A pollutant source tracing method based on fresh air system filtration efficiency
By obtaining the differences between historical data and fresh air system and performing two-dimensional processing, the problem of limited traceability range of pollutants in non-clean rooms in the chip production workshop is solved, and the two-way traceability of the clean room and the outside is realized, and the traceability range and accuracy are expanded. Spend.
Patent Information
- Application Number
- CN202411276124.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-12
AI Technical Summary
The prior art is difficult to effectively monitor and trace pollutants in the non-clean room area of the chip production workshop, resulting in limited traceability range and cannot be effectively expanded to areas where AMC monitors are not installed.
By obtaining historical visitor data and pollution data, predicting access tables and pollution exchange volumes, combining the input and output differences of fresh air system, counting the filter efficiency of the filter, performing two-dimensional processing, performing two-way traceability process, and expanding the traceability range.
Two-way traceability of the clean room and the outside of the clean room has been realized, greatly expanding the scope of pollution monitoring, and improving the accuracy and coverage of traceability.
Smart Images

Figure CN118794120B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of clean room pollution source tracing, and in particular to a pollutant source tracing method based on the filtering efficiency of a fresh air system. Background Art
[0002] In the chip manufacturing workshop, there will be a clean room with a fresh air system between the clean room and the workshop. The pollutant requirements inside the clean room are very high. Once pollutants appear, they need to be traced. Most of the existing traceability solutions use AMC monitors installed inside the clean room to monitor pollutants and directly determine which areas have pollutants. This method is feasible, but it can only monitor areas where AMC monitors have been installed. The traceability accuracy is high, but the traceability range is small.
[0003] The inclusion relationship between the chip manufacturing workshop and the clean room. For the non-clean room area in the chip manufacturing workshop, under the condition of certain cost, the existing technology does not perform AMC monitoring, and only installs AMC monitors inside the clean room. How to expand the pollution monitoring scope, perform pollution monitoring on the non-clean room area in the chip manufacturing workshop, that is, the area where the AMC monitor is not installed, and optimize the existing pollution tracing process are the technical problems that the technical solution of the present invention wants to solve. Summary of the invention
[0004] The purpose of the present invention is to provide a pollutant source tracing method based on the filtration efficiency of a fresh air system to solve the problems raised in the above background technology.
[0005] To achieve the above object, the present invention provides the following technical solutions:
[0006] A pollutant source tracing method based on fresh air system filtration efficiency, the method comprising:
[0007] Acquire historical visitor data, and determine a predicted visit table based on the historical visitor data;
[0008] Obtain historical pollution data, determine pollution information at each time of the day based on the historical pollution data, and determine the pollution exchange amount based on the pollution information and the predicted access table;
[0009] Regularly obtain the difference between the input and output of the fresh air system, and determine the filtration efficiency of each filter in the fresh air system according to the difference;
[0010] Count the filtration efficiency of each filter in the fresh air system, and perform two-dimensional processing on the pollutant type and concentration at each filter based on the filtration efficiency;
[0011] The traceability process is performed based on the two-dimensional processing results.
[0012] As a further solution of the present invention: the step of obtaining historical visitor data and determining a predicted visit table according to the historical visitor data comprises:
[0013] Generate an anniversary table containing a label; the granularity of the anniversary table is day, and the label contains an assignment port;
[0014] Assigning values to labels of each element in the annual table according to preset holiday data; wherein, there are at least two types of assignments, which are used to distinguish between working days and rest days;
[0015] Obtain historical visitor data based on the assigned anniversary table and generate / update the predicted visit table.
[0016] As a further solution of the present invention: the step of acquiring historical visitor data based on the assigned anniversary table and generating / updating the predicted visit table includes:
[0017] Reading a plurality of anniversary tables, and determining a standard anniversary table according to characteristic values in the anniversary tables; wherein the step of obtaining the characteristic values comprises: calculating the number of different values in the anniversary table after value assignment, and arranging the different values in ascending order according to the number to obtain a value group; extracting at least one header data in the value group, wherein the header data is the characteristic value;
[0018] Obtain daily visitor data for one year, and insert the daily visitor data into the assigned anniversary table to obtain the to-be-checked anniversary table;
[0019] Folding the inspection-to-be-inspected anniversary table based on the standard anniversary table to obtain a finished product sub-table;
[0020] The finished product sub-table is counted to determine the predicted access table.
