Intelligent simulation optimization method based on digital twinning
Through the use of digital twin models in the industrial park for intelligent simulation optimization, the problem of insufficient fire risk assessment and insufficient fire facilities for fire risk, and achieved more efficient fire safety management and fire control.
Patent Information
- Application Number
- CN202411440267.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2025-01-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the fire protection management of industrial parks, it is difficult for existing technology to conduct scientific fire risk assessment and prediction, resulting in insufficient optimization of fire protection facilities and affecting safety.
Adopt intelligent simulation optimization methods based on digital twins, establish digital twin models by dividing industrial parks into regions, collect image data for risk combustible point analysis and fire spread simulation, evaluate fire safety scores, and optimize fire protection facilities based on fire safety thresholds. Put it with materials.
Effectively predict the occurrence and expansion of fires, optimize the layout of fire protection facilities, reduce the probability of fire in fire, improve the efficiency of fire extinguishing, ensure fire safety standards, and quickly respond and control the fire during the fire.
Smart Images
Figure CN119378869A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent simulation optimization, and in particular to an intelligent simulation optimization method based on digital twins. Background Art
[0002] In the fire protection management of industrial parks, fires are often not controlled in time, or fire protection facilities and resources are insufficient to deal with fires. These problems not only affect the safety of the park, but may also cause serious casualties and property losses;
[0003] At present, in the fire protection management of industrial parks, fire protection facilities are generally equipped according to the floor area of the factory. However, different users have different production environments in the factory when using the factory. Most safety assessments rely on the experience of the inspectors and lack scientific data support and digital tools. This leads to insufficient ability to accurately assess and predict fire risks, and it is difficult to effectively optimize fire protection facilities. Therefore, an intelligent simulation optimization method based on digital twins is proposed. Summary of the invention
[0004] The purpose of the present invention is to provide an intelligent simulation optimization method based on digital twins to solve the problems raised in the above background technology.
[0005] To achieve the above purpose, an intelligent simulation optimization method based on digital twin is provided, which includes the following steps:
[0006] S1. Divide the industrial park into zones based on plant construction and fire protection facilities;
[0007] S2. Establish a digital twin model for each area, and input and collect image data in each plant into the digital twin model for model update;
[0008] S3. Analyze the risk flammable points of the area based on the image data of the factory building, obtain the risk flammable points in each area, and then input the risk flammable points into the digital twin model to simulate the spread of fire, and obtain the fire risk score of the area based on the simulated fire spread;
[0009] S4. Obtain the firefighters available in each area, input the firefighters into the digital twin model for fire rescue simulation, and obtain the fire safety score of the area based on the fire rescue simulation;
[0010] S5. Set a fire safety threshold, compare the fire safety threshold with the fire safety score, and when the fire safety threshold score is higher than the fire safety score, collect the fire resources that can be added from the park management end to generate an optimization plan, so as to obtain the fire optimization plan with the highest fire safety score;
[0011] S6. Compare the fire optimization plan with the fire safety threshold. When the fire safety threshold is higher than the fire optimization plan, optimize the material placement analysis in the digital twin model to obtain the factory optimization plan.
[0012] As a further improvement of the present technical solution, the S1 establishes a data transmission channel with the park management end, thereby collecting architectural drawings of the industrial park from the park management end, and understanding the factory building construction and fire protection facilities through the architectural drawings.
[0013] As a further improvement of the present technical solution, S1 divides the industrial park into grid areas according to the factory building construction, and then classifies the fire-fighting facilities that can provide fire protection for the factory buildings into the same area. When the fire-fighting facilities are located between multiple factory buildings, the fire-fighting facilities can belong to multiple areas.
[0014] As a further improvement of the present technical solution, the S2 accesses the camera installed in each factory building through the park management terminal, and collects the image data in the factory building in real time through the camera.
