Industrial park safety supervision method and system based on digital twin model

Abstract

The invention provides an industrial park safety supervision method and system based on a digital twinborn model, and belongs to the technical field of digital twinborn, and the method specifically comprises the steps: determining whether the identification accuracy of the potential safety hazard of the digital twinborn model meets the requirement or not based on the deviation condition of identification deviation data and an identification deviation date; based on an analysis result of the digital twinborn model, determining model matching conditions of the digital twinborn model and different areas in the industrial park, and determining model updating demand coefficients of the different areas in combination with historical occurrence data and identification deviation data of potential safety hazards of the different areas; and determining historical occurrence data of potential safety hazards of the industrial park at different dates, determining an updating processing strategy of a digital twin model of the industrial park in combination with model updating demand coefficients of different regions, and performing safety supervision processing on the industrial park by using the updated digital twin model. And the identification processing efficiency of the security risk is improved.

Description

Technical Field

[0001] The present invention belongs to the field of digital twin technology, and in particular relates to an industrial park safety supervision method and system based on a digital twin model. Background Art

[0002] The flow of people and vehicles within the industrial park fluctuates greatly, and the enterprise structure within the industrial park is relatively complex, which makes the security management of the industrial park more difficult.

[0003] In order to achieve safety control of industrial parks, the existing technical solution CN202311287148.3 "A method for park safety supervision based on digital twins" uses the collected park operation data to drive the digital twin model for simulation analysis, thereby generating park safety supervision prediction data and early warning information, which improves the efficiency of intervention and processing of safety risks. However, the above technical solution has the following problems: When conducting safety supervision in industrial parks, once the digital twin model within the industrial park is completed, the companies and safety risk potential points within the industrial park will gradually change. This may result in the digital twin model being unable to accurately identify safety risk potential points in real time. Therefore, how to update the digital twin model in a targeted manner has become a technical problem that needs to be solved urgently.

[0004] In response to the above technical problems, the present application specifically provides an industrial park safety supervision method and system based on a digital twin model. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: In the first aspect, the present application provides an industrial park safety supervision method based on a digital twin model, specifically comprising: S1 determines the identification deviation data of the safety hazards of the digital twin model of the industrial park on different dates based on the historical identification data of the safety hazards of the digital twin model, and determines the identification deviation date of the digital twin model using the identification deviation data; S2 determines the deviation of the identification deviation data of the potential safety hazard between different identification deviation dates, and when it is determined that the identification accuracy of the potential safety hazard of the digital twin model meets the requirements based on the deviation of the identification deviation data and the identification deviation date, proceeds to the next step; S3 determines the matching status of the digital twin model with the models of different areas in the industrial park based on the analysis results of the digital twin model, and determines the model update requirement coefficients of different areas in combination with the historical occurrence data and identification deviation data of safety hazards in different areas; S4 determines the historical occurrence data of potential safety hazards in the industrial park on different dates, and combines the model update demand coefficients of different regions to determine the update processing strategy for the digital twin model of the industrial park, and uses the updated digital twin model for safety supervision processing of the industrial park.

[0006] The beneficial effects of the present invention are as follows: By using the deviation situation of the identified deviation data and the identified deviation dates, it is determined whether the recognition accuracy rate of potential safety hazards of the digital twin model meets the requirements, thus fully considering the recognition deviation situation of potential safety hazards of the digital twin model. It not only considers the distribution data of the identified deviation dates with relatively serious recognition deviations, but also considers the distribution dispersion of the recognition deviations of potential safety hazards in different identified deviation dates, realizing the recognition of the situation where the digital twin model cannot accurately identify potential safety hazards, and also laying a foundation for the differential update processing of the digital twin model of the industrial park.

[0007] According to the historical occurrence data of potential safety hazards in the industrial park on different dates and the model update demand coefficients of different regions, the update processing strategy for the digital twin model of the industrial park is determined, realizing the recognition of the digital twin models of industrial parks with more potential safety hazards, industrial parks with deviation in the recognition of potential safety hazards of the digital twin model, and industrial parks with less matching models, thus realizing the determination of the differential update processing strategy for the digital twin model of the industrial park based on the above factors. On the basis of reducing the difficulty of the update processing of the digital twin model, it also improves the accuracy of the recognition and processing of the safety risks of the digital twin model.

