Intelligent clean room control method and system, electronic equipment and medium

Abstract

The invention discloses an intelligent clean room control method and system, electronic equipment and a medium, and relates to the technical field of data processing. The method comprises the steps that an infrared sensor array and a pressure sensor array are deployed in a clean room, and heat signal distribution data and pressure distribution data of personnel are collected respectively; the infrared sensors are installed on the top and the side wall, and the pressure sensors are distributed below the bottom plate in a grid shape. The system firstly normalizes thermal signal data to obtain a thermal signal matrix, and calculates barycentric coordinates of pressure distribution. Spatial position matching is carried out on the thermal signal matrix and the pressure gravity center, the Euclidean distance is calculated, and target matching pairs smaller than a threshold value are screened, so that the actual number of personnel is determined. And the clean room is divided into a plurality of control areas according to the position information of the target matching pair, the rotating speed of a fan is dynamically adjusted based on the personnel density coefficient of each area, and accurate air supply control is achieved. By implementing the technical scheme provided by the invention, the control efficiency of the clean room can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an intelligent clean room control method and system, an electronic device and a medium. BACKGROUND

[0002] With the vigorous development of semiconductor, pharmaceutical manufacturing, precision instruments and other industries, the demand for clean environment in industrial production is increasing. In clean workshops and dust-free rooms, clean rooms as key protective equipment, its main function is to remove dust and particles on the surface of personnel or goods through the blowing action of high-speed airflow, so as to effectively prevent pollutants from entering the clean area. Therefore, the control efficiency of the clean room directly affects the protection quality of the whole clean environment.

[0003] At present, the clean room mainly adopts the mode of setting human body sensing device at the entrance, when detecting that someone enters, starting the fan to run at a preset fixed speed for a fixed time, or according to the preset program to carry out simple on-off control.

[0004] But in actual application, this fixed mode control strategy has obvious shortcomings in actual operation. When multiple people use at the same time, the unified air speed is difficult to meet the dust removal needs of personnel at different positions; while in single use, the excessive air speed will cause unnecessary energy consumption. This control mode is difficult to accurately adjust the fan according to the use state of the clean room, thereby reducing the control efficiency of the clean room. SUMMARY

[0005] The present application provides an intelligent clean room control method and system, an electronic device and a medium, which can improve the control efficiency of the clean room.

[0006] In a first aspect, the present application provides an intelligent clean room control method, comprising: The infrared sensor array arranged in the clean room collects the thermal signal distribution data of personnel, and the pressure sensor array arranged in the clean room collects the pressure distribution data of personnel, the infrared sensor array includes a plurality of infrared sensors, each infrared sensor is distributed on the top and side wall of the clean room according to a preset interval, the pressure sensor array includes a plurality of pressure sensors, each pressure sensor is distributed below the bottom plate of the clean room according to a preset grid shape; The thermal signal distribution data is subjected to signal intensity normalization processing to obtain a normalized thermal signal matrix, each element in the thermal signal matrix represents the thermal signal intensity value of the corresponding spatial position; The pressure distribution data is subjected to center of gravity calculation to determine the center of gravity coordinates of a plurality of pressure concentration areas; spatially match the heat signal matrix with each of the barycentric coordinates to obtain a plurality of matching pairs, and calculate the Euclidean distance between the heat signal peak point and the barycentric coordinate of each of the matching pairs, and screen out a target matching pair with a Euclidean distance less than a preset threshold value; determine the actual number of personnel in the clean room based on the number of target matching pairs, and divide the clean room into a plurality of wind speed control regions according to the position information of the barycentric coordinates in each of the target matching pairs; For each of the wind speed control regions, determine a personnel density coefficient according to the ratio of the number of personnel in the wind speed control region to the area of the region, and adjust the rotating speed of the fan corresponding to the wind speed control region based on the personnel density coefficient, wherein the rotating speed of the fan is positively correlated with the personnel density coefficient.

[0007] By adopting the above technical solutions, the heat signal distribution data and the pressure distribution data of personnel in the clean room are collected by using an infrared sensor array and a pressure sensor array respectively, the heat signal distribution data is normalized to obtain a heat signal matrix, and the barycentric coordinates of the pressure concentration region are determined by performing barycentric calculation on the pressure distribution data, the heat signal matrix is spatially matched with the barycentric coordinates, and target matching pairs are screened based on the Euclidean distance, so that the actual number of personnel and the position distribution in the clean room can be accurately identified; further, the clean room is divided into a plurality of wind speed control regions according to the position information of the target matching pairs, and the rotating speed of the corresponding fan is dynamically adjusted based on the personnel density coefficient of each region, thereby realizing differentiated control of the wind speed in different regions of the clean room, ensuring sufficient dust removal effect in personnel-intensive regions, avoiding energy waste in personnel-sparse regions, and improving the control efficiency of the clean room.

[0008] Optionally, the pressure distribution data is converted into a two-dimensional pressure matrix, and the matrix element value in the two-dimensional pressure matrix represents the pressure value at the corresponding position; the two-dimensional pressure matrix is segmented by using a threshold segmentation algorithm to obtain a plurality of independent pressure signal clusters; the boundary contour of each of the pressure signal clusters is extracted, and the weighted average value of all pressure values in each of the boundary contours is calculated as the characteristic pressure value of the corresponding pressure signal cluster; when the characteristic pressure value is greater than a preset human body pressure threshold value, the corresponding pressure signal cluster is determined as a pressure concentration region; and the centroid of the pressure concentration region is calculated as the corresponding barycentric coordinate.

[0009] Optionally, a three-dimensional coordinate system is constructed, wherein an X-axis and a Y-axis are parallel to a bottom plate of the clean room, and a Z-axis is perpendicular to the bottom plate of the clean room, and the gravity center coordinates are mapped from a two-dimensional plane to the three-dimensional coordinate system; a region with a thermal signal intensity value greater than a preset thermal signal threshold value is detected in the thermal signal matrix, and a three-dimensional coordinate corresponding to a thermal signal peak point of the region is determined; a spherical search space is established with each gravity center coordinate as a center, and a radius of the spherical search space is determined by a historical average height of a human body in the clean room; a three-dimensional coordinate corresponding to a thermal signal peak point is searched in each spherical search space, and when a thermal signal peak point is searched, the searched thermal signal peak point is associated with a gravity center coordinate of the spherical search space to obtain a matching pair; when there are multiple thermal signal peak points in the spherical search space, a thermal signal peak point with the closest projection distance between the gravity center coordinate of the spherical search space is selected for association to obtain a matching pair.

[0010] Optionally, the number of target matching pairs is time-filtered to obtain a filtered number of matching pairs; an access door control signal of the clean room is acquired, and a start time and an end time of the clean room are determined according to the access door control signal; at each start time, the filtered number of matching pairs is taken as an initial number of personnel in the clean room, and the initial number of personnel is updated to a personnel counter; during a time period between two adjacent start times, when a sudden change in the filtered number of matching pairs is detected, the value of the personnel counter is updated based on a difference between the number before and after the sudden change; at the end time, the value of the personnel counter is determined as an actual number of personnel in the clean room.

[0011] Optionally, fan layout information of the clean room is acquired, the fan layout information including installation positions of the fans and air supply coverage ranges; the gravity center coordinates of the target matching pairs are mapped into the air supply coverage ranges of the fans based on the installation positions of the fans; the number of gravity center coordinates in the air supply coverage ranges of the fans is counted, and the air supply coverage ranges of the fans are divided into corresponding air speed control regions based on the number of gravity center coordinates; when there is an overlapping region between the air supply coverage ranges of adjacent fans, and the number of gravity center coordinates in the overlapping region is greater than a preset overlapping threshold value, the overlapping region is divided into independent air speed control regions.

[0012] Optionally, a heat map of the air supply coverage of the fan is constructed, a pixel value of the heat map is determined by the number of the barycentric coordinates of the corresponding position; the heat map is subjected to region growing segmentation processing, taking the barycentric coordinate position as a seed point, within a preset growing threshold range, adjacent regions with a pixel value difference absolute value less than a preset pixel threshold are merged into the same segmented region; the total number of barycentric coordinates in each segmented region is calculated, and the segmented region with a barycentric coordinate total number greater than a preset person number threshold is marked as a candidate wind speed control region; the candidate wind speed control region is matched with the air supply coverage of the fan, and when the coincidence degree of the candidate wind speed control region with the air supply coverage of any one fan is greater than a preset proportion, the candidate wind speed control region is determined as the wind speed control region corresponding to the fan.

[0013] Optionally, a ratio of the area of the wind speed control region to the rated air volume of the fan is calculated to obtain a reference air volume per unit area; the reference air volume is linearly weighted according to the personnel density coefficient to obtain a target air volume per unit area; the total air volume required is calculated based on the target air volume per unit area and the total area of the wind speed control region; the target fan rotating speed value corresponding to the total air volume is determined according to the reference characteristic curve of the fan; the rotating speed of the fan corresponding to the wind speed control region is adjusted to the target fan rotating speed value.

