A smart building sampling detection control system based on internet of things sensing

Abstract

The application relates to a smart building sampling detection control system based on internet-of-things sensing, belonging to the technical field of building environment control, which comprises an environment state sensing unit, a predictive analysis unit, a flow field preprocessing unit, a path planning unit and a cooperative control unit. The environment state sensing unit is used for collecting environment state data of a target monitoring area to generate a real-time data vector. The predictive analysis unit is used for receiving the real-time data vector and performing diffusion trajectory deduction according to a preset state space norm to generate a predicted state vector. The flow field preprocessing unit is used for performing vortex kinetic energy deconstruction processing on a thermal plume in response to the predicted state vector to generate a weakened flow field environment. The application wins valuable decision-making advance for subsequent accurate removal, and ensures the real-time performance of prediction by using a pre-trained model.

Description

Technical Field

[0001] This invention relates to the field of building environment control, specifically to a smart building sampling and detection control system based on Internet of Things (IoT) sensing. Background Technology

[0002] In semiconductor manufacturing, especially in cleanrooms for wafer fabrication at 3nm and below nodes, the control requirements for gaseous molecular contaminants are extremely stringent. During operation or start-up and shutdown, production equipment instantaneously releases trace amounts of AMCs, such as ammonia and acid gases, accompanied by powerful and irregular dynamic thermal plumes. These thermal plumes carry AMCs and diffuse rapidly; once they come into contact with the wafer surface, they can cause the entire batch of products to be scrapped.

[0003] Existing technologies primarily employ a full-space dilution purification strategy, which dilutes pollutant concentrations by increasing the air exchange rate throughout the cleanroom. The inherent drawback of this method is twofold: firstly, the global increase in ventilation volume to address localized, transient contamination leads to system energy consumption increasing exponentially by the cube of the air velocity (…). First, the air quality deteriorates exponentially, resulting in extremely low energy efficiency. Second, the response speed is slow, making it impossible to effectively intercept pollutants before they spread. Third, excessively high wind speeds may disrupt the laminar flow in the work area, stirring up secondary pollutants from equipment or ground sediment, creating a vicious cycle.

[0004] Against this backdrop, a sharp technical contradiction emerges: to achieve rapid capture of instantaneous AMC carried by dynamic thermal plumes—that is, to pursue extremely high local purification accuracy—ultra-high airflow velocities must be used for suppression. However, this inevitably leads to a sharp deterioration in energy consumption and an increased risk of secondary contamination. Existing technologies adhere to the design philosophy that static uniform laminar flow is the optimal solution for cleanrooms, lacking an effective solution for the problem of optimal energy removal of dynamic, heterogeneous, and instantaneous contaminants. Therefore, a new control system that can overcome this technical contradiction and achieve synergistic optimization of energy consumption and purification accuracy is urgently needed.

[0005] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a smart building sampling and detection control system based on Internet of Things (IoT) sensing to solve the problems mentioned in the background art.

[0007] The technical solution of the present invention includes an environmental state sensing unit, a predictive analysis unit, a flow field preprocessing unit, a path planning unit, and a cooperative control unit.

[0008] An environmental state sensing unit is configured to collect environmental state data of a target monitoring area to generate a real-time data vector;

[0009] A predictive analysis unit is configured to receive the real-time data vector and perform diffusion trajectory deduction according to a preset state space paradigm to generate a predicted state vector;

[0010] A flow field preprocessing unit is configured to perform vortex kinetic energy deconstruction processing on the thermal plume in response to the predicted state vector to generate a weakened flow field environment;

[0011] A path planning unit is configured to perform quantitative planning analysis of a guide path in combination with the predicted state vector and the weakened flow field environment to generate a clearing signal;

[0012] A cooperative control unit is configured to generate a virtual air duct topology structure according to the clearing signal and generate a flow field execution instruction based on the virtual air duct topology structure.

[0013] Preferably, the process of collecting environmental state data by the environmental state sensing unit includes:

[0014] acquiring a three-dimensional motion vector of the gaseous molecular pollutants;

[0015] acquiring a surface temperature distribution of the device;

[0016] acquiring a local gaseous molecular pollutant concentration;

[0017] and fusing the three-dimensional motion vector, the surface temperature distribution, and the local gaseous molecular pollutant concentration to generate the real-time data vector.

[0018] Preferably, the process of generating the predicted state vector is as follows:

[0019] inputting a system state vector at a current time, the real-time data vector generated by the environmental state sensing unit, and a control vector of a previous control period into a preset nonlinear mapping function to perform operation to generate the predicted state vector;

[0020] The system state vector includes position information and concentration information of the gaseous molecular pollutants.

[0021] Preferably, the process of vortex kinetic energy deconstruction processing is as follows:

[0022] determining a predicted thermal plume intensity according to the predicted state vector;

[0023] adjusting a vibration frequency of the micro vortex plate array according to the predicted thermal plume intensity to determine an active dissipation coefficient;

[0024] and accelerating large-scale vortex total kinetic energy decay of the thermal plume based on the active dissipation coefficient to generate the weakened flow field environment.

[0025] Preferably, the quantitative planning analysis process of the guiding path is as follows:

[0026] Based on the predicted state vector, determine the purification invalidity index;

[0027] Determine the energy consumption of driving the airflow control node, and normalize the energy consumption to determine the energy cost;

[0028] Obtain the preset energy cost weight factor and purification risk weight factor;

[0029] And the energy cost and purification invalidity index are weighted and summed to generate a comprehensive cost function, and then a cleaning signal is generated according to the comprehensive cost function.

