Whole-cycle collaborative optimization method, system, equipment and medium for water treatment process chain and energy system

Abstract

The invention relates to a full-period collaborative optimization method, system and device for a water treatment process chain and an energy system and a medium, and the method comprises the steps: obtaining and processing multi-dimensional data, and obtaining a data set; constructing a photovoltaic panel two-degree-of-freedom adjustment model, and introducing generated power feedback; calculating an electric quantity self-sufficiency rate based on the data set, when the self-sufficiency rate is lower than a critical threshold value, executing elastic adjustment of discharge depth constraint of an energy storage unit and priority dynamic distribution of power of non-critical process equipment, and monitoring and triggering a compensation strategy of working point correction and load redistribution of a photovoltaic panel in real time to form dynamic balance of power distribution; by constructing a water quality and energy consumption prediction model, a parameter optimization instruction of process equipment is generated, and a power distribution state is associated synchronously, so that multi-dimensional collaborative convergence is formed. By integrating multi-dimensional data acquisition, photovoltaic power generation dynamic adjustment, electric power elastic distribution and process parameter closed-loop optimization, the energy self-consistency and operation efficiency of the water treatment system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment and energy optimization, and particularly to a full-cycle collaborative optimization method, system, device and medium for a water treatment process chain and an energy system. Background Art

[0002] With the growth of the global demand for clean energy and the improvement of environmental protection requirements, the application scope of distributed photovoltaic power generation technology has gradually expanded. At the same time, as a key field involving people's livelihood and environmental protection, the energy consumption and operation efficiency of the water treatment industry have become the focus of attention. Currently, traditional water treatment plants have significant limitations in aspects such as energy supply, data processing, and equipment control, restricting the overall efficiency of the system.

[0003] In terms of energy utilization, traditional water treatment plants mainly rely on external power grids for power supply, and the integrated utilization of clean energy such as solar energy is relatively low. Due to the lack of a collaborative operation mechanism with renewable energy, water treatment devices usually operate with fixed process parameters, making it difficult to match the volatility of photovoltaic power generation with the real-time demand of the water treatment load. In addition, existing data acquisition systems mostly adopt independently deployed sensors and data transmission devices in a decentralized manner. Due to the lack of unified planning among various units, complex wiring architectures are required, which not only increases the construction and maintenance costs but also limits the real-time performance and reliability of data interaction. At the equipment control level, existing technologies mostly rely on manual experience or preset timing control strategies. Since they cannot dynamically respond to changes in real-time working conditions such as water quality parameters and light intensity, the energy utilization rate is reduced, and it is difficult to ensure the stability of the effluent water quality.

[0004] Furthermore, due to the deficiencies in energy scheduling, data integration, and intelligent regulation of traditional water treatment plants, the system operation cost and environmental pressure continue to increase. The decentralized data acquisition method and inefficient control means in the existing technologies result in a high equipment failure rate and significantly increased maintenance difficulty, ultimately affecting the economy and reliability of the water treatment process. Therefore, there is an urgent need for a technical solution that can improve energy utilization efficiency, optimize equipment operation, and enhance the overall performance of the system. Summary of the Invention

[0005] (1) Technical Problems to be Solved

[0006] In view of the above-mentioned shortcomings and deficiencies of the existing technology, the present invention provides a full-cycle collaborative optimization method, system, device and medium for a water treatment process chain and an energy system, which solves the technical problems that traditional water treatment plants rely on external power grids for energy supply, have low integrated utilization of clean energy, and have deficiencies in energy scheduling, data integration, intelligent regulation, and high operation costs.

[0007] (2) Technical Solutions

[0008] To achieve the above object, the main technical solutions adopted by the present invention include:

[0009] In a first aspect, an embodiment of the present invention provides a full-cycle collaborative optimization method for a water treatment process chain and an energy system, including:

[0010] Obtain and process multi-dimensional data including process equipment condition parameters, water quality treatment data, photovoltaic power generation efficiency, and energy storage unit status to obtain a data set;

[0011] According to the obtained astronomical time sequence parameters and local meteorological disturbance factors, construct a two-degree-of-freedom adjustment model for photovoltaic panels, and introduce power generation power feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panels with different environmental conditions;

[0012] Calculate the electricity self-sufficiency rate based on the data set. When the self-sufficiency rate is lower than the critical threshold, perform elastic adjustment of the discharge depth constraint of the energy storage unit and dynamic priority allocation of the power of non-critical process equipment, and trigger a compensation strategy for correcting the working point of the photovoltaic panel and redistributing the load based on real-time monitoring of the power deviation to form a dynamic balance of power distribution;

[0013] By constructing a water quality and energy consumption prediction model, generate parameter optimization instructions for process equipment driven by closed-loop feedback, synchronously associate the power distribution status, and form a collaborative convergence of water quality treatment efficiency, energy consumption indicators, and power distribution schemes by adjusting the optimization step size of the parameter optimization instructions and reconstructing the power distribution scheme.

