Clean room intelligent operation adaptation method and system based on environmental constraint linkage

Abstract

This invention discloses a method and system for intelligent operation adaptation in cleanrooms based on environmental constraint linkage, relating to the field of cleanroom operation and adjustment technology. It includes: S1, real-time acquisition of multi-constraint operation data and data preprocessing; S2, analysis of the changing characteristics of the multi-constraint operation data, assessment of the urgency of environmental constraints, generation of multi-constraint urgency comparison results, determination of the current dominant constraint type, and output of priority control strategies; S3, using the changing characteristics of the multi-constraint operation data to determine the conflict between energy consumption costs and pressure difference benefits, adjusting the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level; S4, monitoring the operating frequency and changing characteristics of the supply fan, assessing the stability of the linkage control, and implementing optimized adjustment actions. This solves the problems of fixed priorities being difficult to adaptively adjust under dynamic multi-constraint conditions in cleanrooms, easily leading to constraint conflicts and mismatches, resulting in energy consumption fluctuations and operational instability.

Description

Technical Field

[0001] This invention relates to the field of cleanroom operation and regulation technology, specifically to a method and system for intelligent cleanroom operation adaptation based on environmental constraints. Background Technology

[0002] Cleanroom environments are widely used in high-cleanliness environments such as semiconductor manufacturing, biopharmaceuticals, precision electronics, and medical devices. Their core objective is to maintain a stable process environment within a controlled space through continuous regulation of air cleanliness, pressure gradient, temperature and humidity levels, and airflow organization. With increasing production process precision and expanded operational scale, cleanroom systems are increasingly characterized by multi-parameter coupling, frequent dynamic fluctuations, and a significant proportion of energy consumption. Cleanroom environment control has evolved from maintaining a single indicator to comprehensive operation management oriented towards multi-constraint coordination, becoming a crucial foundation for modern high-end manufacturing and the life sciences industry.

[0003] For example, invention patent CN114460885B discloses a cleanroom building management device, including a main management device and slave management devices. The main management device can communicate with multiple slave management devices via a WIFI network. The slave management devices collect environmental information within the room and manage smart appliances. The main management device includes a main control module, and connected to the main control module are a main power module, a door lock management module, a disinfection channel management module, a main WIFI communication module, and a 4G communication module. The door lock management module is used for opening and closing the disinfection channel door lock. The disinfection channel management module can monitor the status of people and goods within the disinfection channel. The main WIFI communication module is used to connect IP cameras and slave management devices. This invention facilitates centralized intelligent management and control, can detect and control the laboratory environment, and has a personnel-person separation disinfection management function, possessing good market application value.

[0004] For example, invention patent CN117170333A discloses a cleanroom environmental monitoring and management system, which includes an environmental monitoring module, a target screening module, a scheme planning module, a monitoring controller, an information acquisition module, and a disinfection suggestion module. The environmental monitoring module collects environmental parameter information at multiple sampling points in the cleanroom. The target screening module screens and identifies pollution source information. The scheme planning module identifies high-pollution areas based on pollution source information and generates environmental monitoring schemes. The monitoring controller sends equipment control parameters to the environmental parameter acquisition devices at each sampling point according to the environmental monitoring scheme, sets the parameters, processes the environmental parameter information collected from each sampling point according to the monitoring process information, and compares it with preset parameter thresholds to achieve environmental monitoring of the cleanroom. This application effectively improves the accuracy of environmental monitoring while reducing energy consumption.

[0005] However, existing technologies typically employ fixed thresholds and preset control priorities for multiple objectives such as temperature, humidity, pressure difference, particle concentration, and energy consumption, and adjust them in conjunction with actuators such as supply and exhaust air volume, temperature control settings, and filtration units. Due to varying operating conditions, such as personnel entry and exit, equipment start-up and shutdown, and low nighttime loads, the urgency and coupling relationships of each constraint dynamically change. Static priorities struggle to adjust the control order in a timely manner when constraints conflict, easily leading to mismatches such as "pressure difference satisfied but particle levels temporarily or locally exceeding limits" or "particle levels falling but energy consumption suddenly increasing per unit time, and airflow frequently fluctuating." This results in increased duration of cleanliness index exceedances, increased energy consumption and actuator actuation frequency, decreased operational stability, and difficulty in establishing a traceable "constraint conflict, control response, and result" chain for operation and maintenance optimization.

[0006] Therefore, in order to address the above issues, there is an urgent need for intelligent operation adaptation methods and systems for cleanrooms based on environmental constraints. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a method and system for intelligent operation adaptation of cleanrooms based on environmental constraint linkage, which solves the problems of fixed priorities being difficult to adaptively adjust under dynamic operating conditions with multiple constraints in cleanrooms, easily causing constraint conflicts and mismatches, and resulting in energy consumption fluctuations and operational instability.

[0009] Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solution: a cleanroom intelligent operation adaptation method based on environmental constraint linkage, comprising the following steps: S1, real-time acquisition of multi-constraint operation data, and time alignment, anomaly correction, and normalization preprocessing of the multi-constraint operation data; S2, analysis of the dynamic change characteristics of the preprocessed multi-constraint operation data, assessment of the urgency of environmental constraints, generation of multi-constraint urgency comparison results within a sliding time window, determination of the current dominant constraint type based on the comparison results, and output of a priority control strategy; S3, using the dynamic change characteristics of the multi-constraint operation data, conflict judgment of the relationship between energy consumption cost and pressure difference benefit in the linkage adjustment process, and adjustment of the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level based on the priority control strategy and conflict judgment results; S4, real-time monitoring of the supply fan operating frequency and change characteristics, assessment of linkage control stability, and implementation of optimization adjustment actions based on the stability assessment results.

[0011] Furthermore, the specific process of real-time acquisition of multi-constraint operation data and preprocessing of the multi-constraint operation data including time alignment, anomaly correction, and normalization is as follows: Real-time acquisition of multi-constraint operation data in the cleanroom, including particle concentration, cleanroom pressure difference, temperature, humidity, total operating power, and air supply fan operating frequency; Time alignment processing is performed on the multi-constraint operation data, and anomaly sampling points are identified using the median deviation detection method of a sliding time window. Interpolation correction is performed on the anomaly sampling points, and minimum-maximum normalization processing is performed on the multi-constraint operation data; Based on the preprocessed particle concentration, cleanroom pressure difference, and total operating power, the particle concentration change rate, pressure difference change rate, and total operating power change rate are obtained by dividing the difference between adjacent sampling times by the time interval; A sliding time window is constructed, and the mean values ​​of temperature, humidity, and total operating power within the window are calculated to obtain temperature reference values, humidity reference values, and total operating power reference values; A cleanroom operation adaptation database is established to store multi-constraint operation data, various change rates, and various reference values.

[0012] Furthermore, the dynamic change characteristics of the preprocessed multi-constraint operation data were analyzed, and the specific process for assessing the urgency of environmental constraints was as follows: Particle concentration and cleanroom pressure difference were read in real time, along with the corresponding rates of change in particle concentration and pressure difference; the positive component of the particle concentration change rate and the negative component of the pressure difference change rate were extracted; the sum of squares of the positive and negative components of the particle concentration change rate and the pressure difference change rate were calculated to obtain the sum of squares of the dynamic fluctuations of cleanroom constraints; the sum of squares of particle concentration and cleanroom pressure difference was calculated to obtain the baseline sum of squares of the cleanroom constraint scales; the sum of squares of the dynamic fluctuations of cleanroom constraints was divided by the baseline sum of squares of the cleanroom constraint scales, and then added to a base value and the natural logarithm was taken to obtain the environmental constraint urgency response value.

