Fire extinguishing strategy optimization method and system based on fire-fighting wastewater pollution toxicity derivation

Abstract

The invention relates to the technical field of fire extinguishing strategy optimization, in particular to a fire extinguishing strategy optimization method and system based on fire-fighting wastewater pollution toxicity derivation, and the method comprises the steps: obtaining real fire scene video data and fire extinguishing agent use records as input sources; selecting corresponding scene data from the fire scene library based on a multi-modal feature matching algorithm; identifying a fire source position and a comburent category in a real fire video through a target detection algorithm, and deducing a wastewater toxicity result under an original fire extinguishing strategy in combination with scene library data; and based on the derived wastewater toxicity result, an optimized fire extinguishing strategy is generated by using a multi-objective optimization model, and optimization objectives include reduction of wastewater toxicity, reduction of the use amount of a fire extinguishing agent and improvement of fire extinguishing efficiency. The method can scientifically evaluate the toxicity of the wastewater, reduce the risk of environmental pollution, improve the fire extinguishing efficiency, provide accurate decision support for complex fire scenes, and have significant technical effects and social benefits.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire safety and environmental protection, and specifically relates to a fire extinguishing strategy optimization method and system based on the deduction of fire wastewater pollution toxicity. Background Art

[0002] Fire is a serious threat to human life and property. Its spread is influenced by many factors, including the size of the fire source, the combustion properties of the material, and environmental conditions. my country, as the world's second-largest developing country by population, remains prone to frequent and high-risk fires, and the impact of fire on both people and the environment cannot be ignored. In addition to the toxic and harmful gases produced by fires themselves, such as carbon monoxide, hydrogen cyanide, and acrolein, the extensive use of water and foam extinguishing agents during firefighting and rescue operations can also cause environmental pollution.

[0003] Traditional firefighting strategies, when dealing with complex fire scenarios, rely heavily on empirical judgment, which limits their ability to assess post-fire wastewater pollution. This is particularly true when fighting building fires, chemical fires (such as oil fires), and new energy fires. The wastewater produced by the interaction between different extinguishing agents and fuel types contains a variety of toxic components. These components can cause long-term contamination of surface water, groundwater, and soil, impacting ecosystems and human health.

[0004] In recent years, with the establishment of fire scene libraries and the development of toxicity testing technology, it has become possible to use historical data to record fire scale (such as heat release rate), fuel type, and the composition of fire extinguishing agent wastewater pollutants. However, how to quickly match scene library data with real fire scene videos and combine them with original fire extinguishing strategies to derive wastewater toxicity results, thereby optimizing fire extinguishing strategies to reduce environmental pollution, remains an urgent problem. Summary of the Invention

[0005] The present invention aims to provide a firefighting strategy optimization method and system based on the toxicity of firefighting wastewater. This method addresses the existing problem of wastewater contamination assessment relying on empirical judgment and lacking adaptability to complex fire scenarios. By constructing a multi-dimensional fire scenario library and integrating it with toxicity test data, this method achieves scientific and environmentally friendly optimization of firefighting strategies.

[0006] In a first aspect, the present invention provides a fire extinguishing strategy optimization method based on the derivation of fire wastewater pollution toxicity, comprising the following steps: obtaining real fire scene video data and fire extinguishing agent usage records as input sources, the real fire video data including RGB video stream and thermal imaging data, and the fire extinguishing agent usage records including the fire extinguishing agent type, dosage and spraying area distribution; selecting corresponding scene data from a fire scene library based on a multimodal feature matching algorithm, the fire scene library including three categories: building fire, chemical fire (such as oil fire) and new energy fire, each type of fire scene data records the fire scale (heat release rate), fuel type and wastewater pollutant composition and toxicity generated by different fire extinguishing agents; identifying the fire source location and combustible material category in the real fire video through a target detection algorithm, and deducing the wastewater toxicity results under the original fire extinguishing strategy in combination with the scene library data; based on the derived wastewater toxicity results, generating an optimized fire extinguishing strategy using a multi-objective optimization model, the optimization objectives including reducing wastewater toxicity, reducing the amount of fire extinguishing agent used and improving fire extinguishing efficiency.