[0014] Optionally, obtaining and processing multi-dimensional data including process equipment condition parameters, water quality treatment data, photovoltaic power generation efficiency, and energy storage unit status to obtain a data set includes:

[0015] Through a unified data acquisition network based on the Internet of Things, use wireless ad hoc network or industrial Ethernet communication protocol to synchronously collect process equipment condition parameters, water quality treatment data, power generation efficiency data of distributed photovoltaic power generation equipment, and energy storage unit status data;

[0016] Successively perform noise filtering, missing value filling, and outlier correction on all the collected data, and perform data spatio-temporal alignment based on time stamps and device identifiers to generate an intermediate data set associated with time series;

[0017] Unify the formats of heterogeneous data in the intermediate data set through data fusion, and construct a standardized data set with device ID, time stamp, and data category as the combined primary key, and store it in the database.

[0018] Optionally, according to the obtained astronomical time sequence parameters and local meteorological disturbance factors, construct a two-degree-of-freedom adjustment model for photovoltaic panels, and introduce power generation power feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panels with different environmental conditions includes:

[0019] Obtain astronomical time series parameters including solar declination angle, local latitude and solar hour angle, and synchronously obtain local meteorological disturbance factors including irradiance data of the irradiance sensor on the surface of the photovoltaic panel, cloud cover rate and light intensity parameters;

[0020] In the pre-constructed two-degree-of-freedom adjustment model of the photovoltaic panel, calculate the theoretical azimuth angle according to the solar hour angle, and superimpose the meteorological disturbance correction term to generate the real-time azimuth angle, and calculate the initial tilt angle according to the solar declination angle, local latitude and solar hour angle, and introduce the surface irradiance distribution entropy value determined by the data ratio of the irradiance sensor for compensation to obtain the real-time tilt angle;

[0021] Send real-time azimuth angle and real-time tilt angle adjustment commands to the bracket drive device, and monitor the power generation power improvement rate after adjustment in real time. When the power generation power improvement rate is lower than the preset threshold, trigger the following adaptive parameter adjustment mechanism:

[0022] According to the linear relationship between the PWM duty cycle and the adjustment speed of the bracket drive device, dynamically adjust the duty cycle to change the adjustment speed, where the duty cycle adjustment amount is determined by gradient descent;

[0023] Decay the angle increment exponentially according to the set adjustment step and adjustment times to gradually approach the optimal tilt angle and azimuth angle in multiple adjustments;

[0024] Encode the adjusted adjustment speed, azimuth angle and tilt angle into adjustment commands to obtain a multi-dimensional adjustment command set;

[0025] Conduct feasibility verification on the command set through preset mechanical motion constraint conditions. If it exceeds the mechanical limit, scale the adjustment speed and angle increment proportionally, send them to the bracket drive device to perform two-degree-of-freedom pose adjustment, and accept real-time feedback of the actual angle and power generation power;

[0026] Among them, the two-degree-of-freedom adjustment model of the photovoltaic panel is:

[0027]

[0028] In the formula, α is the real-time azimuth angle, ω is the theoretical azimuth angle determined by the solar hour angle, Δα corr is the meteorological disturbance correction term generated by the weighted function of the cloud cover rate and the change of light intensity, β is the real-time tilt angle, δ is the solar declination, is the local latitude, λ is the surface irradiance distribution entropy value is the weight coefficient of, χ i is the data ratio of the i-th irradiance sensor.

