Fire pump station water supply regulation control system and method based on artificial intelligence

Abstract

The invention discloses a fire pump station water supply regulation control system and method based on artificial intelligence, and the system comprises an obtaining module which is used for obtaining the real-time water supply parameters and environment state information of a fire pump station; the strategy generation module is used for generating an optimal water supply adjustment strategy based on a pre-trained artificial intelligence model according to the real-time water supply parameters and the environment state information; and the control module is used for executing the optimal water supply adjustment strategy to realize intelligent adjustment control of water supply of the fire pump station. The operation efficiency of the fire pump station can be greatly improved, the operation cost is reduced, the reliability and safety of the fire pump station are ensured, and therefore a more stable and efficient guarantee is provided for a fire fighting system.

Description

Technical Field

[0001] The present invention relates to the technical field of water supply regulation and control, and particularly to a water supply regulation and control system and method for a fire pump station based on artificial intelligence. Background Art

[0002] With the continuous expansion of the urban scale and the continuous growth of the number of high-rise buildings, fire safety has become increasingly prominent in the urban public safety system. As an important guarantee means to cope with emergencies such as fires, fire pump stations play an indispensable role in the urban fire water supply system. However, the existing fire pump station water supply regulation technologies generally have the following deficiencies:

[0003] The water supply regulation of most fire pump stations still relies on fixed threshold control or manual intervention. Due to the extremely sudden and unpredictable nature of fires, fixed threshold control often cannot dynamically adapt to the rapidly changing fire situation and water supply demand. For example, in the case of a sudden intensification of the fire or a large amount of water consumption in a short time, traditional control methods are difficult to adjust the start and stop of pump groups and valve openings in a timely manner, resulting in insufficient water supply or excessive water supply fluctuations, affecting the fire extinguishing efficiency and safety. The information perception ability of traditional systems for the states of fire pump stations and the surrounding environment is relatively limited. Many fire pump stations only have the monitoring of a small number of parameters such as their own pressure and flow rate, lacking the real-time analysis and comprehensive judgment ability for important information such as external meteorological conditions, the fire situation of buildings, and the pressure distribution of water supply pipelines. In addition, the collection and feedback of the operating states of pump groups are not perfect, resulting in the disconnection between control decisions and actual operating conditions, and it is difficult to effectively balance operating energy consumption and equipment wear. Again, the existing fire pump station water supply regulation system lacks the ability to predict future demand changes. The water demand at the fire site has obvious change uncertainties. Simply relying on the current working conditions for simple passive regulation often makes it difficult to balance fire protection needs and system load. If there is a lack of accurate prediction of water supply demand, the system is prone to situations such as blind water supply allocation, resource waste, or inability to quickly respond to sudden changes in the fire situation. Finally, in the face of sudden situations at the fire site or system abnormalities, traditional systems lack fast and effective emergency handling capabilities. Once equipment failures or drastic changes in the fire situation occur, multiple instructions and dispatching by manual are required, making it difficult to meet the water supply demand in a timely manner and there are potential safety hazards.

[0004] Therefore, there is an urgent need for a water supply regulation and control system and method for a fire pump station based on artificial intelligence. Summary of the Invention

[0005] The present invention provides a water supply regulation and control system and method for a fire pump station based on artificial intelligence to solve the above problems existing in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] Artificial intelligence-based water supply regulation control system for fire pump stations, including:

[0008] An acquisition module, used to acquire real-time water supply parameters and environmental status information of the fire pump station;

[0009] A strategy generation module, used to generate an optimal water supply regulation strategy based on a pre-trained artificial intelligence model according to the real-time water supply parameters and environmental status information;

[0010] A control module, used to execute the optimal water supply regulation strategy to achieve intelligent regulation control of the water supply of the fire pump station.

[0011] Among them, the acquisition module includes:

[0012] A data acquisition sub-module, used to collect real-time pressure, flow rate, temperature, water level and operating status data of each pump group of the fire pump station;

[0013] An environmental monitoring sub-module, used to monitor the meteorological conditions, building fire conditions and water supply network pressure distribution around the fire pump station.

[0014] Among them, the strategy generation module includes:

[0015] A model construction sub-module, used to perform pre-training based on the historical operating water supply parameters of the fire pump station and the corresponding environmental status information, and construct an artificial intelligence model;

[0016] A scenario recognition sub-module, used to analyze the acquired real-time water supply parameters and environmental status information based on the pre-trained artificial intelligence model, and identify the current water supply scenario type;

[0017] A demand prediction sub-module, used to predict the change trend of water supply demand within a preset future time period according to the identified scenario type and combined with historical data;

[0018] A strategy reasoning sub-module, used to generate multiple groups of candidate water supply regulation strategies by comprehensively considering factors such as water supply demand, system energy consumption and equipment life;

[0019] A strategy evaluation sub-module, used to evaluate multiple groups of candidate strategies and select the strategy with the highest comprehensive score as the optimal water supply regulation strategy.

[0020] Among them, the control module includes:

[0021] A strategy decomposition sub-module, used to analyze the complexity of the optimal water supply regulation strategy. When the complexity value is greater than the execution complexity threshold, the strategy is decomposed into multiple continuously executed sub-strategies;

[0022] An instruction conversion sub-module, used to convert the water supply regulation strategy or sub-strategy into specific control instructions for pump group start / stop, variable frequency speed regulation, and valve opening;

[0023] An execution monitoring sub-module, which is used to monitor the execution effect of control instructions in real time and record the changes in key water supply parameters;

[0024] An emergency handling sub-module, which is used to quickly start the corresponding emergency water supply adjustment plan based on a preset emergency plan library when a sudden change in the water supply demand at the fire scene or system abnormality is detected.

[0025] Among them, the model construction sub-module includes:

[0026] An acquisition unit, which is used to acquire the historical operation water supply parameters of the fire pump station, the corresponding environmental status information, and the corresponding water supply efficiency evaluation data;

[0027] A model construction unit, which is used to construct a multi-scenario water supply demand model based on the historical operation water supply parameters and the corresponding environmental status information;

[0028] A sample acquisition unit, which is used to acquire multiple groups of training samples. The training samples include water supply demand data under different fire types, different building structures, and different environmental conditions;

[0029] An evaluation unit, which is used to evaluate each training sample based on the multi-scenario water supply demand model to obtain the water supply efficiency score of each training sample;

[0030] A training unit, which is used to train an artificial intelligence model based on the training samples whose water supply efficiency scores are greater than or equal to a preset efficiency threshold.

[0031] Among them, the model construction unit includes:

[0032] A data classification sub-unit, which is used to classify and process the historical operation water supply parameters and the corresponding environmental status information to obtain a multi-dimensional feature parameter set;

[0033] A rule determination sub-unit, which is used to determine the water supply rule knowledge corresponding to the multi-dimensional feature parameter set from the water supply rule knowledge base; the water supply rule knowledge includes: multiple groups of scene feature recognition rules and water supply demand calculation rules that correspond one by one;

[0034] A scene recognition sub-unit, which is used to sequentially traverse each scene feature recognition rule, and based on the traversed scene feature recognition rule, identify a specific scene type from the historical operation data;

[0035] A sub-model generation sub-unit, which is used to generate a scene water supply demand sub-model according to the specific scene type based on the water supply demand calculation rule corresponding to the traversed scene feature recognition rule;

[0036] A model integration sub-unit, which is used to integrate the scene water supply demand sub-models generated each time the scene feature recognition rule is traversed after traversing all the scene feature recognition rules to obtain a multi-scenario water supply demand model.

[0037] Among them, the execution monitoring sub-module includes:

[0038] A monitoring unit for continuously monitoring the operating status of the water supply system;

[0039] An analysis unit for, if the monitored data shows that the water supply pressure fluctuation exceeds the stable range for N consecutive times, and the patterns of each fluctuation conform to a predefined standard fluctuation relationship, and the sum of the association strengths of the conforming standard fluctuation relationships is greater than or equal to the warning threshold, extracting the characteristic of the pressure data of each fluctuation to obtain a fluctuation characteristic set; the warning threshold is the product of N and the risk coefficient;

[0040] A matching unit for matching the system risk factors corresponding to the fluctuation characteristic set from the fault prediction knowledge base;

[0041] A prediction unit for predicting the operation trend of the water supply system within a preset first time period in the future based on the system risk factors;

[0042] An adjustment unit for adjusting the water supply parameters in advance based on the prediction result to prevent system failures.

