An intelligent management system for cleanroom garments equipped with iris recognition technology

By using iris recognition technology and a contamination level identification model, the problem of unreasonable cleaning cycles for cleanroom garments has been solved, enabling intelligent management of cleanroom garments and ensuring the continuity of the clean environment.

CN120355150BActive Publication Date: 2026-03-06HANYANG CLEAN (JIANGSU) TECHNOLOGY CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510430153.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-04-08
Publication Date
2026-03-06
Estimated Expiration
2045-04-08

AI Technical Summary

Technical Problem

The current cleaning cycle for cleanroom garments does not take into account the impact of staff behavior, leading to unclear assessment of the degree of contamination, untimely cleaning, and pollution of the clean environment.

Method used

By employing iris recognition technology, and through modules for area division, environmental monitoring, personnel tracking, external pollution identification, internal pollution identification, and intelligent management, a pollution level identification model is constructed. This allows for adjustments to iris permissions and access control systems, thereby enabling intelligent management of cleanroom garments.

Benefits of technology

Accurately identify the contamination level of cleanroom garments, prevent contaminants from entering the clean area, improve the level of intelligence in cleanroom garment management, and ensure the continuity of the clean environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120355150B_ABST
    Figure CN120355150B_ABST
Patent Text Reader

Abstract

This invention relates to the field of intelligent management technology for cleanroom garments, specifically an intelligent management system for cleanroom garments equipped with iris recognition technology. The system divides the work area into sub-areas based on cleanliness levels, establishes iris access control systems between these sub-areas, and monitors environmental parameters of each sub-area using sensors. It tracks workers wearing cleanroom garments in real time, obtaining work trajectory data and work status data. Based on the work trajectory data, it obtains trajectory environmental parameters; by identifying these parameters and data, it obtains external contamination data; by identifying the work status data, it obtains internal contamination data; and based on the external and internal contamination data, it determines the contamination level of the worker's cleanroom garment. This invention achieves intelligent management of cleanroom garments by identifying contamination data from the worker's cleanroom garments, adjusting iris access permissions based on cleanliness and contamination levels, and adjusting the activity range based on iris access permissions and the iris access control system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for cleanroom garments, specifically to an intelligent management system for cleanroom garments equipped with iris recognition technology. Background Technology

[0002] Cleanroom garments are protective suits specifically designed for clean environments. They are typically used in work environments requiring high cleanliness, such as electronics manufacturing, pharmaceuticals, food processing, biological laboratories, semiconductor production, and medical device manufacturing. Their main function is to prevent contaminants such as particles, dander, sweat, and grease from the wearer's body from entering the cleanroom area, while also preventing contaminants from the external environment from entering the clean area.

[0003] The cleaning cycle is a key factor in ensuring a clean environment during the use of cleanroom garments. Current technologies primarily determine the cleaning cycle based on the cleanliness level of the work environment, the material of the garment, and the type of work. However, most cleaning cycles are fixed durations and do not consider the impact of the behavior of the staff wearing the garments. This leads to unclear assessments of the degree of contamination in the garments and unreasonable cleaning cycle settings. There are instances where heavily contaminated garments are used despite delayed cleaning, resulting in contaminated garments negatively impacting the environment.

[0004] To address this, an intelligent management system for cleanroom garments with iris recognition technology is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent management system for cleanroom garments equipped with iris recognition technology. By identifying the contamination data of the cleanroom garments of staff, the contamination level is obtained; iris permissions are adjusted according to the cleanliness level and the contamination level; and the activity range is adjusted according to the iris permissions and the iris access control system, thereby realizing intelligent management of the cleanroom garments.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent management system for cleanroom garments equipped with iris recognition technology, comprising:

[0007] The area division module divides the work area into sub-areas based on the cleanliness level; an iris recognition access control system is then installed between these sub-areas.

[0008] The environmental monitoring module uses sensors to monitor the environmental parameters of the working sub-area in real time and obtain the environmental parameters of the sub-area.

[0009] The personnel tracking module tracks staff wearing cleanroom suits in real time, obtaining work trajectory data and work status data. The work trajectory data includes stationary trajectory data and movement trajectory data. The work status data includes sweating data, heart rate data, breathing data, and movement data.

[0010] The external pollution identification module identifies the distance between the worker and the sensor based on the work trajectory data, identifies the environmental parameters of the sub-area of ​​different sensors based on the distance, and obtains the trajectory environmental parameters; it constructs an external pollution identification model to identify the trajectory environmental parameters and work trajectory data, and obtains external pollution data.

[0011] The internal contamination identification module acquires the work status data of the staff, builds an internal contamination identification model to identify the work status data, and obtains internal contamination data.

[0012] The pollution level identification module identifies the pollution level of the staff's cleanroom clothing by using a pollution level identification model to identify external and internal pollution data.

[0013] The intelligent management module identifies the pollution level based on the cleanliness level of the work sub-area, adjusts the iris access permissions of staff based on the identification results, and adjusts the activity range of staff based on iris access permissions and the iris access control system.

[0014] The cleanliness level is determined based on the cleanliness parameters required for production activities in the work sub-area;

[0015] The cleaning parameters include standard suspended particle size data and standard suspended particle concentration data, with different cleaning parameters corresponding to different cleaning levels.

[0016] The iris access control system includes an access control system that identifies users based on their irises, and its workflow includes:

[0017] The system obtains the staff's identity information through iris recognition, confirms the staff's iris access rights based on the identity information, and determines whether to open the access control for the staff based on the iris access rights.

