Intelligent multifunctional water quality monitoring display control method and device

Abstract

The present application relates to the technical field of water quality monitoring, and discloses an intelligent multifunctional water quality monitoring display control method and device. The method includes: collecting target water body temperature data and target water body flow data of the water purifier pipeline through a controller; performing feature extraction and feature fusion to obtain a temperature-flow feature matrix; performing multi-mode intelligent analysis and time series prediction through an initial water quality analysis model to obtain a comprehensive water quality evaluation result; performing multi-objective trade-offs and optimization calculations to obtain the optimal water body control sequence of the controller; performing step-by-step execution and real-time feedback adjustment to obtain control execution process data and water quality change response data; performing visualization processing and multi-mode display, and obtaining water purifier operation status data and user interaction data to optimize the initial water quality analysis model to obtain a target water quality analysis model. The present application realizes intelligent multifunctional water quality monitoring and display control.

Description

Technical Field

[0001] The present application relates to the technical field of water quality monitoring, and in particular to an intelligent multifunctional water quality monitoring display control method and device. Background Art

[0002] Water purification equipment is increasingly used in homes and commercial places. However, traditional water purification systems often lack intelligent and refined management, and are difficult to adapt to complex and changing water quality conditions and user needs. Existing water quality monitoring methods are usually limited to the detection of a single parameter, which cannot fully reflect the water quality status, and the data analysis and processing capabilities are limited, making it difficult to achieve accurate water quality prediction and effective control strategy formulation.

[0003] In addition, the control systems of most water purification equipment still use fixed control logic, lacking flexibility and adaptability, and unable to dynamically adjust operating parameters according to real-time water quality changes and user needs. This may not only lead to low water purification efficiency, but also affect the service life and operating costs of the equipment. At the same time, existing water quality monitoring and control systems usually lack user-friendly interfaces and visual display functions, making it difficult for users to intuitively understand the water quality status and equipment operation status, and unable to easily perform personalized settings and adjustments. Summary of the invention

[0004] The present application provides an intelligent multifunctional water quality monitoring and display control method and device, which are used to implement intelligent multifunctional water quality monitoring and display control.

[0005] In a first aspect, the present application provides an intelligent multifunctional water quality monitoring display control method, the intelligent multifunctional water quality monitoring display control method comprising:

[0006] The original water temperature data and the original water flow data of the water purifier pipeline are collected and preprocessed by a preset controller to obtain the target water temperature data and the target water flow data;

[0007] Performing feature extraction and feature fusion on the target water body temperature data and the target water body flow data respectively to obtain a temperature-flow feature matrix;

[0008] Input the temperature-flow characteristic matrix into a preset initial water quality analysis model for multi-mode intelligent analysis and time series prediction to obtain a comprehensive water quality assessment result;

[0009] Perform multi-objective trade-offs and optimization calculations based on the comprehensive water quality assessment results to obtain the optimal water body control sequence of the controller;

[0010] The optimal water body control sequence is executed step by step and adjusted with real-time feedback to obtain control execution process data and water quality change response data;

[0011] The control execution process data and the water quality change response data are visualized and displayed in multiple modes, and the water purifier operation status data and user interaction data are obtained to optimize the initial water quality analysis model to obtain a target water quality analysis model.

[0012] In a second aspect, the present application provides an intelligent multifunctional water quality monitoring display control device, the intelligent multifunctional water quality monitoring display control device comprising:

[0013] The acquisition module is used to acquire the original water temperature data and the original water flow data of the water purifier pipeline through a preset controller and perform preprocessing to obtain the target water temperature data and the target water flow data;

[0014] A fusion module is used to extract and fuse the target water body temperature data and the target water body flow data respectively to obtain a temperature-flow feature matrix;

[0015] An analysis module, used for inputting the temperature-flow characteristic matrix into a preset initial water quality analysis model for multi-mode intelligent analysis and time series prediction to obtain a comprehensive water quality assessment result;

[0016] A calculation module, used for performing multi-objective trade-offs and optimization calculations based on the comprehensive water quality assessment results to obtain an optimal water body control sequence of the controller;

[0017] An execution module is used to perform step-by-step execution and real-time feedback adjustment on the optimal water body control sequence to obtain control execution process data and water quality change response data;

[0018] The optimization module is used to visualize and display the control execution process data and the water quality change response data in multiple modes, and obtain the water purifier operation status data and user interaction data to optimize the initial water quality analysis model to obtain the target water quality analysis model.

[0019] The third aspect of the present application provides an intelligent multifunctional water quality monitoring and display control device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the intelligent multifunctional water quality monitoring and display control device executes the above-mentioned intelligent multifunctional water quality monitoring and display control method.

[0020] The fourth aspect of the present application provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the above-mentioned intelligent multifunctional water quality monitoring and display control method.

[0021] In the technical solution provided by this application, comprehensive monitoring of water quality parameters is achieved by simultaneously collecting and processing water temperature and flow data, and technologies such as noise elimination, outlier detection and data smoothing are used to effectively improve the quality and reliability of the original data. Through time window segmentation, statistical feature calculation and correlation analysis, effective feature extraction and fusion of temperature and flow data are achieved. Combined with time series decomposition and multiple prediction models, a comprehensive analysis of water quality trends, seasonality and randomness is achieved, and the accuracy and reliability of predictions are improved. Through a multi-objective optimization algorithm, a balance is achieved between water quality, energy consumption and cost, and a better control strategy is obtained. The step-by-step execution and real-time feedback mechanism are adopted to enable the control strategy to be dynamically adjusted according to actual conditions, thereby improving the accuracy and adaptability of the control. Through multi-dimensional visualization and interactive design, intuitive data display and a convenient user interface are provided, enhancing the usability of the system. Through continuous learning and parameter optimization, the self-improvement of the water quality analysis model is achieved, and the long-term performance and adaptability of the system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0023] Figure 1 This is a schematic diagram of an embodiment of the intelligent multifunctional water quality monitoring display control method in the embodiment of the present application;

[0024] Figure 2 This is a schematic diagram of an embodiment of an intelligent multifunctional water quality monitoring display control device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The embodiment of the present application provides an intelligent multifunctional water quality monitoring display control method and device. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the intelligent multifunctional water quality monitoring display control method in the embodiment of the present application includes:

[0027] Step S101: collecting original water temperature data and original water flow data of the water purifier pipeline through a preset controller and preprocessing them to obtain target water temperature data and target water flow data;

[0028] It is understandable that the execution subject of the present application may be an intelligent multifunctional water quality monitoring display control device, or a terminal or a server, which is not limited here. The present application embodiment is described by taking a server as the execution subject as an example.

