Air pressure fluctuation balancing and pressure stabilizing method and system in buffer tank

Abstract

The invention provides an air pressure fluctuation balancing and pressure stabilizing method and system in a buffer tank. Wherein the pressure sensor array is used for monitoring the air pressure in the buffer tank in real time, preprocessing collected data, removing noise and enhancing the signal definition, and an air pressure adjustment starting signal is generated when air pressure fluctuation exceeds a threshold value; according to the air pressure regulation starting signal, optimizing a gas supplementing or discharging rate by using an adaptive neural fuzzy inference system and a nonlinear control algorithm of particle swarm optimization, and generating a preliminary air pressure regulation strategy; on the basis of the initial air pressure adjusting strategy, a multi-target genetic algorithm is adopted to automatically adjust the air supplementing or discharging rate, and a final air pressure adjusting scheme is generated; and based on the final air pressure regulation scheme, analyzing data of a pressure sensor in the buffer tank, and continuously optimizing an air pressure regulation strategy. According to the technical scheme provided by the invention, the air pressure can be accurately adjusted.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of buffer tanks, and in particular to a method and system for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank. Background Art

[0002] In the chemical, petroleum, and natural gas industries, buffer tanks are important storage and transmission equipment. The stability of the internal air pressure directly affects production safety, efficiency, and product quality. Especially under special working conditions such as high pressure, flammable and explosive, it is necessary to monitor and accurately control the air pressure in the tank in real time to prevent safety accidents and economic losses caused by air pressure fluctuations. Therefore, it is particularly important to develop a technical solution that can monitor, respond quickly, and accurately control air pressure fluctuations in real time.

[0003] At present, the common air pressure control method is mainly based on switch control with fixed thresholds. This method usually relies on a single or a small number of pressure sensors for monitoring, and uses simple logical judgment to decide whether to start gas replenishment or discharge operations. Although this method can meet basic air pressure control needs to a certain extent, it often exhibits problems such as slow response speed and low control accuracy when dealing with air pressure fluctuations under complex working conditions.

[0004] Traditional air pressure control methods have the following major defects: they are unable to capture small changes in air pressure in time, resulting in the inability to quickly suppress air pressure fluctuations; due to the lack of advanced signal processing technology and intelligent control algorithms, it is difficult to achieve precise regulation of air pressure, and over- or under-regulation is prone to occur; fixed thresholds and simple logical judgments cannot adapt to complex working conditions, especially when external conditions or gas components in the tank change, the control effect will be greatly reduced; in addition, these methods often ignore the optimization of system energy efficiency and equipment service life, resulting in energy waste and increased equipment loss. Summary of the invention

[0005] The embodiments of the present application provide a method and system for balancing air pressure fluctuations and stabilizing pressure in a buffer tank, so as to solve the problem that it is difficult to achieve accurate regulation of air pressure in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank, comprising:

[0007] Use a high-precision pressure sensor array to monitor the air pressure in the buffer tank in real time, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds the preset threshold;

[0008] According to the gas pressure regulation start signal, the gas replenishment or discharge rate is dynamically adjusted and optimized using an adaptive neural fuzzy inference system and a particle swarm optimization nonlinear control algorithm to ensure that the gas pressure fluctuation is effectively offset and generate a preliminary gas pressure regulation strategy;

[0009] When the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while taking into account the system energy efficiency ratio and equipment service life, to generate the final air pressure regulation plan;

[0010] Based on the final gas pressure regulation plan, the pressure sensor data at different positions of the buffer tank are analyzed. Combined with the external conditions and changes in the gas composition in the tank, the gas pressure regulation strategy is continuously optimized to ensure that the internal gas pressure of the buffer tank is within the ideal range. The key parameters of each adjustment are recorded to generate data support for performance evaluation and system improvement.

[0011] In a second aspect, an embodiment of the present application provides a system for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank, comprising:

[0012] A processing module is used to monitor the air pressure in the buffer tank in real time using a high-precision pressure sensor array, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds a preset threshold;

[0013] A regulating module, for dynamically adjusting and optimizing the gas replenishment or discharge rate according to the gas pressure regulation start signal using an adaptive neural fuzzy inference system and a nonlinear control algorithm of a particle swarm optimization, to ensure that the gas pressure fluctuation is effectively offset, and to generate a preliminary gas pressure regulation strategy;

[0014] The adjustment module, when the air pressure fluctuation tends to be flat and reaches a preset stable range, uses a multi-objective genetic algorithm to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability based on the preliminary air pressure adjustment strategy, while taking into account the system energy efficiency ratio and equipment service life, to generate a final air pressure adjustment plan;

[0015] The optimization module analyzes the pressure sensor data at different locations of the buffer tank based on the final gas pressure regulation plan, and continuously optimizes the gas pressure regulation strategy in combination with external conditions and changes in the gas composition in the tank to ensure that the gas pressure inside the buffer tank is within the ideal range. It also records the key parameters of each adjustment and generates data support for performance evaluation and system improvement.

[0016] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank as described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank as described in the first aspect.

[0018] In an embodiment of the present application, a high-precision pressure sensor array is used to monitor the air pressure in the buffer tank in real time, and the collected data is preprocessed to remove noise and enhance signal clarity. When it is detected that the air pressure fluctuation exceeds a preset threshold, an air pressure regulation start signal is generated; according to the air pressure regulation start signal, an adaptive neural fuzzy inference system and a nonlinear control algorithm of particle swarm optimization are used to dynamically adjust and optimize the gas replenishment or discharge rate to ensure that the air pressure fluctuation is effectively offset and generate a preliminary air pressure regulation strategy; when the air pressure fluctuation tends to be flat and reaches a preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while considering the system energy efficiency ratio and equipment service life to generate a final air pressure regulation plan; based on the final air pressure regulation plan, the pressure sensor data at different positions of the buffer tank are analyzed, and the air pressure regulation strategy is continuously optimized in combination with external conditions and changes in the gas components in the tank to ensure that the air pressure inside the buffer tank is within an ideal range, and the key parameters of each adjustment are recorded to generate data support for performance evaluation and system improvement; the air pressure fluctuation in the buffer tank provided by the present application The balancing and pressure stabilization method has the following beneficial effects: by real-time monitoring of air pressure changes through a high-precision pressure sensor array, the air pressure fluctuation can be captured quickly and accurately, and timely response can be made, effectively avoiding the inaccuracy of air pressure control caused by response delay; the nonlinear control algorithm combining an adaptive neural fuzzy inference system with a particle swarm optimization not only improves the adaptability to air pressure fluctuations under complex working conditions, but also can automatically adjust the optimal control strategy under different environmental conditions, thereby enhancing the robustness and flexibility of the system; the air pressure regulation process is further optimized through a multi-objective genetic algorithm, and on the basis of ensuring air pressure stability, the frequency and magnitude of gas replenishment or discharge are reduced as much as possible, energy consumption is reduced, equipment life is extended, and the energy efficiency ratio of the entire system is improved; the air pressure regulation strategy is continuously monitored and optimized to ensure that the air pressure inside the buffer tank is kept within the ideal range even in the face of changes in external conditions or changes in the gas composition in the tank, which helps to maintain the long-term stability and reliability of the system; the key parameters in each adjustment process are recorded, providing detailed data support for subsequent performance evaluation, which is conducive to discovering potential problems and implementing targeted improvement measures, and continuously optimizing system performance.

[0019] By using the adaptive neural fuzzy inference system and the nonlinear control algorithm of particle swarm optimization, the air pressure regulation start signal is analyzed, the future air pressure change trend is predicted, a preliminary gas replenishment or emission rate adjustment plan is formulated, and the adjustment plan is continuously optimized through the particle swarm optimization algorithm to generate the final gas replenishment or emission rate change curve, thereby generating a preliminary air pressure regulation strategy to ensure that the air pressure fluctuation is effectively controlled; the air pressure fluctuation balance and pressure stabilization method in the buffer tank provided in the present application has the following beneficial effects: through the combination of the adaptive neural fuzzy inference system and the particle swarm optimization algorithm, the air pressure fluctuation can be analyzed quickly and accurately and an optimized regulation strategy can be generated. The strategy can effectively improve the response speed and control accuracy of the system; the use of historical air pressure data and prediction models can better predict future air pressure change trends, formulate reasonable adjustment plans, and enhance the adaptability and robustness of the system under complex working conditions; by continuously updating and optimizing the change curve of gas replenishment or emission rate, it can ensure that air pressure fluctuations are effectively controlled while minimizing energy consumption and equipment wear, thereby improving the system's energy efficiency and equipment service life; the entire process is fully automated from air pressure fluctuation detection to air pressure adjustment strategy generation, ensuring that the system can respond to air pressure changes in real time, realize intelligent management, and improve overall performance and economic benefits.

