Water quality detection method, device and equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and provides a water quality detection method, device and equipment and a storage medium, and the method comprises the following steps: obtaining the temperature and turbidity of a specific water sample, carrying out standardization treatment on the temperature to obtain a standardized temperature, analyzing the standardized temperature and the turbidity, obtaining long-term water quality change prediction, and carrying out data driving simulation. The method comprises the following steps: obtaining a simulated water quality change path and expected environmental influence, adjusting temperature by utilizing the simulated water quality change path to obtain a temperature adjusting scheme, optimizing turbidity by utilizing the expected environmental influence to obtain a turbidity optimization scheme, and combining the temperature adjusting scheme and the turbidity optimization scheme to obtain the turbidity optimization scheme. And obtaining a comprehensive water quality management scheme and generating a water quality maintenance report. Dynamic monitoring and accurate prediction are realized by using monitoring data of temperature and turbidity, and the problems of insufficient detection accuracy and prediction capability caused by incapability of effectively predicting and coping with a long-term water quality change trend when the water quality is detected are solved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a water quality detection method, device, equipment and storage medium. Background Art

[0002] Water quality monitoring is a key link in environmental supervision and water resources management. With the acceleration of industrialization and urbanization, water pollution is becoming more and more serious, and the threat to healthy ecosystems is intensifying. Therefore, real-time and accurate monitoring of water quality and prediction of water quality trends have become important tasks in environmental protection and water resources management. The development of water quality monitoring technology, especially the application of information technology and data analysis technology, has made water quality monitoring methods increasingly efficient and intelligent.

[0003] Among the relevant technical means, temperature and turbidity are used as the main monitoring indicators. Traditional water quality detection methods focus on the real-time measurement of these two indicators, and use simple statistical methods to analyze the data to achieve preliminary early warning of water quality changes. For example, by measuring the temperature and turbidity of water samples, environmental scientists can quickly assess whether the water body is affected by thermal pollution or suspended particulate matter, so as to make a quick response.

[0004] Regarding the above technical solution, although the water quality status can be monitored in real time through temperature and turbidity measurements, the in-depth analysis of the long-term impact of temperature changes on water quality is ignored when testing the water quality. It is impossible to effectively predict and respond to long-term water quality change trends, and there are problems with insufficient accuracy and predictive ability. Summary of the invention

[0005] In order to improve the problem of insufficient detection accuracy and prediction ability due to the inability to effectively predict and respond to long-term water quality change trends when testing water quality, the present application provides a water quality testing method, device, equipment and storage medium.

[0006] The present invention provides a water quality detection method, comprising: obtaining the temperature and turbidity of a specific water sample, standardizing the temperature to obtain a standardized temperature, correlating the standardized temperature with the turbidity to obtain a preliminary water quality index; performing a graph analysis on the preliminary water quality index to obtain a detailed water quality graph, using the detailed water quality graph to perform a deep analysis on the standardized temperature to obtain a water temperature impact assessment; performing a multidimensional data correlation analysis on the detailed water quality graph to obtain a key water quality index, adjusting the key water quality index through the water temperature impact assessment to obtain a water quality adjustment index, and using the water quality adjustment index to monitor the temperature change trend; Perform a time series analysis on the change trend to obtain temperature predictions for several time nodes, perform trend mapping on the temperature predictions for all time nodes to obtain a long-term water quality change prediction; perform data-driven simulation on the long-term water quality change prediction to obtain a simulated water quality change path and expected environmental impact, formulate a temperature adjustment strategy using the simulated water quality change path to obtain a temperature adjustment plan, optimize the turbidity using the expected environmental impact to obtain a turbidity optimization plan; evaluate the synergistic effect of the turbidity optimization plan based on the temperature adjustment plan to obtain a comprehensive water quality management plan, and generate a water quality maintenance report based on the comprehensive water quality management plan.

[0007] As a preferred embodiment, the steps of obtaining the temperature and turbidity of a specific water sample, standardizing the temperature to obtain a standardized temperature, and correlating the standardized temperature with the turbidity to obtain a preliminary water quality index include: obtaining the temperature of the specific water sample using a temperature sensor, and standardizing the temperature using a preset temperature calibration module to obtain a standardized temperature; obtaining the turbidity of the specific water sample based on a light scattering detector, inputting the standardized temperature and the turbidity into a preset data analysis system for correlation analysis, and in the data analysis system, calculating the correlation between the standardized temperature and the turbidity using a regression analysis method to obtain a preliminary water quality index.

[0008] As a preferred scheme, the step of performing a spectral analysis on the preliminary water quality index to obtain a detailed water quality map, and performing an in-depth analysis of the standardized temperature using the detailed water quality map to obtain a water temperature impact assessment includes: reducing the dimension of the preliminary water quality index by principal component analysis to obtain a principal component score vector, a water sample concentration vector and a calibration coefficient, classifying the principal component score vector using a spectral clustering algorithm to obtain a classification result and a classification center, regressing and fitting the water sample concentration vector using a linear regression analysis of the classification result to obtain a fitting result; performing a regression analysis on the calibration coefficient using a multivariate regression analysis of the classification center to obtain a calibration result; performing a cluster analysis on the fitting result and the calibration result to obtain a detailed water quality map; performing a regression analysis on the detailed water quality map and the standardized temperature using a multivariate linear regression model to obtain a statistical error and a goodness of fit, correcting the statistical error by error correction to obtain a corrected error, and evaluating the goodness of fit by residual analysis to obtain an analysis result; and performing a comprehensive analysis on the corrected error and the analysis result using a Bayesian analysis method to obtain a water temperature impact assessment.

[0009] As a preferred scheme, the steps of performing multidimensional data association analysis on the detailed water quality map to obtain a key water quality index, adjusting the key water quality index through the water temperature impact assessment to obtain a water quality adjustment index, and using the water quality adjustment index to monitor the temperature change trend include: performing signal decomposition on the detailed water quality map using empirical mode decomposition to obtain a signal component, a trend component and a noise component, applying a differential method to smooth the signal component to obtain a smoothed result and a residual result; performing denoising on the trend component through wavelet transform analysis of the smoothed result to obtain a denoised result; performing spectral analysis on the residual result and the noise component through Fourier transform analysis to obtain a spectral result; performing frequency domain analysis on the denoised result and the spectral result through fast Fourier transform to obtain a key water quality index; performing correlation analysis on the water temperature impact assessment and the key water quality index through linear regression to obtain a statistical result. The method comprises the following steps: calculating the error parameters and the correction coefficient of the statistical parameters, performing error evaluation on the statistical parameters by residual analysis to obtain the error evaluation result, correcting the correction coefficient by generalized maximum expectation estimation method to obtain the correction result; comprehensively analyzing the error evaluation result and the correction result by covariance analysis method to obtain the water quality adjustment index; performing state transition analysis on the water quality adjustment index by applying a preset Markov chain model to obtain the state probability matrix, transition probability and steady-state probability, estimating the state probability matrix by Bayesian estimation to obtain the estimation matrix and matrix confidence interval, jointly estimating the estimation matrix and the transition probability by expectation maximization algorithm to obtain the joint estimation result, numerically simulating the matrix confidence interval and the steady-state probability by Monte Carlo simulation to obtain the numerical simulation result; performing trend analysis on the joint estimation result and the numerical simulation result based on the hidden Markov model to obtain the temperature change trend.