[0013] Furthermore, the specific process of generating multi-constraint urgency comparison results within the sliding time window is as follows: Based on the sliding time window, the mean and peak values ​​of the environmental constraint urgency response are calculated in real time. The mean and peak values ​​are multiplied and added together, and the natural logarithm is taken to obtain the environmental constraint urgency estimate, which is then normalized. The absolute differences between the current temperature, humidity, and total operating power and the corresponding reference values ​​are calculated respectively to obtain the temperature normalization deviation, humidity normalization deviation, and total operating power normalization deviation. The environmental constraint urgency estimate, temperature normalization deviation, humidity normalization deviation, and total operating power normalization deviation are combined to construct a multi-constraint urgency comparison set.

[0014] Furthermore, the specific process of determining the current dominant constraint type based on the comparison results and outputting the priority control strategy is as follows: Select the factor with the largest value from the multi-constraint urgency comparison set to determine the dominant constraint type; output the priority control results based on the dominant constraint type: when the estimated environmental constraint urgency value is the largest, particle concentration and cleanroom pressure difference are determined to be priority constraints; when the normalized deviation of total operating power is the largest, energy saving is determined to be a priority constraint; when the normalized deviation of temperature or humidity is the largest, temperature and humidity are determined to be priority constraints; write the multi-constraint urgency comparison set and the priority control results into the cleanroom operation adaptation database.

[0015] Furthermore, utilizing the dynamic change characteristics of multi-constraint operating data, the specific process for conflict judgment of the relationship between energy consumption cost and pressure difference benefit in the linkage regulation process is as follows: read the pressure difference change rate and the total operating power change rate; divide the square of the total operating power change rate by the sum of the square of the pressure difference change rate and the smallest positive number to obtain the control cost benefit ratio; add the control cost benefit ratio to a constant and take the natural logarithm to obtain the control action conflict judgment value.

[0016] Furthermore, combining the priority control strategy and conflict judgment results, the specific process for adjusting the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level is as follows: When particle concentration and cleanroom pressure difference are determined to be the priority constraints, and the control action conflict judgment value is less than the conflict threshold, the supply fan operating frequency is increased to increase the supply air volume, and the exhaust valve opening is simultaneously adjusted to maintain the target difference between the supply and exhaust air volumes; when particle concentration and cleanroom pressure difference are determined to be the priority constraints, and the control action conflict judgment value is greater than or equal to the conflict threshold, the increase in supply air volume is limited, and the supply and exhaust valve openings are coordinated and adjusted accordingly. The relative ratio of the air valve opening is used to maintain the differential pressure, and the filtration air volume level of the filter unit is increased synchronously. The filter unit is an FFU or an adjustable air volume filter module. When temperature and humidity are determined to be the primary constraints, the opening of the coil valve and the humidification and dehumidification actuator are adjusted in conjunction with each other according to the direction of the deviation of temperature and humidity from their respective reference values. When energy saving is determined to be the primary constraint, the increase in the operating frequency of the air supply fan is limited, and the opening of the air supply valve is reduced while the opening of the exhaust valve is adjusted synchronously, provided that the differential pressure constraint of the clean room is met. The control action conflict judgment value and linkage control strategy are written into the clean room operation adaptation database.

[0017] Furthermore, the specific process for evaluating the stability of the linkage control by real-time monitoring of the operating frequency and variation characteristics of the blower is as follows: The operating frequency of the blower is read in real time, and the difference between the operating frequencies of adjacent blowers is calculated at each sampling moment to obtain the change in blower frequency action; based on a sliding time window, the change in blower frequency action at each sampling point within the window is squared and accumulated to obtain the sum of squares of action jitter intensity; the operating frequency of the blower at each sampling point within the window is squared and accumulated to obtain the sum of squares of the operating scale baseline; the sum of squares of action jitter intensity is divided by the sum of the sum of squares of the operating scale baseline and the smallest positive number, and the opposite number is taken as the exponent for natural exponential calculation to obtain the stability maintenance value of the linkage control.

[0018] Furthermore, the specific process of implementing optimized adjustment actions based on the stability assessment results is as follows: At each sampling moment, the stability maintenance value of the linkage control is calculated in real time and compared with the stability threshold: when the duration of the linkage control stability maintenance value being lower than the stability threshold exceeds the allowable time threshold, it is determined that the current linkage control has a phenomenon of frequent actuator action, and a stability suppression command is output to limit the variation range of the operating frequency of the air supply fan; when the duration of the linkage control stability maintenance value being greater than or equal to the stability threshold exceeds the allowable time threshold, it is determined that the current linkage control process is stable, and it is allowed to continue to execute the air supply and exhaust adjustment and temperature and humidity adjustment actions according to the linkage control strategy; the linkage control stability maintenance value and the judgment result are written into the cleanroom operation adaptation database and stored in association with the environmental constraint urgent response value, control action conflict judgment value, and priority control result.

[0019] The second aspect of this invention provides a cleanroom intelligent operation adaptation system based on environmental constraint linkage, comprising: a constraint data acquisition and processing module, used to acquire multi-constraint operation data in real time, and perform time alignment, anomaly correction, and normalization preprocessing on the multi-constraint operation data; an urgency assessment and priority module, used to analyze the dynamic change characteristics of the preprocessed multi-constraint operation data, assess the urgency of environmental constraints, generate multi-constraint urgency comparison results within a sliding time window, determine the current dominant constraint type based on the comparison results, and output a priority control strategy; a conflict discrimination and linkage control module, used to use the dynamic change characteristics of multi-constraint operation data to discriminate the relationship between energy consumption cost and pressure difference benefit in the linkage adjustment process, and adjust the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level based on the priority control strategy and conflict discrimination results; and an operation evaluation and traceability learning module, used to monitor the operating frequency and change characteristics of the supply fan in real time, evaluate the stability of linkage control, and implement optimized adjustment actions based on the stability evaluation results.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects:

[0022] (1) This invention assesses the urgency of the dynamic changes in particle concentration and cleanroom pressure difference, and generates a comparison result of the urgency of multiple constraints within a sliding time window. It can determine the current dominant constraint type in real time under dynamic conditions such as personnel entry and exit and equipment start-up and shutdown. It breaks through the traditional fixed threshold and static priority control method, realizes the adaptive dominant switching between clean indicators, temperature and humidity constraints and energy-saving targets, and improves the real-time performance and matching of multi-objective regulation.

[0023] (2) By introducing a control action conflict discrimination method based on the rate of change of total operating power and the rate of change of differential pressure, this invention can identify the linkage mismatch situation of "rapid increase in energy consumption but limited improvement in differential pressure", and adjust the supply and exhaust valve ratio, the frequency increase of the supply fan and the filter unit filter air volume level accordingly, effectively suppressing constraint conflict problems such as sudden increase in energy consumption and frequent swing of air volume, and improving the economy and stability of linkage control strategy.

[0024] (3) In this invention, by real-time monitoring of the operating frequency and action change characteristics of the blower, a linkage control stability maintenance value is constructed, and under the condition of stability threshold triggering, a suppression command is output to limit the frequency change amplitude of the blower, thereby reducing the frequent action of the actuator and control jitter, improving the stability and long-term reliability of the cleanroom operation process, and avoiding the high-frequency oscillation of the control strategy under dynamic working conditions.