[0008] A further technical solution lies in that the historical recognition data includes the occurrence times of potential safety hazards and the recognition and processing results of potential safety hazards.

[0009] A further technical solution lies in that the identified deviation data includes the delayed recognition times and unrecognized times of potential safety hazards.

[0010] A further technical solution lies in that the delayed recognition times are the recognition times when the recognition processing duration is greater than the preset recognition processing duration.

[0011] A further technical solution lies in that the method for determining the identified deviation dates of the digital twin model is as follows: Using the identified deviation data to obtain the delayed recognition times and unrecognized times of potential safety hazards in the digital twin model on different dates; Based on the delayed recognition times and unrecognized times of potential safety hazards in different regions, the identified deviation regions in the regions are obtained; According to the number of the identified deviation regions, it is determined whether the date is an identified deviation date.

[0012] A further technical solution lies in that the recognition deviation area is an area with a delay recognition count or an unrecognized count.

[0013] A further technical solution lies in that the method for determining the recognition deviation risk coefficient of the potential safety hazard in the area is as follows: Determine the risk coefficients of different potential safety hazards by multiplying the historical occurrence counts of different potential safety hazards by a preset proportionality factor; Determine the recognition deviation proportionality coefficients of different potential safety hazards according to the ratio of the recognition deviation counts to the historical occurrence counts of different potential safety hazards; Determine the recognition deviation risk coefficient of the potential safety hazard in the area by summing the products of the risk coefficients and the recognition deviation proportionality coefficients of different potential safety hazards.

[0014] A further technical solution lies in that the value range of the model update requirement coefficient of the area is between 0 and 1, where the larger the model update requirement coefficient of the area, the higher the update requirement degree of the digital twin model of the area.

[0015] A further technical solution lies in that the method for determining the update processing strategy of the digital twin model of the industrial park is as follows: Based on the model update requirement coefficients of different areas, determine the average value of the model update requirement coefficients of different areas and use it as the basic update requirement coefficient of the industrial park; Based on the historical occurrence data of potential safety hazards in the industrial park on different dates, determine the proportion of the number of dates with potential safety hazards and use it as the proportion of the number of hazard dates in the industrial park; Determine the update requirement coefficient of the digital twin model of the industrial park through the basic update requirement coefficient and the proportion of the number of hazard dates of the industrial park, and use the update requirement coefficient to determine the update processing strategy of the digital twin model of the industrial park.

[0016] A further technical solution lies in that the update requirement coefficient of the digital twin model of the industrial park is determined according to the product of the basic update requirement coefficient and the proportion of the number of hazard dates of the industrial park.

[0017] A further technical solution lies in that using the update requirement coefficient to determine the update processing strategy of the digital twin model of the industrial park specifically includes: When the update requirement coefficient is greater than a preset requirement coefficient threshold, use a preset update strategy to perform the update processing of the digital twin model; When the update requirement coefficient is not greater than the preset requirement coefficient threshold, it is determined whether the update requirement coefficient is within the preset coefficient range. When it is within the preset coefficient range, the update processing strategy for the digital twin models of different regions is determined according to the model update requirement coefficients of different regions. When it is not within the preset coefficient range, the update processing of the digital twin model of the industrial park is not performed temporarily.

[0018] A further technical solution is that the preset update strategy is to perform update processing on the digital twin models of all regions in the industrial park.

[0019] A further technical solution is that determining the update processing strategy for the digital twin models of different regions according to the model update requirement coefficients of different regions specifically includes: Taking the regions where the model update requirement coefficients are within the preset model coefficient interval as target regions, and performing update processing on the digital twin models of the target regions.

[0020] In a second aspect, the present invention provides an industrial park safety supervision system based on a digital twin model, adopting the above-mentioned industrial park safety supervision method based on a digital twin model, specifically including: An accuracy evaluation module, an update requirement evaluation module, and an update processing module; Among them, the accuracy evaluation module is responsible for determining whether the recognition accuracy of the potential safety hazards of the digital twin model meets the requirements; The update requirement evaluation module is responsible for determining the model update requirement coefficients of different regions; The update processing module is responsible for determining the update processing strategy for the digital twin model of the industrial park, and performing safety supervision processing on the industrial park by using the updated digital twin model.

