnel not wearing masks within the evaluation period to obtain evaluation data;

[0103] Data processing module, used to process and connect the evaluation data;

[0104] A model building module, used to build an operation model and a state model according to the evaluation data of the previous evaluation cycle, and the model building module is connected to the data processing module;

[0105] An operation status evaluation module is used to obtain the enterprise operation safety level and the enterprise state safety level according to the operation model and the state model. The operation status evaluation module is connected with the model construction module;

[0106] A weight parameter setting module is used to set the weight parameter matrix according to the historical grading evaluation data, and the weight parameter setting module is connected to the operation status evaluation module;

[0107] A grading evaluation module is used to grade and evaluate the enterprise process safety management according to the weight parameter matrix. The grading evaluation module is connected with the weight parameter setting module;

[0108] A specific correction module is used to perform specific correction on the screening process of the enterprise's historical grading evaluation data according to the number of failures of the enterprise's process equipment in the current evaluation cycle. The specific correction module is connected to the grading evaluation module.

[0109] The universal correction module is used to perform universal correction on the screening process of historical grading evaluation data according to the number of specific corrections of grading evaluation, and the universal correction module is connected with the specific correction module.

[0110] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for constructing a process safety management grading evaluation model, characterized in that: include: Step S1, collecting the equipment working hours, equipment maintenance time intervals, safety facility status, number of personnel wearing safety masks, standing areas for personnel not wearing masks, and standing time for personnel not wearing masks within the evaluation period to obtain evaluation data; Step S2, processing the evaluation data; Step S3, constructing an operation model and a state model according to the evaluation data of the previous evaluation cycle; Step S4, obtaining the enterprise operation security level and the enterprise state security level according to the operation model and the state model; Step S5, setting the weight parameter matrix according to the historical rating evaluation data; Step S6, grading and evaluating the enterprise's process safety management according to the weight parameter matrix; Step S7, specifically modifying the screening process of the enterprise's historical rating evaluation data according to the number of failures of the enterprise's process equipment in the current evaluation period; Step S8, making universal corrections to the screening process of historical rating evaluation data according to the rating evaluation specific correction times.

2. The method for constructing a process safety management grading evaluation model according to claim 1, characterized in that: In step S2, when the evaluation data is processed, the life t2 of each device is obtained, the device working parameter T is calculated according to the device working time t1, T=t1 / t2 is set, the personnel wearing ratio p is calculated according to the number of personnel wearing safely n and the total number of people in the current working area n0, p=n / n0 is set, the personnel wearing ratio p is compared with the preset personnel wearing ratio p0, and the personnel wearing situation is judged according to the comparison result, wherein: When p≥p0, it is judged that the person's wearing condition is normal; When p<p0, it is determined that the wearing condition of the personnel is abnormal, and the adjustment coefficient v is set, 0.87<v<0.98, and the safety facility coverage rate u is adjusted according to the adjustment coefficient v. The adjusted safety facility coverage rate is uv, and uv=v×u is set.

3. The method for constructing a process safety management grading evaluation model according to claim 2, characterized in that: In step S2, the process of judging the wearing status of the person is modified according to the standing area of ​​the person who is not wearing the wearer, wherein: When the area where the non-wearing person stands is a first-level dangerous area, the standing time i of the non-wearing person is compared with the first preset standing time i 1, where: If i≤i 1, the judgment process of the personnel wearing condition is not corrected; If i>i 1, the judgment process of the wearing condition of the personnel is corrected, and the correction coefficient J is set, 1.02<J<1.2, and the preset wearing proportion p0 of the personnel in the judgment process of the wearing condition of the personnel is corrected. The corrected preset wearing proportion of the personnel is pj0, and pj0=J×p0 is set. When pj0>1, pj0 takes the value of 1; When the area where the person who does not wear the mask stands is a secondary dangerous area, the standing time i of the person who does not wear the mask is compared with the second preset standing time i2, where: If i≤i2, the judgment process of the wearing condition of the personnel will not be corrected; If i>i2, the judgment process of the wearing condition of the personnel is corrected, and the correction coefficient J is set, 1.01<J<1.15, and the preset personnel wearing ratio p0 in the judgment process of the wearing condition of the personnel is corrected. The corrected preset personnel wearing ratio is pj0, and pj0=J×p0 is set. When pj0>1, pj0 takes the value of 1; When the area where people who are not wearing the device are standing is a safe area, the judgment process of the person wearing the device is not corrected; The equipment operating parameters and equipment maintenance time intervals are taken as operation data, and the safety facility status and safety facility coverage rate are taken as status data.