[0029] Specifically, the original water temperature data in the water purifier pipeline is sampled regularly by a preset controller to obtain a temperature sampling sequence. The temperature sampling sequence is subjected to noise elimination processing to remove environmental interference and sensor errors, and preliminary denoised temperature data is obtained. The preliminary denoised temperature data is subjected to data smoothing processing, and the data curve is made smoother and continuous by technical means such as filters or moving average methods to obtain target water temperature data. At the same time, the controller samples the original water flow data in the water purifier pipeline regularly to obtain a flow sampling sequence. In order to improve the reliability of the flow data, the flow sampling sequence is subjected to outlier detection, and abnormal data points caused by sensor failure or emergencies are identified and eliminated to obtain preliminary processed flow data. The preliminary processed flow data is subjected to data smoothing processing so that the flow data exhibits more stable and continuous characteristics in the time series, and smoothed flow data is obtained. A flow prediction model is established based on the smoothed flow data. The model can be constructed using methods such as time series analysis and machine learning, and through training and calibration of historical data, it can make reasonable predictions of future flow changes. After obtaining the flow prediction result, the flow prediction result is data fused with the actual measured value. The data fusion process can use weighted averaging, Kalman filtering and other technologies to comprehensively consider the reliability and accuracy of the predicted results and the actual measured values ​​to obtain the target water flow data. Time synchronization processing is performed on the target water temperature data and the target water flow data to ensure that the temperature and flow data at the same time point can be matched to form a complete water quality data time series. Time synchronization processing can be achieved through interpolation, time alignment and other methods to obtain synchronized water quality data. Data standardization processing is performed on the synchronized water quality data. By normalizing or standardizing the data, data of different dimensions and ranges can be compared and analyzed on the same scale to obtain standardized target water temperature data and target water flow data.

[0030] Step S102, performing feature extraction and feature fusion on the target water body temperature data and the target water body flow data respectively to obtain a temperature-flow feature matrix;

[0031] Specifically, the target water body temperature data is segmented into time windows, and the continuous temperature data is segmented into several temperature data subsequence sets by setting a certain time interval, and the statistical features of each temperature data subsequence set are calculated, including mean, variance, maximum value, minimum value, etc., to obtain the temperature statistical feature vector. At the same time, the target water body flow data is segmented into similar time windows to obtain the flow data subsequence set, and the corresponding statistical features of the flow data subsequence set are calculated to obtain the flow statistical feature vector. The temperature statistical feature vector and the flow statistical feature vector are dimensionally aligned, and the length and order of the feature vectors are adjusted to make them consistent in time and dimension to obtain the aligned feature vector. The aligned feature vector is subjected to correlation analysis, and the correlation coefficient between the temperature and flow data is calculated to generate the temperature-flow correlation coefficient matrix. According to the temperature-flow correlation coefficient matrix, high-correlation features are selected, and those features that have a significant impact on temperature and flow are screened out to obtain the filtered feature set. The filtered feature set is subjected to principal component analysis, and the high-dimensional feature vector is converted into a low-dimensional feature vector through dimensionality reduction technology to reduce the redundancy and noise of the data, and the reduced-dimensional feature vector is obtained. The eigenvectors after dimensionality reduction are standardized, and the eigenvalues ​​of different scales are converted to the same dimension range to obtain standardized eigenvectors. The standardized eigenvectors are arranged in chronological order to ensure that the temperature and flow characteristics at each time point can accurately correspond to each other, forming a complete temperature-flow characteristic matrix.

[0032] Step S103, inputting the temperature-flow characteristic matrix into a preset initial water quality analysis model for multi-mode intelligent analysis and time series prediction to obtain a comprehensive water quality assessment result;

[0033] Specifically, the temperature-flow characteristic matrix is ​​decomposed into trend items, seasonal items, and random items. The trend item reflects the long-term trend of the data, the seasonal item captures the periodic change characteristics of the data, and the random item represents the unpredictable components and noise in the data. The trend item is modeled by a two-layer long short-term memory network. The deep learning model can effectively capture the long-term dependency and short-term fluctuations in the time series to obtain the trend prediction results. At the same time, the seasonal item is subjected to Fourier analysis to extract its periodic characteristic parameters. Based on these parameters, a seasonal prediction model is constructed to capture the periodic fluctuations in the data and obtain the seasonal prediction results. For the random item, an autoregressive model is used for modeling. By analyzing the self-correlation of the data, the future changes of the random item are predicted to obtain the random item prediction results. The trend prediction results, seasonal prediction results, and random item prediction results are combined to form a comprehensive prediction result. The confidence interval of the comprehensive prediction result is calculated to quantify the uncertainty range of the prediction result. At the same time, the comprehensive prediction result is detected for anomalies based on historical water quality data, and potential anomalies in the data are identified by setting thresholds or applying statistical methods. Combined with the uncertainty range and potential anomalies, the comprehensive forecast results are risk assessed to determine the risk level of water quality. The risk assessment process takes into account the uncertainty of the forecast results and the severity of potential anomalies to ensure the accuracy and practicality of the risk level assessment. The comprehensive forecast results, water quality risk levels and historical water quality data are compared and analyzed in multiple dimensions. Through vertical and horizontal comparisons, the trends and patterns of water quality changes are revealed, and a comprehensive water quality comprehensive assessment result is obtained.

[0034] Step S104: Perform multi-objective trade-offs and optimization calculations based on the comprehensive water quality assessment results to obtain the optimal water body control sequence of the controller;

[0035] Specifically, the comprehensive water quality assessment results are decomposed into specific water quality optimization goals, energy consumption optimization goals and cost optimization goals. These goals correspond to the requirements of improving water quality, reducing energy consumption and reducing operating costs. A multi-objective optimization model is constructed based on the water quality optimization goals, energy consumption optimization goals and cost optimization goals, and these three goals are combined to form an initial optimization problem. The model is mathematically expressed as a multi-objective optimization problem, which requires the optimization of multiple goals and the satisfaction of constraints at the same time. The constraints of the initial optimization problem are analyzed to clarify the constraints under various actual conditions, such as equipment operation restrictions, energy consumption limits and cost budgets, so as to determine the feasible solution space. In this feasible solution space, the initial population is generated by random or heuristic methods to obtain a candidate solution set. The candidate solution set is non-dominated sorted, and the rank and congestion of each solution are determined by the sorting algorithm. Non-dominated sorting is a sorting method for multi-objective optimization, which can effectively evaluate the advantages and disadvantages of each solution on multiple goals. Excellent individuals are selected according to the rank and congestion to form a parent population to ensure that the population has good diversity and high fitness. The parent population is subjected to crossover and mutation operations, and a new offspring population is generated through the basic operations of the genetic algorithm. These operations simulate the natural evolution process and promote the diversity of solutions and global search capabilities. The parent population and the offspring population are merged and a new round of non-dominated sorting is performed to obtain an updated population. The merging process helps to retain excellent solutions while introducing new solutions for exploration. The updated population is iteratively optimized and solved, and the optimal solution is gradually approached through multiple iterations until the preset termination conditions are reached, such as reaching the maximum number of iterations or the change amplitude of the solution meets the convergence criteria. Through iterative optimization, the Pareto optimal solution set is finally obtained. The Pareto optimal solution set contains a set of solutions that perform well on multiple objectives and represent different trade-offs. Fuzzy decision-making is performed on the Pareto optimal solution set, and the optimal control strategy is selected in combination with actual needs and preferences to obtain the optimal water control sequence of the controller. The fuzzy decision-making method can handle the uncertainty and ambiguity in multi-objective optimization and provide more flexible and practical decision support.

