Remote monitoring method and system for layered water taking facility

Abstract

The invention provides a remote monitoring method and system for a layered water taking facility, and the method comprises the steps: obtaining historical operation data, carrying out the preprocessing, and extracting an operation rule through principal component analysis; secondly, a layered water taking model is built based on the operation rule, and a multi-parameter monitoring model is built in combination with water quality monitoring, flow control and equipment maintenance strategies; fusing the two models to form a combined model, and constructing a remote monitoring model through a remote monitoring platform; comparing actual data to verify the precision of the model, and optimizing until the fitting degree reaches the standard; and finally, introducing scene analysis, including conventional, emergency and optimized water taking scenes, and comparing different scene models to determine an optimal strategy and a maintenance scheme. The water taking efficiency, the water quality guarantee and the equipment operation reliability can be improved, and water taking strategies and maintenance schemes under different scenes can be optimized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of water conservancy projects and intelligent monitoring technology, and more particularly, to a remote monitoring method and system for a layered water taking facility. BACKGROUND

[0002] In the field of water resource management and utilization, layered water taking facilities have been widely used as an important technical means. Existing layered water taking facilities usually set water taking outlets in different water layers, combined with water quality monitoring equipment and flow control devices to achieve layered water taking. The technical principle mainly relies on the monitoring and control of water quality, water level and water taking flow, and the opening and closing and flow of the water taking outlet are adjusted by manual or simple automatic system to meet different water demand and optimize the utilization efficiency of water resources. However, there are many limitations in the operation process of this traditional layered water taking facility. On the one hand, the automation degree of its monitoring and control system is low, and data collection and analysis mainly rely on manual operation, which leads to insufficient real-time and accuracy, and it is difficult to respond to the dynamic adjustment of water layer changes and water demand in time. On the other hand, the existing facilities lack the ability to deeply mine and analyze historical operation data, and cannot effectively identify and utilize the operation rules to optimize the water taking strategy and equipment maintenance plan, thereby affecting the water taking efficiency and the reliability of equipment operation.

[0003] In the implementation process of the embodiments of the present application, the inventors found that there are at least the following problems or defects in the prior art: First, the monitoring system of the existing layered water taking facility has a single function, and cannot realize comprehensive monitoring and analysis of multiple parameters, making it difficult to comprehensively evaluate the influence of various factors in the water taking process on the operation effect. Secondly, there is a lack of effective modeling of water taking layer conversion rules and conversion probability, which makes it impossible to accurately adjust the water taking strategy when facing complex water layer conditions and dynamic water demand. In addition, the strategy for equipment maintenance in the prior art lacks scientific basis, and cannot develop a reasonable maintenance plan according to the actual operation state and historical data of the equipment, increasing the risk of equipment failure and maintenance cost. Finally, the existing layered water taking facility lacks flexibility in dealing with emergency situations and different water taking scenarios, lacks effective emergency response mechanism and optimization scheme, and is difficult to meet the requirements of modern water resource management for high efficiency, intelligence and sustainability. SUMMARY

[0004] The present application provides a remote monitoring method and system for a layered water taking facility.

[0005] In the first aspect of the present application, a remote monitoring method for a layered water taking facility is provided, comprising: Step S1: obtaining historical operation data of the layered water taking facility, pre-processing the historical operation data, and obtaining operation rules of the layered water taking facility by principal component analysis method; Step S2: Obtain a water taking layer conversion rule according to the operation rule by using the hierarchical water taking model, construct the hierarchical water taking model according to the water taking layer conversion rule, collect water quality monitoring strategies, flow control strategies and equipment maintenance strategies, and construct a multi-parameter monitoring model by using the remote monitoring system according to the water quality monitoring strategies, the flow control strategies and the equipment maintenance strategies; Step S3: Fuse the hierarchical water taking model and the multi-parameter monitoring model to obtain a hierarchical water taking monitoring combination model, and establish a hierarchical water taking remote monitoring model according to the hierarchical water taking monitoring combination model by using a remote monitoring platform; Step S4: Model verification is performed on the hierarchical water taking remote monitoring result and actual operation data, point-by-point comparison is performed to obtain fitting accuracy, the hierarchical water taking remote monitoring model is continuously optimized until the fitting accuracy is greater than or equal to an expected threshold, and the best hierarchical water taking remote monitoring model is obtained; Step S5: Introduce a scenario analysis into the hierarchical water taking remote monitoring model, obtain hierarchical water taking remote monitoring models under different scenarios, compare and analyze the hierarchical water taking remote monitoring models under different scenarios, and obtain an optimal water taking strategy and an equipment maintenance scheme.

[0006] Further, the step S1 specifically comprises: Step S201: Obtain the historical operation data, wherein the historical operation data comprises sensor collected data, water quality parameter data, equipment operation state data and environment monitoring data; Step S202: Perform data preprocessing on the sensor collected data, the water quality parameter data, the equipment operation state data and the environment monitoring data to obtain historical operation data after removing redundancy; Step S203: Perform attribution analysis on the historical operation data after removing redundancy by using a principal component analysis method to obtain various influence factors and weights of the various influence factors; Step S204: Obtain an operation rule of the hierarchical water taking facility according to the weights of the various influence factors; The influence factors comprise water quality factors, flow factors and equipment state factors.

[0007] Further, the step S2 specifically comprises: Step S201: Set a water taking layer state in the hierarchical water taking model to comprise a non-water taking layer and a water taking layer, obtain a water taking layer conversion rule and a water taking layer conversion probability according to the operation rule, and establish the hierarchical water taking model according to the water taking layer conversion rule and the water taking layer conversion probability; Step S202: Collect water quality monitoring strategies, flow control strategies and equipment maintenance strategies, wherein the water quality monitoring strategies comprise a water quality monitoring priority P1, the flow control strategies comprise a flow adjustment priority P2, and the equipment maintenance strategies comprise an equipment maintenance priority P3; The water quality monitoring priority P1 is expressed as follows:

[0008] in, represents the probability of water pollution risk, represents the water quality importance index, It represents a dynamic adjustment coefficient used to balance the impact of pollution risk and water quality importance; The flow regulation priority P2 is expressed as follows:

[0009] Among them, P21 represents flow stability, P22 represents water extraction efficiency, P23 represents equipment energy consumption, and P24 represents environmental impact. a, b, c, d represent the weight coefficients of each factor, and a+b+c+d=1. , Represents the dynamic adjustment coefficient, which is used to balance the comprehensive impact of various factors; The equipment maintenance priority P3 is expressed as follows:

[0010] Among them, P3 represents the equipment maintenance priority. Indicates the monitoring window size, Indicates the first Rank The device status value of the column, Indicates the dynamic adjustment coefficient, which is used to balance the impact of device status; Step S203 , obtaining the water layer conversion probability of a certain water layer according to the water quality monitoring strategy, the flow control strategy and the equipment maintenance strategy, and establishing a multi-parameter monitoring model according to the water layer conversion probability.

[0011] Furthermore, the step S3 specifically includes: Step S301, obtaining the final water-intake layer conversion probability according to the water-intake layer conversion probability and the multi-parameter monitoring model; Step S302, using data fusion technology to match sensor collected data with model parameters one by one; Step S303: using the remote monitoring platform to establish a stratified water intake monitoring combination model according to the final water intake layer conversion probability and the water intake layer conversion rules.

