Wastewater treatment process data acquisition method and system

Abstract

The invention discloses a wastewater treatment process data acquisition method and system, and belongs to the technical field of data acquisition, and the method comprises the following steps: setting a plurality of water quality information acquisition points at each step of a water quality treatment process, acquiring and uploading water quality information at each water quality information acquisition point, setting a flow simulation diagram of the water quality treatment process, generating a composite curve graph by using historical water quality information of each water quality information acquisition point, training a neural network model by using the composite curve graph to obtain a curve extension judgment model, intercepting the composite curve graph, inputting the composite curve graph into the curve extension judgment model to obtain a predicted extension curve, and performing deep learning on the curve extension judgment model to obtain a predicted extension curve; the new water quality information is processed through the model, the newly received water quality information is corrected according to the selected water quality information to obtain simulated corrected water quality information, and the received water quality information is used as actual detected water quality information, and the method has the effects of providing a simulated proofreading result of a detection result and improving the detection precision.

Description

Technical Field

[0001] This invention relates to the field of data acquisition, and in particular to a method and system for acquiring data in a wastewater treatment process. Background Technology

[0002] With the rapid pace of industrialization and urbanization, wastewater treatment has become a crucial aspect of environmental protection. Real-time and effective data acquisition is essential for the efficiency and effectiveness of wastewater treatment. The wastewater treatment process includes primary treatment (physical interception), secondary treatment (microbial degradation or sedimentation filtration), tertiary treatment (fine purification), and sludge and waste disposal. While the details of different wastewater treatment processes may vary, the overall flow is largely the same. Data acquisition during wastewater treatment presents numerous challenges, including complex water quality conditions and the susceptibility of testing equipment to damage.

[0003] The existing technical solutions mentioned above have the following drawbacks: due to the uneven distribution of impurities in the wastewater, the accuracy of the test results is not high and there will usually be a small deviation. If the data acquisition process is not standardized or the acquisition equipment malfunctions, there may be a large deviation. Summary of the Invention

[0004] To increase detection accuracy, this application provides a data acquisition method and system for wastewater treatment processes.

[0005] On the one hand, the wastewater treatment process data acquisition method provided in this application adopts the following technical solution: A method for data acquisition in a wastewater treatment process includes the following steps: Multiple water quality information collection points are set up at each step of the water treatment process. Each water quality information collection point collects and uploads water quality information, which includes routine parameters and pollutant parameters set according to specific circumstances. Set up a process simulation diagram of water quality treatment, mark water quality information collection points on the process simulation diagram, associate water quality information with water quality information collection points on the process simulation diagram when receiving water quality information, and record the collection time. A composite curve graph is generated using historical water quality information from each water quality information collection point. Set up a neural network model, train the neural network model using a composite curve graph to obtain a curve extension judgment model, and output a predicted extension curve based on each curve in the received composite curve graph. The composite curve graph is extracted and input into the curve extension judgment model to obtain the predicted extension curve. The obtained predicted extension curve is compared with the curves of the same time period on the complete composite curve graph, and deep learning is performed on the curve extension judgment model. When new water quality information is received, the previous composite curve is input into the curve extension judgment model. The curve extension judgment model outputs a predicted extension curve. On the predicted extension curve, the coordinate point at the same time as the newly received water quality information is selected. The water quality information of the selected coordinate point is read. The newly received water quality information is corrected according to the water quality information of the selected coordinate point to obtain simulated corrected water quality information. The received water quality information is used as the actual detected water quality information. Displays simulated corrected water quality information and actual tested water quality information.

[0006] By adopting the above scheme, in the wastewater treatment process, this system can divide the collection points according to the wastewater treatment process, and then automatically train a deep learning model based on the on-site records. When detecting wastewater quality later, the deep learning model generates water quality information on the expected changes in water quality. Users can compare the actual detection information with the actual detection information to determine whether there is a large deviation in the actual detection information and the direction of the deviation, which can effectively improve the accuracy of detection.