[0029] Optionally, calculate the electricity self-sufficiency rate based on the dataset. When the self-sufficiency rate is lower than the critical threshold, perform elastic adjustment of the discharge depth constraint of the energy storage unit and dynamic priority allocation of the power of non-critical process equipment, and trigger a compensation strategy for photovoltaic panel operating point correction and load redistribution based on real-time monitoring of power deviation, forming a dynamic balance of power distribution, including:

[0030] Calculate the electricity self-sufficiency rate through the photovoltaic power generation efficiency data obtained based on the dataset and the total power of all process equipment. When it is detected that the electricity self-sufficiency rate is lower than the preset critical threshold, trigger the power supply and demand imbalance regulation process;

[0031] Calculate the actual discharge depth according to the dynamic relationship between the current remaining power and the rated capacity of the energy storage unit. If the actual discharge depth exceeds the set maximum discharge depth constraint threshold, dynamically compress the discharge power according to the preset safety margin ratio, and generate an energy storage unit discharge power adjustment instruction;

[0032] Dynamically reduce or delay the power demand of the corresponding non-critical equipment according to the preset non-critical equipment priority coefficient, and preferentially maintain the power supply continuity of critical process equipment, generating an equipment power adjustment instruction;

[0033] Real-time monitor the deviation value between the actual power and the expected power of each process equipment in use. If the deviation value exceeds the allowable threshold, synchronously perform the following operations;

[0034] Based on the photovoltaic panel characteristic curve and the photovoltaic power generation efficiency data, analyze the equivalent series resistance value and parallel resistance value corresponding to the maximum power point, and drive the photovoltaic panel operating point to shift towards the maximum power output area by dynamically adjusting the resistance value;

[0035] According to the non-critical equipment priority coefficient and the real-time power gap ratio, redistribute the remaining load capacity, generating a load redistribution compensation instruction;

[0036] Continuously monitor the adjusted electricity self-sufficiency rate, discharge depth and power deviation parameters. If any parameter fails to return to the equilibrium range, iteratively optimize and adjust the energy storage discharge power threshold, non-critical equipment priority weight coefficient and photovoltaic operating point correction step through an adaptive learning model, forming a closed-loop feedback dynamic balance mechanism for power distribution.

[0037] Optionally, by constructing a water quality and energy consumption prediction model, generate parameter optimization instructions for process equipment driven by closed-loop feedback, synchronously associate the power distribution status, and form a coordinated convergence of water quality treatment efficiency, energy consumption indicators and power distribution scheme by adjusting the optimization step of the parameter optimization instructions and reconstructing the power distribution scheme, including:

[0038] Based on the correlation between historical water quality parameters and sewage treatment volume, a water quality treatment volume prediction model is constructed through a multiple linear regression algorithm. Combining the dynamic relationship between the energy consumption data of process equipment and the sewage treatment volume, an energy consumption demand prediction model is established to generate an optimized instruction set for process parameters;

[0039] Associate the optimized instruction set for process parameters with the current power distribution status to mark the feasible execution interval of the optimized instruction set for process parameters;

[0040] According to the feasible execution interval of the parameter optimization instruction, based on the non-critical equipment priority coefficient and the energy storage discharge depth constraint, construct a power distribution weight matrix to make the power distribution plan match the energy demand of the process parameter optimization instruction in real time;

[0041] During the optimization period, real-time monitor the deviation of water quality treatment efficiency, the unit energy consumption index, and the power supply and demand deviation. If any index exceeds the preset threshold, trigger the following iterative optimization until the deviation of water quality treatment efficiency, the unit energy consumption index, and the power supply and demand deviation all converge to the preset optimization interval:

[0042] Update the regression coefficient of the water quality prediction model and the proportional coefficient of the energy consumption prediction model;

[0043] Taking the treatment effect deviation amount as a regulation factor, combining with the historical optimization step size, adaptively adjust the optimization step size through linear superposition, and at the same time, according to the corrected optimization step size, proportionally adjust the optimized instruction set for process parameters;

[0044] And regenerate the optimized instruction set for process parameters.

[0045] Optionally, it further includes:

[0046] Continuously obtain the working condition parameters of process equipment and historical maintenance records, and construct a multi-dimensional feature vector including vibration frequency, energy consumption efficiency, and temperature change rate;

[0047] Input the multi-dimensional feature vector into a pre-trained neural network model, output the real-time health index of the equipment, and predict the remaining service life based on time series analysis;

[0048] When it is detected that the equipment operation parameters deviate from the preset operation threshold range, or the predicted remaining service life is lower than the preset life critical value, send a warning message including the equipment ID, abnormal type, warning level, and recommended maintenance measures to the management personnel;

[0049] According to the warning level, equipment operation load, and available maintenance resource information, dynamically generate a maintenance priority queue, and automatically allocate the maintenance time window and resource scheduling plan.