[0010] As a preferred solution, the step of performing time series analysis on the change trend to obtain temperature predictions for several time nodes, performing trend mapping on the temperature predictions for all time nodes, and obtaining long-term water quality change predictions includes: using an autoregressive moving average model to perform time series modeling on the change trend to obtain autoregressive coefficients and moving average coefficients, estimating the autoregressive coefficients by the least squares method to obtain an estimated result and an estimated error, and filtering the moving average coefficients by a Kalman filter to obtain a filtered result; performing a predictive analysis based on the estimated result and the filtered result to obtain several time nodes. temperature prediction; using an isometric mapping algorithm to map the temperature predictions of all time nodes to obtain a multi-state sequence, using the Viterbi algorithm to perform optimal path estimation on the multi-state sequence to obtain a path estimation result; performing probability modeling on the path estimation result through Gaussian process regression to obtain a probability distribution and a probability confidence interval, performing numerical simulation on the probability distribution through the Monte Carlo simulation method to obtain a numerical result, and correcting the probability confidence interval through the Monte Carlo simulation to obtain an interval correction result; performing a comprehensive analysis on the numerical result and the interval correction result through robustness analysis to obtain a long-term water quality change prediction.

[0011] As a preferred scheme, the steps of performing data-driven simulation on the prediction of long-term water quality changes to obtain a simulated water quality change path and expected environmental impact, formulating a temperature adjustment strategy using the simulated water quality change path to obtain a temperature adjustment plan, and optimizing the turbidity using the expected environmental impact to obtain a turbidity optimization plan include: performing data-driven modeling on the prediction of long-term water quality changes through numerical simulation of a preset proxy model to obtain proxy model parameters, simulation parameters, and predicted environmental variables, performing multi-parameter sampling on the proxy model parameters using Latin hypercube sampling to obtain multi-parameter sampling results, and performing regression analysis on the simulation parameters using multivariate regression to obtain multivariate regression results; performing environmental modeling based on the multi-parameter sampling results and the multivariate regression results. to obtain a simulated water quality change path and expected environmental impact; to optimize the simulated water quality change path through an environmental simulation path optimization method to obtain an optimized path, to perform predictive control analysis on the optimized path through a predictive control method to obtain a control strategy; to formulate a temperature adjustment plan according to the control strategy to obtain a temperature adjustment plan; to simulate and analyze the expected environmental impact using a numerical simulation method to obtain expected simulation results and expected environmental variables, to perform regression analysis on the expected simulation results through multiple regression to obtain expected regression results, to simulate and analyze the expected environmental variables through a Monte Carlo simulation method to obtain variable simulation results; to comprehensively optimize the expected regression results and the variable simulation results through a preset control method to obtain a turbidity optimization plan.

[0012] As a preferred scheme, the steps of evaluating the synergistic effect of the turbidity optimization scheme according to the temperature adjustment scheme to obtain a comprehensive water quality management scheme, and generating a water quality maintenance report according to the comprehensive water quality management scheme include: using a comprehensive evaluation model in combination with the temperature adjustment scheme to perform a comprehensive benefit analysis on the turbidity optimization scheme to obtain optimization evaluation results and synergistic benefit results, performing regression analysis on the optimization evaluation results by partial least squares regression to obtain regression coefficients, performing synergistic optimization analysis on the regression coefficients and the synergistic benefit results to obtain a comprehensive water quality management scheme; and inputting the comprehensive water quality management scheme into a preset water quality assessment system to generate a water quality maintenance report.

[0013] The present application also provides a water quality detection device, including: an acquisition module, used to acquire the temperature and turbidity of a specific water sample, standardize the temperature to obtain a standardized temperature, and perform correlation analysis on the standardized temperature and the turbidity to obtain a preliminary water quality index; an analysis module, used to perform a spectrum analysis on the preliminary water quality index to obtain a detailed water quality spectrum, and perform a deep analysis on the standardized temperature using the detailed water quality spectrum to obtain a water temperature impact assessment; an adjustment module, used to perform a multi-dimensional data correlation analysis on the detailed water quality spectrum to obtain a key water quality index, adjust the key water quality index through the water temperature impact assessment to obtain a water quality adjustment index, and use the water quality adjustment index to monitor the temperature change trend; A prediction module is used to perform a time series analysis on the change trend to obtain temperature predictions for several time nodes, and to perform trend mapping on the temperature predictions for all time nodes to obtain a long-term water quality change prediction; an optimization module is used to perform a data-driven simulation on the long-term water quality change prediction to obtain a simulated water quality change path and expected environmental impact, and to formulate a temperature adjustment strategy using the simulated water quality change path to obtain a temperature adjustment plan, and to optimize the turbidity using the expected environmental impact to obtain a turbidity optimization plan; a generation module is used to evaluate the synergistic effect of the turbidity optimization plan based on the temperature adjustment plan to obtain a comprehensive water quality management plan, and to generate a water quality maintenance report based on the comprehensive water quality management plan.

[0014] The present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and wherein the processor implements any of the above-mentioned water quality detection methods when executing the computer program.

[0015] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor is enabled to execute the water quality detection method as described in any one of the above.

[0016] Compared with the prior art, the present application has the following beneficial effects: high detection accuracy and sufficient prediction capability. By comprehensively utilizing the monitoring data of temperature and turbidity, and executing methods including standardization processing, correlation analysis, graph analysis, multidimensional data correlation analysis, time series analysis and data-driven simulation, the dynamic monitoring and accurate prediction of water quality are realized, which not only improves the understanding and prediction ability of water quality change trends, but also forms a scientific temperature adjustment scheme and turbidity optimization scheme through data-driven simulation and optimization, which improves the problem of insufficient detection accuracy and prediction ability due to the inability to effectively predict and respond to long-term water quality change trends when testing water quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0019] Figure 1 It is a schematic diagram of a flow chart of a water quality detection method provided by an embodiment of the present invention; Figure 2 is a schematic block diagram of the structure of a water quality detection device provided by an embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0020] Description of reference numerals: 10. Water quality detection device; 11. Acquisition module; 12. Analysis module; 13. Adjustment module; 14. Prediction module; 15. Optimization module; 16. Generation module; 20. Electronic device; 21. Memory; 22. Processor. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0023] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0024] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0026] Example 1 like Figure 1 As shown, a water quality detection method provided in an embodiment of the present application includes steps S100 to S600.