[0021] As a further solution of the present invention: the steps of obtaining historical pollution data, determining pollution information at each time of the day according to the historical pollution data, and determining the pollution exchange amount based on the pollution information and the predicted access table include:
[0022] Obtain the historical pollution data of the previous day, perform statistical processing on the historical pollution data, and obtain the change function of the historical pollution data within one day;
[0023] For any date, query the number of exchanges on that day according to the predicted access table;
[0024] In one day, the number of exchanges is allocated to determine the number of exchanges in each time period, and the pollution exchange amount is determined based on the allocated number of exchanges and the pollution information at the corresponding time.
[0025] As a further solution of the present invention: the step of obtaining the historical pollution data of the previous day, performing statistical processing on the historical pollution data, and obtaining a change function of the historical pollution data in one day comprises:
[0026] Receiving a time span set by a staff member, and obtaining pollution data within the time span as historical pollution data; the component unit of the time span is day;
[0027] Under the preset step length, the historical pollution data at each moment is aligned, and the historical pollution data at each moment is averaged to obtain the pollution data at each moment;
[0028] Arrange the pollution data at each moment and fit the change function within a day;
[0029] The step length is in minutes.
[0030] As a further solution of the present invention: the steps of allocating the number of exchanges within a day, determining the number of exchanges in each time period, and determining the pollution exchange amount based on the allocated number of exchanges and the pollution information at the corresponding time include:
[0031] Obtaining a work time plan, and determining the access probability of each time period based on the work time plan;
[0032] Allocating the number of exchanges based on the access probability to obtain the number of exchanges in each time period;
[0033] Based on the change function, the pollution information of each time period is queried, the pollution information is accumulated according to the number of exchanges, and the pollution exchange amount is determined.
[0034] As a further solution of the present invention: the step of regularly obtaining the difference between the input and output of the fresh air system and determining the filtration efficiency of each filter in the fresh air system according to the difference:
[0035] Get input based on the detector at the entrance of the fresh air system;
[0036] Obtain output based on the detector at the outlet of the fresh air system;
[0037] comparing the output with the input and calculating a difference;
[0038] determining the filtration efficiency of each filter according to the difference;
[0039] The input, output and difference are all arrays of the same dimension, and each element corresponds to a filter.
[0040] As a further solution of the present invention: the step of calculating the filtering efficiency of each filter in the fresh air system and performing two-dimensional processing on the pollutant type and concentration at each filter based on the filtering efficiency includes:
[0041] Count the filtration efficiency of each filter in the fresh air system and compare the filtration efficiency with the preset standard efficiency;
[0042] When the filtration efficiency does not reach a preset standard efficiency, reading the input and output of the filter;
[0043] The input and output are identified, outliers are selected, and the outliers are processed in two dimensions.
[0044] As a further solution of the present invention: the steps of identifying the input and output, selecting abnormal values, and performing two-dimensional processing on the abnormal values include:
[0045] Comparing the output with a preset standard threshold, and when the output exceeds the preset standard threshold, treating the output as an abnormal value;
[0046] When the output does not reach a preset standard threshold, the input is regarded as an abnormal value;
[0047] Convert outliers to color values and fill them into a two-dimensional graph.
[0048] As a further solution of the present invention: the step of performing the traceability process based on the two-dimensional processing result includes:
[0049] When the abnormal value is output, trace it back to the clean room;
[0050] When an abnormal value is input, trace it back to the outside of the clean room;
[0051] During the tracing process, the two-dimensional image is fuzzified, and the color value of each point after the fuzzification process is divided into regions to obtain the contaminated area.
[0052] Compared with the prior art, the present invention has the following beneficial effects:
[0053] The present invention provides a two-way traceability process, which takes the filtering efficiency of the fresh air system as a benchmark and combines the input and output of the fresh air system to simultaneously trace the clean room and the outside of the clean room, greatly expanding the traceability range. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.