[0050] In a second aspect, an embodiment of the present invention provides a full-cycle collaborative optimization system for a water treatment process chain and an energy system, including:

[0051] A data acquisition and processing module, configured to acquire and process multi-dimensional data including process equipment operating conditions, water treatment data, photovoltaic power generation efficiency, and energy storage unit status, and obtain a data set;

[0052] A photovoltaic panel adjustment module, configured to construct a two-degree-of-freedom adjustment model of the photovoltaic panel according to the acquired astronomical time sequence parameters and local meteorological disturbance factors, and introduce power generation power feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panel and different environmental conditions;

[0053] A power distribution module, configured to calculate the power self-sufficiency rate based on the data set. When the self-sufficiency rate is lower than the critical threshold, perform elastic adjustment of the discharge depth constraint of the energy storage unit and dynamic priority allocation of the power of non-critical process equipment, and trigger a compensation strategy for correcting the operating point of the photovoltaic panel and re-distributing the load based on the real-time monitoring of the power deviation, to form a dynamic balance of power distribution;

[0054] A collaborative optimization module, configured to generate parameter optimization instructions for process equipment driven by closed-loop feedback by constructing a water quality and energy consumption prediction model, synchronously associate the power distribution status, and form a collaborative convergence of water treatment efficiency, energy consumption index, and power distribution scheme by adjusting the optimization step size of the parameter optimization instructions and reconstructing the power distribution scheme.

[0055] Thirdly, an embodiment of the present invention provides a full-cycle collaborative optimization device for a water treatment process chain and an energy system, including:

[0056] A multi-dimensional data perception network, including a sensor group deployed on process equipment, a power generation monitoring unit deployed on distributed photovoltaic power generation equipment, and a status monitoring unit deployed on an energy storage unit, for real-time collecting process condition parameters, water quality indicators, photovoltaic power generation efficiency, and energy storage unit status data;

[0057] A control center, communicatively connected to the multi-dimensional data perception network, for executing the full-cycle collaborative optimization method of the water treatment process chain and the energy system as described above;

[0058] And a cloud platform, bidirectionally connected to the control center, process equipment, and distributed photovoltaic power generation equipment, for storing and analyzing historical operation data, and sending optimization suggestions to the control center;

[0059] Wherein, the multi-dimensional data perception network, the control center, and the cloud platform constitute a cloud-edge collaborative architecture to achieve full-cycle collaborative processing of data acquisition, real-time control, and parameter optimization.

[0060] Optionally, the process equipment includes a sewage pretreatment tank, a biochemical treatment area, and an effluent detection area, and the biochemical treatment area includes an anoxic tank, an aerobic tank, and a clarification tank; the distributed photovoltaic power generation equipment includes a photovoltaic panel and a battery pack electrically connected to the photovoltaic panel.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium, on which computer-executable instructions are stored. When the executable instructions are executed by a processor, the above-mentioned full-cycle collaborative optimization method based on the water treatment process chain and the energy system is implemented.

[0062] (III) Advantageous Effects

[0063] The beneficial effects of the present invention are as follows:

[0064] First of all, by constructing a two-degree-of-freedom adjustment model for photovoltaic panels, the present invention integrates astronomical time series parameters (solar declination, hour angle) and local meteorological disturbance factors (cloud cover, irradiance entropy value), and introduces a feedback mechanism for the power generation increase rate to adaptively adjust the adjustment speed and angle increment, realizing the dynamic optimization of the spatial attitude of photovoltaic panels, greatly improving the power generation efficiency under different environmental conditions, and effectively alleviating the excessive dependence of traditional water treatment plants on the power grid.

[0065] At the same time, the electricity self-sufficiency rate is calculated in real time based on the collected multi-dimensional data set. When the self-sufficiency rate is lower than the critical threshold, by restricting the discharge depth of the energy storage unit and dynamically allocating the power priority of non-critical equipment, combined with the compensation strategy of photovoltaic operating point correction and load redistribution, a dynamic balance of power supply and demand is formed. Compared with the traditional passive mode relying on the external power grid, this method effectively solves the contradiction between the intermittency of photovoltaic power generation and the volatility of process load, improves the utilization rate of clean energy while ensuring the stable power supply of key equipment, and significantly reduces the dependence on the external power grid and carbon emissions.

[0066] Furthermore, big data analysis is carried out on water quality data and treatment volume, a water quality-energy consumption prediction model is constructed, and parameter optimization instructions driven by closed-loop feedback are generated. By synchronously associating the power distribution state, optimizing step size control and power scheme reconstruction, the collaborative convergence of water quality treatment efficiency, energy consumption index and power distribution is realized.