[0027] Step S100, obtaining the temperature and turbidity of a specific water sample, standardizing the temperature to obtain a standardized temperature, and performing correlation analysis between the standardized temperature and the turbidity to obtain a preliminary water quality index.

[0028] In this step, the temperature and turbidity data of the water samples are collected by using sensors; specifically, the temperature data is converted into standardized temperature through an algorithm to ensure the independence of the data from environmental factors, and the turbidity data is combined with a statistical model for correlation analysis, thereby effectively mapping the preliminary status of the water quality.

[0029] For example, if the collected temperature data is 15°C, after standardization, the data is converted into a relative value such as 0.5 (assumed to be between 0 and 1). This standardization process takes into account seasonal temperature differences and geographical differences. The standardized temperature is then associated with the turbidity value measured during the same period. The relationship between the two is analyzed through a machine learning model to obtain preliminary water quality indicators.

[0030] Step S200: Analyze the preliminary water quality indicators to obtain a detailed water quality map, and use the detailed water quality map to deeply analyze the standardized temperature to obtain a water temperature impact assessment.

[0031] In this step, preliminary water quality indicators are visualized by using graphical analysis tools. Specifically, a detailed water quality map is constructed to reveal the complex relationships between different indicators, and the impact of standardized temperature is deeply analyzed through advanced data analysis techniques to derive a specific impact assessment of temperature on water quality.

[0032] For example, the map analysis showed areas where turbidity anomalies increased when the temperature rose. This pattern confirmed the impact of temperature change on turbidity anomalies through further regression analysis, thus providing a scientific basis for water temperature impact assessment.

[0033] Step S300: perform multidimensional data correlation analysis on the detailed water quality map to obtain a key water quality index, adjust the key water quality index through water temperature impact assessment to obtain a water quality adjustment index, and use the water quality adjustment index to monitor the temperature change trend.

[0034] In this step, multidimensional data correlation analysis is performed by comprehensively applying a variety of data analysis techniques; specifically, key water quality indices are extracted from detailed water quality maps using data mining methods, and these indices are adjusted in combination with water temperature impact assessments to obtain more accurate water quality adjustment indices.

[0035] For example, analysis shows that the concentrations of copper and zinc increase significantly during high temperatures. At this time, by adjusting key water quality indices, the monitoring weight of these heavy metals is increased to better predict and respond to the potential impact of temperature changes on water quality.

[0036] Step S400: Perform time series analysis on the change trend to obtain temperature predictions for several time nodes, perform trend mapping on the temperature predictions for all time nodes, and obtain long-term water quality change predictions.

[0037] In this step, the monitored water quality adjustment index is analyzed for long-term trends through time series analysis techniques; specifically, the temperature at several future time nodes is predicted, and these predictions are trend mapped with historical data to form a long-term prediction of water quality changes.

[0038] For example, the ARIMA model is used to fit data from the past five years to predict temperature trends in the next 12 months. These trends are combined with the water quality adjustment index to infer future changes in water quality to guide future water quality management strategies.

[0039] Step S500, perform data-driven simulation on the long-term water quality change prediction to obtain the simulated water quality change path and expected environmental impact, use the simulated water quality change path to formulate a temperature adjustment strategy to obtain a temperature adjustment plan, and use the expected environmental impact to optimize turbidity to obtain a turbidity optimization plan.

[0040] In this step, data-driven scenario analysis is performed using advanced simulation techniques; specifically, a simulation model is constructed to predict the water quality change pathways under different management strategies and to assess the potential impacts of these pathways on the environment, thereby developing targeted temperature regulation and turbidity optimization plans.

[0041] For example, the simulation showed how turbidity responded to these adjustments under different temperature regulation schemes. The simulation results showed that turbidity was significantly reduced under the strategy of reducing industrial emissions, thus determining the optimal temperature regulation and turbidity optimization scheme.

[0042] Step S600: Evaluate the synergistic effect of the turbidity optimization scheme according to the temperature adjustment scheme to obtain a comprehensive water quality management scheme, and generate a water quality maintenance report according to the comprehensive water quality management scheme.

[0043] In this step, the synergistic effects of various schemes are evaluated; specifically, the effects of the temperature regulation scheme and the turbidity optimization scheme are comprehensively analyzed to confirm the joint benefits of these measures and form a comprehensive water quality management plan based on them.

[0044] For example, simulation analysis confirmed that the temperature regulation program can effectively reduce the increase in chemical oxygen demand during high temperature periods, and the turbidity optimization program can reduce the concentration of suspended particulate matter. The combination of these two measures significantly improves the overall water quality.

[0045] In this embodiment, first, by obtaining the temperature and turbidity of a specific water sample, the temperature is standardized to obtain the standardized temperature. Then, the standardized temperature and turbidity are correlated and analyzed to obtain preliminary water quality indicators. Then, the preliminary water quality indicators are analyzed by graph analysis to obtain a detailed water quality graph, and the standardized temperature is deeply analyzed using the detailed water quality graph to obtain a water temperature impact assessment. After that, the detailed water quality graph is subjected to multidimensional data correlation analysis to obtain a key water quality index, and the key water quality index is adjusted by the water temperature impact assessment to obtain a water quality adjustment index. The water quality adjustment index is used to monitor the temperature change trend, and the change trend is analyzed by time series to obtain a temperature forecast for several time nodes. The temperature forecasts for all time nodes are trend mapped to obtain a long-term water quality change forecast. Finally, a data-driven simulation is performed on the long-term water quality change forecast to obtain a simulated water quality change path and expected environmental impact, and a temperature adjustment strategy is formulated using the simulated water quality change path to obtain a temperature adjustment plan, and the turbidity is optimized using the expected environmental impact to obtain a turbidity optimization plan. The synergistic effect of the turbidity optimization plan is evaluated according to the temperature adjustment plan to obtain a comprehensive water quality management plan, and a water quality maintenance report is generated based on the comprehensive water quality management plan.