[0015] As a further improvement of this technical solution, the steps of S3 are as follows:
[0016] S3.1. Analyze the image data of the factory to obtain the type of goods and the working environment in the factory, analyze the risk ignitable points based on the type of goods and the working environment, and obtain the risk ignitable points in the factory area;
[0017] S3.2. Input the risky flammable points into the digital twin model of the same area for fire spread simulation. Simulate the fire at each risky flammable point to obtain the fire spread speed of each risky flammable point. Then, assign a fire risk score to each risky flammable point based on the fire spread speed. Then, use the highest fire risk score as the fire risk score for the area.
[0018] As a further improvement of the technical solution, the S4 obtains the number of security guards in the industrial park through the park management terminal, and extracts the number of workers from the image data of the factory building, and uses the number of workers combined with the number of security guards as the firefighters that can participate in the area.
[0019] As a further improvement of the technical solution, the step of S4 is as follows:
[0020] S4.1. Input the firefighters who can participate into the digital twin model of the same area. The fire situation of the digital twin model is the fire situation with the highest fire risk score in S3.2. Then simulate the process of firefighters using firefighting facilities in the area to extinguish the fire.
[0021] S4.2. The fire safety score of the area is determined based on the efficiency of suppressing the spread of fire.
[0022] As a further improvement of the technical solution, the step of S5 is as follows:
[0023] S5.1. Set fire safety thresholds according to the requirements of the park management end;
[0024] S5.2. Compare the fire safety threshold and the fire safety score. When the fire safety threshold score is higher than the fire safety score, collect the additional fire resources from the park management end, and optimize the fire facilities based on the existing fire facilities, obtain the fire optimization plan for adjusting multiple fire facilities, and then substitute the fire optimization plan into the digital twin model for simulation, and screen out the fire optimization plan with the highest fire safety score.
[0025] S5.3. When the fire safety threshold score is lower than the fire safety score, no fire optimization plan will be generated.
[0026] As a further improvement of the technical solution, the step of S6 is as follows:
[0027] S6.1. Compare the fire optimization plan with the highest fire safety score obtained in S5.2 with the fire safety threshold;
[0028] S6.2. When the fire safety threshold is higher than the fire optimization plan, the material placement is optimized and analyzed in the digital twin model to reduce the flammable points in the factory and control the speed of fire spread, thereby generating a factory optimization plan. The plan is screened among the factory optimization plans to obtain the factory optimization plan with the least adjustment workload and send it to the park management end.
[0029] Compared with the prior art, the present invention has the following beneficial effects:
[0030] In this intelligent simulation optimization method based on digital twins, through the simulation analysis of the digital twin model, it is possible to effectively predict the occurrence and spread of fires, optimize the placement of materials and the layout of fire-fighting facilities, thereby reducing the probability of fires and improving fire-fighting efficiency. By comparing fire safety thresholds and optimization plans, fire-fighting facilities and material placement are optimized to minimize the adjustment workload while ensuring that the fire safety standards set by the park management are met or exceeded. This can effectively save resources and improve efficiency during implementation. The optimized fire safety plan can quickly respond to and control the fire when it occurs, protect personnel and property safety, and reduce the risk of business interruption and property loss. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 It is the overall flow chart of the present invention;
[0032] Figure 2 A flowchart of the present invention using the highest fire risk score as the fire risk score of the area;
[0033] Figure 3 A flowchart of the present invention using the efficiency of suppressing the spread of fire as the fire safety score of the area;
[0034] Figure 4 A flowchart of a fire optimization solution for obtaining the highest fire safety score of the present invention;
[0035] Figure 5 A flowchart of the present invention for obtaining a plant optimization solution with the least adjustment workload and sending it to a park management terminal. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0037] See also Figure 1-Figure 5 As shown, the purpose of this embodiment is to provide an intelligent simulation optimization method based on digital twins, comprising the following steps:
[0038] S1. Divide the industrial park into zones based on plant construction and fire protection facilities;
[0039] The S1 establishes a data transmission channel with the park management end, thereby collecting the architectural drawings of the industrial park from the park management end, and understanding the factory building and fire protection facilities through the architectural drawings. The working steps are as follows:
[0040] Technology selection: Choose Wi-Fi, Bluetooth, LoRa, etc. to establish a data transmission channel between the park management end and the industrial park;
[0041] Data format: Understand the data format of architectural drawings, such as CAD files, PDF, etc., for subsequent processing and analysis;
[0042] Data analysis: Analyze the acquired architectural drawings and extract useful information, such as building structure, fire protection facility layout, etc.;
[0043] Data storage: Store the parsed data in a database or cloud platform to facilitate subsequent query and analysis;
[0044] Architectural drawing analysis: Use architectural drawing information to plan and optimize plant construction design;
[0045] Fire-fighting facility extraction: Analyze the plant construction plan to obtain the layout of fire-fighting facilities.
