A combustible, toxic gas monitoring method and system

Abstract

The application provides a combustible and toxic gas monitoring method and system, the method comprising: dynamically adjusting the sensor density based on historical leakage risk weights, collecting multi-modal environmental data and fusing and correcting to generate an environmental data set; constructing a gas diffusion model based on the environmental data set, predicting future concentration distribution in combination with environmental variables and identifying high-risk areas; for the high-risk areas, designing an optimization objective function with the optimization objective of minimizing gas concentration distribution and energy consumption, generating an optimal control strategy through the optimization objective function, adjusting temperature, wind speed and ventilation intensity to suppress gas diffusion; and executing the optimal control strategy and feeding back the optimization in real time to ensure the balance between system robustness and energy consumption. The application can dynamically optimize the monitoring and control process of gas leakage, realize more accurate safety management, and effectively improve the safety and energy efficiency of industrial sites.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of gas monitoring, and particularly relates to a combustible and toxic gas monitoring method and system. BACKGROUND

[0002] In industrial scenarios such as petrochemical industry, energy storage, laboratory and underground pipe gallery, leakage of combustible and toxic gases is a serious safety hazard, which may cause fire, explosion, poisoning and other major accidents. Currently, fixed gas sensor networks are mainly used for leakage monitoring in industrial sites. These sensors are distributed at key points (such as around storage tanks, pipe interfaces, ventilation openings, etc.), which can detect the concentration of target gases in the air in real time and trigger an alarm when the safety threshold is exceeded. However, due to the influence of environmental factors such as wind speed, temperature and humidity, obstacles, etc., the diffusion path of the leaked gas after leakage is greatly affected, and the leaked gas may bypass the sensor arrangement area, resulting in the existence of monitoring blind area, so that the system cannot detect the leakage in time. In addition, the existing system usually relies on fixed threshold to trigger alarm, and the alarm will only be triggered when the detected gas concentration exceeds the set value, which cannot predict the diffusion trend of the gas in advance, resulting in response lag and increasing the risk of accidents. For the control of leaked gas, the commonly used method is to start mechanical ventilation equipment to increase air flow, or to dilute the gas concentration through a spraying system, but this passive control strategy often lacks pertinence and cannot accurately match the actual situation of leakage, and in some environments it may even accelerate the diffusion of the gas and expand the dangerous range, while the continuous operation of the ventilation equipment also causes high energy consumption.

[0003] Therefore, the existing technology still has the problems of monitoring blind area, response lag, and extensive control strategy and high energy consumption in gas leakage monitoring and control, and there is an urgent need for a more intelligent, accurate and efficient solution to realize real-time prediction and accurate suppression of leaked gas. SUMMARY

[0004] The purpose of the present application is to provide a combustible and toxic gas monitoring method and system, which can predict the diffusion trend of the gas by analyzing environmental data in real time, and intelligently adjust environmental parameters based on the diffusion situation to achieve more accurate and efficient leakage suppression.

[0005] In order to achieve the above purpose, in the first aspect of the present application, a combustible and toxic gas monitoring method is provided, which comprises the following steps:

[0006] Based on the historical leakage risk weight, the sensor density is dynamically adjusted, the multi-modal environmental data is collected and fused and corrected to generate an environmental data set;

[0007] A gas diffusion model is constructed based on the environmental data set, and a future concentration distribution is predicted and a high-risk area is identified in combination with environmental variables; wherein the determination rule of the high-risk area is based on the future gas concentration and the lower explosive limit;

[0008] For the high-risk area, an optimization objective function is designed with the optimization objectives of minimizing the gas concentration distribution and energy consumption, and an optimal control strategy is generated by the optimization objective function to adjust the temperature, wind speed and ventilation intensity to suppress gas diffusion;

[0009] The optimal control strategy is executed and real-time feedback optimization is performed to ensure system robustness and energy consumption balance.

[0010] Preferably, the historical leakage risk weight is used to dynamically adjust the sensor density, and the specific steps are as follows:

[0011] Collect environmental factors, including: historical gas leakage records, wind speed and direction changes, and obstacle positions;

[0012] Based on the environmental factors, the leakage risk weight is obtained through weighted analysis.

[0013] Preferably, the multi-modal environmental data is collected and fused and corrected to generate an environmental data set, and the specific steps are as follows:

[0014] Collect sensor data;

[0015] In combination with the spatio-temporal correlation, the abnormal values are detected and corrected;

[0016] The corrected data is subjected to multi-index weighted comprehensive fusion analysis to obtain fused environmental data;

[0017] The fused environmental data is subjected to a dynamic weighted average correction operation based on historical trends to generate an environmental data set;

[0018] If the measurement value of a certain sensor deviates from the average value of adjacent sensors by more than a set threshold, it is considered abnormal and the data is excluded or corrected;

[0019] The dynamic weighted average correction operation based on historical trends is as follows:

[0020] When the wind speed is maximum, the weight is minimum, the influence of historical data is enhanced, and the error accumulation caused by sensor lag response is prevented;

[0021] When the wind speed is minimum, the weight is maximum, the influence of the current measurement value is enhanced, and the error caused by historical data is reduced.