[0043] Among them, the execution monitoring sub-module further includes:

[0044] A mutation detection unit for, when the system detects a mutation in the water supply demand at the fire scene, obtaining the change information of the water supply parameters within a preset second time period before and after the mutation;

[0045] A pattern analysis unit for performing a time series analysis on the change information of the water supply parameters to obtain a demand change pattern;

[0046] A matching unit for matching the demand change pattern with multiple predefined standard emergency situation patterns to obtain a matching similarity;

[0047] A scheme selection unit for extracting key parameters from the change information of the water supply parameters based on the emergency response rules corresponding to the standard emergency situation pattern with the highest matching similarity;

[0048] A condition matching unit for matching the key parameters with the triggering conditions of multiple preset emergency plans, and when the matching is met, obtaining the preset emergency plan that meets the matching and its execution priority;

[0049] An execution judgment unit for judging whether the current system state meets the execution conditions of the selected emergency plan;

[0050] A start unit for, when the system state meets the execution conditions of the selected emergency plan, immediately starting the emergency water supply adjustment plan to optimize the on-site water supply efficiency.

[0051] Among them, it further includes:

[0052] A knowledge graph building module for building a knowledge graph for the water supply regulation of a fire pump station, where the knowledge graph includes pump station equipment parameters, the topological structure of the water supply network, historical fire cases, and fire water supply experience;

[0053] A verification module for verifying the rationality of the water supply regulation strategy generated by the artificial intelligence model based on the knowledge graph for the water supply regulation of the fire pump station;

[0054] An execution module for executing the water supply regulation strategy when the verification result shows that the reliability of the strategy is greater than or equal to the reliability threshold;

[0055] An optimization module for, when the verification result shows that the reliability of the strategy is less than the reliability threshold, optimizing and adjusting the water supply regulation strategy based on the reasons for the verification failure and then verifying again until the verification passes or the maximum number of verification times is reached.

[0056] Among them, an artificial intelligence-based method for controlling the water supply regulation of a fire pump station includes:

[0057] S101: Obtain the real-time water supply parameters and environmental status information of the fire pump station;

[0058] S102: Based on a pre-trained artificial intelligence model, generate an optimal water supply regulation strategy according to the real-time water supply parameters and environmental status information;

[0059] S103: Execute the optimal water supply regulation strategy to achieve intelligent regulation and control of the water supply of the fire pump station.

[0060] Compared with the prior art, the present invention has the following advantages:

[0061] An artificial intelligence-based water supply regulation control system for a fire pump station includes: an acquisition module for acquiring the real-time water supply parameters and environmental status information of the fire pump station; a strategy generation module for generating an optimal water supply regulation strategy based on a pre-trained artificial intelligence model according to the real-time water supply parameters and environmental status information; a control module for executing the optimal water supply regulation strategy to achieve intelligent regulation and control of the water supply of the fire pump station. It can greatly improve the operation efficiency of the fire pump station, reduce the operation cost, ensure its reliability and safety, and thus provide a more stable and efficient guarantee for the fire protection system.

[0062] Other features and advantages of the present invention will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention.

[0063] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0064] The accompanying drawings are used to provide a further understanding of the present invention and form a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0065] Figure 1 It is a structural diagram of the fire pump station water supply regulation control system based on artificial intelligence in the embodiment of the present invention;

[0066] Figure 2 It is a structural diagram of the acquisition module in the embodiment of the present invention;

[0067] Figure 3 It is a flowchart of the fire pump station water supply regulation control method based on artificial intelligence in the embodiment of the present invention. Detailed Embodiments

[0068] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0069] The embodiment of the present invention provides as Figure 1 shown, a fire pump station water supply regulation control system based on artificial intelligence, including:

[0070] An acquisition module, configured to acquire real-time water supply parameters and environmental status information of the fire pump station;

[0071] A strategy generation module, configured to generate an optimal water supply regulation strategy based on a pre-trained artificial intelligence model according to the real-time water supply parameters and environmental status information;

[0072] A control module, configured to execute the optimal water supply regulation strategy to achieve intelligent regulation and control of the water supply of the fire pump station.

[0073] The working principle of the above technical solution is as follows: The acquisition module collects parameter data such as pressure, flow rate, and temperature of the water supply system in real time through a sensor network installed at key points of the fire pump station. At the same time, this module also collects external environmental status information such as environmental temperature and humidity, weather conditions, and building fire risk levels. These data are preprocessed and screened to form a standardized data set, which is transmitted to the strategy generation module for analysis and processing. The system supports multiple data collection frequencies and can automatically adjust the sampling interval according to the urgency to ensure high-frequency and high-precision parameter information at critical moments.

[0074] The strategy generation module receives the real-time data transmitted by the acquisition module and inputs it into a pre-trained artificial intelligence model. This model is trained based on a large amount of historical data and fire water supply cases and has deep learning and prediction capabilities. When receiving the real-time data, the model will, through the comparative analysis of the current parameters and the historical optimal parameters, combined with the environmental status information, comprehensively evaluate various water supply regulation schemes. Through weight calculation and multi-objective optimization algorithms, it quickly generates the most suitable water supply regulation strategy for the current situation, including specific indicators such as the start-stop timing of pumps, the adjusted value of water supply pressure, and flow control parameters, and transmits these strategy instructions to the control module for execution.

[0075] The control module receives the optimal water supply regulation strategy instructions output by the strategy generation module and converts the strategy into specific execution commands through a standardized communication protocol. These commands directly act on the various actuators of the fire pump station, including pump start-stop controllers, variable frequency speed regulation devices, valve opening controllers, etc. The control module adopts a closed-loop control method, continuously monitors the deviation between the execution result and the expected target, and automatically fine-tunes the execution parameters according to the deviation size to ensure that the water supply system operates stably according to the optimal strategy. At the same time, the control module also has an emergency intervention mechanism and can accept manual instructions in extreme cases to immediately adjust the system operation state.

[0076] The beneficial effects of the above technical solution are as follows: Through artificial intelligence strategy optimization, the water supply parameters can be accurately matched to the requirements of different fire scenarios, reducing unnecessary energy consumption. Intelligent adjustment and control reduce the risk of human operation errors and improve the stability and reliability of the water supply system. The optimal water supply strategy can reduce the frequent start-stop and overloading operation of equipment, effectively extending the service life of the key equipment in the pump station.

[0077] In another embodiment, as Figure 2 shown, the acquisition module includes:

[0078] A data acquisition sub-module for collecting the real-time pressure, flow, temperature, water level and the operation status data of each pump group in the fire pump station;

[0079] An environmental monitoring sub-module for monitoring the meteorological conditions, building fire conditions and water supply pipe network pressure distribution around the fire pump station.

[0080] The working principle of the above technical solution is as follows: The data acquisition sub-module continuously acquires the core parameters of the system operation through a variety of high-precision sensor networks deployed at key positions in the fire pump station. Specifically, pressure sensors are installed on the inlet and outlet pipelines of the pump station to monitor the change of water supply pressure in real time; electromagnetic flowmeters are installed on the main water supply pipeline to accurately record the flow data; temperature sensors are distributed at the pump motor, bearings and water supply network nodes to monitor the operating temperature of the equipment; ultrasonic water level gauges are installed in the reservoir to track the water source reserve; the operating status of the pump group is comprehensively monitored through current monitors, vibration sensors and tachometers. These sensors collect data at a preset sampling frequency (5 seconds per time under normal conditions, which can be increased to 1 second per time in case of emergency), and transmit the data to the data processing unit through the fieldbus network. In the data processing unit, the raw data is processed through filtering, calibration and standardization to form a structured data packet. The system preliminarily screens the abnormal data through edge computing technology and triggers an early warning mechanism for parameters exceeding the preset threshold. Finally, the processed data is transmitted to the central control system in real time to provide a data basis for subsequent strategy generation.