[0018] The environmental parameters of the sub-region are the environmental parameters within the working sub-region, including suspended particle size data, suspended particle concentration data, temperature data, humidity data, and wind speed data; these are acquired through monitoring by sensors installed within the working sub-region.

[0019] The sensor is set up as follows: the spatial structure of the working sub-region is identified; based on the spatial structure of the working sub-region, historical trajectory data of all staff members are collected; the historical trajectory data of all staff members are clustered and identified using a clustering algorithm to obtain dense activity distribution data; and the sensor placement location is determined based on the dense activity distribution data.

[0020] The process of acquiring the action data is as follows:

[0021] The work process of the staff in the work sub-area is monitored by a camera device to obtain a work video set; the work video set is divided according to the staff's actions to obtain work video subsets;

[0022] The images in the work video subset are identified frame by frame, and the motion amplitude is obtained through the motion characteristics of the staff; motion data is obtained based on the motion amplitude of the entire work video subset.

[0023] The trajectory environment parameters include stationary trajectory environment parameters and motion trajectory environment parameters;

[0024] The method for obtaining the stationary trajectory environmental parameters is as follows: acquiring the stationary trajectory data of the exerciser, wherein the stationary trajectory data is the trajectory data of the worker stationed in a fixed position area, including the stationary position and stationary duration; selecting the sub-region environmental parameters of the sensor with the smallest distance from the stationary position as the stationary trajectory environmental parameters;

[0025] The method for obtaining the motion trajectory environmental parameters is as follows: acquiring the motion trajectory data of the worker, which is the movement data of the worker in the work sub-area, including the motion trajectory and movement speed; determining the sensor with the smallest distance from the worker as the reference sensor based on the motion trajectory; dividing the motion trajectory according to the reference sensor to obtain the motion sub-trajectory; each motion sub-trajectory corresponds to a reference sensor; and obtaining the motion trajectory environmental parameters based on the sub-area environmental parameters of the reference sensor.

[0026] The external contamination identification model includes a data input layer, a data processing layer, an external contamination identification layer, and a data output layer;

[0027] The data input layer is used to acquire trajectory environment parameters and working trajectory data;

[0028] The data processing layer identifies the stationary trajectory data of the working trajectory data and the stationary trajectory environment parameters of the trajectory environment parameters to obtain first identification data; it also identifies the motion trajectory data of the working trajectory data and the motion trajectory environment parameters of the trajectory environment parameters to obtain second identification data.

[0029] The external pollution identification layer identifies first pollution data based on first identification data and second pollution data based on second identification data; it also obtains external pollution data based on the first pollution data and the second pollution data.

[0030] The data output layer is used to output external pollution data.

[0031] The process of obtaining the internal contamination identification model is as follows:

[0032] Internal contamination tests were conducted on personnel wearing cleanroom suits to obtain an internal contamination test set.

[0033] The internal contamination test set includes sweating data, heart rate data, respiratory data, and movement data of the test personnel during the test; the sweating data, heart rate data, and respiratory data are acquired by monitoring the test personnel through sensors; the movement data includes the range of motion of the personnel during the test.

[0034] The internal surface contamination data of the cleanroom garments worn by the test personnel is detected to obtain test contamination data; the initial model is trained based on the internal contamination test set and the test contamination data to obtain the internal contamination identification model.

[0035] The process of obtaining the pollution level identification model is as follows:

[0036] Obtain the initial environmental parameters and cleanliness level of the work sub-area;

[0037] A time threshold is set, and staff wearing test cleanroom suits are selected to work in the work sub-area based on the time threshold; the test cleanroom suits have different external and internal contamination data.

[0038] After the working duration threshold is reached, the termination environment parameters of the working sub-region are obtained;

[0039] The pollution coefficient of the working sub-area environment is determined based on the initial and final environmental parameters; the pollution level of the test cleanroom garment is determined based on the pollution coefficient and the cleanliness level, and a pollution level recognition model is trained.

[0040] The process for adjusting staff iris recognition permissions based on cleanliness and contamination levels is as follows:

[0041] Based on the pollution level and the cleanliness level of the work sub-area, determine whether the staff will cause pollution to the work sub-area;

[0042] If it will not cause pollution, then enable iris access for staff to enter the work sub-area, allowing staff to access the iris access control system to the work sub-area;

[0043] If contamination is likely to occur, iris access to the work area will be disabled, preventing staff from activating the iris access control system to that work area. If a staff member is already in the work area, a deportation warning will be issued, and the corresponding cleanroom garment will be marked.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0045] 1. Based on the spatial structure of the work sub-area, this invention collects historical trajectory data of all staff members in the work sub-area; then, it uses a clustering algorithm to cluster and identify the historical trajectory data to obtain the dense distribution data of staff activity; and finally, it determines the sensor placement location based on the dense distribution data of activity, thereby accurately monitoring the environmental parameters at the staff trajectory location and providing a data basis for the contamination measurement of cleanroom garments.

[0046] 2. Based on the movement characteristics of the workers, this invention divides the workers' work trajectory data into stationary trajectory data and movement trajectory data; based on the stationary position in the stationary trajectory data, the environmental parameters of the sub-region of the sensor with the smallest distance are determined as the stationary trajectory environmental parameters; based on the movement trajectory in the movement trajectory data, multiple closest sensors are determined as reference sensors, and the movement trajectory environmental parameters are obtained based on the monitoring data of the reference sensors; through the stationary trajectory environmental parameters and the movement trajectory environmental parameters, the trajectory environmental parameters of the workers are accurately identified.