[0012] Furthermore, the step S4 specifically includes: Step S401, obtaining actual operating data and equipment status of the stratified water intake facility; In step S402, the layered water taking remote monitoring model is compared with the actual operation data and the equipment state by using the point-by-point comparison method to obtain the fitting accuracy of each water taking layer in the layered water taking remote monitoring model. In step S403, the model fitting accuracy K is obtained according to the fitting accuracy of each water taking layer, and the expression of the model fitting accuracy K is as follows:

[0013] Wherein, P0 represents the proportion of correct simulation, Pc represents the expected simulation proportion under random conditions, Pp represents the proportion of correct simulation under ideal conditions, RMSE represents the root mean square error, and MaxRMSE represents the maximum possible root mean square error. In step S404, if the fitting accuracy K of the layered water taking remote monitoring model is greater than or equal to the expected threshold, the layered water taking remote monitoring model is defined as the best monitoring model. If the fitting accuracy K of the layered water taking remote monitoring model is less than the expected threshold, the water taking layer fitting accuracy is sorted, and n water taking layers with substandard fitting accuracy are screened out. The water taking layers with substandard fitting accuracy are analyzed and adjusted until the model fitting accuracy K reaches the expected threshold, and the adjusted layered water taking remote monitoring model is defined as the best monitoring model.

[0014] Further, the step S5 specifically includes: In step S501, the operation data of the current layered water taking facility is obtained, and the current operation data is preprocessed. In step S502, different water taking scenarios are formulated according to the layered water taking demand, and multiple water taking strategies are obtained according to the different water taking scenarios. In step S503, multiple layered water taking remote monitoring models are established for each water taking strategy and the preprocessed operation data, and the best scenario and the layered water taking remote monitoring model under the best scenario are screened out according to the layered water taking demand. The water taking scenarios include a regular water taking scenario, an emergency water taking scenario and an optimized water taking scenario.

[0015] Further, the steps S203 and S204 include: The principal component analysis function is set; The influence factors and the weights of the influence factors are obtained by using the principal component analysis function; The influence factors are normalized by using the standardization processing function; The operation rules of the layered water taking facility are obtained according to the weights of the influence factors and the random interference factors by introducing the random interference factors.

[0016] Further, the water taking layer conversion rule and the water taking layer conversion probability are obtained according to the operation rules. obtaining the neighborhood water taking probability by using the neighborhood operation; introducing the neighborhood factor into the influence factor, and obtaining the neighborhood factor weight by using the principal component analysis method; obtaining the water taking layer conversion rule and the water taking layer conversion probability according to the influence factor after the neighborhood factor weight is added and the influence factor weight.

[0017] Further, the hierarchical water taking remote monitoring model is compared with the actual operation data and the equipment state by using the point-by-point comparison method, including water taking layer area comparison and water taking layer distribution comparison. The water taking layer area comparison includes obtaining water taking layer area accuracy according to simulated water taking area and actual water taking area. The water taking layer distribution comparison includes obtaining distribution comparison accuracy according to simulated water taking layer position distribution and actual water taking layer position distribution, and the distribution comparison accuracy is used to measure the consistency of the water taking layer position distribution.

[0018] In the second aspect of the present application, a hierarchical water taking facility remote monitoring system is provided, comprising: a sensor interface module, configured to obtain historical operation data of the hierarchical water taking facility, perform data preprocessing on the historical operation data, and obtain operation rules of the hierarchical water taking facility by using the principal component analysis method; a data processing module, configured to obtain water taking layer conversion rules according to the operation rules by using the hierarchical water taking model, construct the hierarchical water taking model according to the water taking layer conversion rules, collect water quality monitoring strategies, flow control strategies and equipment maintenance strategies, and construct a multi-parameter monitoring model by using the remote monitoring system according to the water quality monitoring strategies, the flow control strategies and the equipment maintenance strategies; a model construction module, configured to fuse the hierarchical water taking model and the multi-parameter monitoring model, obtain a hierarchical water taking monitoring combined model, and establish a hierarchical water taking remote monitoring model according to the hierarchical water taking monitoring combined model by using a remote monitoring platform; a model optimization module, configured to perform model verification on the hierarchical water taking remote monitoring result and actual operation data, obtain fitting accuracy by point-by-point comparison, and continuously optimize the hierarchical water taking remote monitoring model until the fitting accuracy is greater than or equal to an expected threshold value, so as to obtain an optimal hierarchical water taking remote monitoring model; a scenario analysis module, configured to introduce scenario analysis into the hierarchical water taking remote monitoring model, obtain hierarchical water taking remote monitoring models under different scenarios, compare and analyze the hierarchical water taking remote monitoring models under different scenarios, and obtain optimal water taking strategies and equipment maintenance schemes.

[0019] The remote monitoring method and system of the layered water taking facility according to the above embodiments of the present application at least have the following beneficial effects: the remote monitoring method and system of the layered water taking facility can effectively improve the operation efficiency and management level of the layered water taking facility. By obtaining historical operation data and using the principal component analysis method to obtain operation rules, the key influencing factors and their weights of the layered water taking facility can be accurately grasped, thereby providing a scientific basis for subsequent model construction. On this basis, a multi-parameter monitoring model is constructed in combination with a water quality monitoring strategy, a flow control strategy and an equipment maintenance strategy, and is fused with a layered water taking model to form a layered water taking monitoring combination model, and then a layered water taking remote monitoring model is established, thereby realizing comprehensive, real-time and remote monitoring of the layered water taking facility, enabling management personnel to timely grasp the operation state of the facility and make quick decisions, improving water taking efficiency and water quality guarantee capability, reducing equipment failure risk, prolonging equipment service life, and ensuring stable operation of the layered water taking facility, which is of great significance for rational development and utilization of water resources.

[0020] In addition, the method and system can enhance the ability of the layered water taking facility to cope with complex working conditions and emergency events. By introducing different water taking scenarios such as a regular water taking scenario, an emergency water taking scenario and an optimized water taking scenario through a scenario analysis module, and establishing corresponding layered water taking remote monitoring models for each scenario, the best scenario and the corresponding monitoring model can be selected according to different needs, thereby providing strong support for formulating optimal water taking strategies and equipment maintenance schemes. At the same time, in the model optimization process, the layered water taking remote monitoring model is compared with actual operation data through the point-by-point comparison method to obtain fitting accuracy, and the model is continuously optimized until the fitting accuracy reaches the expected threshold, which can ensure the accuracy and reliability of the model, enable the layered water taking facility to maintain efficient and stable operation under various complex working conditions, improve its emergency response capability and adaptability, and provide strong support for sustainable utilization of water resources. BRIEF DESCRIPTION OF DRAWINGS

[0021] The above and other objects, features and advantages of the exemplary embodiments of the present application will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of a remote monitoring method of a layered water taking facility provided by an embodiment of the present application is shown; Figure 2 A structure diagram of a remote monitoring system of a layered water taking facility provided by an embodiment of the present application is shown; Figure 3 A structure diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] The principles and spirits of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only for better understanding of the present application by those skilled in the art, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0023] Those skilled in the art will appreciate that the embodiments of the present application can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present application can be embodied in the form of entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0024] It should be noted that the number of any elements in the accompanying drawings is used for illustration only and not limitation, and any naming is only for distinction and does not have any limiting meaning.