[0020] When the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while taking into account the system energy efficiency ratio and equipment service life, to generate the final air pressure regulation plan; the air pressure fluctuation balance and pressure stabilization method in the buffer tank provided in the present application has the following beneficial effects: optimizing the gas replenishment or discharge rate through a multi-objective genetic algorithm to ensure that while maintaining air pressure stability, the system energy efficiency ratio is maximized and energy waste is reduced; comprehensively considering the service life of the equipment, optimizing the gas replenishment or discharge rate, reducing the frequent start and stop and excessive wear of the equipment, extending the service life of the equipment, and reducing maintenance costs; the multi-objective genetic algorithm can find the optimal combination of gas replenishment or discharge rates to ensure that the air pressure inside the buffer tank is maintained within the ideal range for a long time, thereby improving the stability and reliability of the system; by comprehensively considering the system energy efficiency ratio, equipment service life and air pressure stability, a final air pressure regulation plan is generated to optimize the overall performance of the system and improve production efficiency and economic benefits.

[0021] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A flow chart of a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the structure of a pressure fluctuation balancing and pressure stabilization system in a buffer tank provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0027] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0029] Figure 1 A flow chart of a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0030] 101. Use a high-precision pressure sensor array to monitor the air pressure in the buffer tank in real time, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds a preset threshold;

[0031] By deploying a high-precision pressure sensor array inside the buffer tank, the air pressure data inside the tank can be continuously collected; the collected data is preprocessed, mainly to remove noise (such as erroneous readings caused by external interference) and enhance signal clarity, so as to more accurately reflect the actual air pressure status in the tank; when the monitored air pressure fluctuation exceeds the pre-set safety threshold, the system will automatically generate an air pressure regulation start signal, indicating that the system needs to take action to adjust the air pressure.

[0032] 102. According to the air pressure regulation start signal, using an adaptive neural fuzzy inference system and a nonlinear control algorithm of particle swarm optimization, dynamically adjusting and optimizing the gas replenishment or discharge rate to ensure that the air pressure fluctuation is effectively offset and generate a preliminary air pressure regulation strategy;

[0033] This is an advanced control technology that combines the learning ability of neural networks and fuzzy logic to handle uncertainty. It can generate a forecast of future pressure change trends based on the characteristics of current pressure fluctuations (such as amplitude, direction, and rate of change), combined with historical data and prediction models; using this algorithm, the system can automatically search for the optimal gas replenishment or discharge rate change curve to offset pressure fluctuations at the fastest speed and with the least energy consumption. This process will produce a preliminary pressure regulation strategy.

[0034] Optionally, in step 102, according to the air pressure regulation start signal, a nonlinear control algorithm of an adaptive neural fuzzy inference system and particle swarm optimization is used to dynamically adjust and optimize the gas replenishment or discharge rate to ensure that the air pressure fluctuation is effectively offset and generate a preliminary air pressure regulation strategy, which specifically includes the following steps:

[0035] According to the air pressure regulation start signal, the amplitude, direction and change rate of the current air pressure fluctuation are analyzed and processed by using an adaptive neural fuzzy inference system, and the historical air pressure data and the prediction model are combined to obtain the prediction results of the future air pressure change trend; based on the prediction results, a preliminary gas replenishment or emission rate adjustment plan is formulated to quickly respond to air pressure fluctuations; based on the preliminary gas replenishment or emission rate adjustment plan, a nonlinear control algorithm based on particle swarm optimization is adopted to automatically search for the optimal gas replenishment or emission rate change curve by simulating the group behavior in nature, to ensure that the air pressure fluctuation is effectively offset, and to generate optimization suggestions; based on the optimization suggestions, the gas replenishment or emission rate change curve is continuously updated and optimized until the optimal solution is found, and the optimized gas replenishment or emission rate change curve is generated; based on the optimized gas replenishment or emission rate change curve, a preliminary air pressure regulation strategy is generated to ensure that the air pressure fluctuation is effectively controlled.

[0036] Assume that there is a buffer tank with a high-precision pressure sensor array installed inside. At a certain moment, the system detects that the air pressure fluctuation exceeds the preset threshold, triggering the air pressure regulation start signal; the system collects the current air pressure fluctuation amplitude of 10kPa, the direction is rising, and the change rate is 2kPa / s; ANFIS is used to analyze these data, combined with the historical air pressure data of the past month and the prediction model, and predicts that the air pressure will continue to rise in the next 5 minutes, and the maximum fluctuation amplitude may reach 15kPa; the air pressure will continue to rise in the next 5 minutes, and the maximum fluctuation amplitude may reach 15kPa; the system decides to gradually increase the gas emission rate from the current 10m 3 / min increased to 15m 3 / min to offset the trend of rising gas pressure; the gas discharge rate is from 10m 3 / min increased to 15m 3 / min; Use the PSO algorithm to initialize the particle swarm, and each particle represents a possible gas emission rate change curve. Through multiple iterations, the position and speed of the particles are continuously updated, and finally the optimal gas emission rate change curve is found, so that the pressure fluctuation is effectively offset; After the optimization of the PSO algorithm, the system finds the optimal gas emission rate change curve, as follows: In the first minute, the emission rate is increased from 10m / s to 10m / s. 3 / min increased to 12m 3 / min, increasing to 14m / min in the second minute 3 / min, and finally increase to 15m in the 3rd minute 3 / min - ; The system continuously updates the change curve of the gas emission rate according to the optimization suggestions to ensure that the pressure fluctuation is effectively controlled; the gas emission rate increases from 10m / s to 10m / s within the first minute. 3 / min increased to 12m 3 / min, increasing to 14m / min in the second minute 3 / min, and finally increase to 15m in the 3rd minute 3 / min; Based on the optimized gas emission rate change curve, the system generates a preliminary gas pressure regulation strategy to ensure that the gas pressure fluctuation is effectively controlled.

[0037] Through the above steps, the system can effectively cope with air pressure fluctuations and ensure that the air pressure in the buffer tank is stable within the ideal range.

[0038] Optionally, based on the preliminary gas replenishment or discharge rate adjustment plan, a nonlinear control algorithm based on particle swarm optimization is used to automatically search for the optimal gas replenishment or discharge rate change curve by simulating the group behavior in nature, ensure that the pressure fluctuation is effectively offset, and generate optimization suggestions, which specifically include the following steps:

[0039] Based on the preliminary gas replenishment or emission rate adjustment plan, the search range of the particle swarm optimization algorithm is determined to cover all possible gas replenishment or emission rate change curves, and a basic optimization framework is constructed; based on the optimization basic framework, the particle swarm in the particle swarm optimization algorithm is initialized, each particle represents a potential gas replenishment or emission rate change curve, and an initial particle swarm is generated; based on the initial particle swarm, a fitness function is set for each particle, and the fitness function evaluates the quality of the particle according to the ability to offset the air pressure fluctuation, and a fitness evaluation standard is generated; based on the fitness evaluation standard, the group behavior in nature is simulated, and the particle swarm is allowed to move within the search range, and each particle adjusts its flight direction and speed according to its own historical optimal position and the global optimal position of the group, and the position and speed of the particle are continuously updated to generate an optimal gas replenishment or emission rate change curve; based on the optimal gas replenishment or emission rate change curve, it is ensured that the air pressure fluctuation is effectively offset, and an optimization suggestion is generated.