[0014] In a second aspect of the present application, an intelligent clean room control system is provided, the system comprising: A data acquisition module is configured to acquire thermal signal distribution data of personnel through an infrared sensor array arranged in the clean room, and to acquire pressure distribution data of personnel through a pressure sensor array arranged in the clean room, the infrared sensor array comprising a plurality of infrared sensors, each of which is distributed on the top and side wall of the clean room at a preset interval, and the pressure sensor array comprising a plurality of pressure sensors, each of which is distributed under the floor of the clean room in a preset grid shape; A target matching pair determination module is configured to perform signal intensity normalization processing on the thermal signal distribution data to obtain a normalized thermal signal matrix, each element in the thermal signal matrix representing a thermal signal intensity value of the corresponding spatial position; to perform barycentric calculation on the pressure distribution data to determine the barycentic coordinates of a plurality of pressure concentration areas; to perform spatial position matching between the thermal signal matrix and each of the barycentric coordinates to obtain a plurality of matching pairs, and to calculate the Euclidean distance between the thermal signal peak point and the barycentric coordinates of each matching pair, and to screen out a target matching pair with a Euclidean distance less than a preset threshold; A wind speed control region determination module is configured to determine the actual number of personnel in the clean room based on the number of target matching pairs, and to divide the clean room into a plurality of wind speed control regions according to the position information of the barycentric coordinates in each target matching pair. The clean room control module is configured to determine a personnel density coefficient according to a ratio of the number of personnel to the area of the wind speed control region in each wind speed control region, and adjust the rotation speed of the corresponding air blower of the wind speed control region based on the personnel density coefficient, wherein the rotation speed of the air blower is positively correlated with the personnel density coefficient.

[0015] In a third aspect of the present application, an electronic device is provided, which comprises a memory, a processor, and a program stored in the memory and executable on the processor, and the program can be loaded and executed by the processor to implement the intelligent clean room control method.

[0016] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program can be executed by a processor to make the processor implement the intelligent clean room control method.

[0017] In summary, the one or more technical solutions provided by the present application have at least the following technical effects or advantages: By adopting the above technical solution, the infrared sensor array and the pressure sensor array are used to respectively collect the thermal signal distribution data and the pressure distribution data of the personnel in the clean room, the thermal signal matrix is obtained by normalizing the thermal signal distribution data, the gravity coordinates of the pressure concentration area are determined by performing gravity calculation on the pressure distribution data, the target matching pair is screened based on the Euclidean distance by matching the thermal signal matrix with the gravity coordinates in space position, so that the actual number of personnel and the position distribution in the clean room can be accurately identified; further, the clean room is divided into multiple wind speed control regions according to the position information of the target matching pair, and the rotation speed of the corresponding air blower is dynamically adjusted based on the personnel density coefficient of each region, thereby realizing the differentiated control of the wind speed in different regions of the clean room, which can not only ensure that the personnel-intensive area obtains sufficient dust removal effect, but also avoid energy waste in the personnel-sparse area, thereby improving the control efficiency of the clean room. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of an intelligent clean room control method provided by an embodiment of the present application; Figure 2 is a structural schematic diagram of an intelligent clean room control system provided by an embodiment of the present application; Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0019] Legend of reference signs: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0020] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in combination with the accompanying drawings in the specification embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0021] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0022] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used only for the purpose of description, and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0023] The embodiments of the present application provide an intelligent clean room control method. In one embodiment, please refer to Figure 1 , Figure 1 is a flowchart of the intelligent clean room control method provided by the embodiments of the present application. The method can be implemented by relying on a computer program, which can be integrated in an application or run as an independent tool application. The method can also be implemented by relying on a single-chip microcomputer or run on an intelligent clean room control system based on the von Neumann system. Specifically, the method can include the following steps: Step 101: collecting the thermal signal distribution data of personnel through an infrared sensor array arranged in the clean room, and collecting the pressure distribution data of personnel through a pressure sensor array arranged in the clean room, the infrared sensor array including a plurality of infrared sensors, each infrared sensor being distributed on the top and side wall of the clean room according to a preset interval, the pressure sensor array including a plurality of pressure sensors, each pressure sensor being distributed below the bottom plate of the clean room according to a preset grid shape.

[0024] The infrared sensor array represents a sensing network formed by a plurality of infrared sensors arranged at a specific interval, for detecting the heat radiation emitted by the human body; the pressure sensor array represents a detection unit composed of a plurality of pressure sensors arranged in a grid shape, for measuring the pressure exerted by the human body on the ground; the heat signal distribution data represent a set of heat radiation intensity values of each point in the space detected by the infrared sensor; the pressure distribution data represent a set of pressure values of each point on the ground collected by the pressure sensor; the preset interval represents the fixed installation distance between the infrared sensors, which is usually determined according to the size of the clean room and the detection accuracy requirement; and the preset grid shape represents the way in which the pressure sensors are arranged in a regular rectangular grid.

[0025] Specifically, this step starts to execute when the clean room starts to operate, and continuously collects sensing data after the personnel enter the clean room. A plurality of infrared sensors are installed on the top and side wall of the clean room, and the sensors maintain a fixed interval, forming a complete heat signal detection network, which collects the heat radiation intensity distribution in the space in real time; at the same time, pressure sensors are installed under the floor of the clean room in a regular grid shape, which detects the pressure generated when the personnel stand or move in real time, and obtains the ground pressure distribution. The two types of sensors work together to collect personnel position information from different dimensions, providing a data basis for subsequent personnel positioning and wind speed control.

[0026] In some embodiments, the collection of heat signal and pressure data can be realized in various ways: optionally, a thermopile infrared sensor array is used for heat signal collection, the sensor array is first connected to a data acquisition module, then an analog-to-digital converter is used to convert the analog signal to a digital signal, then the digital signal is subjected to noise filtering and temperature compensation processing, and finally the processed data is saved to a data buffer area; optionally, a piezoresistive pressure sensor array is used for pressure data collection, the pressure sensor is first connected to a microprocessor through a signal conditioning circuit, then the voltage values of each sensor are read in real time and subjected to linear calibration, then the voltage values are converted to actual pressure values according to the calibration curve, and finally the pressure data is stored in a data matrix according to the position information. It can be understood that other types of sensors or other data collection methods can also be used to achieve the same function, which is not limited here.

[0027] Step 102: performing signal intensity normalization processing on the heat signal distribution data to obtain a normalized heat signal matrix, each element in the heat signal matrix representing the heat signal intensity value of the corresponding spatial position.

[0028] Wherein, the signal intensity normalization processing represents a mathematical processing process of uniformly converting thermal signal data of different dimensions and ranges to the [0, 1] interval; the thermal signal matrix refers to a data matrix formed by rearranging the thermal signal intensity values in the three-dimensional space according to the spatial position relationship; the thermal signal intensity value represents the thermal radiation energy measured at a certain spatial position point, which is usually represented by temperature or voltage value; the spatial position refers to the specific position coordinates of the thermal signal collection point in the three-dimensional coordinate system of the clean room; the element is used to represent the numerical item in the matrix, and each element corresponds to a sampling point in the actual space.

[0029] Specifically, this step is executed immediately after the thermal signal distribution data collection is completed, for standardizing the original data. First, the thermal signal intensity values of all sampling points are obtained, and the maximum and minimum values in the data set are determined, and then the thermal signal intensity value of each sampling point is mapped to the [0, 1] interval according to the normalization formula, wherein the normalization formula is: normalized value=(original value-minimum value) / (maximum value-minimum value). Then, according to the spatial layout relationship of the sensor, the normalized thermal signal intensity values are reorganized into a three-dimensional matrix form, and each dimension of the matrix corresponds to the length, width and height directions of the space respectively, thereby constructing a complete thermal signal spatial distribution model.

[0030] In some embodiments, the normalization processing and matrix construction of the thermal signal data can be realized in various ways: optionally, the maximum and minimum value normalization method is adopted, first the original thermal signal data is traversed, and the maximum and minimum values are recorded, then each data point is divided by the difference between the maximum value and the minimum value after subtracting the minimum value, then the normalized data is rearranged into a matrix form according to the spatial index of the sampling point; optionally, the mean standardization method is adopted, first the average value and the standard deviation of all thermal signal data are calculated, then each data point is divided by the standard deviation after subtracting the average value, to obtain the standardized value, then the interval mapping is performed on the standardized value to make it fall within the [0, 1] range, and finally the thermal signal matrix is constructed according to the spatial position information. It can be understood that other normalization algorithms or matrix construction methods can also be used to realize the standardization processing of the data, which is not limited here.

[0031] Step 103: Calculate the center of gravity of the pressure distribution data to determine the center of gravity coordinates of the plurality of pressure concentration regions.