[0025] The principles and spirits of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only for better understanding of the present application by those skilled in the art, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art. Figure 1 , Figure 1 The flowchart of the remote monitoring method of the layered water taking facility provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, a remote monitoring method of a layered water taking facility includes: Figure 1 Step S1: obtaining historical operation data of the layered water taking facility, pre-processing the historical operation data, and obtaining operation rules of the layered water taking facility by using principal component analysis method; Step S2: obtaining water taking layer conversion rules according to the operation rules by using the layered water taking model, constructing the layered water taking model according to the water taking layer conversion rules, collecting water quality monitoring strategy, flow control strategy and equipment maintenance strategy, and constructing a multi-parameter monitoring model by using the remote monitoring system according to the water quality monitoring strategy, flow control strategy and equipment maintenance strategy; Step S3: fusing the layered water taking model and the multi-parameter monitoring model to obtain a layered water taking monitoring combination model, and establishing a layered water taking remote monitoring model according to the layered water taking monitoring combination model by using a remote monitoring platform; Step S4: model verification of the layered water taking remote monitoring result and actual operation data, point-by-point comparison to obtain fitting accuracy, continuous optimization of the layered water taking remote monitoring model, until the fitting accuracy is greater than or equal to the expected threshold, and the best layered water taking remote monitoring model is obtained; Step S5: introducing scenario analysis into the layered water taking remote monitoring model, obtaining the layered water taking remote monitoring model under different scenarios, comparing and analyzing the layered water taking remote monitoring model under different scenarios, and obtaining the optimal water taking strategy and equipment maintenance scheme.

[0026] ​It should be noted that when acquiring historical operating data for stratified water intake facilities, this data includes sensor data, water quality parameter data, equipment operating status data, and environmental monitoring data. This data is a collection of various information generated during the operation of stratified water intake facilities. Sensor data refers to real-time data acquired by various sensors installed on the water intake facilities, such as water temperature, water pressure, and flow rate. Water quality parameter data involves the chemical and biological properties of the water, such as dissolved oxygen, pH, and turbidity. Equipment operating status data refers to the operating conditions of individual devices within the water intake facilities, such as pump speed and valve opening and closing status. Environmental monitoring data includes meteorological and hydrological information related to the operating environment of the water intake facilities, such as temperature, rainfall, and water level changes. Data preprocessing is primarily performed to remove redundant information and noise, thereby improving data quality and usability. Principal component analysis is a statistical method used to extract the main components from multiple related variables, thereby simplifying the data structure and retaining key information. Principal component analysis can be used to identify the operating rules of stratified water intake facilities, namely, the key factors affecting their operation and their interrelationships.

[0027] Specifically, the water-intake layer status in the stratified water-intake model includes non-intake layers and intake layers, representing the functional division of different water layers within the water-intake facility. A non-intake layer refers to a water layer currently not drawing water, while an intake layer refers to a water layer currently drawing water. Determining the intake layer transition rules and intake layer transition probabilities based on operational rules involves analyzing historical operational data to determine under what conditions a water layer will transition from a non-intake state to an intake state, as well as the probability of such a transition. The water quality monitoring priority (P1) in the water quality monitoring strategy is an indicator measuring the importance of water quality monitoring. It is calculated by considering the probability of water pollution risk and the water quality importance index, with a dynamic adjustment coefficient used to balance the impact of these two factors. The flow regulation priority (P2) in the flow control strategy integrates multiple factors, including flow stability, water-intake efficiency, equipment energy consumption, and environmental impact, and is determined using weighting coefficients and dynamic adjustment coefficients. The equipment maintenance priority (P3) in the equipment maintenance strategy is calculated based on the equipment status value and reflects the urgency of equipment maintenance. These priority indicators provide a quantitative basis for constructing a multi-parameter monitoring model, enabling the monitoring system to dynamically adjust based on the importance of different factors.

[0028] Preferably, the construction process of the hierarchical water taking model can be further refined. First, when determining the water taking layer conversion rule according to the operation rule, the neighborhood operation can be used to obtain the neighborhood water taking probability, that is, the influence of the surrounding water layers on the current water layer taking state is considered. Then, the neighborhood factor is introduced into the influence factor, and the principal component analysis method is used to obtain the neighborhood factor weight, so as to more accurately reflect the influence of each factor on the water taking layer conversion. When constructing the multi-parameter monitoring model, the specific parameter settings of the water quality monitoring strategy, the flow control strategy and the equipment maintenance strategy can be used, for example, in the calculation formula of the water quality monitoring priority P1, the water quality pollution risk probability can be obtained through statistical analysis of historical water quality data, and the water quality importance index can be determined according to water demand and water quality standards, and the dynamic adjustment coefficient can be adjusted according to the actual operation to achieve the best balance. In the calculation of the flow regulation priority P2, the weight coefficients of each factor can be allocated according to the importance in actual operation, and the dynamic adjustment coefficient is used to balance the comprehensive influence of each factor. In the calculation of the equipment maintenance priority P3, the equipment state value can be obtained through the device sensor data, the monitoring window size can be set according to the operation period and maintenance period of the equipment, and the dynamic adjustment coefficient is used to balance the influence of the equipment state. Through the setting of these specific parameters and the construction steps of the model, the remote monitoring of the hierarchical water taking facility can be more accurately realized.

[0029] In some embodiments, the step S1 specifically comprises: Step S201, obtaining the historical operation data, the historical operation data including sensor acquisition data, water quality parameter data, equipment operation state data and environment monitoring data; Step S202, data preprocessing of the sensor acquisition data, the water quality parameter data, the equipment operation state data and the environment monitoring data to obtain the historical operation data after removing redundancy; Step S203, using principal component analysis method to perform attribution analysis on the historical operation data after removing redundancy to obtain each influence factor and the weight of each influence factor; Step S204, obtaining the operation rule of the hierarchical water taking facility according to the weight of each influence factor; The influence factors include water quality factors, flow factors and equipment state factors.

[0030] It should be noted that step S201 mainly involves obtaining historical operation data of the layered water intake facility, which is various types of information accumulated during the operation of the layered water intake facility, including sensor collected data, water quality parameter data, equipment operation state data and environmental monitoring data. Sensor collected data refers to real-time monitoring information obtained through various sensors, such as water temperature, water pressure, flow rate, etc.; water quality parameter data includes chemical and biological properties of water body, such as dissolved oxygen, pH value, turbidity, etc.; equipment operation state data refers to the operation of each device in the water intake facility, such as the speed of the pump, the opening and closing state of the valve, etc.; environmental monitoring data includes meteorological and hydrological information related to the operating environment of the water intake facility, such as air temperature, rainfall, water level change, etc. These data are the basis for subsequent analysis and modeling, providing a rich source of information for remote monitoring of the layered water intake facility.

[0031] Specifically, the data preprocessing in step S202 is to remove redundant information and noise in the historical operation data, improve the quality and availability of the data. Redundant information refers to repeated or irrelevant data, while noise refers to abnormal or erroneous values in the data. Through data preprocessing, data features that are important to the operation of the layered water intake facility can be extracted. In step S203, the principal component analysis method is a statistical method used to extract principal components from multiple related variables, thereby simplifying the data structure and retaining key information. Through principal component analysis, various influence factors and their weights can be obtained. Influence factors refer to factors that have a significant impact on the operation of the layered water intake facility, such as water quality factors, flow factors and equipment state factors. Water quality factors reflect the influence of water quality on the water intake process; flow factors involve the stability, efficiency, etc. of the water intake flow; equipment state factors reflect the influence of equipment operation state on the water intake process. These influence factors and their weights are the basis for constructing the operation rules of the layered water intake facility.

