Industrial clean workshop air conditioning system intelligent regulation and control method and system based on production environment parameter prediction

Abstract

The invention discloses an intelligent regulation and control method and system for an industrial clean workshop air conditioning system based on production environment parameter prediction. The intelligent regulation and control method comprises the steps that an operation and maintenance management database, a random forest regression model and a joint simulation platform are built; predicting the operation and maintenance data of the air conditioning system based on the current weather variable factors and the random forest regression model; selecting a reference working condition point close to the current weather variable factor in an operation and maintenance management database; performing simulation by taking the historical simulation data and the historical operation and maintenance data corresponding to the reference working condition points as initial values of the platform to obtain risk point data and simulation operation and maintenance data; calculating recommended operation and maintenance data under the current weather variable factor by using the simulation operation and maintenance data and the prediction operation and maintenance data; and the air conditioning system is adjusted based on the risk point data and the recommended operation and maintenance data. According to the method, the air conditioning system control strategy is jointly determined by using the operation and maintenance data predicted by the model and the operation and maintenance simulated by the joint simulation platform, accurate recommended operation and maintenance data is provided for the current weather variable factor, and the control precision and stability of the air conditioning system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optimization control of HVAC systems, and in particular to an intelligent control method and system for industrial clean room air conditioning systems based on production environment parameter prediction. Background Art

[0002] In high-tech factory production environments, existing air conditioning systems often rely on feedback regulation after indoor environmental parameters reach preset thresholds. These methods, such as proportional-integral-derivative (PID) control or programmable logic controllers (PLCs), primarily rely on comparing actual parameters (such as temperature and humidity) monitored by indoor environmental sensors with preset values. When actual parameters deviate from these values, the air conditioning system's operating state is adjusted, such as by adjusting the air supply volume or chilled water flow rate, to restore indoor environmental stability. However, the regulatory effect of feedback control lags behind the disturbance effect and exhibits a hysteresis, causing indoor environmental parameters to fluctuate within a short period of time, impacting the stability of the production environment.

[0003] Existing model predictive control combines feedback control with feedforward control. The prediction model predicts the disturbance, achieving feedforward control. The predicted value is then corrected using the error between the predicted and measured values, achieving feedback control. The corrected predicted value is then fed into a rolling optimization module, where an optimization algorithm is used to solve the objective function. The first control vector obtained from the result becomes the controller's output signal at the next moment, achieving rolling optimization. However, data quality and integrity are crucial to model prediction accuracy. Currently, the accuracy of model predictive control is hampered by a number of issues, including a lack of large datasets to train the algorithm and significant discrepancies between the characteristics of the training data and subsequent real-world data. Summary of the Invention

[0004] Purpose of the invention: The purpose of the present invention is to provide an intelligent control method and system for industrial clean room air-conditioning systems based on the prediction of production environment parameters, so as to improve the accuracy and stability of air-conditioning system control and reduce the lag of control.

[0005] Technical solution: To achieve the above-mentioned purpose, the present invention provides an intelligent control method for an industrial clean room air conditioning system based on production environment parameter prediction, comprising the following steps:

[0006] S1: Build an operation and maintenance management database, including multiple sets of historical data. Each set of historical data includes weather variable factors with historical timestamps and historical forecast operation and maintenance data, historical simulation data, and historical operation and maintenance data corresponding to the weather variable factors.

[0007] S2: Establish a random forest regression model between weather variables and historical operation and maintenance data;

[0008] S3: Obtain current weather variables, use the random forest regression model to make predictions, obtain predicted operation and maintenance data, and store it in the operation and maintenance management database;

[0009] S4: Based on the current weather variable factors, a sensitivity analysis is performed on the weather variable factors in the operation and maintenance management database, and the operating point with the most similar sensitive conditions is used as the reference operating point close to the current weather variable factors;

[0010] S5: Build a joint simulation platform, including the factory building complex simulation model, the air conditioning system simulation model, and the factory production environment simulation model;