[0047] 3. This invention constructs an external pollution identification model to identify trajectory environmental parameters and working trajectory data. Based on the stationary trajectory data of the working trajectory data and the stationary trajectory environmental parameters of the trajectory environmental parameters, first identification data is obtained; based on the motion trajectory data of the working trajectory data and the motion trajectory environmental parameters of the trajectory environmental parameters, second identification data is obtained; first pollution data is obtained based on the first identification data, and second pollution data is obtained based on the second identification data; external pollution data can be accurately identified based on the first pollution data and the second pollution data.

[0048] 4. The invention selects test personnel to conduct internal contamination tests. Based on the test personnel's sweating data, heart rate data, breathing data, and movement data, an internal contamination test set is obtained. Test contamination data is obtained by detecting contamination data on the inner surface of cleanroom garments. An internal contamination identification model is trained based on the internal contamination test set and test contamination data. The internal contamination identification model can accurately identify internal contamination data based on the work status data of the staff.

[0049] 5. This invention selects workers wearing test cleanroom suits to work in a sub-area based on a time threshold; determines the pollution coefficient of the work sub-area environment based on the initial and final environmental parameters before and after work; determines the pollution level of the test cleanroom suit based on the pollution coefficient and cleanliness level, and trains a pollution level identification model; the pollution level identification model can accurately identify the pollution level based on the external and internal pollution data of the cleanroom suit.

[0050] 6. This invention divides the work area into multiple sub-areas and sets up an iris access control system between the sub-areas; it identifies the contamination level based on the contamination data of the staff's cleanroom garments; it adjusts the staff's iris permissions according to the contamination level and the cleanliness level of the sub-areas. Through iris permissions and the iris access control system, the activity range of the staff's cleanroom garments can be effectively managed intelligently, avoiding contamination of the work sub-areas by contaminated cleanroom garments. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the structure of an intelligent management system for cleanroom garments equipped with iris recognition technology according to the present invention;

[0052] Figure 2 This is a schematic diagram of the external contamination identification model of the present invention;

[0053] Figure 3 This is a schematic diagram of the working area division of the present invention;

[0054] Figure 4 This is a schematic diagram of the motion trajectory reference sensor determination method of the present invention.

[0055] In the diagram: 11. First working sub-area; 12. Second working sub-area; 13. Third working sub-area; 14. Fourth working sub-area; 15. Iris recognition access control system; 21. First sensor; 22. Second sensor; 23. Third sensor; 24. Fourth sensor; 31. Initial position; 32. Transfer position; 33. Termination position; 41. First dividing point; 42. Second dividing point. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Example 1

[0058] This invention proposes an intelligent management system for cleanroom garments equipped with iris recognition technology. The structure of the system is as follows: Figure 1 As shown, it includes: a regional division module, an environmental monitoring module, a personnel tracking module, an external pollution identification module, an internal pollution identification module, a level identification module, and an intelligent management module.

[0059] The area division module divides the work area into sub-areas based on the cleanliness level; an iris access control system is then installed between these sub-areas.

[0060] The cleanliness level is determined based on the cleanliness parameters required for production activities in the work sub-area;

[0061] The cleaning parameters include standard suspended particle size data and standard suspended particle concentration data, with different cleaning parameters corresponding to different cleaning levels.

[0062] The iris access control system includes an access control system that identifies users based on their irises, and its workflow includes:

[0063] The system obtains the staff's identity information through iris recognition, confirms the staff's iris access rights based on the identity information, and determines whether to open the access control for the staff based on the iris access rights.

[0064] The environmental monitoring module uses sensors to monitor the environmental parameters of the working sub-area in real time, thereby obtaining the environmental parameters of the sub-area.

[0065] The sub-region environmental parameters are the environmental parameters within the working sub-region, including suspended particle size data, suspended particle concentration data, temperature data, humidity data, and wind speed data; these are acquired by monitoring with sensors installed within the working sub-region.

[0066] The sensor is configured as follows: the spatial structure of the work sub-area is identified; historical trajectory data of all staff are collected; the historical trajectory data of all staff are clustered using a clustering algorithm to obtain dense activity distribution data; the sensor's location is determined based on the dense activity distribution data; the sensor has Internet of Things (IoT) functionality.

[0067] This invention collects historical trajectory data of all staff members in the work sub-area based on the spatial structure of the work sub-area; it then uses a clustering algorithm to cluster and identify the historical trajectory data to obtain dense distribution data of staff activity; and finally determines the sensor placement location based on the dense distribution data of activity, thereby accurately monitoring the environmental parameters at the staff's trajectory location and providing a data basis for the contamination measurement of cleanroom garments.

[0068] The personnel tracking module tracks staff wearing cleanroom suits in real time, obtaining work trajectory data and work status data. The work trajectory data includes stationary trajectory data and movement trajectory data. The work status data includes sweating data, heart rate data, breathing data, and motion data.

[0069] The sweating data, heart rate data, and respiratory data are acquired by monitoring the test personnel through sensors; the motion data includes the range of motion of the personnel during the test.

[0070] The process of acquiring the action data is as follows:

[0071] The work process of the staff in the work sub-area is monitored by a camera device to obtain a work video set; the work video set is divided according to the staff's actions to obtain work video subsets;

[0072] The images in the work video subset are identified frame by frame using a convolutional neural network model, and the motion amplitude is obtained from the motion characteristics of the workers; motion data is obtained from the motion amplitude of the entire work video subset.