[0046] Through temperature standardization and turbidity correlation analysis, the preliminary situation of water quality changes can be grasped more accurately. Detailed water quality maps are used for in-depth analysis and water temperature impact assessment to improve the accuracy of water quality monitoring. Through multi-dimensional data correlation analysis and the use of water quality adjustment index, not only can water quality conditions be monitored in real time, but future water quality changes can also be accurately predicted. Finally, through multi-stage in-depth analysis and adjustment, such as the comprehensive application of temperature adjustment solutions and turbidity optimization solutions, comprehensive and dynamic management of water quality is achieved, which improves the problem of insufficient detection accuracy and prediction ability due to the inability to effectively predict and respond to long-term water quality changes when testing water quality.

[0047] Embodiment 2: In step S100, the temperature of a specific water sample is acquired by using a temperature sensor, and the temperature is standardized by a preset temperature calibration module to obtain a standardized temperature.

[0048] Real-time data is acquired through the temperature sensor and algorithmically processed through the calibration module to standardize the temperature data to ensure the accuracy of subsequent analysis.

[0049] For example, a temperature sensor is used to collect the water temperature once every minute, and the actual temperature is converted into a standardized temperature through a calibration algorithm in the microprocessor to eliminate the impact of environmental variations.

[0050] The turbidity of a specific water sample is obtained based on a light scattering detector, and the standardized temperature and turbidity are input into a preset data analysis system for correlation analysis. In the data analysis system, the correlation between the standardized temperature and turbidity is calculated using a regression analysis method to obtain a preliminary water quality indicator.

[0051] Through the integration of optical measurement technology and data processing algorithms, in-depth analysis and quantitative evaluation of factors affecting water quality can be achieved.

[0052] For example, the turbidity data measured by the light scattering detector and the standardized temperature data processed by the temperature calibration module are input into a multivariate regression model. The model analyzes the relationship between the two and accurately predicts preliminary water quality indicators, such as suspended particulate matter content and potential pollution level, to obtain preliminary water quality indicators.

[0053] In step S200, the preliminary water quality index is reduced in dimension through principal component analysis to obtain the principal component score vector, water sample concentration vector and calibration coefficient, the principal component score vector is classified using the spectral clustering algorithm to obtain the classification result and classification center, and the classification result is regressed and fitted on the water sample concentration vector through linear regression analysis to obtain the fitting result.

[0054] By applying statistical analysis techniques and machine learning methods, efficient simplification of water quality data and accurate extraction of key features are achieved.

[0055] For example, multiple water quality indicators are input into principal component analysis to obtain several principal component score vectors, which reflect the most influential factors in water quality data. Subsequently, similar data samples are grouped using a spectral clustering algorithm to determine different water quality categories, and the specific concentration of each category is accurately predicted using a linear regression method to obtain a fitting result.

[0056] The calibration coefficients were regressed using the classification center of multiple regression analysis to obtain the calibration results. The fitting results and calibration results were aggregated to obtain a detailed water quality map.

[0057] Through comprehensive multi-dimensional data processing and analysis technology, comprehensive calibration of water quality data and detailed description of water quality characteristics are achieved.

[0058] For example, calibration parameters were determined by performing multiple regression analysis on the calibration coefficients for each classification center, and these data were further integrated to form a comprehensive and detailed water quality map that can describe various aspects of water quality in detail.

[0059] The detailed water quality map and the standardized temperature were regressed using a multiple linear regression model to obtain statistical errors and goodness of fit. The statistical errors were corrected by error correction to obtain the corrected errors. The goodness of fit was evaluated by residual analysis to obtain the analysis results.

[0060] Multiple linear regression is used to ensure that the correlation analysis between water quality profiles and temperature data is accurate, and error correction and residual analysis are used to optimize model performance and improve the model's predictive ability and accuracy.

[0061] For example, after analysis, it was found that the statistical error of the model was high, so the error correction technology was used to adjust the original model parameters, and the residual analysis method was further used to detect the goodness of fit to ensure that the final model can accurately reflect the impact of temperature on water quality.

[0062] The Bayesian analysis method is used to comprehensively analyze the correction errors and analysis results to obtain the water temperature impact assessment.

[0063] By integrating the corrected errors and water quality analysis results through Bayesian analysis, the impact of temperature changes on water quality can be accurately evaluated, providing scientific decision-making support for water quality management.

[0064] For example, the corrected model errors and water quality data are input into the Bayesian analysis framework to calculate the range of water quality changes and corresponding probabilities under different temperature conditions, providing a quantitative basis for formulating response measures.

[0065] In step S300, the detailed water quality map is decomposed by using empirical mode decomposition to obtain signal components, trend components and noise components, and the signal components are smoothed by using a differential method to obtain smoothing results and residual results.

[0066] The essential characteristics of complex signals are analyzed through empirical mode decomposition, and effectively smoothed through the difference method to improve the accuracy of data analysis and the reliability of prediction models.

[0067] For example, the data in the detailed water quality atlas is separated into multiple eigenmode functions through empirical mode decomposition, each mode represents a specific frequency component of the water quality signal, and then the difference method is applied to smooth these signals to reduce random fluctuations in the analysis, thereby obtaining a more stable data representation, and obtaining smoothed results and residual results.

[0068] The trend component is denoised by wavelet transform analysis and smoothing results to obtain the denoised result.

[0069] Through the multi-scale analysis capability of wavelet transform, noise can be effectively removed from the trend component, further clarifying the display of water quality change trends and enhancing the accuracy of data interpretation.

[0070] For example, the smoothed signal can be further denoised using wavelet transform. This method can subdivide the signal at different scales, accurately remove noise components, and retain more critical trend information, thereby providing clear and accurate trend data for water quality analysis.

[0071] The residual results and noise components are analyzed by Fourier transform analysis to obtain the spectrum results.

[0072] The time series data is converted into frequency domain representation through Fourier transform, and its frequency components are analyzed in detail to effectively identify and analyze the periodicity and randomness characteristics in the signal.

[0073] For example, by performing Fourier transform on residuals and noise and analyzing the spectral characteristics of these components, periodic fluctuations and abnormal frequencies in water quality data can be identified, which helps to further understand the inherent laws and abnormal sources of water quality changes.

[0074] The denoising results and spectrum results were analyzed in the frequency domain by fast Fourier transform to obtain the key water quality index.

[0075] Through the high efficiency and accuracy of fast Fourier transform, the denoised data and spectrum analysis results are comprehensively evaluated to extract key indicators that affect water quality changes.

[0076] For example, fast Fourier transform is used to perform frequency domain analysis on the denoised data, and combined with the results of spectrum analysis, the frequency components most relevant to water quality changes, such as the frequency of changes in concentration of specific chemical substances, are selected to define key water quality indices.

[0077] Linear regression is used to conduct correlation analysis between water temperature impact assessment and key water quality indexes to obtain statistical parameters and correction coefficients. Error assessment of statistical parameters is performed through residual analysis to obtain error assessment results. The correction coefficients are corrected through generalized maximum expectation estimation method to obtain corrected results.