[0011] S6: Use the historical simulation data and historical operation and maintenance data corresponding to the adjacent reference operating point as the initial values ​​of the joint simulation platform to simulate, obtain the risk point data and simulated operation and maintenance data under the current weather variable factors, and store them in the operation and maintenance management database;

[0012] S7: Perform weighted calculation on the simulated operation and maintenance data and the predicted operation and maintenance data to obtain recommended operation and maintenance data under the current weather variable factors, and store the data in the operation and maintenance management database;

[0013] S8: Upload the monitoring risk point data and recommended operation and maintenance data to the terminal to realize automatic or manual adjustment of the air conditioning system.

[0014] Among them, the weather variable factors described in S1 include air pressure, weather conditions, precipitation probability, precipitation amount, temperature, perceived temperature, relative humidity, wind direction, wind speed, gusts, and cloud cover; the operating point represents the operation and maintenance data of the air-conditioning system under specific weather variable factors; the historical simulation data includes historical risk point data and historical simulation data; the operation and maintenance data of the air-conditioning system includes but is not limited to cooling water temperature, cooling water flow, chilled water temperature, chilled water flow, supply air temperature, supply air volume, return air volume, fresh air volume, clean room temperature, clean room humidity, clean room pressure and particle number, water valve opening, air valve opening, equipment start and stop records, fault records, alarm information and abnormal records.

[0015] Among them, the random forest regression model established between weather variable factors and historical operation and maintenance data as described in S2 includes:

[0016] S201. Data preprocessing: quantify, clean, and standardize the weather variables and historical operation and maintenance data coding methods in each set of historical data;

[0017] S202. Establish a random forest regression model: Use the preprocessed weather variable factors in each set of data as the feature variable X, and the historical operation and maintenance data as the target variable Y, train the random forest regression model, and obtain a trained random forest regression model.

[0018] Among them, the method for S4 to obtain the reference operating point through sensitivity analysis is:

[0019] S401. Calculate the feature importance score of the weather variable factor in each set of historical data using the trained random forest model, and calculate the weight of the weather variable factor based on the feature importance;

[0020] S402: Match the current weather variable factor with the weather variable factor in each set of historical data. For each piece of historical data, calculate the weighted Euclidean distance between the current weather variable factor and the historical weather variable factor using weights, and calculate the weighted Euclidean distance between the current expected operating point and the historical operating point.

[0021] S403: traverse the historical data, calculate the comprehensive distance of each set of historical data, and select the operating point corresponding to the historical data with the smallest comprehensive distance as the reference operating point close to the current weather variable factor.

[0022] Among them, the joint simulation platform described in S5 adopts CAE technology (computer-aided engineering) and modelica language, in which the factory building complex simulation model is the top-level model, providing external environment dynamic data as simulation input conditions for the air-conditioning system simulation model and the factory production environment simulation model; the air-conditioning system simulation model and the factory production environment simulation model receive the output data of the factory building complex simulation model as input conditions, and the air-conditioning system simulation model and the factory production environment simulation model transmit simulation results to each other as each other's input conditions, forming a closed-loop joint simulation platform.

[0023] In S7, the simulated operation and maintenance data and the predicted operation and maintenance data are weighted and calculated to obtain the recommended operation and maintenance data under the current weather variable factors, including:

[0024] Calculate the weight coefficient weight of simulation operation and maintenance data and predicted operation and maintenance data {CAE} 、weight {reg} ; Then the simulation operation and maintenance data prediction described in S6 {CAE} And the prediction operation data of the random forest regression model described in S3 {reg} Perform weighted calculations to obtain the recommended operation and maintenance data prediction under the current weather variable factors {final} :

[0025] prediction {final}=weight {reg} ×prediction {reg} +weight {CAE} ×prediction {CAE} .