[0073] This invention monitors the work process of workers in a work sub-area using a camera device to obtain a work video set; identifies and divides the actions in the work video set to obtain work video subsets; identifies the images in the work video subsets frame by frame to obtain the action amplitude through the action characteristics of the workers; obtains action data based on the action amplitude of all work video subsets; and accurately identifies and measures the actions of the workers.

[0074] The external pollution identification module identifies the distance between the worker and the sensor based on the work trajectory data, and identifies the environmental parameters of the sub-area of ​​different IoT sensors based on the distance to obtain the trajectory environmental parameters; it constructs an external pollution identification model to identify the trajectory environmental parameters and work trajectory data to obtain external pollution data.

[0075] The trajectory environment parameters include stationary trajectory environment parameters and motion trajectory environment parameters;

[0076] The method for obtaining the stationary trajectory environmental parameters is as follows: acquiring the stationary trajectory data of the exerciser, wherein the stationary trajectory data is the trajectory data of the worker stationed in a fixed position area, including the stationary position and stationary duration; selecting the sub-region environmental parameters of the sensor with the smallest distance from the stationary position as the stationary trajectory environmental parameters;

[0077] The method for obtaining the motion trajectory environmental parameters is as follows: acquiring the motion trajectory data of the worker, which is the movement data of the worker in the work sub-area, including the motion trajectory and movement speed; determining the sensor with the smallest distance from the worker as the reference sensor based on the motion trajectory; dividing the motion trajectory according to the reference sensor to obtain the motion sub-trajectory; each motion sub-trajectory corresponds to a reference sensor; and obtaining the motion trajectory environmental parameters based on the sub-area environmental parameters of the reference sensor.

[0078] This invention divides the worker's work trajectory data into stationary trajectory data and motion trajectory data based on the worker's movement characteristics. Based on the stationary position in the stationary trajectory data, the environmental parameters of the sub-region of the sensor with the smallest distance are determined as the stationary trajectory environmental parameters. Based on the motion trajectory in the motion trajectory data, multiple closest sensors are determined as reference sensors, and the motion trajectory environmental parameters are obtained based on the monitoring data of the reference sensors. Through the stationary trajectory environmental parameters and the motion trajectory environmental parameters, the worker's trajectory environmental parameters are accurately identified.

[0079] The external contamination identification model is built based on a deep neural network model, and its structure is as follows: Figure 2 As shown; it includes a data input layer, a data processing layer, an external contamination identification layer, and a data output layer;

[0080] The data input layer is used to acquire trajectory environment parameters and working trajectory data;

[0081] The data processing layer identifies the stationary trajectory data of the working trajectory data and the stationary trajectory environment parameters of the trajectory environment parameters to obtain first identification data; it also identifies the motion trajectory data of the working trajectory data and the motion trajectory environment parameters of the trajectory environment parameters to obtain second identification data.

[0082] The external pollution identification layer identifies first pollution data based on first identification data and second pollution data based on second identification data; it also obtains external pollution data based on the first pollution data and the second pollution data.

[0083] The data output layer is used to output external pollution data.

[0084] This invention constructs an external contamination identification model to identify trajectory environmental parameters and work trajectory data. Based on the dwell trajectory data of the work trajectory data and the dwell trajectory environmental parameters of the trajectory environmental parameters, first identification data is obtained; based on the movement trajectory data of the work trajectory data and the movement trajectory environmental parameters of the trajectory environmental parameters, second identification data is obtained; first contamination data is obtained based on the first identification data, and second contamination data is obtained based on the second identification data; based on the first contamination data and the second contamination data, the external contamination data of the cleanroom garment can be accurately identified.

[0085] The internal contamination identification module acquires the work status data of the staff, builds an internal contamination identification model to identify the work status data, and obtains internal contamination data.

[0086] The internal contamination identification model is built based on a deep neural network model, and its acquisition process is as follows:

[0087] Internal contamination tests were conducted on personnel wearing cleanroom suits to obtain an internal contamination test set.

[0088] The internal contamination test set includes sweating data, heart rate data, respiratory data, and movement data of the test personnel during the test; the sweating data, heart rate data, and respiratory data are acquired by monitoring the test personnel through sensors; the movement data includes the range of motion of the personnel during the test.

[0089] The internal surface contamination data of the cleanroom garments worn by the test personnel is detected to obtain test contamination data; the initial model is trained based on the internal contamination test set and the test contamination data to obtain the internal contamination identification model.

[0090] This invention selects test personnel to conduct internal contamination tests. Based on the test personnel's sweating data, heart rate data, breathing data, and movement data, an internal contamination test set is obtained. Test contamination data is obtained by detecting contamination data on the inner surface of cleanroom garments. An internal contamination identification model is trained based on the internal contamination test set and test contamination data. The internal contamination identification model can accurately identify internal contamination data based on the work status data of the staff.

[0091] The pollution level identification module uses a pollution level identification model to identify external and internal pollution data to determine the pollution level of staff.

[0092] The pollution level identification model is built based on a deep neural network model, and its acquisition process is as follows:

[0093] Obtain the initial environmental parameters and cleanliness level of the work sub-area;

[0094] A time threshold is set, and staff wearing test cleanroom suits are selected to work in the work sub-area based on the time threshold; the test cleanroom suits have different external and internal contamination data.

[0095] After the working duration threshold is reached, the termination environment parameters of the working sub-region are obtained;

[0096] The pollution coefficient of the working sub-area environment is determined based on the initial and final environmental parameters; the pollution level of the test cleanroom garment is determined based on the pollution coefficient and the cleanliness level, and a pollution level recognition model is trained.