[0021] Other features and advantages will be described in the following description, and part of them will become obvious from the description, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the description and the drawings.

[0022] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0023] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious.

[0024] Figure 1 is a flowchart of an industrial park safety supervision method based on a digital twin model; Figure 2It is a flowchart of a method for determining the identification deviation date of a digital twin model; Figure 3 It is a flowchart of a method for determining the model update demand coefficient of a region; Figure 4 It is a framework diagram of an industrial park safety supervision system based on a digital twin model. Detailed implementation manners

[0025] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar structures, and thus their detailed descriptions will be omitted.

[0026] The terms "a", "an", "the", and "said" are used to denote the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to mean an open inclusion and mean that there may be additional elements / components / etc. in addition to the listed elements / components / etc.

[0027] Example 1 To solve the above problems, according to one aspect of the present invention, as Figure 1 shown, the present application provides an industrial park safety supervision method based on a digital twin model, specifically including: S1 Using the historical identification data of safety hazards of the digital twin model of the industrial park, determine the identification deviation data of safety hazards of the digital twin model on different dates, and use the identification deviation data to determine the identification deviation date of the digital twin model; Furthermore, the historical identification data includes the occurrence times of safety hazards and the identification and treatment results of safety hazards.

[0028] Specifically, the identification deviation data includes the delayed identification times and unrecognized times of safety hazards.

[0029] It should be noted that the delayed identification times are the identification times when the identification processing duration is greater than the preset identification processing duration.

[0030] It can be understood that, as Figure 2 shown, the method for determining the identification deviation date of the digital twin model is: Using the identification deviation data to obtain the delayed identification times and unrecognized times of safety hazards of the digital twin model on different dates; Based on the number of delayed identifications and the number of non-identifications of potential safety hazards in different regions, identify the regions with identification deviations in the said regions; Determine whether the date is an identification deviation date according to the number of the identified deviation regions.

[0031] It should be noted that the identified deviation regions are the regions with the number of delayed identifications or the number of non-identifications.

[0032] In another embodiment, determining whether the date is an identification deviation date according to the number of the identified deviation regions specifically includes: When the number of the identified deviation regions in the said date is greater than the preset number of deviation regions, determine that the date is an identification deviation date.

[0033] Optionally, the method for determining the identification deviation date of the digital twin model is: Use the identified deviation data to conduct the number of delayed identifications and the number of non-identifications of potential safety hazards in the digital twin model on different dates. When the total number of the number of delayed identifications and the number of non-identifications of potential safety hazards in the said date does not meet the requirements, determine that the date is an identification deviation date; When the total number of the number of delayed identifications and the number of non-identifications of potential safety hazards in the said date meets the requirements: Based on the number of delayed identifications and the number of non-identifications of potential safety hazards in different regions, identify the regions with identification deviations in the said regions. When there are identified deviation regions where the total number of the number of delayed identifications and the number of non-identifications does not meet the requirements, determine that the date is an identification deviation date; When there are no identified deviation regions where the total number of the number of delayed identifications and the number of non-identifications does not meet the requirements: Obtain the number of the identified deviation regions in the said date. When the number of the identified deviation regions in the said date does not meet the requirements, determine that the date is an identification deviation date; When the number of the identified deviation regions in the said date meets the requirements: Obtain the number of delayed identifications and the number of non-identifications of different potential safety hazards in different identified deviation regions, and combine the identification processing duration of the number of delayed identifications of different potential safety hazards to determine the regional identification deviation coefficient of different identified deviation regions. When there are identified deviation regions where the regional identification deviation coefficient does not meet the requirements, determine that the date is an identification deviation date; When there are no identified deviation regions where the regional identification deviation coefficient does not meet the requirements: When there are no identified deviation regions within the preset deviation coefficient range and the number of identified deviation regions is within the preset region number range, determine that the date does not belong to the identification deviation date; When there is an identification deviation area with the area identification deviation coefficient within the preset deviation coefficient range or the number of identification deviation areas is not within the preset area number range: Determine the identification deviation amount of the date according to the area identification deviation coefficients of different identification deviation areas, and determine whether the date is an identification deviation date based on the identification deviation amount.