[0026] Among them, the weight coefficients of simulated operation and maintenance data and predicted operation and maintenance data are weight {CAE} 、weight {reg} The calculation method is:

[0027] Calculate the historical error between the historical forecast operation and maintenance data and the historical operation and maintenance data corresponding to each historical weather variable factor in the operation and maintenance management database, and set the forecast operation and maintenance data error to obey a certain probability distribution;

[0028] Calculate the historical error between the historical simulation data and the historical operation and maintenance data corresponding to each historical weather variable factor in the operation and maintenance management database, and set the error of the simulation operation and maintenance data to obey a certain probability distribution;

[0029] Calculate the probability density pdf of the error in the predicted operation and maintenance data based on the probability distribution {reg} and the probability density of the simulation operation and maintenance data error pdf {CAE} sum:

[0030] pdf {total} =pdf {reg} +pdf {CAE} ,

[0031] The weight coefficient of the predicted operation and maintenance data corresponding to the random forest regression model is:

[0032]

[0033] The weight coefficient of the simulation operation and maintenance data corresponding to the joint simulation platform is:

[0034]

[0035] The present invention provides an intelligent control system for an industrial clean room air conditioning system based on production environment parameter prediction, comprising:

[0036] Database module: Build an operation and maintenance management database, including multiple sets of historical data. Each set of historical data includes weather variable factors with historical timestamps and historical forecast operation and maintenance data, historical simulation data, and historical operation and maintenance data corresponding to the weather variable factors.

[0037] Prediction model building module: establish a random forest regression model between weather variable factors and historical operation and maintenance data;

[0038] Predictive operation and maintenance data generation module: obtains current weather variable factors, uses random forest regression model to make predictions, and obtains predicted operation and maintenance data;

[0039] Reference operating point acquisition module: Based on the current weather variable factors, sensitivity analysis is performed on the weather variable factors in the operation and maintenance management database, and the operating point with the most similar sensitive conditions is used as the reference operating point close to the current weather variable factors;

[0040] Joint simulation platform building module: Build a joint simulation platform, including the factory building complex simulation model, air conditioning system simulation model and factory production environment simulation model;

[0041] Simulation data generation module: Uses historical simulation data and historical operation and maintenance data corresponding to the adjacent reference operating point as the initial values ​​of the joint simulation platform to simulate, obtain risk point data and simulated operation and maintenance data under the current weather variable factors, and stores them in the operation and maintenance management database;

[0042] Recommended operation and maintenance data generation module: performs weighted calculation on simulated operation and maintenance data and predicted operation and maintenance data to obtain recommended operation and maintenance data under current weather variable factors;

[0043] Data upload module: uploads monitoring risk point data and recommended operation and maintenance data to the terminal to realize automatic or manual adjustment of the air-conditioning system.

[0044] Beneficial effects: The present invention has the following advantages: 1. By establishing a random forest regression model, the present invention can predict the operation and maintenance needs of the air-conditioning system according to the current weather variable factor values, thereby predicting the operation and maintenance needs of the air-conditioning system before the production environment parameters fluctuate, reducing the control lag of the air-conditioning system; 2. By building a joint simulation platform, model predictive control can be realized on the basis of a small number of data sets, and at the same time, early warning of production environment risk points can be given, providing a scientific basis for operation and maintenance decisions; 3. The predictive control of the random forest regression model is preliminarily realized using a small number of data sets, and the simulation results of the joint simulation platform and the prediction results of the random forest regression model are combined through weighted calculation to determine the control strategy, which can provide accurate recommended operation and maintenance data under the current weather variable factors, thereby improving the accuracy and stability of the air-conditioning system control. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of the process of this method. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is described in detail below with reference to the embodiments and drawings.

[0047] like Figure 1 As shown, the intelligent control method of the industrial clean room air conditioning system based on production environment parameter prediction according to the present invention includes the following steps:

[0048] 1. Build an operation and maintenance management database.

