Method and system for analyzing contamination sources of cleanroom AMC

Abstract

The present application is suitable for the technical field of pollution source analysis, and particularly relates to a clean space AMC pollution source analysis method and system, which comprises the following steps: delimiting the area range of the clean space, selecting source equipment generating AMC in the area range, collecting AMC data at the source equipment by using a mobile monitoring device deployed in the area range, configuring the emission fingerprint of each source equipment based on the historical value of the AMC data, reading the real-time value in the AMC data, calculating the similarity between the real-time value and each emission fingerprint by using a cosine similarity calculation formula, dividing the similarity into several intervals, wherein each interval corresponds to a moving speed, integrating the interval and the moving speed, and generating a comparison table. The present application can remove background interference by collecting background noise, so that the monitoring value is closer to the real emission, the accuracy of AMC pollution source analysis is improved, and reliable data support and decision basis are provided for AMC pollution control in the area range.

Description

Technical Field

[0001] This invention relates to the field of pollution source analysis technology, and in particular to a method and system for pollution source analysis in cleanroom ambient control rooms (AMCs). Background Technology

[0002] Clean spaces typically include semiconductor plants, display panel workshops, optical manufacturing workshops, and pharmaceutical sterile areas. In clean spaces, even extremely low concentrations of gaseous contaminants at the molecular level can directly affect the process stability and yield of high-precision manufacturing processes in semiconductors, displays, optics, and biopharmaceuticals. Therefore, monitoring AMC concentration is extremely important.

[0003] In existing technologies, AMC concentration monitoring is generally conducted using fixed-point methods. These fixed points are typically placed in locations that are easy to install and maintain, such as ceilings, walls, or air conditioning return air vents. However, these locations are often far from the actual sources of pollution, such as process equipment exhaust outlets, equipment gaps, pipe joints, valves, pumps, and material replacement points. As a result, the accuracy of monitoring is easily affected by the local "microenvironment." Furthermore, due to cost and maintenance considerations, sensor density is usually limited, and the detection network cannot form a sufficiently fine spatial resolution for accurate source tracing. Moreover, some critical locations are difficult to install monitoring equipment due to space constraints or cleanliness level restrictions, further expanding the blind spots.

[0004] Therefore, "how to conduct motion monitoring in a clean space" is the technical problem that this invention aims to solve. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for analyzing AMC pollution sources in clean spaces, in order to solve the problem of "how to conduct mobile monitoring in clean spaces" mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for analyzing contamination sources in cleanroom ambient temperature monitoring (AMC), the method comprising:

[0008] Define the area of ​​the clean space, select the source devices that generate AMC within the area, collect AMC data at the source devices using mobile monitoring devices pre-deployed within the area, and configure the emission fingerprint of each source device based on the historical values ​​of the AMC data.

[0009] The real-time values ​​in the AMC data are read, and the cosine similarity calculation formula is used to calculate the similarity between the real-time values ​​and each emission fingerprint. The similarity is divided into several intervals, each interval corresponding to a movement speed. The intervals and movement speeds are integrated to generate a comparison table, which is then sent to the motion monitoring device.

[0010] Based on the similarity, anomalous devices are defined. Using a sampling device pre-integrated into the mobile monitoring device, gas samples are collected from the anomalous devices, and attribute data is recorded.

[0011] The movement path of the mobile monitoring device is obtained, and the movement path between two adjacent source devices is defined as a segment. Several calibration points are selected from each segment. When the mobile monitoring device reaches the calibration point, the AMC data at the calibration point is collected and defined as background noise. The emission fingerprint is offset using the background noise, the abnormal device is updated, and sent to a preset terminal.

[0012] Furthermore, the step of defining the area of ​​the clean space and selecting the source equipment that generates AMC within the area includes:

[0013] Draw a planar distribution map within the area, and mark the source device on the planar distribution map;

[0014] The propagation factors within the designated area are defined, including at least location, wind direction, and exhaust path. A pollution propagation map is generated using the propagation factors and a planar distribution map.

[0015] Furthermore, the step of collecting AMC data from the source device using mobile monitoring devices pre-deployed within the area includes:

[0016] The location of each source device is located, and the nearest neighbor algorithm is used to connect all the locations to generate a movement path, which is then sent to the movement monitoring device.

