Multi-source sensing water quality monitoring and diagnosing system and method based on cloud-side cooperation

Abstract

The invention belongs to the technical field of water quality monitoring, diagnosis and detection, and discloses a multi-source sensing water quality monitoring and diagnosis system and method based on cloud edge collaboration. The system comprises a water quality data acquisition module, a regional data acquisition module, a comprehensive water area feature generation module, a water quality prediction reference value generation module, an alarm decision module, an automatic firmware upgrading module and a user interaction display module, and is used for acquiring a water quality data set, acquiring a regional data set, preprocessing the water quality data set and the regional data set, and displaying the preprocessed water quality data set and the preprocessed regional data set. The method comprises the steps of obtaining a comprehensive water area characteristic data set, analyzing according to the comprehensive water area characteristic data set, obtaining a water quality prediction reference value, analyzing the water quality prediction reference value, obtaining an alarm decision report, processing an abnormal signal, and selecting whether to trigger firmware upgrade according to a processing result. The method has the remarkable advantages of being high in water body prediction processing adaptive capacity, large in auxiliary decision-making effect and good in edge cloud collaborative equipment processing effect.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring and diagnosis detection, and more specifically, to a multi-source perception water quality monitoring and diagnosis system and method based on cloud-edge collaboration. Background Art

[0002] Water quality monitoring refers to the process of monitoring and measuring the types of pollutants in water bodies, the concentrations of various pollutants and their changing trends, and evaluating the water quality status. As the source of life, water has an extremely important position in people's daily lives. With the development of society and the improvement of industrialization level, the pollution sources of water bodies have become increasingly diversified, and people have paid more and more attention to the water quality safety of water bodies. Traditional water quality monitoring and diagnosis methods often involve manually sampling and detecting water bodies in designated areas. Given the vast waters in our country, a large amount of manpower and material resources are required for long-term monitoring and diagnosis. Moreover, for different water bodies such as rivers, lakes, and oceans, there are many differences in the monitoring and diagnosis methods, which further increases the burden of water quality monitoring and diagnosis.

[0003] The patent with the application publication number CN115127605B discloses a remote intelligent diagnosis system and method for a water quality automatic monitoring system. By obtaining valuable operation status data of functional modules, including vibration signals, digestion temperature signals, reference light intensity signals, system voltage signals, etc., it has no impact on the water body parameter monitoring process of the system itself, is easy to implement, and is applicable to instrument equipment of different manufacturers. By performing early maintenance on the water quality automatic monitoring system with a health degree value exceeding the standard, it is possible to prevent the further spread of fault problems within the system, evaluate the system health status in advance, and nip the faults in the bud. By sorting the deviation degree values of each functional module from high to low according to the priority level, it helps the operation and maintenance personnel prepare a maintenance plan in advance, quickly identify and locate the "faulty" module, improve the operation and maintenance efficiency, and avoid the impact of long-term downtime maintenance on continuous monitoring services.

[0004] However, although the above remote intelligent diagnosis system and method for a water quality automatic monitoring system can, to a certain extent, predict water quality problems by performing early maintenance on the water quality automatic monitoring system with a health degree value exceeding the standard, in the use of the water quality monitoring and diagnosis system, the system is often restricted by the different water body-related data brought about by different water bodies, making it difficult to accurately predict water quality changes. Moreover, the relevant countermeasures for abnormal water quality also require a relatively high professional level for the staff. At the same time, due to long-term and high-intensity underwater operation, water quality monitoring equipment is prone to equipment failures, and upgrading and monitoring faulty equipment will also greatly increase the work intensity of the staff. Therefore, how to effectively improve the adaptability, decision-making accuracy, and automaticity of system firmware upgrade of the water quality monitoring and diagnosis system is particularly important for the water quality monitoring and diagnosis industry.