[0078] The relationship between water temperature and key water quality indices was established through linear regression, and residual analysis and generalized maximum expectation estimation were used to optimize model parameters to ensure the high accuracy and reliability of the analysis results.

[0079] For example, a linear regression model is used to analyze the impact of water temperature changes on key water quality indices, errors in the model are identified through residual analysis, and then the generalized maximum expectation estimation method is used to adjust and optimize the model coefficients, thereby improving the accuracy and stability of the prediction model.

[0080] The error assessment results and correction results were comprehensively analyzed by covariance analysis to obtain the water quality adjustment index.

[0081] The corrected model errors and statistical parameters are integrated through covariance analysis to form a comprehensive water quality adjustment index, providing a quantitative adjustment basis for water quality management.

[0082] For example, the covariance analysis method is used to analyze the adjusted errors and model parameters. This method can more comprehensively evaluate the accuracy and applicability of the model and obtain a water quality adjustment index that comprehensively considers various factors, which is helpful to accurately regulate and improve water quality.

[0083] The preset Markov chain model is applied to perform state transition analysis on the water quality adjustment index to obtain the state probability matrix, transition probability and steady-state probability. The state probability matrix is ​​estimated through Bayesian estimation to obtain the estimation matrix and matrix confidence interval. The estimation matrix and transition probability are jointly estimated using the expectation maximization algorithm to obtain the joint estimation result. The matrix confidence interval and steady-state probability are numerically simulated through Monte Carlo simulation to obtain the numerical simulation results.

[0084] The Markov chain model is used to accurately calculate the probability changes of water quality status, and the Bayesian estimation and expectation maximization algorithms are used to optimize the probability matrix. The Monte Carlo simulation is used to verify and accurately predict the water quality changes.

[0085] For example, the Markov chain model is used to analyze the state transition of the water quality adjustment index, and the Bayesian method is used to accurately estimate the elements of the transition probability matrix. These estimates are further adjusted through the expectation maximization algorithm to more accurately reflect the dynamics of actual water quality changes. Monte Carlo simulation is used to generate confidence intervals for these probabilities and provide stability analysis with statistical support.

[0086] Based on the hidden Markov model, trend analysis is performed on the joint estimation results and numerical simulation results to obtain the temperature change trend.

[0087] The hidden state of the water quality adjustment index is analyzed through the hidden Markov model to predict the temperature change trend and provide more in-depth time series analysis and prediction for water quality management.

[0088] For example, the hidden Markov model is applied to take the output of the Markov chain model as input, analyze the underlying state transition trend, and predict future temperature changes, providing a deep understanding of the water body's response to temperature changes and effective management strategies.

[0089] In step S400, the autoregressive moving average model is used to perform time series modeling on the changing trend to obtain the autoregressive coefficient and the moving average coefficient. The autoregressive coefficient is estimated by the least squares method to obtain the estimated result and the estimation error. The moving average coefficient is filtered by the Kalman filter to obtain the filtered result.

[0090] By combining the autoregressive moving average model with the Kalman filtering technology, dynamic modeling and precise filtering of water quality change trends can be achieved, thereby optimizing the accuracy of the prediction results.

[0091] For example, an autoregressive moving average model is used to establish a time series model of water quality changes, the model parameters are estimated by the least squares method, and the Kalman filtering technology is used to perform real-time corrections on these estimated results to obtain filtered results, thereby improving the accuracy and reliability of the model's predictions of future water quality changes.

[0092] Based on the estimation results and filtering results, forecast analysis is performed to obtain temperature forecasts for several time nodes.

[0093] By combining the estimation and filtering results, the temperature change trend at future time nodes can be predicted, providing quantitative prediction data for water quality management.

[0094] For example, by combining the results of the autoregressive moving average model and the Kalman filter, temperature trends in the coming months can be predicted, providing a scientific basis for adjusting water quality management measures to ensure that water quality remains optimal under changing temperature conditions.

[0095] The temperature predictions of all time nodes are mapped using the isometric mapping algorithm to obtain a multi-state sequence. The optimal path of the multi-state sequence is estimated using the Viterbi algorithm to obtain the path estimation result.

[0096] Through the isometric mapping algorithm and Viterbi algorithm, the state sequence mapping and optimal path analysis of the temperature prediction results are realized, providing the optimal action path based on time series for water quality management decisions.

[0097] For example, the isometric mapping algorithm is used to convert the temperature prediction results into a state sequence, each state represents a temperature classification at a point in time. Then, the Viterbi algorithm is applied to estimate the optimal transition path between these states, thereby providing a basis for the formulation of water temperature adjustment strategies and optimizing long-term water quality management.

[0098] The path estimation results are probability modeled by Gaussian process regression to obtain the probability distribution and probability confidence interval. The probability distribution is numerically simulated by Monte Carlo simulation to obtain numerical results. The probability confidence interval is corrected by Monte Carlo simulation to obtain the interval correction result.

[0099] Through Gaussian process regression and Monte Carlo simulation techniques, in-depth probability analysis and numerical simulation are carried out to accurately assess the uncertainty and risk of future water quality changes.

[0100] For example, the Gaussian process regression model is used to model the probability characteristics of the optimal path, and then these probability distributions are simulated through the Monte Carlo method to generate accurate probability confidence intervals, which can be used to evaluate the reliability and error range of the model predictions.

[0101] The numerical results and interval correction results were comprehensively analyzed through robust analysis to obtain the long-term water quality change prediction.

[0102] Through the integrated application of numerical simulation and robustness analysis, comprehensive predictions of long-term changes in water quality are provided, which can assist in strategic planning and decision-making for water quality management.

[0103] For example, by combining simulation results with data optimized through robustness analysis, a comprehensive forecast report on long-term changes in water quality is formed. This report not only points out the trend of changes, but also evaluates the risks caused by various environmental factors, providing a scientific reference for future water quality management.

[0104] In step S500, data-driven modeling is performed on the long-term water quality change prediction through numerical simulation of a preset proxy model to obtain proxy model parameters, simulation parameters and predicted environmental variables, Latin hypercube sampling is used to perform multi-parameter sampling on the proxy model parameters to obtain multi-parameter sampling results, and multivariate regression is used to perform regression analysis on the simulation parameters to obtain multivariate regression results.

[0105] Through proxy models and multi-parameter sampling technology, efficient simulation and analysis of complex environmental variables can be achieved, providing a more accurate and scientific prediction model for water quality changes.