[0022] Preferably, the gas diffusion model is constructed as follows:

[0023] The environmental state correction term is determined by weighting and according to the wind speed and direction changes and the position of the obstacle;

[0024] An initial gas diffusion model is constructed in combination with the fluid mechanics characteristics;

[0025] The initial gas diffusion model is corrected based on the environmental state correction term to generate a gas diffusion model and obtain a gas diffusion rate; wherein the gas diffusion model includes the wind speed at position , the temperature at position , and the gas pressure at position .

[0026] Preferably, the future concentration distribution is predicted and the high-risk area is identified in combination with the environmental variables, and the specific steps include:

[0027] The gas diffusion rate is obtained, and the gas concentration at a future time is calculated based on the current gas distribution in combination with the environmental state correction term;

[0028] The gas concentration at the future time is subjected to gas leakage risk area determination analysis to obtain a high-risk area;

[0029] The gas leakage risk area determination analysis is specifically:

[0030] The spatial area where the gas concentration reaches a dangerous threshold is screened out through the proportional relationship of the predicted gas concentration at the future time and the lower explosive limit; wherein the proportional relationship is adjusted by a safety factor;

[0031] When the predicted gas concentration at the future time at a certain area exceeds , , which is the lower explosive limit of the target gas, it is determined that the area is a high-risk area.

[0032] Preferably, the optimization objective function is:

[0033]

[0034] wherein, is an adaptive control strategy, including temperature, wind speed, and ventilation adjustment; is the predicted future gas concentration distribution, with units of ppm; is a safety concentration threshold to ensure that the gas concentration is much lower than the explosion limit; is an energy consumption weight factor for balancing the control effect and energy consumption; is the total energy consumption of the control strategy execution, including temperature adjustment energy consumption , wind speed adjustment energy consumption , and ventilation energy consumption ;

[0035] wherein, is calculated as follows:

[0036]

[0037] wherein, is a coefficient for controlling energy consumption, determined by the energy efficiency parameters of the industrial system; is the current temperature, wind speed, and ventilation intensity; is the optimized control variable.

[0038] Preferably, the optimal control strategy is generated by optimizing the objective function, adjusting the temperature, wind speed, and ventilation intensity to suppress gas diffusion, specifically including:

[0039] For local temperature, in high-risk areas, reduce the temperature to reduce the gas evaporation rate, and generate a temperature reduction strategy based on temperature gradient correction;

[0040] For wind speed guidance, in high-risk areas, adjust the wind speed to control the direction of gas diffusion, and generate a wind speed guidance strategy based on wind speed gradient correction;

[0041] For ventilation strategy, in high-risk areas, adjust the local ventilation intensity to accelerate gas dilution, and generate a ventilation optimization strategy based on ventilation intensity gradient correction;

[0042] According to the temperature reduction strategy, wind speed guidance strategy, and ventilation optimization strategy, the optimal control strategy is generated.

[0043] Preferably, the optimal control strategy is executed and real-time feedback optimization is performed to ensure system robustness and energy consumption balance, specifically including:

[0044] The optimal control strategy is executed, and an adaptive execution correction term is introduced for correction to generate the current executed control parameter;

[0045] The environmental data is re-collected, and the new gas concentration is obtained;

[0046] Based on the re-collected environmental data and the new gas concentration, an adaptive weight adjustment mechanism is adopted to dynamically optimize the control strategy according to the control effect;

[0047] wherein, the adaptive weight adjustment mechanism includes the current executed control parameter, gas concentration change, and noise correction term to ensure the balance of control effect and energy efficiency; the noise correction term is used to prevent instability caused by sudden adjustment.

[0048] Preferably, the adaptive execution correction is based on the current executed control parameter, combined with the deviation of historical execution state, and weighted adjustment is performed through the execution correction coefficient.

[0049] In another aspect of the present application, a combustible and toxic gas monitoring system is provided, the system comprising:

[0050] A dynamic sensing module for dynamically adjusting sensor density based on historical leakage risk weights, collecting multi-modal environmental data and fusing corrections to generate an environmental dataset;

[0051] A diffusion prediction module for constructing a gas diffusion model based on the environmental dataset, predicting future concentration distribution in combination with environmental variables and identifying high-risk areas; wherein the determination rule of the high-risk areas is based on future gas concentration and lower explosive limit;

[0052] An intelligent control module for designing an optimization objective function with the optimization objective of minimizing gas concentration distribution and energy consumption for high-risk areas, generating an optimal control strategy through the optimization objective function, and adjusting temperature, wind speed and ventilation intensity to suppress gas diffusion;

[0053] An execution feedback module for executing the optimal control strategy and feeding back optimization in real time to ensure system robustness and energy consumption balance.