[0005] In view of this, the present invention proposes a multi-source perception water quality monitoring and diagnosis system and method based on cloud-edge collaboration to solve the above problems. Summary of the Invention

[0006] To overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solutions, including: The water quality data acquisition module is used to acquire a water quality data set, which includes dissolved oxygen data, pH value data, conductivity data, water body temperature data, ocean salinity data, river flow velocity data, and lake transparency data; The regional data acquisition module is used to acquire a regional data set, which includes ocean data, river data, and lake data; The comprehensive water area feature generation module is used to preprocess the water quality data set and the regional data set to obtain a comprehensive water area feature data set; Further, the way to preprocess the water quality data set and the regional data set includes: A1. Integrate and process the dissolved oxygen data, pH value data, conductivity data, and water body temperature data in the water quality data set. The specific expression formula for integration and processing is: ; Obtain water quality feature data, where is the th water quality feature data, is the dissolved oxygen data, is the pH value data, is the conductivity data, is the water body temperature data; A2. Calculate the relevant features of the water quality data set and the regional data set. The specific calculation formula for the relevant features is: ; Obtain relevant feature data, where is the mean value of the water quality feature data, is the data in the th regional data set, is the mean value of the data in the th regional data set; A3. Calculate the data trend within a sliding time window for the ocean salinity data, river flow velocity data, lake transparency data, and relevant feature data in the water quality data set. The specific expression formula for trend calculation is: ; Obtain time series feature data, where is the time period; A4. Package the water quality characteristic data, related characteristic data, and time series characteristic data to obtain a comprehensive water area characteristic dataset; The water quality prediction reference value generation module is used to analyze based on the comprehensive water area characteristic dataset to obtain the water quality prediction reference value; Furthermore, the water quality prediction reference value generation module further includes a historical data reading module, a model construction module, a data input module, and a result transmission module, where: The historical data reading module is used to support the system to retrieve the historical comprehensive water area characteristic dataset stored in the database; The model construction module is used to support the system to establish the required operation models; The data input module is used to support manual output of the actual water quality reference value and the residual threshold required by the system; The result transmission module is used to support the system to output the water quality prediction reference value; Furthermore, the steps of analyzing based on the water quality dataset and the comprehensive water area characteristic dataset include: Step 1: Based on the historical data reading module, obtain a set of historical comprehensive water area characteristic datasets stored in the database, and group and mark them from near to far based on the time stamp. The marking results are L1, L2, L3,..., Ln, and use the marking results as the sample set; Step 2: Based on the model construction module, and according to the sample set obtained in Step 1, divide the sample set into an 80% training set and a 20% validation set, and establish the first water quality prediction model; Step 3: By substituting into the calculation formula: ; Obtain the initial water quality prediction reference value, where, 、 and are the weight factors corresponding to each sub-item respectively, and satisfy , is the non-linear weight factor of the th water quality characteristic data, is the time series attenuation factor, is the smoothing constant, is the hyperbolic tangent function; Step 4: Based on the initial water quality prediction reference value obtained in Step 3, according to the actual water quality reference value corresponding to the time stamp in the data input module, subtract the actual water quality reference value from the initial water quality prediction reference value to obtain the prediction residual. When the absolute value of the prediction residual is greater than or equal to the residual threshold, trigger the weight adjustment to obtain a new set of weight factors, and return to Step 3 and substitute them into the calculation formula. Otherwise, output the initial water quality prediction reference value to Step 5; Step Five: Based on the initial water quality prediction reference value obtained in Step Three, when the regional enhancement item conflicts with the historical related feature data, a secondary adjustment is triggered. The specific calculation formula for the secondary adjustment is: ; The first water quality prediction reference value is obtained, where is the mean of the historical related feature data; Step Six: Repeat Steps Three to Five until the preset number of iterations is reached, and output the obtained water quality prediction model; Step Seven: Input the comprehensive water area feature dataset into the water quality prediction model to obtain the water quality prediction reference value, and based on the result transmission module, output the water quality prediction reference value to the alarm decision module; Furthermore, the specific calculation formula group for triggering the weight adjustment is: ; The first weight factor and the second weight factor are obtained respectively, where is the learning rate, is the sign function, is the residual threshold; Package the first weight factor and the second weight factor to obtain a new weight factor set; The alarm decision module is used to analyze the water quality prediction reference value to obtain an alarm decision report; Furthermore, the ways to analyze the water quality prediction reference value include: B1. By comprehensively scoring the water quality prediction reference value, the specific calculation formula for the comprehensive score is: ; The scoring reference value is obtained, where is the weight factor of the th type of water quality data, is the water quality prediction reference value of the th type of water quality data, is the th safety threshold; B2. By classifying the scoring reference value, an alarm decision report is obtained. The specific ways of classification include: When the water body is a marine water body, when the scoring reference value is greater than 0, a normal report is generated; when the scoring reference value is less than or equal to 0 and greater than -1, a warning report is generated; when the scoring reference value is less than or equal to -1, an alarm report is generated; The normal report includes an explanation that all water quality parameter prediction values meet the safety threshold and the system is running smoothly; The early warning report includes an indication that the water quality is approaching the safety threshold. Please ask the staff to check whether the tidal cycle affects the ocean salinity data and deploy buoys to track the direction of pollution spread; The alarm report includes an indication that the water quality parameters seriously exceed the standard. Please ask the staff to notify the relevant units to immediately block the polluted sea area, deploy adsorbents and use a geostationary satellite to monitor the pollution range in real time; B3, package the normal report, early warning report and alarm report to obtain an alarm decision report; The described automatic firmware upgrade module is used to process abnormal signals and select whether to trigger firmware upgrade according to the processing results; Furthermore, the ways to process abnormal signals include: Collect the vibration values of the equipment in the specified area through a piezoelectric accelerometer to obtain vibration intensity data; collect the sound frequency values of the equipment in the specified area through an acoustic resonance sensor to obtain sound frequency data; When the vibration intensity data is greater than or equal to three times the standard deviation of the historical vibration intensity data or the sound frequency data is greater than or equal to 1.5 times the historical sound frequency standard deviation, trigger a firmware upgrade report; otherwise, do not process it; Firmware upgrade includes sending a firmware upgrade request to the cloud; According to the device model and the type of anomaly, the cloud selects a matching firmware upgrade package; The edge node verifies the signature and hash value of the firmware upgrade package; Write the firmware upgrade package into the backup area, and switch to the running area to start the firmware upgrade package after passing the verification; When the firmware upgrade package fails to start, the edge node automatically rolls back to the old version and uploads an error log to the cloud; The user interaction display module is used to process the alarm decision report to obtain a regional pollution report, and display the water quality prediction reference value, regional pollution report and alarm decision report; Furthermore, the ways to process the alarm decision report include: When the regional pollution report is an early warning report and an alarm report, generate a regional pollution report in combination with the geographical coordinates of the polluted area; Furthermore, The specific calculation formula of ; Among them, is the weight factor, is the th water quality characteristic data in the th time period, is the mean value of the water quality characteristic data, is the time period; Further, S1: water quality data set, the water quality data set includes dissolved oxygen data, pH value data, conductivity data, water temperature data, ocean salinity data, river flow rate data and lake transparency data; S2: Collect regional data sets, including ocean data, river data, and lake data; S3: preprocess the water quality dataset and the regional dataset to obtain a comprehensive water area characteristic dataset; S4: Analyze the comprehensive water characteristics data set to obtain the water quality prediction reference value; S5: Analyze the water quality prediction reference value and obtain an alarm decision report; S6: Process the abnormal signal and choose whether to trigger a firmware upgrade based on the processing result; S7: Process the alarm decision report to obtain a regional pollution report, and display the water quality prediction reference value, the regional pollution report and the alarm decision report.

