Workshop pollutant distribution discrimination and pollutant discharge method
By constructing a pollutant distribution model of the workshop and extracting characteristics, the pollutant concentration is predicted, and the problem of inaccurate identification of pollutant distribution in the workshop is solved, and refined pollutant emission control is achieved.
Patent Information
- Application Number
- CN202510256111.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-05
- Publication Date
- 2025-06-27
AI Technical Summary
The prior art cannot accurately determine the distribution of pollutants in the workshop, making it difficult to objectively control the timing of pollutants emissions.
By constructing a pollutant distribution model based on real-time data, the spatial and time series characteristics of pollutants are extracted, the pollutant concentration is predicted, and whether pollutant emissions are performed based on the predicted concentration is determined.
Accurate judgment of pollutant distribution in the workshop and refined emission control are achieved, and misjudgment and misjudgment of pollutants caused by subjective empirical judgments in traditional technology are avoided.
Smart Images
Figure CN120217037A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of pollutant treatment, and particularly to a method for discriminating the distribution of pollutants in a workshop and discharging pollutants. Background Art
[0002] With the rapid development of industrialization, the production processes involved in factory workshops are becoming increasingly complex. Therefore, how to discriminate and discharge the pollutants generated during the production operations of factory workshops has become one of the important research directions in the industry.
[0003] Traditional methods mainly rely on the experience of technicians to discriminate and monitor the pollutant distribution in factory workshops. Although this traditional method has improved the efficiency of discriminating the pollutant distribution in factory workshops to a certain extent, thereby indirectly improving the production efficiency of factory workshops, there is uncertainty in the accuracy of discriminating the pollutant distribution. Therefore, it is difficult to objectively control the timing of pollutant discharge. Based on this, there is an urgent need in the industry for a method that can accurately discriminate the pollutant distribution in the workshop to control the timing of pollutant discharge. Summary of the Invention
[0004] The main purpose of the present application is to provide a method for discriminating the distribution of pollutants in a workshop and discharging pollutants, aiming to solve the technical problem that the prior art cannot accurately discriminate the pollutant distribution in the workshop to control the timing of pollutant discharge.
[0005] To achieve the above object, the present application provides a method for discriminating the distribution of pollutants in a workshop and discharging pollutants, and the method includes the following steps:
[0006] Construct a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop;
[0007] Extract the spatial features and time series features corresponding to the pollutants from the pollutant distribution model;
[0008] Determine the predicted pollutant concentration of the target workshop based on the spatial features and the time series features;
[0009] Judge whether to discharge pollutants from the target workshop according to the predicted pollutant concentration.
[0010] In one embodiment, the real-time data includes real-time image data and real-time sensor data, and the step of constructing a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop includes:
[0011] Collect the real-time image data and real-time sensor data of the target workshop, and preprocess the real-time image data to obtain processed image data;
[0012] Construct a pollutant distribution model corresponding to the target workshop based on the processed image data and the real-time sensor data.
[0013] In one embodiment, the step of preprocessing the real-time image data to obtain processed image data includes:
[0014] Perform denoising processing, edge detection, and grayscale processing on the real-time image data to obtain first image data;
[0015] Perform semantic segmentation processing on the pollutant area in the real-time image data to obtain second image data;
[0016] Perform object detection on the real-time image data based on the second image data to obtain pollutant position coordinates and pollutant categories;
[0017] Mark the pollutant position coordinates and the pollutant categories into the first image data to obtain processed image data.
[0018] In one embodiment, the step of extracting spatial features and time series features corresponding to pollutants from the pollutant distribution model includes:
[0019] Use a convolutional neural network to extract spatial features corresponding to pollutants from the pollutant distribution model, where the spatial features include pollutant concentration, pollutant area, pollutant volume, and pollutant diffusion speed;
[0020] Use a recurrent neural network or a long short-term memory neural network to extract time series features corresponding to pollutants from the pollutant distribution model, where the time series features include pollutant growth rate and pollutant diffusion pattern.