[0007] Preferably, the step "collecting and uploading water quality information at each water quality information collection point" also includes: Preset test time range and detection time range; Use water testing equipment with known water quality and adjust the equipment according to the test results, and record the test time; Wastewater samples were collected at water quality information collection points, the sampling time was recorded, and the wastewater samples were tested using testing equipment. The water quality information and testing time were recorded. Determine whether the time between the test time and the detection time is within the test time range; An alarm will be issued if the test is not within the specified time frame. If the test time is within the specified time range, determine whether the time between the sampling time and the detection time falls within the detection time. An alarm will be issued if the detection time is not within the specified time range; If the test is within the testing period, a preliminary check of the water quality information will be performed, and an alarm will be issued if any abnormal information is found. If no abnormal information is found, upload the water quality information.

[0008] By adopting the above scheme, and by monitoring the testing time of the testing equipment and the testing time of water quality information, it is possible to effectively monitor whether the data collection process is standardized, and reduce inaccurate data caused by non-standard data collection process.

[0009] Preferably, the step of "setting a flow simulation diagram of the water treatment process" further includes: Receive the water treatment process and determine the type of wastewater being treated based on the process. The water treatment process is divided into multiple nodes according to the treatment area, and the nodes are connected in order of the water treatment process to generate a process simulation diagram. The water quality changes are determined based on the water treatment process and wastewater type corresponding to each node. The magnitude of water quality change is determined based on the water quality changes at each node; When new water quality information is received, the system determines whether any abnormal information has appeared based on the magnitude of the water quality change.

[0010] By adopting the above scheme, the system can determine the magnitude of water quality changes by combining the water treatment process with experience or Internet data, and determine whether there are any abnormalities in the water quality information based on the magnitude of water quality changes.

[0011] Preferably, the step of "training a neural network model using a composite curve graph to obtain a curve extension judgment model" further includes: The composite curve is broken down into multiple water quality data curves. The curve extension judgment model records the magnitude of change of each water quality data curve and its relationship with the changes of other water quality data curves to obtain the change rules of a single water quality data curve. The variation rules of all water quality data curves are incorporated into the composite curve graph for correction, and an algorithm is obtained in which the variation rules of each water quality data curve are consistent with each other. Based on the obtained algorithm, the predicted extension curve of the composite curve graph is predicted.

[0012] By adopting the above scheme, the model can be trained by analyzing the correlation between each water quality data curve, thus combining the mutual influence between different water quality information, making data prediction more reasonable, and further increasing the confidence of the model processing.

[0013] Preferably, the following steps are also included: Preset prediction limit difference; Compare the differences between individual water quality values ​​of simulated corrected water quality information and actual measured water quality information from the same collection point; If a difference exceeds the predicted limit, the wastewater at the corresponding sampling point will be re-tested. If a single water quality value in the simulated corrected water quality information differs from the same water quality value in the actual detected water quality information, and the difference is less than the prediction limit difference, it is marked as higher than expected or lower than expected.

[0014] By adopting the above scheme, given the large amount and complexity of water quality information, the system can intelligently compare the results after testing and directly output the results, making it easier for users to understand the accuracy of the water quality information.

[0015] On the other hand, the wastewater treatment process data acquisition system provided in this application adopts the following technical solution: A wastewater treatment process data acquisition system includes a data storage module, a sample acquisition module, a curve generation module, a model generation module, a water quality judgment module, and a data display module. The data storage module receives and stores data, and the data storage module has a preset flow simulation diagram of the water treatment process; The sample collection module calls the process simulation diagram of the data storage module, sets multiple water quality information collection points at each step of the water treatment process, receives water quality information uploaded by each collection point, and the water quality information includes conventional parameters and pollutant parameters set according to specific circumstances. The water quality information collection points are marked on the process simulation diagram. When receiving water quality information, the water quality information is associated with the water quality information collection points on the process simulation diagram, and the collection time is recorded. The recorded process simulation diagram is then transmitted to the data storage module. The curve generation module calls the water quality information from the data storage module, uses the historical water quality information from each water quality information collection point to generate a composite curve, and transmits the composite curve to the model generation module and the water quality judgment module. The model generation module has a preset neural network model. The neural network model is trained using a composite curve graph to obtain a curve extension judgment model. The curve extension judgment model outputs a predicted extension curve based on each curve in the received composite curve graph. The composite curve graph is extracted and input into the curve extension judgment model to obtain the predicted extension curve. The obtained predicted extension curve is compared with the curves in the same time period on the complete composite curve graph. Deep learning is performed on the curve extension judgment model, and the curve extension judgment model is transmitted to the water quality judgment module. The water quality judgment module is connected to the data storage module. When the data storage module receives new water quality information, it inputs the previous composite curve graph into the curve extension judgment model. The curve extension judgment model outputs a predicted extension curve. On the predicted extension curve, it selects the coordinate point at the same time as the newly received water quality information, reads the water quality information of the selected coordinate point, corrects the corresponding newly received water quality information based on the water quality information of the selected coordinate point to obtain simulated corrected water quality information, uses the received water quality information as the actual detected water quality information, and transmits the simulated corrected water quality information and the actual detected water quality information to the data display module. The data display module shows simulated corrected water quality information and actual tested water quality information.