[0007] The technical effects and advantages of the multi-source sensing water quality monitoring and diagnosis system and method based on cloud-edge collaboration of the present invention are as follows: The present invention collects regional data sets through water quality data sets, which include dissolved oxygen data, pH value data, conductivity data, water body temperature data, ocean salinity data, river flow rate data and lake transparency data, and pre-processes the water quality data sets and regional data sets to obtain a comprehensive water area characteristic data set, analyzes the comprehensive water area characteristic data set to obtain a water quality prediction reference value, analyzes the water quality prediction reference value to obtain an alarm decision report, processes abnormal signals, selects whether to trigger a firmware upgrade based on the processing result, processes the alarm decision report to obtain a regional pollution report, and displays the water quality prediction reference value, the regional pollution report and the alarm decision report, so that the system has the ability to Adaptability to processing a variety of water body data. In addition, through multiple data re-verification and auditing of the water quality prediction model, the system's prediction accuracy in the face of multi-source data can be further improved, thereby greatly improving the system's water quality prediction ability. Through the alarm decision-making module, the prediction results are classified and analyzed, so that the system can effectively assist staff to quickly complete the decision-making processing of abnormal water quality, greatly reducing the expansion of pollution caused by the long processing process. At the same time, through the automatic firmware upgrade module, the cloud-edge collaboration can be effectively utilized to complete the online upgrade of edge node devices, thereby achieving the improvement of the system firmware problem processing automation capability. Overall, the present invention has the significant advantages of strong adaptability to water body prediction and processing, large auxiliary decision-making role and good edge-cloud collaborative equipment processing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1Schematic diagram of the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration of the present invention; Figure 2 Schematic diagram of the multi-source perception water quality monitoring and diagnosis method based on cloud-edge collaboration of the present invention. Specific implementation manners

[0009] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0010] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0011] Depending on the context, the words "if", "when" as used herein can be interpreted as "when...", "when...", "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined", "in response to determining", "when detected (stated condition or event)", or "in response to detecting (stated condition or event)".