[0034] S2 Determine the deviation situation of the identification deviation data of potential safety hazards between different identification deviation dates, and when it is determined that the identification accuracy rate of potential safety hazards of the digital twin model meets the requirements based on the deviation situation of the identification deviation data and the identification deviation dates, proceed to the next step; Furthermore, the deviation situation of the identification deviation data includes the deviation situation of potential safety hazards with identification deviations between different identification deviation dates.

[0035] Specifically, determining that the identification accuracy rate of potential safety hazards of the digital twin model meets the requirements specifically includes: Based on the deviation situation of the identification deviation data, determine the deviation quantity of potential safety hazards with identification deviations between different identification deviation dates, and use the deviation quantity to determine the distribution deviation coefficient of potential safety hazards with identification deviations between different identification deviation dates; Obtain the proportion of the number of the identification deviation dates, and use the proportion of the number of the identification deviation dates as the proportion of the number of deviation dates; Determine the model identification deviation amount of potential safety hazards of the digital twin model through the average value of the distribution deviation coefficients of potential safety hazards with identification deviations between different identification deviation dates and the proportion of the number of deviation dates, and use the model identification deviation amount to determine whether the identification accuracy rate of potential safety hazards of the digital twin model meets the requirements.

[0036] Furthermore, the distribution deviation coefficient of potential safety hazards with identification deviations between the identification deviation dates is determined according to the product of the deviation quantity between the identification deviation dates and the preset proportional factor.

[0037] It can be understood that using the model identification deviation amount to determine whether the identification accuracy rate of potential safety hazards of the digital twin model meets the requirements specifically includes: When the model identification deviation amount is greater than the preset deviation amount threshold, it is determined that the identification accuracy rate of potential safety hazards of the digital twin model does not meet the requirements.

[0038] Specifically, when the identification accuracy rate of potential safety hazards of the digital twin model does not meet the requirements, it is determined to adopt a preset update strategy for updating the digital twin model.

[0039] Optionally, it is determined that the recognition accuracy rate of identifying potential safety hazards of the digital twin model meets the requirements, specifically including: Obtain the proportion of the number of the recognition deviation dates. When the proportion of the number of the recognition deviation dates is greater than the preset proportion of the number of deviation dates, it is determined that the recognition accuracy rate of identifying potential safety hazards of the digital twin model does not meet the requirements; When the proportion of the number of the recognition deviation dates is not greater than the preset proportion of the number of deviation dates: Based on the recognition deviation data in different recognition deviation dates, determine the number of recognition deviations in different recognition deviation dates. When the number of recognition deviation dates with the number of recognition deviations within the preset deviation number range is greater than the preset number of deviation dates, it is determined that the recognition accuracy rate of identifying potential safety hazards of the digital twin model does not meet the requirements; When the number of recognition deviation dates with the number of recognition deviations within the preset deviation number range is not greater than the preset number of deviation dates: Based on the deviation situation of the recognition deviation data, determine the deviation quantity of potential safety hazards with recognition deviations between different recognition deviation dates, and use the deviation quantity to determine the distribution deviation coefficient of the recognition deviations between different recognition deviation dates. When the average value of the distribution deviation coefficients of the recognition deviations between different recognition deviation dates is greater than the preset distribution deviation coefficient threshold: When any one of the proportion of the number of the recognition deviation dates and the number of the recognition deviation dates is not within the preset range, it is determined that the recognition accuracy rate of identifying potential safety hazards of the digital twin model does not meet the requirements; When both the proportion of the number of the recognition deviation dates and the number of the recognition deviation dates are within the preset range or the average value of the distribution deviation coefficients of the recognition deviations between different recognition deviation dates is not greater than the preset distribution deviation coefficient threshold: Determine the model recognition deviation quantity of the potential safety hazards of the digital twin model through the average value of the distribution deviation coefficients of the recognition deviations between different recognition deviation dates and the proportion of the number of deviation dates, and use the model recognition deviation quantity to determine whether the recognition accuracy rate of the potential safety hazards of the digital twin model meets the requirements.

[0040] Furthermore, the number of recognition deviations includes the number of delayed recognitions and the number of non-recognitions.

[0041] S3 Based on the analysis result of the digital twin model, determine the model matching situation between the digital twin model and different areas in the industrial park, and combine the historical occurrence data and recognition deviation data of potential safety hazards in different areas to determine the model update demand coefficient of different areas; Specifically, the model matching situation of the area is determined according to the matching situation between the digital twin model of the area and the actual situation of the area, specifically determined according to the ratio of the number of models built based on the digital twin model of the area to all the numbers.