[0030] Preferably, the energy cost is the energy consumption required to drive a single airflow control node to generate the airflow, which is normalized with a preset reference energy value.

[0031] The purification invalidity index is the ratio of the predicted residual concentration of the pollutant after passing through a single airflow control node to the preset safety threshold concentration.

[0032] Preferably, the generation process of the cleaning signal includes:

[0033] Compare and analyze the comprehensive cost function with the preset cost threshold value;

[0034] If the comprehensive cost function is greater than the cost threshold value, an emergency cleaning signal is generated, and the purification risk weight factor is set to be greater than the energy cost weight factor;

[0035] If the comprehensive cost function is not greater than the cost threshold value, a regular cleaning signal is generated, and the energy cost weight factor is set to be greater than or equal to the purification risk weight factor.

[0036] Preferably, the generation process of the flow field execution instruction is as follows:

[0037] Calculate the air supply pulsation angular frequency for each unit in the vector air supply unit array;

[0038] Calculate the initial phase for each unit;

[0039] And combine the air supply pulsation angular frequency and the initial phase calculated for each unit to generate the flow field execution instruction.

[0040] Preferably, it further includes a flow field execution unit;

[0041] The flow field execution unit is used to receive and execute the flow field execution instruction to generate a virtual air duct for wrapping and guiding the pollutants, thereby realizing the capture of the pollutants.

[0042] The application provides a smart building sampling detection control system based on Internet of Things sensing by improvement, and has the following improvements and advantages compared with the prior art.

[0043] 1. By fusing the three-dimensional motion vector of gaseous molecular pollutants, the device surface temperature distribution and the local gaseous molecular pollutant concentration, a real-time data vector containing multi-dimensional physical information is generated; such high-fidelity data input provides the predictive analysis unit with complete cognition of the pollution situation; the predictive analysis unit further inputs the real-time data vector, the current system state vector and the control vector of the last control period into the preset nonlinear mapping function, so as to accurately deduce the future diffusion trend of the pollutants on the basis of fully considering the evolution law of the system itself and the influence of the control behavior, and generate a predicted state vector; such a prediction mechanism enables the whole control system to change from passive response to active intervention, and wins valuable decision-making lead time for subsequent accurate removal, and ensures the real-time of prediction due to the use of a pre-trained model;

[0044] 2. The application discards the traditional idea of using strong wind for suppression; the flow field preprocessing unit intervenes at the initial stage of the development of the hot plume in response to the predicted state vector, determines the active dissipation coefficient by adjusting the vibration frequency of the micro-turbulence piece array, and then accelerates the decay of the large-scale vortex total kinetic energy of the hot plume; such vortex kinetic energy disintegration processing weakens the diffusion power of the pollutants at the source with extremely low energy cost, and generates a more easily controlled and weakened flow field environment; this creates a prerequisite for subsequent low-energy guiding and capturing operations, and embodies extremely high control energy efficiency ratio;

[0045] 3. The application realizes quantitative optimization of control decisions; the path planning unit abstracts the purification task into a solvable mathematical problem; based on the predicted state vector, the purification invalidity index is determined, the energy consumption of the driving air flow control node is normalized to determine the energy cost, and the two mutually restrictive indexes are weighted and summed to generate a comprehensive cost function; this quantitative analysis process enables the system to abandon experience-based fuzzy decision-making, and instead calculates an optimal path that achieves the best balance between purification effect and energy consumption according to the comprehensive cost function, and generates a removal signal. BRIEF DESCRIPTION OF DRAWINGS

[0046] The application will be further explained below in combination with the drawings and embodiments:

[0047] Figure 1 is the flow chart of the system of the application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the application clearer, the application will be further described in detail below in combination with specific embodiments.

[0049] Embodiment 1

[0050] Reference Figure 1 The application provides a smart building sampling detection control system based on Internet of Things sensing, comprising an environmental state sensing unit, a predictive analysis unit, a flow field preprocessing unit, a path planning unit and a cooperative control unit.

[0051] The environmental state sensing unit is used for collecting environmental state data of a target monitoring area to generate a real-time data vector.

[0052] The predictive analysis unit is used for receiving the real-time data vector and performing diffusion trajectory deduction according to a preset state space norm to generate a predicted state vector.

[0053] The flow field preprocessing unit is used for performing vortex kinetic energy deconstruction processing on a thermal plume in response to the predicted state vector to generate a weakened flow field environment.

[0054] The path planning unit is used for performing quantitative planning analysis of a guide path in combination with the predicted state vector and the weakened flow field environment to generate a cleaning signal.

[0055] The cooperative control unit is used for generating a virtual air duct topology structure according to the cleaning signal and generating a flow field execution instruction based on the virtual air duct topology structure.

[0056] A smart building sampling detection control system based on Internet of Things sensing aims to solve the technical contradiction that the existing technology globally increases the ventilation volume to cope with local and instantaneous pollutants, resulting in a significant increase in energy consumption, slow response and an increased risk of secondary pollution. The embodiment discards the traditional mode of resisting pollution with strong wind and instead adopts a new paradigm of guiding pollution with delicate airflow, thereby achieving rapid and accurate removal of pollution sources without significantly increasing the total energy consumption of the system. The system comprises an environmental state sensing unit, a predictive analysis unit, a flow field preprocessing unit, a path planning unit and a cooperative control unit.

[0057] It should be emphasized that the optimal performance of the system is realized in a semi-closed environment with relatively stable boundary conditions and known main disturbance sources, such as a semiconductor super-clean room designed by the system. The prediction accuracy of the model depends on sufficient learning of the main physical processes in the environment, such as the thermal plume of key equipment. For sudden strong disturbance events not covered by the model, the system will rely on real-time data from the environmental state sensing unit for rapid response. Although the advantage of prediction in advance will be weakened at this time, the error correction capability of closed-loop control still exists.