[0054] The beneficial technical effects of the present application are at least as follows:

[0055] In view of the deficiencies of the prior art, the present application proposes an intelligent adaptive control system based on gas diffusion prediction, which analyzes environmental data in real time, predicts gas diffusion trends, and intelligently adjusts environmental parameters based on diffusion conditions to achieve more accurate and efficient leakage suppression. First, the present application uses a dynamic gas diffusion prediction method to analyze various environmental variables (such as wind speed, temperature, air pressure, etc.) in real time, calculate the diffusion path of the leaked gas, and thus trigger an early warning when the gas concentration has not yet reached a dangerous level, improving monitoring coverage and reducing response lag problems. Secondly, the present application uses an intelligent adaptive control strategy to automatically adjust the environmental parameters (such as temperature, air flow direction, ventilation intensity, etc.) of the local area based on the gas diffusion prediction results, accurately suppress gas leakage, avoid the high energy consumption problem caused by relying solely on mechanical ventilation, and prevent unreasonable air flow from exacerbating gas diffusion. Compared with the traditional fixed monitoring + mechanical ventilation method, the present application can dynamically optimize the monitoring and control process of gas leakage, achieve more accurate safety management, and effectively improve the safety and energy efficiency of industrial sites. BRIEF DESCRIPTION OF DRAWINGS

[0056] The present application is further illustrated by the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present application. For ordinary skilled in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0057] Figure 1A combustible and toxic gas monitoring method flowchart is disclosed in the embodiments of the present application. DETAILED DESCRIPTION

[0058] Embodiments of the present application are described in detail below with reference to examples illustrated in the accompanying drawings, in which the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only for explanation of the present application, and cannot be understood as limiting the present application.

[0059] Embodiment one

[0060] As shown in the figure, the combustible and toxic gas monitoring method provided by the embodiments of the present application comprises the following steps: Figure 1

[0061] S1, dynamically adjusting the sensor density based on the historical leakage risk weight, collecting multi-modal environment data and fusing and correcting to generate an environment data set.

[0062] Specifically, the purpose of this step is to establish a high-precision environment data set to ensure that the gas diffusion prediction (step 2) is based on high-quality input data, thereby improving the accuracy of leakage monitoring and adaptive control.

[0063] Preferably, in an industrial environment, the gas leakage points are unevenly distributed, and the traditional regular arrangement method may cause the monitoring density in some areas to be too low, forming a blind area, and the monitoring density in some areas to be too high, increasing the redundant cost. Therefore, the present application proposes a dynamic sensor optimization arrangement strategy based on leakage risk, which adaptively increases the sensor density in high-risk areas to improve the monitoring coverage.

[0064] In order to optimize the distribution of sensors, the present application defines a leakage risk weight which is calculated in combination with historical gas leakage records, wind speed and direction changes, obstacle positions and other environmental factors. The calculation is as follows:

[0065]

[0066] Wherein:

[0067] : historical gas concentration, a larger value means high leakage risk;

[0068] : wind speed gradient, areas with large wind speed changes are prone to form high-concentration gas clusters;

[0069] : obstacle influence factor, the area close to the obstacle is not easy to diffuse the leaked gas, and the sensor density needs to be increased;

[0070] ​ : weight coefficient, determined based on experiments.

[0071] After optimization, the sensor density is dynamically adjusted to be denser in high-risk areas, ensuring comprehensive monitoring, reducing blind spots, and improving data quality.

[0072] Preferably, industrial sensors may have noise interference, measurement errors, equipment failures and other problems in actual operation. Direct use of raw data may lead to false diffusion prediction. Therefore, this step uses a multi-sensor data fusion algorithm to detect and correct abnormal values based on spatial and temporal correlation.

[0073] Core idea: Spatial consistency correction: the sensor measurement value should be consistent with the measurement value of its adjacent sensors, otherwise there may be errors. Environmental factor compensation: gas diffusion is affected by wind speed and temperature, these factors should be considered during data fusion to improve correction accuracy. Dynamic credibility weighting: if a sensor has a history of drift or has more abnormal data, its current data weight is reduced to reduce its interference with the overall data.

[0074] The fusion calculation is as follows:

[0075]

[0076] Where:

[0077] : sensor adjacent sensor set of the sensor;

[0078] : weight of adjacent sensor, dynamically adjusted based on measurement stability;

[0079] : environmental compensation factor, considering the influence of wind speed and temperature on gas diffusion, to prevent individual sensor measurement anomalies from affecting global data.