[0032] Preferably, the operation rules in step S204 are derived based on the weights of various influence factors, used to guide the operation and monitoring of the layered water intake facility. The formulation of operation rules needs to consider multiple aspects such as water quality, flow and equipment state, to ensure the efficiency and stability of the water intake process. For example, in terms of water quality factors, the probability of water pollution risk and the water quality importance index can be determined based on historical statistical analysis of water quality parameter data, and then the water quality monitoring priority can be calculated. In terms of flow factors, the flow regulation priority can be calculated based on the weights of flow stability, water intake efficiency, equipment energy consumption and environmental impact, etc. In terms of equipment state factors, the equipment maintenance priority can be calculated based on equipment operation state data. These priority indicators provide quantitative basis for subsequent monitoring models, enabling the monitoring system to dynamically adjust according to the importance of different factors.

[0033] In some embodiments, step S2 specifically includes: Step S201, setting the water intake layer state in the stratified water intake model to include a non-water intake layer and a water intake layer, obtaining a water intake layer conversion rule and a water intake layer conversion probability according to the operation rule, and establishing a stratified water intake model according to the water intake layer conversion rule and the water intake layer conversion probability; Step S202, collecting and acquiring a water quality monitoring strategy, a flow control strategy, and an equipment maintenance strategy, wherein the water quality monitoring strategy includes a water quality monitoring priority P1, the flow control strategy includes a flow regulation priority P2, and the equipment maintenance strategy includes an equipment maintenance priority P3; The water quality monitoring priority P1 is expressed as follows:

[0034] in, represents the probability of water pollution risk, represents the water quality importance index, It represents a dynamic adjustment coefficient used to balance the impact of pollution risk and water quality importance; The flow regulation priority P2 is expressed as follows:

[0035] Among them, P21 represents flow stability, P22 represents water extraction efficiency, P23 represents equipment energy consumption, and P24 represents environmental impact. a, b, c, d represent the weight coefficients of each factor, and a+b+c+d=1. , Represents the dynamic adjustment coefficient, which is used to balance the comprehensive impact of various factors; The equipment maintenance priority P3 is expressed as follows:

[0036] Among them, P3 represents the equipment maintenance priority. Indicates the monitoring window size, Indicates the first Rank The device status value of the column, Indicates the dynamic adjustment coefficient, which is used to balance the impact of device status; Step S203 , obtaining the water layer conversion probability of a certain water layer according to the water quality monitoring strategy, the flow control strategy and the equipment maintenance strategy, and establishing a multi-parameter monitoring model according to the water layer conversion probability.

[0037] It should be noted that the embodiment mainly describes the construction process of the layered water taking model in the layered water taking facility remote monitoring method. The layered water taking model is established by defining the water taking layer state and obtaining the water taking layer conversion rule and conversion probability based on the operation rule. The water taking layer state includes non-water taking layer and water taking layer, which is the functional division of different water layers in the water taking facility. The non-water taking layer refers to the water layer that does not perform water taking operation at present, while the water taking layer refers to the water layer that is taking water. The operation rule is obtained by analyzing the historical operation data, which is used to guide the conversion of the water taking layer state. The water taking layer conversion rule and conversion probability are further refined based on these operation rules, which are used to describe under what conditions the water layer will convert from non-water taking state to water taking state, and the possibility of such conversion. In addition, the water quality monitoring strategy, the flow control strategy and the equipment maintenance strategy are important parts in the operation process of the layered water taking facility. They respectively set different priorities to guide the construction of the monitoring model, so as to realize the multi-parameter monitoring of the layered water taking facility.

[0038] Specifically, the construction of the layered water taking model involves multiple key elements. First, the setting of the water taking layer state is the basis of the model, and the division of the non-water taking layer and the water taking layer clearly defines the functions of different water layers. Second, the operation rule is obtained by analyzing the historical operation data, which includes water quality factors, flow factors and equipment state factors, etc. These factors and their weights reflect their importance in the operation process. The water quality monitoring priority P1 in the water quality monitoring strategy is calculated by considering the probability of water pollution risk and the water quality importance index, and the dynamic adjustment coefficient is used to balance the influence of the two. The flow regulation priority P2 in the flow control strategy integrates multiple factors such as flow stability, water taking efficiency, equipment energy consumption and environmental impact, and is determined by weight coefficient and dynamic adjustment coefficient. The equipment maintenance priority P3 in the equipment maintenance strategy is calculated according to the equipment state value, which reflects the urgency of equipment maintenance. These priority indicators provide quantitative basis for the construction of multi-parameter monitoring model, so that the monitoring system can dynamically adjust according to the importance of different factors.

[0039] Preferably, the construction process of the hierarchical water taking model can be further refined. First, the acquisition of the water taking layer conversion rule can be achieved by analyzing the change law of the water taking layer state in the historical operation data. For example, it can be determined through statistical analysis that under what water quality conditions, flow demand or equipment state change, the water layer will be converted from a non-water taking state to a water taking state. The calculation of the water taking layer conversion probability can be obtained by analyzing the frequency of the conversion event in the historical data. When constructing the multi-parameter monitoring model, the specific parameter settings of the water quality monitoring strategy, flow control strategy and equipment maintenance strategy can be optimized. For example, in the calculation of the water quality monitoring priority P1, the water quality pollution risk probability can be obtained by statistical analysis of the historical water quality data, the water quality importance index can be determined according to the water demand and water quality standard, and the dynamic adjustment coefficient can be adjusted according to the actual operation to achieve the best balance. In the calculation of the flow regulation priority P2, the weight coefficients of each factor can be allocated according to the importance in the actual operation, and the dynamic adjustment coefficient is used to balance the comprehensive influence of each factor. In the calculation of the equipment maintenance priority P3, the equipment state value can be obtained through the equipment sensor data, the monitoring window size can be set according to the operation period and maintenance period of the equipment, and the dynamic adjustment coefficient is used to balance the influence of the equipment state. Through the setting of these specific parameters and the construction steps of the model, the remote monitoring of the hierarchical water taking facility can be more accurately realized.

[0040] In some embodiments, the step S3 specifically comprises: Step S301, acquiring a final water taking layer conversion probability according to the water taking layer conversion probability and the multi-parameter monitoring model; Step S302, using data fusion technology to correspond the sensor collected data with the model parameters one by one; Step S303, using a remote monitoring platform to establish a hierarchical water taking monitoring combination model according to the final water taking layer conversion probability and the water taking layer conversion rule.

[0041] It should be noted that the present embodiment describes the fusion process of the hierarchical water taking model and the multi-parameter monitoring model in the hierarchical water taking facility remote monitoring method. The hierarchical water taking model is established based on the water taking layer conversion rule and the conversion probability, and is used to describe the change law of the water taking layer state; the multi-parameter monitoring model is constructed according to the water quality monitoring strategy, the flow control strategy and the equipment maintenance strategy, and is used to monitor the running state of the hierarchical water taking facility in real time. The purpose of fusing these two models is to comprehensively consider the water taking layer state change and the monitoring strategy, so as to establish a more comprehensive hierarchical water taking monitoring combination model. Finally, through the remote monitoring platform, a hierarchical water taking remote monitoring model is established according to the combination model, realizing the remote, real-time and comprehensive monitoring of the hierarchical water taking facility.

[0042] Specifically, the water intake layer transition probability and the multi-parameter monitoring model are two key elements in the fusion process. The water intake layer transition probability reflects the possibility of the water intake layer state changing under certain conditions and is obtained by analyzing historical operation data and water intake layer transition rules. The multi-parameter monitoring model integrates multiple monitoring strategies such as water quality monitoring priority, flow regulation priority, and equipment maintenance priority. These priority indicators are calculated based on the weights of water quality, flow, and equipment state factors. In the fusion process, the final water intake layer transition probability is obtained by considering various factors in the water intake layer transition rules and the multi-parameter monitoring model. It provides a more accurate water intake layer state prediction for the hierarchical water intake monitoring combination model. The data fusion technology is a one-to-one correspondence process between sensor collected data and model parameters, ensuring that the monitoring model can accurately reflect the actual operation situation. The remote monitoring platform is the carrier for realizing the hierarchical water intake remote monitoring model, which realizes remote monitoring and management of hierarchical water intake facilities through network connection and data transmission.