[0040] Assume that there is a buffer tank with a high-precision pressure sensor array installed inside. At a certain moment, the system detects that the pressure fluctuation exceeds the preset threshold, triggering the gas pressure regulation start signal. Based on the preliminary gas replenishment or discharge rate adjustment plan, the system decides to use the particle swarm optimization (PS0) algorithm to optimize the gas discharge rate; the gas discharge rate is increased from 10m 3 / min increased to 15m 3 / min - ; Determine the search range to be 10m 3 / min to 15m 3 All possible gas emission rate change curves between / min are used to build the basic framework for optimization; the search range is 10m 3 / min to 15m 3 / min - Initialize the particle swarm in the particle swarm optimization algorithm. Assume that the initial particle swarm contains 100 particles, and each particle represents a possible gas emission rate change curve. For example, particle 1 may represent a gas emission rate change curve from 10m in the first minute. 3 / min increased to 11m 3 / min, increasing to 13m in the second minute 3 / min, increase to 15m in the third minute 3 / min; 100 particles, each particle represents a gas emission rate change curve; set a fitness function for each particle, and the fitness function evaluates the quality of the particle based on the offset effect of air pressure fluctuations. For example, the fitness function can be defined as:

[0041] f(x)=-air pressure fluctuation amplitude + α·system energy efficiency ratio + β·equipment service life

[0042] Among them, α and β are weight coefficients used to adjust the importance of each target; the fitness evaluation standard is the fitness value of each particle; the group behavior in nature is simulated to allow the particle group to move within the search range. Each particle adjusts its flight direction and speed based on its own historical optimal position and the global optimal position of the group. The specific update formula is as follows:

[0043]

[0044] in, is the new velocity of the ith particle in the dth dimension, w(t) is the inertia weight that changes dynamically with the number of iterations, c1(t) and c2(t) are acceleration constants that change dynamically with the number of iterations, r1 and r2 are two independent random numbers, usually drawn from a uniform distribution [0, 1]. is the personal best historical position of the ith particle in the dth dimension, is the current position of the ith particle in the dth dimension, is the global optimal position in the dth dimension; the optimal gas replenishment or emission rate change curve: after multiple rounds of iterations, the particle swarm optimization algorithm finds the optimal gas emission rate change curve. For example, the optimal gas emission rate change curve may be from 10m in the first minute to 3 / min increased to 12m 3 / min, increasing to 14m in the second minute 3 / min, and finally increase to 15m in the 3rd minute 3 / min; based on the optimal gas replenishment or discharge rate change curve, generate optimization suggestions to ensure that gas pressure fluctuations are effectively offset.

[0045] Through the above steps, the system can automatically search and find the optimal gas replenishment or discharge rate change curve to ensure that the gas pressure fluctuation is effectively controlled. This not only improves the system's response speed and accuracy, but also optimizes the system's energy efficiency and equipment life.

[0046] This application takes into account that in the buffer tank pressure fluctuation balance and pressure stabilization system, it is necessary to dynamically adjust the gas replenishment or discharge rate to ensure that the pressure fluctuation is effectively offset. The particle swarm optimization (PSO) algorithm is widely used in such optimization problems because of its simplicity, high efficiency and easy implementation. PSO simulates the behavior of bird flocks or fish schools in nature and uses swarm intelligence to find the optimal solution.

[0047] Optionally, based on the preliminary gas replenishment or discharge rate adjustment plan, a nonlinear control algorithm based on particle swarm optimization is used to automatically search for the optimal gas replenishment or discharge rate change curve by simulating the group behavior in nature to ensure that the pressure fluctuation is effectively offset, including:

[0048] Initialize the particle group, define the initial position and velocity of each particle, and the position of each particle represents a set of gas replenishment or emission rate change curves;

[0049] defining a fitness function, wherein the fitness function is used to determine the quality of a gas replenishment or discharge rate change curve;

[0050] Update the particle's velocity using the following calculation formula to get the particle's new velocity:

[0051]

[0052] in, is the new velocity of the ith particle in the dth dimension; is the inertia weight that changes dynamically with the number of iterations t, w max and w min are the maximum and minimum inertia weights respectively, T is the maximum number of iterations; t is the current number of iterations; δ is a small perturbation coefficient used to introduce periodic fluctuations; is the current velocity of the ith particle in the dth dimension; c1(t) and c2(t) are acceleration constants that change dynamically with the number of iterations t, c 1，max 、c 1，min 、c 2，max and c 2，min are the maximum and minimum values ​​of the acceleration constant, ∈1 and ∈2 are small perturbation coefficients used to introduce dynamic adjustment of logarithmic growth; r1 and r2 are two independent random numbers, usually drawn from a uniform distribution [0, 1], used to increase the randomness of the search; is the personal best historical position of the ith particle in the dth dimension; is the current position of the ith particle in the dth dimension; is the global optimal position in the dth dimension; is the historical optimal position in the dth dimension, that is, the historical best position of all particles in this dimension; α and β are coefficients that control the influence of additional terms, which are used to introduce the influence of the historical optimal position; and are the fitness values ​​of the current particle position and the global optimal position respectively;

[0053] Update the particle's position using the following calculation formula to get the particle's new position:

[0054]

[0055] in, represents the new position of the i-th particle in the d-th dimension; represents the current position of the i-th particle in the d-th dimension; γ is a coefficient that controls the influence of the individual's historical optimal position; λ is an index that controls the influence of the individual's historical optimal position; represents the personal historical optimal position of the i-th particle in the d-th dimension; ηη is a coefficient that controls the influence of the historical optimal position; μ is an index that controls the influence of the historical optimal position; Represents the historical optimal position in the dth dimension; and c Represent the fitness values ​​of the current particle position and the individual historical optimal position respectively; and Represent the fitness values ​​of the current particle position and the historical optimal position respectively; v is a coefficient that controls the influence of periodic fluctuations; rand() is a random number drawn from a uniform distribution [0, 1]; represents the average position of all particles in the dth dimension;

[0056] Generate a new gas replenishment or emission rate change curve based on the new speed and new position of each particle, and calculate the corresponding fitness value. The fitness function of the particle is calculated by the following calculation formula:

[0057] f(x)=α·f stability (x)η+β·f cfficiency (x) θ +γ·f lifetime (x)φ+δ·log(1+f stability (x)+f efficiency (x)+f lifetime (x))

[0058] Among them, f(x) represents the fitness value of particle x; fstability (x) is the evaluation index of air pressure stability; f cfficiency (x) is the evaluation index of system energy efficiency ratio; f lifetime (x) is the evaluation index of equipment life; α, β, γ and δ are the weight coefficients of air pressure stability, system energy efficiency ratio, equipment life and comprehensive items respectively; η, θ and φ are the corresponding indexes used to adjust the importance of each goal; update the personal historical optimal position of each particle and the global optimal position The particle speed and position are updated repeatedly until a predetermined number of iterations is reached or convergence conditions are met, thereby obtaining an optimal gas replenishment or discharge rate change curve.

[0059] Assume there is a buffer tank that needs to adjust the gas pressure from 100 kPa to 120 kPa within 5 minutes. The initial gas replenishment or discharge rate adjustment plan is to increase from 10 m / min to 15 m / min. 3 / min. The PSO algorithm is used to optimize this process; the number of particles is 100; 100 particles are randomly generated, each particle represents a gas replenishment or emission rate change curve; the speed of 100 particles is randomly generated; α = 0.5, β = 0.3, γ = 0.2, δ = 0.1; η = 2, θ = 1.5, φ = 1; w max =0.9, w min =0.4; C 1,max =2.5, c 1,min =0.5; C 2,max =2.5, c 2,min =0.5;∈1=0.01,∈2=0.01;δ=0.05;α=0.5,β=0.5;γ=0.5,λ=2;η=0.5,μ=2;v=0.1;maximum number of iterations T=100;assuming the initial position of the first particle Initial Speed Calculating Inertia Weight Calculate the acceleration constant Calculate the acceleration constant Assume r1 = 0.7, r2 = 0.8, Calculate new speed Calculate new position Calculate fitness value Update personal best historical position Update the global optimal position Continue with multiple rounds of iterations until the maximum number of iterations, 100, is reached or the convergence condition is met.

[0060] Through the above steps, the system can automatically search and find the optimal gas replenishment or discharge rate change curve to ensure that the gas pressure fluctuation is effectively controlled. This not only improves the system's response speed and accuracy, but also optimizes the system's energy efficiency and equipment life.