[0097] This invention selects workers wearing test cleanroom suits to work in a sub-area based on a time threshold; determines the pollution coefficient of the work sub-area environment based on the initial and final environmental parameters before and after work; determines the pollution level of the test cleanroom suit based on the pollution coefficient and cleanliness level, and trains a pollution level identification model; the pollution level identification model can accurately identify the pollution level based on the external and internal pollution data of the cleanroom suit.

[0098] The intelligent management module identifies the pollution level based on the cleanliness level of the work sub-area, adjusts the iris access permissions of staff based on the identification results, and adjusts the activity range of staff based on iris access permissions and the iris access control system.

[0099] Based on the pollution level and the cleanliness level of the work sub-area, determine whether the staff will cause pollution to the work sub-area;

[0100] If it will not cause pollution, then enable iris access for staff to enter the work sub-area, allowing staff to access the iris access control system to the work sub-area;

[0101] If contamination is likely to occur, iris access to the work area will be disabled, preventing staff from activating the iris access control system to that work area. If a staff member is already in the work area, a deportation warning will be issued, and the corresponding cleanroom garment will be marked.

[0102] This invention divides the work area into multiple sub-areas and sets up an iris access control system between them. Based on the contamination data of the staff's cleanroom garments, the contamination level is identified. The staff's iris access permissions are adjusted according to the contamination level and the cleanliness level of the work sub-areas. Through iris access permissions and the iris access control system, the activity range of the staff's cleanroom garments can be effectively managed, preventing contaminated cleanroom garments from contaminating the work sub-areas.

[0103] This invention divides the work area into sub-areas based on cleanliness levels, and sets up an iris recognition access control system between these sub-areas. Environmental parameters of each sub-area are monitored by sensors. Workers wearing cleanroom suits are tracked in real time, obtaining work trajectory data and work status data. Trajectory environmental parameters are derived from the work trajectory data. External contamination data is obtained by identifying these parameters and the work trajectory data. Internal contamination data is obtained by identifying the work status data. The contamination level of the worker's cleanroom suit is determined based on both the external and internal contamination data. Iris recognition permissions are adjusted according to the cleanliness and contamination levels, and the activity range is adjusted based on these permissions and the iris access control system, thus achieving intelligent management of the cleanroom suits.

[0104] Example 2

[0105] Work area P requires a high level of cleanliness for its production activities. Cleanroom garments are used to prevent contamination and ensure production quality. However, in actual production, the degree of contamination of the cleanroom garments is often unclear, leading to errors in the cleaning cycle settings. This frequently results in over-contaminated cleanroom garments continuing to be used.

[0106] Therefore, work area P adopts the intelligent management system for cleanroom garments with iris recognition technology described in this invention to intelligently manage the cleanroom garments.

[0107] The structure of the system is as follows Figure 1 As shown, it includes: a regional division module, an environmental monitoring module, a personnel tracking module, an external pollution identification module, an internal pollution identification module, a level identification module, and an intelligent management module.

[0108] The area division module divides the work area into sub-areas based on the cleanliness level; an iris recognition access control system is then installed between these sub-areas.

[0109] The cleanliness level is determined based on the cleanliness parameters required for production activities in the work sub-area;

[0110] The cleaning parameters include suspended particle size data and suspended particle concentration data; different cleaning levels correspond to different cleaning parameters.

[0111] The cleanliness level and corresponding cleanliness parameters for work area P are determined according to Chinese GMP standards, as shown in Table 1.

[0112] Table 1 Cleaning Parameters for Cleanliness Level P in the Work Area

[0113]

[0114] The iris access control system includes an access control system that identifies users based on their irises, and its workflow includes:

[0115] The system obtains the staff's identity information through iris recognition, confirms the staff's iris access rights based on the identity information, and determines whether to open the access control for the staff based on the iris access rights.

[0116] Subsequently, work area P is divided into zones based on the cleanliness requirements of different production activities within the work area, and an iris access control system is installed between the divided sub-zones, such as... Figure 3As shown, the area is divided into four working sub-areas: the first working sub-area 11, with a cleanliness level of 3; the second working sub-area 12, with a cleanliness level of 4; the third working sub-area 13, with a cleanliness level of 4; and the fourth working sub-area 14, with a cleanliness level of 4. An iris access control system is installed between the working sub-areas, such as the iris access control system 15 between the first working sub-area 11 and the second working sub-area 12.

[0117] The environmental monitoring module uses sensors to monitor the environmental parameters of the working sub-area in real time, thereby obtaining the environmental parameters of the sub-area.

[0118] Sensors are installed in the divided sub-areas of the working area P to monitor environmental parameters in real time, including suspended particle size data, suspended particle concentration data, temperature data, humidity data, and wind speed data; the sensors transmit information through the Internet of Things.

[0119] In determining the sensor placement location, the spatial structure of the working sub-region is identified by the working area P; historical trajectory data of all staff are collected; clustering algorithm is used to cluster the historical trajectory data of all staff to obtain activity density distribution data; and the sensor placement location is determined based on the activity density distribution data.

[0120] The personnel tracking module tracks staff wearing cleanroom suits in real time, obtaining work trajectory data and work status data. The work trajectory data includes stationary trajectory data and movement trajectory data. The work status data includes sweating data, heart rate data, breathing data, and movement data.