[0012] In addition, the step timing in the following method embodiments is only an example, rather than a strict limitation.

[0013] In fact, the server devices deployed by the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration may consist of one or more devices. The above-mentioned multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can be implemented as: business instances, virtual machines, and hardware devices. For example, the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can be understood as a piece of software deployed on a cloud node, which is used to provide the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration for each client. Or, the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can also be implemented as a virtual machine deployed on one or more devices in a cloud node. An application software for managing each client is installed in the virtual machine. Or, the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can also be implemented as a server composed of many identical or different types of hardware devices, and one or more hardware devices are set to provide the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration for each client.

[0014] In terms of implementation form, the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration and the client adapt to each other. That is, if the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration is an application installed on a cloud service platform, then the client is a client that establishes a communication connection with this application; or if the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration is implemented as a website, then the client is implemented as a web page; or if the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration is implemented as a cloud service platform, then the client is implemented as a small program in an instant messaging application.

[0015] As Figure 1 shown, it is the system architecture diagram of the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration provided by an embodiment of the present invention.

[0016] The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration described in the present invention can be set in a cloud server. In terms of implementation form, it can be used as one or more service devices, or can be installed as an application on the cloud (such as the server of a mobile service operator, a server cluster, etc.), or can also be developed into a website. According to the functions to be realized, the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can include a water quality data acquisition module, a regional data acquisition module, a comprehensive water area feature generation module, a water quality prediction reference value generation module, an alarm decision module, an automated firmware upgrade module, and a user interaction display module. The modules described in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0017] In the embodiments of the present invention, in the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration, each of the above modules can be independently implemented and called with other modules. Here, the call can be understood as that a certain module can be connected to multiple modules of another type and provide corresponding services for the multiple modules it is connected to. For example, the sharing and evaluation module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, in the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration provided by the embodiments of the present invention, without modifying the program code, the applicable range of the architecture of the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration can be adjusted by adding modules and directly calling, so as to achieve cluster-level horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration. In practical applications, the above modules can be set in the same device or different devices, or can be set in virtual devices, such as service instances in a cloud server. Embodiment 1