[0007] In the process of constructing the fire scenario library, the wastewater pollution characteristics of different types of fires are modeled by combining physical and chemical models with experimental data. Specifically, for building fires, the wastewater composition of indoor decoration combustibles is recorded (optionally, the combustion products of common building materials such as wood and plastic can also be recorded); for chemical fires, the combustion products of oil fuels and their wastewater composition are recorded; for new energy fires, the combustion products of electric bicycles and electric vehicles and their wastewater composition are recorded. For each type of fire, wastewater toxicity data is obtained through luminescent bacteria acute toxicity tests or umu toxicity tests, recording the concentration and toxicity level of key pollutants in the wastewater. In order to improve the applicability of the scenario library, simulation experiments are conducted on combinations of different fire scales, fire extinguishing agent types and spraying methods to form a multi-dimensional scenario data set.

[0008] In the process of deducing wastewater toxicity, a deep learning model combined with a graph structure analysis method is used to model the migration paths of wastewater pollutants. Specifically, the main pollutants in the wastewater are regarded as nodes in the graph, and the transformation relationships and migration paths between pollutants are regarded as edges. The diffusion trend of pollutants in water bodies and soil is predicted through a graph neural network. At the same time, based on the wastewater toxicity data in the scenario library, the toxicity level is divided by the dose-response curve. If the toxicity index is less than 1.5, it is judged as low risk and conventional treatment is recommended; if the toxicity index is between 1.5 and 2.0, it is judged as medium risk and secondary degradation is required; if the toxicity index is greater than or equal to 2.0, it is judged as high risk, direct discharge is prohibited and special adsorbent treatment is recommended.

[0009] During the fire extinguishing strategy optimization process, a multi-objective optimization algorithm is used to generate a Pareto-optimal solution set. The optimization objectives include minimizing wastewater toxicity, minimizing extinguishing agent dosage, and maximizing fire extinguishing efficiency. Constraints include extinguishing agent compatibility, wastewater treatment costs, and fire extinguishing time limits. A genetic algorithm combined with a particle swarm optimization algorithm is used to find the optimal solution set. Users can then select the optimal fire extinguishing strategy from the solution set based on their specific needs. The optimized fire extinguishing strategy significantly reduces wastewater toxicity while maintaining fire extinguishing efficiency by adjusting the extinguishing agent type, dosage, and spray pattern.

[0010] In its second aspect, the present invention provides a fire extinguishing strategy optimization system based on the derivation of firefighting wastewater pollution toxicity, comprising a data acquisition module, a scene matching module, a wastewater toxicity derivation module, and a fire extinguishing strategy optimization module. The data acquisition module is used to receive real fire scene video data and fire extinguishing agent usage records, and preprocess the data, including denoising, keyframe extraction, and environmental parameter extraction; the scene matching module calls the fire scene library and dynamically selects corresponding scene data based on input features; the wastewater toxicity derivation module receives the scene data output by the scene matching module, simulates the pollutant migration path through a graph neural network, and generates a wastewater toxicity report based on toxicity test data; the fire extinguishing strategy optimization module generates fire extinguishing strategy solutions based on a multi-objective optimization algorithm and supports interactive selection.

[0011] The data flow between modules is coordinated and managed through a distributed computing platform. Uploading real-world fire videos to the platform triggers data preprocessing. This preprocessed data is then passed to the scene matching module to generate matching results. The wastewater toxicity data from these matching results is then passed to the wastewater toxicity derivation module to generate a toxicity report. Ultimately, a visual interface displays a wastewater toxicity heat map and optimized firefighting strategies. The entire system's hardware architecture comprises distributed computing servers, a laboratory automation platform, and data storage units, all connected via a high-speed network for efficient collaboration.

[0012] This invention combines multiple advanced technologies, including multimodal feature matching algorithms, graph neural networks, and multi-objective optimization algorithms, to address the limited adaptability of traditional firefighting strategy optimization methods to complex fire scenarios. It also enables rapid and accurate assessment of wastewater toxicity using toxicity test data. This system not only effectively reduces the long-term environmental pollution risk of firefighting wastewater but also provides scientific decision-making support for firefighters and rescuers, resulting in significant technical and social benefits.