[0021] In one embodiment, the step of determining whether to perform pollutant emissions on the target workshop according to the predicted pollutant concentration includes:
[0022] If it is determined that the predicted pollutant concentration is greater than a first preset threshold, perform pollutant emissions on the target workshop;
[0023] If it is determined that the predicted pollutant concentration is less than or equal to the first preset threshold, update the predicted pollutant concentration and continuously monitor the updated predicted pollutant concentration.
[0024] In one embodiment, the step of performing pollutant emissions on the target workshop includes:
[0025] Perform harmless treatment on the pollutants in the target workshop and monitor the pollutant emission concentration of the target workshop after the harmless treatment;
[0026] If the pollutant emission concentration is less than the second preset threshold, the pollutants after harmless treatment are discharged;
[0027] If the pollutant emission concentration is greater than or equal to the second preset threshold, the harmless treatment process is adjusted, and the pollutants in the target workshop are harmlessly treated according to the adjusted harmless treatment process.
[0028] In addition, to achieve the above object, the present application also proposes a workshop pollutant distribution discrimination and pollutant emission device, and the workshop pollutant distribution discrimination and pollutant emission device includes:
[0029] A model construction module, configured to construct a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop;
[0030] A feature extraction module, configured to extract the spatial features and time series features corresponding to the pollutants from the pollutant distribution model;
[0031] A concentration prediction module, configured to determine the predicted pollutant concentration of the target workshop based on the spatial features and the time series features;
[0032] A condition judgment module, configured to judge whether to discharge pollutants from the target workshop according to the predicted pollutant concentration.
[0033] In addition, to achieve the above object, the present application also proposes a workshop pollutant distribution discrimination and pollutant emission device, and the device includes: a memory, a processor, and a workshop pollutant distribution discrimination and pollutant emission program stored on the memory and executable on the processor, and the workshop pollutant distribution discrimination and pollutant emission program is configured to implement the steps of the workshop pollutant distribution discrimination and pollutant emission method as described above.
[0034] In addition, to achieve the above object, the present application also proposes a storage medium, and the storage medium is a computer-readable storage medium, and a workshop pollutant distribution discrimination and pollutant emission program is stored on the storage medium, and when the workshop pollutant distribution discrimination and pollutant emission program is executed by a processor, the steps of the workshop pollutant distribution discrimination and pollutant emission method as described above are implemented.
[0035] In addition, to achieve the above object, the present invention also provides a computer program product, and the computer program product includes a workshop pollutant distribution discrimination and pollutant emission program, and when the workshop pollutant distribution discrimination and pollutant emission program is executed by a processor, the steps of the workshop pollutant distribution discrimination and pollutant emission method as described above are implemented.
[0036] This application constructs a pollutant distribution model corresponding to the target workshop based on the real-time data of the target workshop; extracts the spatial features and time series features corresponding to the pollutants from the pollutant distribution model; determines the predicted concentration of pollutants in the target workshop based on the spatial features and the time series features; and determines whether to discharge pollutants in the target workshop according to the predicted concentration of pollutants. The above method of this application first extracts the spatial features and time series features corresponding to the pollutants from the pollutant distribution model corresponding to the target workshop, then determines the predicted concentration of pollutants in the target workshop according to the spatial features and the time series features, and finally controls whether to discharge pollutants in the target workshop according to the predicted concentration of pollutants, thus avoiding the occurrence of situations such as misjudgment and missed judgment of pollutants that may be caused by the subjective experience judgment of technicians in the traditional technology, and further achieving the technical effect of accurately discriminating the pollutant distribution in the workshop to control the timing of pollutant discharge. Description of the Drawings
[0037] Figure 1 It is a schematic structural diagram of a workshop pollutant distribution discrimination and pollutant emission device for the hardware operating environment involved in the solution of the embodiment of this application;
[0038] Figure 2 It is a schematic flowchart of the first embodiment of the method for workshop pollutant distribution discrimination and pollutant emission of this application;
[0039] Figure 3 It is a schematic flowchart of the second embodiment of the method for workshop pollutant distribution discrimination and pollutant emission of this application;
[0040] Figure 4 It is a schematic flowchart of the third embodiment of the method for workshop pollutant distribution discrimination and pollutant emission of this application;
[0041] Figure 5 It is a structural block diagram of the first embodiment of the workshop pollutant distribution discrimination and pollutant emission device of this application.