[0067] Therefore, the present invention breaks through the bottlenecks of traditional water treatment plants such as single energy supply, data islanding and lagging regulation. Through the full-cycle collaboration of "energy-process-data", a trinity solution of efficient utilization of clean energy, precise regulation of water quality treatment and optimization of system operation cost is constructed, providing technical support for the low-carbon and intelligent transformation of the water treatment industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a schematic flowchart of the method provided by the embodiment of the present invention;

[0069] Figure 2 is a specific flowchart of step S1 of the method provided by the embodiment of the present invention;

[0070] Figure 3Schematic diagram of the specific process of step S2 of the method provided by the embodiment of the present invention;

[0071] Figure 4 Schematic diagram of the specific process of step S3 of the method provided by the embodiment of the present invention;

[0072] Figure 5 Schematic diagram of the specific process of step S4 of the method provided by the embodiment of the present invention;

[0073] Figure 6 Correlation diagram between multiple steps of the method provided by the embodiment of the present invention. Detailed implementation manners

[0074] In order to better explain the present invention for easy understanding, the present invention will be described in detail below in conjunction with the accompanying drawings through specific implementation manners.

[0075] As Figure 1 shown, the embodiment of the present invention proposes to obtain and process multi-dimensional data including process equipment condition parameters, water quality treatment data, photovoltaic power generation efficiency, and energy storage unit status to obtain a data set; construct a two-degree-of-freedom adjustment model for photovoltaic panels according to the obtained astronomical time series parameters and local meteorological disturbance factors, and introduce power generation power feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panels with different environmental conditions; calculate the electricity self-sufficiency rate based on the data set. When the self-sufficiency rate is lower than the critical threshold, perform elastic adjustment of the discharge depth constraint of the energy storage unit and dynamic allocation of the priority of non-critical process equipment power, and trigger a compensation strategy for correcting the working point of the photovoltaic panel and redistributing the load based on real-time monitoring of power deviation to form a dynamic balance of power distribution; generate parameter optimization instructions for process equipment driven by closed-loop feedback by constructing a water quality and energy consumption prediction model, synchronously associate the power distribution status, and form a collaborative convergence of water quality treatment efficiency, energy consumption index, and power distribution scheme by adjusting the optimization step size of the parameter optimization instructions and reconstructing the power distribution scheme.

[0076] First, the present invention constructs a two-degree-of-freedom adjustment model for photovoltaic panels, fuses astronomical time series parameters (solar declination, hour angle) with local meteorological disturbance factors (cloud cover, irradiance entropy value), and introduces a power generation power increase rate feedback mechanism to adaptively adjust the adjustment speed and angle increment, realizing dynamic optimization of the spatial attitude of the photovoltaic panels, greatly improving the power generation efficiency under different environmental conditions, and effectively alleviating the excessive dependence of traditional water plants on the power grid.

[0077] Meanwhile, the electricity self - supply rate is calculated in real - time based on the collected multi - dimensional data set. When the self - supply rate is lower than the critical threshold, by restricting the discharge depth of the energy storage unit and dynamically allocating the power priorities of non - critical devices, combined with the compensation strategy of photovoltaic operating point correction and load redistribution, a dynamic balance of power supply and demand is formed. Compared with the traditional passive mode that relies on the external power grid, this method effectively solves the contradiction between the intermittency of photovoltaic power generation and the volatility of process loads. While ensuring the stable power supply of critical devices, it improves the utilization rate of clean energy, significantly reduces the dependence on the external power grid and carbon emissions.

[0078] Furthermore, big data analysis is carried out on water quality data and treatment volume, a water quality - energy consumption prediction model is constructed, and parameter optimization instructions driven by closed - loop feedback are generated. By synchronously correlating the power distribution status, with optimized step - size control and power scheme reconstruction, the collaborative convergence of water treatment efficiency, energy consumption indicators, and power distribution is achieved.

[0079] Thus, the present invention breaks through the bottlenecks of traditional water plants such as single energy supply, data islanding, and lagging regulation. Through the full - cycle coordination of "energy - process - data", a trinity solution of efficient utilization of clean energy, precise regulation of water treatment, and optimization of system operation cost is constructed, providing technical support for the low - carbon and intelligent transformation of the water treatment industry.