[0025] (4) This invention forms a traceable closed-loop operation link by associating and storing environmental constraints, urgent response values, control action conflict judgment values, priority control results and stability assessment results in the cleanroom operation adaptation database. This provides data basis for subsequent operation and maintenance review, strategy optimization and self-learning update, realizing the closed-loop evolution of cleanroom intelligent operation from single adjustment to continuous optimization, and enhancing the interpretability and long-term adaptability of the system.

[0026] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0027] Figure 1 A flowchart illustrating the intelligent operation adaptation method for cleanrooms based on environmental constraints.

[0028] Figure 2 This is a structural diagram of a cleanroom intelligent operation adaptation system based on environmental constraints.

[0029] Figure 3 A trend chart of environmental constraint-driven response values;

[0030] Figure 4 A flowchart for adapting a closed-loop linkage control system driven by multiple constraints in cleanrooms. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. As those skilled in the art will understand, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Please see Figures 1-4 This invention provides a technical solution: a cleanroom intelligent operation adaptation method based on environmental constraint linkage, such as... Figure 1 As shown, the process includes the following steps: S1, real-time acquisition of multi-constraint operation data, and preprocessing of the multi-constraint operation data including time alignment, anomaly correction, and normalization; S2, analysis of the dynamic change characteristics of the preprocessed multi-constraint operation data, assessment of the urgency of environmental constraints, generation of multi-constraint urgency comparison results within a sliding time window, determination of the current dominant constraint type based on the comparison results, and output of priority control strategy; S3, using the dynamic change characteristics of the multi-constraint operation data, conflict judgment of the relationship between energy consumption cost and pressure difference benefit in the linkage regulation process, and adjustment of the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level based on the priority control strategy and conflict judgment results; S4, real-time monitoring of the operating frequency and change characteristics of the supply fan, assessment of the linkage control stability, and implementation of optimization adjustment actions based on the stability assessment results.

[0033] Specifically, the process of real-time acquisition of multi-constraint operation data and preprocessing of the multi-constraint operation data including time alignment, anomaly correction, and normalization is as follows: Real-time acquisition of multi-constraint operation data in the cleanroom, including particle concentration, cleanroom pressure difference, temperature, humidity, total operating power, and air supply fan operating frequency; wherein, particle concentration is acquired in real time through a laser particle counter, cleanroom pressure difference is acquired through a pressure difference sensor, temperature and humidity are acquired through temperature and humidity sensors, total operating power is obtained through an energy metering module, and air supply fan operating frequency is read through the controller communication bus, thereby ensuring that each data has a clear physical source and a quantifiable measurement basis. Time alignment processing is performed on multi-constraint operational data. Ideally, time alignment uses a unified sampling period as a benchmark, mapping data with different sampling frequencies to the same timestamp sequence. A linear resampling method is used to fill in missing moments, ensuring comparability of different constraint quantities at the same sampling time. Anomaly sampling points are identified using a median deviation detection method with a sliding time window. Sudden noise or abnormal sensor drift is identified by calculating the deviation between the sampled value and the median of the window. Interpolation correction is performed on the abnormal sampling points. Ideally, linear interpolation of adjacent normal sampling points is used to restore the continuous data sequence, avoiding misjudgments of subsequent urgency assessments due to outliers. The sliding time window is a continuous sampling data sequence interval ending at the current sampling time, used to statistically analyze the steady-state distribution characteristics of cleanroom operational data within a local time scale. Its value is determined based on the sampling period and typical time scales of cleanroom environmental changes. Preferably, when the sampling period is 1 to 60 seconds, the sliding time window length is 10 to 120 seconds. Minimum-maximum normalization is performed on multi-constraint operational data. The normalization benchmark is determined based on the minimum and maximum values ​​of the historical operational interval, uniformly mapping particle concentration, pressure difference, temperature, humidity, and power data to the range of 0 to 1, thereby eliminating dimensional differences and improving the consistency of multi-constraint comparisons. Based on the pre-processed particle concentration, cleanroom pressure difference, and total operating power, the difference between adjacent sampling times is divided by the time interval to obtain the particle concentration change rate, pressure difference change rate, and total operating power change rate. The time interval is the actual time difference between adjacent sampling times, and the change rate is used to characterize the evolution speed and fluctuation trend of constraint indicators under dynamic operating conditions. A sliding time window is constructed, preferably determined based on the temperature and humidity regulation inertia and energy consumption fluctuation time scale. Preferably, when the sampling period is 1 to 60 seconds, the sliding time window length is 10 to 120. The mean values ​​of temperature, humidity, and total operating power within the window are calculated to obtain temperature reference values, humidity reference values, and total operating power reference values. These reference values ​​characterize the stable benchmark level of the cleanroom in the current operational stage, providing a unified reference for subsequent deviation calculations and constraint urgency comparisons.Establish a cleanroom operation adaptation database and store multi-constraint operation data, various change rates, and various reference values ​​to form a traceable historical operation record. This database supports continuous invocation and self-learning updates for subsequent dynamic priority generation, constraint conflict identification, and linkage control strategy optimization processes.

[0034] In this implementation plan, real-time acquisition and unified preprocessing of multi-constraint operational data, such as particle concentration, cleanroom pressure difference, temperature and humidity, operating power, and fan frequency, combined with time alignment, anomaly correction, and normalization, ensure that multi-source constraint information is comparable and stable and reliable at the same scale. Furthermore, through rate of change extraction and reference benchmark construction, the dynamic evolution trend of cleanroom environmental constraints can be quantified, providing a consistent data foundation and traceable support for subsequent urgency assessment, dominant constraint determination, and the generation of linkage control strategies. This effectively improves the real-time adaptability, stability, and control optimization capabilities of cleanroom operation.

[0035] Specifically, the process of analyzing the dynamic changes in preprocessed multi-constraint operational data and assessing the urgency of environmental constraints involves real-time reading of particle concentration and cleanroom pressure differential, along with the corresponding rates of change in particle concentration and pressure differential. Particle concentration characterizes the level of suspended particulate contamination in the cleanroom air, while cleanroom pressure differential characterizes the positive pressure isolation capability of the clean area relative to adjacent areas. Both are core physical indicators of cleanroom constraints and can be continuously acquired in real-time by sensors. The positive component of the particle concentration change rate and the negative component of the pressure differential change rate are extracted. The positive component of the particle concentration change rate depicts the worsening trend of increasing particle concentration, while the negative component of the pressure differential change rate depicts the worsening trend of weakened isolation capability due to decreasing pressure differential. This ensures that the urgency assessment triggers a response only when cleanroom constraints evolve in an unfavorable direction. The sum of squares of the positive component of the particle concentration change rate and the negative component of the pressure difference change rate is calculated to obtain the sum of squares of the dynamic fluctuations of the cleanroom constraint. The squaring operation enhances the sensitivity to rapid abrupt disturbances, significantly increasing the dynamic fluctuation term when particle concentration suddenly rises or pressure difference drops sharply, thus reflecting the urgency of constraint deterioration. The sum of squares of the particle concentration and the cleanroom pressure difference is calculated to obtain the baseline sum of squares of the cleanroom constraint scale. This baseline sum of squares characterizes the operational magnitude of the cleanroom constraint at the current sampling time, thereby normalizing the sum of squares of the dynamic fluctuations and avoiding incomparability of urgency response values ​​under different dimensions and operational levels. The environmental constraint urgency response value is obtained by dividing the sum of squares of the dynamic fluctuations of the cleanroom constraint by the baseline sum of squares of the cleanroom constraint scale and adding it to a base, then taking the natural logarithm. The natural logarithm operation is used to compress the numerical amplitude under extreme fluctuation conditions, improving the smoothness of the urgency response value. The environmental constraint urgency response value is based on the deterioration and evolution characteristics of particle concentration and differential pressure constraints during cleanroom operation. By extracting the positive component of the particle concentration change rate and the negative component of the differential pressure change rate, it focuses on characterizing two adverse trends: increased contamination and decreased isolation capacity. Furthermore, it uses square operations to enhance the sensitivity to sudden disturbances and normalizes the value to the square benchmark of the current constraint scale, making the urgency level comparable under different operating conditions. Finally, it outputs the urgency response value in logarithmic form, achieving a smooth quantitative assessment of the urgency of cleanroom constraints, and providing a basis for dynamic priority generation and triggering of linkage control strategies.

