Abnormal pollution discharge detection method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a pollution discharge anomaly detection method and device, a nonvolatile storage medium and electronic equipment. The method comprises the steps that first power consumption data corresponding to multiple pieces of production equipment and second power consumption data corresponding to pollution control equipment are obtained, and the pollution control equipment is used for processing pollution discharge caused by the multiple pieces of production equipment; based on the first power consumption data and the second power consumption data corresponding to the multiple production devices, identification results corresponding to the multiple production devices are determined, and the identification results are used for indicating whether the corresponding production devices are abnormal in pollution discharge or not; determining target equipment of which the identification result indicates that the pollution discharge is abnormal in the multiple pieces of production equipment; and on the basis of the first power utilization data corresponding to the target equipment, determining an abnormal discharge amount of the target equipment caused by abnormal pollution discharge. According to the invention, the technical problem of non-ideal sewage discharge anomaly detection efficiency in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of sewage discharge detection, and in particular, to a method, device, non-volatile storage medium, and electronic device for detecting abnormal sewage discharge. Background Art

[0002] With the rapid advancement of industrialization, the environmental pollution problems of enterprises have become increasingly severe, and the emission monitoring and treatment of enterprises have become an urgent task. In related technologies, it is difficult for emission monitoring to meet the requirements of accurate monitoring of enterprise pollution emissions. In related technologies, methods such as on-site sampling and analysis detection, wireless sensor network detection, image recognition detection, and remote sensing satellite detection are used for sewage discharge detection. Among them, the sampling and analysis method judges the sewage discharge situation by collecting samples on-site and then performing detection and analysis. The wireless sensor network monitoring performs sewage discharge detection by installing sensor nodes and processing the data received by the sensors. The image processing and recognition technology obtains image data through cameras, drones, or other image acquisition devices, and analyzes and processes the image data to detect abnormal sewage discharge. The on-site sampling and analysis detection method has technical problems of untimely detection and high detection costs. In related technologies, it relies on relevant detections of emission results and requires additional detection equipment, resulting in high limitations in the processing of sewage discharge detection and unsatisfactory processing efficiency.

[0003] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, non-volatile storage medium, and electronic device for detecting abnormal sewage discharge, so as to at least solve the technical problem of unsatisfactory efficiency in detecting abnormal sewage discharge in related technologies.

[0005] According to one aspect of the embodiments of the present invention, a method for detecting abnormal sewage discharge is provided, including: obtaining first power consumption data respectively corresponding to a plurality of production devices, and second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharged by the plurality of production devices respectively; determining identification results respectively corresponding to the plurality of production devices based on the first power consumption data respectively corresponding to the plurality of production devices and the second power consumption data, where the identification results are used to indicate whether the corresponding production devices have abnormal sewage discharge; determining target devices in the plurality of production devices whose identification results indicate abnormal sewage discharge; and determining abnormal discharge amounts generated by the target devices due to abnormal sewage discharge based on the first power consumption data corresponding to the target devices.

[0006] Optionally, determining the recognition results corresponding to the multiple production devices based on the first power consumption data corresponding to the multiple production devices and the second power consumption data includes: determining the first operation characteristics corresponding to the multiple production devices based on the first power consumption data corresponding to the multiple production devices; determining the second operation characteristics corresponding to the pollution control device based on the second power consumption data corresponding to the pollution control device; processing the second operation characteristics and the first operation characteristics corresponding to the multiple production devices respectively by using a first predetermined recognition model to determine the recognition results corresponding to the multiple production devices, where the first predetermined recognition model is determined based on the first historical characteristics corresponding to the multiple production devices and the second historical characteristics corresponding to the pollution control device in a predetermined historical time period.

[0007] Optionally, determining the first operation characteristics corresponding to the multiple production devices based on the first power consumption data corresponding to the multiple production devices includes: for a first device among the multiple production devices, when the first power consumption data corresponding to the first device includes multiple types of electrical parameters corresponding to different power consumption types, determining the extraction strategies corresponding to the multiple types of electrical parameters according to the power consumption types corresponding to the multiple types of electrical parameters; using the extraction strategies corresponding to the multiple types of electrical parameters to perform extraction processing on the multiple types of electrical parameters to obtain candidate operation characteristics corresponding to the multiple types of electrical parameters; determining the first operation characteristics corresponding to the first device based on the device type corresponding to the first device among the candidate operation characteristics corresponding to the multiple types of electrical parameters; and determining the first operation characteristics corresponding to the multiple production devices in the same way as obtaining the first operation characteristics corresponding to the first device.