[0017] Set the type of abnormal device and create emergency response rules that correspond one-to-one with the type.

[0018] Furthermore, the step of reading the real-time value from the AMC data includes:

[0019] Select the abnormal points within the area and update them dynamically, then insert the updated abnormal points into the movement path.

[0020] Acquire readings from multiple sources within the area and define the readings from these multiple sources and mobile monitoring devices as real-time values.

[0021] Furthermore, the step of dividing the similarity into several intervals includes:

[0022] Configure the risk level corresponding to each interval, and activate the pre-edited purification plan when the risk level is greater than the threshold.

[0023] Integrate all purification solutions, generate a solution set, and grant the preset terminals the right to adjust the solution set.

[0024] Furthermore, the step of defining anomalous devices via the similarity includes:

[0025] Sort all source devices in descending order of similarity to generate a queue;

[0026] Select a preset number of source devices from the front of the queue and define them as abnormal devices.

[0027] Furthermore, the step of using the background noise to offset the real-time value, update the abnormal device, and send it to the preset terminal includes:

[0028] The frequency of occurrence of each abnormal device was counted, and the movement path was adjusted accordingly;

[0029] The diffusion trend of AMC is determined through the exhaust path, a stable point is selected, and the AMC data at the stable point is defined as global noise, and the real-time value is corrected.

[0030] Furthermore, the system includes:

[0031] The configuration module is used to delineate the area of ​​the clean space, select the source devices that generate AMC within the area, collect AMC data at the source devices using mobile monitoring devices pre-deployed within the area, and configure the emission fingerprint of each source device based on the historical values ​​of the AMC data.

[0032] The distribution module is used to read the real-time values ​​in the AMC data, calculate the similarity between the real-time values ​​and each emission fingerprint using the cosine similarity calculation formula, divide the similarity into several intervals, each interval corresponding to a movement speed, integrate the intervals and movement speeds to generate a lookup table, and distribute it to the motion monitoring device.

[0033] The recording module is used to define abnormal devices based on the similarity, collect gas samples from the abnormal devices using a sampling device pre-integrated in the mobile monitoring device, and record the attribute data.

[0034] The update module is used to obtain the movement path of the mobile monitoring device, define the movement path between two adjacent source devices as segments, select several calibration points from each segment, and collect AMC data at the calibration point when the mobile monitoring device reaches the calibration point, define it as background noise, use the background noise to offset the emission fingerprint, update the abnormal device, and send it to the preset terminal.

[0035] Furthermore, the configuration module includes:

[0036] The annotation unit is used to draw a planar distribution map within the area and to annotate the source device onto the planar distribution map;

[0037] The setting unit is used to set the propagation factors within the area, wherein the propagation factors include at least: location, wind direction and exhaust path, and a pollution propagation map is generated using the propagation factors and the plan distribution map;

[0038] The positioning unit is used to locate the position of each source device, connect all the positions using the nearest neighbor algorithm, generate a movement path, and send it to the movement monitoring device.

[0039] Create a unit to set the type of abnormal device and create emergency response rules that correspond one-to-one with the type.

[0040] Furthermore, the distribution module includes:

[0041] The insertion unit is used to select abnormal points within the area and dynamically update them, inserting the updated abnormal points into the movement path.

[0042] The acquisition unit is used to acquire the readings of multi-source devices within the area and define the readings of multi-source devices and mobile monitoring devices as real-time values.

[0043] The activation unit is used to configure the risk level corresponding to each interval. When the risk level is greater than the threshold, the pre-edited purification plan is activated.