[0106] For example, proxy models are used to simulate long-term environmental factors such as temperature and pH value, and model parameters are optimized through Latin hypercube sampling technology to ensure wide coverage and high accuracy of simulation results. Then, multiple regression analysis is used to analyze the specific impact of these parameters on water quality, providing quantitative data support for management decisions.

[0107] Environmental simulation was performed based on multi-parameter sampling results and multiple regression results to obtain the simulated water quality change path and expected environmental impacts.

[0108] By combining multi-parameter sampling and multiple regression analysis, the water quality change path can be accurately simulated, and the response of water quality under different environmental factors can be predicted, providing a basis for the formulation of effective water quality management strategies.

[0109] For example, the results of multivariate regression analysis can be used to predict the changing paths of water quality under different environmental settings, identify key influencing factors, and evaluate their specific impacts on water quality, so as to develop targeted adjustment measures to cope with future environmental changes.

[0110] The simulated water quality change path is optimized by the environmental simulation path optimization method to obtain the optimized path, and the optimized path is predicted and controlled by the predictive control method to obtain the control strategy.

[0111] Through path optimization and predictive control technology, the path of water quality changes can be effectively adjusted and managed to ensure the best effect and continuous stability of water quality management.

[0112] For example, path optimization algorithms are used to adjust the predicted water quality change path, and water quality management measures are adjusted in real time through predictive control methods to respond to future water quality changes shown in simulation results, ensuring that water quality meets the expected management standards under various environmental conditions.

[0113] A temperature regulation plan is formulated according to the control strategy to obtain a temperature regulation plan.

[0114] Through detailed predictive control analysis and optimization paths, specific temperature regulation plans are developed to keep water quality stable at optimal conditions. These plans are designed to mitigate the impact of environmental changes on water quality by precisely controlling water temperature.

[0115] For example, based on the results of the control strategy analysis, specific temperature ranges and adjustment time points are set to ensure that these parameters can minimize the risk of water quality changes. At the same time, other water quality management measures, such as pH adjustment and dissolved oxygen level control, are combined to form a comprehensive water quality management system.

[0116] The expected environmental impacts are simulated and analyzed using numerical simulation methods to obtain expected simulation results and expected environmental variables. The expected simulation results are regressed and analyzed using multiple regression to obtain expected regression results. The expected environmental variables are simulated and analyzed using the Monte Carlo simulation method to obtain variable simulation results.

[0117] Through numerical simulation and multiple regression analysis, the impact of various environmental factors on water quality is comprehensively evaluated, providing a scientific basis for formulating more effective water quality management strategies.

[0118] For example, numerical simulation methods are used to predict water quality responses under different environmental settings, such as changes in dissolved oxygen when the temperature increases or decreases. These simulation results are then analyzed through multiple regression to accurately quantify the influence of different factors and provide quantitative adjustment guidelines for actual operations.

[0119] The expected regression results and variable simulation results are comprehensively optimized through the preset control method to obtain the turbidity optimization plan.

[0120] Combining expected regression analysis and simulation results, data optimization is performed through advanced control algorithms to develop a detailed plan for turbidity adjustment to ensure that water quality remains clear within an acceptable range.

[0121] For example, the results of simulation and regression analysis can be integrated and the turbidity control strategy can be adjusted using an optimization algorithm to ensure that the turbidity of water quality is effectively controlled under predicted environmental conditions to meet safety and regulatory requirements.

[0122] In step S600, a comprehensive benefit analysis of the turbidity optimization scheme is performed using a comprehensive evaluation model combined with a temperature adjustment scheme to obtain optimization evaluation results and synergistic benefit results. The optimization evaluation results are regressed by partial least squares regression to obtain regression coefficients. The regression coefficients and synergistic benefit results are synergistically optimized to obtain a comprehensive water quality management plan.

[0123] Through comprehensive evaluation models and partial least squares regression methods, the effects of various water quality management measures are systematically analyzed and optimized to ensure that various measures work together to achieve the optimal effect of overall water quality management.

[0124] For example, a comprehensive evaluation model is applied to evaluate the benefits of temperature regulation and turbidity control, and the interaction of these strategies is analyzed through partial least squares regression, so as to adjust and optimize the entire water quality management plan to achieve the best water quality and economic benefits.

[0125] The comprehensive water quality management plan is input into the preset water quality assessment system to generate a water quality maintenance report.

[0126] By inputting all management measures and prediction results into an integrated evaluation system, a detailed water quality maintenance report is automatically generated, providing decision makers with comprehensive data support and implementation recommendations.

[0127] For example, the combined effects of temperature regulation, turbidity control and other related water quality adjustment strategies are input into the water quality assessment system. The system will generate a detailed maintenance report based on these data. The report includes key performance indicators, expected effect evaluation and recommended improvement measures to help managers make scientific decisions and adjust strategies.

[0128] In this embodiment, accurate control and management of water quality are achieved through Markov chain, hidden Markov model, autoregressive moving average model, Gaussian process regression, and covariance analysis, combined with real-time monitoring and prediction technology. The comprehensive application of these methods not only improves the accuracy and efficiency of water quality management, but also enhances the adaptability and response speed to future water quality changes. In addition, through the system's data integration and intelligent report generation functions, managers can easily obtain key information and make more informed decisions, thereby effectively protecting and improving the water environment.

[0129] Embodiment 3: like Figure 2 As shown, the present application also provides a water quality detection device 10, including an acquisition module 11, an analysis module 12, an adjustment module 13, a prediction module 14, an optimization module 15 and a generation module 16.

[0130] The acquisition module 11 is mainly used to obtain the temperature and turbidity of a specific water sample, standardize the temperature to obtain the standardized temperature, and perform correlation analysis between the standardized temperature and the turbidity to obtain a preliminary water quality index.

[0131] The analysis module 12 is mainly used to perform a graph analysis on the preliminary water quality indicators to obtain a detailed water quality graph, and use the detailed water quality graph to perform an in-depth analysis on the standardized temperature to obtain a water temperature impact assessment.

[0132] The adjustment module 13 is mainly used to perform multi-dimensional data correlation analysis on the detailed water quality map to obtain the key water quality index, adjust the key water quality index through water temperature impact assessment to obtain the water quality adjustment index, and use the water quality adjustment index to monitor the temperature change trend.

[0133] The prediction module 14 is mainly used to perform time series analysis on the change trend, obtain temperature predictions for several time nodes, perform trend mapping on the temperature predictions for all time nodes, and obtain long-term water quality change predictions.

[0134] The optimization module 15 is mainly used to perform data-driven simulation on the prediction of long-term water quality changes, obtain the simulated water quality change path and expected environmental impact, formulate the temperature adjustment strategy using the simulated water quality change path, obtain the temperature adjustment plan, and optimize the turbidity using the expected environmental impact to obtain the turbidity optimization plan.