[0036] Step S105, performing step-by-step execution and real-time feedback adjustment on the optimal water body control sequence to obtain control execution process data and water quality change response data;

[0037] Specifically, the optimal water body control sequence is divided into time steps, and the control sequence is subdivided into multiple time segments to obtain a control subsequence set. Each control subsequence represents a specific control instruction within a time step. The first subsequence in the control subsequence set is converted into an execution instruction, and the high-level control instruction is converted into a specific control parameter. The specific control parameters may include the running speed of the pump, the opening of the valve, and other parameters related to the operation of the water purifier. The controller controls the water purifier pipeline according to the specific control parameters, and implements the operation required by the subsequence by executing these specific parameters to obtain the initial execution state data. The initial execution state data includes the operating state of the water purifier, the feedback information of the equipment, etc., which is the direct result of the control operation. The initial execution state data is monitored in real time, and the short-term water quality change data is obtained through sensors and monitoring systems to reflect the immediate changes in water quality after the initial control operation. The deviation analysis of the short-term water quality change data and the expected target is performed, and the deviation evaluation result is obtained by comparing the actual water quality change with the expected target. The deviation evaluation result reveals the gap between the current control operation and the ideal state, which is the basis for adjusting the control strategy. According to the deviation evaluation results, the next control subsequence is dynamically adjusted and the control parameters are updated to compensate for the deviation in the previous operation. The updated control parameters will better meet the current water quality conditions and control objectives. Use the updated control parameters to continue to perform control operations and obtain new execution status data. By continuously adjusting and executing control parameters, each step of the operation moves in the direction of optimization. This process is repeated until all control subsequences are completed, and multiple execution process data are finally obtained. By integrating all execution process data in time series, a comprehensive execution trajectory is obtained. The comprehensive execution trajectory is correlated with the water quality change data, and the control execution process data and water quality change response data are obtained by comparing and analyzing the comprehensive execution trajectory with the actual water quality response.

[0038] Step S106: Visualize and display the control execution process data and water quality change response data in multiple modes, obtain the water purifier operation status data and user interaction data to optimize the initial water quality analysis model, and obtain the target water quality analysis model.

[0039] Specifically, the control execution process data is normalized, and the standardized control execution data is obtained by converting data of different dimensions into the same scale range. At the same time, the water quality change response data is decomposed into trend, cycle and random component data by time series decomposition technology. The standardized control execution data and trend, cycle and random component data are visually mapped in multiple dimensions, and the relationship between the data is intuitively displayed by using charts and graphs to obtain the initial visualization chart. The initial visualization chart is interactively designed to increase the functions that users can directly operate and adjust, and obtain a multi-mode display interface. Users can view and analyze the data through the multi-mode display interface, and the system collects the user's operation behavior data through the interface to obtain user interaction data. The operating parameters of the water purifier pipeline are collected and processed in real time, and the various operating status data of the water purifier are obtained using sensors and monitoring systems. These data reflect the operation status and performance of the water purifier at different time points. The user interaction data and the water purifier operation status data are correlated and analyzed, and the model optimization suggestions are obtained by analyzing the relationship between the user's operation behavior and the actual operation of the water purifier. These suggestions may include adjusting the structure of the model, modifying the parameters of the model, etc., so that the model better meets the actual situation and user needs. According to the model optimization suggestions, the initial water quality analysis model is structurally adjusted, and the updated model structure is obtained by adding or deleting certain model components, changing the connection method of the model, etc. After the structural adjustment, the control execution process data and water quality change response data are used to re-estimate the parameters of the updated model structure, and the various parameters of the model are re-estimated through the optimization algorithm to ensure that the model can accurately reflect the characteristics and laws of the actual data and obtain the optimized model parameters. The optimized model parameters are loaded into the updated model structure, and combined with the optimized model structure and parameters to form a complete target water quality analysis model.

[0040] In the embodiment of the present application, by simultaneously collecting and processing water body temperature and flow data, comprehensive monitoring of water quality parameters is achieved, and technologies such as noise elimination, outlier detection and data smoothing are adopted to effectively improve the quality and reliability of the original data. Through time window segmentation, statistical feature calculation and correlation analysis, effective feature extraction and fusion of temperature and flow data are achieved, and combined with time series decomposition and multiple prediction models, a comprehensive analysis of water quality trends, seasonality and randomness is achieved, and the accuracy and reliability of prediction are improved. Through the multi-objective optimization algorithm, a balance is achieved between water quality, energy consumption and cost, and a better control strategy is obtained. The step-by-step execution and real-time feedback mechanism are adopted so that the control strategy can be dynamically adjusted according to the actual situation, which improves the accuracy and adaptability of the control. Through multi-dimensional visualization and interactive design, intuitive data display and convenient user operation interface are provided, and the usability of the system is enhanced. Through continuous learning and parameter optimization, the self-improvement of the water quality analysis model is achieved, and the long-term performance and adaptability of the system are improved.

[0041] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0042] (1) The original water temperature data in the water purifier pipeline is sampled regularly through a preset controller to obtain a temperature sampling sequence;

[0043] (2) Perform noise elimination processing on the temperature sampling sequence to obtain preliminary denoised temperature data, and perform data smoothing processing on the preliminary denoised temperature data to obtain the target water body temperature data;

[0044] (3) Regularly sample the original water flow data in the water purifier pipeline to obtain a flow sampling sequence;

[0045] (4) Performing outlier detection on the flow sampling sequence to obtain preliminarily processed flow data, and performing data smoothing on the preliminarily processed flow data to obtain smoothed flow data;

[0046] (5) Establish a flow prediction model based on the smoothed flow data to obtain the flow prediction results, and fuse the flow prediction results with the actual measured values ​​to obtain the target water body flow data;

[0047] (6) Performing time synchronization processing on the target water body temperature data and the target water body flow data to obtain synchronized water quality data;

[0048] (7) Perform data standardization on the synchronized water quality data to obtain standardized target water body temperature data and target water body flow data.