[0055] Figure 1 The overall flow chart of the pollutant source tracing method based on the filtration efficiency of the fresh air system is shown. DETAILED DESCRIPTION
[0056] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0057] Figure 1 The overall flow chart of the pollutant source tracing method based on the filtration efficiency of the fresh air system is as follows. In an embodiment of the present invention, a pollutant source tracing method based on the filtration efficiency of the fresh air system includes:
[0058] Step S100: Acquire historical visitor data, and determine a predicted visit table according to the historical visitor data;
[0059] The clean room involved in the present invention is inside the workshop and belongs to an area within the workshop. A fresh air system is installed between the clean room and the workshop. In actual applications, the air quality in the workshop itself is relatively high. After passing through the high-precision fresh air system, the air quality inside the clean room can be further improved; for the workshop, the internal connection with the outside world is generally through air conditioning equipment, including air conditioning and filtered air vents (which can be understood as a low-precision fresh air system for connecting the workshop with the outside world). Under normal circumstances, the air quality in the workshop is higher than that of the outside world, but when there are people entering and exiting the workshop, there will be air exchange between the workshop and the outside world. Therefore, this application needs to count historical visitor data, and the historical visitor data is used to represent the process of people visiting the workshop.
[0060] Furthermore, the step of obtaining historical visitor data and determining a predicted visit table according to the historical visitor data includes:
[0061] Generate an anniversary table containing a label; the granularity of the anniversary table is day, and the label contains an assignment port;
[0062] Assigning values to labels of each element in the annual table according to preset holiday data; wherein, there are at least two types of assignments, which are used to distinguish between working days and rest days;
[0063] Obtain historical visitor data based on the assigned anniversary table and generate / update the predicted visit table.
[0064] Generate an anniversary table, which can be understood as a calendar with labels, each label can be assigned a value; there can be many types of assignments, but they are limited, the main purpose is to distinguish various holidays, such as Dragon Boat Festival, Mid-Autumn Festival, Labor Day, National Day or Spring Festival. Assign values to these holidays according to the length of the holiday. It is worth mentioning that the values of weekends and weekdays are the most basic values. Then, based on the calendar with the assigned labels, obtain the historical visitor data of the year.
[0065] The step of acquiring historical visitor data based on the assigned anniversary table and generating / updating the predicted visit table includes:
[0066] Reading a plurality of anniversary tables, and determining a standard anniversary table according to characteristic values in the anniversary tables; wherein the step of obtaining the characteristic values comprises: calculating the number of different values in the anniversary table after value assignment, and arranging the different values in ascending order according to the number to obtain a value group; extracting at least one header data in the value group, wherein the header data is the characteristic value;
[0067] Obtain daily visitor data for one year, and insert the daily visitor data into the assigned anniversary table to obtain the to-be-checked anniversary table;
[0068] Folding the inspection-to-be-inspected anniversary table based on the standard anniversary table to obtain a finished product sub-table;
[0069] The finished product sub-table is counted to determine the predicted access table.
[0070] The holiday situation is different every year. Specifically, starting from New Year's Day, National Day is fixed, but the time of other holidays in between is deviated. Therefore, the historical visitor data of different years cannot be directly calculated. Therefore, before the calculation, a standard anniversary table is determined based on the anniversary tables of different years. The standard anniversary table can be an average anniversary table determined by multiple anniversary tables, or any anniversary table can be directly used as the standard anniversary table. Then, the anniversary table to be checked is folded according to the standard anniversary table. This step needs to be explained. For example, the standard anniversary table has New Year's Day at position 0, and then Qingming Festival at position 26%, while the anniversary table to be checked has New Year's Day at position 0, and then Qingming Festival at position 27%. Then, the historical visitor data from 0 to 27% in the anniversary table to be checked needs to be folded to 26%. It is worth mentioning that the folding multiple can also be a value less than 1. In layman's terms, the folding includes magnification.
[0071] In addition, the finished product sub-table is just an artificially defined concept, which is used to refer to the folded annual table to be inspected. The reason for defining it as a sub-table is that it is only the annual table to be inspected for one year. The annual tables to be inspected in different years are counted to determine the predicted access table.
[0072] Step S200: Obtain historical pollution data, determine pollution information at each time of the day according to the historical pollution data, and determine the pollution exchange amount based on the pollution information and the predicted access table;
[0073] Obtain historical pollution data. The historical pollution data is the external pollution parameters, which are different at different times. It can be obtained with the help of existing weather services, such as PM2.5 values. These are all regular weather forecast contents. If users need to obtain more types of pollution data, monitors can be set up around the workshop to obtain different types of pollution data.