[0046] S1 divides the industrial park into grid areas according to the factory building construction, and then classifies the fire protection facilities that can provide fire protection for the factory building into the same area. When the fire protection facilities are located between multiple factory buildings, the fire protection facilities can belong to multiple areas. The working steps are as follows:
[0047] Plan the grid size: Design the grid according to the floor space of the plant;
[0048] Grid allocation: Assign grid cells to each plant building and its surrounding area, ensuring that each plant building is contained in one or more grid cells;
[0049] Define fire protection facilities: determine which facilities are included, such as fire pools, fire hydrants, and fire extinguishers;
[0050] Firefighting facility attribution rules: According to the location and impact range of specific facilities, formulate classification rules. For example, a firefighting pool may cover multiple factory buildings and therefore belong to multiple grid areas at the same time.
[0051] S2. Establish a digital twin model for each area, and input and collect image data in each plant into the digital twin model for model update; the working steps are as follows:
[0052] Data collection and modeling: First, it is necessary to collect and organize relevant data in each plant, including image data, plant construction plan, and fire protection facility layout. These data will serve as input for the digital twin model;
[0053] Model selection and establishment: Select a suitable model architecture to build a digital twin model, usually using machine learning modeling methods, which can reflect the actual operation and environmental conditions in the factory;
[0054] Camera data collection: Cameras installed in the factory capture scenes in real time and transmit image data to the park management end, which then uploads it to the digital twin model;
[0055] Continuous optimization: Continuously collect new data and adjust model parameters or architecture based on actual conditions to optimize the performance and accuracy of the digital twin model.
[0056] The S2 accesses the camera installed in each factory building through the park management terminal, and collects the image data in the factory building in real time through the camera. The working steps are as follows:
[0057] Camera installation and network connection: Install cameras in each factory building. The cameras should have network connection function, usually connected to the park management end through LAN (local area network) or wireless network, to ensure that the camera position can fully cover the area in the factory building;
[0058] Campus management end configuration: Set up a unified management platform or system at the campus management end to receive and process image data transmitted by all cameras, ensuring that the management end has sufficient computing power and storage space to process and store large amounts of image data;
[0059] S3. Analyze the risk flammable points of the area based on the image data of the factory building, obtain the risk flammable points in each area, and then input the risk flammable points into the digital twin model to simulate the spread of fire, and obtain the fire risk score of the area based on the simulated fire spread;
[0060] The steps of S3 are as follows:
[0061] S3.1. Analyze the image data of the factory to obtain the type of goods and working environment in the factory. Combine the type of goods with the working environment to perform risk flammable point analysis to obtain the risk flammable points in the factory area. The working steps are as follows:
[0062] Image preprocessing: Preprocess the image, including denoising, enhancement, image segmentation, etc., to extract useful information and features;
[0063] Object detection and classification: Use object detection algorithms to identify different types of goods in the factory;
[0064] Classifier model: You can use pre-trained deep learning models, such as ResNet, MobileNet, etc., to classify detected objects;
[0065] Environmental perception: extracting environmental features from images, such as light intensity, air flow, etc.