[0043] Preferably, the process of fusing the hierarchical water intake model and the multi-parameter monitoring model can be further refined. First, when obtaining the final water intake layer transition probability, the priority indicators in the water intake layer transition rules and the multi-parameter monitoring model can be combined to calculate it by weighted average or other statistical methods. For example, the water intake layer transition probability can be adjusted according to the weights of water quality monitoring priority, flow regulation priority, and equipment maintenance priority to make it more consistent with actual operation requirements. Second, when using data fusion technology, data calibration and synchronization processing methods can be used to ensure the one-to-one correspondence between sensor collected data and model parameters. For example, through timestamp alignment and data format conversion, the consistency and accuracy of the data are ensured. Finally, when establishing the hierarchical water intake monitoring combination model, the effectiveness of the model can be verified through simulation testing and actual operation data. For example, the model can be applied to the operation monitoring of actual hierarchical water intake facilities, and the model can be optimized and adjusted to improve the accuracy and reliability of monitoring by comparing the model prediction results with the actual operation data.

[0044] In some embodiments, the step S4 specifically comprises: Step S401, obtaining actual operation data and equipment state of the hierarchical water intake facility; Step S402, comparing the hierarchical water intake remote monitoring model with the actual operation data and equipment state by using the point-by-point comparison method to obtain the fitting accuracy of each water intake layer in the hierarchical water intake remote monitoring model; Step S403, obtaining the model fitting accuracy K according to the fitting accuracy of each water intake layer, and the expression of the model fitting accuracy K is as follows:

[0045] wherein P0 represents the proportion of correct simulations, Pc represents the proportion of simulations expected by chance, Pp represents the proportion of correct simulations in the ideal case, RMSE represents the root mean square error, and MaxRMSE represents the maximum possible root mean square error; Step S404, if the fitting accuracy K of the layered water taking remote monitoring model is greater than or equal to the expected threshold, the layered water taking remote monitoring model is defined as the best monitoring model. If the fitting accuracy K of the layered water taking remote monitoring model is less than the expected threshold, the water taking layer fitting accuracy is sorted, and n water taking layers with substandard fitting accuracy are screened out. The water taking layers with substandard fitting accuracy are analyzed and adjusted until the model fitting accuracy K reaches the expected threshold, and the adjusted layered water taking remote monitoring model is defined as the best monitoring model.

[0046] It should be noted that the embodiment mainly describes the verification and optimization process of the layered water taking facility remote monitoring model. Model verification is to compare the prediction results of the layered water taking remote monitoring model with the actual operation data to evaluate the accuracy and reliability of the model. Fitting accuracy is a key indicator for measuring the consistency between the model prediction results and the actual data. The fitting accuracy of the model at each water taking layer can be obtained by the point-by-point comparison method. Model optimization is to adjust and improve the model according to the fitting accuracy results until the fitting accuracy reaches the expected threshold. This process ensures that the layered water taking remote monitoring model can accurately reflect the operation state of the layered water taking facility in actual application, thereby providing a reliable basis for optimizing the water taking strategy and equipment maintenance scheme.

[0047] Specifically, the verification of the layered water taking remote monitoring model involves multiple key steps. First, obtaining actual operation data and equipment state is the basis for verification. These data include real-time water quality parameters, flow data, equipment operation state, etc., which are used to compare with the prediction results of the model. The point-by-point comparison method means comparing each water taking layer parameter predicted by the model with the actual measured value one by one to calculate the fitting accuracy of each water taking layer. The calculation formula of the model fitting accuracy K integrates the proportion of correct simulations, the proportion of random simulations, the proportion of ideal simulations, and the root mean square error, etc., to comprehensively evaluate the performance of the model. If the fitting accuracy K of the model reaches or exceeds the expected threshold, the model is considered as the best monitoring model; otherwise, the water taking layers with substandard fitting accuracy need to be analyzed and adjusted. This process ensures that the model can accurately reflect the actual situation in all water taking layers.

[0048] Preferably, the process of model verification and optimization can be further refined. First, when obtaining actual operation data, data can be collected in real time through a sensor network installed on the water intake facility, and noise and outliers can be removed through data cleaning and preprocessing steps. Second, in the point-by-point comparison process, different comparison parameters can be set, for example, the comparison of water quality parameters can include dissolved oxygen, pH value, etc., and the comparison of flow parameters can include instantaneous flow and cumulative flow, etc. For the calculation of fitting accuracy K, the weights of various parameters can be adjusted according to actual needs, for example, in water quality sensitive areas, the weight of water quality parameters can be increased. In the model optimization stage, for the water intake layer with substandard fitting accuracy, the reasons can be analyzed, such as whether it is sensor failure, unreasonable model parameter setting, etc., and targeted adjustments can be made. For example, if it is found that sensor failure causes data deviation, the sensor can be replaced or calibrated; if it is a model parameter problem, the weight coefficients or conversion rules in the model can be adjusted. Through these refined steps, the layered water intake remote monitoring model can be more effectively verified and optimized to ensure its accuracy and reliability in actual application.

[0049] In some embodiments, the step S5 specifically comprises: Step S501, obtaining operation data of the current layered water intake facility, and preprocessing the current operation data; Step S502, formulating different water intake scenarios according to the layered water intake demand, and obtaining multiple water intake strategies according to the different water intake scenarios; Step S503, establishing multiple layered water intake remote monitoring models for each water intake strategy and the preprocessed operation data, and screening out the best scenario and the layered water intake remote monitoring model under the best scenario according to the layered water intake demand; The water intake scenarios include a regular water intake scenario, an emergency water intake scenario, and an optimized water intake scenario.

[0050] It should be noted that the present embodiment mainly describes the application of the scenario analysis module in the layered water intake facility remote monitoring method. Scenario analysis is to preprocess the operation data of the current layered water intake facility, and formulate multiple water intake scenarios according to different water intake demands, so as to establish corresponding layered water intake remote monitoring models for each scenario. These scenarios include a regular water intake scenario, an emergency water intake scenario, and an optimized water intake scenario. By comparing and analyzing the monitoring models under different scenarios, the best scenario and the corresponding monitoring model can be screened out, thereby providing a basis for formulating the optimal water intake strategy and equipment maintenance scheme. This method can effectively cope with the demand changes of the layered water intake facility under different operating conditions, and improve the adaptability and flexibility of the system.

[0051] Specifically, the implementation of the scenario analysis module involves the following key steps. First, pre-process the operation data of the current layered water intake facility, which includes data cleaning, format conversion and outlier processing to ensure the accuracy and availability of the data. Second, develop different water intake scenarios based on layered water intake demand. The regular water intake scenario refers to the water intake demand under normal operating conditions; the emergency water intake scenario refers to the water intake demand under sudden situations (such as water source pollution, equipment failure, etc.); the optimized water intake scenario refers to the water intake demand under specific goals (such as energy saving, efficient water intake, etc.). For each scenario, a corresponding layered water intake remote monitoring model needs to be established based on its characteristics. The establishment of these models needs to consider factors such as water quality monitoring strategy, flow control strategy and equipment maintenance strategy, and adjust the model parameters according to the specific scenario. Finally, by comparing and analyzing the monitoring models under different scenarios, the best scenario and the corresponding monitoring model are selected to provide the best water intake strategy and equipment maintenance scheme for actual operation.