[0016] By adopting the above scheme, in the wastewater treatment process, this system can divide the collection points according to the wastewater treatment process, and then automatically train a deep learning model based on the on-site records. When detecting wastewater quality later, the deep learning model generates water quality information on the expected changes in water quality. Users can compare the actual detection information with the actual detection information to determine whether there is a large deviation in the actual detection information and the direction of the deviation, which can effectively improve the accuracy of detection.

[0017] Preferably, the system also includes a data acquisition and monitoring module. This module accesses the detection point information from the sample acquisition module. The module presets a test time range and a detection time range, uses a water quality testing instrument with known water quality and adjusts the instrument based on the test results, records the test time, collects wastewater samples at the water quality information collection point, records the sampling time, uses the testing instrument to test the wastewater samples, records the detected water quality information and the detection time, and determines whether the time between the test time and the detection time is within the test time range. If it is not within the test time range, an alarm is issued and the sample acquisition module is prevented from receiving uploaded water quality information. If it is within the test time range, the module determines whether the time between the sampling time and the detection time is within the detection time. If it is not within the detection time range, an alarm is issued and the sample acquisition module is prevented from receiving uploaded water quality information. If it is within the detection time, a preliminary check of the detected water quality information is performed. If abnormal information is found, an alarm is issued; otherwise, no response is given.

[0018] By adopting the above scheme, and by monitoring the testing time of the testing equipment and the testing time of water quality information, it is possible to effectively monitor whether the data collection process is standardized, and reduce inaccurate data caused by non-standard data collection process.

[0019] Preferably, it also includes a process generation module, which receives the water treatment process, obtains the type of wastewater to be treated based on the water treatment process, divides the water treatment process into multiple nodes according to the treatment area, sorts and connects the nodes according to the order of the water treatment process to generate a process simulation diagram, determines the water quality changes according to the partial water treatment process and wastewater type corresponding to each node, determines the water quality change range according to the water quality changes of each node, and transmits the processed process simulation diagram to the data storage module. When the data acquisition and monitoring module receives new water quality information, it determines whether there is any abnormality in the corresponding water quality information based on the water quality change range on the process simulation diagram.

[0020] By adopting the above scheme, the system can determine the magnitude of water quality changes by combining the water treatment process with experience or Internet data, and determine whether there are any abnormalities in the water quality information based on the magnitude of water quality changes.

[0021] Preferably, the model generation module splits the composite curve graph into multiple water quality data curves. The curve extension judgment model records the relationship between the change magnitude of each water quality data curve and the changes of other water quality data curves, obtains the change rules of individual water quality data curves, and modifies the change rules of all water quality data curves into the composite curve graph to obtain an algorithm in which the change rules of each water quality data curve are consistent with each other. Based on the obtained algorithm, the predicted extension curve of the composite curve graph is predicted.

[0022] By adopting the above scheme, the model can be trained by analyzing the correlation between each water quality data curve, thus combining the mutual influence between different water quality information, making data prediction more reasonable, and further increasing the confidence of the model processing.