[0036] The specific formula for the environmental constraint urgency response value is as follows:

[0037] ;

[0038] In the formula, This represents the environmental constraint urgency response value, used to comprehensively characterize the "urgency" of cleanroom environmental constraints at each sampling time, i.e. whether the particle concentration and cleanroom pressure difference show a rapid deterioration trend under the current operating conditions; Particle concentration is used to reflect the state of air cleanliness and is one of the most critical quality control indicators for cleanrooms. The higher the value, the greater the risk of particle contamination. The pressure differential in a cleanroom reflects the room's ability to isolate airflow and prevent external contaminants from entering. An abnormal decrease in pressure differential can lead to the failure of the cleanroom boundary. It represents the rate of change in particle concentration, reflecting whether the particle concentration shows a rapid upward diffusion trend, and is a sensitive indicator of cleanliness deterioration; It represents the rate of change of differential pressure, reflecting whether the differential pressure constraint is showing a rapid instability and pressure relief trend, and is a key indicator of the decline in differential pressure isolation capability.

[0039] In this embodiment, Table 1 is a data table of environmental constraint urgency response values. The table details the normalized particle concentration, cleanroom pressure difference, particle concentration change rate, pressure difference change rate, and environmental constraint urgency response value at five different time points. Specifically, at time 1, the normalized particle concentration is 0.05, the cleanroom pressure difference is 0.92, the particle concentration change rate is 0.012, the pressure difference change rate is -0.015, and the environmental constraint urgency response value is 0.000435; at time 2, the normalized particle concentration is 0.11, the cleanroom pressure difference is 0.78, the particle concentration change rate is 0.041, the pressure difference change rate is -0.043, and the environmental constraint urgency response value is 0.005673; at time 3, the normalized particle concentration is 0.31, the cleanroom pressure difference is 0.60, and the particle concentration change rate is... The normalized particle concentration at time 4 was 0.58, the cleanroom pressure difference was 0.38, the particle concentration change rate was 0.184, the pressure difference change rate was -0.170, and the environmental constraint emergency response value was 0.122681; the normalized particle concentration at time 5 was 0.91, the cleanroom pressure difference was 0.18, the particle concentration change rate was 0.295, the pressure difference change rate was -0.270, and the environmental constraint emergency response value was 0.170461.

[0040] Table 1. Environmental Constraint Urgent Response Values ​​Data Table

[0041]

[0042] like Figure 3 The figure shows the trend of environmental constraint urgency response values. It illustrates the changing trend of environmental constraint urgency response values ​​over time. The horizontal axis represents the sampling time number, and the vertical axis represents the environmental constraint urgency response value at the corresponding time, comprehensively reflecting the combined urgency of the increasing particle concentration trend and the decreasing cleanroom pressure differential trend. (See Table 1 and...) Figure 3As can be seen, during the period from time 1 to time 2, the environmental constraint urgency response value remained at a low level, indicating that the particle concentration change rate was small and the pressure difference fluctuation was limited, and the cleanroom constraint was in a relatively stable state. Starting from time 3, the environmental constraint urgency response value showed a significant increase, indicating that the particle concentration increased at a faster rate and the pressure difference decreased more strongly, and the urgency of the environmental constraint gradually intensified. Especially during the period from time 4 to time 5, the environmental constraint urgency response value increased rapidly and reached its highest level, indicating that the cleanroom operation entered a high-urgency range, requiring priority to trigger the linkage control response of particle and pressure difference constraints. Therefore, the trend graph intuitively reflects the dynamic evolution process of cleanroom environmental constraints from a stable state to an urgent state, which can provide a basis for dynamic priority switching and control strategy output.

[0043] In this implementation scheme, by acquiring particle concentration and cleanroom pressure difference and their rate of change in real time, the scheme focuses on two types of cleanroom constraint deterioration trends: rising particle concentration and decreasing pressure difference. The corresponding directional components are extracted to achieve urgency-sensitive triggering. Furthermore, the scheme combines square operations to enhance the response capability to sudden disturbances and normalizes the results using constraint scale benchmarks to ensure comparability of urgency assessment results under different operating conditions. Finally, the scheme outputs smooth environmental constraint urgency response values ​​in logarithmic form, providing a reliable basis for determining dominant constraints, generating dynamic priorities, and triggering linkage control strategies, thereby improving the real-time performance and stability of cleanroom operation adaptation.

[0044] Specifically, the process of generating a comparison of the urgency of multiple constraints within a sliding time window is as follows: Based on the sliding time window, the mean and peak values ​​of the environmental constraint urgency response are calculated in real time. The mean and peak values ​​are multiplied and added together, and the natural logarithm is taken to obtain the estimated value of the environmental constraint urgency, which is then normalized. The mean value of the environmental constraint urgency response is used to characterize the continuous urgency level of the cleanliness constraint within the window, and the peak value is used to characterize the maximum sudden urgency within the window. The combination of the mean and peak values ​​can simultaneously depict long-term trends and short-term risks. The natural logarithm operation is used to suppress the excessive amplification of the estimation results by extreme peak values, and the normalization process is used to map the estimated value of the environmental constraint urgency to a uniform scale interval to ensure its comparability with temperature and humidity deviations and power deviations. The absolute differences between the current temperature, humidity, and total operating power and their corresponding reference values ​​are calculated to obtain the normalized deviations for temperature, humidity, and total operating power. The reference value is the stable baseline mean calculated within a sliding time window. The absolute difference characterizes the deviation of the current sampling state from the steady-state baseline. The normalized deviations for temperature and humidity reflect the instantaneous mismatch of temperature and humidity constraints, while the normalized deviation for total operating power reflects the deviation from energy consumption constraints. The deviations are further normalized to ensure that the deviations of different physical quantities can be compared in terms of constraint urgency on the same scale. The estimated environmental constraint urgency, normalized deviations for temperature, humidity, and total operating power are combined to construct a multi-constraint urgency comparison set. This set is used to form a unified urgency characterization of particle pressure difference constraints, temperature and humidity constraints, and energy-saving constraints at the current sampling time. This provides a direct basis for subsequent determination of dominant constraint types and output of dynamic priority control strategies, and is written into the cleanroom operation adaptation database to support process traceability and self-learning optimization.

[0045] In this implementation plan, by jointly statistically analyzing the mean and peak values ​​of environmental constraint urgency response values ​​within a sliding time window, a comprehensive characterization of the continuous urgency of cleanroom constraints and sudden risks is achieved. Normalization ensures the comparability of results under different operating conditions. Furthermore, by combining the unified quantification of temperature, humidity, and energy consumption deviations, a multi-constraint urgency comparison set is constructed, enabling particle pressure difference constraints, temperature and humidity constraints, and energy-saving constraints to be dynamically ranked on the same scale. This provides a reliable basis for determining the dominant constraint and generating priority control strategies, improving the real-time performance, stability, and traceability of cleanroom operation adaptation.