[0080] In addition, if the measurement value of a sensor deviates from the mean value of adjacent sensors by more than a certain threshold, it is considered abnormal and the data is excluded or corrected to avoid the influence of false data on diffusion prediction.

[0081] Preferably, in an industrial environment, sensors may have temporary data loss due to faults, signal interference, data loss, etc. If missing data is used directly, it will affect the stability of gas diffusion prediction, so this step introduces a time series correction mechanism to estimate missing data based on historical trends to improve system robustness. The basic method of data correction is dynamic weighted average based on historical trends:

[0082]

[0083] Where, Dynamic adjustment by environmental parameters (such as wind speed):

[0084] When the wind speed is large, Take the smaller value, enhance the influence of historical data, prevent error accumulation caused by sensor lag response;

[0085] When the wind speed is small, Take the larger value, enhance the influence of the current measurement value, to reduce the error caused by historical data.

[0086] Finally, all data after sensor optimization arrangement, anomaly detection and correction, time series completion, get the modified environmental data set:

[0087]

[0088] S2, based on the environmental data set, build a gas diffusion model, combine environmental variables to predict future concentration distribution and identify high-risk areas; wherein the determination rule of the high-risk area is based on the future gas concentration and the lower explosive limit.

[0089] Specifically, the goal of this step is to predict the future gas concentration distribution based on the high-quality environmental data generated in step 1, and identify high-risk areas to support intelligent control strategy calculation. Gas leakage in industrial environments is affected by complex factors such as wind speed, temperature and humidity, air pressure, obstacles, etc., with spatial and temporal non-uniformity and strong dynamic change characteristics. Traditional fixed threshold monitoring methods cannot predict leakage trends in advance, but can only trigger alarms when gas concentration exceeds the set value, resulting in delayed response. Therefore, this step builds a real-time gas diffusion model, adjusts the prediction model based on environmental variables, and evaluates potential dangerous areas to ensure that the control system can take measures before danger occurs.

[0090] Preferably, the gas diffusion model is constructed: the diffusion behavior of the gas is affected by environmental variables, among which the most important influencing factors are wind speed , temperature and air pressure . In order to accurately model gas diffusion, this step introduces the gas diffusion rate , which combines fluid mechanics characteristics and introduces a dynamic correction term based on environmental state:

[0091]

[0092] Where:

[0093] : wind speed at position , unit m / s;

[0094] : wind speed at position Temperature at that location, in °C;

[0095] :Location The air pressure at that location, in hPa;

[0096] : Used to adjust the weights of the effects of different environmental factors on the diffusion rate, optimized from experimental data;

[0097] : Environmental condition correction term, used to correct diffusion errors caused by factors such as obstacles and environmental turbulence.

[0098] The calculation is as follows:

[0099]

[0100] in:

[0101] Obstacle impact factor: diffusion is limited in areas near obstacles;

[0102] Wind speed gradient: Areas with drastic changes in wind speed are prone to forming high-concentration air masses;

[0103] When there is a large temperature gradient or temperature difference, the gas diffusion behavior becomes more complex.

[0104] The parameters for adjusting the weights of the correction terms are determined experimentally.

[0105] The model is characterized by dynamically adjusting the diffusion rate to adapt to different environmental conditions, making the predictions more accurate.

[0106] Preferably, in obtaining the gas diffusion rate Subsequently, the present invention is based on the current gas distribution. Calculate future moments gas concentration Traditional gas diffusion equations are typically based on simple diffusivity calculations, while this step further incorporates an environmental impact term to enhance the model's adaptability.

[0107]

[0108] in:

[0109] Current location The current gas concentration at the location, in ppm;

[0110] : Gas concentration gradient, indicating the direction of diffusion;

[0111] : predicted time step, unit s;

[0112] : external environment disturbance term, simulating unstable factors such as turbulence, air flow fluctuation, etc.

[0113] Calculation method:

[0114]

[0115] : wind speed change rate, when the air flow changes sharply, the gas concentration fluctuation is intensified;

[0116] : air pressure change rate, unstable air pressure may cause abnormal gas flow;

[0117] : obstacle influence factor, high concentration gas may accumulate near the obstacle;

[0118] : adjustment weight, used to balance the influence of each factor.

[0119] Compared with the traditional diffusion equation, the model increases the influence factors of meteorological environment, so that the prediction is more in line with the actual leakage scene.

[0120] Preferably, in order to ensure that the monitoring system can discover the dangerous area in advance, the present application defines a high-risk area , the determination rule of which is based on the future gas concentration and the lower explosive limit (LEL), and the gas leakage danger area determination analysis:

[0121]

[0122] Wherein:

[0123] : lower explosive limit of target gas, unit ppm;

[0124] : safety factor, usually taken , indicating that measures are taken before reaching the lower explosive limit.