[0023] Preferably, it also includes a prediction and judgment module. The prediction and judgment module presets a prediction limit difference. The prediction and judgment module calls the simulated corrected water quality information and the actual detected water quality information from the water quality judgment module, and compares the difference between the individual water quality values ​​of the simulated corrected water quality information and the actual detected water quality information at the same collection point. If the difference exceeds the prediction limit difference, an alarm is issued. If the individual water quality value in the simulated corrected water quality information is different from the same water quality value in the actual detected water quality information, and the difference is less than the prediction limit difference, it is marked as higher than expected or lower than expected, and the marked simulated corrected water quality information and actual detected water quality information are transmitted to the data display module.

[0024] By adopting the above scheme, given the large amount and complexity of water quality information, the system can intelligently compare the results after testing and directly output the results, making it easier for users to understand the accuracy of the water quality information.

[0025] In summary, the present invention has the following beneficial effects: 1. In the wastewater treatment process, this system can divide the collection points according to the wastewater treatment process, and then automatically train a deep learning model based on the on-site records. When detecting wastewater quality, the deep learning model generates water quality information on the expected changes in water quality. Users can compare the actual detection information with the actual detection information to determine whether there is a large deviation in the actual detection information and the direction of the deviation, which can effectively improve the accuracy of detection. Attached Figure Description

[0026] Figure 1 This is an overall system block diagram of an embodiment of this application.

[0027] Explanation of reference numerals in the attached figures: 1. Data storage module; 2. Sample collection module; 3. Curve generation module; 4. Model generation module; 5. Water quality assessment module; 6. Data display module; 7. Collection and monitoring module; 8. Process generation module; 9. Prediction and judgment module. Detailed Implementation

[0028] The following is in conjunction with the appendix Figure 1 - Further detailed description of this application.

[0029] Example 1: This application discloses a data acquisition method for a wastewater treatment process, the specific steps of which are as follows: Preset test time range, detection time range, and prediction limit difference.

[0030] Multiple water quality information collection points are set up at each step of the water treatment process.

[0031] Set up a process simulation diagram of water treatment process, receive water treatment process, obtain the type of wastewater to be treated according to the water treatment process, divide the water treatment process into multiple nodes according to the treatment area, and connect the nodes in the order of water treatment process to generate process simulation diagram.

[0032] Water quality changes are determined based on the specific water treatment process and wastewater type corresponding to each node.

[0033] The magnitude of water quality change is determined based on the water quality changes at each node.

[0034] Use water testing equipment with known water quality and adjust the equipment according to the test results, and record the test time.

[0035] Wastewater samples were collected at water quality information collection points, the sampling time was recorded, and the wastewater samples were tested using testing equipment. The water quality information and testing time were recorded.

[0036] Determine whether the time between the test time and the detection time is within the test time range.

[0037] An alarm will be issued if the test is not conducted within the specified time frame.

[0038] If the test time is within the specified time range, determine whether the time between the sampling time and the detection time falls within the detection time.

[0039] An alarm will be issued if the detection time is outside the detection period.

[0040] If the test is within the specified time, a preliminary check of the water quality information will be conducted. The magnitude of the water quality change will be used to determine whether any abnormal information has been detected. If any abnormal information is detected, an alarm will be issued.

[0041] If no abnormal information is found, upload the water quality information. The water quality information includes standard parameters and pollutant parameters set according to specific circumstances.

[0042] Mark water quality information collection points on the process simulation diagram. When receiving water quality information, associate the water quality information with the water quality information collection points on the process simulation diagram and record the collection time.

[0043] A composite curve is generated using historical water quality information from each water quality data collection point.

[0044] Set up a neural network model, train the neural network model using a composite curve graph to obtain a curve extension judgment model, split the composite curve graph into multiple water quality data curves, and the curve extension judgment model records the magnitude of change of each water quality data curve and its relationship with the changes of other water quality data curves to obtain the change rules of a single water quality data curve.

[0045] The variation rules of all water quality data curves are incorporated into the composite curve graph for correction, resulting in an algorithm where the variation rules of each water quality data curve conform to each other. Based on this algorithm, the predicted extension curve of the composite curve graph is predicted. The curve extension judgment model outputs the predicted extension curve based on each curve in the received composite curve graph. By training the model through the correlation between each water quality data curve, it can combine the mutual influence between different water quality information, making the data prediction more reasonable and further increasing the confidence of the model's processing.