[0008] Optionally, determining the abnormal emission amount generated by the target device due to abnormal sewage discharge based on the first power consumption data corresponding to the target device includes: determining the target recognition model corresponding to the target device among multiple second predetermined recognition models, where the multiple second predetermined recognition models respectively correspond to the multiple production devices, and the multiple second predetermined recognition models are respectively trained by using the historical operation data and historical abnormal data of the corresponding production devices, the historical operation data is the power consumption data of the corresponding production device during normal operation in a predetermined historical time period, and the historical abnormal data is the emission data generated by the corresponding production device during abnormal operation in the predetermined historical time period; and processing the first power consumption data corresponding to the target device by using the target recognition model to determine the abnormal emission amount.

[0009] Optionally, the obtaining of the first power consumption data corresponding to the multiple production devices includes: obtaining the initial power consumption data corresponding to the multiple production devices respectively by using a wired manner and / or a wireless manner; performing noise reduction processing on the initial power consumption data corresponding to the multiple production devices respectively to obtain the noise reduction data corresponding to the multiple production devices respectively; and performing data complementation on the noise reduction data corresponding to the multiple production devices respectively according to a predetermined time series to obtain the first power consumption data corresponding to the multiple production devices respectively.

[0010] Optionally, the method further includes: when there are multiple target devices, determining the device position information, device function information, and timing information indicating the abnormal occurrence time corresponding to the multiple target devices respectively; and determining an emission control strategy based on the device position information, device function information, and timing information corresponding to the multiple target devices respectively.

[0011] Optionally, the determining of the emission control strategy based on the device position information, device function information, and timing information corresponding to the multiple target devices respectively includes: performing visualization processing on the device position information, device function information, and timing information corresponding to the multiple target devices respectively to generate a knowledge graph including the multiple target devices; processing the knowledge graph by using a graph neural network to determine the association paths of the multiple target devices; determining the operation control parameters corresponding to the multiple target devices respectively based on the association paths; and adjusting the multiple target devices according to the operation control parameters corresponding to the multiple target devices respectively as the emission control strategy.

[0012] According to another aspect of the embodiments of the present invention, there is provided a sewage discharge anomaly detection device, including: a data acquisition module, configured to acquire the first power consumption data corresponding to multiple production devices respectively and the second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharged by the multiple production devices respectively; an anomaly identification module, configured to determine the identification results corresponding to the multiple production devices respectively based on the first power consumption data corresponding to the multiple production devices respectively and the second power consumption data, where the identification results are used to indicate whether the corresponding production devices have sewage discharge anomalies; a device confirmation module, configured to determine target devices in the multiple production devices whose identification results indicate sewage discharge anomalies; and an emission confirmation module, configured to determine the abnormal emission amounts generated by the target devices due to sewage discharge anomalies based on the first power consumption data corresponding to the target devices.

[0013] According to another aspect of the embodiments of the present invention, there is provided a non-volatile storage medium storing multiple instructions, and the instructions are suitable for being loaded and executed by a processor to execute any one of the sewage discharge anomaly detection methods.

[0014] According to another aspect of the embodiments of the present invention, there is provided an electronic device, including: one or more processors and a memory, where the memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the sewage discharge anomaly detection method described in any one of the above.

[0015] In the embodiments of the present invention, by obtaining first power consumption data respectively corresponding to a plurality of production devices and second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharges caused by the plurality of production devices respectively; based on the first power consumption data respectively corresponding to the plurality of production devices and the second power consumption data, determining identification results respectively corresponding to the plurality of production devices, where the identification results are used to indicate whether the corresponding production devices have sewage discharge anomalies; determining target devices among the plurality of production devices whose identification results indicate sewage discharge anomalies; and based on the first power consumption data corresponding to the target devices, determining the abnormal discharge amounts generated by the target devices due to sewage discharge anomalies. The purpose of determining the abnormal discharge amounts by analyzing the power consumption data is achieved, the technical effect of improving the efficiency of sewage discharge anomaly detection is realized, and further the technical problem of unsatisfactory efficiency of sewage discharge anomaly detection existing in the related art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0017] Figure 1 is a flowchart of an optional sewage discharge anomaly detection method provided according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of data processing of an optional sewage discharge anomaly detection method provided according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a page of an optional sewage discharge anomaly detection method provided according to an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of an optional sewage discharge anomaly detection device provided according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, an embodiment of a method for detecting abnormal sewage discharge is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0024] Figure 1 is a flowchart of a method for detecting abnormal sewage discharge according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0025] Step S102, obtain first power consumption data respectively corresponding to multiple production devices and second power consumption data corresponding to a pollution treatment device, wherein the pollution treatment device is used to treat the sewage discharged by each of the multiple production devices;

[0026] It can be understood that the pollution treatment device treats the sewage discharged by each of the multiple production devices. By installing detection devices on the multiple production devices and the pollution treatment device, the first power consumption data corresponding to the multiple production devices and the second power consumption data corresponding to the pollution treatment device are obtained, providing data support for subsequent processing. Through the above processing, the first power consumption data respectively corresponding to the multiple production devices and the second power consumption data corresponding to the pollution treatment device are obtained, providing data support for subsequent detection of abnormal sewage discharge based on the power consumption data.