[0049] The database includes multiple sets of historical data, each set of historical data includes weather variable factors with historical timestamps and historical forecast operation and maintenance data, historical simulation data, and historical operation and maintenance data corresponding to the weather variable factors. Among them, weather variable factors include air pressure, weather conditions, precipitation probability, precipitation amount, temperature, perceived temperature, relative humidity, wind direction, wind speed, gusts, cloud cover, etc.; operating point represents the operation and maintenance setting data of the air conditioning system under specific weather variable factors; the historical simulation data includes historical risk point data and historical simulation data; the operation and maintenance data of the air conditioning system includes cooling water temperature, cooling water flow, chilled water temperature, chilled water flow, supply air temperature, supply air volume, return air volume, fresh air volume, clean room temperature, clean room humidity, clean room pressure and particle count, water valve opening, air valve opening, equipment start and stop records, fault records, alarm information, and abnormal records.

[0050] 2. Establish a random forest regression model between weather variable factors and historical operation and maintenance data.

[0051] 1. Data preprocessing: Quantify the weather variable factors and historical operation and maintenance data coding methods in each set of historical data (for example, clear is coded as 4, cloudy is coded as 3, overcast is coded as 2, and rain is coded as 1), cleanse, and standardize them.

[0052] Cleaning is used to check whether there are missing values ​​in the data. For missing values, different methods are used to process them according to the characteristics of the data. For example, for numerical data (such as temperature, humidity, water volume, wind volume, etc.), the median or mean is used to fill in; for categorical data (such as wind direction, weather conditions), the most common category of the three days before and after is used to fill in; for outliers, they are identified by drawing box plots of the data and other methods. If the outliers are found to be significantly deviated from the normal range, consider deleting them or correcting them.

[0053] Data standardization is to calculate the mean and standard deviation of numerical features such as "weather conditions (quantified)", "precipitation (mm)", "wind force (level)", "temperature (°C)", and "humidity (%)" using the following formula to standardize them so that the mean is close to 0 and the standard deviation is close to 1.

[0054]

[0055] Among them, x is the weather variable factor characteristic value, μ is the mean of the characteristic, σ is the standard deviation, and Z is the standardized value.

[0056] 2. Establish a random forest regression model: The pre-processed weather variable factors in each set of historical data are used as feature variables X (such as quantified "weather conditions", "precipitation (mm)", "wind force (level)", "wind direction", "temperature (℃)", "humidity (%)"), and historical operation and maintenance data are used as target variables Y (such as "cooling water temperature (℃)", "chilled water temperature (℃)", "supply air temperature (℃)" of each unit, "supply air volume (m 3 / h)” and “risk point data” in the production workshop) to train the random forest regression model.

[0057] 3. Obtain current weather variable factors (such as "weather conditions", "precipitation (mm)", "wind force (level)", "wind direction", "temperature (°C)", and "humidity (%)") in real time, perform preprocessing, and use the trained random forest regression model to make predictions to obtain predicted operation and maintenance data.

[0058] 4. Based on the current weather variables, a sensitivity analysis is conducted on the weather variables in the operation and maintenance management database, and the operating point with the most similar sensitive conditions is used as the reference operating point close to the current weather variables. Specifically:

[0059] 1. Feature importance evaluation and weight calculation: Use the trained random forest model to calculate feature importance and obtain the importance score of each feature. For a model with n features, the importance scores are:

[0060] importance scores =[score1,score2,...,scoren];

[0061] The weights are:

[0062]

[0063] 2. Calculate the weighted Euclidean distance: Match the current weather variable factors with the weather variable factors in the historical data. For each piece of historical data, use the weight to calculate the weighted Euclidean distance between the current weather variable factors and the historical weather variable factors. At the same time, calculate the weighted Euclidean distance between the current expected operating point and the historical operating point.