[0066] Risk factor assessment: Risk assessment is conducted based on the cargo type and working environment data. The formula is as follows:
[0067] FP=(T c +T a )×F b
[0068] Among them, FP is the flash point of the substance, T c is the ambient temperature, that is, the temperature of the substance, T a The temperature of the air, usually 20°C, is used to represent standard ambient conditions. b This is a coefficient or correction factor of material properties, which is used to reflect the influence of the material's own properties on the flash point;
[0069] T c +T a It represents the sum of ambient temperature and standard temperature. The flash point of a substance will decrease as the ambient temperature increases, because high temperature will increase the volatility of the substance. bIt is a multiplication factor used to adjust according to the physical properties of the specific substance. Different substances have different F b Values reflect their sensitivity to changes in ambient temperature and their own volatility.
[0070] S3.2. Input the risky flammable points into the digital twin model of the same area to simulate the fire spread. Simulate the fire at each risky flammable point to obtain the fire spread speed of each risky flammable point. Then, score the fire risk of each risky flammable point according to the fire spread speed. Then, use the highest fire risk score as the fire risk score of the area. The working steps are as follows:
[0071] Fire spread simulation: Fire spread simulation is performed for each risky ignitable point to simulate the propagation path and speed of flames and heat after a fire breaks out. Digital twin models are usually based on physical principles and historical data to simulate the spread of fire, taking into account factors such as wind speed, vegetation type, and terrain;
[0072] Fire risk score: Based on the simulation results, the fire spread rate of each risky ignitable point is calculated and converted into a fire risk score. The evaluation factors include:
[0073] the speed and path of fire spread;
[0074] Types and storage conditions of combustible materials;
[0075] The flammability of the surrounding environment and obstacles to spread;
[0076] Determine the fire risk score for the area: After scoring all risky ignitable points, select the highest score as the fire risk score for the area.
[0077] S4. Obtain the firefighters available in each area, input the firefighters into the digital twin model for fire rescue simulation, and obtain the fire safety score of the area based on the fire rescue simulation;
[0078] The S4 obtains the number of security guards in the industrial park through the park management terminal, and uses image processing or computer vision technology to extract the number of workers from the image data of the factory building, and combines the number of workers with the number of security guards as the firefighters available in the area;
[0079] The steps of S4 are as follows:
[0080] S4.1. Input the firefighters who can participate into the digital twin model of the same area. The fire situation of the digital twin model is the fire situation with the highest fire risk score in S3.2. Then simulate the process of firefighters using firefighting facilities in the area to extinguish the fire.
[0081] S4.2. The fire safety score of the area is based on the efficiency of suppressing the spread of fire. The working steps are as follows:
[0082] Simulate the firefighting process: In the digital twin model, simulate the process of firefighters using firefighting facilities in the area to extinguish fires, including the use of firefighting equipment, personnel movement path planning, water supply, etc.
[0083] Evaluation of fire safety: Based on the simulation results, the firefighting efficiency of firefighters and their control effect on the spread of fire can be evaluated through indicators such as fire extinguishing time, fire control range, and personnel safety. The formula is as follows:
[0084]
[0085] Among them, T extinguish It is the time required to extinguish the fire. The shorter this time is, the faster the firefighters can control the fire. Therefore, the safety score S is fire This will increase the countdown of time. A measure of firefighting efficiency, i.e. the more efficient the firefighting action, the higher the score;
[0086] Area controlled is the scope of the fire that was successfully controlled. This value is usually a ratio or a percentage relative to the entire affected area. The larger the controlled scope, the more effectively the firefighters prevented the spread of the fire, thereby improving the safety score.
[0087] Safetyfactor is a safety factor that takes into account the safety factors in firefighting operations. This can include factors such as the safety of firefighters, the safety of equipment and materials used, etc. A higher safety factor value means that the firefighting operation effectively controls the fire while ensuring the safety of personnel, thus also increasing the safety score;
[0088] S fire It is a fire safety score, which is calculated based on the above three factors. This score can be used as a comprehensive indicator to measure the effectiveness of firefighting actions. It can be used to compare the effects of different firefighting actions or to evaluate the fire safety of different areas or buildings.