[0042] Specifically, as Figure 3 shown, the method for determining the model update requirement coefficient of the area is: Based on the model matching situation between the digital twin model and the area, determine the ratio of the number of models built by the digital twin model in the area to the number of all devices and buildings, and use it as the model matching coefficient; According to the historical occurrence data of potential safety hazards in the area, determine the historical occurrence times of different potential safety hazards, and use the historical occurrence times of different potential safety hazards and the number of identification deviation times to determine the identification deviation risk coefficient of potential safety hazards in the area; Based on the ratio of the identification deviation risk coefficient to the model matching coefficient, determine the model update requirement coefficient of the area.

[0043] It should be noted that the method for determining the identification deviation risk coefficient of potential safety hazards in the area is: Use the product of the historical occurrence times of different potential safety hazards and the preset proportionality factor to determine the risk coefficient of different potential safety hazards; According to the ratio of the number of identification deviation times to the historical occurrence times of different potential safety hazards, determine the identification deviation proportionality coefficient of different potential safety hazards; Determine the identification deviation risk coefficient of potential safety hazards in the area by the sum of the products of the risk coefficients and the identification deviation proportionality coefficients of different potential safety hazards.

[0044] Furthermore, the value range of the model update requirement coefficient of the area is between 0 and 1. The larger the model update requirement coefficient of the area, the higher the update requirement degree of the digital twin model of the area.

[0045] S4 Determine the historical occurrence data of potential safety hazards in the industrial park on different dates, and combine the model update requirement coefficients of different areas to determine the update processing strategy of the digital twin model of the industrial park, and use the updated digital twin model for the safety supervision and management of the industrial park.

[0046] It should be noted that the method for determining the update processing strategy of the digital twin model of the industrial park is: Based on the model update requirement coefficients of different areas, determine the average value of the model update requirement coefficients of different areas, and use it as the basic update requirement coefficient of the industrial park; Based on the historical occurrence data of potential safety hazards in the industrial park on different dates, determine the proportion of the number of dates with potential safety hazards, and use it as the proportion of the number of dates with potential hazards in the industrial park; Based on the basic update demand coefficient of the industrial park and the proportion of the number of dates with potential hazards, determine the update demand coefficient of the digital twin model of the industrial park, and use the update demand coefficient to determine the update processing strategy of the digital twin model of the industrial park.

[0047] Furthermore, the update demand coefficient of the digital twin model of the industrial park is determined according to the product of the basic update demand coefficient of the industrial park and the proportion of the number of dates with potential hazards.

[0048] It can be understood that using the update demand coefficient to determine the update processing strategy of the digital twin model of the industrial park specifically includes: When the update demand coefficient is greater than the preset demand coefficient threshold, use the preset update strategy to perform the update processing of the digital twin model; When the update demand coefficient is not greater than the preset demand coefficient threshold, determine whether the update demand coefficient is within the preset coefficient range. When it is within the preset coefficient range, determine the update processing strategy of the digital twin model of different regions according to the model update demand coefficients of different regions. When it is not within the preset coefficient range, temporarily do not perform the update processing of the digital twin model of the industrial park.

[0049] Furthermore, the preset update strategy is to perform update processing on the digital twin models of all regions in the industrial park.

[0050] It should be noted that determining the update processing strategy of the digital twin model of different regions according to the model update demand coefficients of different regions specifically includes: Regard the regions with model update demand coefficients within the preset model coefficient interval as target regions, and perform the update processing of the digital twin models of the target regions.

[0051] Optionally, the method for determining the update processing strategy of the digital twin model of the industrial park is: S41 Based on the model update demand coefficients of different regions, determine the average value of the model update demand coefficients of different regions, and use it as the basic update demand coefficient of the industrial park; S42 Based on the historical occurrence data of potential safety hazards in the industrial park on different dates, determine the historical occurrence times of potential safety hazards in the industrial park on different dates, and use the historical occurrence times of potential safety hazards in the industrial park on different dates to determine the potential safety hazard risk coefficient of the industrial park; S43 determines the update requirement coefficient of the digital twin model of the industrial park through the basic update requirement coefficient and the safety hazard risk coefficient of the industrial park, and determines the update processing strategy of the digital twin model of the industrial park by using the update requirement coefficient.