[0032] The pressure distribution data represents the spatial distribution of the ground pressure values collected by the pressure sensor array. The center of gravity calculation refers to the calculation process of determining the mass center of the pressure distribution area by mathematical methods. The pressure concentration area represents a continuous spatial range where the pressure values are significantly higher than the surrounding areas, usually corresponding to the standing position of the personnel. The center of gravity coordinates represent the position of the mass center of the pressure concentration area in the two-dimensional plane coordinate system. The mass center is used to represent the geometric balance point of the pressure distribution, and its position is calculated by weighting the pressure values of each point in the area. The continuous spatial range represents a collection of areas with similar pressure values and adjacent physical positions.

[0033] Specifically, this step is performed after obtaining the pressure distribution data, and is used to accurately locate the standing position of the personnel in the clean room. First, the pressure data collected by the pressure sensor array is converted into a two-dimensional pressure distribution matrix, and each element in the matrix corresponds to the pressure reading of a sensor. Then, the pressure distribution matrix is denoted to eliminate the influence of environmental interference and sensor drift. Then, the matrix is segmented using a pressure threshold, and adjacent areas above the threshold are divided into independent pressure concentration areas. For each pressure concentration area, the weighted average position of all pressure values in the area is calculated, which is the center of gravity coordinates of the area. The calculation of the center of gravity coordinates needs to consider the pressure value of each point as the weight, and the final center of gravity position is obtained by weighted average of the pressure value and the position coordinate.

[0034] In some embodiments, the center of gravity calculation of the pressure concentration area can be implemented in various ways: optionally, a region growing algorithm is used to divide the pressure concentration area, a point with the maximum pressure value is first selected as a seed point, then the adjacent high pressure points are searched by expanding to the surrounding, when the pressure difference between the adjacent points and the seed point is less than a preset threshold, the adjacent points are merged into the current area, then the pressure weighted center of gravity coordinates of all points in the merged area are calculated; optionally, a clustering analysis method is used to determine the pressure concentration area, first, the pressure data is subjected to K-means clustering analysis to divide similar pressure values into the same category, then the spatial range and boundary of each category are calculated, and then the center of gravity position of each category pressure distribution is determined by using the centroid calculation formula. It can be understood that other region division or center of gravity calculation methods can also be used to realize the positioning of the pressure concentration area, which is not limited here.

[0035] Based on the above embodiments, as an optional embodiment, in step 103, the pressure distribution data is subjected to center of gravity calculation to determine the center of gravity coordinates of the multiple pressure concentration areas. This step can further include the following steps: Step 201: converting the pressure distribution data into a two-dimensional pressure matrix, and the matrix element value in the two-dimensional pressure matrix represents the pressure value at the corresponding position; using a threshold segmentation algorithm to segment the two-dimensional pressure matrix to obtain multiple independent pressure signal clusters.

[0036] wherein, the pressure distribution data refers to the original pressure signal data set collected by the pressure sensor array; the two-dimensional pressure matrix represents the row-column data structure reorganized by the spatial pressure distribution data; the matrix element value represents the actual pressure measurement value corresponding to each position in the matrix; the threshold segmentation algorithm refers to a mathematical processing method for dividing the data in the matrix into different regions by setting a pressure threshold; the pressure signal cluster represents a continuous region set with similar pressure values and adjacent positions.

[0037] Specifically, the pressure sensor array is rearranged into an M x N two-dimensional matrix according to the row-column relationship of the physical layout, and each matrix element corresponds to a pressure reading of a sensor. A reference pressure threshold P0 is set, and scanning is started from the top left corner of the matrix. When a point with a pressure value greater than P0 is encountered, it is marked as a seed point. Using the seed point as the center, an 8-neighborhood search method is used to expand around it, and all adjacent points with a pressure difference less than ΔP from the seed point are merged into the current pressure signal cluster. Repeat the expansion process until no new merging points can be found, and complete the division of a pressure signal cluster. Continue to scan the matrix elements that have not been processed, and repeat the above process until the entire matrix is traversed. Finally, multiple independent pressure signal clusters are obtained. The selection of P0 needs to consider the measurement range of the sensor and the environmental noise level, and ΔP is used to control the connectivity of the signal cluster, which is usually 10%-20% of P0.

[0038] Step 202: Extract the boundary contour of each pressure signal cluster, and calculate the weighted average value of all pressure values in each boundary contour as the characteristic pressure value of the corresponding pressure signal cluster.

[0039] wherein, the boundary contour represents the set of peripheral edge points of the pressure signal cluster; the weighted average value refers to the average pressure value calculated by considering the pressure value as the weight; the characteristic pressure value represents the comprehensive pressure intensity characteristic of the entire pressure signal cluster.

[0040] Specifically, the boundary tracking algorithm is used to extract the boundary contour of the pressure signal cluster. First, find the leftmost top corner of the pressure signal cluster as the starting point, then search the 8-neighborhood boundary points in clockwise direction. For the current boundary point, its 8-neighborhood is numbered from 0 to 7 in clockwise direction from the top left corner. Starting from number 0, check whether each neighborhood point belongs to the pressure signal cluster. When the first point belonging to the signal cluster is found, record it as a new boundary point and update the current position. Repeat the search process until the starting point is returned, and complete the extraction of the complete boundary contour. For each pressure signal cluster, collect the pressure values of all points in the boundary contour, and calculate the characteristic pressure value using the weighted average method: characteristic pressure value = Σ(Pi x Wi) / ΣWi, where Pi is the pressure value of the ith point, and Wi is the corresponding weight coefficient, which is set to Wi = Pi to highlight the contribution of high pressure areas.

[0041] Step 203: When the feature pressure value is greater than the preset human body pressure threshold value, the corresponding pressure signal group is determined as a pressure concentration area; the centroid of the pressure concentration area is calculated as the corresponding barycentric coordinate.

[0042] wherein the human body pressure threshold value refers to a pressure criterion for determining whether the pressure signal group is generated by the human body; the pressure concentration area represents a confirmed human body standing area; and the centroid coordinate represents a geometric center position of the pressure distribution.

[0043] Specifically, the feature pressure value of each pressure signal group is compared with the preset human body pressure threshold value Pth, and when the feature pressure value is greater than Pth, it is confirmed that the pressure signal group corresponds to an actual human body standing position, and it is marked as a pressure concentration area. The setting of the human body pressure threshold value Pth needs to consider the average weight of adults and the area distribution of the pressure sensor. For the confirmed pressure concentration area, the centroid coordinate is calculated in a pressure-weighted manner. The coordinate calculation formula is: Xbarycenter =∑(xi×Pi) / ∑Pi, Ybarycenter =∑(yi×Pi) / ∑Pi, wherein (xi, yi) is the coordinate of the ith point in the area, and Pi is the pressure value of the point. This calculation method takes into account the unevenness of the pressure distribution and can more accurately reflect the position of the human body barycenter. The calculation accuracy of the centroid coordinate is mainly affected by the resolution of the pressure sensor and the accuracy of the signal group boundary extraction.

[0044] Step 104: Spatial position matching is performed between the heat signal matrix and each barycentric coordinate to obtain a plurality of matching pairs, and the Euclidean distance between the heat signal peak point and the barycentric coordinate of each matching pair is calculated, and a target matching pair with an Euclidean distance less than a preset threshold value is screened out.

[0045] wherein the spatial position matching represents the process of establishing the corresponding relationship between the heat signal distribution and the pressure barycenter in the three-dimensional space; the matching pair refers to the combination of the corresponding heat signal peak point and barycentic coordinate; the heat signal peak point represents the spatial position where the heat signal intensity reaches the maximum value in the local area; the Euclidean distance represents the straight-line distance between two points in the three-dimensional space; and the target matching pair refers to the effective heat signal-pressure barycenter combination that meets the distance threshold requirement.

[0046] Specifically, this step is performed after obtaining the heat signal matrix and the pressure barycentric coordinate, and is used to establish the spatial correspondence between the heat signal distribution and the pressure distribution. First, the pressure barycentric coordinate on the two-dimensional plane is mapped to the three-dimensional space, and a complete spatial coordinate is constructed by adding the height dimension. Then, the local maximum points in the heat signal matrix are searched, which usually correspond to the heat signal peak value of the human head position. For each heat signal peak point, the Euclidean distance between it and all barycentric coordinates is calculated, and the distance calculation formula is: d=[(x1-x2)²+(y1-y2)²+(z1-z2)²] 1 / 2where (x1, y1, z1) and (x2, y2, z2) are three-dimensional coordinates of the peak point of the thermal signal and the barycenter, respectively. The calculated distance value is compared with a preset matching threshold, and matching pairs with a distance less than the threshold are selected as effective target matching pairs.