[0064] The current weather variable factors are expressed as:

[0065] current {weather} =[s,p,w,d,t,h],

[0066] Among them, s, p, w, d, t, and h represent the pre-processed weather conditions, precipitation, wind speed, wind direction, temperature, and humidity, respectively;

[0067] The historical weather variables are:

[0068] hsitory {weather} =[s h ,p h ,w h ,d h ,t h ,h h ],

[0069] Among them, s h ,p h ,w h ,d h ,t h ,h h Respectively represent historical data of weather conditions, precipitation, wind speed, wind direction, temperature, and humidity;

[0070] The weight of each factor is:

[0071] weights=[w s ,w p ,w w ,w d ,w t ,w h ],

[0072] Among them, w s ,w p ,w w ,w d ,w t ,w h Weights corresponding to weather conditions, precipitation, wind speed, wind direction, temperature, and humidity;

[0073] The weighted Euclidean distance calculation formula between the current weather variable factors and the historical weather variable factors is:

[0074] distance=np.sqrt(w s ×(ss h ) 2 +w p ×(pp h ) 2 +w w ×(ww h ) 2 +w d ×(dd h ) 2 +w t ×(tt h ) 2 +w h ×(hh h ) 2 .

[0075] The current expected operating point data is expressed as:

[0076] current {condition} =[Q_c,T_c,Q_i,T_i,V_a,T_a],

[0077] Among them, Q_c, T_c, Q_i, T_i, V_a, and T_a represent the chilled water flow, chilled water temperature, cooling water flow, cooling water temperature, supply air volume, and supply air temperature of each unit at the current expected operating point, respectively;

[0078] The historical operating point data is expressed as:

[0079] history {condition} =[Q_c h ,T_c h ,Q_i h ,T_i h ,V_a h ,T_a h ],

[0080] Among them, Q_c h ,T_c h ,Q_i h ,T_i h ,V_a h ,T_a h Respectively represent the historical data of each unit's chilled water flow, chilled water temperature, cooling water flow, cooling water temperature, supply air volume, and supply air temperature.

[0081] The weight of each factor is expressed as:

[0082] weights {condition} =[w Q_c ,w T_c ,w Q_i ,w T_i ,w V_a ,w T_a ]

[0083] Among them, w Q_c ,w T_c ,w Q_i ,w T_i ,w V_a ,w T_a The weights corresponding to the chilled water flow, chilled water temperature, cooling water flow, cooling water temperature, supply air volume, and supply air temperature of each unit.

[0084] The weighted Euclidean distance calculation formula between the current expected operating point and the historical operating point is expressed as:

[0085] distance {condition} =np.sqrt(wQ_c ×(Q_c-Q_c h ) 2 +w T_c ×(T_c-T_c h ) 2 +w Q_i ×(Q_i-Q_i h ) 2 +w T_i ×(T_i-T_i h ) 2 +w V_a ×(V_a-V_a h ) 2 +w T_a ×(T_a-T_a h ) 2 .

[0086] 3. Traverse the historical data and calculate the comprehensive distance of each set of historical data, that is, the sum of the weighted Euclidean distance between the current weather variable factor and the historical weather variable factor and the weighted Euclidean distance between the current expected operating point and the historical operating point. Select the operating point corresponding to the historical data with the smallest comprehensive distance as the reference operating point close to the current weather variable factor.

[0087] 5. Build a joint simulation platform, including a simulation model of the factory building complex, a simulation model of the air-conditioning system, and a simulation model of the factory production environment.

[0088] Factory complex simulation model: A geometric model of all buildings within the factory was created, using simulations encompassing flow, heat, and pollutant physics. This model considered varying wind directions, upstream pollution sources (air pollutants from surrounding factories, such as power plants and electronics factories), and upstream temperature sources (such as air conditioning exhaust and substations). The resulting simulated data, including factory airflow, temperature gradients, and pollutant diffusion paths, was then passed to other simulation models for use as boundary inputs.

[0089] Air conditioning system simulation model: A modular simulation model is constructed based on the Modelica language, including air conditioning units, control systems, piping networks, etc. The plant building complex simulation model and the factory production environment simulation model provide input conditions for this model, and output air conditioning system operating parameters (such as chilled water flow, air supply volume, valve opening) and control signals (such as PID output value and air valve adjustment instructions).