[0061] Optionally, in step 102, according to the air pressure adjustment start signal, an adaptive neural fuzzy inference system is used to analyze and process the amplitude, direction and change rate of the current air pressure fluctuation, and a prediction result of the future air pressure change trend is obtained by combining historical air pressure data and a prediction model, which specifically includes the following steps:

[0062] According to the air pressure regulation start signal, the amplitude, direction and change rate of the current air pressure fluctuation are analyzed and processed in real time by using an adaptive neural fuzzy inference system to generate characteristic parameters of air pressure fluctuation; based on the characteristic parameters of air pressure fluctuation and in combination with historical air pressure data, the trend and development direction of the current air pressure fluctuation are evaluated to generate an air pressure fluctuation trend evaluation report; based on the air pressure fluctuation trend evaluation report, the prediction model parameters are adjusted to optimize the accuracy and reliability of the prediction model to generate an optimized prediction model; based on the optimized prediction model, the future air pressure change trend is predicted to ensure accurate reflection of the future air pressure fluctuation situation and generate preliminary prediction results of the future air pressure change trend; based on the preliminary prediction results of the future air pressure change trend, verification and correction are performed to ensure the accuracy of the prediction and obtain the prediction results of the future air pressure change trend.

[0063] Suppose there is a buffer tank with a high-precision pressure sensor array installed inside. At a certain moment, the system detects that the air pressure fluctuation exceeds the preset threshold, triggering the air pressure regulation start signal; air pressure regulation start signal, the current air pressure fluctuation amplitude is 10kPa, the direction is rising, and the change rate is 2kPa / s; ANFIS is used to analyze and process these data in real time to generate air pressure fluctuation characteristic parameters, for example, the amplitude is 10kPa; the direction is rising; the change rate is 2kPa / s; air pressure fluctuation characteristic parameters, historical air pressure data for the past month; combined with historical air pressure data, the trend and development direction of the current air pressure fluctuation are evaluated to generate an air pressure fluctuation trend evaluation report. For example, the report points out that the current air pressure fluctuation trend is a continuous rise, and the air pressure is expected to continue to rise in the next 5 minutes, and the maximum fluctuation amplitude may reach 15kPa; air pressure fluctuation trend evaluation report; adjust the parameters of the prediction model according to the evaluation report to optimize the accuracy and reliability of the prediction model. For example, adjust the weight coefficient of the model to better fit the historical data and generate an optimized prediction model; input the optimized prediction model; based on the optimized prediction model, predict the future trend of air pressure changes and generate preliminary prediction results for the future trend of air pressure changes. For example, the prediction results show that the air pressure will continue to rise in the next 5 minutes, and the maximum fluctuation range may reach 15kPa; input the preliminary prediction results; verify and correct the preliminary prediction results to ensure the accuracy of the prediction. For example, by comparing the actual air pressure changes with the prediction results, it is found that the prediction results are relatively accurate, and finally generate the prediction results for the future trend of air pressure changes, confirming that the air pressure will continue to rise in the next 5 minutes, and the maximum fluctuation range may reach 15kPa.

[0064] Through the above steps, the system can accurately predict the future trend of air pressure changes, provide a scientific basis for subsequent air pressure regulation, and ensure that air pressure fluctuations are effectively controlled. This not only improves the system's response speed and accuracy, but also optimizes the system's energy efficiency and equipment life.

[0065] 103. When the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while considering the system energy efficiency ratio and equipment service life to generate the final air pressure regulation plan;

[0066] When the air pressure fluctuation has become flat and entered the preset stable range, in order to ensure long-term air pressure stability, taking into account the energy efficiency of the system and the service life of the equipment, a multi-objective genetic algorithm is used to further optimize the gas replenishment or discharge rate. This process aims to find the best solution that can maintain air pressure stability while saving energy and reducing equipment wear; based on the preliminary air pressure regulation strategy, through the optimization of the multi-objective genetic algorithm, a set of air pressure regulation solutions that can ensure air pressure stability while taking into account system efficiency and equipment life are finally generated.

[0067] Optionally, in step 103, when the air pressure fluctuation tends to be flat and reaches a preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while considering the system energy efficiency ratio and equipment service life, to generate a final air pressure regulation plan, which specifically includes the following steps:

[0068] When the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, the current gas replenishment or emission rate is preliminarily set to ensure that the air pressure fluctuation is effectively controlled and generate the preliminarily set gas replenishment or emission rate; based on the preliminarily set gas replenishment or emission rate, define the search space of the multi-objective genetic algorithm, including all possible gas replenishment or emission rate combinations, and generate a search space for optimization; based on the search space for optimization, set a fitness function for the multi-objective genetic algorithm, the fitness function comprehensively considers the system energy efficiency ratio, equipment service life and air pressure stability requirements, evaluates the quality of each gas replenishment or emission rate combination, and generates a fitness evaluation standard; based on the fitness evaluation standard, run the multi-objective genetic algorithm, and automatically search for the optimal gas replenishment or emission rate combination by simulating the process of natural selection and genetic variation, to ensure that the air pressure is stable, while maximizing the system energy efficiency ratio and extending the equipment service life, and generating a multi-objective optimization result; based on the multi-objective optimization result, determine the final gas replenishment or emission rate to ensure that the internal air pressure of the buffer tank is kept within the ideal range for a long time, while optimizing the system performance and equipment maintenance cost, and generating a final air pressure regulation solution.

[0069] Assume that there is a buffer tank with a high-precision pressure sensor array installed inside. At a certain moment, the system detects that the air pressure fluctuation tends to be flat and reaches the preset stable range, triggering the air pressure regulation start signal; input the preliminary air pressure regulation strategy; when the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, the current gas replenishment or discharge rate is preliminarily set to ensure that the air pressure fluctuation is effectively controlled. For example, the preliminary set gas discharge rate is 12m 3 / min - ; Input the initial set gas replenishment or exhaust rate (12m3 / min); Based on the initially set gas replenishment or emission rate, define the search space of the multi-objective genetic algorithm, including all possible gas replenishment or emission rate combinations. For example, the search space is 10m 3 / min to 15m 3 / min; input the search space for optimization; set the fitness function for the multi-objective genetic algorithm, which comprehensively considers the requirements of system energy efficiency, equipment service life and gas pressure stability, and evaluates the quality of each gas replenishment or emission rate combination. For example, the fitness function can be defined as:

[0070] f(x)=α·f stability (x)+β·f efficiency (x)+γ·f lifetime (x)

[0071] Among them, α, β, and γ are weight coefficients used to adjust the importance of each goal. Assume that α = 0.5, β = 0.3, and γ = 0.2; input the fitness evaluation standard; based on the fitness evaluation standard, run the multi-objective genetic algorithm to automatically search for the optimal gas replenishment or emission rate combination by simulating the process of natural selection and genetic variation; the specific steps include: generating 100 initial chromosomes, each chromosome represents a possible gas emission rate combination; calculating the fitness value of each chromosome; selecting high-quality chromosomes as parents according to the fitness value; performing crossover operations on parent chromosomes to generate new daughter chromosomes; performing mutation operations on daughter chromosomes to increase the diversity of the population; repeating the above steps until the predetermined number of iterations is reached or the collection condition is met, and the result of multi-objective optimization is generated; the result of multi-objective optimization; based on the result of multi-objective optimization, determine the final gas replenishment or emission rate to ensure that the internal gas pressure of the buffer tank remains within the ideal range for a long time, while optimizing system performance and equipment maintenance costs. For example, the results of multi-objective optimization show that the optimal gas emission rate is 13m 3 / min, at this time the air pressure is stable, the system energy efficiency ratio is the highest, and the equipment service life is the longest.

[0072] Through the above steps, the system can automatically adjust the gas replenishment or exhaust rate to ensure stable gas pressure while maximizing the system energy efficiency and extending the service life of the equipment. This not only improves the system's response speed and accuracy, but also optimizes the overall system performance and equipment maintenance costs.