[0049] Specifically, the original water temperature data in the water purifier pipeline is sampled regularly through a preset controller to form a temperature sampling sequence. The temperature sampling sequence is subjected to noise elimination. Common methods include moving average filtering and Kalman filtering. For example, a moving average filter is used to process the temperature data. Set a window size ,For example , then De-noised temperature data It can be expressed as:

[0050] ;

[0051] Thus, a preliminary denoised temperature data sequence is obtained. The preliminary denoised temperature data is smoothed. The exponential smoothing method can be used for smoothing, and its formula is:

[0052] ;

[0053] in It is Smoothed data at each time point, is the smoothing coefficient, which ranges from 0 to 1. For example, if you select , smooth the initial denoised temperature data to obtain the target water body temperature data At the same time, the original water flow data in the water purifier pipeline is sampled regularly. Assuming that the flow data is collected once a minute, 60 flow data points are obtained in one hour to form a flow sampling sequence: ,in Representative Flow value of the minute. Detect outliers in the flow sampling sequence. Use the three sigma principle to detect and calculate the mean of the flow data. and standard deviation , and mark the excess The values ​​in the range are outliers. In this way, the preliminarily processed flow data is obtained after the outliers are removed. The preliminarily processed flow data is smoothed by using the same method as the temperature data, such as exponential smoothing, to obtain smoothed flow data. . A traffic prediction model is established based on smoothed traffic data. Assuming that the autoregressive integrated moving average model (ARIMA) is used for modeling, the model can be expressed as:

[0054] ;

[0055] in and are the autoregressive and moving average polynomials, is the regression delay operator, is the difference order, is the error term. The model is trained with historical data to obtain the traffic prediction result. The traffic prediction results are fused with the actual measured values. The fusion method can be weighted average method, the formula is:

[0056] ;

[0057] in is the fused traffic data. and is the weight coefficient, satisfying , get the target water flow data . Perform time synchronization processing on the target water body temperature data and the target water body flow data to obtain synchronized water quality data. Perform data standardization processing on the synchronized water quality data to obtain standardized target water body temperature data and target water body flow data.

[0058] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0059] (1) The target water body temperature data is segmented into time windows to obtain a temperature data subsequence set, and the statistical features of the temperature data subsequence set are calculated to obtain a temperature statistical feature vector;

[0060] (2) Segment the target water body flow data into time windows to obtain a flow data subsequence set, and calculate the statistical features of the flow data subsequence set to obtain a flow statistical feature vector;

[0061] (3) Dimensionally aligning the temperature statistical feature vector and the flow statistical feature vector to obtain an aligned feature vector, and performing correlation analysis on the aligned feature vector to obtain a temperature-flow correlation coefficient matrix;

[0062] (4) Select high-correlation features according to the temperature-flow correlation coefficient matrix to obtain a screened feature set, and perform principal component analysis on the screened feature set to obtain a feature vector after dimensionality reduction;

[0063] (5) The eigenvector after dimensionality reduction is standardized to obtain a standardized eigenvector, and the standardized eigenvector is arranged in chronological order to obtain a temperature-flow characteristic matrix.

[0064] Specifically, the target water body temperature data is segmented into time windows. Assume there is a temperature data sequence containing 1000 data points. , select a window size , split the temperature data series into 10 subsequences, each containing 100 data points. Subsequence It can be expressed as: In this way, we get the temperature data subsequence set . Calculate statistical features for the temperature data subsequence set. For each subsequence , calculate its statistical characteristics such as mean, standard deviation, maximum and minimum. Indicates The mean of the subsequences is calculated as:

[0065] ;

[0066] in is a subsequence Similarly, we calculate the standard deviation , maximum value and minimum value These statistical features constitute the temperature statistical feature vector At the same time, the target water body flow data is segmented into time windows, assuming that the flow data sequence Also select the window size , split it into 10 subsequences , each subsequence contains 100 data points. The statistical characteristics of the flow data subsequence set are calculated in the same way as the temperature data, and the flow statistical feature vector is obtained. In order to align the dimensions of the temperature statistical feature vector and the flow statistical feature vector, ensure that each feature vector has the same length and corresponding features. Perform correlation analysis on the aligned feature vectors and calculate the correlation coefficient between the temperature and flow features. Correlation coefficient matrix Elements Indicates temperature characteristics and flow characteristics The correlation between them is calculated as:

[0067] ;

[0068] Where Cov represents covariance, represents the standard deviation. Correlation coefficient matrix It can help identify highly correlated feature pairs. Select high-correlation features according to the temperature-flow correlation coefficient matrix to obtain the filtered feature set. Assume that the feature pairs with absolute values ​​of correlation coefficients greater than 0.8 are selected as high-correlation features to form a filtered feature set. Perform principal component analysis on the filtered feature set, convert high-dimensional feature vectors into low-dimensional feature vectors through linear transformation, and extract the main feature components. The mathematical process of principal component analysis includes calculating eigenvalues ​​and eigenvectors, and the formula is:

[0069] ;

[0070] in is the covariance matrix, is a diagonal matrix of eigenvalues, is the eigenvector matrix. By choosing The eigenvector corresponding to the maximum eigenvalue is obtained to obtain the eigenvector after dimensionality reduction The eigenvectors after dimensionality reduction are standardized, and the features of different dimensions are converted to the same scale range to obtain standardized eigenvectors. The standardized eigenvectors are arranged in chronological order to form a temperature-flow feature matrix.

[0071] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0072] (1) Perform time series decomposition on the temperature-flow characteristic matrix to obtain trend terms, seasonal terms, and random terms;

[0073] (2) A two-layer long short-term memory network model is used to model the trend term to obtain the trend prediction result, and Fourier analysis is performed on the seasonal term to obtain the periodic characteristic parameters;

[0074] (3) Construct a seasonal prediction model based on the periodic characteristic parameters to obtain seasonal prediction results, and perform autoregressive modeling on the random terms to obtain random term prediction results;

[0075] (4) Combine the trend forecast results, seasonal forecast results and random item forecast results to obtain a comprehensive forecast result;

[0076] (5) Calculate the confidence interval of the comprehensive prediction results to obtain the uncertainty range, and perform anomaly detection on the comprehensive prediction results based on historical water quality data to obtain potential anomalies;

[0077] (6) Combine the uncertainty range and potential anomalies to conduct risk assessment on the comprehensive prediction results and obtain the water quality risk level;

[0078] (7) Conduct a multi-dimensional comparative analysis of the comprehensive prediction results, water quality risk levels, and historical water quality data to obtain a comprehensive water quality assessment result.