[0046] Specifically, the process of determining the current dominant constraint type and outputting the priority control strategy based on the comparison results is as follows: The dominant constraint type is determined by selecting the factor with the largest value from the multi-constraint urgency comparison set. Each factor in the multi-constraint urgency comparison set has been normalized and mapped to a uniform scale range, so its value directly reflects the relative urgency of different constraints at the current sampling time. The maximum value is selected for real-time determination of the dominant constraint. To avoid frequent switching of the dominant constraint due to instantaneous fluctuations when the urgency of multiple constraints is close, a duration confirmation mechanism is preferably introduced to determine the dominant constraint type. That is, only when a factor continuously exceeds the other factors and maintains its maximum state to reach the preset minimum number of confirmation samples is it officially output as the current dominant constraint type, thereby suppressing control target jumps caused by instantaneous noise or short-term disturbances. The dominant constraint type is used to characterize the control target that needs to be satisfied most urgently, thereby dynamically adjusting the control dominance order under constraint conflict conditions. Based on the dominant constraint type, the output priority control results are as follows: When the estimated urgency of environmental constraints is the highest, particle concentration and cleanroom pressure difference are determined as priority constraints. This indicates an imminent risk of increased contamination or decreased isolation capacity in cleanrooms. The priority control strategy will prioritize ensuring a decrease in particle concentration and a stable pressure difference to shorten the duration of exceeding cleanliness limits. When the normalized deviation of total operating power is the highest, energy saving is determined as a priority constraint. This indicates a significant increase in energy consumption deviating from the steady-state baseline. The priority control strategy will prioritize suppressing excessive increases in fan frequency and drastic fluctuations in supply and exhaust air volume to reduce energy consumption per unit time and the number of actuator actions. When the normalized deviation of temperature or humidity is the highest, temperature and humidity are determined as priority constraints. This indicates that the indoor thermal and humidity environment deviates from process requirements. The priority control strategy will prioritize coordinating the linkage adjustment of coil valves and humidification / dehumidification actuators to restore temperature and humidity to the target range and maintain process stability. The set of multiple constraint urgency comparisons and priority control results are written into the cleanroom operation adaptation database to form a traceable link of "constraint urgency, dominant constraint determination, and control priority output," providing historical basis for subsequent constraint conflict identification, linkage control strategy optimization, and operation self-learning updates.

[0047] In this implementation scheme, by determining the maximum value of the multiple constraint urgency comparison set under a unified scale, the dominant type of particle pressure difference, temperature and humidity and energy-saving constraints can be identified in real time, and priority control strategies can be dynamically output accordingly. This enables the system to automatically adjust the control dominance order under constraint conflict conditions, prioritizing the most urgent cleanliness or energy consumption targets. At the same time, the determination results and comparison sets are written into the operation adaptation database to form a traceable control decision link, thereby improving the adaptability, stability and operation and maintenance optimization capabilities of cleanroom operation adjustment.

[0048] Specifically, the process of conflict judgment regarding the relationship between energy consumption cost and pressure difference benefit in the linkage regulation process, utilizing the dynamic change characteristics of multi-constraint operating data, is as follows: The pressure difference change rate and the total operating power change rate are read. The pressure difference change rate characterizes the dynamic response amplitude of the supply and exhaust air linkage regulation to the positive pressure isolation capability of the cleanroom, while the total operating power change rate characterizes the energy consumption cost fluctuation level caused by the linkage regulation action. Both are obtained by dividing the difference between adjacent sampling times by the time interval and can be acquired continuously in real time. The control cost-benefit ratio is obtained by dividing the square of the total operating power change rate by the sum of the square of the pressure difference change rate and a minimum positive number. The squaring operation is used to characterize the intensity of the change amplitude and eliminate the influence of positive and negative directions, significantly increasing the ratio when the power fluctuation is more severe or the pressure difference response is more insufficient. A minimum positive number is introduced into the denominator to avoid numerical divergence when the pressure difference change rate approaches zero, ensuring the numerical stability and feasibility of the conflict judgment calculation process. The control cost-benefit ratio characterizes the energy consumption cost level corresponding to a unit pressure difference response amplitude, thereby characterizing the degree of cost-benefit mismatch in the linkage regulation action. The control action conflict discrimination value is obtained by adding the control cost-benefit ratio to a constant and taking the natural logarithm. The natural logarithm operation is used to compress the numerical range under extreme ratios, improving the smoothness of the conflict discrimination value and the stability of the threshold determination. The control action conflict discrimination value is based on the mismatch between energy consumption cost fluctuations and pressure difference response benefits during the linkage regulation process. By constructing the ratio of the amplitude of the total operating power change rate to the amplitude of the pressure difference change rate, the energy consumption cost level corresponding to a unit pressure difference response is characterized. When power fluctuations are significant and pressure difference improvement is insufficient, the discrimination value increases significantly, thereby enabling real-time identification of inefficient or conflicting linkage control actions, providing a basis for adjusting the supply and exhaust air ratio and limiting the increase in fan frequency.

[0049] The specific formula for the control action conflict discrimination value is as follows:

[0050] ;

[0051] In the formula, This represents the control action conflict discrimination value. By comparing the relative strength of the total operating power change rate and the differential pressure change rate, it identifies whether the control action exhibits a typical conflict situation of "significant power fluctuations but limited differential pressure improvement". It represents the total operating power, which reflects the overall energy consumption level of the linkage regulation process and is an important evaluation metric for energy conservation constraints. It represents the rate of change of total operating power, reflecting the growth rate of energy consumption cost or the intensity of power fluctuation caused by control actions. When the rate of change is large, it indicates that the linkage adjustment action has a strong energy consumption disturbance. It represents the pressure difference in the cleanroom and is used to characterize the airflow isolation capability of the clean area and the effect of preventing the intrusion of external contaminants. It is an important control target for cleanroom constraints. This represents the rate of change of differential pressure, reflecting the degree of improvement benefit of the linkage control action on the differential pressure constraint. When the rate of change is small while the power change is large, it indicates that the control action is not effective enough. This represents a very small positive number, used to avoid numerical divergence in the denominator when the rate of change of pressure difference approaches zero, ensuring the stability and feasibility of the conflict discrimination value calculation process. A value of [value missing] is preferred. arrive .

[0052] In this implementation plan, by acquiring the differential pressure change rate and the total operating power change rate in real time, a ratio relationship between the power fluctuation amplitude and the differential pressure response amplitude is constructed, thereby quantifying the degree of mismatch between energy consumption cost and differential pressure benefit during the linkage adjustment process. When the power cost increases rapidly while the differential pressure improvement is insufficient, the control action conflict discrimination value increases significantly, thus enabling timely identification of inefficient or conflicting adjustment situations. This provides a reliable basis for subsequent optimization of supply and exhaust air ratio, limitation of fan frequency increase, and adjustment of linkage control strategy, thereby improving the stability and energy efficiency of cleanroom operation adjustment.