[0047] In some embodiments, the spatial matching of the thermal signal and the barycenter can be achieved in various ways: optionally, a nearest neighbor matching algorithm is used, a KD tree data structure containing all barycenter coordinates is first constructed, then a nearest neighbor search is performed in the KD tree for each peak point of the thermal signal, the nearest barycenter coordinate is found, then the Euclidean distance between the two points is calculated and compared with the threshold, and finally the point pairs that meet the conditions are recorded as target matching pairs; optionally, a bidirectional search matching method is used, a spherical search space is first established with each barycenter coordinate as the center, and the search radius is the preset threshold, then the peak points of the thermal signal are searched in each search space, then the Euclidean distance between each found peak point and the center of the sphere is calculated, and finally the peak point with the smallest distance is selected to be paired with the barycenter coordinate. It can be understood that other spatial matching algorithms can also be used to pair the peak points of the thermal signal and the barycenter coordinates, which are not limited here.

[0048] On the basis of the above embodiments, as an optional embodiment, in step 104: the thermal signal matrix is spatially matched with each barycenter coordinate to obtain a plurality of matching pairs, this step can further include the following steps: Step 301: a three-dimensional coordinate system is constructed, the X and Y axes in the three-dimensional coordinate system are parallel to the floor of the clean room, the Z axis is perpendicular to the floor of the clean room, and the barycenter coordinates are mapped from a two-dimensional plane to a three-dimensional coordinate system.

[0049] wherein the three-dimensional coordinate system represents a spatial reference frame composed of three mutually perpendicular coordinate axes X, Y and Z; the floor refers to the floor of the clean room; and the barycenter coordinate mapping represents a mathematical transformation process of converting two-dimensional plane coordinates to three-dimensional space coordinates.

[0050] Specifically, a three-dimensional space rectangular coordinate system is established, taking the clean room bottom plate plane as the XY plane, selecting the left front corner of the bottom plate as the coordinate origin O, the right direction as the positive direction of the X axis, the forward direction as the positive direction of the Y axis, and the vertical upward direction as the positive direction of the Z axis. After establishing the coordinate system, the pressure barycenter coordinates (x, y) on the two-dimensional plane are converted into three-dimensional space coordinates (x, y, z). For initial conversion, the two-dimensional coordinates are directly mapped to the XY plane, and the z coordinate value is set to 0 at this time. The coordinate mapping process needs to consider unit conversion, and the row and column indexes of the pressure sensor array are converted into actual physical distances. For example, if the sensor array spacing is d mm, then the actual coordinates of the sensor in the ith row and jth column are x = i x d and y = j x d. After mapping is completed, each barycenter coordinate has a clear position representation in the three-dimensional space, providing basic data for subsequent space matching.

[0051] Step 302: Detecting a region with a heat signal intensity value greater than a preset heat signal threshold value in the heat signal matrix, and determining the three-dimensional coordinates corresponding to the heat signal peak point of the region; establishing a spherical search space with each barycenter coordinate as the center, and the radius of the spherical search space is determined by the historical average height of the human body in the clean room.

[0052] wherein the heat signal threshold value represents an intensity criterion for screening effective heat signals; the heat signal peak point represents the spatial position corresponding to the local maximum of the heat signal intensity; the spherical search space refers to a spherical region with the barycenter coordinate as the center and a specified radius; and the historical average height of the human body represents the average height data of the users of the clean room obtained according to statistics.

[0053] Specifically, a threshold segmentation method is applied in the heat signal matrix to extract the significant heat signal region. Set the heat signal threshold value Th, and traverse each element in the heat signal matrix. When the heat signal intensity value of a certain position is greater than Th, mark the point as a heat signal region. In the marked heat signal region, a local maximum value search algorithm is used to find the heat signal peak point. For each heat signal region, compare the heat signal intensity values of all points in the region, and determine the point with the maximum intensity value as the peak point. After determining the peak point, map it to the three-dimensional space coordinate system according to the installation position information of the sensor. At the same time, for each pressure barycenter coordinate that has been mapped to the three-dimensional space, establish a spherical search space with the coordinate as the center. The radius R of the spherical search space is determined according to the historical statistical average height data of the human body, and is usually between 0.6 and 0.8 times the average height. This setting ensures that the search space can cover the entire range from the human foot to the head, while avoiding excessive search range that may lead to matching errors.

[0054] Step 303: Searching for the three-dimensional coordinates corresponding to the heat signal peak point in each spherical search space, and when the heat signal peak point is searched, associating the searched heat signal peak point with the barycenter coordinate of the spherical search space to obtain a matching pair.

[0055] wherein, the searching in the spherical search space represents searching for a qualified heat signal peak point in a spherical region centered on the barycenter coordinate; the three-dimensional coordinate refers to the position of the heat signal peak point in a space rectangular coordinate system; the association represents establishing a corresponding relationship between the heat signal peak point and the barycenter coordinate; and the matching pair refers to a combination of the heat signal peak point and the barycenter coordinate after the association is completed.

[0056] Specifically, the heat signal peak point searching operation is performed for each spherical search space. The spatial position of each heat signal peak point is compared with the boundary of the spherical search space to determine whether the point is located in the spherical region. In the determination process, the center position and the search radius of the sphere are first determined, and then the actual distance from the heat signal peak point to the center of the sphere is calculated. When the actual distance is less than the search radius, it indicates that the heat signal peak point is located in the spherical search space. Once it is confirmed that the heat signal peak point is located in the search space, the point is immediately associated with the corresponding barycenter coordinate, and the spatial coordinate information of the two points is recorded to form a complete matching pair. This search method ensures that each heat signal peak point can establish a correct spatial corresponding relationship with its corresponding pressure barycenter.

[0057] Step 304: When there are multiple heat signal peak points in the spherical search space, the heat signal peak point with the shortest projection distance to the barycenter coordinate of the spherical search space is selected for association to obtain a matching pair.

[0058] wherein, the multiple heat signal peak points represent multiple local maximum points in the same spherical search space; the projection distance represents the projection length of the line connecting the heat signal peak point to the barycenter coordinate on the horizontal plane; and the nearest heat signal peak point refers to the peak point with the smallest projection distance.

[0059] Specifically, when multiple heat signal peak points are detected in the spherical search space, the optimal matching point needs to be determined by the horizontal projection distance. First, the position information of all heat signal peak points in the spherical search space is projected onto the horizontal plane to obtain the two-dimensional positions of the points on the plane. At the same time, the barycenter coordinate is also projected onto the same plane. The plane distance between the projection point of each heat signal peak point and the barycenter projection point is calculated. By comparing the sizes of all projection distances, the heat signal peak point with the smallest distance is selected as the final matching point. This selection method is based on the feature that the head and the feet of a human body are aligned in the vertical direction when standing, which ensures the accuracy of the matching. The selected heat signal peak point and the barycenter coordinate form a matching pair, and other heat signal peak points not selected are no longer involved in the subsequent processing.

[0060] Step 105: Determine the actual number of personnel in the clean room based on the number of target matching pairs, and divide the clean room into multiple wind speed control regions according to the position information of the barycenter coordinates in each target matching pair.

[0061] Wherein, the number of target matching pairs represents the number of effective heat signal-pressure barycenter combinations after distance screening; the actual number of personnel refers to the number of people currently present in the clean room; the position information of barycenter coordinates represents the specific distribution of personnel standing positions in space; the wind speed control area refers to an independent air supply area divided according to personnel distribution; and the division refers to the process of dividing the clean room space into regions according to the use state.

[0062] Specifically, this step is executed after the heat signal and pressure barycenter matching is completed, for determining the number of people using the clean room and performing regional division. First, the number of target matching pairs that meet the Euclidean distance threshold requirement is counted, since each target matching pair corresponds to a person, the number of matching pairs directly reflects the actual number of personnel in the clean room. Then, the position data of the barycenter coordinates in all target matching pairs is collected to construct a personnel distribution density map. Based on the density map, the clean room space is zoned, and personnel at adjacent positions are divided into the same control area to ensure that the personnel distribution in each control area is relatively concentrated. For areas with sparse personnel distribution, they are merged into adjacent control areas or set as independent low wind speed areas according to air supply requirements. The division result needs to be adapted to the layout of the air supply system of the clean room to ensure that each control area can obtain effective air supply coverage.

[0063] In some embodiments, personnel number determination and regional division can be achieved in various ways: optionally, a time series filtering method is used to determine the number of personnel, first, the number of target matching pairs is time series sampled, then a moving average filter is used to eliminate short-term fluctuations, then a number change threshold is set to detect personnel entry and exit events, and finally the personnel counter is updated according to the number change; optionally, a density clustering algorithm is used for regional division, first, the barycenter coordinates are converted to two-dimensional plane distribution, then the distance matrix between coordinate points is calculated, then DBSCAN density clustering is performed by setting a clustering radius, and finally the clustering result is mapped to the wind speed control area. It can be understood that other number statistics or space division methods can also be used to achieve personnel number determination and regional division, which are not limited here.

[0064] On the basis of the above embodiments, as an optional embodiment, in step 105: determining the actual number of personnel in the clean room based on the number of target matching pairs, this step can further include the following steps: Step 401: Time series filtering is performed on the number of target matching pairs to obtain the filtered number of matching pairs.