[0074] Furthermore, the steps of obtaining historical pollution data, determining pollution information at each time of the day according to the historical pollution data, and determining the pollution exchange amount based on the pollution information and the predicted access table include:
[0075] Obtain the historical pollution data of the previous day, perform statistical processing on the historical pollution data, and obtain the change function of the historical pollution data within one day;
[0076] For any date, query the number of exchanges on that day according to the predicted access table;
[0077] In one day, the number of exchanges is allocated to determine the number of exchanges in each time period, and the pollution exchange amount is determined based on the allocated number of exchanges and the pollution information at the corresponding time.
[0078] Pollution data is generally stable. The historical pollution data of the previous day can be obtained as the predicted pollution data for the day. The number of exchanges for the day can be queried in the predicted access table (the number of exchanges is determined by the number of people visiting). The number of exchanges is random and is allocated on the same day. During the allocation process, a time period (generally in hours) is randomly selected within the 24 hours of the day as the time period for the number of exchanges to fall into. When the number of exchanges is randomly selected, the allocation is completed. It is worth mentioning that, combined with the nature of the work, the allocation process is generally carried out during the day, such as 8 am to 8 pm.
[0079] After the allocation is completed, you can get the number of visits in each time period (hour), and query the pollution information at the corresponding time to calculate the pollution exchange amount; the calculation process is very simple, and the relationship between the single pollution exchange amount and the pollution information is set in advance. The pollution exchange amount and the pollution information (which can be understood as the pollution concentration) are generally proportional. The higher the pollution concentration, the greater the pollution exchange amount. Then, multiply the number of times by the single exchange amount, and then accumulate all time periods to get the pollution exchange amount of the day.
[0080] Furthermore, the step of obtaining the historical pollution data of the previous day, performing statistical processing on the historical pollution data, and obtaining a change function of the historical pollution data in one day includes:
[0081] Receiving a time span set by a staff member, and obtaining pollution data within the time span as historical pollution data; the component unit of the time span is day;
[0082] Under the preset step length, the historical pollution data at each moment is aligned, and the historical pollution data at each moment is averaged to obtain the pollution data at each moment;
[0083] Arrange the pollution data at each moment and fit the change function within a day;
[0084] The step length is in minutes.
[0085] In a preferred embodiment of the technical solution of the present invention, a new solution for determining the pollution information at each moment in a day is provided. The original solution is to use the pollution information of the previous day as the pollution information of the day. The accuracy of this method is not very high. For this, the present application first receives the time span set by the staff, such as a week, and obtains the pollution data within a week as the historical pollution data; then, under a preset step size, the historical pollution data of each moment is aligned, and the step size is in minutes. An actual example of the alignment process is that for each moment (8:00, 8:01 and 8:02, etc.), all the pollution data at the same moment in a week are taken as a group, and then the mean is calculated as the pollution data at each moment; finally, the change of the pollution data within a day is fitted to obtain a change function as the change function of the day. This change function has higher accuracy and is determined based on the pollution data of a week (longer or shorter), which is more in line with the actual situation, and prevents the difference in pollution data caused by the situation that the previous day is rainy and the next day is sunny.
[0086] Furthermore, the steps of allocating the number of exchanges within a day, determining the number of exchanges in each time period, and determining the pollution exchange amount based on the allocated number of exchanges and the pollution information at the corresponding time include:
[0087] Obtaining a work time plan, and determining the access probability of each time period based on the work time plan;
[0088] Allocating the number of exchanges based on the access probability to obtain the number of exchanges in each time period;
[0089] Based on the change function, the pollution information of each time period is queried, the pollution information is accumulated according to the number of exchanges, and the pollution exchange amount is determined.
[0090] The allocation process provided by the original scheme is to perform random allocation with the same probability. In a preferred embodiment of the technical scheme of the present invention, the allocation process of the number of exchanges is limited, and a work time plan is obtained. The access probability of each time period is determined based on the work time plan. The work time plan indicates the time from working time to time in the workshop and the time from rest time to time. The access probability of working time is set larger, and the access probability of rest time is set smaller. The number of exchanges is allocated based on the access probability, which is more in line with the actual situation.
[0091] Step S300: regularly obtaining the difference between the input and output of the fresh air system, and determining the filtration efficiency of each filter in the fresh air system according to the difference;
[0092] The fresh air system in step S300 is a fresh air system between the workshop and the clean room. Since its main function is to filter the pollution inside the workshop, the input is regarded as the air in the workshop and the output is regarded as the air in the clean room (in fact, the ventilation process is a cyclic process). By comparing the input and output, the filtration efficiency of the fresh air system can be obtained.