[0121] The sweating data, heart rate data, and respiratory data are acquired by monitoring the test personnel through sensors; the motion data includes the range of motion of the personnel during the test; the sweating data includes the amount of sweat produced by the personnel; the heart rate data is the heart rate; and the respiratory data is the respiratory rate.

[0122] The process by which the work area P acquires the motion data is as follows:

[0123] The work process of the staff in the work sub-area is monitored by a camera device to obtain a work video set; the work video set is divided according to the staff's actions to obtain work video subsets;

[0124] The images in the work video subset are identified frame by frame, and the motion amplitude is obtained through the motion characteristics of the staff; motion data is obtained based on the motion amplitude of the entire work video subset.

[0125] The external pollution identification module identifies the distance between the worker and the sensor based on the work trajectory data, identifies the environmental parameters of the sub-area of ​​different sensors based on the distance, and obtains the trajectory environmental parameters; it constructs an external pollution identification model to identify the trajectory environmental parameters and work trajectory data, and obtains external pollution data.

[0126] The trajectory environment parameters include stationary trajectory environment parameters and motion trajectory environment parameters;

[0127] The method for obtaining the stationary trajectory environmental parameters is as follows: acquiring the stationary trajectory data of the exerciser, wherein the stationary trajectory data is the trajectory data of the worker stationed in a fixed position area, including the stationary position and stationary duration; selecting the sub-region environmental parameters of the sensor with the smallest distance from the stationary position as the stationary trajectory environmental parameters;

[0128] The method for obtaining the motion trajectory environmental parameters is as follows: acquiring the motion trajectory data of the worker, which is the movement data of the worker in the work sub-area, including the motion trajectory and movement speed; determining the sensor with the smallest distance from the worker as the reference sensor based on the motion trajectory; dividing the motion trajectory according to the reference sensor to obtain the motion sub-trajectory; each motion sub-trajectory corresponds to a reference sensor; and obtaining the motion trajectory environmental parameters based on the sub-area environmental parameters of the reference sensor.

[0129] During the process of acquiring environmental parameters of worker movement trajectories in work area P, the method for determining reference sensors based on movement trajectories is as follows: Figure 4 As shown;

[0130] Sensors were set up based on the dense distribution data of activities in the area, namely, sensor 21, sensor 22, sensor 23, and sensor 24. The movement trajectories of the workers were then acquired, resulting in the initial position 31, intermediate position 32, and ending position 33 of the trajectories. The closest sensor was then determined based on the distance between the movement trajectory and the sensors, resulting in a first dividing point 41 and a second dividing point 42. These two dividing points divided the movement trajectory into three sub-trajectories.

[0131] In the sub-trajectory from the initial position 31 to the first division point 41, the distance between the worker and the first sensor 21 is the smallest; therefore, the first sensor 21 is used as the reference sensor for this sub-region. In the sub-trajectory from the first division point 41 to the intermediate position 32, and then from the intermediate position 32 to the second division point 42, the distance between the worker and the second sensor 22 is the smallest; therefore, the second sensor 22 is used as the reference sensor for this sub-region. In the sub-trajectory from the second division point 42 to the final position 33, the distance between the worker and the third sensor 23 is the smallest; therefore, the third sensor 23 is used as the reference sensor for this sub-region. The division of the sub-trajectories and the corresponding reference sensor data are shown in Table 2.

[0132] Table 2. Division of motion sub-trajectories and corresponding reference sensor data.

[0133] Sub-trajectory of motion starting point end Reference sensor 1 Initial position 31 First dividing point 41 First sensor 21 2 First dividing point 41 Second dividing point 42 Second sensor 22 3 Second dividing point 42 End position 33 Third sensor 23

[0134] After obtaining the trajectory and environmental parameters of the athletes, the external pollution data is identified through the external pollution identification model.

[0135] The external contamination identification model includes a data input layer, a data processing layer, an external contamination identification layer, and a data output layer;

[0136] The data input layer is used to acquire trajectory environment parameters and working trajectory data;

[0137] The data processing layer identifies the stationary trajectory data of the working trajectory data and the stationary trajectory environment parameters of the trajectory environment parameters to obtain first identification data; it also identifies the motion trajectory data of the working trajectory data and the motion trajectory environment parameters of the trajectory environment parameters to obtain second identification data.

[0138] The external pollution identification layer identifies first pollution data based on first identification data and second pollution data based on second identification data; it also obtains external pollution data based on the first pollution data and the second pollution data.

[0139] The data output layer is used to output external pollution data.

[0140] The internal contamination identification module acquires the work status data of the staff, builds an internal contamination identification model to identify the work status data, and obtains internal contamination data.

[0141] The process of obtaining the internal contamination identification model is as follows:

[0142] Internal contamination tests were conducted on personnel wearing cleanroom suits to obtain an internal contamination test set.

[0143] The internal contamination test set includes sweating data, heart rate data, respiratory data, and movement data of the test personnel during the test; the sweating data, heart rate data, and respiratory data are acquired by monitoring the test personnel through sensors; the movement data includes the range of motion of the personnel during the test.

[0144] The internal surface contamination data of the cleanroom garments worn by the test personnel is detected to obtain test contamination data; the initial model is trained based on the internal contamination test set and the test contamination data to obtain the internal contamination identification model.

[0145] The pollution level identification module identifies the pollution level of the staff's cleanroom clothing by using a pollution level identification model to identify external and internal pollution data.