[0013] In order to make the above-mentioned objects, features and advantages of the present invention more clearly understood, embodiments of the present invention are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 This is a flow chart of the method of the present invention, showing the overall steps from data collection to fire extinguishing strategy optimization, including fire video analysis, scene matching, wastewater toxicity derivation and strategy optimization.

[0016] Figure 2 This is a framework diagram for building a fire scenario library, which includes data from three categories: building fires, chemical fires, and new energy fires, as well as the modeling process that combines physical and chemical models with experimental data.

[0017] Figure 3 This is a diagram of the working principle of the wastewater toxicity derivation module, demonstrating the implementation method of pollutant migration path modeling and toxicity level classification based on graph neural network.

[0018] Figure 4 This is the flow chart of the multi-objective optimization algorithm of the fire extinguishing strategy optimization module, which describes the process of generating the Pareto optimal solution set through the genetic algorithm and particle swarm optimization algorithm.

[0019] Figure 5 This is the overall architecture diagram of the system of the present invention, showing the data flow relationship between the data acquisition module, scene matching module, wastewater toxicity derivation module and fire extinguishing strategy optimization module. DETAILED DESCRIPTION

[0020] The present invention provides a fire extinguishing strategy optimization method and system based on the derivation of firefighting wastewater pollution toxicity. Figure 1 To the attached Figure 5 The specific embodiments of the present invention are described in detail by the component numbers in the accompanying drawings. In practical applications, the method and system achieve scientific and environmentally friendly optimization of fire extinguishing strategies through the collaborative work between multiple modules.

[0021] like Figure 5As shown in the figure, the system comprises a data acquisition module, a scene matching module, a wastewater toxicity derivation module, a fire extinguishing strategy optimization module, and a distributed computing platform. These modules are connected via a high-speed network, forming a complete data flow and processing chain. The data acquisition module is responsible for receiving and preprocessing real-world video data from the fire scene and fire extinguishing agent usage records. This preprocessing process includes denoising the RGB video stream and thermal imaging data, extracting keyframes, and extracting information such as fire extinguishing agent type, dosage, and spraying area distribution from the fire extinguishing agent usage records. This preprocessed data is passed as input to the scene matching module.

[0022] The scene matching module calls the fire scene library to dynamically select data that matches the current fire scene. The construction process of the fire scene library is as follows: Figure 2 As shown in the figure, it includes three categories: building fires, chemical fires and new energy fires. The data of each type of fire scene records the scale of the fire (heat release rate), fuel type, and the composition and toxicity of wastewater pollutants produced by different fire extinguishing agents. For building fires, the scene library records the combustion products of common building materials such as wood and plastic and their wastewater components; for chemical fires, the combustion products of oil fuels and their wastewater components are recorded; for new energy fires, the combustion products of electric bicycles and electric vehicles and their wastewater components are recorded. Wastewater toxicity data is obtained through luminescent bacteria acute toxicity tests or umu toxicity tests, and the concentrations and toxicity levels of key pollutants in the wastewater are recorded. In order to improve the applicability of the scene library, simulation experiments are also conducted on combinations of different fire scales, fire extinguishing agent types and spraying methods to form a multi-dimensional scene data set.

[0023] The scene matching module uses a multimodal feature matching algorithm to select the data that best matches the current fire scene from the fire scene library. This algorithm comprehensively analyzes the RGB video stream and thermal imaging data from the fire video to identify the fire source location and burning material type. It also combines information on the type, amount, and spray distribution of extinguishing agents from the extinguishing agent usage records to determine the scene data that most closely matches the current fire scene. The matching results are then passed to the wastewater toxicity derivation module for subsequent wastewater toxicity analysis.

[0024] The working principle of the wastewater toxicity derivation module is as follows Figure 3As shown, its core is to model the migration paths of wastewater pollutants based on graph neural networks. The main pollutants in the wastewater are regarded as nodes in the graph, and the transformation relationships and migration paths between pollutants are regarded as edges. The diffusion trend of pollutants in water bodies and soil is predicted by graph neural networks. At the same time, based on the wastewater toxicity data in the scenario library, the toxicity level is divided by the dose-response curve. If the toxicity index is less than 1.5, it is judged as low risk and conventional treatment is recommended; if the toxicity index is between 1.5 and 2.0, it is judged as medium risk and secondary degradation is required; if the toxicity index is greater than or equal to 2.0, it is judged as high risk, direct discharge is prohibited and special adsorbent treatment is recommended. The wastewater toxicity report generated by the wastewater toxicity derivation module is passed to the fire extinguishing strategy optimization module.