[0093] This application is applied to AMC filtration scenarios. There are many types of AMC pollutants, and each pollutant corresponds to an independent filter. Therefore, according to the filtration conditions of different AMC pollutants, what is actually determined is the filtration efficiency of each filter in the fresh air system.
[0094] Specifically, the step of periodically obtaining the difference between the input and output of the fresh air system and determining the filtration efficiency of each filter in the fresh air system according to the difference is as follows:
[0095] Get input based on the detector at the entrance of the fresh air system;
[0096] Obtain output based on the detector at the outlet of the fresh air system;
[0097] comparing the output with the input and calculating a difference;
[0098] determining the filtration efficiency of each filter according to the difference;
[0099] The input, output and difference are all arrays of the same dimension, and each element corresponds to a filter.
[0100] The input is obtained based on the detector at the entrance of the fresh air system (corresponding to the workshop), and the output is obtained based on the detector at the exit of the fresh air system (corresponding to the clean room). The output is compared with the input, the difference is calculated, and the filtration efficiency is determined according to the difference. Since the detector is pointed to different pollutants, the input and output obtained by the detector correspond to a certain pollutant, and the calculated difference also points to the corresponding pollutant, and the calculated filtration efficiency is also the filtration efficiency of the corresponding pollutant. All inputs correspond to the inputs of all pollutants, all outputs correspond to the outputs of all pollutants, and all filtration efficiencies correspond to the efficiencies of all pollutants. Therefore, they are all represented in the form of an array.
[0101] Step S400: Counting the filtration efficiency of each filter in the fresh air system, and performing two-dimensional processing on the pollutant type and concentration at each filter based on the filtration efficiency;
[0102] After the filtration efficiency of the filter is determined, it is necessary to trace the source of pollution. The present application provides a two-dimensional tracing solution, which obtains a workshop map including the clean room as a plan view, and then inserts the pollutant type and its concentration at each filter into the corresponding position for two-dimensionalization to obtain a map reflecting the filtration process.
[0103] Furthermore, the step of calculating the filtering efficiency of each filter in the fresh air system and performing two-dimensional processing on the pollutant type and concentration at each filter based on the filtering efficiency includes:
[0104] Count the filtration efficiency of each filter in the fresh air system and compare the filtration efficiency with the preset standard efficiency;
[0105] When the filtration efficiency does not reach a preset standard efficiency, reading the input and output of the filter;
[0106] The input and output are identified, outliers are selected, and the outliers are processed in two dimensions.
[0107] For each filter, obtain its filtration efficiency, and compare the filtration efficiency with the preset standard efficiency. When the filtration efficiency reaches the preset standard efficiency, it means that the filtration process is normal. At this time, it is considered that there is no problem and there is no need to trace the problem. When the filtration efficiency does not reach the preset standard efficiency, it is considered that there is a problem and it is necessary to trace the source. The tracing method is to read the input and output of the filter, identify the input and output, select abnormal values, and perform two-dimensional processing on the abnormal values.
[0108] Among them, the abnormal value is to choose one between the input and the output, judging whether the input is in an abnormal state or the output is in an abnormal state, and then selecting the input or output as the abnormal value.
[0109] Specifically, the positions of input and output in the plane diagram are different, corresponding to the inlet and outlet of the filter respectively. When performing two-dimensional processing based on outliers, the corresponding point position is first determined based on whether the outlier is input or output, and then two-dimensional processing is performed based on the size of the outlier.
[0110] In an example of the technical solution of the present invention, the steps of identifying the input and output, selecting abnormal values, and performing two-dimensional processing on the abnormal values include:
[0111] Comparing the output with a preset standard threshold, and when the output exceeds the preset standard threshold, treating the output as an abnormal value;
[0112] When the output does not reach a preset standard threshold, the input is regarded as an abnormal value;
[0113] Convert outliers to color values and fill them into a two-dimensional graph.
[0114] The output is compared with the preset standard threshold. When the output is large enough, it means that the air quality in the clean room does not meet the standard. At this time, the output is taken as an abnormal value. When the output is small, the filtration efficiency should be high in theory. When the filtration efficiency is also low, it means that there may be some problems with the input. At this time, the input is selected as an abnormal value, and then the abnormal value is converted into a color value and filled into the corresponding position.