[0125] When the predicted gas concentration at a certain area exceeds , the area is determined as a high-risk area, and output to step 3 (intelligent adaptive control strategy calculation) for calculating the optimal control scheme.

[0126] S3. For high-risk areas, design an optimization objective function with the goal of minimizing gas concentration distribution and energy consumption. Generate the optimal control strategy by optimizing the objective function, and adjust the temperature, wind speed and ventilation intensity to suppress gas diffusion.

[0127] Specifically, the core objective of this step is to predict the future gas concentration distribution based on the prediction made in step 2. and high-risk areas Calculate the optimal adaptive control strategy This approach enables precise regulation of gas diffusion and ensures that control measures can dynamically adapt to complex industrial environments. Gas leaks in industrial settings often result from high temperatures, complex airflows, and locally enclosed environments, leading to the accumulation of high-concentration gas clouds. Traditional ventilation, spraying, or cooling methods are often insufficient for precise control and require significant energy consumption to achieve the desired effect. Therefore, the goal of this step is to develop an intelligent optimization control strategy that allows the control system to adapt to different operating conditions, dynamically adjusting temperature, wind speed, and ventilation intensity to achieve optimal leak suppression with minimal energy consumption.

[0128] Preferably, the essential objective of gas leakage control is to reduce gas concentration while minimizing the energy consumption of the control strategy. Therefore, this invention designs an optimization objective function that enables the system to achieve a safe gas concentration with minimal resource consumption:

[0129]

[0130] in:

[0131] Adaptive control strategies, including temperature, wind speed, and ventilation adjustments;

[0132] : Predicted future gas concentration distribution, in ppm;

[0133] : The safe concentration threshold is usually set to This is to ensure that the gas concentration is well below the explosion limit;

[0134] Energy consumption weighting factor, used to balance control effectiveness and energy consumption;

[0135] Total energy consumption for implementing the control strategy, including energy consumption for temperature regulation. Energy consumption for wind speed adjustment and ventilation energy consumption .

[0136] in, The calculation is as follows:

[0137]

[0138] : Coefficient of energy consumption, determined by industrial system energy efficiency parameters;

[0139] : Current temperature, wind speed, ventilation intensity;

[0140] : Optimized control variable.

[0141] This objective function ensures that the control strategy can both reduce gas concentration and avoid unnecessary energy waste.

[0142] Preferably, calculate the local temperature adjustment strategy: the volatility of gas is greatly affected by temperature, especially in high-temperature industrial environments (such as chemical plants, tank farms), high temperature can exacerbate gas evaporation and increase the risk of leakage. Therefore, in high-risk areas , the temperature needs to be reduced to reduce the evaporation rate of gas:

[0143]

[0144] Where:

[0145] : Temperature adjustment coefficient, determines the temperature reduction amplitude;

[0146] : Temperature stability correction term, prevents large temperature fluctuations affecting production safety.

[0147] The calculation is as follows:

[0148]

[0149] Where:

[0150] : Temperature gradient, high-temperature areas require more cooling;

[0151] : Adjustment weight, makes the temperature reduction amplitude adaptive to environmental changes.

[0152] This strategy ensures that the temperature is appropriately reduced in high-risk areas, thereby reducing the evaporation of flammable gas.

[0153] Preferably, calculate the wind speed guidance strategy: gas diffusion is mainly affected by wind speed, reasonable adjustment of wind speed can control the direction of gas diffusion, making the gas away from high-risk areas. The wind speed adjustment strategy is calculated as follows:

[0154]

[0155] Where:

[0156] : Wind speed adjustment coefficient, to adapt wind speed changes to gas concentration changes;

[0157] : Wind speed stability correction term, to prevent excessive wind speed fluctuations affecting equipment operation.

[0158] The calculation is as follows:

[0159]

[0160] Where:

[0161] : Wind speed gradient, no further increase of wind speed is needed in strong wind areas;

[0162] : Adjustment coefficient, to ensure smooth wind speed adjustment.

[0163] The role of this strategy is to increase wind speed in high-risk areas, guiding gas to spread to safe areas, thereby reducing the accumulation of local high-concentration gas.

[0164] Preferably, the ventilation optimization strategy is calculated: in some cases, temperature and wind speed adjustment alone may not be effective in controlling gas concentration, so it is necessary to adjust the local ventilation intensity to accelerate gas dilution:

[0165]

[0166] Where:

[0167] : Ventilation adjustment coefficient, to control the adjustment range of ventilation;

[0168] : Ventilation stability correction term, to prevent sudden changes in wind power.

[0169] The calculation is as follows:

[0170]

[0171] Where:

[0172] : Ventilation intensity gradient, to optimize the allocation of ventilation resources;

[0173] : Adjustment parameter, to ensure that ventilation adjustment does not affect the overall air flow stability.