[0065] Wherein, time series filtering refers to a mathematical method for smoothing time series data; the number of target matching pairs refers to the number of effective heat signal-pressure barycenter combinations at a specific time; and the filtered number of matching pairs represents the stable value obtained after smoothing.

[0066] Specifically, the number of target matching pairs is continuously sampled to establish a time series dataset. A sampling period T is set, and the current number of target matching pairs is recorded at each sampling time to form a discrete data sequence {n(t)}. A sliding window average filtering method is used to process the data sequence, and the window length is L sampling points. For the filtered output value at time t, the calculation formula is: N(t) = (n(t-L+1) + n(t-L+2) +... + n(t)) / L. The filtering process is performed point by point, and each time the window moves one sampling point backward until the entire data sequence is processed. The filtering result can effectively eliminate data jitter and retain the real trend of the number of personnel. The selection of the filtering window length L needs to balance the system response speed and the filtering effect, and is usually 5-10 sampling periods.

[0067] Step 402: Obtain the access door control signal of the clean room, and determine the start time and end time of the clean room according to the access door control signal; at each start time, the filtered number of matching pairs is taken as the initial number of personnel in the clean room, and the initial number of personnel is updated to the personnel counter.

[0068] Wherein, the access door control signal represents the on-off state signal of the clean room door; the start time refers to the time point when the clean room starts a new working period; the end time represents the time point when the current working period ends; the initial number of personnel refers to the number of personnel in the clean room at the beginning of the working period; the personnel counter represents a counting unit for recording the current number of personnel.

[0069] Specifically, the door control state signal is obtained from the clean room control system, and when it is detected that the access signal changes from closed to open, the current time ts is recorded as the start time. At the start time, the filtered number of matching pairs N(ts) at this time is read, and the value is set as the initial number of personnel of the current working period, and the value is written into the personnel counter. When it is detected that the exit signal changes from open to closed, the current time te is recorded as the end time. For each working period, the system will re-execute this initialization process to ensure the accuracy of personnel counting. The initial value of the personnel counter needs to be set after confirming that the door is completely open and the personnel enter stably, so as to avoid errors in the transition process.

[0070] Step 403: During the time period between two adjacent start times, when a sudden change in the filtered number of matching pairs is detected, the value of the personnel counter is updated based on the difference between the number before and after the sudden change; at the end time, the value of the personnel counter is determined as the actual number of personnel in the clean room.

[0071] Wherein, adjacent start time represents the time point of two consecutive clean room start operations; Mutation represents that the number of matching pairs changes significantly in a short time; The number difference refers to the difference between the number of matching pairs before and after the mutation; The actual number of personnel represents the final number of personnel at the end of the current working period of the clean room.

[0072] Specifically, the filtered number of matching pairs is continuously monitored between two adjacent start times. A mutation detection threshold δ is set, and when the absolute value of the number difference of the two adjacent sampling points is greater than δ, it is determined that a mutation occurs. The number difference ΔN=N(t2)-N(t1) before and after the mutation is calculated, where t1 and t2 are the time points before and after the mutation. According to the positive and negative of the difference, the personnel counter is updated: when ΔN is positive, it means that personnel enter, and the counter value increases |ΔN|; when ΔN is negative, it means that personnel leave, and the counter value decreases |ΔN|. At the end of the working period te, the current value of the personnel counter is read as the actual number of personnel in this working period. This dynamic updating mechanism can accurately track the change of the number of personnel in the clean room.

[0073] On the basis of the above embodiment, as an optional embodiment, in step 105: according to the position information of the barycenter coordinates in each target matching pair, the clean room is divided into multiple wind speed control regions, this step can also include the following steps: Step 404: Obtain the fan layout information of the clean room, the fan layout information includes the installation position of each fan and the air supply coverage range; based on the installation position of each fan, the barycenter coordinates of the target matching pair are mapped into the air supply coverage range of each fan.

[0074] Wherein, the fan layout information represents the spatial distribution data of the air supply device in the clean room; the installation position refers to the fixed coordinates of the fan in the clean room; the air supply coverage range represents the effective air supply action area of a single fan; the barycenter coordinate mapping refers to the process of corresponding personnel position information to the fan coverage range.

[0075] Specifically, the fan layout configuration information is read from the clean room control system database, including the spatial coordinates (xi, yi, zi) and air supply range parameters of each fan. For each fan, according to its installation height and air supply angle, the geometric range of air supply coverage is calculated on the horizontal plane, which is usually a circular or sector area. The barycenter coordinates of each target matching pair are compared with the coverage range of each fan in space position, and the horizontal distance d and the vertical distance h of the barycenter coordinates to the center axis of the fan are calculated. When the barycenter coordinates fall within the air supply coverage range of the fan, an association relationship between the barycenter coordinates and the corresponding fan is established. This mapping ensures the accurate correspondence between personnel position and air supply area, providing basic data for subsequent wind speed control.

[0076] Step 405: Count the number of gravity coordinates in the air supply coverage of each fan, and divide the air supply coverage of each fan into corresponding wind speed control regions based on the number of gravity coordinates.

[0077] Wherein, the number of gravity coordinates refers to the number of personnel position points detected in the coverage of the fan; the wind speed control region represents the spatial range with the same air supply parameter control; the division based on the number of gravity coordinates represents the process of determining the control region boundary according to the personnel distribution density.

[0078] Specifically, the personnel distribution in the air supply coverage of each fan is counted. First, the total number N of gravity coordinates in the coverage is calculated, and then the control region is divided by using the density clustering method according to the spatial distribution characteristics of the coordinates. The region with dense gravity coordinates is divided into a high-density control region, and the region with sparse coordinates is divided into a low-density control region. For each control region, the area S and the number n of contained gravity coordinates are calculated to obtain the local personnel density p = n / S. The boundary of the control region is determined according to the distribution of the density value, ensuring that the personnel distribution in each region is relatively uniform.

[0079] Based on the above embodiment, as an optional embodiment, in step 405: based on the number of gravity coordinates, the air supply coverage of each fan is divided into corresponding wind speed control regions, this step can also include the following steps: Step 415: Construct a heat map of the air supply coverage of the fan, and the pixel value of the heat map is determined by the number of gravity coordinates at the corresponding position.

[0080] Wherein, the heat map represents a visualization image that uses color depth to represent data distribution density; the pixel value refers to the numerical value of each point in the heat map; the number of gravity coordinates represents the number of personnel position points detected per unit area; the air supply coverage represents the effective air supply area of the fan.

[0081] Specifically, the air supply coverage of the fan is discretized into an MxN grid matrix, and the grid size is determined according to the required spatial resolution, usually 10-20 centimeters. For each grid unit, the number of gravity coordinates falling within its range is counted, and this number value is taken as the pixel value of the corresponding position. Gaussian smoothing is used to eliminate the discontinuity caused by gridding, and the size of the smoothing kernel is usually 3x3 or 5x5. The pixel value distribution after smoothing forms a continuous heat map, and the area with a larger value has a darker color, which directly reflects the intensity of personnel distribution. The calculation of the heat map needs to be updated in real time to reflect the dynamic changes of personnel positions. For example, when the grid size is 15 centimeters and the coverage is 3 meters x 3 meters, the resolution of the heat map is 20x20, and each pixel value represents the number of personnel in a range of 225 square centimeters.

[0082] Step 425: performing region growing segmentation processing on the heat map, taking the barycentric coordinate position as a seed point, and merging adjacent regions with an absolute value of a pixel value difference less than a preset pixel threshold into the same segmentation region within a preset growing threshold range.

[0083] wherein the region growing segmentation represents an image processing method of gradually expanding from an initial point to form a connected region; the seed point refers to an initial position of segmentation start; the growing threshold represents a numerical range for judging whether pixels can be merged; the preset pixel threshold refers to a maximum value of adjacent pixel value difference allowed to be merged; and the segmentation region represents a connected region with similar pixel characteristics.

[0084] Specifically, the region growing segmentation algorithm is performed on the heat map. First, all barycentic coordinate positions are set as seed points, and the initial label value of each seed point is equal to the pixel value at its position. The growing threshold range [T_min, T_max] and the pixel difference threshold δ are set. For each seed point, the 8-neighborhood pixels are checked, and when the absolute value of the difference between the neighborhood pixel value and the average value of the current region is less than δ, and the pixel value falls within the growing threshold range, the pixel is merged into the current segmentation region. The average pixel value of the segmentation region is updated, and the newly merged pixel is taken as the starting point for the next round of expansion. This process is repeated until no new pixel satisfying the condition can be found. The segmentation result forms multiple independent regions, and the pixel value distribution within each region is relatively uniform, and the pixel value at the region boundary changes greatly. For example, when δ=5, T_min=10, and T_max=50, the pixel value at the seed point of 45 can merge the adjacent points with pixel values in the range of [40, 50], but cannot merge the points with pixel values less than 40 or greater than 50.