[0044] The open unit is used to integrate all purification solutions, generate a solution set, and grant the preset terminals the right to adjust the solution set.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] By identifying emission fingerprints, AMC pollution sources can be quickly identified, improving the accuracy of pollution identification and reducing misjudgments. By comparing similarity, subtle differences in emissions from different devices can be quickly distinguished. In cases with multiple pollution sources, the contribution ratio of each source can be accurately quantified, thereby achieving the separation and analysis of multi-source superimposed emissions and further improving the accuracy of pollution source tracing. By constructing a comparison table, interference from mobile monitoring devices during the monitoring process can be reduced, significantly increasing dwell time and sampling frequency, which helps to capture short-term, weak emission fluctuations and further improve the accuracy of pollution source analysis. By collecting background noise, background interference can be removed, making the monitored values ​​closer to the actual emissions and improving the accuracy of AMC pollution source analysis. This provides reliable data support and decision-making basis for AMC pollution control within the region. Attached Figure Description

[0047] Figure 1A flowchart illustrating the cleanroom AMC pollution source analysis method provided in this embodiment of the invention;

[0048] Figure 2 This is a first sub-flowchart of the cleanroom AMC pollution source analysis method provided in an embodiment of the present invention;

[0049] Figure 3 This is a second sub-flowchart of the cleanroom AMC pollution source analysis method provided in an embodiment of the present invention;

[0050] Figure 4 This is a third sub-flowchart of the clean space AMC pollution source analysis method provided in the embodiments of the present invention;

[0051] Figure 5 The fourth sub-flowchart of the clean space AMC pollution source analysis method provided in this embodiment of the invention;

[0052] Figure 6 This is a block diagram of the clean space AMC pollution source analysis system provided in an embodiment of the present invention;

[0053] Figure 7 A block diagram of the configuration modules in the clean space AMC pollution source analysis system provided in this embodiment of the invention;

[0054] Figure 8 A block diagram of the distribution module in the cleanroom AMC pollution source analysis system provided in this embodiment of the invention;

[0055] Figure 9 A block diagram of the recording module in the clean space AMC pollution source analysis system provided in this embodiment of the invention;

[0056] Figure 10 This is a block diagram of the update module in the clean space AMC pollution source analysis system provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0058] In Example 1, Figure 1 The implementation flow of the clean space AMC pollution source analysis method provided in this embodiment of the invention is illustrated below, and is described in detail below:

[0059] S100: Define the area of ​​the clean space, select the source devices that generate AMC within the area, collect AMC data at the source devices using mobile monitoring devices pre-deployed within the area, and configure the emission fingerprint of each source device based on the historical values ​​of the AMC data.

[0060] The clean space area is defined, which can be a semiconductor plant, display panel workshop, optical manufacturing workshop, or pharmaceutical sterile area, etc. This area is the region within the clean space where AMC (Aerobic Methane) contamination source analysis is required. Based on process layout, equipment function, and historical AMC event records, potential AMC-releasing devices, i.e., source devices, are identified. Source devices can be process equipment, air conditioning vents, exhaust systems, gas cylinders, and associated piping interfaces, etc. Mobile monitoring devices are deployed within this area. These devices can be track-mounted or autonomous walking monitoring robots. The mobile monitoring devices integrate high-sensitivity AMC sensing components, positioning modules, and path planning modules, enabling autonomous patrolling and monitoring within the area. When the mobile monitoring device approaches a source device, it collects AMC data at a fixed sampling frequency, with each source device corresponding to a set of AMC data.

[0061] AMC data is recorded in chronological order to determine historical values. These historical values ​​are then arranged in ascending order. Outliers in the AMC data are removed using the interquartile range algorithm. The average value of the AMC data is then calculated and defined as the emission fingerprint. Each source device corresponds to a set of emission fingerprints, which are mainly used to reflect the typical emission characteristics of the source device.

[0062] S200: Read the real-time value from the AMC data, calculate the similarity between the real-time value and each emission fingerprint using the cosine similarity calculation formula, divide the similarity into several intervals, each interval corresponding to a movement speed, integrate the intervals and movement speeds, generate a comparison table, and send it to the motion monitoring device.

[0063] Within the designated area, multiple fixed monitoring points are selected. When the mobile monitoring device reaches a fixed point, the collected AMC (Air Pollution Control Metric) data is defined as a real-time value. The real-time value comprehensively reflects the pollution status across the entire area, showcasing the global AMC distribution characteristics. The determination of the real-time value can also refer to fixed monitoring equipment; each area corresponds to only one set of real-time values. Using the cosine similarity formula, the similarity between the real-time value and each emission fingerprint is calculated. The similarity primarily quantifies the degree of matching between the current airborne AMC characteristics and known fingerprints. A higher similarity indicates a greater likelihood that the airborne AMC originates from the corresponding source device. The similarity is divided into several intervals, and a corresponding mobile speed is assigned to each interval. A lookup table is used to store the intervals and mobile speeds; in other words, the lookup table consists of interval entries and mobile speed entries.