[0081] The environmental monitoring sub-module comprehensively monitors the external factors affecting fire water supply by establishing an environmental perception network around the pump station. First, the meteorological monitoring device includes temperature and humidity sensors, anemometers and barometers, which are installed at appropriate positions outside the pump station to collect meteorological data in real time; second, the monitoring of the building fire situation is connected to the data interface of the building fire protection system to obtain the signal status of fire alarms, smoke detectors and heat detectors, and to grasp the development of the fire situation in real time; third, the pressure distribution of the water supply network is collected through the pressure sensor array distributed at each node of the water supply network to form a complete water supply network pressure distribution map. After the environmental data is collected, it is processed through a dedicated data converter for format unification and time synchronization, and then transmitted to the environmental data analysis platform through a secure communication network. This platform runs specific environmental model algorithms to integrate the scattered environmental data into an environmental status assessment report, including fire risk level assessment, water supply demand prediction and water supply network pressure balance suggestions. These environmental status information and the operating parameters of the data acquisition sub-module together constitute the input conditions for strategy generation, supporting the system to make more practical water supply adjustment decisions.

[0082] The beneficial effects of the above technical solution are as follows: Multi-dimensional and high-frequency data acquisition ensures that the information mastered by the system is accurate and reliable, reducing control errors. Real-time environmental monitoring enables the system to perceive the change of fire situation in advance, pre-adjust the water supply parameters, and shorten the response time. Based on accurate environmental and equipment data, the system can allocate water resources and energy more reasonably, improving the utilization efficiency.

[0083] In another embodiment, the strategy generation module includes:

[0084] A model construction sub-module, which is used to perform pre-training based on the historical operation water supply parameters of the fire pump station and the corresponding environmental status information, and construct an artificial intelligence model;

[0085] A scenario recognition sub-module, which is used to analyze the acquired real-time water supply parameters and environmental status information based on the pre-trained artificial intelligence model, and identify the current water supply scenario type;

[0086] A demand prediction sub-module, which is used to predict the change trend of water supply demand within a preset future time period according to the recognized scenario type and combined with historical data;

[0087] A strategy inference sub-module, which is used to comprehensively consider factors such as water supply demand, system energy consumption, and equipment life to generate multiple groups of candidate water supply adjustment strategies;

[0088] A strategy evaluation sub-module, which is used to evaluate multiple groups of candidate strategies and select the strategy with the highest comprehensive score as the optimal water supply adjustment strategy.

[0089] The working principle of the above technical solution is as follows: The model construction sub-module establishes an artificial intelligence model for predicting water supply demand by systematically processing and analyzing the historical data of the fire pump station. First, this module obtains historical operation data of at least 2 years from the pump station database, including the water supply pressure change curve, flow fluctuation record, pump group start-stop time, and the corresponding environmental status information (such as fire level, meteorological conditions, pipe network pressure distribution); Subsequently, the original data is cleaned to remove outliers and missing records, and the time standardization of data from different sources is performed through time series alignment technology; Then, feature engineering methods are used to extract key features from multi-dimensional data, such as the correlation between pressure peaks, flow change rates, pump group start frequencies and environmental status; Finally, taking these features as inputs, the model is trained through a deep learning neural network (mainly using LSTM and Transformer structures) to establish the mapping relationship between water supply parameters and environmental status. The training process adopts a phased strategy: first, 80% of the historical data is used for basic training, then 10% of the data is used for fine-tuning, and finally the remaining 10% of the data is used for model verification. The model training goal is to minimize the mean square error between the predicted value and the actual value, and at the same time control the model complexity by introducing a regularization term to prevent overfitting. After training, the model will be saved and incrementally updated with the latest data regularly (by default, once a week) to adapt to the gradual changes of system performance and environmental characteristics.

[0090] The scene recognition sub-module analyzes and classifies the current operating state of the pumping station in real time based on a pre-trained artificial intelligence model. This module obtains a set of real-time water supply parameters (pressure, flow rate, temperature, etc.) from the data acquisition sub-module every 10 seconds and environmental status information (fire situation, meteorology, pipe network pressure distribution) from the environmental monitoring sub-module, and integrates these real-time data into a feature vector in a preset format. Subsequently, the feature vector is input into the pre-trained neural network model, and the probability distribution of different scene types is obtained through forward calculation. The system identifies the current situation according to the scene type with the highest probability and records the probability value as a confidence index. Scene types include: normal maintenance scenarios (daily water supply, regular inspection), small-scale fire scenarios (single-point fire, initial fire situation), large-scale fire scenarios (multi-point fire, spreading fire situation), extreme environment scenarios (extremely cold or hot, strong wind and heavy rain), etc. When the confidence of a certain scene is lower than the preset threshold (default 75%), the system will start a multi-model voting mechanism, comprehensively combining a rule-based judgment algorithm and historical similarity comparison to improve the reliability of scene recognition. The recognition results will be recorded and displayed in real time on the system monitoring interface and used as input conditions for the demand prediction sub-module.

[0091] The demand prediction sub-module predicts the change in water supply demand within a future time window based on the identified scene type and combined with historical data. First, the system obtains the current scene type and its confidence from the scene recognition sub-module and extracts the historical development pattern of this type of scene from the database. Then, the system selects a suitable prediction algorithm according to the scene type: for normal maintenance scenarios, time series analysis methods (such as the ARIMA model) are mainly used; for fire scenarios, a combined prediction method is adopted, integrating a physical fire spread model and a data-driven deep learning prediction; for extreme environment scenarios, external variables of meteorological data are introduced for comprehensive prediction. The prediction process is carried out on three time scales: short-term (next 30 minutes, 5-minute granularity), medium-term (next 4 hours, 30-minute granularity), and long-term (next 24 hours, 2-hour granularity). The system updates the prediction results every 5 minutes through a sliding window technique and calculates the prediction interval (default 95% confidence interval) to represent the uncertainty of the prediction. When the actual water supply demand deviates from the prediction interval, the system will trigger an online adjustment mechanism for the prediction model, improving the model's adaptability to similar situations by increasing the weight of the latest deviation samples. The prediction results are output in the form of a water supply - time curve and serve as the key input for the policy inference sub-module.

[0092] The policy inference sub-module generates a combination of water supply regulation policies suitable for the current scenario through a multi-objective optimization algorithm. First, the system receives the water supply demand prediction curve output by the demand prediction sub-module and obtains the operating status of the current pumping station equipment from the data acquisition sub-module. Then, the system establishes a multi-objective optimization model with the water supply guarantee rate, energy consumption, and equipment wear as objectives. The water supply guarantee rate is defined as the ratio of the actual water supply volume to the demand volume. Energy consumption takes into account the power usage efficiency, and equipment wear is evaluated through the start-stop times and operation duration. The optimization process uses an improved particle swarm algorithm, starting from the initial particle swarm (each particle represents a pump group operation plan), and gradually approaching the optimal solution through iterative calculations. In each iteration, the system evaluates the fitness of each particle according to the objective function and updates the position and velocity of the particle. To improve the algorithm efficiency, the system sets an adaptive weight adjustment mechanism to dynamically adjust the weights of the three objectives of the water supply guarantee rate, energy consumption, and equipment wear for different scenario types: in the fire scenario, the weight of the water supply guarantee rate is significantly increased; in the normal maintenance scenario, the weights of energy consumption and equipment wear are relatively increased. After the preset number of iterations (default 50 times), the system selects the Pareto optimal solution set from the final particle swarm to form 5 - 8 groups of candidate water supply regulation policies. Each group of policies includes specific pump group switch states, speed settings, and pressure regulation parameters, as well as the expected water supply curve, energy consumption estimation, and equipment life impact assessment. These candidate policies will be passed to the policy evaluation sub-module for further screening.