[0018] Please refer to Figure 1 As shown, in the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration in this embodiment, the system includes: The water quality data collection module is used to collect a water quality data set, and the water quality data set includes dissolved oxygen data, pH value data, conductivity data, water body temperature data, ocean salinity data, river flow velocity data, and lake transparency data; It should be explained that through an electrode type sensor, the reaction intensity of oxygen molecules and fluorescent substances in the water body of a specified area is collected to obtain dissolved oxygen data; through a solid PH sensor, the PH value of the water body in a specified area is collected to obtain pH value data; through a four-electrode conductivity sensor, the conductivity value of the water body in a specified area is collected to obtain conductivity data; through a thermistor temperature probe, the temperature value of the water body in a specified area is collected to obtain water body temperature data; through an electromagnetic induction salinometer, the salt content of the water body in the ocean area is collected to obtain ocean salinity data; through an electromagnetic flowmeter, the water flow velocity of the water body in the river area is collected to obtain river flow velocity data; through an optical turbidity sensor, the transparency value of the lake area is collected to obtain lake transparency data; The area data collection module is used to collect an area data set, and the area data set includes ocean data, river data, and lake data; It should be explained that through an ocean tide table and a water level sensor, the tide cycle and depth value of the ocean area are collected to obtain ocean data; through a geographic information system, the area values of the river area and the lake area are respectively collected to obtain river data and lake data; The comprehensive water area feature generation module is used to preprocess the water quality data set and the area data set to obtain a comprehensive water area feature data set; Further, the methods for preprocessing the water quality dataset and the regional dataset include: A1. Integrate the dissolved oxygen data, pH value data, conductivity data, and water temperature data in the water quality dataset. The specific expression formula for integration is: ; Obtain water quality characteristic data, where is the th water quality characteristic data, is the dissolved oxygen data, is the pH value data, is the conductivity data, is the water temperature data; A2. Calculate the relevant characteristics of the water quality dataset and the regional dataset. The specific calculation formula for the relevant characteristics is: ; Obtain relevant characteristic data, where is the mean value of the water quality characteristic data, is the nd data in the th regional dataset, is the mean value of the data in the th regional dataset; ; Obtain time series characteristic data, where is the time period; It should be noted that The calculation formula of A4. Package the water quality characteristic data, relevant characteristic data, and time series characteristic data to obtain a comprehensive water area characteristic dataset; The water quality prediction reference value generation module is used to analyze based on the comprehensive water area characteristic dataset to obtain the water quality prediction reference value; Further, the water quality prediction reference value generation module further includes a historical data reading module, a model construction module, a data input module, and a result transmission module, where: The historical data reading module is used to support the system to retrieve the historical comprehensive water area characteristic dataset stored in the database; The model construction module is used to support the system to establish the required operation model; The data input module is used to support manual output of the actual water quality reference value and the residual threshold required by the system; The result transmission module is used to support the system to output the water quality prediction reference value; Further, the steps of analyzing based on the water quality data set and the comprehensive water area feature data set include: Step 1: Based on the historical data reading module, obtain a set of historical comprehensive water area feature data sets stored in the database, and group and label them from near to far based on the time stamp. The labeling results are L1, L2, L3,..., Ln, and use the labeling results as the sample set; Step 2: Based on the model construction module, and according to the sample set obtained in Step 1, divide the sample set into an 80% training set and a 20% validation set, and establish the first water quality prediction model; Step 3: By substituting into the calculation formula: ; Obtain the initial water quality prediction reference value, where , and are the weight factors corresponding to each sub-item respectively, and satisfy , is the non-linear weight factor of the th water quality characteristic data, is the time series decay factor, is the smoothing constant, is the hyperbolic tangent function; It should be noted that the hyperbolic tangent function is used to compress the output data into the range of -1 to 1; the time series decay factor is greater than 0; Step 4: Based on the initial water quality prediction reference value obtained in Step 3, according to the actual water quality reference value corresponding to the time stamp in the data input module, subtract the actual water quality reference value from the initial water quality prediction reference value to obtain the prediction residual. When the absolute value of the prediction residual is greater than or equal to the residual threshold, trigger the weight adjustment to obtain a new weight factor set, and return to Step 3 and substitute it into the calculation formula. Otherwise, output the initial water quality prediction reference value to Step 5; Step 5: Based on the initial water quality prediction reference value obtained in Step 3, when the regional enhancement item conflicts with the historical related feature data, trigger the secondary adjustment. The specific calculation formula for the secondary adjustment is: ; Obtain the first water quality prediction reference value, where is the mean value of the historical related feature data; It should be noted that the conflict between the regional enhancement item and the historical related feature data means that for example, when the ocean salinity data in the ocean water body is lower than the ocean salinity threshold interval, it is considered that there is a conflict between the regional enhancement item and the historical related feature data; Step Six: Repeat Step Three to Step Five until the preset number of iterations