[0064] For example, in a semiconductor workshop, using fixed monitoring equipment or mobile monitoring devices in an open area or the center of the workshop, the concentration of ammonia is detected to be 22 ppb and the concentration of formaldehyde is 0.05 ppb, i.e., the real-time values ​​are: ammonia 22 ppb and formaldehyde 0.05 ppb. When the mobile monitoring device is moved to device A, the concentration of ammonia is detected to be 3 ppb and formaldehyde 0.002 ppb. When device B is moved, the concentration of ammonia is detected to be 40 ppb and formaldehyde 0.09 ppb. Then, calculate the similarity between (22, 0.05) and (3, 0.002) and (22, 0.05) and (40, 0.09), respectively.

[0065] Let's define the similarity range of 1.001-1.0019 as the first interval, corresponding to a movement speed of 1 m / s, and the similarity range of 1.002-1.0029 as the second interval, corresponding to a movement speed of 1.2 m / s. Using the intervals and their corresponding movement speeds, we can create a comparison table.

[0066] S300: Based on the similarity, an anomalous device is defined. Using a sampling device pre-integrated in the mobile monitoring device, a gas sample is collected at the anomalous device, and the attribute data is recorded.

[0067] Multiple source devices with high similarity are selected and defined as anomalous devices. When the mobile monitoring device reaches the anomalous device, a sampling device pre-integrated in the mobile monitoring device is used to collect gas samples from the emission port, near the surface, and within the process area of ​​the anomalous device. The sampling device can be a miniature gas sampling pump or a reactive adsorption plate sampler, etc. The attribute data of the sampling device is recorded, including the location of the anomalous device and the sampling time. After sampling is completed and the mobile monitoring device returns to its initial position, a notification is sent to the inspection personnel. The inspection personnel remove the samples from the sampling device and manually verify the emission fingerprint of the anomalous device. The advantage of this method is that it can not only quickly identify potential anomalous emission sources, but also provide data support for emission fingerprint updates, source verification, and pollution tracing.

[0068] S400: Obtain the movement path of the mobile monitoring device, define the movement path between two adjacent source devices as segments, select several calibration points from each segment, collect AMC data at the calibration point after the mobile monitoring device reaches the calibration point, define it as background noise, use the background noise to offset the emission fingerprint, update the abnormal device, and send it to the preset terminal.

[0069] The mobile monitoring device's movement path is determined, and the source device is divided into several segments. Within each segment, several calibration points are selected. The number of calibration points can be one or more, and should be determined by professionals. When the mobile monitoring device reaches a calibration point along the movement path, AMC data at that point is collected and defined as background noise. In actual analysis, both personnel and the mobile monitoring device may generate short-term disturbances or introduce additional AMC during movement, causing offsets in the real-time acquisition results of the source device. Therefore, by defining background noise, disturbance factors can be separated from the true emission signal, achieving offset correction of the real-time value, making the corrected AMC data closer to the true environmental concentration distribution within the area. After offsetting the emission fingerprint, abnormal devices are updated and sent to a preset terminal, where the abnormal device is the AMC pollution source. The preset terminal refers to the terminal of the cleanroom management or maintenance personnel.

[0070] In this embodiment, mobile monitoring devices are used to collect AMC data for each source device and calculate the average value of AMC data at multiple times. This average value is defined as the emission fingerprint. Using fixed or mobile monitoring devices, AMC data at multiple locations are collected and the global AMC distribution characteristics are determined. By comparing the emission fingerprint and the global AMC distribution characteristics, it is possible to determine which source devices have emission characteristics that are most similar to the current environment on an overall spatial scale, and finally identify the pollution source.