[0135] The generation module 16 is mainly used to evaluate the synergistic effect of the turbidity optimization scheme according to the temperature adjustment scheme, obtain a comprehensive water quality management scheme, and generate a water quality maintenance report according to the comprehensive water quality management scheme.

[0136] In this embodiment, by integrating the acquisition module 11, the analysis module 12, the adjustment module 13, the prediction module 14, the optimization module 15 and the generation module 16, a multifunctional water quality detection device 10 is formed, which realizes the whole process water quality management from data acquisition, analysis, adjustment to prediction and optimization. These modules have clear division of labor, cooperate with each other, and jointly complete the accurate monitoring and management of water quality. The acquisition module 11 is responsible for real-time acquisition of water sample temperature and turbidity, and conducts preliminary correlation analysis; the analysis module 12 further evaluates the influence of water temperature through detailed spectral analysis; the adjustment module 13 corrects the key water quality index and monitors the temperature change trend; the prediction module 14 provides the prediction of future temperature changes through time series analysis; the optimization module 15 uses these prediction results to formulate and optimize water quality management strategies; the generation module 16 finally integrates all data to generate a comprehensive water quality management plan and maintenance report, thereby providing comprehensive decision support and management measures. The overall device realizes efficient and accurate water quality management through multi-level and multi-angle data analysis and optimization methods, improves the ability to cope with complex environmental changes, and ensures the long-term stability and safety of water quality.

[0137] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned embodiment 1, and will not be repeated here.

[0138] Embodiment 4: like Figure 3 As shown, the present application also provides an electronic device 20, including a memory 21 and a processor 22, wherein the memory 21 stores a computer program that can be executed on the processor 22, and is characterized in that the water quality detection method in Example 1 is implemented when the processor 22 executes the computer program.

[0139] In this embodiment, the water quality detection method in Example 1 is implemented by running a computer program stored in the memory 21 on the processor 22. This embodiment makes full use of the powerful computing power and storage resources of the electronic device 20, so that complex water quality monitoring, analysis and prediction can be carried out efficiently and accurately. The computer program executed by the processor 22 covers steps such as data acquisition, graph analysis, multidimensional data association, time series prediction, model optimization, etc., and systematically converts raw data into operational management strategies. This implementation method based on the electronic device 20 not only simplifies the deployment and operation in practical applications, but also greatly improves the processing speed and processing capacity, providing a strong guarantee for real-time and efficient water quality monitoring.

[0140] Embodiment 5: The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the processor executes the water quality detection method as in Example 1.

[0141] In this embodiment, the water quality detection method in Example 1 is implemented through a computer program stored on a computer-readable storage medium. This embodiment fully considers the universal portability of computer programs, so that the water quality detection method can be run in various hardware environments. The computer program completes the entire process from temperature and turbidity collection, standardization, complex data association and analysis, trend prediction to optimization decision-making through real-time processing and analysis of water sample data. Utilizing the flexibility of the storage medium, this implementation method can easily update and maintain the program, improve the scalability and service life of the system, and provide a stable, reliable and efficient solution for water quality detection and management.

[0142] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. 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 invention.

Claims

1. A water quality detection method, characterized in that: include: Acquiring the temperature and turbidity of a specific water sample, standardizing the temperature to obtain a standardized temperature, and correlating the standardized temperature with the turbidity to obtain a preliminary water quality index; Performing a graph analysis on the preliminary water quality index to obtain a detailed water quality graph, and using the detailed water quality graph to deeply analyze the standardized temperature to obtain a water temperature impact assessment; Performing multidimensional data correlation analysis on the detailed water quality map to obtain a key water quality index, adjusting the key water quality index through the water temperature impact assessment to obtain a water quality adjustment index, and using the water quality adjustment index to monitor the temperature change trend; Performing a time series analysis on the change trend to obtain temperature predictions for several time nodes, and performing trend mapping on the temperature predictions for all time nodes to obtain a long-term water quality change prediction; Performing data-driven simulation on the long-term water quality change prediction to obtain a simulated water quality change path and expected environmental impact, formulating a temperature adjustment strategy using the simulated water quality change path to obtain a temperature adjustment plan, and optimizing the turbidity using the expected environmental impact to obtain a turbidity optimization plan; The synergistic effect of the turbidity optimization scheme is evaluated according to the temperature adjustment scheme to obtain a comprehensive water quality management scheme, and a water quality maintenance report is generated according to the comprehensive water quality management scheme.

2. The water quality detection method according to claim 1, characterized in that: The steps of obtaining the temperature and turbidity of a specific water sample, standardizing the temperature to obtain a standardized temperature, and correlating the standardized temperature with the turbidity to obtain a preliminary water quality index include: Using a temperature sensor to obtain the temperature of a specific water sample, and performing standardization processing on the temperature through a preset temperature calibration module to obtain a standardized temperature; The turbidity of a specific water sample is obtained based on a light scattering detector, and the standardized temperature and the turbidity are input into a preset data analysis system for correlation analysis. In the data analysis system, a regression analysis method is used to calculate the correlation between the standardized temperature and the turbidity to obtain a preliminary water quality indicator.

3. The water quality detection method according to claim 1, characterized in that: The step of performing a graph analysis on the preliminary water quality index to obtain a detailed water quality graph, and performing an in-depth analysis of the standardized temperature using the detailed water quality graph to obtain a water temperature impact assessment comprises: The preliminary water quality index is reduced in dimension by principal component analysis to obtain a principal component score vector, a water sample concentration vector and a calibration coefficient, the principal component score vector is classified by a spectral clustering algorithm to obtain a classification result and a classification center, and the classification result is analyzed by linear regression to regress and fit the water sample concentration vector to obtain a fitting result; Applying multiple regression analysis to the classification center to perform regression analysis on the calibration coefficient to obtain a calibration result; performing aggregation analysis on the fitting result and the calibration result to obtain a detailed water quality map; Performing regression analysis on the detailed water quality map and the standardized temperature using a multiple linear regression model to obtain statistical errors and goodness of fit, correcting the statistical errors through error correction to obtain corrected errors, and evaluating the goodness of fit through residual analysis to obtain analysis results; The correction error and the analysis result are comprehensively analyzed using a Bayesian analysis method to obtain a water temperature impact assessment.