[0025] The fire extinguishing strategy optimization module generates the Pareto optimal solution set based on the multi-objective optimization algorithm. The process is as follows: Figure 4 As shown in the figure, the optimization objective functions include minimizing wastewater toxicity, minimizing fire extinguishing agent usage, and maximizing fire extinguishing efficiency. Constraints include fire extinguishing agent compatibility, wastewater treatment costs, and fire extinguishing time limits. A genetic algorithm combined with a particle swarm optimization algorithm is used to find the optimal solution set, from which users can select the optimal fire extinguishing strategy based on their actual needs. The optimized fire extinguishing strategy significantly reduces wastewater toxicity while maintaining fire extinguishing efficiency by adjusting the type, dosage, and spraying pattern of the fire extinguishing agent. The final optimization results are displayed through a visual interface, showing a wastewater toxicity heat map and the optimized fire extinguishing strategy.

[0026] The entire system's hardware architecture comprises a distributed computing server, a laboratory automation platform, and a data storage unit. The distributed computing platform coordinates data flow management between modules. Uploading real-world fire videos to the platform triggers data preprocessing. This preprocessed data is then passed to the scene matching module to generate matching results. The wastewater toxicity data from these matching results is then passed to the wastewater toxicity derivation module to generate a toxicity report. Finally, a visual interface displays a wastewater toxicity heat map and optimized firefighting strategies. Each component is connected via a high-speed network for efficient collaboration.

[0027] In a practical application scenario, imagine an oil fire at a chemical plant. Firefighters arrive at the scene and activate the system. The data acquisition module receives on-site fire video data and extinguishing agent usage records. The video data includes an RGB video stream and thermal imaging data. The extinguishing agent usage records indicate that the extinguishing agent used was foam, 500 liters were used, and the spraying area was the primary combustion area. The data acquisition module denoises and extracts keyframes from the video data. It also extracts relevant information from the extinguishing agent usage records and passes this preprocessed data to the scene matching module. The scene matching module accesses a fire scene library and uses a multimodal feature matching algorithm to identify the fire type as a chemical fire. It then selects scene data that matches the current fire size and extinguishing agent usage. The matching results are then passed to the wastewater toxicity derivation module.

[0028] The Wastewater Toxicity Derivation Module uses a graph neural network to model the migration pathways of wastewater pollutants. It analyzes the composition and migration pathways of wastewater pollutants generated by foam fire extinguishing agents during oil fire extinguishing. Using dose-response curves to categorize toxicity, the module determined that the toxicity index of benzene series and polycyclic aromatic hydrocarbons (PAHs) in the wastewater was 1.8, placing it at a medium risk level and requiring secondary degradation treatment. The module generates a wastewater toxicity report and transmits it to the Fire Extinguishing Strategy Optimization Module.

[0029] The firefighting strategy optimization module generates a Pareto-optimal solution set based on a multi-objective optimization algorithm. The optimization objectives include reducing wastewater toxicity, reducing fire extinguishing agent usage, and improving firefighting efficiency. Using a genetic algorithm combined with a particle swarm optimization algorithm, the module found that by switching to dry powder extinguishing agent, reducing the amount to 400 liters, and optimizing the spraying pattern, the wastewater toxicity index could be reduced to 1.2 while maintaining firefighting efficiency. The optimization results are displayed in a visual interface, along with a wastewater toxicity heat map and the optimized firefighting strategy, for firefighters to follow.

[0030] Through the above steps, this system achieves scientific and environmentally friendly optimization of fire extinguishing strategies, solves the problem of insufficient adaptability of traditional fire extinguishing strategy optimization methods to complex fire scenarios, and realizes accurate evaluation of wastewater toxicity through toxicity test data.

[0031] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is supplemented below with reference to a specific application scenario.