is reached, and output the water quality prediction model; Step Seven: Input the comprehensive water area feature dataset into the water quality prediction model to obtain the water quality prediction reference value, and output the water quality prediction reference value to the alarm decision-making module based on the result transmission module; Furthermore, the specific calculation formula group for triggering weight adjustment is: ; Obtain the first weight factor and the second weight factor , where is the learning rate, is the sign function, is the residual threshold; It should be noted that the sign function is used when the residual threshold is less than 0, the value is -1, when the residual threshold is equal to 0, the value is 0, and when the residual threshold is greater than 0, the value is 1; Package the first weight factor and the second weight factor to obtain a new weight factor set; The alarm decision-making module is used to analyze the water quality prediction reference value to obtain an alarm decision report; Furthermore, the methods for analyzing the water quality prediction reference value include: B1. By comprehensively scoring the water quality prediction reference value, the specific calculation formula for the comprehensive score is: ; Obtain the score reference value, where is the weight factor of the th type of water quality data, is the water quality prediction reference value of the th type of water quality data, is the th safety threshold; B2. By classifying the score reference value, obtain the alarm decision report. The specific methods for classification include: When the water body is a marine water body, when the score reference value is greater than 0, generate a normal report; when the score reference value is less than or equal to 0 and greater than -1, generate a warning report; when the score reference value is less than or equal to -1, generate an alarm report; The normal report includes an explanation that all water quality parameter prediction values meet the safety threshold and the system is running smoothly; The warning report includes an explanation that the water quality is approaching the safety threshold. Please ask the staff to check whether the tidal cycle affects the ocean salinity data and deploy buoys to track the direction of pollution spread; The alarm report includes an explanation that the water quality parameters seriously exceed the standard. Please ask the staff to notify the relevant units to immediately block the polluted sea area, deploy adsorbents and use synchronous satellites to monitor the pollution range in real time; B3, package the normal report, warning report and alarm report to obtain the alarm decision report; The described automatic firmware upgrade module is used to process abnormal signals and select whether to trigger firmware upgrade according to the processing results; Furthermore, the ways to process abnormal signals include: Collect the vibration values of the equipment in the specified area through a piezoelectric accelerometer to obtain vibration intensity data; collect the sound frequency values of the equipment in the specified area through an acoustic resonance sensor to obtain sound frequency data; When the vibration intensity data is greater than or equal to three times the standard deviation of the historical vibration intensity data or the sound frequency data is greater than or equal to 1.5 times the historical sound frequency standard deviation, trigger the firmware upgrade report; otherwise, do not process it; Firmware upgrade includes sending a firmware upgrade request to the cloud; According to the device model and abnormal type, the cloud selects a matching firmware upgrade package; The edge node verifies the signature and hash value of the firmware upgrade package; Write the firmware upgrade package into the backup area, and switch to the running area to start the firmware upgrade package after passing the verification; When the firmware upgrade package fails to start, the edge node automatically rolls back to the old version and uploads the error log to the cloud; The user interaction display module is used to process the alarm decision report to obtain the regional pollution report, and display the water quality prediction reference value, regional pollution report and alarm decision report; Furthermore, the ways to process the alarm decision report include: When the regional pollution report is a warning report and an alarm report, generate a regional pollution report in combination with the geographical coordinates of the polluted area; Furthermore, The specific calculation formula of ; Among them, is the weight factor, is the th water quality characteristic data in the th time period, is the mean value of the water quality characteristic data, is the time period; The present embodiment has the beneficial effects of collecting regional data sets through water quality data sets, which include dissolved oxygen data, pH value data, conductivity data, water body temperature data, ocean salinity data, river flow rate data and lake transparency data, preprocessing the water quality data sets and regional data sets to obtain a comprehensive water area characteristic data set, analyzing the comprehensive water area characteristic data set to obtain a water quality prediction reference value, analyzing the water quality prediction reference value to obtain an alarm decision report, processing abnormal signals, selecting whether to trigger a firmware upgrade based on the processing results, processing the alarm decision report to obtain a regional pollution report, and displaying the water quality prediction reference value, the regional pollution report and the alarm decision report, so that the system has It has the adaptability to process a variety of water body data. In addition, through multiple data re-verification and auditing of the water quality prediction model, the system's prediction accuracy in the face of multi-source data can be further improved, thereby greatly improving the system's water quality prediction ability. Through the alarm decision-making module, the prediction results are classified and analyzed, so that the system can effectively assist staff to quickly complete the decision-making and processing of abnormal water quality, greatly reducing the expansion of pollution caused by the long processing process. At the same time, through the automatic firmware upgrade module, the cloud-edge collaboration can be effectively utilized to complete the online upgrade of edge node devices, thereby achieving the improvement of the system firmware problem processing automation capability. Overall, the present invention has the significant advantages of strong adaptability to water body prediction and processing, large auxiliary decision-making role and good edge-cloud collaborative equipment processing effect. Example 2