[0146] The process of obtaining the pollution level identification model is as follows:

[0147] Obtain the initial environmental parameters and cleanliness level of the work sub-area;

[0148] A time threshold is set, and staff wearing test cleanroom suits are selected to work in the work sub-area based on the time threshold; the test cleanroom suits have different external and internal contamination data.

[0149] After the working duration threshold is reached, the termination environment parameters of the working sub-region are obtained;

[0150] The pollution coefficient of the working sub-area environment is determined based on the initial and final environmental parameters; the pollution level of the test cleanroom garment is determined based on the pollution coefficient and the cleanliness level, and a pollution level recognition model is trained.

[0151] The pollution coefficient includes 0 and 1; when the pollution coefficient is 0, it indicates that the changes in the initial environmental parameters and the final environmental parameters are small and have no significant impact, that is, no impact on the current cleanliness level; when the pollution coefficient is 1, it indicates that the changes in the initial environmental parameters and the final environmental parameters are large and have a significant impact, that is, an impact on the current cleanliness level.

[0152] Work area P is classified into 5 contamination levels based on 4 cleanliness levels. Contamination level 1 is uncontaminated and can be entered into all cleanliness levels of work sub-areas. Contamination level 2 allows entry into cleanliness levels 2, 3, and 4. Contamination level 3 allows entry into cleanliness levels 3 and 4. Contamination level 4 allows entry into cleanliness level 4. Contamination level 5 is severely contaminated and cannot be entered into any cleanliness level of work sub-area. At the same time, a warning message is sent to the target staff.

[0153] The data from the contamination level test of cleanroom garments in work area P are shown in Table 3.

[0154] Table 3. Test Data on Contamination Level of Cleanroom Garments in Work Area P

[0155]

[0156] The intelligent management module identifies the pollution level based on the cleanliness level of the work sub-area, adjusts the iris access permissions of staff based on the identification results, and adjusts the activity range of staff based on iris access permissions and the iris access control system.

[0157] Based on the pollution level and the cleanliness level of the work sub-area, determine whether the staff will cause pollution to the work sub-area;

[0158] If it will not cause pollution, then enable iris access for staff to enter the work sub-area, allowing staff to access the iris access control system to the work sub-area;

[0159] If contamination is likely to occur, iris access to the work area will be disabled, preventing staff from activating the iris access control system to that work area. If a staff member is already in the work area, a deportation warning will be issued, and the corresponding cleanroom garment will be marked.

[0160] As shown in Table 3, the contamination level of cleanroom garment No. 1 is 4. Iris access permissions allow the staff wearing this cleanroom garment to open the iris access control system to the work sub-area of ​​cleanliness level 4. The contamination level of cleanroom garment No. 2 is 3. Iris access permissions allow the staff wearing this cleanroom garment to open the iris access control system to the work sub-areas of cleanliness level 3 and cleanliness level 4. The contamination level of cleanroom garment No. 3 is 5. All iris access permissions of the staff wearing this cleanroom garment are immediately disabled, and a warning message is sent to the staff. At the same time, the cleanroom garment is marked as needing cleaning.

[0161] This invention divides the work area into sub-areas based on the cleanliness level (P) of the work area. An iris recognition access control system is installed between these sub-areas. Environmental parameters of each sub-area are monitored by sensors. Workers wearing cleanroom suits are tracked in real-time, obtaining work trajectory data and work status data. Environmental parameters are derived from the work trajectory data. External contamination data is obtained by identifying these parameters and the work trajectory data. Internal contamination data is obtained by identifying the work status data. The contamination level of the worker's cleanroom suit is determined based on the external and internal contamination data. Iris recognition permissions are adjusted according to the cleanliness and contamination levels, and the activity range is adjusted based on these permissions and the iris access control system, thus achieving intelligent management of the cleanroom suits within the work area (P).

[0162] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A clean clothes intelligent management system with iris recognition technology, characterized in that, The system comprises: a region division module, which divides the working region according to the cleaning level of the working region to obtain working sub-regions, and sets up an iris access control system between the working sub-regions; an environment monitoring module, which monitors the environment parameters of the working sub-regions in real time through sensors to obtain sub-region environment parameters; a personnel tracking module, which tracks the personnel wearing clean clothes in real time to obtain working trajectory data and working state data; the working trajectory data includes stay trajectory data and motion trajectory data; the working state data includes sweat data, heart rate data, breathing data and action data; an external pollution identification module, which identifies the distance between the personnel and the sensors according to the working trajectory data, identifies the sub-region environment parameters of different sensors according to the distance, obtains trajectory environment parameters, and constructs an external pollution identification model to identify the trajectory environment parameters and the working trajectory data to obtain external pollution data; an internal pollution identification module, which obtains the working state data of the personnel, constructs an internal pollution identification model to identify the working state data, and obtains internal pollution data; a level identification module, which identifies the external pollution data and the internal pollution data through a pollution level identification model to obtain the pollution level of the clean clothes of the personnel; an intelligent management module, which identifies the pollution level according to the cleaning level of the working sub-regions, adjusts the iris permission of the personnel according to the identification result, and adjusts the activity range of the personnel according to the iris permission and the iris access control system.

2. The clean clothes intelligent management system with iris recognition technology according to claim 1, wherein: the cleaning level is determined according to the cleaning parameters required by the production activities of the working sub-regions; the cleaning parameters include standard suspended particle size data and standard suspended particle concentration data, and different cleaning levels correspond to different cleaning parameters.