[0027] Optionally, the detection device may include, for example, a current transformer, an instrument for converting a large current on the primary side into a small current on the secondary side to measure current, a voltage transformer, an instrument for realizing the voltage measurement function by converting the high voltage of a high-voltage circuit or a low-voltage circuit into a low voltage, an industrial power quality analyzer, a dedicated instrument for analyzing the operation quality of a power grid, etc. The detection device may collect power consumption data at a high frequency of, for example, 100 Hz to ensure that the instantaneous changes of electrical parameters are detected.

[0028] In an optional embodiment, obtaining the first power consumption data corresponding to multiple production devices respectively includes: obtaining the initial power consumption data corresponding to multiple production devices respectively by using a wired method and / or a wireless method; performing noise reduction processing on the initial power consumption data corresponding to multiple production devices respectively to obtain the noise reduction data corresponding to multiple production devices respectively; and performing data complementation on the noise reduction data corresponding to multiple production devices respectively according to a predetermined time series to obtain the first power consumption data corresponding to multiple production devices respectively.

[0029] It can be understood that, in order to expand the detection range, the obtained initial power consumption data is transmitted to the data server by using a wired method and / or a wireless method. There will be noise in the obtained initial power consumption data, so it is necessary to perform noise reduction processing on the initial power consumption data. There will be data missing in the data after noise reduction processing. The noise reduction data after noise reduction processing is complemented according to the time series. Data complementation can be performed by using methods such as linear interpolation method, moving average method, regression method, etc. The first power consumption data corresponding to multiple production devices respectively is obtained based on the complemented data. Through the above processing, the noise reduction processing and complementation processing are performed on the data transmitted to the server by wire or wirelessly, improving the data quality of the power consumption data for analysis and improving the accuracy of detecting abnormal sewage discharge.

[0030] Optionally, the noise reduction processing may be performed by using, for example, a wavelet transform algorithm. A wavelet basis function matching the characteristics of the initial power consumption data is selected, and the initial power consumption data is wavelet decomposed to obtain wavelet coefficients at different scales. The decomposition can be performed using discrete wavelet transform. A noise reduction threshold is determined, the threshold processing is applied to the wavelet coefficients, and the processed wavelet coefficients are used for signal reconstruction. The processed wavelet coefficients are reconstructed into a noise-reduced signal through inverse wavelet transform to obtain the noise reduction data.

[0031] Optionally, in order to exclude the error data caused by instrument failures, data cleaning operations may be performed on the collected initial power consumption data. The data cleaning may be performed in the following ways: deleting outliers, performing smoothing processing by using a moving average method, deleting duplicate values, standardizing the data ratio, performing data normalization processing, etc.

[0032] Optionally, Figure 2It is a schematic diagram of data processing for an optional sewage discharge anomaly detection method provided according to an embodiment of the present invention. As Figure 2 shown, first, multiple sets of current transformers, voltage transformers, and industrial power quality analyzers are installed on multiple production devices and pollution control devices to collect data such as voltage, current, and power of multiple production devices and pollution control devices. The collected data is transmitted to the data server through wired transmission or wireless transmission. Among them, wired transmission can use, for example, an RJ45 (Registered Jack 45) interface or a USB (Universal Serial Bus) interface. Wireless transmission can use, for example, 4G network (Fourth Generation network communication technology), LoRa (Long Range), WiFi (Wireless Fidelity), etc. The data server stores data using, for example, a relational database.

[0033] Step S104: Based on the first power consumption data and the second power consumption data respectively corresponding to multiple production devices, determine the recognition results respectively corresponding to multiple production devices, where the recognition results are used to indicate whether the corresponding production devices have sewage discharge anomalies;

[0034] It can be understood that by analyzing the first power consumption data and the second power consumption data respectively corresponding to multiple production devices, the recognition results respectively corresponding to multiple production devices are determined, and the recognition results are whether the corresponding production devices have sewage discharge anomalies. Through the above processing, by analyzing the first power consumption data and the second power consumption data respectively corresponding to multiple production devices, the production devices with sewage discharge anomalies are determined among multiple production devices according to the recognition results, improving the efficiency of detecting production devices with sewage discharge anomalies.

[0035] In an optional embodiment, based on the first power consumption data and the second power consumption data respectively corresponding to multiple production devices, determining the recognition results respectively corresponding to multiple production devices includes: based on the first power consumption data respectively corresponding to multiple production devices, determining the first operation characteristics respectively corresponding to multiple production devices; based on the second power consumption data corresponding to the pollution control device, determining the second operation characteristics corresponding to the pollution control device; based on the second operation characteristics and the first operation characteristics respectively corresponding to multiple production devices, using a first predetermined recognition model for processing to determine the recognition results respectively corresponding to multiple production devices, where the first predetermined recognition model is determined based on the first historical characteristics respectively corresponding to multiple production devices and the second historical characteristics corresponding to the pollution control device in a predetermined historical time period.