[0090] Factory production environment simulation model: simulates the airflow organization, temperature and humidity, pressure, pollutant concentration, etc. in the production area. The simulation results of the factory building complex simulation model and the air conditioning system simulation model provide input boundary conditions for this model. The real-time values ​​of temperature and humidity, pressure difference, and particle concentration at each monitoring point in the clean room can be obtained, as well as risk point warning data (such as local temperature exceeding the standard and insufficient airflow speed).

[0091] The above three models realize coupled simulation: the factory building complex simulation model is the top-level model, which provides dynamic data of the external environment as the input conditions for the simulation of other models; the air-conditioning system simulation model and the factory production environment simulation model receive the output data of the factory building complex simulation model as input conditions, and at the same time, the two transmit the generated results to each other as each other's input, forming a closed loop.

[0092] 6. Use the historical simulation data and historical operation and maintenance data corresponding to the nearby reference operating points as the initial values ​​of the joint simulation platform to simulate and obtain the risk point data and simulation operation and maintenance data under the current weather variable factors.

[0093] Because climate fluctuations are not particularly drastic, historical simulation data can be used as initial values ​​to accelerate simulation convergence. Simulated indoor environmental parameters and monitoring points are used as risk point data (e.g., whether temperatures are locally too cold or too hot, or particle concentrations exceed standards), to issue production environment warnings.

[0094] 7. Perform weighted calculation on the simulated operation and maintenance data and the operation and maintenance data predicted by the random forest regression model to calculate the recommended operation and maintenance data under the current weather variable factors.

[0095] 1. Calculate the predicted value y of the random forest regression model based on the weather variable factors at historical timestamps {true} and the true value y {reg} Historical errors {reg} =y {true} -y {reg} , assuming that historical errors obey a certain probability distribution, we further estimate the mean and variance of the probability distribution;

[0096] If we assume that the historical error of the random forest regression model obeys the normal distribution, we can estimate its mean and variance and obtain the normal distribution N(μ {reg} ,σ {reg} ), where μ {reg} is the historical error mean, σ {reg} is the historical error variance.

[0097] 2. Compute historical errors on the joint simulation platform {CAE} , that is, the historical error between the operation and maintenance data simulated by the joint simulation platform under historical operating points and the actual operation and maintenance data, and determine that it obeys a certain probability distribution, and estimate its mean and variance. If there is no actual historical error data, a mean and variance are first determined based on experience or preliminary experiments, and then adjusted based on more data to obtain the historical error of the joint simulation platform that obeys a normal distribution N(μ {CAE} ,σ {CAE} ), where μ CAE is the historical error mean, σ CAEis the historical error variance.

[0098] 3. Calculate the weight coefficients of simulation data and prediction data based on the random forest regression model and the output results of the joint simulation platform: First, calculate the probability density pdf of the error in the predicted operation and maintenance data based on the probability distribution {reg} and the probability density of the simulation operation and maintenance data error pdf {CAE} Sum: pdf {total} =pdf {reg} +pdf {CAE} .

[0099] The weight coefficient of the predicted operation and maintenance data corresponding to the random forest regression model is:

[0100]

[0101] The weight coefficient of the simulation operation and maintenance data corresponding to the joint simulation platform is:

[0102]

[0103] 4. Simulate the operation and maintenance data prediction in step 6 {cfd} And random forest regression model prediction operation and maintenance data prediction {reg} Perform weighted calculations to obtain the recommended operation and maintenance data prediction under the current weather variable factors {final} :

[0104] prediction {final} =weight {reg} ×prediction {reg} +weight {cfd} ×prediction {cfd} .

[0105] 8. Upload the monitoring risk point data and recommended operation and maintenance data to the terminal to notify the operation and maintenance management personnel. The terminal includes but is not limited to the central control room, the operation and maintenance personnel's mobile phone, etc. The operation and maintenance personnel adjust the operating status of the air-conditioning system according to the recommended operation and maintenance data or realize automatic adjustment of the air-conditioning system by pre-implanting the corresponding function in the automatic control system.