[0058] Unlike the prior art which relies on a single information source for passive response, the progress of the present application is first in its forward-looking predictive ability; the environmental state sensing unit generates real-time data vectors containing multi-dimensional physical information by fusing the three-dimensional motion vector of gaseous molecular pollutants, the device surface temperature distribution and the local gaseous molecular pollutant concentration; such high-fidelity data input provides the predictive analysis unit with a complete understanding of the pollution situation; the predictive analysis unit further inputs the real-time data vector, the current system state vector and the control vector of the last control period into the preset nonlinear mapping function, so as to accurately deduce the future diffusion trend of the pollutants and generate a predicted state vector, based on sufficient consideration of the system's own evolution law and the influence of control behavior; this prediction mechanism enables the entire control system to change from passive response to active intervention, gaining valuable decision-making lead time for subsequent accurate removal, and ensuring the real-time nature of the prediction due to the use of a pre-trained model;

[0059] The environmental state sensing unit aims to capture multi-dimensional physical information related to pollutant diffusion in the target monitoring area in real time and high fidelity, and integrate these information into structured data; in this embodiment, the unit is a multi-modal sensing network deployed in a semiconductor clean room to collect environmental state data and fuse to generate real-time data vectors; real-time data vectors refer to comprehensive data sets containing information about pollutant spatial distribution, motion vector, local concentration and ambient temperature at the same timestamp, and their role is to provide accurate and immediate real-world input for subsequent predictive analysis;

[0060] The predictive analysis unit aims to prospectively deduce the diffusion trend of pollutants in the future short time based on the current environmental state, providing decision-making lead time for active intervention; the unit receives real-time data vectors generated by the environmental state sensing unit and performs diffusion trajectory deduction based on a preset state space paradigm to generate a predicted state vector; the predicted state vector refers to a mathematical description of the spatial distribution and concentration of pollutants at a future time, and its role is as a target input for flow field preprocessing and path planning; the prediction process is completed through a nonlinear mapping function based on a long short-term memory network; the preset nonlinear mapping function refers to a neural network model whose internal weights and bias parameters have been determined through offline supervised learning on massive historical operation data of the clean room; this pre-training mechanism enables the model to capture the complex time series law of fluid motion, so that when receiving real-time input, it can quickly generate an accurate prediction of the future without the need for immediate calculation with huge resource consumption;

[0061] The pre-training here refers to offline supervised learning of the long short-term memory network model using a large amount of historical running data of the clean room before the system is formally deployed; the historical data contains sensor readings under different working conditions, i.e., real-time data vectors , previously executed control instructions, i.e., control vectors , and actual pollutant diffusion results caused by the conditions, i.e., real system states , and ; by learning these question-answer pairs, the internal weights and bias parameters of the network model are adjusted and determined, so that the model can simulate and represent the real physical evolution law of the system; therefore, in real-time operation, the model has become a high-efficiency mapping function, which only needs to substitute the current input vector ( ) into the formula:

[0062] ;

[0063] , wherein : predicted state vector, model output of the prediction of the position and concentration of gaseous molecular pollutants at the next time; : nonlinear mapping function, representing the model of the physical evolution law of the system, which is a neural network model whose internal weights and bias parameters have been determined through offline supervised learning on a large amount of historical running data of the clean room; : system state vector at the current time; : real-time data vector; : control vector of the last control period; : system process noise vector; : subscript, representing time;

[0064] Through one-time fast operation of the above formula, an accurate predicted state vector can be obtained, thereby avoiding complex real-time fluid dynamics solving;

[0065] The flow field preprocessing unit aims to weaken the energy of the hot plume, the main carrier of pollutants, before the pollutants are guided, change the flow field structure of the hot plume, and convert it from a macroscopic vortex with strong destructive power into a microscopic turbulent flow that is easier to control; the unit performs vortex kinetic energy deconstruction processing on the hot plume that is about to form or strengthen in response to the predicted state vector generated by the predictive analysis unit; this processing is realized by a micro vortex plate array driven by a piezoelectric ceramic, which adjusts the vibration frequency of the array according to the predicted intensity of the hot plume, thereby actively increasing the dissipation of the flow field and accelerating the decay of the large-scale vortex kinetic energy, and finally generating a weakened flow field environment; the weakened flow field environment refers to a flow field whose macroscopic vortex kinetic energy is significantly reduced and whose turbulent flow scale is changed, and its role is to create a lower energy consumption and more stable control basis for subsequent virtual wind channel guidance;

[0066] The present application discards the traditional idea of suppressing with strong wind for the key carrier of pollutant diffusion, the hot plume; the flow field preprocessing unit intervenes at the early stage of the development of the hot plume in response to the predicted state vector, determines the active dissipation coefficient by adjusting the vibration frequency of the micro vortex plate array, and thereby accelerates the decay of the large-scale vortex total kinetic energy of the hot plume; this vortex kinetic energy deconstruction processing weakens the diffusion power of pollutants from the source at a very low energy cost, generating a more controllable and weakened flow field environment; this creates a prerequisite for subsequent low-energy guidance and capture operations, and embodies a very high control energy efficiency ratio;