[0052] Optionally, the above step S41 includes the following content: S411 Based on the model update requirement coefficients of different regions, when it is determined that there is a region where the model update requirement coefficient is greater than the preset update requirement coefficient threshold, it proceeds to step S412. When there is no region where the model update requirement coefficient is greater than the preset update requirement coefficient threshold, it proceeds to step S413; S412 When the number of regions where the model update requirement coefficient is greater than the preset update requirement coefficient threshold is greater than the preset number of updated regions, it is determined to adopt the preset update strategy for the update processing of the digital twin model. When the number of regions where the model update requirement coefficient is greater than the preset update requirement coefficient threshold is not greater than the preset number of updated regions, it proceeds to step S413; S413 takes the average value of the model update requirement coefficients of different regions as the basic update requirement coefficient of the industrial park. When the basic update requirement coefficient of the park is greater than the preset coefficient setting value, it is determined to adopt the preset update strategy for the update processing of the digital twin model. When the basic update requirement coefficient of the park is not greater than the preset coefficient setting value, it proceeds to step S414; S414 When the basic update requirement coefficient of the park is within the preset interval, it proceeds to step S42. When the basic update requirement coefficient of the park is not within the preset interval, the update processing of the digital twin model of the industrial park is not performed temporarily.

[0053] Optionally, the above step S42 includes the following content: S421 Based on the historical occurrence data of safety hazards in the industrial park on different dates, determines the proportion of the number of dates with safety hazards and takes it as the proportion of the number of hazard dates of the industrial park. When the proportion of the number of hazard dates of the industrial park is greater than the preset hazard date proportion threshold, it is determined to adopt the preset update strategy for the update processing of the digital twin model. When the proportion of the number of hazard dates of the industrial park is not greater than the preset hazard date proportion threshold, it proceeds to step S422; S422 Based on the historical occurrence data of safety hazards in the industrial park on different dates, determines the historical occurrence times of safety hazards in the industrial park on different dates. When there is a date in the industrial park where the historical occurrence times are greater than the preset number threshold, it proceeds to step S423. When there is no date in the industrial park where the historical occurrence times are greater than the preset number threshold, it proceeds to step S424; S423 When the proportion of the number of dates with the historical occurrence times greater than the preset number threshold is greater than the preset date proportion value, it is determined to adopt the preset update strategy to update the digital twin model. When the proportion of the number of dates with the historical occurrence times greater than the preset number threshold is not greater than the preset date proportion value, it proceeds to step S424; S424 Use the historical occurrence times of the potential safety hazards in the industrial park on different dates to determine the potential safety hazard risk coefficient of the industrial park. When the potential safety hazard risk coefficient of the industrial park is greater than the preset potential hazard risk coefficient threshold, it is determined to adopt the preset update strategy to update the digital twin model. When the potential safety hazard risk coefficient of the industrial park is greater than the preset potential hazard risk coefficient threshold, it proceeds to step S43.

[0054] Embodiment 2 In a second aspect, as Figure 4 shown, the present invention provides an industrial park safety supervision system based on a digital twin model, which adopts the above-mentioned industrial park safety supervision method based on a digital twin model, and specifically includes: An accuracy evaluation module, an update requirement evaluation module, and an update processing module; Among them, the accuracy evaluation module is responsible for determining whether the recognition accuracy of the potential safety hazards of the digital twin model meets the requirements; The update requirement evaluation module is responsible for determining the model update requirement coefficients of different regions; The update processing module is responsible for determining the update processing strategy of the digital twin model of the industrial park, and using the updated digital twin model to perform safety supervision processing on the industrial park.