[0032] First, during the fire scene data collection phase, after firefighters activate the system, the data acquisition module uses high-speed cameras and thermal imaging equipment to capture RGB video streams and thermal imaging data from the fire scene. Simultaneously, records of fire extinguishing agent usage are uploaded to the system in real time. The data acquisition module denoises the video stream and extracts keyframes to reduce redundant information. Furthermore, information such as the type, amount, and spraying area distribution of the fire extinguishing agent is obtained by analyzing the fire extinguishing agent usage records. This pre-processed data is then passed to the scene matching module, providing a foundation for subsequent analysis.

[0033] Then, the scene matching module calls Figure 2 The fire scene library shown in the figure contains three categories: building fires, chemical fires and new energy fires. The data for each type of fire scene are constructed based on physical and chemical models and experimental data, covering the scale of the fire (such as heat release rate), fuel type, and the composition and toxicity of wastewater pollutants produced by different fire extinguishing agents. Taking chemical fires as an example, the scene library records the concentration and toxicity level of pollutants such as benzene series and polycyclic aromatic hydrocarbons in the combustion products of oil fuels and their wastewater. The scene matching module adopts a multimodal feature matching algorithm to comprehensively analyze the RGB video stream and thermal imaging data in the fire video, identify the location of the fire source and the category of the burning material, and combine the information in the fire extinguishing agent usage record to select the data that best matches the current fire scene from the scene library. This matching process ensures the high relevance of the selected scene data and provides an accurate basis for the subsequent derivation of wastewater toxicity.

[0034] In the wastewater toxicity derivation stage, the wastewater toxicity derivation module is based on Figure 3 The working principle shown in the figure uses a graph neural network to model the migration paths of wastewater pollutants. The main pollutants in the wastewater are considered nodes, and the transformation relationships and migration paths between pollutants are considered edges. For example, when foam fire extinguishing agents are used to extinguish oil fires, the wastewater may contain benzene and polycyclic aromatic hydrocarbons. The diffusion trends of these substances in water and soil are predicted using a graph neural network. Simultaneously, based on wastewater toxicity data from a scenario library, a dose-response curve is used to categorize toxicity levels. If the toxicity index is less than 1.5, the risk is determined to be low, and conventional treatment is recommended. If the toxicity index is between 1.5 and 2.0, the risk is determined to be medium, requiring secondary degradation. If the toxicity index is greater than or equal to 2.0, the risk is determined to be high, prohibiting direct discharge and recommending specialized adsorbent treatment. The wastewater toxicity report generated by the wastewater toxicity derivation module details the pollutant composition, migration pathways, and toxicity level, providing a scientific basis for optimizing firefighting strategies.

[0035] Next, the fire extinguishing strategy optimization module is based on Figure 4The multi-objective optimization algorithm flow shown generates a Pareto-optimal solution set. The optimization objectives include minimizing wastewater toxicity, minimizing extinguishing agent usage, and maximizing fire extinguishing efficiency. Constraints include extinguishing agent compatibility, wastewater treatment costs, and fire extinguishing time limits. The optimal solution set is found by combining a genetic algorithm with a particle swarm optimization algorithm. For example, in a chemical plant oil fire, the initial firefighting strategy used foam extinguishing agent. The toxicity index of benzene and polycyclic aromatic hydrocarbons in the wastewater was 1.8, placing it at a medium risk. Optimization calculations revealed that by switching the extinguishing agent to dry powder, reducing the extinguishing agent usage to 400 liters, and optimizing the spraying pattern, the wastewater toxicity index could be reduced to 1.2 while maintaining fire extinguishing efficiency. The optimization results are displayed in a visual interface, along with a wastewater toxicity heat map and the optimized firefighting strategy, for firefighters' reference and implementation.

[0036] Finally, the hardware architecture of the entire system is as follows Figure 5 As shown in the figure, each module achieves efficient collaboration through a distributed computing platform. The distributed computing platform coordinates data flow management, ensuring smooth data transmission between the data acquisition module, scene matching module, wastewater toxicity derivation module, and fire extinguishing strategy optimization module. After a real fire video is uploaded to the platform, data preprocessing is triggered. The preprocessed data is passed to the scene matching module to generate a matching result. The wastewater toxicity data in the matching result is further passed to the wastewater toxicity derivation module to generate a toxicity report. Finally, a visual interface displays a wastewater toxicity heat map and the optimized fire extinguishing strategy plan. Each component achieves efficient collaboration through a high-speed network connection, ensuring the real-time and reliable operation of the system.