[0067] The path planning unit aims to comprehensively consider the two core indicators of energy consumption and purification effect, and calculate an optimal path for guiding and removing pollutants, i.e., the topology of the virtual wind channel; the unit performs quantitative planning analysis of the guidance path in combination with the predicted state vector and the weakened flow field environment; this analysis is realized by solving the minimum value of the comprehensive cost function, which performs weighted summation on energy cost and purification risk; the final output of path planning is a removal signal; the removal signal refers to an information instruction containing the node sequence of the optimal path, and its role is to provide a determined target for the collaborative control unit to generate specific flow field execution instructions;

[0068] The present application realizes quantitative optimization of control decisions; the path planning unit abstracts the purification task as a solvable mathematical problem; based on the predicted state vector, the purification invalidity index is determined, and the energy consumption of the driving air flow control node is normalized to determine the energy cost, and the two mutually restrictive indicators are weighted and summed to generate a comprehensive cost function; this quantitative analysis process enables the system to abandon experience-based fuzzy decision-making and instead calculate an optimal path that achieves the best balance between purification effect and energy consumption based on the comprehensive cost function, and generate a removal signal;

[0069] The cooperative control unit aims to convert the abstract path instructions output by the path planning unit into precise and synchronized hardware control commands executable in the physical world. Based on the received cleaning signal, the unit generates a virtual air duct topology structure. Based on this topology structure, the unit calculates precise operating parameters for each air supply and air extraction unit in the flow field execution system through a preset inverse solver, and generates flow field execution instructions. The flow field execution instructions refer to a set of specific parameters including phase, frequency, amplitude, etc., which drive the flow field execution unit to act cooperatively and generate the expected focused airflow.

[0070] To convert the optimal path into a physical reality, the cooperative control unit accurately calculates parameters such as air supply pulsation angular frequency and initial phase for each unit in the vector air supply unit array based on the cleaning signal, and generates flow field execution instructions. The flow field execution unit receives and executes the instructions, and forms a virtual air duct in space through the cooperative air supply of each unit to wrap and guide pollutants. This non-contact guiding method has unparalleled flexibility, response speed, and extremely low energy consumption compared to physical isolation or global ventilation, ultimately achieving efficient capture of pollutants.

[0071] Through the cooperative work of the above-mentioned units, this embodiment realizes predictive, active, and low-energy precise cleaning of dynamic pollutants. By predicting pollution trajectories, preprocessing flow field environments, planning optimal guiding paths, and generating virtual air ducts based on phased array principles, the traditional global dilution purification mode is transformed into a local precise surgical cleaning mode, thereby solving the sharp contradiction between local purification precision and system total energy consumption, and achieving the cooperative optimization of purification effect and energy efficiency.

[0072] The process of collecting environmental state data by the environmental state sensing unit includes:

[0073] Obtaining a three-dimensional motion vector of gaseous molecular pollutants;

[0074] Obtaining a surface temperature distribution of the device;

[0075] Obtaining a local gaseous molecular pollutant concentration;

[0076] Fusing the three-dimensional motion vector, the surface temperature distribution, and the local gaseous molecular pollutant concentration to generate a real-time data vector;

[0077] In this embodiment, a specific implementation of the environmental state sensing unit is more specific in the process of collecting environmental state data.

[0078] The process of collecting environmental state data by the environmental state sensing unit integrates multiple sensing modalities to obtain comprehensive information; to obtain the three-dimensional motion vector of gaseous molecular pollutants, the system releases a quantum dot aerosol with a surface that has been functionally modified near the key equipment to achieve this, which can specifically adsorb target gaseous molecular pollutants, and a high-speed fluorescence camera array is used to analyze the three-dimensional spatial position, shape and motion vector field of the pollution cloud in real time through triangulation and particle image velocimetry algorithm; to obtain the surface temperature distribution of the equipment, an infrared thermal imaging unit deployed above the monitoring area is used to monitor the temperature field distribution of the dynamic thermal plume generated by the operation or start-stop of the production equipment; to obtain the local gaseous molecular pollutant concentration, a high-sensitivity chemical sensing unit array deployed in the key area is used to provide real-time AMC concentration calibration value; the collected three-dimensional motion vector, surface temperature distribution and local gaseous molecular pollutant concentration are fused to generate a real-time data vector ; the fusion process aligns the timestamps and registers the spatial coordinates to integrate heterogeneous data from different sensors into a unified vector structure, providing comprehensive and consistent input for the prediction model;

[0079] Compared with a single information source, this multi-modal data collection and fusion method provides highly accurate and complete information about the state of pollutants; not only the position, concentration and temperature of the pollutants are known, but more importantly, the motion vector is known; the richness of this information greatly improves the accuracy of subsequent diffusion trajectory prediction, laying a solid data foundation for the effectiveness of the entire closed-loop control.

[0080] The generation process of the predicted state vector is as follows:

[0081] The system state vector at the current time, the real-time data vector generated by the environmental state sensing unit, and the control vector of the last control period are input into a preset nonlinear mapping function for operation to generate a predicted state vector;

[0082] The system state vector includes position information and concentration information of gaseous molecular pollutants;

[0083] This embodiment is a specific implementation of the generation process of the predicted state vector in the predictive analysis unit;

[0084] The generation process of the predicted state vector uses the state space paradigm in control theory to abstract complex fluid dynamics problems into calculable prediction models; the internal logic is that the system state vector at the current time , the real-time data vector generated by the environmental state sensing unit , and the control vector of the last control period are jointly input into a preset nonlinear mapping function An operation is performed to generate a predicted state vector for a future very short time step ; the process is described by the following equation:

[0085] ;

[0086] In this equation, each parameter is defined as follows:

[0087] : system state vector at the current time, a vector containing the current known AMC position information and concentration information, data type: vector, source: predicted value at the last time or initial measurement value;