[0055] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0056] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0057] The above are only one or more embodiments of this specification and are not intended to limit this specification. For those skilled in the art, various changes and modifications can be made to one or more embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A method for industrial park safety supervision based on a digital twin model, characterized in that: Specifically include: Using historical identification data of safety hazards of the digital twin model of the industrial park, determining identification deviation data of safety hazards of the digital twin model on different dates, and using the identification deviation data to determine the identification deviation date of the digital twin model; Determine the deviation of the identification deviation data of the potential safety hazard between different identification deviation dates, and when it is determined based on the deviation of the identification deviation data and the identification deviation date that the identification accuracy of the potential safety hazard of the digital twin model meets the requirements, proceed to the next step; Based on the analysis results of the digital twin model, determine the matching status of the digital twin model with the models of different areas in the industrial park, and determine the model update demand coefficients of different areas in combination with the historical occurrence data and identification deviation data of safety hazards in different areas; Determine the historical occurrence data of safety hazards in the industrial park on different dates, and determine the update processing strategy of the digital twin model of the industrial park in combination with the model update demand coefficient of different regions, and use the updated digital twin model to carry out safety supervision of the industrial park.

2. The industrial park safety supervision method based on the digital twin model as claimed in claim 1 is characterized in that: The historical identification data includes the number of occurrences of potential safety hazards and identification and processing results of potential safety hazards.

3. The industrial park safety supervision method based on the digital twin model as claimed in claim 1 is characterized in that: The identification deviation data includes the number of delayed identifications and the number of unidentified times of potential safety hazards.

4. The industrial park safety supervision method based on the digital twin model as claimed in claim 1 is characterized in that: The method for determining the identification deviation date of the digital twin model is: Using the recognition deviation data, the digital twin model is used to determine the number of delayed recognitions and the number of unrecognized safety hazards on different dates; Based on the number of delayed identifications and the number of unidentified safety hazards in different areas, identifying deviation areas in the areas; Whether the date is an identification deviation date is determined according to the number of the identification deviation areas.

5. The industrial park safety supervision method based on the digital twin model as claimed in claim 4 is characterized in that: The recognition deviation area is an area where there are delayed recognition times or unrecognized times.

6. The industrial park safety supervision method based on the digital twin model as claimed in claim 4 is characterized in that: Determining whether the date is an identification deviation date according to the number of the identification deviation areas specifically includes: When the number of identified deviation areas in the date is greater than the preset number of deviation areas, the date is determined to be an identified deviation date.

7. The industrial park safety supervision method based on the digital twin model as claimed in claim 1 is characterized in that: The method for determining the update processing strategy of the digital twin model of the industrial park is: Based on the model update demand coefficients of different regions, determine the average value of the model update demand coefficients of different regions, and use it as the basic update demand coefficient of the industrial park; Based on the historical occurrence data of safety hazards of the industrial park on different dates, determine the percentage of dates on which safety hazards occur, and use it as the percentage of dates on which safety hazards occur in the industrial park; The update demand coefficient of the digital twin model of the industrial park is determined by the basic update demand coefficient of the industrial park and the proportion of the number of hidden danger dates, and the update processing strategy of the digital twin model of the industrial park is determined using the update demand coefficient.

8. The industrial park safety supervision method based on the digital twin model as claimed in claim 7 is characterized in that: The update requirement coefficient of the digital twin model of the industrial park is determined based on the product of the basic update requirement coefficient of the industrial park and the proportion of the number of hidden danger dates.

9. The industrial park safety supervision method based on the digital twin model as claimed in claim 7 is characterized in that: The update demand coefficient is used to determine the update processing strategy of the digital twin model of the industrial park, specifically including: When the update demand coefficient is greater than a preset demand coefficient threshold, the digital twin model is updated using a preset update strategy; When the update demand coefficient is not greater than the preset demand coefficient threshold, it is determined whether the update demand coefficient is within the preset coefficient range. When it is within the preset coefficient range, the update processing strategy of the digital twin model of different regions is determined according to the model update demand coefficient of different regions. When it is not within the preset coefficient range, the update processing of the digital twin model of the industrial park is temporarily not performed.

10. An industrial park safety supervision system based on a digital twin model, adopting an industrial park safety supervision method based on a digital twin model as described in any one of claims 1 to 9, characterized in that: Specifically include: Accuracy assessment module, update demand assessment module, update processing module; The accuracy evaluation module is responsible for determining whether the accuracy of identifying safety hazards of the digital twin model meets the requirements; The update demand assessment module is responsible for determining the model update demand coefficients of different regions; The update processing module is responsible for determining the update processing strategy of the digital twin model of the industrial park, and using the updated digital twin model to perform safety supervision processing on the industrial park.

Images