[0093] The strategy evaluation sub-module comprehensively evaluates the candidate water supply regulation strategies through a comprehensive scoring system. First, the system receives multiple groups of candidate strategies generated by the strategy inference sub-module and reads the current scoring weight configuration from the system configuration. Then, the system scores each group of strategies from three dimensions: safety, reliability, and efficiency. The safety score mainly considers the stability of the water supply pressure and the risk of over-limit, which is calculated through pressure fluctuation simulation. The reliability score focuses on the probability of equipment failure and maintenance requirements, and is evaluated based on the equipment wear model and historical failure data. The efficiency score combines energy consumption efficiency and economic cost, and is calculated through the energy consumption model and operating cost. The analytic hierarchy process is used in the scoring process. First, the sub-indicators under each dimension are scored (on a 0-100 scale), and then the dimension scores are obtained by applying the corresponding weight configuration according to the current scenario type. Finally, the scores are aggregated into a comprehensive score. In special cases, the system will introduce an additional scoring adjustment mechanism. For example, when the emergency level of the fire scene is relatively high, the weight of the response speed indicator will be increased; when the equipment is approaching the maintenance cycle, the weight of the equipment protection indicator will be increased. After scoring, the system selects the strategy with the highest comprehensive score as the optimal water supply regulation strategy and generates a detailed strategy execution report, including the adjusted values of each parameter, the expected effects, and risk warnings. In addition, the system will retain the sub-optimal strategy as an alternative plan and quickly switch when the execution effect of the optimal strategy is not good. The final strategy will be sent to the execution equipment through the control interface to achieve intelligent control of the pump station water supply.

[0094] The beneficial effects of the above technical solutions are as follows: Through rapid scene recognition and future demand prediction, the system can adjust the water supply parameters in advance; The multi-objective optimization algorithm balances the water supply demand and energy consumption, saving power consumption while ensuring water supply; By generating strategies considering equipment wear factors, unnecessary frequent starts and stops are reduced, and the service life of key equipment can be extended.

[0095] In another embodiment, the control module includes:

[0096] The strategy decomposition sub-module is used to analyze the complexity of the optimal water supply regulation strategy. When the complexity value is greater than the execution complexity threshold, the strategy is decomposed into multiple sub-strategies that are executed continuously;

[0097] The instruction conversion sub-module is used to convert the water supply regulation strategy or sub-strategy into specific control instructions for pump group start / stop, frequency conversion speed regulation, and valve opening;

[0098] The execution monitoring sub-module is used to monitor the execution effect of the control instructions in real time and record the changes in key water supply parameters;

[0099] The emergency handling sub-module is used to quickly start the corresponding emergency water supply regulation plan based on the preset emergency plan library when a sudden change in the water supply demand at the fire scene or system abnormality is detected.

[0100] The working principle of the above technical solution is as follows: The policy decomposition sub-module evaluates the complexity of the optimal water supply regulation policy to ensure the system execution efficiency. When the complexity of the optimal water supply policy calculated by the system exceeds the preset threshold, this module will automatically decompose the complex policy into multiple sub-policies that are executed sequentially. The specific operation process is as follows: First, the module receives the optimal water supply regulation policy from the decision-making layer; then, it analyzes the policy using a multi-dimensional complexity evaluation algorithm, and the evaluation indicators include the pump group switching frequency, the change in speed regulation range, and the valve regulation complexity; finally, when the complexity value exceeds the execution threshold, the module uses a time-series decomposition algorithm to split the policy into multiple sub-policies that are executed sequentially, and the complexity of each sub-policy is lower than the system preset threshold to ensure the smoothness of execution.

[0101] The instruction conversion sub-module is responsible for converting the abstract water supply regulation policy into specific execution instructions. This module first receives the water supply regulation policy or sub-policy from the policy decomposition sub-module, and then converts the policy into device-level control instructions through an instruction mapping library, including: the start-stop sequence of the pump group, the speed regulation parameters of the frequency converter, and the precise control signals for the opening degrees of each valve. During the conversion process, the module considers device characteristics, start-up sequence, and safety constraints to generate an optimized instruction sequence to ensure the safety and efficiency of instruction execution. For example, in the scenario of boosting water supply at a fire site, the module will automatically generate an instruction sequence of first starting the main pump and then adjusting the valve opening degree to avoid water hammer effects.

[0102] The execution monitoring sub-module real-time tracks the execution effect of the control instructions and records the changes in key water supply parameters. This module realizes monitoring from three aspects: one is to collect real-time data such as pipeline network pressure, flow rate, and pump group operation status through a distributed sensor network; the second is to compare and analyze the collected data with the expected effect to calculate the execution deviation; the third is to establish a parameter change curve to record the water supply response characteristics. When the monitored execution deviation exceeds the allowable range, the module will trigger a policy fine-tuning mechanism to ensure that the water supply regulation effect meets the expectations. For example, when it is detected that the pipeline network pressure in a certain area is insufficient, the system can timely adjust the rotation speed of the relevant pump group or the valve opening degree.

[0103] The emergency handling sub-module is used to quickly respond to sudden changes in the water supply demand at the fire site or system anomalies. This module maintains a preset emergency plan library and pre-designs response strategies for different types of emergencies (such as main pump failures, pipeline network ruptures, sudden increases in water demand at the fire site, etc.). When the system detects an anomaly, the emergency handling sub-module quickly identifies the type of anomaly through a scenario matching algorithm and calls the most matching emergency water supply regulation plan from the plan library. For example, when it is detected that a certain main pump fails, the module can start the standby pump group and re-allocate the flow path within milliseconds to ensure uninterrupted water supply.

[0104] The beneficial effects of the above technical solution are as follows: An intelligent and highly reliable water supply regulation control system for fire pump stations is constructed, which can adapt to complex and changeable fire scenarios, provide accurate, stable and reliable water supply guarantee, and significantly improve the efficiency and safety of fire rescue.

[0105] In another embodiment, the model construction sub-module includes:

[0106] An acquisition unit, configured to acquire historical operating water supply parameters, corresponding environmental status information, and corresponding water supply efficiency evaluation data of the fire pump station;

[0107] A model construction unit, configured to construct a multi-scenario water supply demand model based on historical operating water supply parameters and corresponding environmental status information;

[0108] A sample acquisition unit, configured to acquire multiple groups of training samples, and the training samples include water supply demand data under different fire types, different building structures, and different environmental conditions;

[0109] An evaluation unit, configured to evaluate each training sample based on the multi-scenario water supply demand model to obtain the water supply efficiency score of each training sample;

[0110] A training unit, configured to train an artificial intelligence model based on the training samples whose water supply efficiency scores are greater than or equal to a preset efficiency threshold.

[0111] Among them, obtaining the water supply efficiency score of each training sample includes:

[0112] Obtain a sample set including multiple groups of training samples. The sample set includes a first type of water supply parameter configuration corresponding to a first type of fire scenario and a second type of water supply parameter configuration corresponding to a second type of fire scenario. The first type of water supply parameter configuration and the second type of water supply parameter configuration are preliminarily classified according to a first evaluation criterion;

[0113] Construct a multi-scenario water supply demand model, and the multi-scenario water supply demand model includes a water supply demand feature extraction module and a water supply efficiency evaluation module for different fire scenarios;

[0114] Input the sample set into the multi-scenario water supply demand model, and perform simulation calculations on the water supply parameter configurations of each training sample under different fire scenarios;

[0115] Based on the simulation calculation results, respectively obtain the performance indicators of each training sample in multiple dimensions of fire extinguishing efficiency, water resource utilization rate, and energy consumption;

[0116] According to a preset comprehensive scoring formula, calculate the water supply efficiency score of each training sample, where the comprehensive scoring formula is:

[0117] E = α·F + β·W + γ·C

[0118] Among them, E represents the water supply efficiency score, F represents the fire extinguishing efficiency index, W represents the water resource utilization rate index, C represents the energy consumption index, α, β, and γ are the weight coefficients of the corresponding dimensions respectively, and α + β + γ = 1;

[0119] Display the water supply efficiency score results of each training sample so that the management personnel of the fire pump station can view the score data under the first type of fire scene;

[0120] When it is detected that the evaluation system receives a scene switching instruction, adjust the evaluation parameters of the multi-scene water supply demand model, and recalculate and obtain the water supply efficiency score under the second type of fire scene;

[0121] Display the water supply efficiency score results under the second type of fire scene so that the technical personnel of the fire pump station can optimize the corresponding water supply parameter configuration.