[0088] : real-time data vector, containing the AMC motion vector, temperature field and concentration information collected by the sensor at the current time, data type: vector, source: environmental state sensing unit;

[0089] : control vector of the last control period, containing the control parameters such as the wind speed and direction of each vector air supply unit that have been applied, data type: vector, source: historical instruction record of the cooperative control unit;

[0090] : nonlinear mapping function, representing the model of the physical evolution law of the system, data type: long short-term memory network model, source: pre-trained and determined by offline supervised learning on the historical operation data of the clean room;

[0091] : system process noise vector, representing the uncertainty of the model and the unmodeled small disturbance, data type: vector, source: random variable based on statistical characteristics;

[0092] : predicted state vector, the model output of the prediction of the AMC position and concentration at the next time, data type: vector, source: calculation result of this equation;

[0093] By introducing the control vector of the last period as input , this embodiment enables the prediction model to understand the influence of the control behavior on the evolution of the system, so that the future state of the system under active intervention can be more accurately predicted; using a pre-trained LSTM model as the mapping function , it can effectively capture the high nonlinearity and time dependence of fluid diffusion, greatly improve the prediction speed compared with traditional physical model solving, and realize the rapid forward-looking deduction that meets the real-time control requirements;

[0094] To ensure the robustness and safety of the system, the system also includes a set of fault diagnosis and safety guarantee mechanism; the mechanism monitors the validity of the input data in real time When the sensor data exceeds the reasonable threshold or is not updated for a long time, it will be marked as untrusted, and the adjacent sensor data will be interpolated or the historical data will be degraded to predict; at the same time, the flow field execution instruction generated by the cooperative control unit will pass through a feasibility checking module before being issued, to ensure that all parameters are within the safe working range of the hardware executor; in addition, the system is built-in monitoring module, continuously comparing the predicted state With the actual sensor state of the next moment, if the error between the two exceeds the preset threshold continuously, the system will judge that the model is mismatched, and can trigger an alarm or automatically switch to a preset safe purification mode that does not rely on complex models, such as global low-speed ventilation, to ensure the minimum safety performance.

[0095] The process of vortex kinetic energy decomposition processing is as follows:

[0096] Determine the predicted thermal plume intensity according to the predicted state vector;

[0097] According to the predicted thermal plume intensity, adjust the vibration frequency of the micro-vortex plate array to determine the active dissipation coefficient;

[0098] And based on the active dissipation coefficient, accelerate the large-scale vortex total kinetic energy decay of the thermal plume to generate a weakened flow field environment;

[0099] This embodiment is a specific implementation of the vortex kinetic energy decomposition processing process in the flow field preprocessing unit;

[0100] The process of vortex kinetic energy decomposition processing aims to actively accelerate the energy dissipation of large-scale vortices in the thermal plume; this process is quantitatively described by a vortex kinetic energy dissipation model improved based on the cascade theory of turbulent energy; to realize this process, the system determines the predicted thermal plume intensity according to the temperature field information contained in the predicted state vector , such as quantifying the predicted buoyancy flux; according to the predicted thermal plume intensity, adjust the vibration frequency of the micro-vortex plate array ; the micro-vortex plate array refers to a group of small, fast-responding mechanical structures made of piezoelectric material, which can introduce small disturbances in the fluid through high-frequency vibration; there is a preset function relationship between the vibration frequency and the active dissipation coefficient ; the preset function relationship refers to a nonlinear mapping relationship stored in the system in the form of lookup table or polynomial function after calibration through high-precision fluid simulation or wind tunnel experiment, which ensures that the dissipation effect of a specific size can be accurately generated as needed and quickly accessed;

[0101] Based on a determined active dissipation coefficient The system accelerates the total kinetic energy of large-scale vortices in the thermal plume. The attenuation of the flow field generates a weakened flow environment; this process is described by the following equation:

[0102] ;

[0103] In this formula, the parameters are defined as follows:

[0104] : Total kinetic energy of large-scale vortices, characterizing the energy of macroscopic vortices in thermal plumes, dimension: joule, source: estimated from flow field data;

[0105] Time, unit: second;

[0106] : Vortex kinetic energy generation rate, generated by the buoyancy of the heat source, dimension: watt, source: calculated based on the predicted intensity of the thermal plume;

[0107] Turbulent natural dissipation rate: Characterizes the rate of natural energy loss caused by fluid viscosity, which is transferred from large-scale eddies to small-scale pulsations and ultimately converted into heat energy. Dimension: Watt. Source: Estimated based on fluid dynamics theory.

[0108] Active dissipation coefficient, an coefficient introduced by the spoiler array and related to the vibration frequency. The related additional dissipation term has the following dimensions: This coefficient is related to the total kinetic energy of the vortex. product This represents the additional energy dissipation rate introduced by active control, measured in watts; source: determined based on control commands and preset functional relationships; vibration frequency. With active dissipation coefficient There exists a pre-defined functional relationship between them. This univariate functional relationship is a simplified model obtained through high-precision simulation or wind tunnel testing under specific and representative operating conditions, such as standard background flow velocity and heat source intensity. It captures the dose-effect relationship of frequency, the most important control variable, thus achieving rapid and simple control. In actual operation, the closed-loop characteristics of the system will compensate for the model errors caused by its simplification.