[0019] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a multi-source perception water quality monitoring and diagnosis method based on cloud-edge collaboration is provided, and the method includes: S1: collecting a water quality data set, the water quality data set includes dissolved oxygen data, pH value data, conductivity data, water temperature data, ocean salinity data, river flow rate data and lake transparency data; S2: Collect regional data sets, including ocean data, river data, and lake data; S3: preprocess the water quality dataset and the regional dataset to obtain a comprehensive water area characteristic dataset; S4: Analyze the comprehensive water characteristics data set to obtain the water quality prediction reference value; S5: Analyze the water quality prediction reference value and obtain an alarm decision report; S6: Process the abnormal signal and choose whether to trigger a firmware upgrade based on the processing result; S7: Process the alarm decision report to obtain a regional pollution report, and display the water quality prediction reference value, the regional pollution report and the alarm decision report. Example 3

[0020] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0021] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be encompassed within the present invention. Any associated drawing reference signs in the claims should not be construed as limiting the claims involved.

[0022] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use the knowledge to obtain the best results.

[0023] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices described in the system claims can also be implemented by one unit or device through software or hardware. The terms such as first and second are used to denote names and do not denote any particular order.

[0024] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration, characterized in that The system includes: a water quality data collection module, a regional data collection module, a comprehensive water area feature generation module, a water quality prediction reference value generation module, an alarm decision-making module, an automated firmware upgrade module, and a user interaction display module, where: The water quality data collection module is used to collect a water quality data set, and the water quality data set includes dissolved oxygen data, pH value data, conductivity data, water body temperature data, ocean salinity data, river flow velocity data, and lake transparency data; The regional data collection module is used to collect a regional data set, and the regional data set includes ocean data, river data, and lake data; The comprehensive water area feature generation module is used to preprocess the water quality data set and the regional data set to obtain a comprehensive water area feature data set; The water quality prediction reference value generation module is used to analyze based on the comprehensive water area feature data set to obtain a water quality prediction reference value; The alarm decision-making module is used to analyze the water quality prediction reference value to obtain an alarm decision report; The automated firmware upgrade module is used to process abnormal signals and select whether to trigger firmware upgrade according to the processing results; The user interaction display module is used to process the alarm decision report to obtain a regional pollution report, and display the water quality prediction reference value, the regional pollution report, and the alarm decision report.

2. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 1, wherein The methods for preprocessing the water quality data set and the regional data set include: A1. Integrate and process the dissolved oxygen data, pH value data, conductivity data, and water body temperature data in the water quality data set. The specific expression formula for integration processing is: ； Obtain water quality characteristic data, where is the th water quality characteristic data, is the dissolved oxygen data, is the pH value data, is the conductivity data, is the water body temperature data; A2. Calculate relevant features for the water quality data set and the regional data set. The specific calculation formula for relevant features is: ； Obtain relevant feature data, where is the mean of the water quality feature data is the data in the th regional dataset is the mean of the data in the th regional dataset; A3. Calculate the data trend within a sliding time window for the ocean salinity data, river flow velocity data, lake transparency data, and relevant feature data in the water quality data set. The specific expression formula for trend calculation is: ； Obtain the timing feature data, where is the time period; A4. Package the water quality feature data, relevant feature data, and time series feature data to obtain a comprehensive water area feature data set.

3. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 1, characterized in that, The water quality prediction reference value generation module further includes a historical data reading module, a model construction module, a data input module, and a result transmission module, where: The historical data reading module is used to support the system to retrieve the historical comprehensive water area feature data set stored in the database; The model construction module is used to support the system to establish the required operation models; The data input module is used to support manual output of the actual water quality reference value and residual threshold required by the system; The result transmission module is used to support the system to output the water quality prediction reference value.

4. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 3, characterized in that, The steps for analyzing based on the water quality data set and the comprehensive water area feature data set include: Step 1: Based on the historical data reading module, obtain a group of historical comprehensive water area feature data sets stored in the database, and perform grouped marking from near to far based on timestamps. The marking results are L1, L2, L3,..., Ln, and use the marking results as the sample set; Step 2: Based on the model construction module, and according to the sample set obtained in Step 1, divide the sample set into an 80% training set and a 20% validation set, and establish a first water quality prediction model; Step 3: By substituting into the calculation formula: ； Obtain the initial water quality prediction reference value, where , and are the weight factors corresponding to each sub-item respectively, and satisfy , is the non-linear weight factor of the th water quality characteristic data, is the time series attenuation factor, is the smoothing constant, is the hyperbolic tangent function. Step 4: Based on the initial water quality prediction reference value obtained in Step 3, according to the actual water quality reference value corresponding to the timestamp in the data input module, subtract the actual water quality reference value from the initial water quality prediction reference value to obtain a prediction residual. When the absolute value of the prediction residual is greater than or equal to the residual threshold, trigger weight adjustment to obtain a new set of weight factors, and return to Step 3 and substitute it into the calculation formula. Otherwise, output the initial water quality prediction reference value to Step 5; Step Five: Based on the initial water quality prediction reference value obtained in Step Three, when the regional enhancement item conflicts with the historical relevant feature data, a secondary adjustment is triggered, and the specific calculation formula for the secondary adjustment is: ； Obtain a first water quality prediction reference value, where is the mean of historical related feature data; Step 6: Repeat Step 3 to Step 5 until the preset number of iterations is reached, and output the water quality prediction model; Step 7: Input the comprehensive water area feature dataset into the water quality prediction model to obtain the water quality prediction reference value, and based on the result transmission module, output the water quality prediction reference value to the alarm decision module.

5. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 4, wherein The specific calculation formula group for triggering weight adjustment is: ； Obtain the first weight factor respectively and the second weight factor , where is the learning rate, is the sign function, is the residual threshold; Pack the first weight factor and the second weight factor to obtain a new set of weight factors.

6. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 1, wherein, The methods for analyzing the water quality prediction reference value include: B1. By comprehensively scoring the water quality prediction reference value, the specific calculation formula for the comprehensive score is: ； Obtain the scoring reference value, where, is the weight factor of the th water quality data, is the water quality prediction reference value of the th water quality data, is the th safety threshold; B2. By classifying the scoring reference value to obtain an alarm decision report. The specific methods for classification include: When the water body is a marine water body, when the scoring reference value is greater than 0, generate a normal report; when the scoring reference value is less than or equal to 0 and greater than -1, generate a warning report; when the scoring reference value is less than or equal to -1, generate an alarm report; The normal report includes an explanation that all water quality parameter prediction values meet the safety threshold and the system is running smoothly; The warning report includes an explanation that some water quality is close to the safety threshold. Please ask the staff to check whether the tidal cycle affects the marine salinity data and deploy buoys to track the pollution diffusion direction; The alarm report includes an explanation that the water quality parameters seriously exceed the standard. Please ask the staff to notify the relevant units to immediately block the polluted sea area, put adsorbents, and conduct real-time monitoring of the pollution range by synchronous satellites; B3. Package the normal report, warning report, and alarm report to obtain the alarm decision report.

7. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 1, characterized in that, The methods for processing abnormal signals include: Collect the vibration values of the equipment in the specified area through a piezoelectric accelerometer to obtain vibration intensity data; collect the sound frequency values of the equipment in the specified area through an acoustic resonance sensor to obtain sound frequency data; When the vibration intensity data is greater than or equal to three times the standard deviation of the historical vibration intensity data or the sound frequency data is greater than or equal to 1.5 times the historical sound frequency standard deviation, trigger a firmware upgrade report. Otherwise, do not process it; Firmware upgrade includes sending a firmware upgrade request to the cloud; According to the device model and abnormal type, the cloud selects a matching firmware upgrade package; The edge node verifies the signature and hash value of the firmware upgrade package; Write the firmware upgrade package into the backup area, and after passing the verification, switch to the running area to start the firmware upgrade package; When the firmware upgrade package fails to start, the edge node automatically rolls back to the old version and uploads the error log to the cloud.

8. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 1, wherein, The methods for processing the alarm decision report include: When the regional pollution report is a warning report and an alarm report, generate a regional pollution report in combination with the geographical coordinates of the polluted area.

9. The multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration according to claim 2, wherein The specific calculation formula is as follows: ； Among them, is the weight factor, is at the th th water quality characteristic data in the is the mean value of the water quality characteristic data, is the time period.

10. A multi-source perception water quality monitoring and diagnosis method based on cloud-edge collaboration, implemented according to the multi-source perception water quality monitoring and diagnosis system based on cloud-edge collaboration described in any one of claims 1-9, characterized in that, It includes the following working steps: S1: Collect a water quality data set, which includes dissolved oxygen data, pH value data, conductivity data, water body temperature data, ocean salinity data, river flow velocity data, and lake transparency data; S2: Collect a regional data set, which includes ocean data, river data, and lake data; S3: Preprocess the water quality data set and the regional data set to obtain a comprehensive water area feature data set; S4: Analyze based on the comprehensive water area feature data set to obtain a water quality prediction reference value; S5: Analyze the water quality prediction reference value to obtain an alarm decision report; S6: Process the abnormal signal and select whether to trigger firmware upgrade according to the processing result; S7: Process the alarm decision report to obtain a regional pollution report, and display the water quality prediction reference value, the regional pollution report, and the alarm decision report.

Images