[0174] This strategy ensures appropriate increase of ventilation in high-risk areas to accelerate dilution of leaked gas.

[0175] S4, execute the optimal control strategy and real-time feedback optimization to ensure system robustness and energy balance.

[0176] Specifically, the core goal of this step is to execute intelligent regulation operations based on the optimal control strategy calculated in step 3 , and to make the system self-adaptive by real-time monitoring and feedback optimization of the control strategy. Gas leakage control in industrial environments is not a one-time decision problem, but a dynamic optimization process. Due to the influence of uncertain factors such as gas flow changes, temperature fluctuations, and gas source changes, the control strategy needs to be continuously adjusted to adapt to new working conditions. Therefore, the core task of this step is to execute the control strategy and build a closed-loop feedback mechanism to enable the control system to self-learn and optimize, improving long-term stability.

[0177] Preferably, based on the control strategy calculated in step 3 , this step executes temperature regulation, wind speed guidance, and ventilation optimization through an industrial control system:

[0178] Temperature regulation execution: adjust the temperature control equipment in high-risk areas to make the actual temperature close to the optimal target ;

[0179] Wind speed regulation execution: adjust the local air supply system to make the actual wind speed close to the optimal target ;

[0180] Ventilation optimization execution: adjust the regional ventilation equipment to make the actual ventilation intensity close to .

[0181] During execution, there are problems such as device response delay, external environmental interference, and energy consumption limitations, so this invention introduces a self-adaptive execution correction term:

[0182]

[0183] Where:

[0184] : the current control parameter being executed;

[0185] : the control parameter executed at the last time;

[0186] : execution correction coefficient, used to smooth control execution and prevent sudden changes.

[0187] This strategy ensures the stability of control execution and avoids system overshoot or oscillation.

[0188] Preferably, to evaluate the actual effect of the control strategy, it is necessary to re-collect the environmental data after the execution of the control strategy and calculate the new gas concentration .

[0189] During the monitoring process, the following indicators need to be focused on:

[0190] Gas concentration change: calculate the change rate of relative to ;

[0191] Control response time: calculate the time required for the environmental variable to reach a stable state after the execution of ;

[0192] Device energy consumption: calculate the total energy consumed by the execution of the control .

[0193] New environmental data is calculated as follows:

[0194]

[0195] This data will be input into Step 2 (Gas Diffusion Prediction) for optimizing the next round of control strategy.

[0196] Preferably, due to the constant changes in air flow and temperature in industrial environments, the control system needs to adjust the optimization strategy according to real-time feedback. The present invention uses an adaptive weight adjustment mechanism to dynamically optimize the control strategy according to the control effect:

[0197]

[0198] where:

[0199] : adaptive weight adjustment coefficient, determines the strategy update amplitude;

[0200] : noise correction term, prevents instability caused by sudden adjustment.

[0201] is calculated as follows:

[0202]

[0203] where:

[0204] : current gas concentration gradient;

[0205] ​: Smooth adjustment coefficient, prevent error amplification.

[0206] The feedback mechanism ensures that the control system can adaptively adjust the control strategy at the next moment according to the real-time monitoring results.

[0207] Preferably, in order to prevent the control system from failing due to sudden environmental changes, the present application introduces a stability constraint condition to make the optimization process robust:

[0208]

[0209] Wherein:

[0210] : Allowable maximum adjustment amplitude, prevent adjustment too fast leading to system instability.

[0211] The constraint condition ensures that the control system does not fluctuate sharply during continuous optimization, ensuring stable operation of the entire system.

[0212] Example two

[0213] In another embodiment of the present application, a combustible and toxic gas monitoring system is disclosed, the system comprising:

[0214] Dynamic perception module, for dynamically adjusting sensor density based on historical leakage risk weight, collecting multi-modal environmental data and fusing correction to generate environmental data set;

[0215] Diffusion prediction module, for constructing gas diffusion model based on environmental data set, combining environmental variables to predict future concentration distribution and identify high-risk areas; wherein the determination rule of the high-risk area is based on future gas concentration and lower explosive limit;

[0216] Intelligent control module, for designing optimization objective function aiming at high-risk areas, with the optimization objective of minimizing gas concentration distribution and energy consumption, generating optimal control strategy through optimization objective function, adjusting temperature, wind speed and ventilation intensity to suppress gas diffusion;

[0217] Execution feedback module, for executing optimal control strategy and feeding back optimization in real time, ensuring system robustness and energy consumption balance.

[0218] The above describes certain embodiments of the present application, other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be executed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily have to be implemented in the specific order shown or in a continuous order to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0219] The systems, apparatuses, modules, or units illustrated by the above embodiments can be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0220] For the convenience of description, the above apparatuses are described in various units by functions respectively. Of course, the functions of the units can be implemented in one or more software and / or hardware in the implementation of the present specification.