[0106] Based on the actual operating status of the air-conditioning system, the current risk point data, the operating point of the air-conditioning system, and the actual operation and maintenance data are recorded, and then uploaded to the operation and maintenance management database together with the operation and maintenance data predicted by the random forest regression model and the historical simulation data of the joint simulation platform.

Claims

1. An intelligent control method for industrial clean room air conditioning system based on production environment parameter prediction, characterized in that: The following steps are involved: S1: Build an operation and maintenance management database, including multiple sets of historical data. Each set of historical data includes weather variable factors with historical timestamps and historical forecast operation and maintenance data, historical simulation data, and historical operation and maintenance data corresponding to the weather variable factors. S2: Establish a random forest regression model between weather variables and historical operation and maintenance data; S3: Obtain current weather variables, use the random forest regression model to make predictions, obtain predicted operation and maintenance data, and store it in the operation and maintenance management database; S4: Based on the current weather variable factors, a sensitivity analysis is performed on the weather variable factors in the operation and maintenance management database, and the operating point with the most similar sensitive conditions is used as the reference operating point close to the current weather variable factors; S5: Build a joint simulation platform, including the factory building complex simulation model, the air conditioning system simulation model, and the factory production environment simulation model; S6: Use the historical simulation data and historical operation and maintenance data corresponding to the adjacent reference operating point as the initial values ​​of the joint simulation platform to simulate, obtain the risk point data and simulated operation and maintenance data under the current weather variable factors, and store them in the operation and maintenance management database; S7: Perform weighted calculation on the simulated operation and maintenance data and the predicted operation and maintenance data to obtain recommended operation and maintenance data under the current weather variable factors, and store the data in the operation and maintenance management database; S8: Upload the monitoring risk point data and recommended operation and maintenance data to the terminal to realize automatic or manual adjustment of the air conditioning system.

2. The intelligent control method for industrial clean room air conditioning system according to claim 1 is characterized in that: The weather variable factors described in S1 include air pressure, weather conditions, precipitation probability, precipitation amount, temperature, perceived temperature, relative humidity, wind direction, wind speed, gusts, and cloud cover; the operating point represents the operation and maintenance data of the air-conditioning system under specific weather variable factors.

3. The intelligent control method for industrial clean room air conditioning system according to claim 1 is characterized in that: The historical simulation data described in S1 include historical risk point data and historical simulation operation and maintenance data; the operation and maintenance data of the air-conditioning system include but are not limited to cooling water temperature, cooling water flow, chilled water temperature, chilled water flow, supply air temperature, supply air volume, return air volume, fresh air volume, clean room temperature, clean room humidity, clean room pressure and particle number, water valve opening, air valve opening, equipment start and stop records, fault records, alarm information and abnormality records.

4. The intelligent control method for industrial clean room air conditioning system according to claim 1 is characterized in that: S2 establishes a random forest regression model between weather variables and historical operation and maintenance data, including: S201. Data preprocessing: quantify, clean, and standardize the weather variables and historical operation and maintenance data coding methods in each set of historical data; S202. Establish a random forest regression model: Use the preprocessed weather variable factors in each set of data as the feature variable X, and the historical operation and maintenance data as the target variable Y, train the random forest regression model, and obtain a trained random forest regression model.

5. The intelligent control method for industrial clean room air conditioning system according to claim 1 is characterized in that: The method for S4 to obtain the reference operating point through sensitivity analysis is: S401. Calculate the feature importance score of the weather variable factor in each set of historical data using the trained random forest model, and calculate the weight of the weather variable factor based on the feature importance; S402: Match the current weather variable factor with the weather variable factor in each set of historical data. For each piece of historical data, calculate the weighted Euclidean distance between the current weather variable factor and the historical weather variable factor using weights, and calculate the weighted Euclidean distance between the current expected operating point and the historical operating point. S403: traverse the historical data, calculate the comprehensive distance of each set of historical data, and select the operating point corresponding to the historical data with the smallest comprehensive distance as the reference operating point close to the current weather variable factor.