[0036] It can be understood that, based on the first power consumption data corresponding to multiple production devices respectively, feature extraction is performed to extract the first operation features that effectively reflect the respective operation states of the multiple production devices. Based on the second power consumption data corresponding to the pollution control device, feature extraction is performed to extract the second operation features that effectively reflect the operation state of the pollution control device. The historical operation data corresponding to the multiple production devices and the pollution control device are used to construct a training data set, and a first predetermined recognition model is trained. Based on the second power consumption data corresponding to the pollution control device and the first operation features corresponding to the multiple production devices respectively, the pre-trained first predetermined recognition model is used for processing, so as to obtain the recognition results corresponding to the multiple production devices. Through the above processing, the pre-trained first predetermined recognition model is used to process the first operation features and the second operation features, and the recognition results corresponding to the multiple production devices are obtained, improving the recognition efficiency.

[0037] Optionally, the first predetermined recognition model can adopt an SVM model (Support Vector Machines). The SVM model is a linear classifier with the largest margin defined in the feature space. The largest margin makes it different from the perceptron; the SVM also includes a kernel trick, which makes it a substantially non-linear classifier. The learning strategy of the SVM is to maximize the margin, which can be formalized as a problem of solving a convex quadratic programming, and is also equivalent to the minimization problem of the regularized hinge loss function. The learning algorithm of the SVM can be an optimization algorithm for solving convex quadratic programming.

[0038] Optionally, the historical operation data corresponding to the multiple production devices and the pollution control device are used to construct a training data set. The data in the normal state is marked as 1, and the data in the fault state is marked as -1. The power consumption and power consumption stability are selected as features to construct two feature vectors, x1: average active power, and x2: degree of power consumption fluctuation.

[0039] In an optional embodiment, based on the first power consumption data corresponding to multiple production devices respectively, determining the first operation features corresponding to the multiple production devices respectively includes: for the first device among the multiple production devices, when the first power consumption data corresponding to the first device includes multiple types of electrical parameters corresponding to different power consumption types, determining the extraction strategies corresponding to the multiple types of electrical parameters according to the power consumption types corresponding to the multiple types of electrical parameters; using the extraction strategies corresponding to the multiple types of electrical parameters to perform extraction processing on the multiple types of electrical parameters to obtain the candidate operation features corresponding to the multiple types of electrical parameters respectively; based on the device type corresponding to the first device, determining the first operation feature corresponding to the first device among the candidate operation features corresponding to the multiple types of electrical parameters respectively; using the method of obtaining the first operation feature corresponding to the first device to determine the first operation features corresponding to the multiple production devices respectively.

[0040] It can be understood that there are multiple types of electrical parameters, such as voltage data type, current data type, and power data type. For electrical parameters of different electricity consumption types, corresponding extraction strategies need to be adopted to extract operation characteristics. When extracting the first operation characteristics from the first electricity consumption data corresponding to the first device among multiple production devices, corresponding extraction strategies are adopted for extraction processing according to multiple types of electrical parameters of different electricity consumption types in the first electricity consumption data, so as to obtain candidate operation characteristics corresponding to multiple types of electrical parameters respectively. Different production devices have different power demands, and the candidate operation characteristics corresponding to different types of electrical parameters provide different targeted feature information. Therefore, among the candidate operation characteristics corresponding to multiple types of electrical parameters obtained, the candidate operation characteristics with the highest pertinence to the first device should be selected as the first operation characteristics corresponding to the first device. By adopting the above method, the first operation characteristics corresponding to multiple production devices are determined respectively. Through the above processing, the first operation characteristics corresponding to multiple production devices are obtained, ensuring the relevance between multiple production devices and their corresponding first operation characteristics, and improving the efficiency of feature information extraction.

[0041] Step S106: Determine the target device whose identification result indicates sewage discharge abnormality among multiple production devices;

[0042] It can be understood that according to the identification results corresponding to multiple production devices, such as normal or abnormal, the target device with the identification result of sewage discharge abnormality is determined. Through the above processing, the target device with sewage discharge abnormality is determined among multiple production devices, improving the efficiency of sewage discharge abnormality detection for the target device with sewage discharge abnormality.

[0043] Step S108: Based on the first electricity consumption data corresponding to the target device, determine the abnormal discharge amount generated by the target device due to sewage discharge abnormality.

[0044] It can be understood that according to the first electricity consumption data corresponding to the target device, the abnormal discharge amount generated by the target device due to sewage discharge abnormality can be determined. Through the above processing, the abnormal discharge amount generated by the target device with sewage discharge abnormality is clarified, realizing sewage discharge abnormality detection.