[0122] The working principle of the above technical solution is as follows: The acquisition unit is responsible for collecting the historical operation data of the fire pump station, including water supply parameters such as the water supply pressure, flow rate, and energy consumption of the pump station, and at the same time obtaining the environmental status information (such as meteorological data such as temperature, humidity, and wind force) at the corresponding time point, as well as the evaluation results of the corresponding water supply efficiency (an integrated evaluation index of the water pressure stability, water supply sufficiency, and energy utilization efficiency of the fire pump station during the fire extinguishing process). These data are collected in real time through the sensor network in the pump station and stored in the database, providing a data basis for subsequent model construction.

[0123] Based on the historical data collected by the acquisition unit, the model construction unit uses data mining and machine learning algorithms to analyze the correlation between water supply parameters and water supply efficiency under different environmental conditions. This unit classifies the data according to environmental characteristics (such as high temperature, low temperature, strong wind, etc.) and building types (such as high-rise buildings, underground buildings, chemical plants, etc.), and constructs a dedicated water supply demand model for each type of scene to adapt to the best water supply strategy under different scenes. Multi-scene water supply demand model: A set of mathematical models established for the water supply demand characteristics under different types of fires, different building structures, and different environmental conditions.

[0124] The sample acquisition unit collects multiple groups of training samples through methods such as simulation drills, historical fire case analysis, and expert experience summary. Each group of samples contains water supply demand data under specific fire types (such as electrical fires, flammable liquid fires, etc.), building structures (such as reinforced concrete structures, wooden structures, etc.), and environmental conditions (such as high temperature in summer, low temperature in winter, etc.), forming a rich training data set.

[0125] The evaluation unit inputs each set of training samples collected by the sample acquisition unit into the multi-scenario water supply demand model generated by the model construction unit for evaluation. The system performs simulation calculations on the water supply parameter configurations of each set of samples under different scenarios, and obtains the corresponding water supply efficiency scores. The scoring dimensions include multiple aspects such as fire extinguishing efficiency, water resource utilization rate, and energy consumption, and comprehensively evaluates the water supply efficiency of each set of samples.

[0126] The training unit screens out the training samples with water supply efficiency scores greater than or equal to the preset efficiency threshold as high-quality samples. These high-quality samples are used to train an artificial intelligence model (such as a deep neural network, random forest, or support vector machine, etc.) so that the model can identify the best water supply parameter configurations under different scenarios. The training process includes steps such as feature extraction, model parameter optimization, and cross-validation to ensure the generalization ability and accuracy of the model. Preset efficiency threshold: The standard line of the water supply efficiency score preset by the system. Samples above this line are considered to have good water supply effects and are suitable for AI model training.

[0127] The beneficial effects of the above technical solutions are as follows: improving fire extinguishing efficiency, the system can select the best water supply strategy according to the fire type and building structure characteristics, reducing the fire extinguishing time. Optimizing water resource utilization, avoiding water supply shortages or over-supplies, and achieving scientific allocation of water resources. Reducing energy consumption, by intelligently adjusting the operation mode of the pump group, reducing power consumption while meeting the fire extinguishing requirements.

[0128] In another embodiment, the model construction unit includes:

[0129] The data classification sub-unit is used to classify and process the historical operating water supply parameters and the corresponding environmental status information to obtain a multi-dimensional feature parameter set;

[0130] The rule determination sub-unit is used to determine the water supply rule knowledge corresponding to the multi-dimensional feature parameter set from the water supply rule knowledge base; the water supply rule knowledge includes: multiple groups of one-to-one corresponding scenario feature recognition rules and water supply demand calculation rules;

[0131] The scenario recognition sub-unit is used to sequentially traverse each scenario feature recognition rule, and based on the traversed scenario feature recognition rule, identify a specific scenario type from the historical operation data;

[0132] The sub-model generation sub-unit is used to generate a scenario water supply demand sub-model according to the specific scenario type based on the water supply demand calculation rule corresponding to the traversed scenario feature recognition rule;

[0133] The model integration sub-unit is used to integrate the scenario water supply demand sub-models generated each time the scenario feature recognition rule is traversed after traversing all the scenario feature recognition rules to obtain a multi-scenario water supply demand model.

[0134] The working principle of the above technical solution is as follows: The data classification subunit first processes the historical operation data, pairs and analyzes the water supply parameters (such as water pressure, flow rate, temperature) with the environmental status information (such as weather conditions, peak water usage periods), and extracts a multi-dimensional feature parameter set. These parameter sets reflect the water supply characteristic laws under different conditions.

[0135] Based on this, the rule determination subunit accesses the water supply rule knowledge base and retrieves the water supply rule knowledge that matches the current feature parameter set. Each rule knowledge includes two parts: a scenario feature recognition rule (used to determine what kind of water supply scenario is currently in) and the corresponding water supply demand calculation rule (determining how to calculate the water supply demand in this scenario).

[0136] The scenario recognition subunit sequentially traverses each scenario feature recognition rule. For each rule traversed, it applies the rule to the historical operation data to identify a specific scenario type, such as "fire emergency status", "daily maintenance status", or "energy-saving operation status", etc.

[0137] For each identified scenario type, the sub-model generation subunit applies the corresponding water supply demand calculation rule to generate a water supply demand sub-model for that specific scenario. For example, the sub-model for the fire emergency status may prioritize quickly reaching high pressure and large flow rate, while the sub-model for the energy-saving operation status may focus on minimizing energy consumption while meeting basic requirements.

[0138] After completing the traversal of all scenario feature recognition rules, the model integration subunit integrates the water supply demand sub-models for each scenario to form a unified multi-scenario water supply demand model. This model can automatically switch to the most suitable water supply mode according to the real-time monitored conditions.

[0139] The beneficial effects of the above technical solution are as follows: Through multi-dimensional parameter analysis, the system can more accurately predict and meet the water supply demands in different scenarios, reducing the situations of insufficient or excessive water supply. In case of a fire emergency, the system can quickly identify the scenario and switch to the emergency mode to ensure that the water pressure and flow rate meet the fire requirements at critical moments. In non-emergency states, the system can automatically switch to the energy-saving mode, reducing unnecessary energy consumption and lowering the operation cost.

[0140] In another embodiment, the execution monitoring sub-module includes:

[0141] A monitoring unit for continuously monitoring the operation status of the water supply system;

[0142] An analysis unit, which is configured to, if the monitored data shows that the water supply pressure fluctuations exceed the stable range for N consecutive times, and the patterns of each fluctuation conform to a predefined standard fluctuation relationship, and the sum of the correlation strengths of the conforming standard fluctuation relationships is greater than or equal to the warning threshold, extract the feature of the pressure data of each fluctuation to obtain a fluctuation feature set; the warning threshold is the product of N and the risk coefficient;

[0143] A matching unit, which is configured to match the system risk factors corresponding to the fluctuation feature set from the fault prediction knowledge base;

[0144] A prediction unit, which is configured to predict the operation trend of the water supply system within a preset first time period in the future based on the system risk factors;

[0145] An adjustment unit, which is configured to adjust the water supply parameters in advance based on the prediction result to prevent system failures.

[0146] The working principle of the above technical solution is as follows: The monitoring unit continuously and real-time collects the operation status data of the water supply system, including key parameters such as water pressure, flow rate, temperature, and vibration. These data are collected through a sensor network and transmitted to the system central processing module at a preset time interval (such as every second or every minute) to form a continuous time series data stream.

[0147] The analysis unit performs intelligent analysis on the collected monitoring data. When the system detects that the monitored data shows that the water supply pressure fluctuations exceed the stable range for N consecutive times (N is a configurable parameter, such as 5 consecutive times), it further analyzes the relationship patterns between these fluctuations. The analysis unit calculates the degree of conformity of each fluctuation with a predefined standard fluctuation relationship (such as linear increase, periodic fluctuation, stepwise decrease, etc.) and calculates the sum of the correlation strengths. If the sum of the correlation strengths is greater than or equal to the warning threshold (warning threshold = N × risk coefficient, and the risk coefficient is preset according to the importance of the system and environmental conditions), the system extracts the feature of the pressure data of each fluctuation to obtain a fluctuation feature set containing information such as fluctuation amplitude, frequency, and duration.