[0071] In Example 2, Figure 2 The implementation flow of the clean space AMC pollution source analysis method provided by an embodiment of the present invention is illustrated. The following details the steps of delineating the area of ​​the clean space and selecting the source devices that generate AMC within the area:

[0072] S101: Draw a planar distribution map within the area and mark the source device on the planar distribution map.

[0073] Based on the building layout and equipment placement within the area, draw a plan of the area and mark the source equipment at the corresponding location on the plan.

[0074] S102: Set the propagation factors within the area, wherein the propagation factors include at least: location, wind direction and exhaust path, and generate a pollution propagation map using the propagation factors and the planar distribution map.

[0075] The propagation factors are identified, which refer to factors that may affect the spread of pollutants from the emission source to the surrounding area. These factors include the location of the source equipment, wind direction, and exhaust path. By analyzing the concentration gradient between different locations, the migration trend of wind direction, and the flow direction guided by the exhaust path, a pollution propagation map is generated. The pollution propagation map can intuitively show the diffusion trajectory and the strength of the impact of pollutants from potential emission sources to the surrounding area.

[0076] In Example 3, Figure 2 The implementation flow of the clean space AMC pollution source apportionment method provided by an embodiment of the present invention is illustrated below. The steps of collecting AMC data at the source equipment using a mobile monitoring device pre-deployed within a region are described in detail below:

[0077] S103: Locate the position of each source device, use the nearest neighbor algorithm to connect all the positions, generate a movement path, and send it to the movement monitoring device.

[0078] The actual spatial location of each source device is accurately located. Using the nearest neighbor algorithm, the locations of each source device are connected sequentially to generate a movement path covering all source devices. This movement path can also be fine-tuned by professionals. In other words, the generated path not only needs to consider the shortest spatial distance between devices, but also needs to take into account regional access restrictions and security requirements. The movement path is then sent to the motion monitoring device, which operates according to the movement path and collects AMC data.

[0079] S104: Set the type of abnormal device and create emergency response rules that correspond one-to-one with the type.

[0080] Based on the functional attributes, emission characteristics, and potential risk levels of abnormal equipment, different abnormal equipment are clustered into several types, such as high-emission-risk equipment, short-term peak emission equipment, or continuous trace emission equipment. Corresponding emergency response rules are created for each type of abnormal equipment. These rules include: immediate alarm, prioritizing sampling by mobile monitoring devices, and activating local ventilation or purification measures. By adaptively activating these emergency response rules, not only can the handling efficiency of abnormal equipment be improved, but the impact of AMC (Average Control Mechanism) on cleanroom processes can also be minimized, ensuring a safe and stable production environment.

[0081] In Example 4, Figure 3 The implementation flow of the clean space AMC pollution source analysis method provided by the embodiment of the present invention is shown below. The steps for reading the real-time values ​​from the AMC data are described in detail below:

[0082] S201: Select the abnormal points within the area and update them dynamically, then insert the updated abnormal points into the movement path.

[0083] Within the region, abnormal locations are identified. Abnormal locations refer to areas where AMC pollution may exist. There are multiple factors that may cause abnormal locations, such as fluctuations in the operating conditions of the source equipment or short-term emissions generated during personnel operation. Abnormal locations are added to the movement path.

[0084] S202: Acquire the readings of multi-source devices within the area and define the readings of multi-source devices and mobile monitoring devices as real-time values.

[0085] Identify the multi-source devices within the area, which can be fixed monitoring devices or other AMC monitoring devices. Using multi-source devices and mobile monitoring devices, determine the real-time value of AMC data within the area by calculating the average value of the readings.

[0086] In Example 5, Figure 3The implementation flow of the clean space AMC pollution source analysis method provided by the embodiment of the present invention is shown below. The steps of dividing the similarity into several intervals are described in detail below:

[0087] S203: Configure the risk level corresponding to each interval. When the risk level is greater than the threshold, activate the pre-edited purification plan.

[0088] Configure the risk level for each zone. Continuing with the example above, the risk level of the first zone can be defined as low, and the risk level of the second zone can be defined as medium. When the risk level is high or above, the purification scheme is activated. The purification scheme includes: turning on local or global air purification devices, adjusting fan flow, and starting chemical adsorption, etc.