[0045] In an alternative embodiment, determining the abnormal emission amount generated by the target device due to abnormal sewage discharge based on the first power consumption data corresponding to the target device includes: determining the target recognition model corresponding to the target device among a plurality of second predetermined recognition models, where the plurality of second predetermined recognition models respectively correspond to a plurality of production devices, and the plurality of second predetermined recognition models are respectively trained using the historical operation data and historical abnormal data of the corresponding production devices. The historical operation data is the power consumption data of the corresponding production device during normal operation in a predetermined historical time period, and the historical abnormal data is the emission data generated by the corresponding production device during abnormal operation in a predetermined historical time period; based on the first power consumption data corresponding to the target device, processing using the target recognition model to determine the abnormal emission amount.

[0046] It can be understood that a training data set is constructed using the power consumption data during normal operation and the emission data generated during abnormal operation of a plurality of production devices in a predetermined historical time period, and a plurality of second predetermined recognition models corresponding to the plurality of production devices are trained. Among the plurality of second predetermined recognition models, the target recognition model corresponding to the target device is determined, and the first power consumption data corresponding to the target device is processed using the target recognition model to obtain the abnormal emission amount of the target. Through the above processing, according to the characteristics of each production device, corresponding second predetermined recognition models are used for processing, improving the accuracy and pertinence of abnormal sewage discharge detection.

[0047] In an alternative embodiment, the method further includes: when there are multiple target devices, determining the device location information, device function information, and timing information indicating the abnormal occurrence time corresponding to each of the multiple target devices; based on the device location information, device function information, and timing information corresponding to each of the multiple target devices, determining an emission control strategy.

[0048] It can be understood that when abnormal sewage discharge occurs in multiple production devices, the device location information, device function information, and timing information indicating the time of abnormal occurrence corresponding to each of the multiple target devices are clarified. According to the device location information, device function information, and timing information indicating the time of abnormal occurrence corresponding to each of the multiple target devices, an emission control strategy is determined. Through the above processing, the emission control strategy in different situations is clarified, improving the efficiency of abnormal sewage discharge treatment.

[0049] In an alternative embodiment, based on the device location information, device function information, and timing information respectively corresponding to multiple target devices, an emission control strategy is determined, including: performing visualization processing on the device location information, device function information, and timing information respectively corresponding to multiple target devices to generate a knowledge graph including multiple target devices; using a graph neural network to process the knowledge graph to determine the association paths of multiple target devices; determining the operation control parameters respectively corresponding to multiple target devices based on the association paths; and adjusting multiple target devices according to the operation control parameters respectively corresponding to multiple target devices as the emission control strategy.

[0050] It can be understood that visualization processing is performed on the device location information, device function information, and timing information respectively corresponding to multiple target devices. For example, data is displayed using charts to generate a knowledge graph including the device location information, device function information, and timing information of multiple target devices. The generated knowledge graph including multiple target devices is processed using a graph neural network to identify the association paths between multiple target devices. The operation control parameters respectively corresponding to multiple target devices are determined based on the association paths between multiple target devices. The determined emission control strategy is to adjust multiple target devices according to the operation control parameters respectively corresponding to multiple target devices. Through the above processing, an emission control strategy is automatically generated based on the device location information, device function information, and timing information respectively corresponding to multiple target devices, improving the matching degree of the emission control strategy.

[0051] Optionally, Figure 3 is a page schematic diagram of an alternative sewage discharge anomaly detection method provided according to an embodiment of the present invention. As Figure 3 shown, the page displays a real-time trend graph, sets threshold warning prompts. When a fault occurs, specific fault modes, estimated emissions, etc. are prompted through a page pop-up window, facilitating the response of operators. It displays real-time carbon consumption, real-time emission reduction, cumulative carbon consumption, and cumulative emission reduction (simply indicated by dashed or solid lines in the figure). Four charts are used to display the change curve of overall carbon consumption over time, the change curve of emission reduction over time, the relationship between energy consumption and power factor over time, and a pie chart of carbon consumption distribution (where areas A, B, C, and D are only for illustration).

[0052] Through the above step S102, first electricity consumption data corresponding to multiple production devices and second electricity consumption data corresponding to a pollution control device are obtained, where the pollution control device is used to treat the sewage discharged by the multiple production devices respectively; step S104, based on the first electricity consumption data corresponding to the multiple production devices and the second electricity consumption data, identification results corresponding to the multiple production devices are determined, where the identification results are used to indicate whether the corresponding production devices have abnormal sewage discharge; step S106, target devices whose identification results indicate abnormal sewage discharge are determined among the multiple production devices; step S108, based on the first electricity consumption data corresponding to the target devices, the abnormal discharge amount generated by the target devices due to abnormal sewage discharge is determined, which can achieve the purpose of determining the abnormal discharge amount by analyzing the electricity consumption data, and achieve the technical effect of improving the efficiency of detecting abnormal sewage discharge, thereby solving the technical problem of unsatisfactory efficiency of detecting abnormal sewage discharge in the related art.