[0148] The matching unit matches the extracted fluctuation feature set with the historical cases and theoretical models stored in the fault prediction knowledge base. The knowledge base contains various possible system risk factors (such as pump body wear, pipeline blockage, valve failure, etc.) and their corresponding pressure fluctuation feature patterns. Through pattern recognition and similarity calculation, the matching unit can identify the system risk factors most likely corresponding to the current fluctuation feature.

[0149] The prediction unit predicts the operation trend of the water supply system within a preset first time period in the future (such as the next 30 minutes to 2 hours) based on the identified system risk factors, combined with historical data and machine learning models. The prediction content includes the change trends of key parameters (such as pressure and flow rate), as well as the possibility and severity of system failures.

[0150] According to the prediction results, the adjustment unit automatically calculates and executes the optimal parameter adjustment strategy, such as adjusting the pump speed, switching to standby equipment, adjusting the valve opening, etc., to intervene in the system operation state in advance, prevent failures from occurring or reduce the impact of failures. The adjustment strategy will balance the relationship between water supply demand and equipment protection to ensure that normal water supply functions are not affected while preventing failures.

[0151] The beneficial effects of the above technical solution are as follows: By early identifying potential risk factors, the system can take preventive measures before the failure develops to a serious stage, avoiding the failure of the fire pump station at critical moments. Through predictive maintenance rather than passive response, abnormal working conditions borne by the equipment are reduced, and the service life of key components is significantly extended. Small problems are identified and addressed in advance to prevent them from developing into major failures that require large-scale repairs or replacements, thereby reducing the overall maintenance cost.

[0152] In another embodiment, the execution monitoring sub-module further includes:

[0153] A mutation detection unit, configured to obtain the change information of water supply parameters within a preset second time period before and after the mutation when the system detects a mutation in the water supply demand at the fire scene;

[0154] A pattern analysis unit, configured to perform a time series analysis on the change information of water supply parameters to obtain a demand change pattern;

[0155] A matching unit, configured to match the demand change pattern with multiple predefined standard emergency situation patterns to obtain a matching similarity;

[0156] A solution selection unit, configured to extract key parameters from the change information of water supply parameters based on the emergency response rules corresponding to the standard emergency situation pattern with the highest matching similarity;

[0157] A condition matching unit, configured to match the key parameters with the triggering conditions of multiple preset emergency plans. When the match is met, obtain the preset emergency plan that meets the match and its execution priority;

[0158] An execution judgment unit, configured to judge whether the current system state meets the execution conditions of the selected emergency plan;

[0159] A start unit, configured to immediately start an emergency water supply adjustment plan to optimize the on-site water supply efficiency when the system state meets the execution conditions of the selected emergency plan.

[0160] The working principle of the above technical solution is as follows: The mutation detection unit is responsible for real-time monitoring of the water supply system parameters. When a mutation in the water supply demand at the fire scene is detected, the system will automatically capture the key water supply parameters within a preset time period before and after the mutation, such as pressure changes, flow fluctuations, temperature changes, etc., providing a basis for subsequent analysis.

[0161] The pattern analysis unit receives the captured information on the changes in water supply parameters and conducts a time series analysis. This unit uses time series algorithms to analyze the trends, amplitudes, and rates of parameter changes, thereby identifying specific demand change patterns. For example, a sharp drop in pressure accompanied by a sudden increase in flow in a certain area indicates a water pipe burst pattern.

[0162] The matching unit compares the identified demand change patterns with multiple standard emergency situation patterns pre-stored in the system. By calculating the similarity matrix, it determines which predefined pattern the current situation is closest to. Different scenarios such as the initial spread pattern of a fire and the controlled combustion pattern have their characteristic parameter combinations.

[0163] The solution selection unit, based on the standard pattern with the highest matching similarity, applies the corresponding emergency response rules to extract key decision-making parameters from the currently obtained information on the changes in water supply parameters, such as the required pressure range, minimum guaranteed flow rate, etc.

[0164] The condition matching unit matches the extracted key parameters with the triggering conditions of multiple emergency plans preset in the system. When the triggering condition of a certain emergency plan is met, the system will identify one or more emergency plans most suitable for the current situation and determine their execution priorities according to the preset algorithm.

[0165] The execution judgment unit will evaluate the current operating status of the pump station, the health of the equipment, the available resources, etc., to determine whether the execution conditions of the selected emergency plan are met. This unit ensures that the system will not cause more serious problems due to the execution of the emergency plan.

[0166] The startup unit, after confirming that the execution conditions are met, immediately starts the corresponding emergency water supply regulation plan in the order of priority. This unit is responsible for converting the decision into specific control instructions, adjusting the pump-valve combination, changing the water supply pressure and flow parameters, and optimizing the on-site water supply efficiency.

[0167] The beneficial effects of the above technical solution are as follows: The system can quickly identify emergencies in the early stage of the mutation of water supply demand, shortening the time difference from the occurrence of the problem to the implementation of countermeasures. By intelligently identifying the type and development stage of the fire, the system can provide the water supply parameters most suitable for the current situation, avoiding resource waste or insufficient supply. The multi-level matching and judgment mechanism ensure that the system can accurately distinguish different types of water supply mutation situations, reducing false alarms and incorrect responses.

[0168] In another embodiment, it further includes:

[0169] A knowledge graph building module, which is used to build a knowledge graph for the water supply regulation of the fire pump station. The knowledge graph includes pump station equipment parameters, water supply pipe network topology, historical fire cases, and fire water supply experience.

[0170] A verification module, which is used to verify the rationality of the water supply regulation strategy generated by the artificial intelligence model based on the knowledge graph of the water supply regulation of the fire pump station.

[0171] An execution module, which is used to execute the water supply regulation strategy when the verification result shows that the strategy reliability is greater than or equal to the reliability threshold.

[0172] An optimization module, which is used to optimize and adjust the water supply regulation strategy based on the reasons for verification failure and then verify it again when the verification result shows that the strategy reliability is less than the reliability threshold, until the verification passes or the maximum verification times are reached.

[0173] The working principle of the above technical solution is as follows: The knowledge graph building module collects and integrates various types of information of the fire pump station to construct a complete knowledge graph. The system first collects pump station equipment parameters (such as the flow rate, head, power, etc. of the pump), then maps the water supply pipe network topology (including pipe length, diameter, connection points, etc.), and enters historical fire cases and fire water supply experience. After these data are processed structurally, a multi-dimensional knowledge network is formed, enabling the system to understand the complex relationships in the pump station operation environment. For example, the knowledge graph includes associated information such as "The third water pump is connected to the high-level water distribution tank", "The maximum flow rate of the DN200 pipe is X cubic meters per hour", and "Historical data shows that increasing the water supply pressure in Area B during a fire in the commercial area can improve the fire extinguishing efficiency".

[0174] When the artificial intelligence model generates a water supply regulation strategy, the verification module will verify the rationality of the strategy based on the established knowledge graph. The system checks whether the strategy meets the equipment parameter limitations, whether it adapts to the current pipe network state, whether it conforms to historical successful cases, and other dimensions. For example, if the AI recommends "Increase the operating frequency of Pump 1 to 45 Hz and close the valve of Pipeline 2", the verification module will check: whether Pump 1 can operate safely at this frequency, whether closing Pipeline 2 will cause insufficient water supply in other areas, whether this combination has been used in similar fire situations, etc. The system calculates the strategy reliability score and compares it with the preset threshold.