3. The clean clothes intelligent management system with iris recognition technology according to claim 1, wherein: the iris access control system includes an access control system that identifies according to the iris, and the working process includes: obtaining the identity information of the personnel through iris recognition, confirming the iris permission of the personnel according to the identity information, and determining whether to open the access control for the personnel according to the iris permission.

4. The clean clothes intelligent management system with iris recognition technology according to claim 1, wherein: the sub-region environment parameters are the environment parameters in the working sub-regions, including suspended particle size data, suspended particle concentration data, temperature data, humidity data and wind speed data, which are obtained through sensors set in the working sub-regions; the setting mode of the sensors is to identify the spatial structure of the working sub-regions, collect the historical trajectory data of all personnel according to the spatial structure of the working sub-regions, identify the historical trajectory data of all personnel through clustering algorithm to obtain activity intensive distribution data, and determine the setting position of the sensors according to the activity intensive distribution data.

5. The clean clothes intelligent management system with iris recognition technology according to claim 1, wherein: the process of obtaining the action data is: The working process of the staff in the working sub-area is monitored by the camera to obtain a working video set; the working video set is divided according to the action of the staff to obtain a working video subset; The images in the working video subset are identified frame by frame to obtain the action amplitude through the action characteristics of the staff; and the action data is obtained according to the action amplitudes of all the working video subsets.

6. The clean clothes intelligent management system with iris recognition technology according to claim 5, characterized in that: The trajectory environmental parameters include stay trajectory environmental parameters and motion trajectory environmental parameters; The stay trajectory environmental parameters are obtained by obtaining stay trajectory data of the moving personnel, the stay trajectory data being trajectory data of the staff staying in a fixed position area, including a stay position and a stay duration; The sub-area environmental parameters of the sensor with the smallest distance from the stay position are selected as the stay trajectory environmental parameters; The motion trajectory environmental parameters are obtained by obtaining motion trajectory data of the moving personnel, the motion trajectory data being motion data of the staff in the working sub-area, including a motion trajectory and a motion speed; a reference sensor with the smallest distance from the staff is determined according to the motion trajectory; the motion trajectory is divided according to the reference sensor to obtain a motion sub-trajectory; each motion sub-trajectory corresponds to a reference sensor; and the motion trajectory environmental parameters are obtained according to the sub-area environmental parameters of the reference sensor.

7. The clean clothes intelligent management system with iris recognition technology according to claim 1, characterized in that: The external pollution identification model includes a data input layer, a data processing layer, an external pollution identification layer and a data output layer; The data input layer is used to obtain trajectory environmental parameters and working trajectory data; The data processing layer is used to identify stay trajectory data of the working trajectory data and stay trajectory environmental parameters of the trajectory environmental parameters to obtain first identification data; and identify motion trajectory data of the working trajectory data and motion trajectory environmental parameters of the trajectory environmental parameters to obtain second identification data; The external pollution identification layer is used to identify first pollution data according to the first identification data, identify second pollution data according to the second identification data, and obtain external pollution data according to the first pollution data and the second pollution data; The data output layer is used to output the external pollution data.

8. The clean clothes intelligent management system with iris recognition technology according to claim 1, characterized in that: The obtaining process of the internal pollution identification model is as follows: Test personnel wear clean clothes to perform internal pollution testing to obtain an internal pollution test set; The internal pollution test set includes sweat data, heart rate data, breathing data and action data of the test personnel during the testing; the sweat data, heart rate data and breathing data are obtained by monitoring the test personnel through sensors; and the action data includes action amplitudes of the action personnel during the testing; The inner surface pollution data of the clean clothes worn by the test personnel is detected to obtain test pollution data; and the internal pollution identification model is obtained by training the initialized model according to the internal pollution test set and the test pollution data.

9. The clean clothes intelligent management system with iris recognition technology according to claim 1, characterized in that: the obtaining process of the pollution level identification model is: obtaining initial environmental parameters and a cleaning level of a working sub-area; setting a time threshold, and selecting a worker wearing a test clean clothes to work in the working sub-area according to the time threshold; the test clean clothes has different external pollution data and internal pollution data; after the working time threshold, obtaining termination environmental parameters of the working sub-area; judging a pollution coefficient of the working sub-area environment according to the initial environmental parameters and the termination environmental parameters; determining the pollution level of the test clean clothes according to the pollution coefficient and the cleaning level, and training to obtain the pollution level identification model; the pollution coefficient includes 0 and 1; when the pollution coefficient is 0, it means that the change degree of the initial environmental parameters and the termination environmental parameters is small, and no obvious influence is caused, that is, no influence is caused to the current cleaning level; when the pollution coefficient is 1, it means that the change degree of the initial environmental parameters and the termination environmental parameters is large, and obvious influence is caused, that is, influence is caused to the current cleaning level.

10. The clean garment intelligent management system with iris recognition technology according to claim 1, characterized in that: the adjusting process of the worker's iris permission according to the cleaning level and the pollution level is: judging whether the worker will cause pollution to the working sub-area according to the pollution level and the cleaning level of the working sub-area; if no pollution is caused, the worker's iris permission to enter the working sub-area is opened, so that the worker can open the iris access control system leading to the working sub-area; if pollution is caused, the worker's iris permission to enter the working sub-area is closed, so that the worker cannot open the iris access control system leading to the working sub-area; when the worker is already in the working sub-area, a driving warning is issued, and the corresponding clean clothes is marked.

Citation Information

Patent Citations

  • Information management system and method of micro-nano processing experiment platform

    CN118761737A

  • Ground sensing technology-based entrance and exit identity recognizer special for clean area

    CN210402503U