[0037] Through the above steps, this system achieves scientific and environmentally friendly optimization of fire-fighting strategies, solves the problem of insufficient adaptability of traditional fire-fighting strategy optimization methods to complex fire scenarios, and realizes accurate evaluation of wastewater toxicity through toxicity test data, providing strong support for firefighting and rescue.

[0038] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A fire extinguishing strategy optimization method based on the derivation of firefighting wastewater pollution toxicity, characterized in that: include: Obtaining real fire scene video data and fire extinguishing agent usage records as input sources, the real fire scene video data including RGB video stream and thermal imaging data, and the fire extinguishing agent usage records including fire extinguishing agent type, amount, and spraying area distribution; Based on a multimodal feature matching algorithm, corresponding scene data is selected from a fire scene library. The fire scene library includes three categories: building fires, chemical fires, and new energy fires. Each type of fire scene data records the fire scale, fuel type, and the composition and toxicity of wastewater pollutants generated by different fire extinguishing agents. The target detection algorithm is used to identify the fire source location and burning material category in real fire videos, and the wastewater toxicity results under the original fire extinguishing strategy are derived by combining scene library data; Based on the derived wastewater toxicity results, a multi-objective optimization model was used to generate an optimized fire extinguishing strategy. The optimization objectives included reducing wastewater toxicity, reducing the amount of fire extinguishing agent used, and improving fire extinguishing efficiency.

2. The method according to claim 1, characterized in that The fire scenario library is constructed by combining physical and chemical models with experimental data. For building fires, it records the wastewater composition of combustible materials in indoor decoration; for chemical fires, it records the combustion products of oil fuels and their wastewater composition; for new energy fires, it records the combustion products of electric bicycles and electric vehicles and their wastewater composition.

3. The method according to claim 2, characterized in that Wastewater toxicity data is obtained through luminescent bacteria acute toxicity test or umu toxicity test, and the concentration and toxicity level of key pollutants in the wastewater are recorded.

4. The method according to claim 1, wherein The wastewater toxicity derivation process uses graph neural networks to model the migration paths of wastewater pollutants, treating the main pollutants in the wastewater as nodes, and the transformation relationships and migration paths between pollutants as edges, to predict the diffusion trends of pollutants in water bodies and soil.

5. The method according to claim 4, characterized in that The wastewater toxicity level is divided based on the dose-response curve. If the toxicity index is less than 1.5, it is judged as low risk; if the toxicity index is between 1.5 and 2.0, it is judged as medium risk; if the toxicity index is greater than or equal to 2.0, it is judged as high risk.

6. The method according to claim 1, characterized in that The objective functions of the multi-objective optimization model include minimizing wastewater toxicity, minimizing fire extinguishing agent usage, and maximizing fire extinguishing efficiency. The constraints include fire extinguishing agent compatibility, wastewater treatment cost, and fire extinguishing time limit.

7. The method according to claim 6, characterized in that The Pareto optimal solution set of the multi-objective optimization model is solved by combining genetic algorithm with particle swarm optimization algorithm.

8. A fire extinguishing strategy optimization system based on the derivation of fire wastewater pollution toxicity, characterized by: It includes data acquisition module, scene matching module, wastewater toxicity derivation module and fire extinguishing strategy optimization module; The data acquisition module is used to receive real fire scene video data and fire extinguishing agent usage records, and pre-process the data, including denoising, key frame extraction and environmental parameter extraction; The scene matching module calls the fire scene library and dynamically selects corresponding scene data based on input features; The wastewater toxicity derivation module receives the scene data output by the scene matching module, simulates the pollutant migration path through the graph neural network, and generates a wastewater toxicity report in combination with the toxicity test data; The fire extinguishing strategy optimization module generates fire extinguishing strategy solutions based on a multi-objective optimization algorithm and supports interactive selection.

9. The system according to claim 8, characterized in that The hardware architecture of the system includes a distributed computing server, a laboratory automation platform and a data storage unit, and each component is connected through a high-speed network to achieve efficient collaborative work.

10. The system according to claim 8, wherein: The wastewater toxicity derivation module divides the wastewater toxicity level by a dose-response curve, and generates a wastewater toxicity heat map and an optimized fire extinguishing strategy scheme according to the toxicity index.

Images