[0042] The realization, functional characteristics and advantages of the purpose of this application will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiment
[0043] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.
[0044] Refer to Figure 1 , Figure 1 It is a schematic structural diagram of a workshop pollutant distribution discrimination and pollutant emission device for the hardware operating environment involved in the solution of the embodiment of this application.
[0045] As Figure 1As shown in the figure, the workshop pollutant distribution discrimination and pollutant emission equipment may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed Random Access Memory (RAM) or a stable Non-Volatile Memory (NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0046] Those skilled in the art can understand that Figure 1 the structure shown in the figure does not constitute a limitation on the workshop pollutant distribution discrimination and pollutant emission equipment, and may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.
[0047] As Figure 1 shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and a workshop pollutant distribution discrimination and pollutant emission program.
[0048] In Figure 1 the shown workshop pollutant distribution discrimination and pollutant emission equipment, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the workshop pollutant distribution discrimination and pollutant emission equipment of the present application may be arranged in the workshop pollutant distribution discrimination and pollutant emission equipment. The workshop pollutant distribution discrimination and pollutant emission equipment calls the workshop pollutant distribution discrimination and pollutant emission program stored in the memory 1005 through the processor 1001 and executes the workshop pollutant distribution discrimination and pollutant emission method provided by the embodiments of the present application.
[0049] The embodiments of the present application provide a workshop pollutant distribution discrimination and pollutant emission method. Referring to Figure 2 Figure 2 is a schematic flowchart of the first embodiment of the workshop pollutant distribution discrimination and pollutant emission method of the present application.
[0050] In this embodiment, the method for discriminating the distribution of pollutants in the workshop and the pollutant emission includes the following steps:
[0051] Step S10: Construct a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop.
[0052] It should be noted that the execution subject of the method in this embodiment can be a terminal device with functions of model construction, data processing, and program running, such as a smart phone, a computer, etc., or an electronic device with the same or similar functions, such as the above-mentioned device for discriminating the distribution of pollutants in the workshop and pollutant emission. The following takes the device for discriminating the distribution of pollutants in the workshop and pollutant emission as an example to illustrate this embodiment and the following embodiments.
[0053] It can be understood that the above-mentioned target workshop can refer to a factory workshop that needs to implement pollutant control measures, such as a microelectronic material workshop, a precision machining workshop, a chemical workshop, etc.; the above-mentioned real-time data can refer to data related to pollutant discrimination in the target workshop, such as real-time image data of the pollutant area in the target workshop, real-time sensor data of the environmental characteristics (such as temperature, humidity, dust composition, pollutant concentration, etc.) in the target workshop. This embodiment does not specifically limit the target workshop and the real-time data.
[0054] It should be understood that the above-mentioned pollutant distribution model is a mathematical model used to describe the three-dimensional distribution of pollutants in the target workshop in space.
[0055] In a specific implementation, it is possible to determine which pollutants exist in the target workshop according to the above-mentioned real-time data, and the corresponding material characteristics (including but not limited to spatial characteristics, physical characteristics, chemical characteristics, etc.) of these pollutants in three-dimensional space, and then construct the above-mentioned pollutant distribution model corresponding to the target workshop according to the material characteristics of the pollutants.
[0056] Step S20: Extract the spatial features and time series features corresponding to the pollutants from the pollutant distribution model.
[0057] It should be noted that the above-mentioned spatial features can include but not limited to pollutant concentration, pollutant area, pollutant volume, pollutant diffusion speed, etc., and the above-mentioned time series features can include but not limited to pollutant growth rate, pollutant diffusion mode, etc.
[0058] It should be understood that the pollutants in the above pollutant distribution model can be located, and the spatial characteristics corresponding to the located pollutants can be extracted according to the real-time data of the pollutant distribution model. At the same time, time series analysis can be performed on the above spatial characteristics in the time dimension to reveal the variation law of pollutants over time (such as pollutant growth rate, pollutant diffusion mode, etc.), so as to obtain the above time series characteristics.
[0059] Step S30: Determine the predicted pollutant concentration of the target workshop based on the spatial characteristics and the time series characteristics.