[0053] Specifically, combining the priority control strategy and conflict judgment results, the process of adjusting the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level is as follows: When particle concentration and cleanroom pressure difference are determined to be the priority constraints, and the control action conflict judgment value is less than the conflict threshold, the supply fan operating frequency is increased to increase the supply air volume, and the exhaust valve opening is adjusted simultaneously to maintain the target difference between the supply and exhaust air volumes; wherein, the adjustment of the supply fan operating frequency is performed in a step-by-step increment manner, setting a maximum frequency change step size, which is the maximum frequency adjustment increment allowed for the supply fan in a single control cycle, and controlling the supply fan frequency increase in a single cycle to not exceed The maximum frequency variation step size is preferably between 0.5Hz and 2Hz to avoid airflow disturbance caused by sudden frequency changes. The exhaust valve opening adjustment is limited by the maximum valve opening variation step size, which is the maximum allowable opening change of the supply valve within a single control cycle. The single adjustment opening change is controlled to not exceed the maximum valve opening variation step size; preferably, the maximum valve opening variation step size is between 1% and 5% to ensure the smoothness of the supply and exhaust air linkage adjustment. The maximum frequency variation step size and the maximum valve opening variation step size are set based on the actuator response speed, the allowable range of airflow disturbance, and the cleanroom operation stability requirements. The target difference between the supply air volume and the exhaust air volume is used to maintain the cleanroom differential pressure setpoint. The target difference is preferably obtained through an airflow-differential pressure model, that is, based on the cleanroom space leakage coefficient and door gap flow resistance characteristics, the differential pressure setpoint is mapped to the corresponding supply and exhaust air volume difference. When particle concentration and cleanroom pressure difference are determined to be the primary constraints, and the control action conflict discrimination value is greater than or equal to the conflict threshold, the increase in air supply volume is limited. Pressure difference is maintained by coordinating and adjusting the relative ratio of the air supply valve opening and the exhaust valve opening, while simultaneously increasing the filtration air volume level of the filter unit. Limiting the increase in air supply volume includes limiting the increase in the air supply fan frequency to no more than the lower limit of the maximum frequency change step size, and limiting the change in the air supply valve opening to no more than the maximum valve opening change step size. Pressure difference deviation is converged by adjusting the relative ratio of the air supply valve and the exhaust valve. The preferred method for increasing the filtration unit's operating level is to switch to the high-efficiency filtration operating level while keeping the total air supply volume increase limited, in order to enhance particle removal capacity and reduce the risk of large pressure difference fluctuations. When temperature and humidity are determined to be the primary constraints, the opening of the cooling coil valve and the humidification / dehumidification actuators are adjusted in a coordinated manner according to the direction of deviation of temperature and humidity relative to their respective reference values. The opening of the cooling coil valve is also adjusted step by step using the maximum valve opening change step size. When the temperature is higher than the temperature reference value, the opening of the cooling coil valve is increased; when the temperature is lower than the reference value, the opening is decreased. When the humidity is higher than the humidity reference value, the dehumidification action is executed first; when the humidity is lower than the reference value, the humidification action is executed first, thereby achieving directional closed-loop regulation of the thermal and humidity constraints.When energy conservation is deemed a priority constraint, the increase in the operating frequency of the supply fan is limited. While meeting the cleanroom differential pressure constraint, the opening of the supply air valve is reduced, and the opening of the exhaust air valve is adjusted simultaneously. Specifically, the step size of the supply fan frequency change under the energy conservation constraint is preferably small to avoid unnecessary airflow increases. While reducing the supply air valve opening, the differential pressure is maintained near the set differential pressure value by adjusting the exhaust air valve opening, ensuring that energy-saving adjustments do not violate cleanroom isolation constraints. The control action conflict judgment value and linkage control strategy are written into the cleanroom operation adaptation database.

[0054] In this implementation plan, by combining the priority of the dominant constraints and the results of the conflict judgment of control actions, the frequency change step size and the valve opening change step size are used to constrain the linkage adjustment of the supply and exhaust air, so as to achieve smooth and controllable adjustment of the supply air volume, exhaust air ratio and filter level. At the same time, the conversion relationship between the differential pressure setpoint and the air volume difference is introduced, so that the differential pressure maintenance has a clear and implementable basis. In this way, in the scenario of conflict between tight cleanliness constraints and energy-saving constraints, sudden changes in air volume and sudden increases in energy consumption are effectively avoided, and the stability, adaptability and traceability optimization capability of cleanroom operation adjustment are improved.

[0055] Specifically, the process of evaluating the stability of the linkage control by real-time monitoring of the operating frequency and variation characteristics of the blower is as follows: The operating frequency of the blower is read in real time, and the difference between the operating frequencies of adjacent blowers is calculated at each sampling moment to obtain the change in blower frequency action. The blower operating frequency is acquired in real time by the controller communication bus. The change in frequency action is used to characterize the instantaneous jump amplitude of the blower control command during linkage adjustment, directly reflecting whether the actuator adjustment is smooth and continuous. Based on a sliding time window, the change in blower frequency action at each sampling point within the window is squared and accumulated to obtain the sum of squares of action jitter intensity. The square operation enhances the sensitivity to frequent and large-amplitude adjustment actions, significantly increasing the sum of squares of jitter intensity when the action jumps are more severe. The operating frequency of the blower at each sampling point within the window is also squared and accumulated to obtain the baseline sum of squares of the operating scale. The baseline sum of squares of the operating scale is used to characterize the overall frequency level of the blower operation within the window, thereby normalizing the action jitter intensity and avoiding incomparability of stability indicators under different airflow conditions. The stability retention value of the linkage control is obtained by dividing the sum of the squares of the motion jitter intensity by the sum of the squares of the operating scale and the minimum positive number, and taking the opposite of the sum as the exponent. The minimum positive number is used to avoid numerical divergence due to an excessively small denominator when the fan frequency is close to zero or during low-frequency operation. The natural exponent operation maps the stability retention value of the linkage control to the range of 0 to 1, ensuring that the stability retention value is close to 1 when the control action is smooth and decreases rapidly when motion jitter increases. The stability retention value of the linkage control is based on the jitter characteristics of the fan frequency adjustment action. It characterizes the jump amplitude of the actuator adjustment by statistically analyzing the cumulative intensity of the square of the frequency change within the sliding time window; and normalizes it using the square of the fan operating frequency scale as a benchmark to make the stability indicators comparable under different airflow conditions; finally, the retention value is output in exponential form to achieve a quantitative assessment of the stability of the linkage control.

[0056] The specific formula for the stability maintenance value of the linkage control is as follows:

[0057] ;

[0058] In the formula, This represents the stability retention value of the linkage control, used to quantify the smoothness and vibration intensity of the air supply fan frequency adjustment action during the linkage control process in the cleanroom. Indicates the length of the sliding time window, used to limit the time scale for motion change statistics; Indicates the index of each sampling point within the window; It indicates the operating frequency of the fan, which is used to characterize the air supply volume adjustment status and linkage control execution intensity of the clean room, and also serves as a benchmark for stability assessment. This indicates the change in the fan frequency, used to characterize the jump amplitude and vibration intensity of the fan's adjustment action. When the change in the fan frequency is large and occurs frequently, it indicates that the linkage control action is violent and the stability is reduced. This represents a very small positive number, used when the denominator approaches zero and the value diverges, ensuring the stability and feasibility of the calculation process for maintaining the stability of the linkage control. The preferred value is [value missing]. arrive .

[0059] In this implementation plan, by acquiring the operating frequency and changes of the blower in real time, using a sliding time window to statistically analyze the frequency action jitter intensity and normalizing it with an operating scale benchmark, the quantitative characterization of the actuator jump amplitude and frequent action risk during the linkage adjustment process is achieved. Furthermore, an exponential form is used to output the stability maintenance value, so that the index is close to 1 when the control action is stable and drops rapidly when jitter increases. This provides a reliable basis for linkage control stability assessment, stability suppression and strategy optimization, thereby improving the continuity and stability of cleanroom operation adjustment.