[0109] : Vibration frequency of the micro-spoiler array;

[0110] The gain effect of this embodiment is that, by a delicate way, the energy core of the hot plume is intervened and destructed at the initial stage of the formation of the hot plume, rather than being suppressed by strong wind after the hot plume develops and grows up; by precisely adjusting the value, the system can drive the energy consumption of the spoiler to effectively weaken the strong hot plume with a small energy input, significantly reducing the energy required for the subsequent guiding and capturing steps, and embodying a very high control energy efficiency ratio;

[0111] The purpose of this calibration is to establish a control instruction, the vibration frequency of the micro spoiler array and the physical effect, the generated active dissipation coefficient between them stable and predictable association; by completing this complex fluid dynamics analysis and experiment in advance, the system can store the results into a simple function ; in actual control, when the system needs to generate a specific intensity of dissipation effect to accelerate the decay of vortex kinetic energy, that is, a specific value is needed in the formula , it does not need to be recalculated, but can be directly queried by the vibration frequency set ; this way simplifies the complex physical process into a quick lookup table or function call, greatly improving the response speed and control efficiency of the system.

[0112] Example 2

[0113] The quantitative planning analysis process of the guiding path is as follows:

[0114] Based on the predicted state vector, determine the purification invalidity index;

[0115] Determine the energy consumption of the driving airflow control node, and normalize the energy consumption to determine the energy cost;

[0116] Get the preset energy cost weight factor and purification risk weight factor;

[0117] And the energy cost and purification invalidity index are weighted and summed to generate a comprehensive cost function, and then a cleaning signal is generated according to the comprehensive cost function;

[0118] The energy cost is the value obtained by normalizing the energy consumption required for a single airflow control node to generate airflow with a preset reference energy value;

[0119] The purification invalidity index is the ratio of the predicted residual concentration of the pollutant after passing through a single airflow control node to the preset safety threshold concentration;

[0120] The embodiment is a specific implementation of the quantitative planning analysis process of the guiding path in the path planning unit, and combines the specific definitions in the above.

[0121] The core of the quantitative planning analysis process of the guiding path is to solve the minimum value of the comprehensive cost function defined in the discretized space grid; the process is based on the predicted state vector to determine the purification invalidity index of each node on the path; as described above, the purification invalidity index is the ratio of the predicted residual concentration of the pollutant after passing through a single airflow control node to the preset safety threshold concentration; the preset safety threshold concentration is the upper limit of the AMC concentration that cannot be exceeded according to the stringent requirements of the semiconductor production process, such as the SEMI standard, which is a benchmark value to ensure product yield;

[0122] At the same time, the system determines the energy consumption of the driving airflow control node and normalizes it to determine the energy cost; the energy cost is a dimensionless value obtained by normalizing the energy consumption required to generate airflow by a single airflow control node, such as a vector air supply unit, with a preset reference energy value ; the preset reference energy value is a standardized energy benchmark, such as the energy consumption of a single fan filter unit in a standard operating period, which serves to eliminate the dimensional differences in energy consumption of different execution units, making the cost calculation comparable;

[0123] The system obtains a preset energy cost weight factor and a purification risk weight factor ; these two weights are core adjustable parameters of the system, which are pre-set according to the overall operation strategy, such as energy saving priority or effect priority, during system initialization, and satisfy the normalization constraint ;

[0124] The system performs a weighted sum of the energy cost and the purification invalidity index to generate a comprehensive cost function , and uses an improved A search algorithm to find the node sequence that minimizes the total cost of the path in the discretized space, and then generates a cleaning signal according to the minimum node sequence, and then generates a cleaning signal according to the optimal sequence; the comprehensive cost function is as follows:

[0125] ;

[0126] In this formula, the parameters are defined as follows:

[0127] : refers to the optimal path consisting of a sequence of nodes;

[0128] : refers to the index of the discrete airflow control node on the path;

[0129] : energy cost weight factor, dimensionless, source: system preset;

[0130] : purification risk weight factor, dimensionless, source: system preset;

[0131] : energy consumption of node i, dimension of joule, source: calculated according to required airflow parameters;

[0132] : reference energy value, dimension of joule, source: system preset benchmark;

[0133] : purification inefficiency index, dimensionless, source: calculated according to predicted state vector ;

[0134] This embodiment unifies the two conflicting goals of purification accuracy and energy consumption under the framework through a quantitative and optimizable cost function; the specific definitions above make each component in the cost function have clear physical meaning and comparability; this enables the system to make truly optimal decisions and find a mathematically provable cleaning path that achieves the best balance between energy consumption and purification effect, thereby improving the control strategy from experience-based fuzzy decision to data-based quantitative optimization;

[0135] Weight factors and adjustment are the key to realizing adaptive decision-making by the system; in the comprehensive cost function:

[0136] ;

[0137] and respectively control the importance of energy cost and purification risk in the total cost calculation;

[0138] When the system judges that the pollution risk is not high, it will generate a regular cleaning signal and set greater than or equal to , for example or At this point, energy costs dominate the total cost, and the path planning algorithm will tend to find a path that, while not the fastest in terms of purification speed, is the most energy-efficient.

[0139] Conversely, when the system predicts a high-risk pollution event by comparing the cost function value with a preset threshold, it will generate an emergency cleanup signal and set... Much larger ,Right now This forces the algorithm to prioritize reducing the purification ineffectiveness index during pathfinding. This means that no matter the energy cost, we must plan the fastest and most thorough removal path to ensure production safety.

[0140] The process of generating a clear signal includes:

[0141] The comprehensive cost function is compared and analyzed with the preset cost threshold;

[0142] If the overall cost function is greater than the cost threshold, an emergency cleanup signal is generated, and the cleanup risk weight factor is set to be much greater than the energy cost weight factor.

[0143] If the overall cost function is not greater than the cost threshold, a regular cleanup signal is generated, and the energy cost weighting factor is set to be greater than or equal to the cleanup risk weighting factor.