4. The water quality detection method according to claim 1, characterized in that: The steps of performing multidimensional data correlation analysis on the detailed water quality map to obtain a key water quality index, adjusting the key water quality index through the water temperature impact assessment to obtain a water quality adjustment index, and using the water quality adjustment index to monitor the temperature change trend include: Using empirical mode decomposition to perform signal decomposition on the detailed water quality map to obtain signal components, trend components and noise components, and using a differential method to smooth the signal components to obtain smoothing results and residual results; Analyzing the smoothed result by wavelet transform to perform denoising on the trend component to obtain a denoising result; Performing spectrum analysis on the residual result and the noise component by Fourier transform analysis to obtain a spectrum result; Performing frequency domain analysis on the denoising result and the spectrum result by fast Fourier transform to obtain a key water quality index; Performing correlation analysis on the water temperature impact assessment and the key water quality index by linear regression to obtain statistical parameters and correction coefficients, performing error assessment on the statistical parameters by residual analysis to obtain error assessment results, and correcting the correction coefficients by generalized maximum expectation estimation method to obtain correction results; Comprehensively analyzing the error assessment result and the correction result by covariance analysis to obtain a water quality adjustment index; Applying a preset Markov chain model to perform state transition analysis on the water quality adjustment index to obtain a state probability matrix, a transition probability and a steady-state probability, estimating the state probability matrix through Bayesian estimation to obtain an estimation matrix and a matrix confidence interval, jointly estimating the estimation matrix and the transition probability using an expectation maximization algorithm to obtain a joint estimation result, numerically simulating the matrix confidence interval and the steady-state probability through Monte Carlo simulation to obtain a numerical simulation result; The trend analysis of the joint estimation result and the numerical simulation result is performed based on a hidden Markov model to obtain the temperature variation trend.

5. The water quality detection method according to claim 1, characterized in that: The steps of performing time series analysis on the change trend to obtain temperature predictions at several time nodes, and performing trend mapping on the temperature predictions at all time nodes to obtain long-term water quality change predictions include: Using an autoregressive moving average model to perform time series modeling on the change trend, obtaining an autoregressive coefficient and a moving average coefficient, estimating the autoregressive coefficient by a least square method to obtain an estimated result and an estimation error, and using a Kalman filter to filter the moving average coefficient to obtain a filtering result; Performing forecast analysis based on the estimation result and the filtering result to obtain temperature forecasts for several time nodes; Mapping the temperature predictions of all time nodes by using an equidistant mapping algorithm to obtain a multi-state sequence, and performing optimal path estimation on the multi-state sequence by using a Viterbi algorithm to obtain a path estimation result; Probabilistic modeling of the path estimation result is performed through Gaussian process regression to obtain a probability distribution and a probability confidence interval, numerical simulation of the probability distribution is performed through Monte Carlo simulation to obtain a numerical result, and correction of the probability confidence interval is performed through Monte Carlo simulation to obtain an interval correction result; The numerical results and the interval correction results are comprehensively analyzed through robustness analysis to obtain a long-term water quality change prediction.

6. The water quality detection method according to claim 1, characterized in that: The steps of performing data-driven simulation on the long-term water quality change prediction to obtain a simulated water quality change path and an expected environmental impact, formulating a temperature adjustment strategy using the simulated water quality change path to obtain a temperature adjustment plan, and optimizing the turbidity using the expected environmental impact to obtain a turbidity optimization plan include: The long-term water quality change prediction is data-driven modeled by numerical simulation of a preset proxy model to obtain proxy model parameters, simulation parameters and predicted environmental variables, multi-parameter sampling is performed on the proxy model parameters using Latin hypercube sampling to obtain multi-parameter sampling results, and regression analysis is performed on the simulation parameters using multivariate regression to obtain multivariate regression results; Perform environmental simulation based on the multi-parameter sampling results and the multiple regression results to obtain simulated water quality change paths and expected environmental impacts; Performing path optimization on the simulated water quality change path by using an environmental simulation path optimization method to obtain an optimized path, and performing predictive control analysis on the optimized path by using a predictive control method to obtain a control strategy; Formulate a temperature adjustment plan according to the control strategy to obtain a temperature adjustment plan; Using a numerical simulation method to simulate and analyze the expected environmental impact, to obtain expected simulation results and expected environmental variables, performing regression analysis on the expected simulation results through multiple regression to obtain expected regression results, and performing simulation analysis on the expected environmental variables through a Monte Carlo simulation method to obtain variable simulation results; The expected regression results and the variable simulation results are comprehensively optimized through a preset control method to obtain a turbidity optimization solution.

7. The water quality detection method according to claim 1, characterized in that: The step of evaluating the synergistic effect of the turbidity optimization scheme according to the temperature adjustment scheme to obtain a comprehensive water quality management scheme, and generating a water quality maintenance report according to the comprehensive water quality management scheme includes: A comprehensive benefit analysis is performed on the turbidity optimization scheme by using a comprehensive evaluation model in combination with the temperature adjustment scheme to obtain an optimization evaluation result and a synergistic benefit result, a regression analysis is performed on the optimization evaluation result by partial least squares regression to obtain a regression coefficient, and a synergistic optimization analysis is performed on the regression coefficient and the synergistic benefit result to obtain a comprehensive water quality management scheme; The comprehensive water quality management plan is input into a preset water quality assessment system to generate a water quality maintenance report.

8. A water quality detection device, characterized in that: include: An acquisition module is used to acquire the temperature and turbidity of a specific water sample, standardize the temperature to obtain a standardized temperature, and perform correlation analysis between the standardized temperature and the turbidity to obtain a preliminary water quality index; An analysis module, used to perform a graph analysis on the preliminary water quality index to obtain a detailed water quality graph, and use the detailed water quality graph to perform an in-depth analysis on the standardized temperature to obtain a water temperature impact assessment; An adjustment module, for performing multi-dimensional data correlation analysis on the detailed water quality map to obtain a key water quality index, adjusting the key water quality index through the water temperature impact assessment to obtain a water quality adjustment index, and using the water quality adjustment index to monitor the temperature change trend; A prediction module is used to perform a time series analysis on the change trend to obtain temperature predictions for a number of time nodes, and to perform trend mapping on the temperature predictions for all time nodes to obtain a long-term water quality change prediction; An optimization module is used to perform data-driven simulation on the long-term water quality change prediction to obtain a simulated water quality change path and an expected environmental impact, formulate a temperature adjustment strategy using the simulated water quality change path to obtain a temperature adjustment plan, and optimize the turbidity using the expected environmental impact to obtain a turbidity optimization plan; A generation module is used to evaluate the synergistic effect of the turbidity optimization scheme according to the temperature adjustment scheme to obtain a comprehensive water quality management scheme, and generate a water quality maintenance report according to the comprehensive water quality management scheme.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, the water quality detection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the processor is enabled to execute the water quality detection method as claimed in any one of claims 1 to 7.

Images