[0046] The composite curve graph is used as input to the curve extension judgment model to obtain the predicted extension curve. The obtained predicted extension curve is compared with the curves of the same time period on the complete composite curve graph, and deep learning is performed on the curve extension judgment model.

[0047] When new water quality information is received, the previous composite curve is input into the curve extension judgment model. The curve extension judgment model outputs a predicted extension curve. On the predicted extension curve, the coordinate point at the same time as the newly received water quality information is selected. The water quality information of the selected coordinate point is read. The newly received water quality information is corrected according to the water quality information of the selected coordinate point to obtain simulated corrected water quality information. The received water quality information is used as the actual detected water quality information.

[0048] The difference between individual water quality values ​​is calculated by comparing the simulated corrected water quality information and the actual measured water quality information from the same collection point.

[0049] If a difference exceeds the predicted limit, the wastewater at the corresponding sampling point will be re-tested.

[0050] If a single water quality value in the simulated corrected water quality information differs from the same value in the actual measured water quality information, and the difference is less than the prediction limit, it is marked as higher than or lower than expected. Because water quality information is abundant and complex, the system intelligently compares the results after testing and directly outputs the results, making it easier for users to understand the accuracy of the water quality information.

[0051] Displays simulated corrected water quality information and actual tested water quality information.

[0052] The implementation principle of the wastewater treatment process data acquisition method and system in this application embodiment is as follows: In the wastewater treatment process, this system can divide the collection points according to the wastewater treatment process, and then automatically train a deep learning model based on the on-site records. When detecting the wastewater quality later, the deep learning model generates water quality information of expected changes in water quality. Users can compare the actual detection information with the actual detection information to determine whether there is a large deviation in the actual detection information and the direction of the deviation, which can effectively improve the accuracy of detection.

[0053] Example 2: This application discloses a wastewater treatment process data acquisition system, such as... Figure 1 As shown, it includes a data storage module 1, a sample acquisition module 2, a curve generation module 3, a model generation module 4, a water quality judgment module 5, a data display module 6, an acquisition and monitoring module 7, a process generation module 8, and a prediction and judgment module 9.

[0054] like Figure 1 As shown, the process generation module 8 receives the water treatment process, obtains the type of wastewater to be treated based on the water treatment process, divides the water treatment process into multiple nodes according to the treatment area, sorts and connects the nodes according to the order of the water treatment process to generate a process simulation diagram, determines the water quality changes according to the part of the water treatment process and wastewater type corresponding to each node, determines the water quality change range according to the water quality changes of each node, and transmits the processed process simulation diagram to the data storage module 1.

[0055] like Figure 1 As shown, data storage module 1 receives and stores data, and data storage module 1 has a preset flow simulation diagram of water quality treatment process.

[0056] like Figure 1 As shown, the sample collection module 2 calls the process simulation diagram of the data storage module 1, sets multiple water quality information collection points at each step of the water treatment process, receives water quality information uploaded by each collection point, including conventional parameters and pollutant parameters set according to specific circumstances, marks the water quality information collection points on the process simulation diagram, associates the water quality information with the water quality information collection points on the process simulation diagram when receiving water quality information, records the collection time, and transmits the recorded process simulation diagram to the data storage module 1.

[0057] like Figure 1As shown, the acquisition and monitoring module 7 calls the detection point information of the sample acquisition module 2. The acquisition and monitoring module 7 presets the test time range and detection time range, uses water body testing equipment with known water quality and adjusts the testing equipment according to the test results, records the test time, collects sewage samples at the water quality information collection point, records the sampling time, uses the testing equipment to test the sewage samples, records the detected water quality information and detection time, and determines whether the time between the test time and the detection time is within the test time range. If it is not within the test time range, an alarm is issued and the sample acquisition module 2 is prevented from receiving the uploaded water quality information. If it is within the test time range, it determines whether the time between the sampling time and the detection time is within the detection time. If it is not within the detection time range, an alarm is issued and the sample acquisition module 2 is prevented from receiving the uploaded water quality information. If it is within the detection time, a preliminary check is performed on the detected water quality information. Based on the water quality change range on the process simulation diagram, it determines whether there is any abnormal information in the corresponding water quality information. If there is abnormal information, an alarm is issued; if there is no abnormal information, there is no response. By monitoring the testing time of the testing equipment and the detection time of water quality information, the standardization of the data collection process can be effectively monitored, reducing inaccuracies caused by non-standard data collection. The system can determine the magnitude of water quality changes by combining water treatment processes with experience or internet data, and determine whether any anomalies have occurred in the water quality information based on the magnitude of these changes.