[0060] Specifically, the process of implementing optimized adjustment actions based on the stability assessment results is as follows: At each sampling moment, the stability maintenance value of the linkage control is calculated in real time and compared with the stability threshold. The stability threshold is used to characterize the minimum allowable stability level of the linkage control process. It is preferably preset based on the adjustment inertia of the cleanroom air supply fan actuator and the allowable range of airflow disturbance to distinguish between stable adjustment and frequent operation states. When the linkage control stability maintenance value is lower than the stability threshold for a duration exceeding the allowable time threshold, it is determined that the current linkage control has a phenomenon of frequent operation of the actuator, and a stability suppression command is output to limit the change range of the air supply fan operating frequency. The allowable time threshold is used to avoid misjudgment caused by instantaneous fluctuations. It is preferably taken as a time span consisting of multiple consecutive sampling periods, such as 5s to 60s. The stability suppression command includes limiting the upper limit of the maximum frequency change step of the air supply fan and entering a smooth adjustment mode to suppress airflow disturbance and energy consumption fluctuations caused by rapid frequency jumps. When the duration for which the stability maintenance value of the linkage control is greater than or equal to the stability threshold exceeds the allowable time threshold, the current linkage control process is determined to be stable, allowing continued execution of air supply and exhaust regulation and temperature and humidity regulation actions according to the linkage control strategy. In the stable state, the execution of the current priority control strategy is maintained, and normal linkage adjustment is allowed according to preset frequency steps and valve opening steps to balance cleanliness constraints and energy consumption optimization. The linkage control stability maintenance value and determination result are written into the cleanroom operation adaptation database and stored in association with environmental constraint urgency response values, control action conflict discrimination values, and priority control results. This forms a closed-loop operation link of "urgency assessment, conflict discrimination, priority decision, and stability feedback," supporting subsequent operation and maintenance traceability analysis and self-learning updates of control parameters, thereby improving the stability and sustainable optimization capabilities of the cleanroom's intelligent operation adaptation.

[0061] like Figure 4 The diagram shows the closed-loop adaptation flowchart for the linkage control driven by the urgency of multiple constraints in a cleanroom. It comprehensively demonstrates the complete closed-loop control logic in actual operation. First, real-time data on multiple constraints, including particle concentration, cleanroom pressure difference, temperature and humidity, operating power, and fan frequency, are collected. These data are then preprocessed through time alignment, anomaly correction, and normalization to form a comparable sequence of operating states. Next, the urgency response to environmental constraints is assessed based on positive changes in particle concentration and negative changes in pressure difference. Within a sliding window, the mean and peak values ​​are combined to generate an urgency estimation result. Simultaneously, temperature and humidity deviations and power deviations are calculated to construct a comparison set of multiple constraint urgency, thereby determining the current dominant constraint type and outputting the corresponding priority control strategy. When the dominant constraint is a cleanroom constraint, a control action conflict judgment process is further triggered. By comparing the power change amplitude and the pressure difference response amplitude, the cost-benefit mismatch in the linkage adjustment is identified. Based on the conflict threshold, it is decided whether to allow increased supply air pressure difference maintenance or limit the frequency increase and switch filter levels to suppress sudden increases in energy consumption. After control is executed, the stability maintenance value of the linkage control is calculated in real time, and the stability of the fan movement is evaluated. If the stability is insufficient and the timeout is continuous, the suppression command is output to limit the frequent movement of the actuator. Finally, the urgent response, conflict discrimination, priority decision and stability results are written into the operation adaptation database to form a traceable self-learning closed loop of "constraint evaluation, control response and result feedback", thereby realizing dynamic adaptation and stable operation optimization under multiple constraints of cleanroom.

[0062] In this implementation plan, by calculating the stability maintenance value of the linkage control in real time and determining the duration with the stability threshold, the system effectively distinguishes between frequent actions of the actuator and the stable state of the control process. When the stability is insufficient, the system promptly triggers a suppression command to limit the frequency change amplitude, avoiding airflow fluctuations and energy consumption fluctuations. When the stability is good, the linkage adjustment strategy is allowed to continue, thereby improving the continuity and stability of cleanroom operation control. At the same time, the stability assessment results are associated and stored with emergency response, conflict identification, and priority decision-making to form a traceable closed-loop link, providing support for subsequent strategy optimization and self-learning updates.

[0063] Reference Figure 2As shown, the second aspect of the present invention provides a cleanroom intelligent operation adaptation system based on environmental constraint linkage, applied to the aforementioned cleanroom intelligent operation adaptation method based on environmental constraint linkage, comprising: a constraint data acquisition and processing module, used to acquire multi-constraint operation data in real time, and perform time alignment, anomaly correction, and normalization preprocessing on the multi-constraint operation data; an urgency assessment and priority module, used to analyze the dynamic change characteristics of the preprocessed multi-constraint operation data, assess the urgency of environmental constraints, generate multi-constraint urgency comparison results within a sliding time window, determine the current dominant constraint type based on the comparison results, and output a priority control strategy; a conflict discrimination and linkage control module, used to use the dynamic change characteristics of the multi-constraint operation data to perform conflict discrimination on the relationship between energy consumption cost and pressure difference benefit in the linkage adjustment process, and adjust the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level based on the priority control strategy and conflict discrimination results; and an operation evaluation and traceability learning module, used to monitor the operating frequency and change characteristics of the supply fan in real time, evaluate the stability of linkage control, and implement optimization adjustment actions based on the stability evaluation results.

[0064] In this implementation plan, a closed-loop collaboration of constraint data acquisition and processing, urgency assessment and priority generation, conflict identification and linkage control, and operation assessment and traceability learning is achieved to dynamically adapt and adjust multiple objective constraints such as particle concentration, pressure difference, temperature and humidity, and energy consumption. The system can assess the urgency of environmental constraints in real time under different operating conditions and determine the dominant constraint type. It outputs linkage control strategies by combining energy consumption costs and pressure difference benefits conflict identification. At the same time, it suppresses frequent actions of actuators through stability assessment, forming a traceable "constraint assessment, control response, and operation result" link, thereby improving the adaptability, stability, and energy-saving optimization capabilities of cleanroom operation.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0066] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. As those skilled in the art will understand, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for intelligent operation adaptation of cleanrooms based on environmental constraints, characterized in that, Includes the following steps: S1 collects multi-constraint operation data in real time and performs time alignment, anomaly correction and normalization preprocessing on the multi-constraint operation data; S2 analyzes the dynamic change characteristics of the preprocessed multi-constraint running data, assesses the urgency of environmental constraints, generates a multi-constraint urgency comparison result within the sliding time window, determines the current dominant constraint type based on the comparison result, and outputs a priority control strategy. S3 utilizes the dynamic change characteristics of multi-constraint operating data to determine the conflict between energy consumption cost and pressure difference benefit in the linkage regulation process. Combining the priority control strategy and the conflict determination results, it adjusts the supply and exhaust valve ratio, fan frequency increase and filter unit operating level. S4 monitors the operating frequency and variation characteristics of the blower in real time, evaluates the stability of the linkage control, and implements optimized adjustment actions based on the stability evaluation results.

2. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process of real-time acquisition of multi-constraint operation data, and the preprocessing of time alignment, anomaly correction, and normalization of the multi-constraint operation data is as follows: Real-time acquisition of multi-constraint operating data within the cleanroom, including: particle concentration, cleanroom pressure difference, temperature, humidity, total operating power, and air supply fan operating frequency; Time alignment processing is performed on multi-constraint operating data, and median deviation detection using a sliding time window is used to identify abnormal sampling points. Interpolation correction is applied to abnormal sampling points, and minimum-maximum normalization processing is performed on the multi-constraint operating data. Based on the preprocessed particle concentration, cleanroom differential pressure, and total operating power, the particle concentration change rate, differential pressure change rate, and total operating power change rate are obtained by dividing the difference between adjacent sampling times by the time interval. A sliding time window is constructed, and the mean values ​​of temperature, humidity, and total operating power within the window are calculated to obtain temperature reference values, humidity reference values, and total operating power reference values. A cleanroom operation adaptation database is established to store multi-constraint operating data, various change rates, and various reference values.

3. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process for analyzing the dynamic changes of the preprocessed multi-constraint operational data and assessing the urgency of environmental constraints is as follows: The particle concentration and cleanroom pressure difference are read in real time, and the corresponding particle concentration change rate and pressure difference change rate are read. The positive change component of the particle concentration change rate and the negative change component of the pressure difference change rate are extracted. The sum of squares of the positive change component of the particle concentration change rate and the negative change component of the pressure difference change rate are calculated to obtain the sum of squares of the dynamic fluctuation of cleanroom constraints. The sum of squares of the particle concentration and the cleanroom pressure difference is calculated to obtain the baseline sum of squares of the cleanroom constraints. The sum of squares of the dynamic fluctuation of cleanroom constraints is divided by the baseline sum of squares of the cleanroom constraints, and the result is added to a value and the natural logarithm is taken to obtain the environmental constraint urgency response value.

4. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process of generating multi-constraint urgency comparison results within the sliding time window is as follows: Based on a sliding time window, the mean and peak values ​​of the environmental constraint urgency response are calculated in real time. The mean and peak values ​​are multiplied together and added to one, and the natural logarithm is taken to obtain the estimated value of environmental constraint urgency, which is then normalized. Calculate the absolute differences between the current temperature, humidity, and total operating power and the corresponding reference values ​​to obtain the temperature normalization deviation, humidity normalization deviation, and total operating power normalization deviation. A multi-constraint urgency comparison set is constructed by combining the estimated environmental constraint urgency values, temperature normalization bias, humidity normalization bias, and total operating power normalization bias.

5. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process of determining the current dominant constraint type based on the comparison results and outputting the priority control strategy is as follows: The dominant constraint type is determined by selecting the factor with the largest value from the set of multiple constraint urgency comparisons; priority control results are output based on the dominant constraint type: when the estimated value of environmental constraint urgency is the largest, particle concentration and cleanroom pressure difference are determined to be the priority constraints; when the normalized deviation of total operating power is the largest, energy saving is determined to be the priority constraint. When the temperature normalization deviation or humidity normalization deviation is the largest, temperature and humidity are determined to be the priority constraints; the set of multiple constraint urgency comparisons and the priority control results are written into the cleanroom operation adaptation database.

6. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process of using the dynamic change characteristics of multi-constraint operating data to determine the conflict between energy consumption costs and pressure difference benefits in the linkage regulation process is as follows: Read the rate of change of differential pressure and the rate of change of total operating power; divide the square of the rate of change of total operating power by the sum of the square of the rate of change of differential pressure and the smallest positive number to obtain the control cost-benefit ratio; add the control cost-benefit ratio to a constant and take the natural logarithm to obtain the control action conflict discrimination value.

7. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process of adjusting the supply and exhaust valve ratio, fan frequency increase, and filter unit operating level by combining the priority control strategy and conflict judgment results is as follows: When particle concentration and cleanroom pressure difference are determined to be the priority constraints, and the control action conflict discrimination value is less than the conflict threshold, the operating frequency of the air supply fan is increased to increase the air supply volume, and the opening of the exhaust valve is adjusted synchronously to maintain the target difference between the air supply volume and the exhaust volume. When the particle concentration and the pressure difference of the clean room are determined to be the priority constraints, and the conflict judgment value of the control action is greater than or equal to the conflict threshold, the increase in the air supply volume is limited, and the pressure difference is maintained by coordinating and adjusting the relative ratio of the air supply valve opening and the exhaust valve opening, and the filtration air volume level of the filter unit is increased simultaneously. When temperature and humidity are determined to be the primary constraints, the opening of the coil valve and the humidification and dehumidification actuator are adjusted in conjunction with each other according to the direction of the deviation of temperature and humidity from their respective reference values. When energy conservation is determined to be the priority constraint, the increase in the operating frequency of the air supply fan is limited, and the opening of the air supply valve is reduced and the opening of the exhaust valve is adjusted simultaneously, provided that the pressure difference constraint of the clean room is met. The conflict judgment value of the control action and the linkage control strategy are written into the cleanroom operation adaptation database.

8. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process for evaluating the stability of the linkage control by real-time monitoring of the operating frequency and variation characteristics of the blower is as follows: The operating frequency of the blower is read in real time, and the difference between the operating frequencies of adjacent blowers is calculated at each sampling time to obtain the change in blower frequency. Based on the sliding time window, the changes in fan frequency movement at each sampling point within the window are squared and summed to obtain the sum of squares of movement jitter intensity; the operating frequency of the blower at each sampling point within the window is squared and summed to obtain the sum of squares of operating scale reference; the sum of squares of movement jitter intensity is divided by the sum of squares of operating scale reference and the smallest positive number, and the opposite number is taken as the exponent for natural exponential operation to obtain the linkage control stability maintenance value.

9. The cleanroom intelligent operation adaptation method based on environmental constraint linkage according to claim 1, characterized in that, The specific process of implementing optimized adjustment actions based on the stability assessment results is as follows: At each sampling moment, the stability maintenance value of the linkage control is calculated in real time and compared with the stability threshold: When the duration of the linkage control stability value being lower than the stability threshold exceeds the allowable time threshold, it is determined that the current linkage control has a phenomenon of frequent action of the actuator, and a stability suppression command is output to limit the variation of the blower's operating frequency. When the duration for which the stability value of the linkage control is greater than or equal to the stability threshold exceeds the allowable time threshold, the current linkage control process is determined to be stable, and it is allowed to continue to execute the supply and exhaust air conditioning and temperature and humidity conditioning actions according to the linkage control strategy. The stability maintenance value and judgment result of the linkage control are written into the cleanroom operation adaptation database and stored in association with the environmental constraint urgent response value, control action conflict judgment value and priority control result.

10. A cleanroom intelligent operation adaptation system based on environmental constraint linkage, characterized in that, include: The constraint data acquisition and processing module is used to acquire multi-constraint operation data in real time and perform time alignment, anomaly correction and normalization preprocessing on the multi-constraint operation data. The urgency assessment and prioritization module is used to analyze the dynamic change characteristics of preprocessed multi-constraint runtime data, assess the urgency of environmental constraints, generate multi-constraint urgency comparison results within a sliding time window, determine the current dominant constraint type based on the comparison results, and output a priority control strategy. The conflict detection and linkage control module is used to use the dynamic change characteristics of multi-constraint operating data to detect conflicts between energy consumption costs and pressure difference benefits in the linkage adjustment process. Combined with the priority control strategy and the conflict detection results, the supply and exhaust valve ratio, fan frequency increase and filter unit operating level are adjusted. The operation evaluation and traceability learning module is used to monitor the operating frequency and variation characteristics of the blower in real time, evaluate the stability of the linkage control, and implement optimization adjustment actions based on the stability evaluation results.

Images