[0115] The selection process of the above outliers is further explained as follows:
[0116] ; In the formula, Indicates efficiency, It represents the ratio of output to input. yes The decreasing function of Indicates the output, Represents the input; if the efficiency is low and the output is high, this is easy to understand because the efficiency is inversely proportional to the output. If the efficiency is low and the output is also low, then the input must be smaller, which means that the outside of the clean room does not match the normal situation, marking the input as abnormal.
[0117] In fact, the calculation process of filtration efficiency itself is not complicated. This is the most common solution. Indicates efficiency, Indicates the output, Represents input.
[0118] Step S500: performing a traceability process based on the two-dimensional processing result;
[0119] After the two-dimensional processing is completed, the traceability process can be performed according to the two-dimensional processing results.
[0120] The step of performing the traceability process based on the two-dimensional processing result includes:
[0121] When the abnormal value is output, trace it back to the clean room;
[0122] When an abnormal value is input, trace it back to the outside of the clean room;
[0123] During the tracing process, the two-dimensional image is fuzzified, and the color value of each point after the fuzzification process is divided into regions to obtain the contaminated area.
[0124] The output corresponds to the clean room. Therefore, when the abnormal value is the output, it is traced back to the clean room. The input corresponds to the outside of the clean room and the inside of the workshop. Therefore, it is traced back to the outside of the clean room. The traceability process adopts the simplest solution, which is fuzzy processing based on the abnormal value. Fuzzy processing is a common image processing method, which can be compared to the blending process. A value is set at the abnormal position and then the value is blended to other positions. Each filter corresponds to an abnormal position. On the basis of determining the blending direction, all the fuzzy results are superimposed to obtain the final image reflecting the pollution situation. The contour of the final image is recognized, and the contaminated area can be determined based on the abnormal value.
[0125] It is worth mentioning that the blurring process can be compared with the existing image processing software. For conventional brush tools, size and hardness are two basic parameters. Hardness is similar to the blurring process. The smaller the hardness, the higher the degree of blurring. Specifically, the parameters of the blurring process of this application are determined by the staff according to the specific situation. In addition to the size and blurring method, the blurring direction is also limited. That is, for a certain pixel point with a value, it is only diffused in the direction of the clean room or the outside world; in fact, the essence of the blurring process is to calculate the value of the point at the non-abnormal position. The greater the distance between the point and the abnormal position, the smaller the value. For any point, a corresponding value can be calculated for each abnormal position, and the value at the point is added to obtain the final value for evaluating the degree of contamination. In the contour recognition process, it is easy to identify it, and the points whose final values are greater than the preset threshold are connected as the contaminated area obtained by tracing.
[0126] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.
[0127] Finally, it should be noted that the pollutant source tracing method based on the filtration efficiency of the fresh air system disclosed in the embodiment of the present invention discloses only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions recorded in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims
1. A pollutant source tracing method based on the filtration efficiency of a fresh air system, characterized in that: The method comprises: Acquire historical visitor data, and determine a predicted visit table based on the historical visitor data; Obtain historical pollution data, determine pollution information at each time of the day based on the historical pollution data, and determine the pollution exchange amount based on the pollution information and the predicted access table; Regularly obtain the difference between the input and output of the fresh air system, and determine the filtration efficiency of each filter in the fresh air system according to the difference; Count the filtration efficiency of each filter in the fresh air system, and perform two-dimensional processing on the pollutant type and concentration at each filter based on the filtration efficiency; The traceability process is performed based on the two-dimensional processing results.
2. The pollutant source tracing method based on the filtration efficiency of the fresh air system according to claim 1 is characterized in that: The step of obtaining historical visitor data and determining a predicted visit table according to the historical visitor data comprises: Generate an anniversary table containing a label; the granularity of the anniversary table is day, and the label contains an assignment port; Assigning values to labels of each element in the annual table according to preset holiday data; wherein, there are at least two types of assignments, which are used to distinguish between working days and rest days; Obtain historical visitor data based on the assigned anniversary table and generate / update the predicted visit table.