[0175] When the verification result indicates that the strategy reliability is greater than or equal to the reliability threshold (e.g., 85%), the execution module will send the instruction to the relevant device control system. The system transmits precise control parameters to devices such as the water pump frequency converter and electric valve through standard communication protocols (such as MODBUS, OPC UA, etc.) to achieve the automatic execution of the strategy. For example, after the system confirms that the strategy of "increasing the water outlet pressure of pump No. 3 to 0.6 MPa and turning on the high - zone booster pump" is reliable, it will send specific control signals to the relevant devices to make the devices operate according to the requirements of the strategy.

[0176] When the verification result shows that the strategy reliability is less than the reliability threshold, the optimization module will analyze the reasons for failure. The system identifies specific unreasonable points (such as "pump No. 4 cannot meet the pressure and flow requirements simultaneously"), and then based on the alternative solutions and experience rules in the knowledge graph, makes partial or overall adjustments to the original strategy. For example, when it is found that "closing the ring - network valve A3 will cause insufficient water supply in the south area", the system adjusts to "partially close valve A3 and simultaneously open the standby pipeline B5". The modified strategy re - enters the verification link until it passes the verification or reaches the maximum verification times limit (such as 5 times).

[0177] The beneficial effects of the above - mentioned technical solution are as follows: The system can quickly generate and verify the water supply regulation strategy, significantly shorten the time from the occurrence of a fire to the implementation of the optimal water supply strategy, and improve the fire - fighting and rescue efficiency. Through the knowledge graph and verification mechanism, it reduces the errors that may be brought by human decision - making in emergency situations, and improves the accuracy and safety of water supply regulation. Structurally store the expert experience and historical fire - fighting rescue data in the knowledge graph, so that the valuable fire - fighting water supply experience can be preserved and applied without being lost due to personnel changes.

[0178] In another embodiment, as Figure 3 shown, an artificial - intelligence - based water supply regulation control method for a fire - fighting pump station includes:

[0179] S101: Obtain the real - time water supply parameters and environmental status information of the fire - fighting pump station;

[0180] S102: Based on a pre - trained artificial - intelligence model, generate an optimal water supply regulation strategy according to the real - time water supply parameters and environmental status information;

[0181] S103: Execute the optimal water supply regulation strategy to achieve intelligent regulation and control of the water supply of the fire - fighting pump station.

[0182] The working principle of the above - mentioned technical solution is as follows: Step S101 includes: S1011: Collect the real - time pressure, flow, temperature, water level and operating status data of each pump group of the fire - fighting pump station;

[0183] S1012: Monitor the meteorological conditions, building fire conditions and water supply network pressure distribution around the fire - fighting pump station.

[0184] Step S102 includes:

[0185] S1021: Based on the historical operation water supply parameters of the fire pump station and the corresponding environmental status information, perform pre-training to construct an artificial intelligence model;

[0186] S1022: Based on the pre-trained artificial intelligence model, analyze the obtained real-time water supply parameters and environmental status information to identify the current water supply scenario type;

[0187] S1023: According to the identified scenario type and combined with historical data, predict the change trend of water supply demand in a future preset time period;

[0188] S1024: Considering factors such as water supply demand, system energy consumption, and equipment life comprehensively, generate multiple groups of candidate water supply adjustment strategies;

[0189] S1025: Evaluate multiple groups of candidate strategies and select the strategy with the highest comprehensive score as the optimal water supply adjustment strategy.

[0190] Step S103 includes:

[0191] S1031: Conduct complexity analysis on the optimal water supply adjustment strategy. When the complexity value is greater than the execution complexity threshold, decompose the strategy into multiple continuously executed sub-strategies;

[0192] S1032: Convert the water supply adjustment strategy or sub-strategy into specific control instructions for pump group start / stop, variable frequency speed regulation, and valve opening;

[0193] S1033: Real-time monitor the execution effect of the control instructions and record the change situation of key water supply parameters;

[0194] S1034: When a sudden change in water supply demand at the fire scene or system anomaly is detected, based on the preset emergency plan library, quickly start the corresponding emergency water supply adjustment plan.

[0195] Constructing an artificial intelligence model includes:

[0196] Obtain the historical operation water supply parameters of the fire pump station, the corresponding environmental status information, and the corresponding water supply efficiency evaluation data;

[0197] Based on the historical operation water supply parameters and the corresponding environmental status information, construct a multi-scenario water supply demand model;

[0198] Obtain multiple groups of training samples, and the training samples include water supply demand data under different fire types, different building structures, and different environmental conditions;

[0199] Based on the multi-scenario water supply demand model, evaluate each training sample to obtain the water supply efficiency score of each training sample;

[0200] Train an artificial intelligence model based on the training samples whose water supply efficiency scores are greater than or equal to the preset efficiency threshold.

[0201] Construct a multi-scenario water supply demand model, including:

[0202] Classify the historical operation water supply parameters and the corresponding environmental status information to obtain a multi-dimensional feature parameter set;

[0203] Determine the water supply rule knowledge corresponding to the multi-dimensional feature parameter set from the water supply rule knowledge base; the water supply rule knowledge includes: multiple groups of one-to-one corresponding scenario feature recognition rules and water supply demand calculation rules;

[0204] Traverse each scenario feature recognition rule in turn. Based on the traversed scenario feature recognition rule, identify a specific scenario type from the historical operation data;

[0205] Based on the water supply demand calculation rule corresponding to the traversed scenario feature recognition rule, generate a scenario water supply demand sub-model according to the specific scenario type;

[0206] After traversing all scenario feature recognition rules, integrate the scenario water supply demand sub-models generated each time a scenario feature recognition rule is traversed to obtain a multi-scenario water supply demand model.

[0207] Real-time monitor the execution effect of the control instruction, including:

[0208] Continuously monitor the operation status of the water supply system;

[0209] If the water supply pressure fluctuations in the continuous N monitoring data exceed the stable range, and the patterns of each fluctuation conform to the predefined standard fluctuation relationship, and the sum of the correlation strengths of the conforming standard fluctuation relationships is greater than or equal to the warning threshold, extract the feature of the pressure data of each fluctuation to obtain a fluctuation feature set; the warning threshold is the product of N and the risk coefficient;

[0210] Match the system risk factors corresponding to the fluctuation feature set from the fault prediction knowledge base;

[0211] Based on the system risk factors, predict the operation trend of the water supply system in the future preset first time period;

[0212] Based on the prediction result, adjust the water supply parameters in advance to prevent system failures.

[0213] Real-time monitor the execution effect of the control instruction, and also include:

[0214] When the system detects a sudden change in the water supply demand at the fire scene, obtain the change information of the water supply parameters within the respective preset second time periods before and after the change;

[0215] Conduct a time series analysis on the change information of the water supply parameters to obtain the demand change pattern;

[0216] Match the demand change pattern with multiple predefined standard emergency situation patterns to obtain the matching similarity;

[0217] Based on the emergency response rules corresponding to the standard emergency situation pattern with the highest matching similarity, extract key parameters from the change information of the water supply parameters;

[0218] Match the key parameters with the triggering conditions of multiple preset emergency plans. When the match is met, obtain the preset emergency plan that matches and its execution priority;

[0219] Judge whether the current system state meets the execution conditions of the selected emergency plan;

[0220] When the system state meets the execution conditions of the selected emergency plan, immediately start the emergency water supply regulation plan to optimize the on-site water supply efficiency.

[0221] The water supply regulation control method for the fire pump station further includes:

[0222] Establish a knowledge graph for the water supply regulation of the fire pump station, which includes pump station equipment parameters, water supply network topology, historical fire cases, and fire water supply experience;

[0223] Based on the knowledge graph for the water supply regulation of the fire pump station, verify the rationality of the water supply regulation strategy generated by the artificial intelligence model;

[0224] When the verification result shows that the reliability of the strategy is greater than or equal to the reliability threshold, execute the water supply regulation strategy;

[0225] When the verification result shows that the reliability of the strategy is less than the reliability threshold, based on the reasons for the verification failure, optimize and adjust the water supply regulation strategy and then verify it again until the verification passes or the maximum number of verifications is reached.