6. The intelligent control method for industrial clean room air conditioning system according to claim 1 is characterized in that: S5 The factory building complex simulation model is a top-level model, which provides external environment dynamic data as simulation input conditions for the air-conditioning system simulation model and the factory production environment simulation model; the air-conditioning system simulation model and the factory production environment simulation model receive the output data of the factory building complex simulation model as input conditions, and the air-conditioning system simulation model and the factory production environment simulation model transmit simulation results to each other as each other's input conditions, forming a closed-loop joint simulation platform.

7. The intelligent control method for industrial clean room air conditioning system according to claim 1 is characterized in that: S7 performs weighted calculation on the simulated operation and maintenance data and the predicted operation and maintenance data to obtain the recommended operation and maintenance data under the current weather variable factors, including: Calculate the weight coefficient weight of simulation operation and maintenance data and predicted operation and maintenance data {CAE} 、weight {reg} ; Then the simulation operation and maintenance data prediction described in S6 {CAE} And the prediction operation data of the random forest regression model described in S3 {reg} Perform weighted calculations to obtain the recommended operation and maintenance data prediction under the current weather variable factors {final} : prediction {final} =weight {reg} ×prediction {reg} +weight {CAE} ×prediction {CAE} 。 8. The intelligent control method for industrial clean room air conditioning system according to claim 7 is characterized in that: The weight coefficient weight of the simulated operation and maintenance data and the predicted operation and maintenance data {CAE} 、weight {reg} They are: Among them, pdf {reg} is the probability density of the error in the predicted operation and maintenance data, pdf {CAE} is the probability density of the simulation operation and maintenance data error, pdf {total} =pdf {reg} +pdf {CAE} .

9. The intelligent control method for industrial clean room air conditioning system according to claim 8, characterized in that: The probability density of the predicted operation and maintenance data error and the probability density of the simulated operation and maintenance data error are obtained by: calculating the historical error between the historical predicted operation and maintenance data and the historical operation and maintenance data corresponding to each historical weather variable factor in the operation and maintenance management database, and setting the predicted operation and maintenance data error to obey the probability distribution; calculating the historical error between the historical simulation data and the historical operation and maintenance data corresponding to each historical weather variable factor in the operation and maintenance management database, and setting the simulated operation and maintenance data error to obey the probability distribution; Calculate the probability density pdf of the error in the predicted operation and maintenance data based on the probability distribution {reg} and the probability density of the simulation operation and maintenance data error pdf {CAE} .

10. An intelligent control system for industrial clean room air conditioning system based on production environment parameter prediction, characterized in that: include: Database module: Build an operation and maintenance management database, including multiple sets of historical data. Each set of historical data includes weather variable factors with historical timestamps and historical forecast operation and maintenance data, historical simulation data, and historical operation and maintenance data corresponding to the weather variable factors. Prediction model building module: establish a random forest regression model between weather variable factors and historical operation and maintenance data; Predictive operation and maintenance data generation module: obtains current weather variable factors, uses random forest regression model to make predictions, and obtains predicted operation and maintenance data; Reference operating point acquisition module: Based on the current weather variable factors, sensitivity analysis is performed on the weather variable factors in the operation and maintenance management database, and the operating point with the most similar sensitive conditions is used as the reference operating point close to the current weather variable factors; Joint simulation platform building module: Build a joint simulation platform, including the factory building complex simulation model, air conditioning system simulation model and factory production environment simulation model; Simulation data generation module: Uses historical simulation data and historical operation and maintenance data corresponding to the adjacent reference operating point as the initial values ​​of the joint simulation platform to simulate, obtain risk point data and simulated operation and maintenance data under the current weather variable factors, and stores them in the operation and maintenance management database; Recommended operation and maintenance data generation module: performs weighted calculation on simulated operation and maintenance data and predicted operation and maintenance data to obtain recommended operation and maintenance data under current weather variable factors; Data upload module: uploads monitoring risk point data and recommended operation and maintenance data to the terminal to realize automatic or manual adjustment of the air-conditioning system.

Images