[0052] Preferably, the operation steps of the scenario analysis module can be further refined. First, in the operation data preprocessing stage, data standardization methods can be used to convert data of different sources and formats into a unified format for subsequent analysis. Second, when establishing different scenario layered water intake remote monitoring models, the model input parameters can be adjusted according to the characteristics of the scenario. For example, in the emergency water intake scenario, the water quality monitoring frequency and equipment maintenance priority can be increased to ensure a quick response in the event of an emergency; in the optimized water intake scenario, the flow control strategy can be optimized to improve water intake efficiency. Finally, when comparing and analyzing the monitoring models under different scenarios, performance evaluation indicators such as water intake efficiency, energy consumption, equipment failure rate, etc. can be introduced to select the best scenario and the corresponding monitoring model through quantitative analysis. For example, the performance of the model under different scenarios can be evaluated through simulation testing and actual operation data verification, and the scenario that meets the water intake demand while having the lowest energy consumption and the lowest equipment failure rate is selected as the optimal scenario.

[0053] In some embodiments, the step S203 and the step S204 include: setting a principal component analysis function; obtaining each influence factor and a weight of the influence factor by using the principal component analysis function; normalizing the influence factor by using a standardization processing function; introducing a random interference factor, and obtaining an operation rule of the layered water intake facility according to the weight of each influence factor and the random interference factor.

[0054] It should be noted that the embodiment mainly describes how to obtain the influence factors and their weights through the principal component analysis function and normalize the influence factors in the remote monitoring method of the layered water intake facility. The principal component analysis function is a statistical method for data dimensionality reduction and feature extraction, which can help extract key influence factors from complex historical operation data and determine the weights of these factors. By normalizing the influence factors through the standardization processing function, the differences in dimensions and orders of magnitude between different factors can be eliminated, so that these factors can be compared and analyzed on the same scale. In addition, the introduction of random disturbance factors is to simulate the uncertainty in actual operation, so that the operation rules are more close to the actual situation, and the robustness and adaptability of the model are improved.

[0055] Specifically, the role of the principal component analysis function is to extract the main components from multiple related variables, simplify the data structure and retain the key information. In the operation data of the layered water intake facility, these variables may include water quality parameters, flow data, equipment status, etc. Through principal component analysis, the few factors that have the greatest impact on the operation of the layered water intake facility, i.e. influence factors, can be identified, and their weights can be calculated. The weight reflects the importance of each influence factor in the operation process. The standardization processing function is to normalize the extracted influence factors, usually scaling the data to the [0, 1] interval or normalizing it to a distribution with a mean of 0 and a standard deviation of 1, so as to be used in subsequent analysis. The introduction of random disturbance factors is to simulate the uncertainty factors in actual operation, such as sensor measurement error, environmental change, etc. By adding these random factors to the model, the adaptability of the model to actual operation can be improved.

[0056] Preferably, the construction and use process of the principal component analysis function can be further refined. First, the historical operation data of the layered water intake facility needs to be collected, including water quality parameters, flow data, equipment status, etc. Then, input these data into the principal component analysis function, extract the main components, i.e. influence factors, by calculating the covariance matrix and eigenvalue decomposition, and calculate the weight of each factor. In the standardization process, the Z-score standardization method can be used, i.e. subtracting the mean of each influence factor and dividing by its standard deviation, so as to convert the data to a standard normal distribution. Finally, when introducing random disturbance factors, the distribution (such as normal distribution or uniform distribution) and intensity of random disturbance can be set according to the statistical characteristics of the actual operation data, and the random disturbance can be added to the influence factors through Monte Carlo simulation and other methods, so as to generate operation rules that are more close to the actual operation situation.

[0057] In some embodiments, the method further comprises: obtaining a neighborhood water intake probability using neighborhood operation; The neighborhood factor is introduced into the influence factor, and the principal component analysis method is used to obtain the neighborhood factor weight; The water intake layer conversion rule and the water intake layer conversion probability are obtained according to the influence factor after the neighborhood factor weight is added and the influence factor weight.

[0058] It should be noted that the embodiment mainly describes how to obtain the water intake layer conversion rule and the water intake layer conversion probability according to the operation rule. The operation rule is obtained by analyzing the historical operation data, which reflects the key influence factors and their mutual relationship in the operation process of the layered water intake facility. The water intake layer conversion rule refers to the conditions under which the state of the water intake layer changes, for example, from a non-water intake layer to a water intake layer or vice versa. The water intake layer conversion probability is a quantitative measure of the possibility of such conversion. The neighborhood operation refers to considering the influence of surrounding water layers on the current water layer water intake state, and by calculating the neighborhood water intake probability, the actual operation situation can be more accurately reflected. The principal component analysis method is used here to further optimize the model, by introducing the neighborhood factor and calculating its weight, various factors affecting the water intake layer conversion can be more comprehensively considered, thereby improving the accuracy and reliability of the model.

[0059] Specifically, the operation rule is derived based on the key influence factors and their weights extracted from the historical operation data, which may include water quality parameters, flow data, equipment status, etc. The formulation of the water intake layer conversion rule needs to consider the changes of these influence factors, for example, when the water quality parameter reaches a certain threshold or the flow demand changes, the water intake layer may change. The neighborhood operation considers the influence of surrounding water layers on the current water intake state by calculating the neighborhood water intake probability, which helps to more accurately predict the conversion of the water intake layer. The principal component analysis method is used to process the extended data set containing the neighborhood factor, and by calculating the neighborhood factor weight, the influence of the neighborhood factor can be quantified and included in the model. Finally, combined with the extended data set and the neighborhood factor weight, the water intake layer conversion rule and the conversion probability can be more accurately obtained.

[0060] Preferably, the process of obtaining the water intake layer conversion rule and conversion probability can be further refined. First, based on the operation rule, the neighborhood operation is used to calculate the neighborhood water intake probability. A neighborhood range can be set, for example, several water layers adjacent to the current water intake layer. Then, according to the water quality parameters, flow data, etc. of each water layer in the neighborhood range, the neighborhood water intake probability is calculated. Next, when processing the data set containing the neighborhood factor by principal component analysis method, the neighborhood factor can be analyzed together with other influencing factors. By calculating the covariance matrix and eigenvalue decomposition, the weight of the neighborhood factor is determined. Finally, when constructing the water intake layer conversion rule and conversion probability model, the neighborhood factor weight and other influencing factor weight can be combined, and a model considering multiple factors is established by regression analysis or machine learning algorithm. The input parameters of the model include water quality parameters, flow data, equipment status and neighborhood water intake probability, and the output is the water intake layer conversion rule and conversion probability.

[0061] In some embodiments, the comparison of the hierarchical water intake remote monitoring model with the actual operation data and equipment status by the point-by-point comparison method includes water intake layer area comparison and water intake layer distribution comparison; The water intake layer area comparison includes obtaining water intake layer area accuracy according to simulated water intake area and actual water intake area; The water intake layer distribution comparison includes obtaining distribution comparison accuracy according to simulated water intake layer position distribution and actual water intake layer position distribution, the distribution comparison accuracy being used to measure the consistency of the water intake layer position distribution.