[0085] Step 435: calculating the total number of barycentric coordinates in each segmentation region, and marking the segmentation region with a total number of barycentric coordinates greater than a preset number threshold as a candidate wind speed control region.

[0086] wherein the segmentation region represents a connected region divided by the region growing algorithm; the total number of barycentric coordinates refers to the cumulative number of personnel position points detected in the region; the preset number threshold represents a number standard for judging whether the region needs to be independently controlled; and the candidate wind speed control region refers to a potential control region to be confirmed that meets the number requirement.

[0087] Specifically, personnel distribution statistics analysis is performed for each partitioned region. First, the boundary contour of the partitioned region is obtained, and all grid cells within the region range are determined. Then each grid cell is traversed, and the number of its contained barycentric coordinates is accumulated to obtain the total number of people N in the region. The calculated total number of people is compared with the preset number of people threshold N_th. When N>N_th, it indicates that the personnel density in the region reaches the degree that needs independent control. For the partitioned region that meets the condition, a unique region identifier ID is assigned to it, and it is added to the candidate air velocity control region list. This process ensures that the region with significant personnel aggregation can be independently controlled. For example, when N_th=3, the partitioned region containing 4 or more barycentric coordinates will be marked as a candidate control region.

[0088] Step 445: Matching the candidate air velocity control region with the air supply coverage of the fan, when the coincidence degree of the candidate air velocity control region with the air supply coverage of any fan is greater than the preset proportion, determining the candidate air velocity control region as the air velocity control region corresponding to the fan.

[0089] Wherein, matching means determining the spatial correspondence relationship between the candidate region and the fan coverage; the coincidence degree refers to the ratio of the overlapping area of the two regions to the area of the smaller region; the preset proportion represents the coincidence threshold for judging the region attribution; the air velocity control region represents the finally determined space range that needs independent control.

[0090] Specifically, the candidate air velocity control region is matched with the spatial position of the fan air supply coverage. First, the area S_c of the candidate region and the area S_f of each fan coverage are calculated. Then the overlapping area S_o of the candidate region and each fan coverage is calculated, and the coincidence degree calculation formula is: R=S_o / min(S_c,S_f). The calculated coincidence degree is compared with the preset proportion threshold R_th. When R>R_th, it is confirmed that the candidate region should belong to the corresponding fan control. For the confirmed air velocity control region, its boundary range, the number of the fan to which it belongs, and the personnel distribution characteristics in the region are recorded. These information will be used for subsequent air supply parameter adjustment. For example, when R_th=0.6, it means that the candidate region needs to have at least 60% overlap with the coverage of a certain fan to determine the attribution relationship. This matching mechanism ensures that the division of the control region is adapted to the layout of the actual air supply equipment.

[0091] Step 406: When the air supply coverage of adjacent fans has an overlapping region, and the number of barycentric coordinates in the overlapping region is greater than the preset overlap threshold, the overlapping region is divided into an independent air velocity control region.

[0092] Wherein, the overlapping area represents the intersection part of the adjacent air supply range of the air fan; the overlapping threshold refers to the number standard for judging whether the overlapping area needs independent control; the independent air speed control area represents the space range that needs to set air supply parameters independently.

[0093] Specifically, the air supply coverage of adjacent air fans is checked, and the geometric range of the overlapping area is calculated. For the area with overlap, the number of barycentric coordinates n overlap inside is counted. n overlap is compared with the preset overlapping threshold N th. When n overlap > N th, it indicates that the personnel density in the overlapping area is high, and needs independent control. For the overlapping area determined to need independent control, its boundary range is recalculated, and independent control parameters are allocated. This processing method avoids the air supply interference of the overlapping area, and improves the accuracy of local air supply. The air supply parameters of the independent area need to consider the influence of adjacent air fans to ensure the uniformity of air supply.

[0094] Step 106: For each air speed control area, the personnel density coefficient is determined according to the ratio of the number of personnel in the air speed control area to the area of the area, and the speed of the air fan corresponding to the air speed control area is adjusted based on the personnel density coefficient. The speed of the air fan and the personnel density coefficient are positively correlated.

[0095] Wherein, the air speed control area represents the space range of independent control of air supply parameters in the clean room; the number of personnel refers to the actual number of people detected in the area; the area of the area represents the horizontal projection area of the control area; the personnel density coefficient refers to the degree of personnel distribution density per unit area; the speed of the air fan represents the rotating speed of the impeller of the air supply device; the positive correlation represents the corresponding relationship of the same direction change of the two parameters.

[0096] Specifically, this step is executed after the clean room area is divided, and is used to realize accurate air supply control based on personnel distribution. For each air speed control area, first, the number of target matching pairs in the area is counted as the actual number of personnel N, the horizontal projection area S of the area is measured, and the personnel density coefficient p=N / S is calculated. The speed adjustment amount of the air fan is determined according to the calculated density coefficient, and the adjustment formula is: V=V0×(1+k×p), wherein V0 is the reference speed, and k is the adjustment coefficient. When the personnel density coefficient increases, the speed of the air fan increases, and the air supply amount increases; when the personnel density coefficient decreases, the speed of the air fan decreases, and the air supply amount decreases. This dynamic adjustment mechanism ensures that the air supply intensity matches the actual demand, which not only guarantees the dust removal effect but also avoids energy waste.

[0097] In some embodiments, the dynamic adjustment of the fan speed can be achieved in various ways: alternatively, a piecewise linear adjustment method can be used, in which the range of the personnel density coefficient is first divided into multiple intervals, then a corresponding reference speed and adjustment slope are set for each interval, then the real-time density coefficient is determined to belong to the interval, and finally the target speed is calculated according to the linear relationship in the interval; alternatively, a fuzzy control method can be used, in which the personnel density coefficient and the fan speed are first set to fuzzy levels, then a fuzzy rule base is established to define the mapping relationship between the two, then the real-time density coefficient is subjected to fuzzy reasoning to obtain the speed adjustment amount, and finally the specific speed value is obtained by performing defuzzification calculation. It can be understood that other control algorithms can also be used to achieve dynamic matching of the fan speed and the personnel density, which is not limited here.

[0098] On the basis of the above embodiments, as an optional embodiment, in step 106, the fan speed corresponding to the wind speed control area is adjusted based on the personnel density coefficient. This step can further include the following steps: Step 501: Calculate the ratio of the area of the wind speed control area to the rated air volume of the fan to obtain the reference air volume per unit area.

[0099] Wherein, the wind speed control area area represents the size of the space range that needs to be independently controlled; the fan rated air volume refers to the air volume flow rate of the fan under standard working conditions; the unit area reference air volume represents the air supply volume per square meter area obtained when the space is evenly distributed.

[0100] Specifically, the horizontal projection area S of the determined wind speed control area is measured, with the unit being square meters. The rated air volume parameter Q of the corresponding fan is read, with the unit being cubic meters per minute. The division operation q0=Q / S is performed to obtain the unit area reference air volume, with the unit being cubic meters per minute per square meter. This reference air volume represents the standard air volume value that each square meter area in the control area should obtain under uniform air supply conditions. For example, when the fan rated air volume is 100 cubic meters per minute and the control area area is 20 square meters, the unit area reference air volume is 5 cubic meters per minute per square meter. This reference value serves as a reference for subsequent air volume adjustment, ensuring that the air supply volume distribution meets the spatial scale requirements.

[0101] Step 502: Linearly weight the reference air volume according to the personnel density coefficient to obtain the target unit area air volume.

[0102] Wherein, the personnel density coefficient represents the personnel distribution density in the unit area; linear weighting refers to the calculation method of adjusting the reference air volume in proportion to the density coefficient; the target unit area air volume represents the actual air supply demand considering the personnel distribution.

[0103] Specifically, the air volume adjustment calculation is performed based on the personnel density coefficient ρ and the unit area reference air volume q0 calculated in the previous steps. A linear adjustment coefficient k is set, which represents the degree of influence of personnel density on air volume. A linear weighted calculation is performed: q=q0×(1+k×ρ), where q is the target unit area air volume. When the personnel density coefficient increases, the target air volume increases accordingly; when the personnel density coefficient decreases, the target air volume decreases accordingly. For example, when the reference air volume is 5 cubic meters per minute per square meter, the personnel density coefficient is 0.4, and the adjustment coefficient is 0.5, the calculated target air volume is 5×(1+0.5×0.4)=6 cubic meters per minute per square meter. This adjustment method ensures that the air supply volume matches the actual demand, ensuring dust removal effect and avoiding energy waste.

[0104] Step 503: Calculate the total air volume required based on the target unit area air volume and the total area of the air speed control region.

[0105] Where, the target unit area air volume represents the air supply demand per square meter of space considering personnel distribution; the total area of the air speed control region refers to the size of the space range that needs to be controlled independently; the required total air volume represents the volume flow that meets the air supply requirements of the entire control region.