[0073] Optionally, based on the fitness evaluation criteria, a multi-objective genetic algorithm is run to automatically search for the optimal gas replenishment or discharge rate combination by simulating the process of natural selection and genetic variation, thereby ensuring stable gas pressure while maximizing the system energy efficiency ratio and extending the service life of the equipment, and generating a multi-objective optimization result, which specifically includes the following steps:

[0074] Based on the fitness evaluation criteria, the population of the multi-objective genetic algorithm is initialized, each individual represents a combination of a set of gas replenishment or emission rates, and the initial population is generated;

[0075] Based on the initial population, the impact of each gas supplement or exhaust rate combination on the system energy efficiency ratio, equipment service life and gas pressure stability is evaluated to generate the fitness value of each individual;

[0076] Based on the fitness value of each individual, the natural selection process is simulated to select high-quality individuals as parents, perform crossover operations to generate new offspring individuals, and introduce random mutation operations to increase the diversity of the population and generate a new generation of populations;

[0077] Based on the new generation population, the natural selection, crossover and mutation operations are repeatedly performed, and the population is continuously iterated until the termination condition is met, wherein the termination condition includes reaching a predetermined number of iterations or the fitness value is no longer significantly improved, and the optimal solution in the iterative process is generated;

[0078] Based on the optimal solution in the iterative process, the optimal combination of gas replenishment or discharge rates is determined to ensure stable gas pressure while maximizing the system energy efficiency and extending the service life of the equipment, generating multi-objective optimization results.

[0079] This application considers that in the buffer tank pressure fluctuation balance and pressure stabilization system, it is necessary to dynamically adjust the gas replenishment or discharge rate to ensure that the pressure fluctuation is effectively offset. Multi-objective genetic algorithm (MOGA) is widely used in such optimization tasks due to its powerful global search capability and ability to handle multi-objective optimization problems. MOGA can find the optimal solution in a complex and changing environment by simulating the process of natural selection and genetic variation.

[0080] Optionally, based on the fitness evaluation criteria, a multi-objective genetic algorithm is run to automatically search for the optimal gas replenishment or exhaust rate combination by simulating the process of natural selection and genetic variation, thereby ensuring stable gas pressure while maximizing the system energy efficiency ratio and extending the service life of the equipment, and generating multi-objective optimization results, including:

[0081] Determining an objective function of multi-objective optimization, the objective function is used to search for an optimal gas replenishment or discharge rate combination, the objective function includes multiple objectives, wherein the multiple objectives include minimizing gas pressure fluctuations, maximizing system energy efficiency ratio, and extending equipment service life;

[0082] Creating an initial population, each individual in the initial population represents a set of gas replenishment or emission rates;

[0083] According to the objective function, calculating the fitness value corresponding to each individual in the population, wherein the fitness value indicates the degree to which the individual satisfies all objectives;

[0084] Through the selection probability of natural selection and genetic variation, individuals are selected from the population as the parent individuals of the next generation. The selection probability reflects the probability of an individual being selected to become a parent. The selection probability of natural selection and genetic variation is calculated by the following calculation formula:

[0085]

[0086] Among them, p i is the probability of the i-th individual being selected; f(x i ) is the fitness value of the i-th individual; is an exponential that changes dynamically with the number of iterations t, max and λ min are the maximum and minimum exponents respectively, T is the maximum number of iterations, t is the current number of iterations, ∈ is a small perturbation coefficient used to introduce periodic fluctuations; μ is a small perturbation coefficient used to introduce additional periodic fluctuations; λ max and λ min are the maximum and minimum exponents respectively, T is the maximum number of iterations; ∈ is a small perturbation coefficient used to introduce periodic fluctuations; μ is a small perturbation coefficient used to introduce additional periodic fluctuations;

[0087] A multi-point crossover strategy is used to generate offspring individuals of the parent individuals, wherein the multi-point crossover strategy is defined as:

[0088] The multi-point crossover of natural selection and genetic variation is calculated by the following formula:

[0089] y1=[x a (1), x a (2), ..., x a (k1), x b (k1+1),...,x b (k2), x a (k2+1),...,x a (D)]

[0090] y2=[x b (1), x b (2), ..., x b (k1), x a(k1+1),...,x a (k2), x b (k2+1),...,x b (D)]

[0091] Among them, y1 and y2 are the generated offspring individuals; x a and x b are two parent individuals; k1, k2, ..., k m is the randomly selected intersection position; m is the number of intersections; D is the individual dimension;

[0092] Applying the Gaussian mutation formula, performing mutation operation on the offspring individuals to obtain new individuals; wherein the Gaussian mutation formula includes:

[0093]

[0094] Among them, y′(k) is the value of the mutated individual in the kth dimension; y(k) is the value of the original individual in the kth dimension; σ is a fixed standard deviation used to control the amplitude of the variation; randn is a random number drawn from the standard normal distribution; δ is a small perturbation coefficient used to introduce additional periodic fluctuations; rand() is a random number drawn from the uniform distribution [0, 1];

[0095] Adding the new individual to the population, and updating the population according to the fitness value;

[0096] It is determined whether the population meets a preset population diversity threshold. If so, an optimal solution is output and used as a result of multi-objective optimization.

[0097] Assume there is a buffer tank with a high-precision pressure sensor array installed inside. At a certain moment, the system detects that the air pressure fluctuation tends to be flat and reaches the preset stable range, triggering the air pressure regulation start signal.

[0098] Objective function:

[0099] f(x)=0.5·f stability (x)+0.3·f efficiency (x)+0.2·f lifetime (x)

[0100] Generate 100 initial individuals, each of which represents a set of gas replenishment or emission rates. For example, the gas emission rate of individual 1 is 10m 3 / min, the gas emission rate of individual 2 is 11m 3 / min, and so on; Evaluate the fitness value of each individual. For example, the fitness value of individual 1 is 0.8, the fitness value of individual 2 is 0.7, and so on; Parameter setting: λmax =2;λ min =1;∈=0.05;μ=0.05;T=100;t=1

[0101] Calculate the probability of selection:

[0102]

[0103] Select parent individuals based on the selection probability. For example, select individuals 1 and 2 with higher fitness values ​​as parents; randomly select two crossover points, such as k1=3 and k2=6;

[0104] y1=[x1(1),x1(2),x1(3),x2(4),x2(5),x2(6),x1(7),x1(8),x1(9),x1(10)]

[0105] y2=[x2(1),x2(2),x2(3),x1(4),x1(5),x1(6),x2(7),x2(8),x2(9),x2(10)]

[0106] Parameter settings: σ = 0.1; δ = 0.05

[0107] y′1(3)=y1(3)+0.1·randn·(1+0.05·sin(2π·rand() / 10))

[0108] y′2(6)=y2(6)+0.1·randn·(1+0.05·sin(2π·rand() / 10))

[0109] Add the mutated offspring individuals y′1 and y′2 to the population, update the population according to the fitness value, and determine whether the population meets the preset population diversity threshold. For example, if the population diversity threshold is 0.05 and the current population diversity meets the threshold, the optimal solution is output.

[0110] Through the above steps, the system can automatically adjust the gas replenishment or exhaust rate to ensure stable gas pressure while maximizing the system energy efficiency and extending the service life of the equipment. This not only improves the system's response speed and accuracy, but also optimizes the overall system performance and equipment maintenance costs.

[0111] 104. Based on the final gas pressure regulation scheme, analyze the pressure sensor data at different positions of the buffer tank, combine the external conditions and the changes in the gas composition in the tank, continuously optimize the gas pressure regulation strategy, ensure that the internal gas pressure of the buffer tank is within the ideal range, and record the key parameters of each adjustment to generate data support for performance evaluation and system improvement.

[0112] According to the final air pressure regulation plan, the system will continue to monitor the pressure changes at different locations in the buffer tank, while taking into account external environmental factors (such as temperature, humidity) and changes in the gas composition in the tank, and continuously adjust and optimize the air pressure regulation strategy to ensure that the air pressure in the tank is always within the ideal range; during each adjustment process, the system will record key parameters (such as air pressure values ​​before and after adjustment, environmental conditions, changes in gas composition, etc.). These data are very important for subsequent performance evaluation and continuous improvement of the system, and can be used to analyze the effectiveness of the air pressure regulation strategy, identify potential problem points, and make improvement suggestions.