4. The method for constructing a process safety management grading evaluation model according to claim 3, characterized in that: In step S3, when constructing the operation model and the state model, the operation model is constructed according to the safety facility status of the previous evaluation cycle and the operation safety level corresponding to the safety facility status, and the state model is constructed according to the state data of the previous evaluation cycle and the state safety level corresponding to the state data.

5. The method for constructing a process safety management grading evaluation model according to claim 4, characterized in that: In step S4, the evaluation data of the current evaluation cycle is input into the operation model and the state model, and the enterprise operation safety level and the enterprise state safety level are output respectively.

6. The method for constructing a process safety management grading evaluation model according to claim 1, characterized in that: In the step S5, when setting the weight parameter matrix, the weight parameter matrix is ​​initialized and set to [w1, w2, w3], where w1 is the weight parameter of the enterprise operation safety level, w2 is the weight parameter of the enterprise status safety level, and w3 is the weight parameter of the enterprise average process safety level, w1+w2+w3=1; The weight parameter matrix is ​​trained according to the historical grading evaluation data, and when the accuracy reaches the preset accuracy, the weight parameter matrix is ​​output.

7. The method for constructing a process safety management grading evaluation model according to claim 6, characterized in that: In step S5, the number of enterprise process equipment failures y in each historical evaluation period is compared with the preset average standard enterprise process equipment failure number y0, and the historical grading evaluation data is screened according to the comparison result, wherein: When y≤y0, the grading evaluation data of the historical evaluation period is selected as the historical grading evaluation data; When y>y0, the rating evaluation data of the historical evaluation period is not selected as the historical rating evaluation data.

8. The method for constructing a process safety management grading evaluation model according to claim 7, characterized in that: In step S6, when the enterprise process safety management is graded and evaluated, the enterprise process safety level H is calculated based on the enterprise operation safety level a, the enterprise status safety level b, the enterprise average process safety level c and the weight parameter matrix, and H=a×w1+b×w2+c×w3 is set, and the enterprise process safety level is used as the graded rating result.

9. The method for constructing a process safety management grading evaluation model according to claim 8, characterized in that: In step S7, the number of enterprise process equipment failures y1 in the current evaluation cycle is compared with the number of enterprise process equipment failures y10 of the preset level standard, and the specific correction is determined according to the comparison result, wherein: When y1≤y10, it is determined that no specificity correction is performed; When y1>y10, it is determined that specificity correction is performed and the specificity correction coefficient r1 is set to r1=0.85+e -0.5×(y1-y10)-2 , e is the base of the natural logarithm, and the preset average standard enterprise process equipment failure number y0 in the screening process of the historical grading evaluation data of the enterprise is specifically corrected according to the specific correction coefficient r1. The preset average standard enterprise process equipment failure number after specific correction is yr10, and yr10=r1×y0 is set; The specific correction times m of the grading evaluation are compared with the preset specific correction times m0 of the grading evaluation, and the universal correction is judged according to the comparison result, where: When m≤m0, it is determined that no universal correction is performed; When m>m0, it is determined that universal correction is performed and the universal correction coefficient r2 is set, and r2=0.9+e -0.7×(m-m0)-2.5 , e is the base of the natural logarithm. According to the universal correction coefficient r2, the preset average standard number of enterprise process equipment failures y0 in the screening process of historical grading evaluation data is universally corrected. The preset average standard number of enterprise process equipment failures yr20 after universal correction is set as yr20=r2×y0.

10. A system applied to the method for constructing a process safety management grading evaluation model as claimed in any one of claims 1 to 9, characterized in that: include: The data collection module is used to collect the equipment working hours, equipment maintenance time intervals, safety facility status, number of personnel wearing safety masks, standing areas of personnel not wearing masks, and standing time of personnel not wearing masks within the evaluation period to obtain evaluation data; A data processing module, used to process the evaluation data; Model building module, used to build operation model and status model based on the evaluation data of the previous evaluation cycle; An operation status evaluation module is used to obtain the enterprise operation safety level and enterprise status safety level according to the operation model and the status model; A weight parameter setting module is used to set the weight parameter matrix according to historical rating evaluation data; The grading and evaluation module is used to grade and evaluate the enterprise's process safety management according to the weight parameter matrix; A specific correction module is used to perform specific correction on the screening process of the enterprise's historical rating evaluation data according to the number of failures of the enterprise's process equipment in the current evaluation cycle; The universal correction module is used to make universal corrections to the screening process of historical grading evaluation data according to the number of specific corrections of the grading evaluation.

Images