[0106] Specifically, the total area of the air speed control region and the target unit area air volume are read. By multiplying the target unit area air volume and the total area of the control region, the total air volume required for the entire region is calculated, with the unit being m³ / min. This total air volume represents the actual air supply volume required for the entire control region under the current personnel distribution conditions. For example, when the control region area is 20 m² and the target unit area air volume is 6 m³ / (min·m²), the calculated required total air volume is 120 m³ / min. The calculation result of the total air volume directly determines the operating parameters of the fan, which is a key parameter for realizing precise air supply control.

[0107] Step 504: According to the reference characteristic curve of the fan, determine the target fan speed value corresponding to the total air volume; adjust the fan speed of the air speed control region to the target fan speed value.

[0108] Where, the reference characteristic curve represents the corresponding relationship between the speed and air volume of the fan under standard working conditions; the target fan speed value refers to the rotational speed of the fan impeller that meets the total air volume requirement; the fan speed adjustment represents the process of changing the fan operating parameters through frequency control.

[0109] Specifically, the reference characteristic curve data describing the correspondence between air volume and rotating speed is obtained from the fan parameter database. Based on the data points provided by the characteristic curve, the look-up table or interpolation method is used to determine the rotating speed value corresponding to the target air volume. For example, when the total air volume is 120m³ / min, the corresponding target rotating speed is 1095r / min obtained by looking up the characteristic curve. The determined target rotating speed value is sent to the fan frequency converter through the control instruction, and the frequency converter gradually adjusts the output frequency according to the received instruction, so that the rotating speed of the fan reaches the target value. The rotating speed adjustment based on the characteristic curve ensures that the fan can accurately output the required air volume.

[0110] With reference to Figure 2 An intelligent clean room control system is provided for the embodiments of the present application, and the system comprises a data acquisition module, a target matching pair determination module, a wind speed control area determination module, and a clean room control module, wherein: The data acquisition module is configured to collect thermal signal distribution data of personnel through an infrared sensor array arranged in the clean room, and collect pressure distribution data of personnel through a pressure sensor array arranged in the clean room. The infrared sensor array comprises a plurality of infrared sensors, and each infrared sensor is distributed on the top and side wall of the clean room according to a preset interval. The pressure sensor array comprises a plurality of pressure sensors, and each pressure sensor is distributed below the bottom plate of the clean room according to a preset grid shape. The target matching pair determination module is configured to perform signal intensity normalization processing on the thermal signal distribution data to obtain a normalized thermal signal matrix, wherein each element in the thermal signal matrix represents the thermal signal intensity value of the corresponding spatial position. The target matching pair determination module is further configured to perform gravity calculation on the pressure distribution data to determine the gravity coordinates of a plurality of pressure concentration areas, and perform spatial position matching between the thermal signal matrix and the gravity coordinates to obtain a plurality of matching pairs. The target matching pair determination module is further configured to calculate the Euclidean distance between the peak point of the thermal signal of each matching pair and the gravity coordinates, and screen out a target matching pair with an Euclidean distance less than a preset threshold. The wind speed control area determination module is configured to determine the actual number of personnel in the clean room based on the number of target matching pairs, and divide the clean room into a plurality of wind speed control areas according to the position information of the gravity coordinates in each target matching pair. The clean room control module is configured to determine a personnel density coefficient according to the ratio of the number of personnel in each wind speed control area to the area of the wind speed control area, and adjust the rotating speed of the fan corresponding to the wind speed control area based on the personnel density coefficient. The rotating speed of the fan is positively correlated with the personnel density coefficient.

[0111] On the basis of the above-mentioned embodiments, the target matching pair determination module is further configured to convert the pressure distribution data into a two-dimensional pressure matrix, wherein a matrix element value in the two-dimensional pressure matrix represents a pressure value at a corresponding position; perform segmentation processing on the two-dimensional pressure matrix by using a threshold segmentation algorithm to obtain a plurality of independent pressure signal clusters; extract a boundary contour of each pressure signal cluster and calculate a weighted average value of all pressure values in each boundary contour as a characteristic pressure value of the corresponding pressure signal cluster; when the characteristic pressure value is greater than a preset human body pressure threshold value, determine the corresponding pressure signal cluster as a pressure concentration area; and calculate a centroid of the pressure concentration area as a corresponding gravity center coordinate.

[0112] On the basis of the above-mentioned embodiments, the target matching pair determination module is further configured to construct a three-dimensional space coordinate system, wherein an X-axis and a Y-axis in the three-dimensional space coordinate system are parallel to a bottom plate of the clean room, and a Z-axis is perpendicular to the bottom plate of the clean room, and map the gravity center coordinates from a two-dimensional plane to the three-dimensional space coordinate system; detect an area with a heat signal intensity value greater than a preset heat signal threshold value in the heat signal matrix, and determine a three-dimensional coordinate corresponding to a heat signal peak point of the area; establish a spherical search space with each gravity center coordinate as a center, and a radius of the spherical search space is determined by a historical human body average height of the clean room; search for the three-dimensional coordinate corresponding to the heat signal peak point in each spherical search space, and when the heat signal peak point is searched, associate the searched heat signal peak point with a gravity center coordinate of the spherical search space to obtain a matching pair; and when there are a plurality of heat signal peak points in the spherical search space, select a heat signal peak point closest to a projection distance between the gravity center coordinate of the spherical search space to associate, to obtain a matching pair.

[0113] On the basis of the above-mentioned embodiments, the wind speed control area determination module is further configured to perform time sequence filtering on the target matching pair quantity to obtain a filtered matching pair quantity; obtain an access door control signal of the clean room, and determine a start time and an end time of the clean room according to the access door control signal; at each start time, take the filtered matching pair quantity as an initial personnel quantity in the clean room, and update the initial personnel quantity to a personnel counter; in a time period between two adjacent start times, when a sudden change of the filtered matching pair quantity is detected, update a value of the personnel counter based on a quantity difference before and after the sudden change; and at the end time, determine the value of the personnel counter as an actual personnel quantity of the clean room.

[0114] On the basis of the above-mentioned embodiments, the wind speed control area determination module is further configured to acquire fan layout information of the clean room, the fan layout information comprising installation positions of each fan and air supply coverage ranges of the fans; map the gravity center coordinates of the target matching pair to the air supply coverage ranges of the fans based on the installation positions of the fans; count the number of gravity center coordinates in the air supply coverage ranges of the fans, and divide the air supply coverage ranges of the fans into corresponding wind speed control areas based on the number of gravity center coordinates; and when the air supply coverage ranges of adjacent fans have an overlapping area and the number of gravity center coordinates in the overlapping area is greater than a preset overlap threshold, divide the overlapping area into independent wind speed control areas.

[0115] On the basis of the above-mentioned embodiments, the wind speed control area determination module is further configured to construct a heat map of the air supply coverage ranges of the fans, a pixel value of the heat map being determined by the number of gravity center coordinates at a corresponding position; perform region growing segmentation processing on the heat map, taking the gravity center coordinate positions as seed points, and within a preset growth threshold range, merge adjacent regions with an absolute value of a difference between pixel values less than a preset pixel threshold into the same segmented region; calculate the total number of gravity center coordinates in each segmented region, and mark a segmented region with a total number of gravity center coordinates greater than a preset number threshold as a candidate wind speed control area; and match the candidate wind speed control area with the air supply coverage ranges of the fans, and when the coincidence degree of the candidate wind speed control area with the air supply coverage range of any one of the fans is greater than a preset proportion, determine the candidate wind speed control area as the wind speed control area corresponding to the fan.

[0116] On the basis of the above-mentioned embodiments, the clean room control module is further configured to calculate a ratio of the area of the wind speed control area to the rated air volume of the fan, to obtain a reference air volume per unit area; linearly weight the reference air volume according to the personnel density coefficient, to obtain a target air volume per unit area; calculate a total air volume required based on the target air volume per unit area and the total area of the wind speed control area; determine a target fan rotation speed value corresponding to the total air volume according to the reference characteristic curve of the fan; and adjust the fan rotation speed corresponding to the wind speed control area to the target fan rotation speed value.

[0117] It should be noted that the apparatus provided in the above-mentioned embodiments is only taken as an example for the division of the functional modules, and in actual applications, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above-mentioned embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0118] The present application also discloses an electronic device. Referring to Figure 3 , Figure 3is a structural schematic diagram of an electronic device disclosed by an embodiment of the present application. The electronic device 300 can include at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0119] The communication bus 302 is configured to realize connection and communication between the components.

[0120] The user interface 303 can include a display interface and a camera interface. Optionally, the user interface 303 can further include a standard wired interface and a wireless interface.

[0121] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface).

[0122] The processor 301 can include one or more processing cores. The processor 301 is connected to various parts of the server through various interfaces and lines, and performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process an operating system, a user interface graph, and an application program; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be implemented by a separate chip.

[0123] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for an intelligent cleanroom control method.