[0089] S204: Integrate all purification solutions, generate a solution set, and grant the preset terminals the right to adjust the solution set.

[0090] All purification solutions are integrated to generate a solution set. In other words, the solution set is a collection of purification solutions. The adjustment permission of the solution set is granted to preset terminals. When a certain risk level corresponds to multiple purification solutions, professionals can select and activate the purification solution according to the adjustment permission.

[0091] In Example 6, Figure 4 The implementation flow of the cleanroom AMC pollution source analysis method provided by the embodiment of the present invention is shown. The steps of defining abnormal equipment through the similarity are described in detail below:

[0092] S301: Sort all source devices in descending order of similarity and generate a queue.

[0093] After calculating the similarity between the emission fingerprint of each source device and the real-time value within the region, a correspondence between similarity and source device is established. All source devices are then sorted in descending order of similarity to obtain a queue, where the greater the similarity, the higher the ranking of the source device.

[0094] S302: Select a preset number of source devices from the front of the queue and define them as abnormal devices.

[0095] A preset number of source devices are selected from the front of the queue and defined as abnormal devices. The preset number is determined by professionals.

[0096] In Example 7, Figure 5The implementation flow of the cleanroom AMC pollution source analysis method provided by an embodiment of the present invention is illustrated. The following details the steps of using the background noise to offset the real-time value, update the abnormal equipment, and send it to the preset terminal:

[0097] S401: Count the number of times each abnormal device appears and adjust the movement path accordingly.

[0098] The number of times each abnormal device appears is counted, and the movement path is adjusted according to the number of occurrences. Specifically, the adjustment can be to prioritize monitoring abnormal devices that appear more frequently.

[0099] S402: Determine the diffusion trend of AMC through the exhaust path, select a stable point, define the AMC data at the stable point as global noise, and correct the real-time value.

[0100] By analyzing the exhaust paths corresponding to various sources of equipment, the diffusion trend of AMC in the air is determined, including airflow direction, speed, and the spatial distribution pattern of pollutants. Within the region, several points located in areas with stable airflow and minimal disturbance are selected as stable points. The collected AMC data is defined as global noise, which is used to characterize the baseline background level of AMC throughout the entire region. Using global noise, each real-time value is corrected, and the difference between the real-time value and global noise is calculated or offset corrected. This eliminates short-term fluctuations caused by environmental disturbances, personnel movement, and the movement of the mobile monitoring device itself, and achieves accurate restoration and standardization of AMC concentration.

[0101] Figure 6 This diagram illustrates the structural composition of a cleanroom AMC (Activated Cleanroom Control Center) pollution source apportionment system provided in an embodiment of the present invention. The cleanroom AMC pollution source apportionment system 1 includes:

[0102] Configuration module 11 is used to delineate the area of ​​the clean space, select the source devices that generate AMC within the area, collect AMC data at the source devices using mobile monitoring devices pre-deployed within the area, and configure the emission fingerprint of each source device based on the historical values ​​of the AMC data.

[0103] The distribution module 12 is used to read the real-time value from the AMC data from the mobile monitoring device, calculate the similarity between the real-time value and each emission fingerprint using the cosine similarity calculation formula, divide the similarity into several intervals, each interval corresponding to a movement speed, integrate the intervals and movement speeds to generate a lookup table, and distribute it to the mobile monitoring device.

[0104] The recording module 13 is used to define an abnormal device based on the similarity, collect gas samples at the location of the abnormal device using a sampling device pre-integrated in the mobile monitoring device, and record the attribute data.

[0105] The update module 14 is used to obtain the movement path of the mobile monitoring device, define the movement path between two adjacent source devices as segments, select several calibration points from each segment, collect AMC data at the calibration point when the mobile monitoring device reaches the calibration point, define it as background noise, use the background noise to offset the emission fingerprint, update the abnormal device, and send it to the preset terminal.