[0058] like Figure 1 As shown, the curve generation module 3 calls the water quality information of the data storage module 1, uses the historical water quality information of each water quality information collection point to generate a composite curve, and transmits the composite curve to the model generation module 4 and the water quality judgment module 5.

[0059] like Figure 1As shown, the model generation module 4 has a pre-set neural network model. The neural network model is trained using a composite curve graph to obtain a curve extension judgment model. The composite curve graph is split into multiple water quality data curves. The curve extension judgment model records the relationship between the magnitude of change of each water quality data curve and the changes of other water quality data curves, obtaining the change rules of individual water quality data curves. These change rules are then applied to the composite curve graph for correction, resulting in an algorithm where the change rules of each water quality data curve are mutually consistent. Based on this algorithm, the predicted extension curve of the composite curve graph is predicted. The curve extension judgment model outputs a predicted extension curve based on each curve in the received composite curve graph. A section of the composite curve graph is input into the curve extension judgment model to obtain the predicted extension curve. The obtained predicted extension curve is compared with curves in the same time period on the complete composite curve graph. Deep learning is then applied to the curve extension judgment model, which is then transmitted to the water quality judgment module 5. By training the model through the correlation between each water quality data curve, it can combine the mutual influence between different water quality information, making data prediction more reasonable and further increasing the confidence of the model processing.

[0060] like Figure 1 As shown, the water quality judgment module 5 is connected to the data storage module 1. When the data storage module 1 receives new water quality information, it inputs the previous composite curve into the curve extension judgment model. The curve extension judgment model outputs a predicted extension curve. On the predicted extension curve, it selects the coordinate point at the same time as the newly received water quality information, reads the water quality information of the selected coordinate point, corrects the corresponding newly received water quality information based on the water quality information of the selected coordinate point to obtain simulated corrected water quality information, uses the received water quality information as the actual detected water quality information, and transmits the simulated corrected water quality information and the actual detected water quality information to the data display module 6.

[0061] like Figure 1 As shown, the prediction and judgment module 9 presets a prediction limit difference. It then calls upon the simulated corrected water quality information and the actual detected water quality information from the water quality judgment module 5, comparing the differences in individual water quality values ​​between the simulated corrected and actual detected water quality information at the same collection point. If a difference exceeds the prediction limit difference, an alarm is issued. If an individual water quality value in the simulated corrected water quality information differs from the same value in the actual detected water quality information, and the difference is less than the prediction limit difference, it is marked as higher than or lower than expected. The marked simulated corrected water quality information and actual detected water quality information are then transmitted to the data display module 6. Because water quality information is abundant and complex, the system intelligently compares the results after detection and directly outputs the results, making it easier for users to understand the accuracy of the water quality information. The data display module 6 displays the simulated corrected water quality information and the actual detected water quality information.

[0062] The embodiments described herein are preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape, and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for data acquisition in a wastewater treatment process, characterized in that, Includes the following steps: Multiple water quality information collection points are set up at each step of the water treatment process. Each water quality information collection point collects and uploads water quality information, which includes routine parameters and pollutant parameters set according to specific circumstances. Set up a process simulation diagram of water quality treatment, mark water quality information collection points on the process simulation diagram, associate water quality information with water quality information collection points on the process simulation diagram when receiving water quality information, and record the collection time. A composite curve graph is generated using historical water quality information from each water quality information collection point. Set up a neural network model, train the neural network model using a composite curve graph to obtain a curve extension judgment model, and output a predicted extension curve based on each curve in the received composite curve graph. The composite curve graph is extracted and input into the curve extension judgment model to obtain the predicted extension curve. The obtained predicted extension curve is compared with the curves of the same time period on the complete composite curve graph, and deep learning is performed on the curve extension judgment model. When new water quality information is received, the previous composite curve is input into the curve extension judgment model. The curve extension judgment model outputs a predicted extension curve. On the predicted extension curve, the coordinate point at the same time as the newly received water quality information is selected. The water quality information of the selected coordinate point is read. The newly received water quality information is corrected according to the water quality information of the selected coordinate point to obtain simulated corrected water quality information. The received water quality information is used as the actual detected water quality information. Displays simulated corrected water quality information and actual tested water quality information.