3. The pollutant source tracing method based on the filtration efficiency of the fresh air system according to claim 2 is characterized in that: The step of acquiring historical visitor data based on the assigned anniversary table and generating / updating the predicted visit table includes: Reading a plurality of anniversary tables, and determining a standard anniversary table according to characteristic values in the anniversary tables; wherein the step of obtaining the characteristic values comprises: calculating the number of different values in the anniversary table after value assignment, and arranging the different values in ascending order according to the number to obtain a value group; extracting at least one header data in the value group, wherein the header data is the characteristic value; Obtain daily visitor data for one year, and insert the daily visitor data into the assigned anniversary table to obtain the to-be-checked anniversary table; Folding the inspection-to-be-inspected anniversary table based on the standard anniversary table to obtain a finished product sub-table; The finished product sub-table is counted to determine the predicted access table.
4. The pollutant source tracing method based on the filtration efficiency of the fresh air system according to claim 3 is characterized in that: The steps of obtaining historical pollution data, determining pollution information at each time of the day according to the historical pollution data, and determining the pollution exchange amount based on the pollution information and the predicted access table include: Obtain the historical pollution data of the previous day, perform statistical processing on the historical pollution data, and obtain the change function of the historical pollution data within one day; For any date, query the number of exchanges on that day according to the predicted access table; In one day, the number of exchanges is allocated to determine the number of exchanges in each time period, and the pollution exchange amount is determined based on the allocated number of exchanges and the pollution information at the corresponding time.
5. The pollutant source tracing method based on the filtration efficiency of the fresh air system according to claim 4 is characterized in that: The steps of obtaining the historical pollution data of the previous day, performing statistical processing on the historical pollution data, and obtaining a change function of the historical pollution data in one day include: Receiving a time span set by a staff member, and obtaining pollution data within the time span as historical pollution data; the component unit of the time span is day; Under the preset step length, the historical pollution data at each moment is aligned, and the historical pollution data at each moment is averaged to obtain the pollution data at each moment; Arrange the pollution data at each moment and fit the change function within a day; The step length is in minutes.
6. The pollutant source tracing method based on the filtration efficiency of the fresh air system according to claim 4 is characterized in that: The steps of allocating the number of exchanges within a day, determining the number of exchanges in each time period, and determining the pollution exchange amount based on the allocated number of exchanges and the pollution information at the corresponding time include: Obtaining a work time plan, and determining the access probability of each time period based on the work time plan; Allocating the number of exchanges based on the access probability to obtain the number of exchanges in each time period; Based on the change function, the pollution information of each time period is queried, the pollution information is accumulated according to the number of exchanges, and the pollution exchange amount is determined.
7. The pollutant source tracing method based on fresh air system filtration efficiency according to claim 4 is characterized in that: The step of regularly obtaining the difference between the input and output of the fresh air system and determining the filtration efficiency of each filter in the fresh air system according to the difference: Get input based on the detector at the entrance of the fresh air system; Obtain output based on the detector at the outlet of the fresh air system; comparing the output with the input and calculating a difference; determining the filtration efficiency of each filter according to the difference; The input, output and difference are all arrays of the same dimension, and each element corresponds to a filter.
8. The pollutant source tracing method based on the filtration efficiency of the fresh air system according to claim 7 is characterized in that: The step of counting the filtration efficiency of each filter in the fresh air system and performing two-dimensional processing on the pollutant type and concentration at each filter based on the filtration efficiency includes: Count the filtration efficiency of each filter in the fresh air system and compare the filtration efficiency with the preset standard efficiency; When the filtration efficiency does not reach a preset standard efficiency, reading the input and output of the filter; The input and output are identified, outliers are selected, and the outliers are processed in two dimensions.
9. The pollutant source tracing method based on fresh air system filtration efficiency according to claim 8 is characterized in that: The steps of identifying the input and output, selecting abnormal values, and performing two-dimensional processing on the abnormal values include: Comparing the output with a preset standard threshold, and when the output exceeds the preset standard threshold, treating the output as an abnormal value; When the output does not reach a preset standard threshold, the input is regarded as an abnormal value; Convert outliers to color values and fill them into a two-dimensional graph.
10. The pollutant source tracing method based on fresh air system filtration efficiency according to claim 9 is characterized in that: The step of performing the traceability process based on the two-dimensional processing result includes: When the abnormal value is output, trace it back to the clean room; When an abnormal value is input, trace it back to the outside of the clean room; During the tracing process, the two-dimensional image is fuzzified, and the color value of each point after the fuzzification process is divided into regions to obtain the contaminated area.