[0060] It should be noted that the above predicted pollutant concentration may refer to the predicted concentration of pollutants in the target workshop in the next time period.
[0061] In a specific implementation, after the above spatial characteristics and time series characteristics are extracted, the spatial characteristics and time series characteristics can be input into a pollutant concentration prediction model, and the output of the pollutant concentration prediction model obtained is the predicted pollutant concentration of the target workshop. Among them, the pollutant concentration prediction model can be constructed based on the following steps: First step, obtain the historical spatial characteristics, historical time series characteristics and historical pollutant concentration of the target workshop, and merge them into a historical data set; Second step, divide the historical data set into a training set, a test set and a validation set, and select an initial model; Third step, train the initial model based on the training set, the test set and the validation set to obtain a pollutant concentration prediction model. Among them, the initial model can be a machine learning model (such as a decision tree model, a random forest model, a support vector machine model, etc.), or an XGBoost (optimized distributed gradient boosting library) model or other models capable of data prediction, and this embodiment does not limit this.
[0062] Step S40: Determine whether to discharge pollutants from the target workshop according to the predicted pollutant concentration.
[0063] In a specific implementation, it can be determined whether to discharge pollutants from the target workshop by judging whether the predicted pollutant concentration reaches the discharge standard: when the predicted pollutant concentration reaches the discharge standard, pollutants are discharged from the target workshop; when the predicted pollutant concentration does not reach the discharge standard, pollutants are not discharged from the target workshop.
[0064] In this embodiment, a pollutant distribution model corresponding to the target workshop is constructed based on the real-time data of the target workshop; the spatial features and time series features corresponding to the pollutants are extracted from the pollutant distribution model; the predicted pollutant concentration of the target workshop is determined based on the spatial features and the time series features; and it is judged whether to discharge pollutants in the target workshop according to the predicted pollutant concentration. The above method in this embodiment first extracts the spatial features and time series features corresponding to the pollutants from the pollutant distribution model corresponding to the target workshop, then determines the predicted pollutant concentration of the target workshop according to the spatial features and time series features, and finally controls whether to discharge pollutants in the target workshop according to the predicted pollutant concentration, thereby avoiding the occurrence of situations such as misjudgment and missed judgment of pollutants that may be caused by the subjective experience judgment of technicians in the traditional technology, and further achieving the technical effect of accurately discriminating the pollutant distribution in the workshop to control the timing of pollutant discharge.
[0065] Reference Figure 3 , Figure 3 is a schematic flowchart of the second embodiment of the method for discriminating the pollutant distribution in the workshop and discharging pollutants in this application.
[0066] In a feasible implementation manner, the real-time data includes real-time image data and real-time sensor data, and the step S10 may include:
[0067] Step S101: Collect the real-time image data and real-time sensor data of the target workshop, and preprocess the real-time image data to obtain processed image data.
[0068] Step S102: Construct a pollutant distribution model corresponding to the target workshop according to the processed image data and the real-time sensor data.
[0069] It should be noted that the above real-time image data may refer to the workshop environment image data of the target workshop. Specifically, industrial-grade high-definition cameras (resolution ≥ 1080p) can be used and arranged in different areas of the workshop, and combined with infrared imaging technology to ensure effective data collection in low-light environments, and the above real-time image data can be captured from the target workshop in real time. The above real-time sensor data may be the data collected by various sensors in the target workshop, such as temperature sensors, humidity sensors, pressure sensors, gas composition sensors, particulate matter composition sensors, etc. This embodiment does not limit the types and quantities of sensors.
[0070] In a specific implementation, real-time sensor data can be mapped to corresponding regions in the processed image data, so as to obtain processed image data containing the real-time sensor data. Then, based on the processed image data containing the real-time sensor data, the pollutant distribution in the target workshop is determined (such as the concentration field and diffusion trend of pollutants), so as to construct a pollutant distribution model corresponding to the target workshop.
[0071] In a feasible implementation manner, step S101 may include:
[0072] Step S1011: Perform denoising processing, edge detection, and grayscale processing on the real-time image data to obtain first image data.