2. The wastewater treatment process data acquisition method according to claim 1, characterized in that, The step "Collect and upload water quality information at each water quality collection point" also includes: Preset test time range and detection time range; Use water testing equipment with known water quality and adjust the equipment according to the test results, and record the test time; Wastewater samples were collected at water quality information collection points, the sampling time was recorded, and the wastewater samples were tested using testing equipment. The water quality information and testing time were recorded. Determine whether the time between the test time and the detection time is within the test time range; An alarm will be issued if the test is not within the specified time frame. If the test time is within the specified time range, determine whether the time between the sampling time and the detection time falls within the detection time. An alarm will be issued if the detection time is not within the specified time range; If the test is within the testing period, a preliminary check of the water quality information will be performed, and an alarm will be issued if any abnormal information is found. If no abnormal information is found, upload the water quality information.

3. The wastewater treatment process data acquisition method according to claim 2, characterized in that, The step "setting up a flow simulation diagram of the water treatment process" also includes: Receive the water treatment process and determine the type of wastewater being treated based on the process. The water treatment process is divided into multiple nodes according to the treatment area, and the nodes are connected in order of the water treatment process to generate a process simulation diagram. The water quality changes are determined based on the water treatment process and wastewater type corresponding to each node. The magnitude of water quality change is determined based on the water quality changes at each node; When new water quality information is received, the system determines whether any abnormal information has appeared based on the magnitude of the water quality change.

4. The wastewater treatment process data acquisition method according to claim 1, characterized in that, The step "training a neural network model using a composite curve graph to obtain a curve extension judgment model" also includes: The composite curve is broken down into multiple water quality data curves. The curve extension judgment model records the magnitude of change of each water quality data curve and its relationship with the changes of other water quality data curves to obtain the change rules of a single water quality data curve. The variation rules of all water quality data curves are incorporated into the composite curve graph for correction, and an algorithm is obtained in which the variation rules of each water quality data curve are consistent with each other. Based on the obtained algorithm, the predicted extension curve of the composite curve graph is predicted.

5. The wastewater treatment process data acquisition method according to claim 1, characterized in that, It also includes the following steps: Preset prediction limit difference; Compare the differences between individual water quality values ​​of simulated corrected water quality information and actual measured water quality information from the same collection point; If a difference exceeds the predicted limit, the wastewater at the corresponding sampling point will be re-tested. If a single water quality value in the simulated corrected water quality information differs from the same water quality value in the actual detected water quality information, and the difference is less than the prediction limit difference, it is marked as higher than expected or lower than expected.