[0144] This embodiment is a further adaptive optimization of the path planning process, specifically reflected in the introduction of a dynamic adjustment mechanism in the generation of the clearing signal;

[0145] In this embodiment, the process of generating the clearing signal adds a decision logic layer; to make a decision, the comprehensive cost function calculated above is used. The final value is compared and analyzed with a preset cost threshold; the preset cost threshold is a critical value determined based on risk assessment. For example, the threshold can be set to the cost value corresponding to a high-risk contamination event that is identified through historical data analysis as causing the product batch to be scrapped.

[0146] The decision-making logic is as follows: If the comprehensive cost function If the value exceeds the cost threshold, it indicates that the system has predicted a high-risk pollution event. In this case, the system will generate an emergency cleanup signal and set the cleanup risk weighting factor to be much larger than the energy cost weighting factor. This forces the path planning algorithm to prioritize purification effectiveness, planning the fastest and most thorough removal path. If the overall cost function is not greater than the cost threshold, it indicates that the pollution is within a controllable range. At this time, the system generates a regular purification signal and sets the energy cost weight factor to be greater than or equal to the purification risk weight factor. or Make the system in the premise of ensuring the basic purification effect, with energy saving as the main target path planning;

[0147] This embodiment gives the system intelligent and adaptive operation mode switching capability; it can run in energy saving mode in the normal state to minimize daily energy consumption; and when serious pollution threat is detected, it can automatically and instantaneously switch to emergency mode, at the cost of ensuring production safety; this dynamic adjustment strategy makes the system achieve further optimization of energy efficiency on a macro time scale, while ensuring the robustness and rapid response capability to sudden malignant events.

[0148] Embodiment 3

[0149] The generation process of the flow field execution instruction is as follows:

[0150] Calculate the air supply pulsation angle frequency for each unit in the vector air supply unit array;

[0151] Calculate the initial phase for each unit;

[0152] And combined with the air supply pulsation angle frequency and the initial phase calculated for each unit, generate the flow field execution instruction;

[0153] It also includes a flow field execution unit;

[0154] The flow field execution unit is used to receive and execute the flow field execution instruction to generate a virtual air duct for wrapping and guiding the pollutants, achieving the capture of the pollutants

[0155] This embodiment is a specific implementation of the process of generating a flow field execution instruction by the cooperative control unit, and combines the above-mentioned flow field execution unit for receiving and executing the instruction;

[0156] The generation process of the flow field execution instruction is the reverse solving of the air flow modulation technology; when the cooperative control unit receives the removal signal generated by the path planning unit, i.e. the optimal node path, the internal reverse solver is activated;

[0157] The solver reversely calculates the parameters of multiple air sources required to form focused air flow for each target point on the path; it calculates the required air supply amplitude vector for each unit in the vector air supply unit array air supply pulsation angle frequency and initial phase ; the array of vector air supply units is the core component of the flow field execution unit, composed of multiple air flow nozzles that can independently control the direction, speed and pulsation frequency of the air flow; finally, the system generates complete flow field execution instructions by combining the above parameters calculated for each unit; the goal of the instructions is to make the air flow waves emitted by each unit interfere constructively at the target path point in the far field space, forming a highly directional air flow beam; the target point The focused air flow formed at the target point is formed by the vector superposition described by the following formula:

[0158] ;

[0159] In this formula, each parameter is defined as follows:

[0160] : the resultant air flow velocity vector at the target point and time The resultant velocity is dimensionless: meters / second, source: the calculation result of this formula;

[0161] : the index and total number of air supply units;

[0162] : the air supply amplitude vector of the jth unit, dimensionless: meters / second, source: calculated by the inverse solver;

[0163] : the wave vector, related to the direction of the air flow, source: determined according to the geometric relationship between the unit position and the target point;

[0164] : the pulsation angular frequency and initial phase of the air supply, which is the core calculation output of this process, source: calculated by the inverse solver;

[0165] The system also includes a flow field execution unit; this unit is physically implemented for control, used to receive and execute the above flow field execution instructions; composed of an array of vector air supply units and a network of distributed micro suction ports; after receiving the instructions, each vector air supply unit works cooperatively according to the specified parameters to generate a virtual air duct that wraps and guides the pollutants; this air duct is an invisible pipeline formed by precisely focused air flow, which completely wraps the pollution cloud and stably transports it along the optimal path to the micro suction port activated synchronously, achieving the capture and removal of pollutants;

[0166] The function of this inverse solver is to perform a reverse engineering calculation; the problem it needs to solve is: given the core components of the focused air flow formed at a series of target points on the optimal node path, which can be described by the following idealized wave control model:

[0167] ;

[0168] It should be noted that this formula is a simplified physical model of cooperative control, which is used to guide the inverse solver to calculate the core parameters such as phase and frequency. It assumes that the mutual interference of each airflow in the far field plays a dominant role, and the actual flow field is driven by the instructions calculated by this model and modified by the sensing unit through closed-loop feedback;

[0169] Each air supply unit in the above formula , the air supply pulsation angular frequency and the initial phase which must be adopted are inversely calculated; these core control variables are combined to form the final flow field execution instructions that can be accurately executed and issued to the hardware;

[0170] In this embodiment, the inverse solver is implemented based on an iterative optimization algorithm; the difference between the synthesized airflow velocity vector calculated by the formula at all target points on the path and the expected guide velocity vector; the solver searches for the optimal combination in the parameter space that satisfies physical constraints such as maximum wind speed and frequency range through algorithms such as covariance matrix adaptive evolution strategy or particle swarm optimization, until the objective function converges. This process is completed in real time when the control instructions are generated;