[0089] S5. Set a fire safety threshold, compare the fire safety threshold with the fire safety score, and when the fire safety threshold score is higher than the fire safety score, collect the fire resources that can be added from the park management end to generate an optimization plan, so as to obtain the fire optimization plan with the highest fire safety score;
[0090] The steps of S5 are as follows:
[0091] S5.1. Set fire safety thresholds according to the requirements of the park management end;
[0092] S5.2. Compare the fire safety threshold and the fire safety score. When the fire safety threshold score is higher than the fire safety score, collect the fire resources that can be added from the park management end, and optimize the fire facilities based on the existing fire facilities to obtain the fire optimization plan for adjusting multiple fire facilities. Then substitute the fire optimization plan into the digital twin model for simulation, and screen out the fire optimization plan with the highest fire safety score. The working steps are as follows:
[0093] Setting fire safety thresholds: The campus management defines fire safety thresholds based on the specific needs, regulatory requirements, or safety standards of the campus;
[0094] Calculate Fire Safety Score: Calculate the fire safety score S using the given formula fire , this score is a comprehensive indicator based on the speed, control range and safety factors of firefighting actions;
[0095] Compare Fire Safety Threshold and Fire Safety Score: Compare the Fire Safety Threshold score to the calculated Fire Safety Score.
[0096] Collect firefighting resources: If the fire safety threshold score is higher than the fire safety score, it means that the current firefighting resources may not be sufficient to meet the safety standards. In this case, the report is sent to the park management end, and the demand for additional firefighting resources is collected;
[0097] Optimization of fire-fighting facilities: Based on the existing fire-fighting facilities and resources, formulate optimization plans for multiple fire-fighting facilities adjustments, including adding fire-fighting equipment, improving fire-fighting passages, and upgrading automatic fire alarm systems;
[0098] Digital twin model simulation: The optimization schemes for adjusting various fire-fighting facilities are input into the digital twin model for simulation. The digital twin model simulates the fire spread and fire-fighting action effects under different fire-fighting scenarios.
[0099] Evaluate fire optimization solutions: Evaluate the effectiveness and impact of each optimization solution within the digital twin model, especially its effect on improving fire safety scores;
[0100] Screening the best fire optimization plan: Based on the simulation results and fire safety scores, screen out the fire optimization plan that can achieve the highest fire safety score.
[0101] S5.3. When the fire safety threshold score is lower than the fire safety score, no fire optimization plan will be generated.
[0102] S6. Compare the fire optimization plan with the fire safety threshold. When the fire safety threshold is higher than the fire optimization plan, optimize the material placement analysis in the digital twin model to obtain the factory optimization plan.
[0103] The steps of S6 are as follows:
[0104] S6.1. Compare the fire optimization plan with the highest fire safety score obtained in S5.2 with the fire safety threshold;
[0105] S6.2. When the fire safety threshold is higher than the fire optimization plan, optimize the material placement in the digital twin model, reduce the flammable point in the plant, control the speed of fire spread, and generate a plant optimization plan. Then, select the plant optimization plan with the least adjustment workload and send it to the park management end. The working steps are as follows:
[0106] Compare fire safety thresholds and fire optimization plans: Compare the fire safety thresholds set by the park with the fire optimization plans evaluated through the digital twin model;
[0107] Digital twin model optimization analysis: In the digital twin model, the placement of materials in the factory is optimized and analyzed, with the goal of reducing the distribution of flammable points and controlling the speed of fire spread, thereby reducing the risk of fire outbreak and spread;
[0108] Generate factory optimization plan: Based on the results of the optimization analysis, generate multiple possible factory fire safety optimization plans. These plans may include rearranging materials, adding fire isolation facilities, improving fire passages, etc.;
[0109] Screening out the plan with the least adjustment workload: In the generated plant optimization plan, by comparing the workload and cost, screen out the optimization plan with the least adjustment workload but can reach the fire safety threshold;
[0110] Send to the park management end: Send the selected best factory optimization plan to the park management end for approval and implementation.