[0053] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation manner. Detection devices such as current transformers, voltage transformers, and industrial power quality analyzers are respectively installed on multiple power devices and pollution control devices to collect electricity consumption data. The obtained electricity consumption data is transmitted to the database by wired and / or wireless means. The collected electricity consumption data is subjected to noise reduction processing and data completion processing.

[0054] Extraction strategies corresponding to multiple types of electrical parameters are determined according to the electricity consumption types corresponding to the multiple types of electrical parameters, that is, the electricity consumption data. The multiple types of electrical parameters are subjected to extraction processing by using the extraction strategies corresponding to the multiple types of electrical parameters to obtain candidate operation characteristics corresponding to the multiple types of electrical parameters. Among the candidate operation characteristics corresponding to the multiple types of electrical parameters, the first operation characteristic corresponding to the first device is determined, and the first operation characteristics corresponding to the multiple production devices are determined by using the method of obtaining the first operation characteristic corresponding to the first device. According to the second electricity consumption data corresponding to the pollution control device, the second operation characteristic corresponding to the pollution control device is determined. A training data set is constructed by using the historical operation data corresponding to the multiple production devices and the pollution control device respectively, and a first predetermined identification model is trained.

[0055] According to the second operation characteristics and the first operation characteristics corresponding to multiple production devices respectively, use the first predetermined recognition model for processing to determine the recognition results corresponding to multiple production devices respectively, and determine the target devices whose recognition results indicate abnormal sewage discharge. Use the electricity consumption data during normal operation and the emission data generated during abnormal operation of multiple production devices in a predetermined historical time period to construct a training data set, and train to obtain a second predetermined recognition model corresponding to multiple production devices. Among multiple second predetermined recognition models, determine the target recognition model corresponding to the target device, and use the target recognition model to process the first electricity consumption data corresponding to the target device to determine the abnormal emission amount. When there are multiple target devices, determine the device location information, device function information, and timing information indicating the moment of abnormality corresponding to multiple target devices respectively.

[0056] Visualize the device location information, device function information, and timing information corresponding to multiple target devices respectively to generate a knowledge graph including multiple target devices. Use a graph neural network to process the knowledge graph to determine the association paths of multiple target devices. According to the association paths, determine the operation control parameters corresponding to multiple target devices respectively, and adjust multiple target devices according to the operation control parameters corresponding to multiple target devices respectively as the emission control strategy.

[0057] The above optional implementation manners at least achieve the following effects: By analyzing the first electricity consumption data corresponding to multiple production devices respectively and the second electricity consumption data corresponding to the pollution treatment device, the production devices with abnormal sewage discharge are determined among multiple production devices, improving the efficiency of detecting production devices with abnormal sewage discharge. Adopting the corresponding second predetermined recognition model for processing according to the characteristics of each production device improves the accuracy and pertinence of abnormal sewage discharge detection. By analyzing the electricity consumption data of the production devices with abnormal sewage discharge, the abnormal emission amount is determined, reducing the cost of abnormal sewage discharge detection and improving the efficiency of abnormal sewage discharge detection. By displaying the pollutant emission data in real time on the page, the pollutant emission situation is intuitively shown. An emission control strategy is automatically generated through the device location information, device function information, and timing information corresponding to multiple target devices respectively, improving the emission control efficiency.

[0058] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0059] In this embodiment, a sewage discharge anomaly detection device is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the terms "module" and "device" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0060] According to an embodiment of the present invention, an embodiment of a device for implementing sewage discharge anomaly detection is also provided. Figure 4 It is a schematic diagram of a sewage discharge anomaly detection device according to an embodiment of the present invention. As Figure 4 shown, the above-mentioned sewage discharge anomaly detection device includes a data acquisition module 402, an anomaly identification module 404, a device confirmation module 406, and an emission confirmation module 408. The device will be described below.

[0061] The data acquisition module 402 is used to acquire first power consumption data respectively corresponding to multiple production devices, and second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharged by the multiple production devices respectively.

[0062] The anomaly identification module 404 is connected to the data acquisition module 402 and is used to determine identification results respectively corresponding to the multiple production devices based on the first power consumption data respectively corresponding to the multiple production devices and the second power consumption data, where the identification results are used to indicate whether the corresponding production devices have sewage discharge anomalies.

[0063] The device confirmation module 406 is connected to the anomaly identification module 404 and is used to determine target devices among the multiple production devices whose identification results indicate sewage discharge anomalies.

[0064] The emission confirmation module 408 is connected to the device confirmation module 406 and is used to determine the abnormal emission amount generated by the target device due to sewage discharge anomalies based on the first power consumption data corresponding to the target device.