[0079] Specifically, the temperature-flow characteristic matrix is ​​decomposed into three parts through time series decomposition technology: trend term, seasonal term and random term. Assume that the temperature-flow characteristic matrix is , it can be expressed as: ,in is a trend item, is the seasonal term, is a random term. For the trend term Modeling of a two-layer long short-term memory network. The long short-term memory network is a recursive neural network that can capture long-term dependencies and is suitable for time series prediction. The trend item data is input into the first layer of the long short-term memory network for processing to obtain the intermediate state, and then input into the second layer of the long short-term memory network for further processing. The two-layer structure captures complex patterns in the time series. After training is completed, the trend prediction results are obtained. For seasonal items , perform Fourier analysis to extract its periodic characteristic parameters. Fourier analysis can decompose the time series into a combination of a series of sine waves and cosine waves, thereby extracting the periodic components in the data. The result of Fourier transform can be expressed as:

[0080] ;

[0081] in and are the Fourier coefficients, is the period length of the data. Based on the periodic characteristic parameters, a seasonal prediction model is constructed and the seasonal prediction results are obtained. For random items , an autoregressive model is used for modeling. The autoregressive model makes predictions through a linear combination of the current data and the data at the previous few time points. The form of the autoregressive model can be expressed as:

[0082] ;

[0083] in are the model coefficients, is the model order, is the error term. By training the autoregressive model, we get the prediction results of the random terms. . The trend prediction results , Seasonal forecast results And the random item prediction results Combine to get comprehensive prediction results , the formula is:

[0084] ;

[0085] In order to evaluate the uncertainty of the prediction results, the confidence interval is calculated for the comprehensive prediction results. The calculation of the confidence interval can be based on the distribution of the prediction error. Assuming that the prediction error follows a normal distribution, the confidence interval can be expressed as:

[0086] ;

[0087] in is the quantile of the standard normal distribution, is the standard deviation of the prediction error. Anomaly detection is performed on the comprehensive prediction results based on historical water quality data to identify potential anomalies. Anomaly detection can be achieved by setting thresholds or using statistical methods. For example, the 3-sigma principle is used to identify anomalies that exceed the mean. The values ​​of the range are outliers. The outliers are combined with the confidence interval for risk assessment. The assessment process takes into account the uncertainty of the prediction results and the severity of the outliers to obtain the water quality risk level. The comprehensive prediction results, water quality risk level and historical water quality data are compared and analyzed in multiple dimensions. Through longitudinal (time dimension) and horizontal (different feature dimensions) comparisons, the trends and patterns of water quality changes are revealed, and a comprehensive water quality comprehensive assessment result is obtained. For example, suppose there is a set of temperature-flow characteristic matrices , perform time series decomposition and obtain trend terms , Seasonal Item and random items (Estimated by AR model). Use a two-layer long short-term memory network to estimate the trend term Modeling and trend prediction results For seasonal items Perform Fourier analysis to obtain periodic characteristic parameters , , thereby constructing a seasonal forecasting model and obtaining seasonal forecasting results For random items Perform autoregressive modeling, assuming that the AR model order is 2, and obtain the random item prediction results By combining these prediction results, we get the comprehensive prediction result On this basis, the confidence interval is calculated, assuming that the standard deviation of the prediction error is , then the confidence interval is . Anomaly detection is performed in combination with historical water quality data. By setting thresholds, potential anomalies are identified, and risk assessment is performed in combination with confidence intervals to determine the water quality risk level. Through multi-dimensional comparative analysis of comprehensive prediction results, water quality risk levels, and historical water quality data, the changing trends and potential problems of water quality are revealed, and a comprehensive water quality comprehensive assessment result is obtained.

[0088] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0089] (1) Decompose the comprehensive water quality assessment results into targets to obtain water quality optimization targets, energy consumption optimization targets, and cost optimization targets;

[0090] (2) Construct a multi-objective optimization model based on the water quality optimization goal, energy consumption optimization goal, and cost optimization goal to obtain the initial optimization problem;

[0091] (3) Analyze the constraints of the initial optimization problem to obtain a feasible solution space, generate an initial population in the feasible solution space, and obtain a candidate solution set;

[0092] (4) Perform non-dominated sorting on the candidate solution set to obtain the rank and crowding degree of each solution, and select excellent individuals based on the rank and crowding degree to obtain the parent population;

[0093] (5) Perform crossover and mutation operations on the parent population to obtain the offspring population, and merge the parent population and the offspring population to perform a new round of non-dominated sorting to obtain the updated population;

[0094] (6) Iterate and optimize the updated population until the termination condition is reached and the Pareto optimal solution set is obtained;

[0095] (7) Perform fuzzy decision making on the Pareto optimal solution set to obtain the optimal water body control sequence of the controller.

[0096] Specifically, the comprehensive water quality assessment results are decomposed into targets. It is assumed that the comprehensive water quality assessment results contain data in multiple dimensions, including water quality parameters such as pH value, dissolved oxygen content, turbidity, etc., as well as the corresponding energy consumption and operating cost information. Based on these data, water quality optimization targets, energy consumption optimization targets and cost optimization targets are extracted. The water quality optimization target can be expressed as maximizing the stability and uniformity of certain key water quality parameters, the energy consumption optimization target can be expressed as minimizing the energy consumption of the water purification system, and the cost optimization target can be expressed as minimizing the operating cost of the water purification system. Construct a multi-objective optimization model based on the optimization targets. Assume that there are three objective functions, namely represents the water quality optimization target, represents the energy consumption optimization target, represents the cost optimization objective, where is the control variable vector. The multi-objective optimization problem can be expressed as: , find the solution that makes these three objective functions reach the optimal state at the same time. Perform constraint analysis on the initial optimization problem. Constraints can include equipment operation restrictions, energy consumption limits, and cost budgets. For example, setting the maximum energy consumption of the equipment to and the maximum operating cost is , then the constraints can be expressed as: and . Through these constraints, the feasible solution space is determined, that is, the set of solutions that meet all constraints. Generate an initial population in the feasible solution space, and use random generation or heuristic methods to obtain a set of candidate solutions. The initial population should be diverse so as to cover a wider solution space. Each candidate solution represents a possible control strategy. Perform non-dominated sorting on the candidate solution set and evaluate the performance of each solution on multiple objectives. Non-dominated sorting is a sorting method for multi-objective optimization. By comparing the advantages and disadvantages of solutions on various objectives, the rank and congestion of each solution are determined. The result of non-dominated sorting divides the candidate solutions into different levels, and the solutions in each level are not inferior to other solutions on each objective. Select excellent individuals according to the rank and congestion to form the parent population. The selection method can adopt tournament selection or roulette selection to ensure that the selected individuals have high fitness and diversity. Perform crossover and mutation operations on the parent population to generate a new child population. The crossover operation generates new solutions by exchanging some genes of the parent individuals; the mutation operation introduces new features by randomly modifying some genes of the individuals. The parent population and the child population are merged, and a new round of non-dominated sorting is performed to obtain the updated population. Through multiple rounds of crossover, mutation, and selection operations, the population gradually approaches the optimal solution set. In each generation, non-dominated sorting helps retain excellent solutions while introducing new solutions for exploration. The updated population is iteratively optimized and solved until the preset termination condition is reached. The termination condition can be that the maximum number of iterations is reached or the change in the solution is less than the preset threshold. Through this iterative optimization process, the Pareto optimal solution set is finally obtained. The Pareto optimal solution set contains a set of solutions that perform well on all objectives and represent different trade-offs. Fuzzy decision-making is performed on the Pareto optimal solution set, and the optimal control strategy is selected according to actual needs and preferences. The fuzzy decision-making method can handle the uncertainty and ambiguity in multi-objective optimization and provide more flexible and practical decision support. Finally, the optimal water control sequence of the controller is obtained.