[0221] Those skilled in the art should understand that the embodiments of the present specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) including computer-usable program code.

[0222] The present specification is described with reference to flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow or flows and / or block or blocks.

[0223] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction apparatus that implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow or flows and / or block or blocks.

[0224] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0225] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0226] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the computer stores information about an operating system, application software, and / or the like. Memory is an example of computer readable media.

[0227] Computer readable media includes permanent and non-permanent, moveable and non- moveable media that can be implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that is accessible to a computing device. According to the definition provided herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0228] It is also important to note that the terms "comprises", "comprising", or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0229] ​​The specification can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0230] The various embodiments in the specification are described in progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.

[0231] Finally, it should be noted that: the lithium battery pack chip equalization control platform disclosed by the embodiments of the present application is only the preferred embodiment of the present application, and is used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting combustible and toxic gases, characterized in that, The method includes the following steps: The sensor density is dynamically adjusted based on historical leakage risk weights, multimodal environmental data is collected and fused for correction, and an environmental dataset is generated. A gas diffusion model is constructed based on an environmental dataset, and environmental variables are combined to predict future concentration distribution and identify high-risk areas; wherein, the criteria for determining high-risk areas are based on future gas concentration and lower explosive limit. For high-risk areas, an optimization objective function is designed with the goal of minimizing gas concentration distribution and energy consumption. The optimal control strategy is generated by optimizing the objective function to adjust temperature, wind speed and ventilation intensity to suppress gas diffusion. Execute the optimal control strategy and provide real-time feedback for optimization to ensure a balance between system robustness and energy consumption; The optimization objective function is: Among them, S t ={T * W * V * The adaptive control strategy includes temperature, wind speed, and ventilation adjustments. The predicted future gas concentration distribution is expressed in ppm; C safe The safe concentration threshold is used to ensure that the gas concentration is far below the explosion limit; λ is the energy consumption weighting factor used to balance the control effect and energy consumption; E(S t The total energy consumption for executing the control strategy includes temperature regulation energy consumption E. T Wind speed adjustment energy consumption E W And ventilation energy consumption E V ; Among them, E(S) t The calculation is as follows: Where k1, k2, and k3 are energy consumption control coefficients, determined by the energy efficiency parameters of the industrial system; T t (x,y), W t (x,y),V t (x,y) represents the current temperature, wind speed, and ventilation intensity; T * (x,y), W * (x,y),V * (x,y) are the optimized control variables; The process of generating an optimal control strategy by optimizing the objective function, and adjusting temperature, wind speed, and ventilation intensity to suppress gas diffusion, specifically includes: For localized temperatures, in high-risk areas, the temperature is reduced to decrease the gas evaporation rate, and a temperature reduction strategy is generated based on temperature gradient correction. For wind speed guidance, in high-risk areas, wind speed is adjusted to control the direction of gas diffusion, and a wind speed guidance strategy is generated based on wind speed gradient correction. Regarding ventilation strategies, in high-risk areas, the local ventilation intensity is adjusted to accelerate gas dilution, and a ventilation optimization strategy is generated based on the ventilation intensity gradient correction. The optimal control strategy is generated based on the temperature reduction strategy, wind speed guidance strategy, and ventilation optimization strategy.

2. The method for monitoring combustible and toxic gases according to claim 1, characterized in that, The specific steps for dynamically adjusting sensor density based on historical leakage risk weights are as follows: Collect environmental factors, including: historical gas leak records, wind speed and direction changes, and obstacle locations; Based on environmental factors, leakage risk weights are obtained through weighted analysis.

3. The method for monitoring combustible and toxic gases according to claim 2, characterized in that, The specific steps for collecting, fusing, and correcting multimodal environmental data to generate an environmental dataset are as follows: Collect sensor data; By combining spatiotemporal correlation, outliers are detected and corrected; The corrected data is subjected to multi-indicator weighted comprehensive fusion analysis to obtain fused environmental data; The fused environmental data is corrected by a dynamic weighted average based on historical trends to generate an environmental dataset. If the measured value of a certain sensor deviates from the average value of the neighboring sensors by more than a set threshold, it is considered abnormal, and the data is removed or corrected. Specifically, the correction operation for the dynamic weighted average based on historical trends is as follows: When the wind speed is at its maximum, the weight is set to the minimum value to enhance the influence of historical data and prevent error accumulation caused by sensor lag response. When the wind speed is at its minimum, the weight is set to its maximum value to enhance the influence of the current measurement and reduce errors caused by historical data.