[0065] In a sewage discharge anomaly detection device provided by an embodiment of the present invention, a data acquisition module 402 is provided for acquiring first power consumption data corresponding to multiple production devices respectively, and second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharged by the multiple production devices respectively; an anomaly identification module 404, connected to the data acquisition module 402, for determining identification results corresponding to the multiple production devices respectively based on the first power consumption data corresponding to the multiple production devices respectively and the second power consumption data, where the identification results are used to indicate whether the corresponding production devices have sewage discharge anomalies; a device confirmation module 406, connected to the anomaly identification module 404, for determining target devices among the multiple production devices whose identification results indicate sewage discharge anomalies; an emission confirmation module 408, connected to the device confirmation module 406, for determining abnormal emissions generated by the target devices due to sewage discharge anomalies based on the first power consumption data corresponding to the target devices. The purpose of determining abnormal emissions by analyzing power consumption data is achieved, and the technical effect of improving the efficiency of sewage discharge anomaly detection is realized, thereby solving the technical problem of unsatisfactory efficiency of sewage discharge anomaly detection in the related art.

[0066] It should be noted that the above-mentioned various modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following manner: the above-mentioned various modules can be located in the same processor; or, the above-mentioned various modules are located in different processors in any combination.

[0067] It should be noted here that the above-mentioned data acquisition module 402, anomaly identification module 404, device confirmation module 406, and emission confirmation module 408 correspond to steps S102 to S108 in the embodiment. The examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the content disclosed in the above-mentioned embodiment. It should be noted that the above-mentioned modules can run in a computer terminal as part of the device.

[0068] It should be noted that the optional or preferred implementation manners of this embodiment can refer to the relevant descriptions in the embodiment, and will not be repeated here.

[0069] The above-mentioned sewage discharge anomaly detection device may further include a processor and a memory. The data acquisition module 402, anomaly identification module 404, device confirmation module 406, emission confirmation module 408, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement corresponding functions.

[0070] The processor contains cores, which retrieve corresponding program units from the memory. One or more cores can be set. The memory may include non-permanent memory in a computer-readable medium, forms such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0071] An embodiment of the present invention provides a non-volatile storage medium with a program stored thereon, and when the program is executed by a processor, it implements a sewage discharge anomaly detection method. An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining first power consumption data corresponding to multiple production devices respectively, and second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharged by multiple production devices respectively; based on the first power consumption data corresponding to multiple production devices respectively and the second power consumption data, determining identification results corresponding to multiple production devices respectively, where the identification results are used to indicate whether the corresponding production device has a sewage discharge anomaly; determining target devices among multiple production devices whose identification results indicate a sewage discharge anomaly; based on the first power consumption data corresponding to the target devices, determining the abnormal discharge amount generated by the target devices due to the sewage discharge anomaly. The devices herein can be servers, PCs, etc.

[0072] The present invention also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program initialized with the following method steps: obtaining first power consumption data corresponding to multiple production devices respectively, and second power consumption data corresponding to a pollution treatment device, where the pollution treatment device is used to treat the sewage discharged by multiple production devices respectively; based on the first power consumption data corresponding to multiple production devices respectively and the second power consumption data, determining identification results corresponding to multiple production devices respectively, where the identification results are used to indicate whether the corresponding production device has a sewage discharge anomaly; determining target devices among multiple production devices whose identification results indicate a sewage discharge anomaly; based on the first power consumption data corresponding to the target devices, determining the abnormal discharge amount generated by the target devices due to the sewage discharge anomaly.

[0073] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block in the flowchart illustrations and / or block diagrams, and combinations of flows and / or blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processors of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing device create means for implementing the functions specified in the flowchart Figure 1 one flow or more flows and / or blocks Figure 1 or means for implementing the functions specified in one block or more blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in the flowchart Figure 1 one flow or more flows and / or blocks Figure 1 or means for implementing the functions specified in one block or more blocks.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flowchart Figure 1 one flow or more flows and / or blocks Figure 1 or means for implementing the functions specified in one block or more blocks.

[0077] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0078] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory. The memory is an example of computer-readable media.

[0079] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0081] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0082] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for detecting abnormal sewage discharge, characterized in that: include: Acquire first power consumption data corresponding to a plurality of production equipment, and second power consumption data corresponding to a pollution control equipment, wherein the pollution control equipment is used to process pollution caused by the plurality of production equipment; Based on the first power consumption data respectively corresponding to the plurality of production equipment and the second power consumption data, determining the identification results respectively corresponding to the plurality of production equipment, wherein the identification results are used to indicate whether the corresponding production equipment has abnormal discharge of pollutants; Determining, among the plurality of production equipment, a target equipment indicated by the identification result as having abnormal pollution discharge; Based on the first power consumption data corresponding to the target device, an abnormal emission amount of the target device due to abnormal pollution discharge is determined.