[0097] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0098] S1: Divide the optimal water body control sequence into time steps to obtain a set of control subsequences;

[0099] S2: convert the execution instruction of the first subsequence in the control subsequence set to obtain specific control parameters;

[0100] S3: The controller controls the water purifier pipeline according to specific control parameters to obtain initial execution state data;

[0101] S4: Monitor the initial execution status data in real time to obtain short-term water quality change data;

[0102] S5: Perform deviation analysis on the short-term water quality change data and the expected target to obtain the deviation assessment result;

[0103] S6: dynamically adjust the next control subsequence according to the deviation evaluation result to obtain updated control parameters;

[0104] S7: Continue to execute the control operation using the updated control parameters to obtain new execution status data;

[0105] S8: repeating steps S4 to S7 until all control subsequences are completed, and obtaining a plurality of execution process data;

[0106] S9: integrate multiple execution process data in time series to obtain a comprehensive execution trajectory;

[0107] S10: Correlation analysis is performed on the comprehensive execution trajectory and the water quality change data to obtain control execution process data and water quality change response data.

[0108] Specifically, the optimal water body control sequence is divided into time steps to obtain a set of control subsequences. Assume that the optimal water body control sequence is ,in Indicates By setting the time step , convert the sequence Split into several control subsequence sets , each subsequence contains control instructions, namely ,in . Perform execution instruction conversion on the first subsequence in the control subsequence set to obtain specific control parameters. Assume that the first subsequence is , through the conversion function Convert it into a specific set of control parameters ,in Including specific pump speed, valve opening, disinfectant concentration and other parameters. The controller controls the specific parameters Control the water purifier pipeline, execute these parameters to adjust the operating status of the water purifier, and obtain the initial execution status data ,in Including flow, pressure, chemical parameters and other data recorded during the execution process. Conduct real-time monitoring and use sensors and monitoring systems to obtain short-term water quality change data ,in Indicates the change of water quality parameters in the first time step. With expected goals Perform deviation analysis and calculate deviation ,in Indicates the gap between the current water quality parameters and the expected target. The deviation assessment results will serve as the basis for the next adjustment. , for the next control subsequence Perform dynamic adjustments and update control parameter sets ,in represents the adjustment function, which uses the deviation information to modify the control parameters to make them closer to the expected target. Continue to execute control operations and obtain new execution status data Through dynamic adjustment and execution, it is ensured that each operation is carried out in the optimized direction. The process is repeated continuously, and steps S4 to S7 are repeated until all control subsequences are completed, and finally multiple execution process data are obtained. . For execution process data Perform time series integration to obtain a comprehensive execution trajectory . Comprehensive execution trace It shows the execution status changes in the entire control process and the operating status of the water purifier at different time points. Water quality change data Conduct correlation analysis to obtain control execution process data and water quality change response data. Through comparative analysis, reveal the impact of control operations on water quality, and thus optimize the control strategy.

[0109] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0110] (1) Perform data normalization on the control execution process data to obtain standardized control execution data, and perform time series decomposition on the water quality change response data to obtain trend, cycle and random component data;

[0111] (2) Perform multi-dimensional visualization mapping of standardized control execution data and trend, cycle, and random component data to obtain an initial visualization chart;

[0112] (3) Interactively design the initial visualization chart to obtain a multi-modal display interface, and collect user operation behavior data through the multi-modal display interface to obtain user interaction data;

[0113] (4) Collect and process the operating parameters of the water purifier pipeline in real time to obtain the water purifier operating status data, and perform correlation analysis between user interaction data and water purifier operating status data to obtain model optimization suggestions;

[0114] (5) Adjust the structure of the initial water quality analysis model according to the model optimization suggestions to obtain an updated model structure;

[0115] (6) Use the control execution process data and water quality change response data to re-estimate the parameters of the updated model structure to obtain the optimized model parameters;

[0116] (7) Load the optimized model parameters into the updated model structure to obtain the target water quality analysis model.

[0117] Specifically, the control execution process data is normalized to convert data of different dimensions to the same scale range for subsequent analysis and comparison. The commonly used normalization method is Z-score normalization, and its formula is:

[0118] ;

[0119] in, Represents the original data, is the mean of the data, is the standard deviation of the data. Through this formula, the control execution process data is converted into standardized control execution data , with a mean of 0 and a standard deviation of 1. Perform time series decomposition on the water quality change response data, and decompose the original data into trend items, periodic items, and random items, which represent the long-term change trend, periodic fluctuations, and random fluctuations of the data, respectively. STL (seasonal and trend decomposition method) can be used for decomposition, and the formula is:

[0120] ;