[0073] In a specific implementation, Gaussian filtering or median filtering can be used to remove the noise in the real-time image data to achieve denoising processing, so as to reduce the interference caused by the possible jitter during the acquisition of the real-time image data; the Canny edge detection algorithm can be used to detect the object contours in the real-time image data to achieve edge detection, which is convenient for subsequent segmentation and recognition of the pollutant region; the RGB image corresponding to the real-time image data can be converted into a grayscale image to achieve grayscale processing, so as to reduce the computational complexity while retaining the main information (i.e., the information related to pollutants).
[0074] Step S1012: Perform semantic segmentation processing on the pollutant region in the real-time image data to obtain second image data.
[0075] In a specific implementation, the UNet segmentation algorithm based on deep learning (a convolutional neural network architecture for image segmentation) can be used to perform semantic segmentation processing on the pollutant region in the real-time image data, so as to separate the pollutant region from the background and obtain the above-mentioned second image data. Among them, the generated binary mask after segmentation is used for subsequent identification and positioning of pollutants.
[0076] Step S1013: Perform target detection on the real-time image data based on the second image data to obtain pollutant position coordinates and pollutant categories.
[0077] In a specific implementation, the YOLO algorithm (an end-to-end target detection algorithm) can be used to perform target detection on the above-mentioned real-time image data to identify the pollutants in the image, so as to obtain pollutant position coordinates and pollutant categories.
[0078] Step S1014: Mark the pollutant position coordinates and the pollutant categories in the first image data to obtain processed image data.
[0079] In a feasible implementation manner, step S20 may include:
[0080] Step S201: Use a convolutional neural network to extract the spatial features corresponding to the pollutants from the pollutant distribution model. The spatial features include pollutant concentration, pollutant area, pollutant volume, and pollutant diffusion speed.
[0081] Step S202: Use a recurrent neural network or a long short-term memory neural network to extract the time series features corresponding to the pollutants from the pollutant distribution model. The time series features include pollutant growth rate and pollutant diffusion pattern.
[0082] In this embodiment, real-time image data and real-time sensor data of the target workshop are collected, and the real-time image data is denoised, edge-detected, and grayscaled to obtain first image data; semantic segmentation is performed on the pollutant area in the real-time image data to obtain second image data; target detection is performed on the real-time image data based on the second image data to obtain pollutant position coordinates and pollutant categories; the pollutant position coordinates and the pollutant categories are marked in the first image data to obtain processed image data; a convolutional neural network is used to extract the spatial features corresponding to the pollutants from the pollutant distribution model. The spatial features include pollutant concentration, pollutant area, pollutant volume, and pollutant diffusion speed; a recurrent neural network or a long short-term memory neural network is used to extract the time series features corresponding to the pollutants from the pollutant distribution model. The time series features include pollutant growth rate and pollutant diffusion pattern. The above method of this embodiment preprocesses the real-time image data collected in the target workshop through image processing techniques such as denoising, edge detection, and grayscaling, ensuring the clarity and consistency of the processed image data obtained after preprocessing; at the same time, a pollutant distribution model corresponding to the target workshop is constructed according to the processed image data and the real-time sensor data of the target workshop, enabling this embodiment to more accurately and intuitively describe the three-dimensional distribution of pollutants in the space of the target workshop based on the pollutant distribution model.
[0083] Reference Figure 4 , Figure 4 is a schematic flowchart of the third embodiment of the method for discriminating the pollutant distribution in the workshop and the pollutant emission of this application.
[0084] In a feasible implementation manner, the step S40 may include:
[0085] Step S401: If it is determined that the predicted pollutant concentration is greater than the first preset threshold, pollutant emission is performed on the target workshop.
[0086] Step S402: If it is determined that the predicted pollutant concentration is less than or equal to the first preset threshold, the predicted pollutant concentration is updated, and the updated predicted pollutant concentration is continuously monitored.
[0087] It should be noted that the above first preset threshold can be flexibly set according to the actual factory workshop environment, for example, 10 mg / m 3 .