[0113] Optionally, based on the final air pressure regulation scheme in step 104, the pressure sensor data at different positions of the buffer tank are analyzed, and the air pressure regulation strategy is continuously optimized in combination with external conditions such as real-time ambient temperature and humidity and changes in gas components in the tank to ensure that the air pressure inside the buffer tank is kept within an ideal range for a long time, and key parameters of each adjustment are recorded to generate data support for performance evaluation and system improvement, which specifically includes the following steps:

[0114] Based on the final air pressure regulation scheme, a high-precision pressure sensor array is used to monitor the pressure data at different positions of the buffer tank in real time, remove noise and enhance signal clarity to obtain real-time pressure data; based on the real-time pressure data, combined with external conditions such as ambient temperature and humidity and changes in gas components in the tank, the effectiveness of the current air pressure regulation strategy is evaluated, and an air pressure regulation effect evaluation report is generated; based on the air pressure regulation effect evaluation report, the air pressure regulation strategy is continuously adjusted and optimized to ensure that the air pressure inside the buffer tank remains within the ideal range for a long time, and an optimized air pressure regulation strategy is generated; based on the optimized air pressure regulation strategy, key parameters are recorded during the adjustment process, including the time of air pressure adjustment, air pressure values ​​before and after adjustment, environmental conditions, changes in gas components and other information, to generate a detailed adjustment log; using the detailed adjustment log, regular performance evaluations are performed to analyze the effectiveness of the air pressure regulation strategy, identify potential problems and improvement points, and generate data support for performance evaluation and system improvement.

[0115] Suppose there is an industrial buffer tank with a high-precision pressure sensor array installed inside to monitor pressure changes at different locations. The system needs to continuously optimize the pressure regulation strategy based on the final pressure regulation plan to ensure that the air pressure in the tank remains within the ideal range for a long time; the final pressure regulation plan; use a high-precision pressure sensor array to monitor the pressure data at different locations of the buffer tank in real time. For example, the pressure value monitored by sensor 1 is 100kPa, the pressure value monitored by sensor 2 is 102kPa, and so on. Through signal processing technology, noise is removed and signal clarity is enhanced to obtain real-time pressure data; real-time pressure data, ambient temperature 25℃, humidity 50%, and the gas composition in the tank is 80% nitrogen and 20% oxygen; combined with real-time pressure data, ambient temperature, humidity and changes in the gas composition in the tank, evaluate the effect of the current pressure regulation strategy. For example, the evaluation report shows that the current pressure fluctuation is within the range of ±1kPa, the system energy efficiency ratio is 85%, and the equipment service life is 10 years; pressure regulation effect evaluation report; based on the pressure regulation effect evaluation report, continuously adjust and optimize the pressure regulation strategy. For example, according to the evaluation report, the system decides to appropriately increase the gas discharge rate when the ambient temperature is high to reduce the pressure fluctuation. Generate an optimized pressure regulation strategy to ensure that the internal pressure of the buffer tank is kept within the range of 100kPa±1kPa for a long time; Optimized pressure regulation strategy; During each pressure regulation process, record key parameters, including the time of pressure regulation, pressure values ​​before and after regulation, environmental conditions, gas composition changes and other information. For example, the time of a pressure regulation is recorded as 14:30, the pressure before regulation is 101kPa, the pressure after regulation is 100kPa, the ambient temperature is 25℃, the humidity is 50%, and the gas composition in the tank is 80% nitrogen and 20% oxygen. Generate a detailed regulation log; Enter a detailed regulation log; Use the detailed regulation log to perform performance evaluation regularly. For example, perform a performance evaluation once a month to analyze the effectiveness of the pressure regulation strategy and identify potential problems and improvement points. Generate data support for performance evaluation and system improvement. For example, if it is found that the pressure fluctuation is large in certain specific environments, it is recommended to add more sensor points to improve monitoring accuracy.

[0116] Through the above steps, the system can continuously optimize the gas pressure regulation strategy to ensure that the gas pressure inside the buffer tank remains within the ideal range for a long time, while recording key parameters and generating data support for performance evaluation and system improvement. This not only improves the system's response speed and accuracy, but also optimizes the overall performance of the system and the maintenance cost of the equipment.

[0117] Figure 2 A schematic diagram of a pressure fluctuation balance and pressure stabilization system in a buffer tank is provided for the present application embodiment. Figure 2 As shown, the device comprises:

[0118] The processing module 21 is used to monitor the air pressure in the buffer tank in real time using a high-precision pressure sensor array, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds a preset threshold;

[0119] A regulating module 22, for dynamically adjusting and optimizing the gas replenishment or discharge rate according to the gas pressure regulation start signal using an adaptive neural fuzzy inference system and a nonlinear control algorithm of a particle swarm optimization, to ensure that the gas pressure fluctuation is effectively offset, and to generate a preliminary gas pressure regulation strategy;

[0120] The adjustment module 23, when the air pressure fluctuation tends to be flat and reaches a preset stable range, uses a multi-objective genetic algorithm to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability based on the preliminary air pressure adjustment strategy, while taking into account the system energy efficiency ratio and equipment service life, to generate a final air pressure adjustment plan;

[0121] The optimization module 24 analyzes the pressure sensor data at different positions of the buffer tank based on the final gas pressure regulation plan, and continuously optimizes the gas pressure regulation strategy in combination with external conditions and changes in the gas composition in the tank to ensure that the gas pressure inside the buffer tank is within the ideal range. It also records the key parameters of each adjustment and generates data support for performance evaluation and system improvement.

[0122] Figure 2 The gas pressure fluctuation balance and pressure stabilization system in the buffer tank can be implemented Figure 1 The implementation principle and technical effect of the method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank described in the embodiment shown are not described in detail. The specific manner in which each module and unit performs operations in the gas pressure fluctuation balancing and pressure stabilizing system in a buffer tank in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0123] In one possible design, Figure 2 The gas pressure fluctuation balancing and pressure stabilization system in a buffer tank of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0124] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0125] The processing component 32 is used to: use a high-precision pressure sensor array to monitor the air pressure in the buffer tank in real time, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds a preset threshold; according to the air pressure regulation start signal, use an adaptive neural fuzzy inference system and a nonlinear control algorithm of particle swarm optimization to dynamically adjust and optimize the gas replenishment or discharge rate to ensure that the air pressure fluctuation is effectively offset and generate a preliminary air pressure regulation strategy; when the air pressure fluctuation tends to be flat and reaches a preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while considering the system energy efficiency ratio and equipment service life to generate a final air pressure regulation plan; based on the final air pressure regulation plan, analyze the pressure sensor data at different positions of the buffer tank, combine the external conditions and the changes in the gas components in the tank, continuously optimize the air pressure regulation strategy, ensure that the air pressure inside the buffer tank is within an ideal range, and record the key parameters of each adjustment to generate data support for performance evaluation and system improvement.

[0126] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0127] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0128] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0129] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0130] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0131] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0132] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 A method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank in the illustrated embodiment.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank, characterized in that: include: Use a high-precision pressure sensor array to monitor the air pressure in the buffer tank in real time, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds the preset threshold; According to the gas pressure regulation start signal, the gas replenishment or discharge rate is dynamically adjusted and optimized using an adaptive neural fuzzy inference system and a particle swarm optimization nonlinear control algorithm to ensure that the gas pressure fluctuation is effectively offset and generate a preliminary gas pressure regulation strategy; When the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability, while taking into account the system energy efficiency ratio and equipment service life, to generate the final air pressure regulation plan; Based on the final gas pressure regulation plan, the pressure sensor data at different positions of the buffer tank are analyzed. Combined with the external conditions and changes in the gas composition in the tank, the gas pressure regulation strategy is continuously optimized to ensure that the internal gas pressure of the buffer tank is within the ideal range. The key parameters of each adjustment are recorded to generate data support for performance evaluation and system improvement.