[0106] Figure 7 This diagram illustrates the structural composition of the cleanroom AMC pollution source analysis system provided in an embodiment of the present invention. The configuration module 11 includes:

[0107] The annotation unit 111 is used to draw a planar distribution map within the area and to annotate the source device on the planar distribution map;

[0108] Setting unit 112 is used to set the propagation factors within the area, wherein the propagation factors include at least: location, wind direction and exhaust path, and to generate a pollution propagation map using the propagation factors and the plan distribution map;

[0109] The positioning unit 113 is used to locate the position of each source device, connect all the positions using the nearest neighbor algorithm, generate a movement path, and send it to the movement monitoring device.

[0110] Create unit 114 to set the type of abnormal device and create emergency response rules that correspond one-to-one with the type.

[0111] Figure 8 This diagram illustrates the structural composition of the cleanroom AMC pollution source analysis system provided in an embodiment of the present invention. The distribution module 12 includes:

[0112] Insertion unit 121 is used to select abnormal points within the area and dynamically update them, inserting the updated abnormal points into the movement path.

[0113] The acquisition unit 122 is used to acquire the readings of multi-source devices within the area and define the readings of multi-source devices and mobile monitoring devices as real-time values.

[0114] Activation unit 123 is used to configure the risk level corresponding to each interval. When the risk level is greater than the threshold, the pre-edited purification plan is activated.

[0115] Open unit 124 is used to integrate all purification solutions, generate a solution set, and grant the preset terminal the right to adjust the solution set.

[0116] Figure 9 This diagram illustrates the structural composition of the cleanroom AMC pollution source analysis system provided in an embodiment of the present invention. The recording module 13 includes:

[0117] The sorting unit 131 is used to sort all source devices in descending order of similarity to generate a queue;

[0118] The selection unit 132 is used to select a preset number of source devices from the front of the queue and define them as abnormal devices.

[0119] Figure 10 This diagram illustrates the structural composition of the cleanroom AMC pollution source analysis system provided in an embodiment of the present invention. The update module 14 includes:

[0120] The statistics unit 141 is used to count the number of times each abnormal device appears and adjust the movement path accordingly;

[0121] The correction unit 142 is used to determine the diffusion trend of AMC via the exhaust path, select a stable point, define the AMC data at the stable point as global noise, and correct the real-time value.

[0122] The configuration module 11 is mainly used to complete step S100, the distribution module 12 is mainly used to complete step S200, the recording module 13 is mainly used to complete step S300, and the update module 14 is mainly used to complete step S400.

[0123] The annotation unit 111 is mainly used to complete step S101, the setting unit 112 is mainly used to complete step S102, the positioning unit 113 is mainly used to complete step S103, and the creation unit 114 is mainly used to complete step S104.

[0124] The insertion unit 121 is mainly used to complete step S201, the acquisition unit 122 is mainly used to complete step S202, the activation unit 123 is mainly used to complete step S203, and the opening unit 124 is mainly used to complete step S204.

[0125] The sorting unit 131 is mainly used to complete step S301, and the selection unit 132 is mainly used to complete step S302.

[0126] The statistical unit 141 is mainly used to complete step S401, and the correction unit 142 is mainly used to complete step S402.

[0127] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0129] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing pollution sources in cleanroom ambient temperature monitoring (AMC), characterized in that, The method includes: Define the area of ​​the clean space, select the source devices that generate AMC within the area, collect AMC data at the source devices using mobile monitoring devices pre-deployed within the area, and configure the emission fingerprint of each source device based on the historical values ​​of the AMC data. The real-time value in the AMC data is read, and the similarity between the real-time value and each emission fingerprint is calculated using the cosine similarity calculation formula. The similarity is divided into several intervals, each of which corresponds to a movement speed. The intervals and movement speeds are integrated to generate a comparison table, which is then sent to the motion monitoring device. Based on the similarity, anomalous devices are defined. Using a sampling device pre-integrated into the mobile monitoring device, gas samples are collected from the anomalous devices, and attribute data is recorded. The movement path of the mobile monitoring device is obtained, and the movement path between two adjacent source devices is defined as a segment. Several calibration points are selected from each segment. When the mobile monitoring device reaches the calibration point, the AMC data at the calibration point is collected and defined as background noise. The background noise is used to offset the emission fingerprint, update the abnormal device, and send it to the preset terminal. The steps of defining the area of ​​the clean space and selecting the source equipment that generates AMC within the area include: Draw a planar distribution map within the area, and mark the source device on the planar distribution map; Set up the propagation factors within the area, wherein the propagation factors include at least: location, wind direction and exhaust path, and generate a pollution propagation map using the propagation factors and the planar distribution map; The step of collecting AMC data from the source device using a mobile monitoring device pre-deployed within the area includes: The location of each source device is located, and the nearest neighbor algorithm is used to connect all the locations to generate a movement path, which is then sent to the motion monitoring device. Set the type of abnormal device and create emergency response rules that correspond one-to-one with the type; The step of defining anomalous devices based on the similarity includes: Sort all source devices in descending order of similarity to generate a queue; Select a preset number of source devices from the front of the queue and define them as abnormal devices; The step of using the background noise to offset the real-time value, update the abnormal device, and send it to the preset terminal includes: The frequency of occurrence of each abnormal device was counted, and the movement path was adjusted accordingly; The diffusion trend of AMC is determined through the exhaust path, a stable point is selected, and the AMC data at the stable point is defined as global noise, and the real-time value is corrected.