[0062] It should be noted that the present embodiment mainly describes how to evaluate and optimize the model by the point-by-point comparison method in the hierarchical water intake facility remote monitoring model verification process. The point-by-point comparison method refers to comparing the prediction results of the hierarchical water intake remote monitoring model with the actual operation data and equipment status one by one to obtain the fitting accuracy of the model. The water intake layer area comparison and the water intake layer distribution comparison are two key links in the point-by-point comparison method, which are respectively used to evaluate the accuracy of the model in the water intake layer area and position distribution. The water intake layer area accuracy reflects the consistency between the predicted water intake area of the model and the actual water intake area, while the distribution comparison accuracy measures the matching degree of the predicted water intake layer position distribution of the model and the actual distribution. Through these comparison analyses, the performance of the model can be comprehensively evaluated, and the model can be optimized and adjusted according to the results.

[0063] Specifically, the water intake layer area comparison in the point-by-point comparison method refers to comparing the model-predicted water intake layer area with the actually measured water intake layer area, and calculating the difference between the two. The water intake layer area accuracy can be measured by calculating the ratio or error of the predicted area and the actual area. The water intake layer distribution comparison is to compare the model-predicted water intake layer position distribution with the actual distribution, and the distribution comparison accuracy can be measured by calculating the similarity or distance between the two. The results of these comparison analyses can be used to evaluate the fitting accuracy of the model for different water intake layers. For example, if the area accuracy of a certain water intake layer is low, it may mean that the model's prediction for that layer is biased; if the distribution comparison accuracy is low, it may indicate that the model's prediction of the water intake layer position is not accurate enough. Through these detailed comparison analyses, the places where the model needs to be improved can be identified.

[0064] Preferably, the implementation process of the point-by-point comparison method can be further refined. First, when obtaining the actual operation data and equipment status, a high-precision sensor network can be used to ensure the accuracy and real-time nature of the data. Second, when performing water intake layer area comparison, the model-predicted water intake layer boundary can be geometrically matched with the actually measured boundary, and the overlapping area and difference area can be calculated to obtain the area accuracy. For example, geographic information system (GIS) tools can be used to process and analyze these boundary data. When performing water intake layer distribution comparison, spatial analysis methods such as calculating the spatial distance or similarity index between the predicted distribution and the actual distribution can be used. For example, spatial autocorrelation analysis or spatial clustering analysis can be used to assess the consistency of the distribution. Finally, based on the results of the comparison analysis, the model is optimized and adjusted. For example, if it is found that the model's prediction accuracy for certain water intake layers is low, the model's parameter settings can be adjusted, such as increasing the monitoring data weight for that layer or optimizing the model's algorithm. Through these refined steps, the layered water intake remote monitoring model can be more effectively verified and optimized to ensure its accuracy and reliability in actual applications.

[0065] The above-mentioned various embodiments of the present application have the following beneficial effects: the present application can improve the intelligent management level of layered water intake facilities, and by extracting key influence factors of historical operation data through principal component analysis and establishing operation rules, the water intake layer conversion behavior can be more accurately predicted. The multi-parameter monitoring model constructed in combination with water quality monitoring, flow control and equipment maintenance strategies can dynamically optimize water intake decisions, and at the same time, through data fusion and model verification mechanisms, the monitoring accuracy can be continuously improved, ultimately forming an optimal control scheme that adapts to different scenarios.

[0066] The introduction of scenario analysis can further enhance the adaptability of the system, and provide differentiated strategies for different water demand such as routine, emergency and optimization, so as to ensure water quality safety while improving water efficiency. Through the introduction of neighborhood operation and random disturbance factors, the robustness of the model can be optimized, and the point-by-point comparison verification mechanism can ensure that the monitoring results are highly consistent with the actual operation data, and finally realize the fine and intelligent remote control of the layered water taking facility.

[0067] As shown in Figure 2 A remote monitoring system of a layered water taking facility in some embodiments, the system comprises: A sensor interface module 201 for obtaining historical operation data of the layered water taking facility, pre-processing the historical operation data, and obtaining operation rules of the layered water taking facility using principal component analysis method; A data processing module 202 for obtaining water taking layer conversion rules from the operation rules using a layered water taking model, constructing a layered water taking model according to the water taking layer conversion rules, collecting water quality monitoring strategies, flow control strategies and equipment maintenance strategies, and constructing a multi-parameter monitoring model using the remote monitoring system according to the water quality monitoring strategies, flow control strategies and equipment maintenance strategies; A model construction module 203 for fusing the layered water taking model and the multi-parameter monitoring model to obtain a layered water taking monitoring combination model, and establishing a layered water taking remote monitoring model according to the layered water taking monitoring combination model using a remote monitoring platform; A model optimization module 204 for model verification between the layered water taking remote monitoring results and the actual operation data, point-by-point comparison to obtain fitting accuracy, and continuous optimization of the layered water taking remote monitoring model until the fitting accuracy is greater than or equal to the expected threshold to obtain the best layered water taking remote monitoring model; A scenario analysis module 205 for introducing scenario analysis into the layered water taking remote monitoring model, obtaining layered water taking remote monitoring models under different scenarios, comparing and analyzing the layered water taking remote monitoring models under different scenarios, and obtaining optimal water taking strategies and equipment maintenance schemes.

[0068] It can be understood that the modules described in the remote monitoring system of the layered water taking facility correspond to the steps in the remote monitoring method of the layered water taking facility described with reference to Figure 1 The operations, features and beneficial effects described above for the remote monitoring method of the layered water taking facility also apply to the remote monitoring system of the layered water taking facility and the modules contained therein, and will not be repeated here.

[0069] Reference will now be made to Figure 3, which shows a schematic structural diagram of an electronic device 300 suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0070] like Figure 3 As shown, electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage device 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for the operation of electronic device 300. Processing device 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0071] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0072] Further, the storage medium of the embodiments of the present application stores program instructions capable of realizing all the methods described above, wherein the program instructions can be stored in the storage medium in the form of a software product, and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes, or a computer, a server, a mobile phone, a tablet, and other terminal devices.

[0073] The above description is merely some preferred embodiments of the present application and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present application is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by any combinations of the technical features described above or their equivalent features without departing from the inventive concept described above. For example, the technical solutions formed by mutually replacing the above-described features and the technical features disclosed in the embodiments of the present application (but not limited to) having similar functions.

Claims

1. A remote monitoring method for a stratified water intake facility, characterized in that: include: Step S1: obtaining historical operating data of the stratified water intake facility, performing data preprocessing on the historical operating data, and obtaining operating rules of the stratified water intake facility using a principal component analysis method; Step S2: Using the stratified water intake model to obtain water intake layer conversion rules according to the operation rules, constructing the stratified water intake model based on the water intake layer conversion rules, collecting and obtaining water quality monitoring strategies, flow control strategies, and equipment maintenance strategies, constructing a multi-parameter monitoring model using the remote monitoring system based on the water quality monitoring strategies, flow control strategies, and equipment maintenance strategies; Step S3: Fusing the stratified water intake model and the multi-parameter monitoring model to obtain a stratified water intake monitoring combination model, and establishing a stratified water intake remote monitoring model based on the stratified water intake monitoring combination model using a remote monitoring platform; Step S4: Verify the model by comparing the stratified water intake remote monitoring results with the actual operation data, obtain the fitting accuracy by point-by-point comparison, and continuously optimize the stratified water intake remote monitoring model until the fitting accuracy is greater than or equal to the expected threshold, thereby obtaining the optimal stratified water intake remote monitoring model; Step S5: Introduce scenario analysis into the stratified water extraction remote monitoring model to obtain the stratified water extraction remote monitoring model under different scenarios, perform comparative analysis on the stratified water extraction remote monitoring model under different scenarios, and obtain the optimal water extraction strategy and equipment maintenance plan.

2. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The step S1 specifically includes: Step S201, acquiring the historical operation data, which includes sensor acquisition data, water quality parameter data, equipment operation status data, and environmental monitoring data; Step S202: pre-process the sensor data, water quality parameter data, equipment operation status data, and environmental monitoring data to obtain historical operation data after redundancy removal. Step S203: Perform attribution analysis on the historical operating data after redundancy removal using a principal component analysis method to obtain various influencing factors and their weights; Step S204, obtaining the operating rules of the stratified water intake facility according to the weights of the various influencing factors; The influencing factors include water quality factors, flow factors and equipment status factors.

3. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The step S2 specifically includes: Step S201, setting the water intake layer state in the stratified water intake model to include a non-water intake layer and a water intake layer, obtaining a water intake layer conversion rule and a water intake layer conversion probability according to the operation rule, and establishing a stratified water intake model according to the water intake layer conversion rule and the water intake layer conversion probability; Step S202, collecting and acquiring a water quality monitoring strategy, a flow control strategy, and an equipment maintenance strategy, wherein the water quality monitoring strategy includes a water quality monitoring priority P1, the flow control strategy includes a flow regulation priority P2, and the equipment maintenance strategy includes an equipment maintenance priority P3; The water quality monitoring priority P1 is expressed as follows: in, represents the probability of water pollution risk, represents the water quality importance index, It represents a dynamic adjustment coefficient used to balance the impact of pollution risk and water quality importance; The flow regulation priority P2 is expressed as follows: Among them, P21 represents flow stability, P22 represents water extraction efficiency, P23 represents equipment energy consumption, and P24 represents environmental impact. a, b, c, d represent the weight coefficients of each factor, and a+b+c+d=1. , Represents the dynamic adjustment coefficient, which is used to balance the comprehensive impact of various factors; The equipment maintenance priority P3 is expressed as follows: Among them, P3 represents the equipment maintenance priority. Indicates the monitoring window size, Indicates the first Rank The device status value of the column, Indicates the dynamic adjustment coefficient, which is used to balance the impact of device status; Step S203 , obtaining the water layer conversion probability of a certain water layer according to the water quality monitoring strategy, the flow control strategy and the equipment maintenance strategy, and establishing a multi-parameter monitoring model according to the water layer conversion probability.

4. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The step S3 specifically includes: Step S301, obtaining the final water-intake layer conversion probability according to the water-intake layer conversion probability and the multi-parameter monitoring model; Step S302, using data fusion technology to match sensor collected data with model parameters one by one; Step S303: using the remote monitoring platform to establish a stratified water intake monitoring combination model according to the final water intake layer conversion probability and the water intake layer conversion rules.

5. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The step S4 specifically includes: Step S401, obtaining actual operating data and equipment status of the stratified water intake facility; Step S402: Compare the stratified water intake remote monitoring model with the actual operating data and equipment status using a point-by-point comparison method to obtain the fitting accuracy of each water intake layer in the stratified water intake remote monitoring model; Step S403: Obtain the model fitting accuracy K according to the fitting accuracy of each water extraction layer. The expression of the model fitting accuracy K is as follows: Where P0 represents the proportion of correct simulations, Pc represents the expected proportion of simulations under random conditions, Pp represents the proportion of correct simulations under ideal conditions, RMSE represents the root mean square error, and MaxRMSE represents the maximum possible root mean square error. Step S404: If the fitting accuracy K of the stratified water intake remote monitoring model is greater than or equal to the expected threshold, the stratified water intake remote monitoring model is defined as the optimal monitoring model; If the fitting accuracy K of the stratified water extraction remote monitoring model is less than the expected threshold, the fitting accuracy of the water extraction layers will be sorted, and n water extraction layers with substandard fitting accuracy will be screened out. The water extraction layers with substandard fitting accuracy will be analyzed and adjusted until the model fitting accuracy K reaches the expected threshold. The adjusted stratified water extraction remote monitoring model is then defined as the optimal monitoring model.

6. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The step S5 specifically includes: Step S501, obtaining the current operating data of the stratified water intake facility and preprocessing the current operating data; Step S502: formulate different water intake scenarios according to the stratified water intake requirements, and obtain multiple water intake strategies according to the different water intake scenarios; Step S503: establishing multiple stratified water intake remote monitoring models for each water intake strategy and pre-processed operation data, and selecting the optimal scenario and the stratified water intake remote monitoring model under the optimal scenario according to the stratified water intake demand; The water intake scenarios include conventional water intake scenarios, emergency water intake scenarios and optimized water intake scenarios.

7. The remote monitoring method for a stratified water intake facility according to claim 2, wherein: Step S203 and step S204 include: Set the principal component analysis function; Use the principal component analysis function to obtain each influencing factor and its weight; The impact factor is normalized using the standardized processing function; Random interference factors are introduced, and the operation rules of stratified water intake facilities are obtained according to the weights of various influencing factors and random interference factors.

8. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The obtaining of water layer conversion rules and water layer conversion probabilities according to the operation rules includes: Use neighborhood operations to obtain the probability of neighborhood water withdrawal; The neighborhood factor is introduced into the influencing factor, and the neighborhood factor weight is obtained using the principal component analysis method; The water layer conversion rules and water layer conversion probabilities are obtained based on the influencing factors and influencing factor weights after adding the neighborhood factor weights.

9. The remote monitoring method for a stratified water intake facility according to claim 1, wherein: The point-by-point comparison method is used to compare the stratified water intake remote monitoring model with the actual operating data and equipment status, including the comparison of water intake layer area and water intake layer distribution; The water intake layer area comparison includes obtaining the water intake layer area accuracy based on the simulated water intake area and the actual water intake area; The water intake layer distribution comparison includes obtaining distribution comparison accuracy based on the simulated water intake layer position distribution and the actual water intake layer position distribution, and the distribution comparison accuracy is used to measure the consistency of the water intake layer position distribution.

10. A remote monitoring system for stratified water intake facilities, characterized in that: include: A sensor interface module is used to obtain historical operating data of the stratified water intake facility, perform data preprocessing on the historical operating data, and obtain operating rules of the stratified water intake facility using a principal component analysis method; A data processing module is used to use the stratified water intake model to obtain water intake layer conversion rules according to the operation rules, build the stratified water intake model according to the water intake layer conversion rules, obtain water quality monitoring strategies, flow control strategies and equipment maintenance strategies through collection, and build a multi-parameter monitoring model based on the water quality monitoring strategies, flow control strategies and equipment maintenance strategies using the remote monitoring system; A model building module is used to integrate the stratified water intake model and the multi-parameter monitoring model to obtain a stratified water intake monitoring combination model, and to establish a stratified water intake remote monitoring model based on the stratified water intake monitoring combination model using a remote monitoring platform; The model optimization module is used to verify the model by comparing the stratified water intake remote monitoring results with the actual operation data, obtaining the fitting accuracy by point-by-point comparison, and continuously optimizing the stratified water intake remote monitoring model until the fitting accuracy is greater than or equal to the expected threshold, thereby obtaining the optimal stratified water intake remote monitoring model; The scenario analysis module is used to introduce scenario analysis into the stratified water extraction remote monitoring model, obtain the stratified water extraction remote monitoring model under different scenarios, conduct comparative analysis on the stratified water extraction remote monitoring model under different scenarios, and obtain the optimal water extraction strategy and equipment maintenance plan.

Images