2. The method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank according to claim 1, characterized in that: According to the gas pressure regulation start signal, the gas replenishment or discharge rate is dynamically adjusted and optimized using an adaptive neural fuzzy inference system and a particle swarm optimization nonlinear control algorithm to ensure that the gas pressure fluctuation is effectively offset and generate a preliminary gas pressure regulation strategy, which specifically includes the following steps: According to the air pressure adjustment start signal, the amplitude, direction and change rate of the current air pressure fluctuation are analyzed and processed by using an adaptive neural fuzzy inference system, and the prediction result of the future air pressure change trend is obtained by combining the historical air pressure data and the prediction model; Based on the forecast results, develop a preliminary plan for adjusting the gas replenishment or discharge rate to quickly respond to gas pressure fluctuations; Based on the preliminary gas replenishment or emission rate adjustment plan, a nonlinear control algorithm based on particle swarm optimization is used to automatically search for the optimal gas replenishment or emission rate change curve by simulating the group behavior in nature, ensuring that the pressure fluctuation is effectively offset and generating optimization suggestions; Based on the optimization suggestions, the change curve of the gas replenishment or emission rate is continuously updated and optimized until the optimal solution is found, and the optimized change curve of the gas replenishment or emission rate is generated; Based on the optimized gas replenishment or discharge rate change curve, a preliminary gas pressure regulation strategy is generated to ensure that gas pressure fluctuations are effectively controlled.

3. The method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank according to claim 2, characterized in that: Based on the preliminary gas replenishment or emission rate adjustment plan, a nonlinear control algorithm based on particle swarm optimization is used to automatically search for the optimal gas replenishment or emission rate change curve by simulating the group behavior in nature to ensure that the pressure fluctuation is effectively offset and generate optimization suggestions, which specifically include the following steps: Based on the preliminary gas replenishment or emission rate adjustment plan, determine the search scope of the particle swarm optimization algorithm, cover all possible gas replenishment or emission rate change curves, and build the basic framework of optimization; Based on the optimization basic framework, a particle swarm in a particle swarm optimization algorithm is initialized, each particle represents a potential gas replenishment or emission rate change curve, and an initial particle swarm is generated; Based on the initial particle group, a fitness function is set for each particle. The fitness function evaluates the quality of the particle according to its ability to offset the effect of air pressure fluctuations and generates a fitness evaluation standard. Based on the fitness evaluation standard, the group behavior in nature is simulated to allow the particle group to move within the search range. Each particle adjusts its flight direction and speed according to its own historical optimal position and the global optimal position of the group, continuously updates the position and speed of the particle, and generates the optimal gas replenishment or emission rate change curve; Based on the optimal gas replenishment or exhaust rate change curve, ensure that the gas pressure fluctuation is effectively offset and generate optimization suggestions; Among them, based on the preliminary gas replenishment or emission rate adjustment plan, a nonlinear control algorithm based on particle swarm optimization is used to automatically search for the optimal gas replenishment or emission rate change curve by simulating the group behavior in nature to ensure that the pressure fluctuation is effectively offset, including: Initialize the particle group, define the initial position and velocity of each particle, and the position of each particle represents a set of gas replenishment or emission rate change curves; defining a fitness function, wherein the fitness function is used to determine the quality of a gas replenishment or discharge rate change curve; Update the particle's velocity using the following calculation formula to get the particle's new velocity: in, is the new velocity of the ith particle in the dth dimension; is the inertia weight that changes dynamically with the number of iterations t, w max and w min are the maximum and minimum inertia weights respectively, T is the maximum number of iterations; t is the current number of iterations; δ is a small perturbation coefficient used to introduce periodic fluctuations; is the current velocity of the ith particle in the dth dimension; c1(t) and c2(t) are acceleration constants that change dynamically with the number of iterations t, c 1，max 、c 1，min 、c 2，max and c 2，min are the maximum and minimum values ​​of the acceleration constant, ∈1 and ∈2 are small perturbation coefficients used to introduce dynamic adjustment of logarithmic growth; r1 and r2 are two independent random numbers, usually drawn from a uniform distribution [0, 1], used to increase the randomness of the search; is the personal best historical position of the ith particle in the dth dimension; is the current position of the ith particle in the dth dimension; is the global optimal position in the dth dimension; is the historical optimal position in the dth dimension, that is, the historical best position of all particles in this dimension; α and β are coefficients that control the influence of additional terms, which are used to introduce the influence of the historical optimal position; and are the fitness values ​​of the current particle position and the global optimal position respectively; Update the particle's position using the following calculation formula to get the particle's new position: in, represents the new position of the i-th particle in the d-th dimension; represents the current position of the i-th particle in the d-th dimension; γ is a coefficient that controls the influence of the individual's historical optimal position; λ is an index that controls the influence of the individual's historical optimal position; represents the personal historical optimal position of the i-th particle in the d-th dimension; η is a coefficient that controls the influence of the historical optimal position; μ is an index that controls the influence of the historical optimal position; Represents the historical optimal position in the dth dimension; and Represent the fitness values ​​of the current particle position and the individual historical optimal position respectively; and Represent the fitness values ​​of the current particle position and the historical optimal position respectively; ν is a coefficient that controls the influence of periodic fluctuations; rand() is a random number drawn from a uniform distribution [0, 1]; represents the average position of all particles in the dth dimension; Generate a new gas replenishment or emission rate change curve based on the new speed and new position of each particle, and calculate the corresponding fitness value. The fitness function of the particle is calculated by the following calculation formula: f(x)=α·f stability (x) η +β·f cfficiency (x) θ +γ·f lifetime (x) φ +δ·log(1+f stability (x)+f efficiency (x)+f lifetime (x)) Among them, f(x) represents the fitness value of particle x; f stability (x) is the evaluation index of air pressure stability; f cfficiency (x) is the evaluation index of system energy efficiency ratio; f lifetime (x) is the evaluation index of equipment service life; α, β, γ and δ are the weight coefficients of air pressure stability, system energy efficiency ratio, equipment service life and comprehensive items respectively; η, θ and φ are the corresponding indexes used to adjust the importance of each target; Update each particle's personal best historical position and the global optimal position The particle velocity and position are updated repeatedly until a predetermined number of iterations is reached or convergence conditions are met, thereby obtaining an optimal gas replenishment or discharge rate change curve.

4. The method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank according to claim 2, characterized in that: According to the air pressure adjustment start signal, the adaptive neural fuzzy inference system is used to analyze and process the amplitude, direction and change rate of the current air pressure fluctuation, and the prediction result of the future air pressure change trend is obtained by combining the historical air pressure data and the prediction model, which specifically includes the following steps: According to the air pressure regulation start signal, the adaptive neural fuzzy inference system is used to perform real-time analysis and processing on the amplitude, direction and change rate of the current air pressure fluctuation to generate the characteristic parameters of the air pressure fluctuation; Based on the pressure fluctuation characteristic parameters and in combination with historical pressure data, the trend and development direction of the current pressure fluctuation are evaluated to generate a pressure fluctuation trend evaluation report; Based on the pressure fluctuation trend assessment report, adjust the prediction model parameters, optimize the accuracy and reliability of the prediction model, and generate an optimized prediction model; Based on the optimized prediction model, the future trend of air pressure change is predicted to ensure accurate reflection of future air pressure fluctuations and generate preliminary prediction results of future air pressure change trends; Based on the preliminary prediction results of the future trend of air pressure changes, verification and correction are carried out to ensure the accuracy of the prediction and obtain the prediction results of the future trend of air pressure changes.

5. The method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank according to claim 1, characterized in that: When the air pressure fluctuation tends to be flat and reaches the preset stable range, based on the preliminary air pressure regulation strategy, a multi-objective genetic algorithm is used to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability. At the same time, the system energy efficiency ratio and equipment service life are considered to generate the final air pressure regulation plan, which specifically includes the following steps: When the air pressure fluctuation tends to be flat and reaches the preset stable range, the current gas replenishment or discharge rate is preliminarily set based on the preliminary air pressure regulation strategy to ensure that the air pressure fluctuation is effectively controlled and generate the preliminarily set gas replenishment or discharge rate; Based on the initially set gas replenishment or emission rate, a search space of a multi-objective genetic algorithm is defined, which includes all possible gas replenishment or emission rate combinations, and a search space for optimization is generated; Based on the search space for optimization, a fitness function is set for the multi-objective genetic algorithm, the fitness function comprehensively considers the requirements of system energy efficiency ratio, equipment service life and gas pressure stability, evaluates the quality of each gas replenishment or discharge rate combination, and generates a fitness evaluation standard; Based on the fitness evaluation criteria, a multi-objective genetic algorithm is run to automatically search for the optimal gas replenishment or discharge rate combination by simulating the process of natural selection and genetic variation, ensuring stable gas pressure while maximizing the system energy efficiency and extending the service life of the equipment, generating multi-objective optimization results; Based on the results of multi-objective optimization, the final gas replenishment or discharge rate is determined to ensure that the internal gas pressure of the buffer tank remains within the ideal range for a long time, while optimizing system performance and equipment maintenance costs, and generating the final gas pressure regulation plan.