4. The method for monitoring combustible and toxic gases according to claim 1, characterized in that, The gas diffusion model is constructed as follows: Based on changes in wind speed and direction, and the location of obstacles, environmental condition correction terms are determined through weighted summation. An initial gas diffusion model was constructed by combining fluid dynamics characteristics; The initial gas diffusion model is modified based on the environmental state correction term to generate a gas diffusion model and obtain the gas diffusion rate; wherein, the gas diffusion model includes the wind speed at position (x,y), the temperature at position (x,y), and the air pressure at position (x,y).

5. The method for monitoring combustible and toxic gases according to claim 4, characterized in that, The specific steps for predicting future concentration distribution and identifying high-risk areas by combining environmental variables include: Obtain the gas diffusion rate, and calculate the gas concentration at future times based on the current gas distribution and environmental state correction terms; The gas concentration at the future time is used to determine the gas leakage hazard area, and high-risk areas are obtained; Specifically, the analysis for determining the hazardous area of ​​gas leakage includes: By predicting the ratio of gas concentration to the lower explosive limit at future moments, spatial regions where gas concentration reaches a dangerous threshold are screened out; wherein, the ratio is adjusted by a safety factor. Specifically, if the predicted gas concentration at a certain region (x,y) at a future time exceeds 0.8×LEL, where LEL is the lower explosive limit of the target gas, then the region is determined to be a high-risk region.

6. The method for monitoring combustible and toxic gases according to claim 1, characterized in that, The execution of the optimal control strategy and real-time feedback optimization, ensuring a balance between system robustness and energy consumption, specifically includes: The optimal control strategy is executed, and an adaptive execution correction term is introduced to make corrections, generating the control parameters for the current execution. Recollect environmental data and obtain new gas concentrations; Based on the newly acquired environmental data and the new gas concentration, an adaptive weight adjustment mechanism is adopted to dynamically optimize the control strategy according to the control effect. The adaptive weight adjustment mechanism includes the currently executed control parameters, gas concentration changes, and noise correction terms to ensure a balance between control effectiveness and energy efficiency; the noise correction term is used to prevent instability caused by abrupt adjustments.

7. The method for monitoring combustible and toxic gases according to claim 6, characterized in that, The adaptive execution correction is based on the control parameters of the current execution, combined with the deviation of the historical execution state, and is weighted and adjusted by the execution correction coefficient.

8. A combustible and toxic gas monitoring system, characterized in that, The system includes: The dynamic sensing module is used to dynamically adjust the sensor density based on historical leakage risk weights, collect multimodal environmental data and fuse and correct it to generate an environmental dataset; The diffusion prediction module is used to build a gas diffusion model based on an environmental dataset, combine environmental variables to predict future concentration distribution, and identify high-risk areas; wherein, the criteria for determining high-risk areas are based on future gas concentrations and lower explosive limits. The intelligent control module is used to design an optimization objective function for high-risk areas with the goal of minimizing gas concentration distribution and energy consumption. The optimal control strategy is generated by optimizing the objective function to adjust the temperature, wind speed and ventilation intensity to suppress gas diffusion. The execution feedback module is used to execute the optimal control strategy and provide real-time feedback for optimization, ensuring a balance between system robustness and energy consumption. The optimization objective function is: Among them, S t ={T * W * V * The adaptive control strategy includes temperature, wind speed, and ventilation adjustments. The predicted future gas concentration distribution is expressed in ppm; C safe The safe concentration threshold is used to ensure that the gas concentration is far below the explosion limit; λ is the energy consumption weighting factor used to balance the control effect and energy consumption; E(S t The total energy consumption for executing the control strategy includes temperature regulation energy consumption E. T Wind speed adjustment energy consumption E W And ventilation energy consumption E V ; Among them, E(S) t The calculation is as follows: Where k1, k2, and k3 are energy consumption control coefficients, determined by the energy efficiency parameters of the industrial system; T t (x,y), W t (x,y),V t (x,y) represents the current temperature, wind speed, and ventilation intensity; T * (x,y), W * (x,y),V * (x,y) are the optimized control variables; The process of generating an optimal control strategy by optimizing the objective function, and adjusting temperature, wind speed, and ventilation intensity to suppress gas diffusion, specifically includes: For localized temperatures, in high-risk areas, the temperature is reduced to decrease the gas evaporation rate, and a temperature reduction strategy is generated based on temperature gradient correction. For wind speed guidance, in high-risk areas, wind speed is adjusted to control the direction of gas diffusion, and a wind speed guidance strategy is generated based on wind speed gradient correction. Regarding ventilation strategies, in high-risk areas, the local ventilation intensity is adjusted to accelerate gas dilution, and a ventilation optimization strategy is generated based on the ventilation intensity gradient correction. The optimal control strategy is generated based on the temperature reduction strategy, wind speed guidance strategy, and ventilation optimization strategy.

Images