6. A wastewater treatment process data acquisition system, characterized in that: It includes a data storage module (1), a sample collection module (2), a curve generation module (3), a model generation module (4), a water quality judgment module (5), and a data display module (6); The data storage module (1) receives and stores data, and the data storage module (1) is pre-loaded with a process simulation diagram of the water treatment process; The sample collection module (2) calls the process simulation diagram of the data storage module (1), sets multiple water quality information collection points at each step of the water treatment process, receives water quality information uploaded by each collection point, the water quality information includes conventional parameters and pollutant parameters set according to specific circumstances, marks the water quality information collection points on the process simulation diagram, associates the water quality information with the water quality information collection points on the process simulation diagram when receiving water quality information, records the collection time, and transmits the recorded process simulation diagram to the data storage module (1); The curve generation module (3) calls the water quality information of the data storage module (1), uses the historical water quality information of each water quality information collection point to generate a composite curve, and transmits the composite curve to the model generation module (4) and the water quality judgment module (5). The model generation module (4) has a preset neural network model. The neural network model is trained using a composite curve graph to obtain a curve extension judgment model. The curve extension judgment model outputs a predicted extension curve based on each curve in the received composite curve graph. The composite curve graph is extracted and input into the curve extension judgment model to obtain the predicted extension curve. The obtained predicted extension curve is compared with the curves in the same time period on the complete composite curve graph. Deep learning is performed on the curve extension judgment model, and the curve extension judgment model is transmitted to the water quality judgment module (5). The water quality judgment module (5) is connected to the data storage module (1). When the data storage module (1) receives new water quality information, it inputs the previous composite curve into the curve extension judgment model. The curve extension judgment model outputs the predicted extension curve. On the predicted extension curve, it selects the coordinate point at the same time as the newly received water quality information, reads the water quality information of the selected coordinate point, corrects the corresponding newly received water quality information according to the water quality information of the selected coordinate point to obtain the simulated corrected water quality information, uses the received water quality information as the actual detected water quality information, and transmits the simulated corrected water quality information and the actual detected water quality information to the data display module (6). The data display module (6) displays simulated corrected water quality information and actual detected water quality information.

7. The wastewater treatment process data acquisition system according to claim 6, characterized in that: It also includes a data acquisition and monitoring module (7), which calls the detection point information of the sample acquisition module (2). The data acquisition and monitoring module (7) presets the test time range and the detection time range, uses a water body testing instrument with known water quality and adjusts the testing instrument according to the test results, records the test time, collects sewage samples at the water quality information collection point, records the sampling time, uses the testing instrument to test the sewage samples, records the detected water quality information and the detection time, and judges whether the time between the test time and the detection time is within the test time range. If it is not within the test time range, it issues an alarm and prevents the sample acquisition module (2) from receiving the uploaded water quality information. If it is within the test time range, it judges whether the time between the sampling time and the detection time is within the detection time. If it is not within the detection time range, it issues an alarm and prevents the sample acquisition module (2) from receiving the uploaded water quality information. If it is within the detection time, it performs a preliminary check on the detected water quality information. If abnormal information is found, it issues an alarm. If no abnormal information is found, it does not react.

8. A wastewater treatment process data acquisition system according to claim 7, characterized in that: It also includes a process generation module (8), which receives the water treatment process, obtains the type of wastewater to be treated according to the water treatment process, divides the water treatment process into multiple nodes according to the treatment area, connects the nodes in the order of the water treatment process to generate a process simulation diagram, determines the water quality change according to the part of the water treatment process and the type of wastewater corresponding to each node, determines the water quality change range according to the water quality change of each node, and transmits the processed process simulation diagram to the data storage module (1). When the acquisition and monitoring module (7) receives new water quality information, it determines whether there is any abnormal information in the corresponding water quality information based on the water quality change range on the process simulation diagram.

9. A wastewater treatment process data acquisition system according to claim 6, characterized in that: The model generation module (4) splits the composite curve graph into multiple water quality data curves. The curve extension judgment model records the relationship between the change of each water quality data curve and the change of other water quality data curves, obtains the change rules of a single water quality data curve, and brings the change rules of all water quality data curves into the composite curve graph for correction, obtains an algorithm in which the change rules of each water quality data curve are consistent with each other, and predicts the predicted extension curve of the composite curve graph based on the obtained algorithm.

10. A wastewater treatment process data acquisition system according to claim 6, characterized in that: It also includes a prediction and judgment module (9), which presets a prediction limit difference. The prediction and judgment module (9) calls the simulated corrected water quality information and the actual detected water quality information of the water quality judgment module (5), compares the difference of the single water quality values ​​of the simulated corrected water quality information and the actual detected water quality information at the same collection point, and if there is a difference exceeding the prediction limit difference, an alarm is issued. If the single water quality value in the simulated corrected water quality information is different from the same water quality value in the actual detected water quality information, and the difference is less than the prediction limit difference, it is marked as higher than expected or lower than expected, and the marked simulated corrected water quality information and actual detected water quality information are transmitted to the data display module (6).

Images