2. The method according to claim 1, characterized in that The determining, based on the first power usage data respectively corresponding to the plurality of production devices and the second power usage data, the identification results respectively corresponding to the plurality of production devices comprises: Determining first operation characteristics respectively corresponding to the plurality of production equipment based on first power consumption data respectively corresponding to the plurality of production equipment; determining a second operation characteristic corresponding to the pollution control equipment based on the second electricity consumption data corresponding to the pollution control equipment; Based on the second operating characteristic and the first operating characteristics corresponding to the multiple production equipment respectively, a first predetermined recognition model is used for processing to determine the recognition results corresponding to the multiple production equipment respectively, wherein the first predetermined recognition model is determined based on the first historical characteristics corresponding to the multiple production equipment respectively in a predetermined historical time period and the second historical characteristics corresponding to the pollution control equipment.

3. The method according to claim 2, characterized in that The determining, based on the first power consumption data respectively corresponding to the plurality of production equipment, the first operation characteristics respectively corresponding to the plurality of production equipment comprises: For a first device among the multiple production devices, when the first power usage data corresponding to the first device includes multiple types of electrical parameters of different power usage types, determining extraction strategies corresponding to the multiple types of electrical parameters respectively according to the power usage types respectively corresponding to the multiple types of electrical parameters; Using extraction strategies corresponding to the multiple types of electrical parameters, respectively, to extract and process the multiple types of electrical parameters, and obtain candidate operation features corresponding to the multiple types of electrical parameters, respectively; Based on the device type corresponding to the first device, determining a first operating feature corresponding to the first device from candidate operating features respectively corresponding to the multiple types of electrical parameters; The first operating characteristics corresponding to the plurality of production devices are determined by obtaining the first operating characteristics corresponding to the first device.

4. The method according to claim 1, characterized in that: The determining, based on the first power consumption data corresponding to the target device, the abnormal emission amount of the target device due to abnormal pollution discharge, includes: Determine a target recognition model corresponding to the target device from among a plurality of second predetermined recognition models, wherein the plurality of second predetermined recognition models correspond to the plurality of production devices, respectively, and the plurality of second predetermined recognition models are respectively trained using historical operation data and historical abnormal data of the corresponding production devices, wherein the historical operation data is electricity consumption data of the corresponding production devices during normal operation in a predetermined historical time period, and the historical abnormal data is emission data generated by abnormal operation of the corresponding production devices during the predetermined historical time period; Based on the first electricity consumption data corresponding to the target device, the target recognition model is used for processing to determine the abnormal emission amount.

5. The method according to claim 1, characterized in that The obtaining of first power consumption data respectively corresponding to the plurality of production equipments comprises: Acquiring initial power consumption data corresponding to the plurality of production equipment respectively in a wired manner and / or a wireless manner; Performing noise reduction processing on initial power consumption data respectively corresponding to a plurality of production equipment to obtain noise reduction data respectively corresponding to the plurality of production equipment; Based on the noise reduction data respectively corresponding to the multiple production equipment, data completion is performed according to a predetermined time series to obtain the first power consumption data respectively corresponding to the multiple production equipment.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: In the case where there are multiple target devices, determining device location information, device function information, and timing information indicating the time when the abnormality occurs, respectively corresponding to the multiple target devices; An emission control strategy is determined based on the device location information, device function information, and timing information respectively corresponding to the multiple target devices.

7. The method according to claim 6, characterized in that The determining of the emission control strategy based on the device location information, device function information, and timing information respectively corresponding to the plurality of target devices includes: Performing visualization processing based on device location information, device function information, and timing information respectively corresponding to the multiple target devices to generate a knowledge graph including the multiple target devices; Using a graph neural network to process the knowledge graph and determine association paths of the multiple target devices; Based on the association path, determining operation control parameters corresponding to the plurality of target devices respectively; The plurality of target devices are adjusted according to the operation control parameters respectively corresponding to the plurality of target devices as the emission control strategy.

8. A sewage discharge abnormality detection device, characterized in that: include: A data acquisition module, used to acquire first power consumption data corresponding to a plurality of production equipment, and second power consumption data corresponding to a pollution control equipment, wherein the pollution control equipment is used to process pollution caused by the plurality of production equipment; an abnormality identification module, used to determine the identification results corresponding to the plurality of production equipment respectively based on the first power consumption data respectively corresponding to the plurality of production equipment and the second power consumption data, wherein the identification results are used to indicate whether the corresponding production equipment has a sewage discharge abnormality; An equipment confirmation module, used to determine, among the plurality of production equipment, a target equipment indicated by the identification result as having abnormal pollution discharge; The emission confirmation module is used to determine the abnormal emission amount of the target device due to abnormal pollution discharge based on the first power consumption data corresponding to the target device.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method for detecting abnormal pollution discharge according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the sewage discharge abnormality detection method described in any one of claims 1 to 7.

Images