[0124] exist Figure 3 In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and acquire user input data; while the processor 301 can be used to call an application program of an intelligent cleanroom control method stored in the memory 305. When executed by one or more processors 301, the electronic device 300 performs one or more methods as described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0125] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0126] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments is merely illustrative, and the division of units can be changed according to actual conditions, such as a combination or integration of some units, or a deletion of some features, or an addition of some features. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0127] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0128] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0129] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the methods in the embodiments. The aforementioned storage medium includes: U disk, mobile hard disk, magnetic disk or optical disk, and various program codes that can be stored.

[0130] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the disclosure.

[0131] The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional techniques in the technical field not described in the present disclosure. The specification and examples are only considered as exemplary.

Claims

1. A method for controlling an intelligent cleanroom, characterized in that, include: Thermal signal distribution data of personnel is collected by an infrared sensor array installed in the clean room, and pressure distribution data of personnel is collected by a pressure sensor array installed in the clean room. The infrared sensor array includes multiple infrared sensors, which are distributed at a preset interval on the top and side walls of the clean room. The pressure sensor array includes multiple pressure sensors, which are distributed in a preset grid pattern below the bottom plate of the clean room. The thermal signal distribution data is subjected to signal intensity normalization processing to obtain a normalized thermal signal matrix, where each element in the thermal signal matrix represents the thermal signal intensity value at the corresponding spatial location. The centroid of the pressure distribution data is calculated to determine the centroid coordinates of multiple pressure concentration areas; The thermal signal matrix is ​​spatially matched with each of the centroid coordinates to obtain multiple matching pairs. The Euclidean distance between the thermal signal peak point and the centroid coordinate of each matching pair is calculated, and target matching pairs with an Euclidean distance less than a preset threshold are selected. The actual number of people in the clean room is determined based on the number of target matching pairs, and the clean room is divided into multiple wind speed control zones according to the position information of the centroid coordinates of each target matching pair. For each wind speed control zone, a personnel density coefficient is determined based on the ratio of the number of people in the wind speed control zone to the area of ​​the zone, and the fan speed corresponding to the wind speed control zone is adjusted based on the personnel density coefficient. The fan speed is positively correlated with the personnel density coefficient.

2. The intelligent cleanroom control method according to claim 1, characterized in that, The step of calculating the centroid of the pressure distribution data to determine the centroid coordinates of multiple pressure concentration areas includes: The pressure distribution data is converted into a two-dimensional pressure matrix, where the matrix element values ​​represent the pressure values ​​at the corresponding locations. The two-dimensional pressure matrix is ​​segmented using a threshold segmentation algorithm to obtain multiple independent pressure signal clusters; Extract the boundary contours of each pressure signal cluster, and calculate the weighted average of all pressure values ​​within each boundary contour as the characteristic pressure value of the corresponding pressure signal cluster. When the characteristic pressure value is greater than the preset human body pressure threshold, the corresponding pressure signal cluster is identified as a pressure concentration area. The centroid of the pressure concentration region is calculated as the corresponding centroid coordinates.

3. The intelligent cleanroom control method according to claim 1, characterized in that, The step of spatially matching the thermal signal matrix with each of the centroid coordinates to obtain multiple matching pairs includes: A three-dimensional spatial coordinate system is constructed, in which the plane containing the X-axis and Y-axis is parallel to the bottom plate of the cleanroom, and the Z-axis is perpendicular to the bottom plate of the cleanroom. The centroid coordinates are then mapped from the two-dimensional plane to the three-dimensional spatial coordinate system. In the thermal signal matrix, regions where the thermal signal intensity value is greater than a preset thermal signal threshold are detected, and the three-dimensional coordinates corresponding to the thermal signal peak point in the region are determined; A spherical search space is established with each of the aforementioned center-of-gravity coordinates as the center, and the radius of the spherical search space is determined by the historical average height of human bodies in the cleanroom; Search for the three-dimensional coordinates corresponding to the peak point of the thermal signal in each spherical search space. When the peak point of the thermal signal is found, associate the found peak point of the thermal signal with the centroid coordinates of the spherical search space to obtain a matching pair. When there are multiple thermal signal peak points within the spherical search space, the thermal signal peak point with the closest projected distance to the centroid coordinates of the spherical search space is selected and associated to obtain a matching pair.

4. The intelligent cleanroom control method according to claim 1, characterized in that, Determining the actual number of people in the cleanroom based on the number of target matching pairs includes: The target number of matching pairs is subjected to time-series filtering to obtain the filtered number of matching pairs. The entry and exit control signals of the cleanroom are acquired, and the start and end times of the cleanroom are determined based on the entry and exit control signals. At each startup time, the number of filtered matching pairs is used as the initial number of personnel in the cleanroom, and the initial number of personnel is updated to the personnel counter; During the time interval between two adjacent start times, when a sudden change in the number of filtered matching pairs is detected, the value of the personnel counter is updated based on the difference in the number before and after the change. At the end time, the value of the personnel counter is determined as the actual number of personnel in the cleanroom.

5. The intelligent cleanroom control method according to claim 1, characterized in that, The step of dividing the cleanroom into multiple wind speed control zones based on the position information of the centroid coordinates of each target matching pair includes: Obtain the fan layout information of the cleanroom, which includes the installation location and air supply coverage of each fan; Based on the installation location of each of the wind turbines, the centroid coordinates of the target matching pair are mapped to the air supply coverage area of ​​each of the wind turbines; The number of centroid coordinates within the air supply coverage area of ​​each fan is counted, and the air supply coverage area of ​​each fan is divided into corresponding wind speed control zones based on the number of centroid coordinates. When the air supply coverage of adjacent fans overlaps, and the number of centroid coordinates in the overlapping area is greater than a preset overlap threshold, the overlapping area is divided into an independent wind speed control area.

6. The intelligent cleanroom control method according to claim 5, characterized in that, The method of dividing the air supply coverage area of ​​each fan into corresponding wind speed control zones based on the number of centroid coordinates includes: A heat map of the air supply coverage area of ​​the fan is constructed, wherein the pixel value of the heat map is determined by the number of centroid coordinates at the corresponding location; The heatmap is subjected to region growth segmentation processing. Using the centroid coordinate position as the seed point, within the preset growth threshold range, adjacent regions whose absolute value of the difference in pixel values ​​is less than the preset pixel threshold are merged into the same segmented region. Calculate the total number of centroid coordinates in each segmented region, and mark the segmented regions whose total number of centroid coordinates is greater than a preset number of people threshold as candidate wind speed control regions; The candidate wind speed control area is matched with the air supply coverage of the fan. When the overlap between the candidate wind speed control area and the air supply coverage of any fan is greater than a preset ratio, the candidate wind speed control area is determined to be the wind speed control area corresponding to the fan.

7. The intelligent cleanroom control method according to claim 1, characterized in that, The adjustment of the fan speed corresponding to the wind speed control area based on the personnel density coefficient includes: Calculate the ratio of the area of ​​the wind speed control zone to the rated air volume of the fan to obtain the reference air volume per unit area; The target air volume per unit area is obtained by linearly weighting the baseline air volume based on the personnel density coefficient. The total required air volume is calculated based on the target air volume per unit area and the total area of ​​the wind speed control zone. Based on the reference characteristic curve of the fan, determine the target fan speed value corresponding to the total air volume; Adjust the fan speed corresponding to the wind speed control area to the target fan speed value.

8. An intelligent cleanroom control system, characterized in that, The system includes: The data acquisition module is used to collect thermal signal distribution data of personnel through an infrared sensor array set in the clean room, and to collect pressure distribution data of personnel through a pressure sensor array set in the clean room. The infrared sensor array includes multiple infrared sensors, which are distributed at a preset interval on the top and side walls of the clean room. The pressure sensor array includes multiple pressure sensors, which are distributed in a preset grid pattern below the bottom plate of the clean room. The target matching pair determination module is used to perform signal intensity normalization processing on the thermal signal distribution data to obtain a normalized thermal signal matrix, where each element in the thermal signal matrix represents the thermal signal intensity value at a corresponding spatial location; to perform centroid calculation on the pressure distribution data to determine the centroid coordinates of multiple pressure concentration areas; to perform spatial location matching between the thermal signal matrix and each of the centroid coordinates to obtain multiple matching pairs; and to calculate the Euclidean distance between the thermal signal peak point and the centroid coordinates of each matching pair, and to filter out target matching pairs whose Euclidean distance is less than a preset threshold. The wind speed control zone determination module is used to determine the actual number of people in the clean room based on the number of target matching pairs, and to divide the clean room into multiple wind speed control zones according to the position information of the centroid coordinates of each target matching pair. The cleanroom control module is used to determine the personnel density coefficient for each wind speed control zone based on the ratio of the number of personnel in the wind speed control zone to the area of ​​the zone, and to adjust the fan speed corresponding to the wind speed control zone based on the personnel density coefficient. The fan speed is positively correlated with the personnel density coefficient.

9. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the intelligent cleanroom control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the intelligent cleanroom control method as described in any one of claims 1-7.

Images