[0121] in, is the original time series data, is a trend item, is a periodic term, is a random term. Through this decomposition method, the trend, cycle and random component data of the water quality change response data are obtained respectively. The standardized control execution data and the trend, cycle and random component data are visually mapped in multiple dimensions to obtain the initial visualization chart. The relationship and changes between the data are intuitively displayed through the chart. Using visualization libraries such as matplotlib or seaborn, the standardized control execution data and the decomposed trend, cycle and random component data are plotted in the same chart to show their changes in different time periods. The initial visualization chart is interactively designed to obtain a multi-mode display interface. The purpose of interactive design is to increase the interactivity between users and charts, so that users can view and analyze data more conveniently. Using interactive visualization tools such as Plotly or Bokeh, add functions such as sliders, buttons and hover information, so that users can freely select time ranges, data types and display modes. User operation behavior data is collected through the multi-mode display interface to obtain user interaction data. User operation behaviors on the interactive interface, such as selecting time ranges, switching data types, etc., will be recorded to form user interaction data. These data can be used to analyze user preferences and operating habits, and further optimize visualization interfaces and data analysis models. The operating parameters of the water purifier pipeline are collected and processed in real time to obtain the operating status data of the water purifier. Through sensors and monitoring systems, the operating parameters of the water purifier, such as flow, pressure, temperature and chemical composition, are collected in real time and recorded in the database to form the operating status data of the water purifier. The user interaction data and the operating status data of the water purifier are correlated and analyzed to obtain model optimization suggestions. Through data mining and analysis technology, the relationship between user operation behavior and the operating status of the water purifier is identified to find potential optimization directions. For example, if the user frequently adjusts a parameter and the change of the parameter is significantly correlated with the performance of the water purifier, the parameter can be optimized. According to the model optimization suggestions, the initial water quality analysis model is structurally adjusted to obtain an updated model structure. The structural adjustment can include adding or deleting model variables, modifying model formulas and adjusting model parameters, so that the model can better reflect the actual situation and user needs. The control execution process data and water quality change response data are used to re-estimate the parameters of the updated model structure to obtain the optimized model parameters. The model parameters are recalculated through parameter re-estimation techniques, such as the least squares method or the maximum likelihood estimation method, to make the model more accurate and effective. The optimized model parameters are loaded into the updated model structure to obtain the target water quality analysis model. This model can not only accurately predict water quality changes, but also dynamically adjust according to user operation behavior and water purifier operation status to provide a better control strategy.

[0122] The above describes the intelligent multifunctional water quality monitoring display control method in the embodiment of the present application. The following describes the intelligent multifunctional water quality monitoring display control device in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the intelligent multifunctional water quality monitoring display control device includes:

[0123] The acquisition module 201 is used to acquire the original water temperature data and the original water flow data of the water purifier pipeline through a preset controller and perform preprocessing to obtain the target water temperature data and the target water flow data;

[0124] A fusion module 202 is used to extract and fuse the target water body temperature data and the target water body flow data respectively to obtain a temperature-flow feature matrix;

[0125] The analysis module 203 is used to input the temperature-flow characteristic matrix into a preset initial water quality analysis model for multi-mode intelligent analysis and time series prediction to obtain a comprehensive water quality assessment result;

[0126] The calculation module 204 is used to perform multi-objective trade-offs and optimization calculations based on the comprehensive water quality assessment results to obtain the optimal water body control sequence of the controller;

[0127] An execution module 205 is used to perform step-by-step execution and real-time feedback adjustment of the optimal water body control sequence to obtain control execution process data and water quality change response data;

[0128] The optimization module 206 is used to visualize and display the control execution process data and water quality change response data in multiple modes, and obtain the water purifier operation status data and user interaction data to optimize the initial water quality analysis model to obtain the target water quality analysis model.

[0129] Through the synergy of the above components, by simultaneously collecting and processing water temperature and flow data, comprehensive monitoring of water quality parameters is achieved. The quality and reliability of the original data are effectively improved by adopting technologies such as noise elimination, outlier detection and data smoothing. Through time window segmentation, statistical feature calculation and correlation analysis, effective feature extraction and fusion of temperature and flow data are achieved. Combined with time series decomposition and multiple prediction models, a comprehensive analysis of water quality trends, seasonality and randomness is achieved, and the accuracy and reliability of prediction are improved. Through multi-objective optimization algorithms, a balance is achieved between water quality, energy consumption and cost, and a better control strategy is obtained. The step-by-step execution and real-time feedback mechanism are adopted to enable the control strategy to be dynamically adjusted according to actual conditions, which improves the accuracy and adaptability of control. Through multi-dimensional visualization and interactive design, intuitive data display and convenient user operation interface are provided, which enhances the usability of the system. Through continuous learning and parameter optimization, the self-improvement of the water quality analysis model is achieved, and the long-term performance and adaptability of the system are improved.

[0130] The present application also provides an intelligent multifunctional water quality monitoring and display control device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the intelligent multifunctional water quality monitoring and display control method in the above-mentioned embodiments.

[0131] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the intelligent multifunctional water quality monitoring and display control method.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0134] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent multifunctional water quality monitoring and display control method, characterized in that: The method comprises: The original water temperature data and the original water flow data of the water purifier pipeline are collected and preprocessed by a preset controller to obtain the target water temperature data and the target water flow data; Performing feature extraction and feature fusion on the target water body temperature data and the target water body flow data respectively to obtain a temperature-flow feature matrix; Input the temperature-flow characteristic matrix into the preset initial water quality analysis model for multi-mode intelligent analysis and time series prediction to obtain a comprehensive water quality assessment result; specifically including: performing time series decomposition on the temperature-flow characteristic matrix to obtain trend items, seasonal items and random items; performing double-layer long and short-term memory network modeling on the trend items to obtain trend prediction results, and performing Fourier analysis on the seasonal items to obtain periodic characteristic parameters; constructing a seasonal prediction model based on the periodic characteristic parameters to obtain seasonal prediction results, and performing autoregressive modeling on the random items to obtain random item prediction results; combining the trend prediction results, the seasonal prediction results and the random item prediction results to obtain a comprehensive prediction result; performing confidence interval calculation on the comprehensive prediction results to obtain an uncertainty range, and performing anomaly detection on the comprehensive prediction results based on historical water quality data to obtain potential anomalies; combining the uncertainty range and the potential anomalies to perform risk assessment on the comprehensive prediction results to obtain a water quality risk level; performing multi-dimensional comparative analysis on the comprehensive prediction results, the water quality risk level and historical water quality data to obtain a comprehensive water quality assessment result; Perform multi-objective trade-offs and optimization calculations based on the comprehensive water quality assessment results to obtain the optimal water body control sequence of the controller; The optimal water body control sequence is executed step by step and adjusted with real-time feedback to obtain control execution process data and water quality change response data; The control execution process data and the water quality change response data are visualized and displayed in multiple modes, and the water purifier operation status data and user interaction data are obtained to optimize the initial water quality analysis model to obtain a target water quality analysis model.

2. The intelligent multifunctional water quality monitoring display control method according to claim 1 is characterized in that: The preset controller collects the original water temperature data and the original water flow data of the water purifier pipeline and performs preprocessing to obtain the target water temperature data and the target water flow data, including: The original water temperature data in the water purifier pipeline is sampled regularly through a preset controller to obtain a temperature sampling sequence; Performing noise elimination processing on the temperature sampling sequence to obtain preliminary denoised temperature data, and performing data smoothing processing on the preliminary denoised temperature data to obtain target water body temperature data; The original water flow data in the water purifier pipeline is sampled regularly to obtain a flow sampling sequence; Performing outlier detection on the flow sampling sequence to obtain initially processed flow data, and performing data smoothing on the initially processed flow data to obtain smoothed flow data; Establishing a flow prediction model based on the smoothed flow data to obtain a flow prediction result, and fusing the flow prediction result with the actual measurement value to obtain target water body flow data; Performing time synchronization processing on the target water body temperature data and the target water body flow data to obtain synchronized water quality data; The synchronized water quality data is subjected to data standardization processing to obtain standardized target water body temperature data and target water body flow data.