[0088] In a specific implementation, if it is determined that the predicted pollutant concentration is greater than the first preset threshold, it indicates that the predicted pollutant concentration reaches the emission standard at this time. Therefore, pollutant emissions can be carried out in the target workshop; if it is determined that the predicted pollutant concentration is less than or equal to the first preset threshold, it indicates that the predicted pollutant concentration does not reach the emission standard at this time. Therefore, it is temporarily not necessary to carry out pollutant emissions in the target workshop.
[0089] In a feasible implementation manner, the step S401 may include:
[0090] Step S4011: Carry out harmless treatment on the pollutants in the target workshop, and monitor the pollutant emission concentration in the target workshop after the harmless treatment.
[0091] Step S4012: If the pollutant emission concentration is less than the second preset threshold, discharge the pollutants after the harmless treatment.
[0092] It should be noted that the above second preset threshold can be flexibly set according to the actual scenario, for example, 30 μg / m 3 .
[0093] It should be understood that if the pollutant emission concentration is less than the second preset threshold, it indicates that the pollutant emission concentration meets the emission requirements at this time. Therefore, the pollutants after the harmless treatment can be discharged.
[0094] Step S4013: If the pollutant emission concentration is greater than or equal to the second preset threshold, adjust the harmless treatment process, and carry out harmless treatment on the pollutants in the target workshop according to the adjusted harmless treatment process.
[0095] It should be understood that if the pollutant emission concentration is greater than or equal to the second preset threshold, it indicates that the pollutant emission concentration does not meet the emission requirements at this time. Therefore, it is necessary to adjust the harmless treatment process, and carry out harmless treatment on the pollutants in the target workshop according to the adjusted harmless treatment process until the pollutant emission concentration meets the emission requirements.
[0096] In a specific implementation, if the pollutant emission concentration exceeds the standard, the system can adjust the harmless treatment process in the following ways: extend the harmless treatment time to increase the contact time between the dust and the treatment equipment; adjust the treatment intensity of the equipment, such as increasing the heating temperature and enhancing the efficiency of the chemical decomposition reaction; if the chemical decomposition is not sufficient to reduce the pollutant emission concentration, the required chemical addition amount can be calculated and adjusted through an LSTM (Long Short-Term Memory) model; if the pollutant emission concentration is high during certain periods, the treatment intensity can be appropriately increased or the treatment time can be extended during these periods to prevent excessive emissions; according to the characteristics of different time periods (such as changes in day-night temperature difference, equipment load fluctuations, etc.), the parameters in the treatment process (such as heating power, chemical dosage, etc.) can be dynamically adjusted.
[0097] In this embodiment, if it is determined that the predicted pollutant concentration is greater than the first preset threshold, the pollutants in the target workshop are subjected to harmless treatment, and the pollutant emission concentration of the target workshop after harmless treatment is monitored; if the pollutant emission concentration is less than the second preset threshold, the pollutants after harmless treatment are discharged; if the pollutant emission concentration is greater than or equal to the second preset threshold, the harmless treatment process is adjusted, and the pollutants in the target workshop are subjected to harmless treatment according to the adjusted harmless treatment process; if it is determined that the predicted pollutant concentration is less than or equal to the first preset threshold, the predicted pollutant concentration is updated, and the updated predicted pollutant concentration is continuously monitored. The above method in this embodiment enables the factory workshop to achieve more refined pollutant emission control by subjecting the pollutants in the target workshop to harmless treatment, discharging the pollutants after harmless treatment when the monitored pollutant emission concentration of the target workshop after harmless treatment is less than the second preset threshold, and adjusting the harmless treatment process when the monitored pollutant emission concentration of the target workshop after harmless treatment is greater than or equal to the second preset threshold.
[0098] In addition, an embodiment of the present application also proposes a storage medium, on which a workshop pollutant distribution discrimination and pollutant emission program is stored. When the workshop pollutant distribution discrimination and pollutant emission program is executed by a processor, the steps of the workshop pollutant distribution discrimination and pollutant emission method described above are implemented.
[0099] Refer to Figure 5 , Figure 5 which is a structural block diagram of the first embodiment of the workshop pollutant distribution discrimination and pollutant emission device of the present application.