2. The cleanroom AMC pollution source analysis method according to claim 1, characterized in that, The steps for reading real-time values ​​from AMC data include: Select the abnormal points within the area and update them dynamically, then insert the updated abnormal points into the movement path. Acquire readings from multiple sources within the area and define the readings from these sources and mobile monitoring devices as real-time values.

3. The clean space AMC pollution source analysis method according to claim 1, characterized in that, The step of dividing the similarity into several intervals includes: Configure the risk level corresponding to each interval, and activate the pre-edited purification plan when the risk level is greater than the threshold. Integrate all purification solutions, generate a solution set, and grant the preset terminals the right to adjust the solution set.

4. A cleanroom AMC pollution source analysis system, characterized in that, The system is used to implement the method as described in any one of claims 1 to 3, the system comprising: The configuration module is used to delineate the area of ​​the clean space, select the source devices that generate AMC within the area, collect AMC data at the source devices using mobile monitoring devices pre-deployed within the area, and configure the emission fingerprint of each source device based on the historical values ​​of the AMC data. The distribution module is used to read the real-time values ​​in the AMC data, calculate the similarity between the real-time values ​​and each emission fingerprint using the cosine similarity calculation formula, divide the similarity into several intervals, each interval corresponding to a movement speed, integrate the intervals and movement speeds to generate a lookup table, and distribute it to the motion monitoring device. The recording module is used to define abnormal devices based on the similarity, collect gas samples from the abnormal devices using a sampling device pre-integrated in the mobile monitoring device, and record the attribute data. The update module is used to obtain the movement path of the mobile monitoring device, define the movement path between two adjacent source devices as segments, select several calibration points from each segment, and collect AMC data at the calibration point when the mobile monitoring device reaches the calibration point, define it as background noise, use the background noise to offset the emission fingerprint, update the abnormal device, and send it to the preset terminal.

5. The clean space AMC pollution source analysis system according to claim 4, characterized in that, The configuration module includes: The annotation unit is used to draw a planar distribution map within the area and to annotate the source device onto the planar distribution map; The setting unit is used to set the propagation factors within the area, wherein the propagation factors include at least: location, wind direction and exhaust path, and a pollution propagation map is generated using the propagation factors and the planar distribution map; The positioning unit is used to locate the position of each source device, connect all the positions using the nearest neighbor algorithm, generate a movement path, and send it to the movement monitoring device. Create a unit to set the type of abnormal device and create emergency response rules that correspond one-to-one with the type.

6. The clean space AMC pollution source analysis system according to claim 5, characterized in that, The distribution module includes: The insertion unit is used to select abnormal points within the area and dynamically update them, inserting the updated abnormal points into the movement path. The acquisition unit is used to acquire the readings of multi-source devices within the area and define the readings of multi-source devices and mobile monitoring devices as real-time values. The activation unit is used to configure the risk level corresponding to each interval. When the risk level is greater than the threshold, the pre-edited purification plan is activated. The open unit is used to integrate all purification solutions, generate a solution set, and grant the preset terminals the right to adjust the solution set.

Images