3. The intelligent multifunctional water quality monitoring display control method according to claim 1 is characterized in that: The feature extraction and feature fusion are respectively performed on the target water body temperature data and the target water body flow data to obtain a temperature-flow feature matrix, including: Performing time window segmentation on the target water body temperature data to obtain a temperature data subsequence set, and calculating statistical features on the temperature data subsequence set to obtain a temperature statistical feature vector; Performing time window segmentation on the target water body flow data to obtain a flow data subsequence set, and calculating statistical features on the flow data subsequence set to obtain a flow statistical feature vector; Performing dimension alignment on the temperature statistical feature vector and the flow statistical feature vector to obtain an aligned feature vector, and performing correlation analysis on the aligned feature vector to obtain a temperature-flow correlation coefficient matrix; Selecting high-correlation features according to the temperature-flow correlation coefficient matrix to obtain a screened feature set, and performing principal component analysis on the screened feature set to obtain a feature vector after dimension reduction; The reduced-dimensional feature vectors are standardized to obtain standardized feature vectors, and the standardized feature vectors are arranged in chronological order to obtain a temperature-flow feature matrix.

4. The intelligent multifunctional water quality monitoring display control method according to claim 1 is characterized in that: The multi-objective trade-off and optimization calculation based on the comprehensive water quality assessment result to obtain the optimal water body control sequence of the controller includes: Decomposing the comprehensive water quality assessment results into targets to obtain water quality optimization targets, energy consumption optimization targets and cost optimization targets; Constructing a multi-objective optimization model according to the water quality optimization target, the energy consumption optimization target and the cost optimization target to obtain an initial optimization problem; Performing constraint condition analysis on the initial optimization problem to obtain a feasible solution space, and generating an initial population in the feasible solution space to obtain a candidate solution set; Performing non-dominated sorting on the candidate solution set to obtain the rank and crowding degree of each solution, and selecting excellent individuals according to the rank and crowding degree to obtain a parent population; Performing crossover and mutation operations on the parent population to obtain a child population, and merging the parent population with the child population to perform a new round of non-dominated sorting to obtain an updated population; Iteratively optimizing and solving the updated population until a termination condition is reached to obtain a Pareto optimal solution set; Fuzzy decision making is performed on the Pareto optimal solution set to obtain an optimal water body control sequence of the controller.

5. The intelligent multifunctional water quality monitoring display control method according to claim 1 is characterized in that: The optimal water body control sequence is executed step by step and adjusted with real-time feedback to obtain control execution process data and water quality change response data, including: S1: Divide the optimal water body control sequence into time steps to obtain a control subsequence set; S2: performing execution instruction conversion on the first subsequence in the control subsequence set to obtain specific control parameters; S3: the controller controls the water purifier pipeline according to the specific control parameters to obtain initial execution state data; S4: monitoring the initial execution status data in real time to obtain short-term water quality change data; S5: performing deviation analysis on the short-term water quality change data and the expected target to obtain a deviation assessment result; S6: dynamically adjusting the next control subsequence according to the deviation evaluation result to obtain updated control parameters; S7: Continue to execute the control operation using the updated control parameters to obtain new execution status data; S8: repeating steps S4 to S7 until all control subsequences are completed, and obtaining a plurality of execution process data; S9: integrating the multiple execution process data in time series to obtain a comprehensive execution trajectory; S10: Correlation analysis is performed on the comprehensive execution trajectory and the water quality change data to obtain control execution process data and water quality change response data.

6. The intelligent multifunctional water quality monitoring display control method according to claim 5 is characterized in that: The control execution process data and the water quality change response data are visualized and displayed in multiple modes, and the water purifier operation status data and user interaction data are obtained to optimize the initial water quality analysis model to obtain the target water quality analysis model, including: Performing data normalization processing on the control execution process data to obtain standardized control execution data, and performing time series decomposition on the water quality change response data to obtain trend, cycle and random component data; Perform multi-dimensional visualization mapping on the standardized control execution data and the trend, cycle and random component data to obtain an initial visualization chart; Interactively designing the initial visualization chart to obtain a multi-mode display interface, and collecting user operation behavior data through the multi-mode display interface to obtain user interaction data; The operating parameters of the water purifier pipeline are collected and processed in real time to obtain the operating status data of the water purifier, and the user interaction data and the operating status data of the water purifier are correlated and analyzed to obtain model optimization suggestions; According to the model optimization suggestion, the structure of the initial water quality analysis model is adjusted to obtain an updated model structure; Re-estimating the parameters of the updated model structure using the control execution process data and the water quality change response data to obtain optimized model parameters; The optimized model parameters are loaded into the updated model structure to obtain a target water quality analysis model.

7. An intelligent multifunctional water quality monitoring and display control device, characterized in that: The device is used to execute the intelligent multifunctional water quality monitoring display control method according to any one of claims 1 to 6, comprising: The acquisition module is used to acquire the original water temperature data and the original water flow data of the water purifier pipeline through a preset controller and perform preprocessing to obtain the target water temperature data and the target water flow data; A fusion module is used to extract and fuse the target water body temperature data and the target water body flow data respectively to obtain a temperature-flow feature matrix; An analysis module, used for inputting the temperature-flow characteristic matrix into a preset initial water quality analysis model for multi-mode intelligent analysis and time series prediction to obtain a comprehensive water quality assessment result; A calculation module, used for performing multi-objective trade-offs and optimization calculations based on the comprehensive water quality assessment results to obtain an optimal water body control sequence of the controller; An execution module is used to perform step-by-step execution and real-time feedback adjustment on the optimal water body control sequence to obtain control execution process data and water quality change response data; The optimization module is used to visualize and display the control execution process data and the water quality change response data in multiple modes, and obtain the water purifier operation status data and user interaction data to optimize the initial water quality analysis model to obtain the target water quality analysis model.

8. An intelligent multifunctional water quality monitoring display control device, characterized in that: The intelligent multifunctional water quality monitoring and display control device comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instruction in the memory so that the intelligent multifunctional water quality monitoring and display control device executes the intelligent multifunctional water quality monitoring and display control method as described in any one of claims 1-6.

9. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the intelligent multifunctional water quality monitoring and display control method as described in any one of claims 1 to 6 is implemented.

Images