[0100] As Figure 5 shown, the workshop pollutant distribution discrimination and pollutant emission device proposed in the embodiment of the present application includes:
[0101] The model construction module 501 is configured to construct a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop;
[0102] The feature extraction module 502 is configured to extract the spatial features and time series features corresponding to the pollutants from the pollutant distribution model;
[0103] The concentration prediction module 503 is configured to determine the predicted pollutant concentration of the target workshop based on the spatial features and the time series features;
[0104] The condition judgment module 504 is configured to judge whether to discharge pollutants in the target workshop according to the predicted pollutant concentration.
[0105] In this embodiment, a pollutant distribution model corresponding to the target workshop is constructed according to the real-time data of the target workshop; the spatial features and time series features corresponding to the pollutants are extracted from the pollutant distribution model; the predicted pollutant concentration of the target workshop is determined based on the spatial features and the time series features; and it is judged whether to discharge pollutants in the target workshop according to the predicted pollutant concentration. In the above method of this embodiment, the spatial features and time series features corresponding to the pollutants are first extracted from the pollutant distribution model corresponding to the target workshop, then the predicted pollutant concentration of the target workshop is determined according to the spatial features and time series features, and finally, whether to discharge pollutants in the target workshop is controlled according to the predicted pollutant concentration, thereby avoiding the occurrence of situations such as misjudgment and missed judgment of pollutants that may be caused by the subjective experience judgment of technicians in the traditional technology, and further achieving the technical effect of accurately discriminating the pollutant distribution in the workshop to control the timing of pollutant discharge.
[0106] Based on the first embodiment of the workshop pollutant distribution discrimination and pollutant discharge device of the present application, a second embodiment of the workshop pollutant distribution discrimination and pollutant discharge device of the present application is proposed.
[0107] In this embodiment, the real-time data includes real-time image data and real-time sensor data. The model construction module 501 is further configured to collect the real-time image data and real-time sensor data of the target workshop, preprocess the real-time image data to obtain processed image data; and construct a pollutant distribution model corresponding to the target workshop according to the processed image data and the real-time sensor data.
[0108] Further, the model construction module 501 is further configured to perform denoising processing, edge detection, and grayscale processing on the real-time image data to obtain first image data; perform semantic segmentation processing on the pollutant area in the real-time image data to obtain second image data; perform object detection on the real-time image data based on the second image data to obtain pollutant position coordinates and pollutant categories; and mark the pollutant position coordinates and the pollutant categories in the first image data to obtain processed image data.
[0109] Further, the feature extraction module 502 is further configured to use a convolutional neural network to extract spatial features corresponding to pollutants from the pollutant distribution model, where the spatial features include pollutant concentration, pollutant area, pollutant volume, and pollutant diffusion speed; and use a recurrent neural network or a long short-term memory neural network to extract time series features corresponding to pollutants from the pollutant distribution model, where the time series features include pollutant growth rate and pollutant diffusion pattern.
[0110] Further, the condition judgment module 504 is further configured to, if it is determined that the predicted pollutant concentration is greater than a first preset threshold, perform pollutant emission on the target workshop; if it is determined that the predicted pollutant concentration is less than or equal to the first preset threshold, update the predicted pollutant concentration and continuously monitor the updated predicted pollutant concentration.
[0111] Further, the condition judgment module 504 is further configured to perform harmless treatment on the pollutants in the target workshop and monitor the pollutant emission concentration of the target workshop after the harmless treatment; if the pollutant emission concentration is less than a second preset threshold, emit the pollutants after the harmless treatment; if the pollutant emission concentration is greater than or equal to the second preset threshold, adjust the harmless treatment process and perform harmless treatment on the pollutants in the target workshop according to the adjusted harmless treatment process.
[0112] Other embodiments or specific implementation manners of the workshop pollutant distribution discrimination and pollutant emission device of the present application may refer to the above method embodiments, and will not be elaborated here.
[0113] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including that element.
[0114] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.
[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that makes a contribution to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.
[0116] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application accordingly. Any equivalent structure or equivalent process transformation made by using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.
Claims
1. A method for determining pollutant distribution in a workshop and for discharging pollutants, characterized in that: The method comprises the following steps: Constructing a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop; Extracting spatial characteristics and time series characteristics corresponding to pollutants from the pollutant distribution model; Determining the predicted concentration of pollutants in the target workshop based on the spatial characteristics and the time series characteristics; Whether to discharge pollutants from the target workshop is determined according to the predicted pollutant concentration.