[0111] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. An intelligent simulation optimization method based on digital twins, characterized by: The following steps are involved: S1. Divide the industrial park into zones based on plant construction and fire protection facilities; S2. Establish a digital twin model for each area, and input and collect image data in each plant into the digital twin model for model update; S3. Analyze the risk flammable points of the area based on the image data of the factory building, obtain the risk flammable points in each area, and then input the risk flammable points into the digital twin model to simulate the spread of fire, and obtain the fire risk score of the area based on the simulated fire spread; S4. Obtain the firefighters available in each area, input the firefighters into the digital twin model for fire rescue simulation, and obtain the fire safety score of the area based on the fire rescue simulation; S5. Set a fire safety threshold, compare the fire safety threshold with the fire safety score, and when the fire safety threshold score is higher than the fire safety score, collect the fire resources that can be added from the park management end to generate an optimization plan, so as to obtain the fire optimization plan with the highest fire safety score; S6. Compare the fire optimization plan with the fire safety threshold. When the fire safety threshold is higher than the fire optimization plan, optimize the material placement analysis in the digital twin model to obtain the factory optimization plan.
2. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The S1 establishes a data transmission channel with the park management end, thereby collecting architectural drawings of the industrial park from the park management end, and understanding the factory building construction and fire protection facilities through the architectural drawings.
3. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The S1 divides the industrial park into grid areas according to the factory building construction, and then classifies the fire-fighting facilities that can provide fire protection for the factory buildings into the same area. When the fire-fighting facilities are located between multiple factory buildings, the fire-fighting facilities can belong to multiple areas.
4. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The S2 accesses the cameras installed in each factory building through the park management terminal, and collects image data in the factory building in real time through the cameras.
5. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The steps of S3 are as follows: S3.
1. Analyze the image data of the factory to obtain the type of goods and the working environment in the factory, analyze the risk ignitable points based on the type of goods and the working environment, and obtain the risk ignitable points in the factory area; S3.
2. Input the risky flammable points into the digital twin model of the same area for fire spread simulation. Simulate the fire at each risky flammable point to obtain the fire spread speed of each risky flammable point. Then, assign a fire risk score to each risky flammable point based on the fire spread speed. Then, use the highest fire risk score as the fire risk score for the area.
6. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The S4 obtains the number of security guards in the industrial park through the park management terminal, and extracts the number of workers from the image data of the factory building, and uses the number of workers and the number of security guards as the firefighters available in the area.
7. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The steps of S4 are as follows: S4.
1. Input the firefighters who can participate into the digital twin model of the same area. The fire situation of the digital twin model is the fire situation with the highest fire risk score in S3.
2. Then simulate the process of firefighters using firefighting facilities in the area to extinguish the fire. S4.
2. The fire safety score of the area is determined based on the efficiency of suppressing the spread of fire.
8. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The steps of S5 are as follows: S5.
1. Set fire safety thresholds according to the requirements of the park management end; S5.
2. Compare the fire safety threshold and the fire safety score. When the fire safety threshold score is higher than the fire safety score, collect the additional fire resources from the park management end, and optimize the fire facilities based on the existing fire facilities, obtain the fire optimization plan for adjusting multiple fire facilities, and then substitute the fire optimization plan into the digital twin model for simulation, and screen out the fire optimization plan with the highest fire safety score. S5.
3. When the fire safety threshold score is lower than the fire safety score, no fire optimization plan will be generated.
9. The intelligent simulation optimization method based on digital twin according to claim 1 is characterized in that: The steps of S6 are as follows: S6.
1. Compare the fire optimization plan with the highest fire safety score obtained in S5.2 with the fire safety threshold; S6.
2. When the fire safety threshold is higher than the fire optimization plan, the material placement is optimized and analyzed in the digital twin model to reduce the flammable points in the factory and control the speed of fire spread, thereby generating a factory optimization plan. The plan is screened among the factory optimization plans to obtain the factory optimization plan with the least adjustment workload and send it to the park management end.