[0171] This embodiment describes in detail the transformation process from the abstract path to the physical airflow; by calculating the exact operating parameters for each execution unit, the system can carve out airflow structures of any form in three-dimensional space with extremely high precision and flexibility; the existence of the flow field execution unit makes this delicate control physically possible; this virtual air duct technology completes the guidance and capture of pollutants in a non-contact and adaptive manner, with extremely low energy consumption, extremely fast response speed, and extremely high flexibility, which is the core technology of the invention to achieve efficient and low-cost precise removal;

[0172] The system also has intelligent adaptive decision-making capabilities; by comparing and analyzing the comprehensive cost function value with the preset cost threshold, the system can independently judge the risk level of pollution events; when a high-risk event is predicted, the system generates an emergency removal signal, sets the purification risk weight factor to be higher than the energy cost weight factor, and ensures the removal effect at any cost; in the normal state, a normal removal signal is generated, and the energy cost weight factor is set to be greater than or equal to the purification risk weight factor, with energy saving as the main operating goal; this dynamic adjustment mechanism enables the system to maximize energy efficiency on a macro time scale while ensuring safety redundancy;

[0173] The application constructs a complete closed-loop control system from sensing, prediction to decision-making and execution through deep coupling of environmental state sensing, predictive analysis, flow field preprocessing, path planning and cooperative control; it replaces high-energy consumption global dilution with predictive and low-disturbance precise airflow guidance, changes the control mode of pollutants, and optimizes the purification effect and energy efficiency cooperatively, which has great significance of technical progress.

[0174] It should be noted that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A smart building sampling and detection control system based on IoT sensing, characterized in that, It includes an environmental state sensing unit, a predictive analysis unit, a flow field preprocessing unit, a path planning unit, and a collaborative control unit; The environmental condition sensing unit is used to collect environmental condition data of the target monitoring area to generate real-time data vectors; The predictive analysis unit is used to receive real-time data vectors and perform diffusion trajectory deduction according to a preset state space paradigm to generate a predicted state vector. The flow field preprocessing unit is used to perform vortex kinetic energy deconstruction processing on the thermal plume in response to the predicted state vector, so as to generate a weakened flow field environment. The path planning unit is used to combine the predicted state vector with the weakened flow field environment to perform quantitative planning analysis of the guiding path in order to generate a clearing signal. The collaborative control unit is used to generate a virtual air duct topology based on the clearing signal, and to generate flow field execution commands based on the virtual air duct topology. The process of deconstructing the vortex kinetic energy is as follows: The predicted thermal plume intensity is determined based on the predicted state vector; Based on the predicted thermal plume intensity, the vibration frequency of the micro-turbulence array is adjusted to determine the active dissipation coefficient; Based on the active dissipation coefficient, the total kinetic energy decay of the large-scale vortex of the thermal plume is accelerated to generate a weakened flow field environment. The quantitative planning and analysis process for the guidance path is as follows: The purification ineffectiveness index is determined based on the predicted state vector; Determine the energy consumption of the drive airflow control node and normalize the energy consumption to determine the energy cost; Obtain the preset energy cost weighting factor and purification risk weighting factor; The energy cost and the purification ineffectiveness index are weighted and summed to generate a comprehensive cost function, and then a purification signal is generated based on the comprehensive cost function. The energy cost is a value obtained by normalizing the energy consumption of driving a single airflow control node to generate the required airflow with a preset reference energy value. The purification ineffectiveness index is the ratio of the predicted residual concentration of pollutants after passing through a single airflow control node to the preset safety threshold concentration.

2. The smart building sampling and detection control system based on IoT sensing according to claim 1, characterized in that, The process by which the environmental state sensing unit collects environmental state data includes: Obtain the three-dimensional motion vector of gaseous molecular pollutants; Obtain the surface temperature distribution of the equipment; To obtain the local concentration of gaseous molecular pollutants; It integrates three-dimensional motion vectors, surface temperature distribution, and local concentration of gaseous molecular pollutants to generate real-time data vectors.

3. The intelligent building sampling and detection control system based on IoT sensing according to claim 1, characterized in that, The process of generating the predicted state vector is as follows: The current system state vector, the real-time data vector generated by the environmental state sensing unit, and the control vector of the previous control cycle are input into a preset nonlinear mapping function for calculation to generate a predicted state vector. The system state vector includes the location and concentration information of gaseous molecular pollutants.

4. The intelligent building sampling and detection control system based on IoT sensing according to claim 1, characterized in that, The process of generating the clearing signal includes: The comprehensive cost function is compared and analyzed with the preset cost threshold; If the overall cost function is greater than the cost threshold, an emergency cleanup signal is generated, and the cleanup risk weight factor is set to be greater than the energy cost weight factor. If the overall cost function is not greater than the cost threshold, a regular cleanup signal is generated, and the energy cost weighting factor is set to be greater than or equal to the cleanup risk weighting factor.

5. A smart building sampling and detection control system based on IoT sensing according to claim 1, characterized in that, The process of generating the flow field execution command is as follows: Calculate the air supply pulsation angular frequency for each unit in the vector air supply unit array; The initial phase is calculated for each unit; The flow field execution command is generated by combining the calculated air pulsation angular frequency and initial phase for each unit.

6. The intelligent building sampling and detection control system based on IoT sensing according to claim 1, characterized in that, It also includes a flow field execution unit; The flow field execution unit is used to receive and execute flow field execution commands to generate a virtual air duct to enclose and guide pollutants, thereby capturing the pollutants.

Images