6. The method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank according to claim 5, characterized in that: Based on the fitness evaluation criteria, a multi-objective genetic algorithm is run to automatically search for the optimal gas replenishment or emission rate combination by simulating the process of natural selection and genetic variation. This ensures that the gas pressure is stable while maximizing the system energy efficiency and extending the service life of the equipment. The multi-objective optimization results are generated. The specific steps include: Based on the fitness evaluation criteria, the population of the multi-objective genetic algorithm is initialized, each individual represents a combination of a set of gas replenishment or emission rates, and the initial population is generated; Based on the initial population, the impact of each gas supplement or exhaust rate combination on the system energy efficiency ratio, equipment service life and gas pressure stability is evaluated to generate the fitness value of each individual; Based on the fitness value of each individual, the natural selection process is simulated to select high-quality individuals as parents, perform crossover operations to generate new offspring individuals, and introduce random mutation operations to increase the diversity of the population and generate a new generation of population; Based on the new generation population, the natural selection, crossover and mutation operations are repeatedly performed, and the population is continuously iterated until the termination condition is met, wherein the termination condition includes reaching a predetermined number of iterations or the fitness value is no longer significantly improved, and the optimal solution in the iterative process is generated; Based on the optimal solution in the iterative process, the optimal gas replenishment or exhaust rate combination is determined to ensure stable gas pressure while maximizing the system energy efficiency and extending the equipment service life, generating multi-objective optimization results; Among them, based on the fitness evaluation standard, a multi-objective genetic algorithm is run to automatically search for the optimal gas replenishment or emission rate combination by simulating the process of natural selection and genetic variation, ensuring stable gas pressure while maximizing the system energy efficiency and extending the service life of the equipment, generating multi-objective optimization results, including: Determining an objective function of multi-objective optimization, the objective function is used to search for an optimal gas replenishment or discharge rate combination, the objective function includes multiple objectives, wherein the multiple objectives include minimizing gas pressure fluctuations, maximizing system energy efficiency ratio, and extending equipment service life; Creating an initial population, each individual in the initial population represents a set of gas replenishment or emission rates; According to the objective function, calculating the fitness value corresponding to each individual in the population, wherein the fitness value indicates the degree to which the individual satisfies all objectives; Through the selection probability of natural selection and genetic variation, individuals are selected from the population as the parent individuals of the next generation. The selection probability reflects the probability of an individual being selected to become a parent. The selection probability of natural selection and genetic variation is calculated by the following calculation formula: Among them, p i is the probability of the i-th individual being selected; f(x i ) is the fitness value of the i-th individual; is an exponential that changes dynamically with the number of iterations t, max and λ min are the maximum and minimum exponents respectively, T is the maximum number of iterations, t is the current number of iterations, ∈ is a small perturbation coefficient used to introduce periodic fluctuations; μ is a small perturbation coefficient used to introduce additional periodic fluctuations; λ max and λ min are the maximum and minimum exponents respectively, T is the maximum number of iterations; ∈ is a small perturbation coefficient used to introduce periodic fluctuations; μ is a small perturbation coefficient used to introduce additional periodic fluctuations; A multi-point crossover strategy is used to generate offspring individuals of the parent individuals, wherein the multi-point crossover strategy is defined as: The multi-point crossover of natural selection and genetic variation is calculated by the following formula: y1=[x a (1),x a (2),...,x a (k1),x b (k1+1),...,x b (k2),x a (k2+1),...,x a (D)] y2=[x b (1),x b (2),...,x b (k1),x a (k1+1),...,x a (k2),x b (k2+1),...,x b (D)] Among them, y1 and y2 are the generated offspring individuals; x a and x b are two parent individuals; k1, k2, ..., k m is the randomly selected intersection position; m is the number of intersections; D is the dimension of the individual; Applying the Gaussian mutation formula, performing mutation operation on the offspring individuals to obtain new individuals; wherein the Gaussian mutation formula includes: Among them, y′(k) is the value of the mutated individual in the kth dimension; y(k) is the value of the original individual in the kth dimension; σ is a fixed standard deviation used to control the amplitude of the variation; randn is a random number drawn from the standard normal distribution; δ is a small perturbation coefficient used to introduce additional periodic fluctuations; rand() is a random number drawn from the uniform distribution [0, 1]; Adding the new individual to the population, and updating the population according to the fitness value; It is determined whether the population meets a preset population diversity threshold. If so, an optimal solution is output and used as a result of multi-objective optimization.

7. The method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank according to claim 1, characterized in that: Based on the final pressure regulation scheme, analyze the pressure sensor data at different locations of the buffer tank, combine the real-time ambient temperature, humidity and other external conditions and the changes in the gas composition in the tank, continuously optimize the pressure regulation strategy, ensure that the internal pressure of the buffer tank remains within the ideal range for a long time, and record the key parameters of each adjustment to generate data support for performance evaluation and system improvement. The specific steps include: Based on the final gas pressure regulation scheme, a high-precision pressure sensor array is used to monitor the pressure data at different positions of the buffer tank in real time, remove noise and enhance signal clarity to obtain real-time pressure data; Based on the real-time pressure data, combined with external conditions such as ambient temperature and humidity and changes in gas components in the tank, the effect of the current gas pressure regulation strategy is evaluated, and a gas pressure regulation effect evaluation report is generated; Based on the gas pressure regulation effect evaluation report, the gas pressure regulation strategy is continuously adjusted and optimized to ensure that the gas pressure inside the buffer tank remains within the ideal range for a long time and generate an optimized gas pressure regulation strategy; Based on the optimized gas pressure regulation strategy, key parameters are recorded during the regulation process, including the time of gas pressure regulation, gas pressure values ​​before and after regulation, environmental conditions, gas composition changes, and other information, to generate a detailed regulation log; By using the detailed regulation log, regular performance evaluations are performed to analyze the effectiveness of the gas pressure regulation strategy, identify potential problems and improvement points, and generate data support for performance evaluation and system improvement.

8. A system for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank, characterized in that: include: A processing module is used to monitor the air pressure in the buffer tank in real time using a high-precision pressure sensor array, pre-process the collected data, remove noise and enhance signal clarity, and generate an air pressure regulation start signal when it is detected that the air pressure fluctuation exceeds a preset threshold; A regulating module, for dynamically adjusting and optimizing the gas replenishment or discharge rate according to the gas pressure regulation start signal using an adaptive neural fuzzy inference system and a nonlinear control algorithm of a particle swarm optimization, to ensure that the gas pressure fluctuation is effectively offset, and to generate a preliminary gas pressure regulation strategy; The adjustment module, when the air pressure fluctuation tends to be flat and reaches a preset stable range, uses a multi-objective genetic algorithm to automatically adjust the gas replenishment or discharge rate to the minimum level required to maintain stability based on the preliminary air pressure adjustment strategy, while taking into account the system energy efficiency ratio and equipment service life, to generate a final air pressure adjustment plan; The optimization module analyzes the pressure sensor data at different locations of the buffer tank based on the final gas pressure regulation plan, and continuously optimizes the gas pressure regulation strategy in combination with external conditions and changes in the gas composition in the tank to ensure that the gas pressure inside the buffer tank is within the ideal range. It also records the key parameters of each adjustment and generates data support for performance evaluation and system improvement.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a method for balancing gas pressure fluctuations and stabilizing pressure in a buffer tank as described in any one of claims 1 to 7 is implemented.

Images