2. The method for determining pollutant distribution and discharging pollutants in a workshop according to claim 1, characterized in that: The real-time data includes real-time image data and real-time sensor data. The step of constructing a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop includes: Collecting real-time image data and real-time sensor data of the target workshop, and preprocessing the real-time image data to obtain processed image data; A pollutant distribution model corresponding to the target workshop is constructed according to the processed image data and the real-time sensor data.
3. The method for determining pollutant distribution and discharging pollutants in a workshop according to claim 2, characterized in that: The step of preprocessing the real-time image data to obtain processed image data comprises: Performing denoising, edge detection and grayscale processing on the real-time image data to obtain first image data; Performing semantic segmentation processing on the pollutant area in the real-time image data to obtain second image data; Performing target detection on the real-time image data based on the second image data to obtain pollutant position coordinates and pollutant categories; The pollutant position coordinates and the pollutant category are marked in the first image data to obtain processed image data.
4. The method for determining pollutant distribution and discharging pollutants in a workshop according to claim 1, characterized in that: The step of extracting the spatial characteristics and time series characteristics corresponding to the pollutants from the pollutant distribution model includes: Using a convolutional neural network to extract spatial features corresponding to pollutants from the pollutant distribution model, the spatial features include pollutant concentration, pollutant area, pollutant volume and pollutant diffusion speed; A recurrent neural network or a long short-term memory neural network is used to extract time series features corresponding to pollutants from the pollutant distribution model, and the time series features include pollutant growth rate and pollutant diffusion pattern.
5. The method for determining pollutant distribution and discharging pollutants in a workshop according to claim 1, characterized in that: The step of judging whether to discharge pollutants from the target workshop according to the predicted pollutant concentration includes: If it is determined that the predicted concentration of the pollutant is greater than a first preset threshold, the pollutant is discharged from the target workshop; If it is determined that the predicted pollutant concentration is less than or equal to the first preset threshold, the predicted pollutant concentration is updated, and the updated predicted pollutant concentration is continuously monitored.
6. The method for determining pollutant distribution and discharging pollutants in a workshop according to claim 5, characterized in that: The step of discharging pollutants from the target workshop includes: Performing harmless treatment on pollutants in the target workshop and monitoring the pollutant emission concentration of the target workshop after the harmless treatment; If the pollutant emission concentration is less than the second preset threshold, the pollutants after harmless treatment are discharged; If the pollutant emission concentration is greater than or equal to the second preset threshold, the harmless treatment process is adjusted, and the pollutants in the target workshop are harmlessly treated according to the adjusted harmless treatment process.
7. A pollutant distribution identification and pollutant emission device for a workshop, characterized in that: The workshop pollutant distribution identification and pollutant emission device includes: A model building module, used to build a pollutant distribution model corresponding to the target workshop according to the real-time data of the target workshop; A feature extraction module, used to extract the spatial features and time series features corresponding to the pollutants from the pollutant distribution model; A concentration prediction module, used to determine the predicted concentration of pollutants in the target workshop based on the spatial characteristics and the time series characteristics; The condition judgment module is used to judge whether to discharge pollutants to the target workshop according to the predicted concentration of pollutants.
8. A pollutant distribution identification and pollutant emission equipment for a workshop, characterized in that: The device includes: a memory, a processor, and a workshop pollutant distribution determination and pollutant emission program stored in the memory and executable on the processor, wherein the workshop pollutant distribution determination and pollutant emission program is configured to implement the steps of the workshop pollutant distribution determination and pollutant emission method as described in any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a workshop pollutant distribution determination and pollutant emission program is stored. When the workshop pollutant distribution determination and pollutant emission program is executed by a processor, the steps of the workshop pollutant distribution determination and pollutant emission method as described in any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product includes a workshop pollutant distribution determination and pollutant emission program, and when the workshop pollutant distribution determination and pollutant emission program is executed by a processor, the steps of the workshop pollutant distribution determination and pollutant emission method as described in any one of claims 1 to 6 are implemented.