[0226] The beneficial effects of the above technical solution are as follows: By obtaining the water supply parameters and environmental status information of the fire pump station in real time, the current water supply situation can be accurately grasped. Thus, with the help of the artificial intelligence model, the water supply strategy can be adjusted in real time to ensure that the water supply system of the fire pump station is always in the optimal working state and the water supply efficiency is improved. Based on the pre-trained artificial intelligence model, it can automatically analyze and process a large amount of complex water supply data and generate the optimal water supply adjustment strategy suitable for the current situation. This intelligent adjustment and control can effectively reduce human operation errors and improve the response speed and accuracy of the system. By precisely adjusting the water supply system, unnecessary energy waste can be avoided, the operation load of the pump station can be reduced, and thus the energy consumption and operation cost can be effectively reduced, achieving the goal of energy conservation and emission reduction.

[0227] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and its equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. An artificial intelligence-based water supply regulation control system for a fire pump station, comprising: An acquisition module, configured to acquire real-time water supply parameters and environmental status information of the fire pump station; A strategy generation module, configured to generate an optimal water supply regulation strategy based on a pre-trained artificial intelligence model according to the real-time water supply parameters and environmental status information; A control module, configured to execute the optimal water supply regulation strategy to achieve intelligent regulation control of the water supply of the fire pump station.

2. The fire pump station water supply regulation control system based on artificial intelligence according to claim 1, characterized in that The acquisition module includes: A data acquisition sub-module, configured to collect real-time pressure, flow rate, temperature, water level and operating status data of each pump group of the fire pump station; An environmental monitoring sub-module, configured to monitor meteorological conditions, building fire conditions and water supply network pressure distribution of the surrounding environment of the fire pump station.

3. The fire pump station water supply regulation control system based on artificial intelligence according to claim 1, characterized in that The strategy generation module includes: A model construction sub-module, configured to perform pre-training based on historical operating water supply parameters of the fire pump station and corresponding environmental status information to construct an artificial intelligence model; A scenario recognition sub-module, configured to analyze the acquired real-time water supply parameters and environmental status information based on the pre-trained artificial intelligence model to identify the current water supply scenario type; A demand prediction sub-module, configured to predict the change trend of water supply demand within a preset future time period according to the identified scenario type in combination with historical data; A strategy inference sub-module, configured to generate multiple groups of candidate water supply regulation strategies by comprehensively considering factors such as water supply demand, system energy consumption and equipment life; A strategy evaluation sub-module, configured to evaluate multiple groups of candidate strategies and select the strategy with the highest comprehensive score as the optimal water supply regulation strategy.

4. The artificial intelligence-based fire pump station water supply regulation control system according to claim 1, wherein The control module includes: A strategy decomposition sub-module, configured to perform complexity analysis on the optimal water supply regulation strategy, and when the complexity value is greater than the execution complexity threshold, decompose the strategy into multiple continuously executed sub-strategies; An instruction conversion sub-module, configured to convert the water supply regulation strategy or sub-strategy into specific control instructions for pump group start / stop, variable frequency speed regulation, and valve opening; An execution monitoring sub-module, configured to monitor the execution effect of the control instruction in real time and record the change of key water supply parameters; An emergency handling sub-module, configured to quickly start a corresponding emergency water supply regulation plan based on a preset emergency plan library when a sudden change in water supply demand at the fire scene or system abnormality is detected.

5. The fire pump station water supply regulation control system based on artificial intelligence according to claim 3, characterized in that, The model construction sub-module includes: An acquisition unit, configured to acquire historical operating water supply parameters of the fire pump station, corresponding environmental status information and corresponding water supply efficiency evaluation data; A model construction unit, configured to construct a multi-scenario water supply demand model based on historical operating water supply parameters and corresponding environmental status information; A sample acquisition unit, configured to acquire multiple groups of training samples, and the training samples include water supply demand data under different fire types, different building structures and different environmental conditions; An evaluation unit, configured to evaluate each training sample based on the multi-scenario water supply demand model to obtain the water supply efficiency score of each training sample; A training unit, configured to train the artificial intelligence model based on the training samples with a water supply efficiency score greater than or equal to a preset efficiency threshold.

6. The fire pump station water supply regulation control system based on artificial intelligence according to claim 5, characterized in that The model construction unit includes: A data classification sub-unit, configured to perform classification processing on historical operating water supply parameters and corresponding environmental status information to obtain a multi-dimensional feature parameter set; A rule determination subunit for determining water supply rule knowledge corresponding to a multi-dimensional feature parameter set from a water supply rule knowledge base; the water supply rule knowledge includes: multiple groups of scene feature recognition rules and water supply demand calculation rules that correspond one by one; A scene recognition subunit for sequentially traversing each scene feature recognition rule and identifying a specific scene type from historical operation data based on the traversed scene feature recognition rule; A sub-model generation subunit for generating a scene water supply demand sub-model according to the specific scene type based on the water supply demand calculation rule corresponding to the traversed scene feature recognition rule; A model integration subunit for integrating the scene water supply demand sub-models generated each time a scene feature recognition rule is traversed after traversing all scene feature recognition rules to obtain a multi-scene water supply demand model.

7. The fire pump station water supply regulation control system based on artificial intelligence according to claim 4, characterized in that, The execution monitoring sub-module includes: A monitoring unit for continuously monitoring the operation status of the water supply system; An analysis unit for, if the monitoring data for N consecutive times shows that the water supply pressure fluctuation exceeds the stable range, and the patterns of each fluctuation conform to a predefined standard fluctuation relationship, and the sum of the association strengths of the conforming standard fluctuation relationships is greater than or equal to the warning threshold, extracting the feature of each fluctuating pressure data to obtain a fluctuation feature set; the warning threshold is the product of N and the risk coefficient; A matching unit for matching the system risk factors corresponding to the fluctuation feature set from a fault prediction knowledge base; A prediction unit for predicting the operation trend of the water supply system within a preset first time period in the future based on the system risk factors; An adjustment unit for adjusting the water supply parameters in advance based on the prediction result to prevent system failures.

8. The artificial intelligence-based fire pump station water supply regulation control system according to claim 7, characterized in that The execution monitoring sub-module further includes: A mutation detection unit for, when the system detects a mutation in the water supply demand at the fire scene, obtaining the water supply parameter change information within a preset second time period before and after the mutation; A pattern analysis unit for performing a time series analysis on the water supply parameter change information to obtain a demand change pattern; A matching unit for matching the demand change pattern with multiple predefined standard emergency situation patterns to obtain a matching similarity; A solution selection unit for extracting key parameters from the water supply parameter change information based on the emergency response rule corresponding to the standard emergency situation pattern with the highest matching similarity; A condition matching unit for matching the key parameters with the trigger conditions of multiple preset emergency plans, and when the matching is met, obtaining the preset emergency plan that meets the matching and its execution priority; An execution judgment unit for judging whether the current system state meets the execution conditions of the selected emergency plan; A start unit for immediately starting an emergency water supply adjustment plan to optimize the on-site water supply efficiency when the system state meets the execution conditions of the selected emergency plan.

9. The fire pump station water supply regulation control system based on artificial intelligence according to claim 1, characterized in that It further includes: A knowledge graph building module for building a knowledge graph for fire pump station water supply regulation, which includes pump station equipment parameters, water supply pipe network topology, historical fire cases, and fire water supply experience; A verification module for verifying the rationality of the water supply regulation strategy generated by the artificial intelligence model based on the knowledge graph for fire pump station water supply regulation; An execution module, configured to execute the water supply regulation strategy when the verification result indicates that the strategy reliability is greater than or equal to the reliability threshold; An optimization module, configured to, when the verification result indicates that the strategy reliability is less than the reliability threshold, based on the reasons for verification failure, optimize and adjust the water supply regulation strategy and then verify it again until the verification passes or the maximum number of verifications is reached.

10. A method for regulating and controlling the water supply of a fire pump station based on artificial intelligence, characterized in that, including: S101: Obtain the real-time water supply parameters and environmental status information of the fire pump station; S102: Based on a pre-trained artificial intelligence model, generate an optimal water supply regulation strategy according to the real-time water supply parameters and environmental status information; S103: Execute the optimal water supply regulation strategy to achieve intelligent regulation and control of the water supply of the fire pump station.

Images