[0080] To better understand the above - mentioned technical solution, the exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and the scope of the present invention can be completely conveyed to those skilled in the art.

[0081] Specifically, the present invention provides a full - cycle collaborative optimization method for a water treatment process chain and an energy system, including:

[0082] S1. Obtain and process multi - dimensional data including process equipment condition parameters, water quality treatment data, photovoltaic power generation efficiency, and energy storage unit status to obtain a data set.

[0083] Further, as Figure 2 shown, step S1 includes:

[0084] S11. Through a unified data acquisition network based on the Internet of Things, using wireless ad - hoc network or industrial Ethernet communication protocols, synchronously collect the condition parameters of process equipment, water quality treatment data, power generation efficiency data of distributed photovoltaic power generation equipment, and energy storage unit status data.

[0085] Abandoning the traditional complex and decentralized data acquisition method, the present invention constructs a unified data acquisition network based on Internet of Things technology. Each processing device and detection device in the water plant process equipment transmits data such as the operating status of the equipment, energy consumption, treated water volume, water quality indicators, etc., as well as the power generation data of the photovoltaic power generation panels and the status data of the storage batteries in the distributed photovoltaic power generation equipment to the control center quickly and accurately through low-power and high-reliability sensors via wireless ad hoc network technology or industrial Ethernet. This unified data acquisition network not only improves the data transmission efficiency, but also reduces the system wiring cost and maintenance difficulty.

[0086] S12. Perform noise filtering, missing value filling, and outlier correction on all the collected data in sequence, and perform data spatio-temporal alignment based on the time stamp and device identifier to generate an intermediate data set associated with time series.

[0087] S13. Unify the formats of the heterogeneous data in the intermediate data set through data fusion, including standardizing the unit of water quality parameters to a preset reference unit, normalizing the device energy consumption data to per-unit value, and constructing a standardized data set with the device ID, time stamp, and data category as the combined primary key, and storing it in the database.

[0088] After the data is transmitted to the control center, intelligent preprocessing of the data is first performed. The data cleaning algorithm is used to remove noise data, and different data from different sources and in different formats are integrated through data fusion technology to provide a high-quality data basis for subsequent analysis and decision-making. Specifically: perform sliding window mean filtering on the collected original data stream, and the window size is dynamically adjusted according to the sensor sampling frequency to filter out high-frequency noise; for the missing values caused by data acquisition interruption, use the time series linear interpolation method to fill them. If the continuous missing exceeds the preset time threshold, an alarm for abnormal device status is triggered; based on the 3σ principle of the device historical operation data, set a dynamic threshold to correct the outliers outside the threshold range, and align the data collected by different devices according to the time axis and device topology relationship with the device unique identifier (Device ID) as the spatial index and the time stamp (accurate to milliseconds) as the time series index to generate an intermediate data set with spatio-temporal tags. Finally, fuse and standardize the heterogeneous data, construct a standardized data table with the triple (device ID, time stamp, data category) as the combined primary key, store the standardized data set in the time series database by time partitioning, and establish a combined index of the device ID and data category to facilitate more comprehensive analysis and retrieval of relevant information and system operating conditions.

[0089] S2. Construct a two-degree-of-freedom adjustment model for the photovoltaic panel according to the obtained astronomical time series parameters and local meteorological disturbance factors, and introduce power generation power feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panel with different environmental conditions.

[0090] Further, as Figure 3 shown, step S2 includes:

[0091] S21. Obtain astronomical time series parameters including solar declination angle, local latitude and solar hour angle, and simultaneously obtain local meteorological disturbance factors including irradiance data of the irradiance sensor on the surface of the photovoltaic panel, cloud cover rate and light intensity parameters.

[0092] S22. In the pre-constructed two-degree-of-freedom adjustment model of the photovoltaic panel, calculate the theoretical azimuth angle according to the solar hour angle, and superimpose the meteorological disturbance correction term to generate the real-time azimuth angle, and calculate the initial tilt angle according to the solar declination angle, local latitude and solar hour angle, and introduce the surface irradiance distribution entropy value determined by the data ratio of the irradiance sensor for compensation to obtain the real-time tilt angle.

[0093] Among them, the two-degree-of-freedom adjustment model of the photovoltaic panel is:

[0094]

[0095] In the formula, α is the real-time azimuth angle, ω is the theoretical azimuth angle calculated from the solar hour angle, Δα corr is the meteorological disturbance correction term generated by the weighted function of the cloud cover rate and the change of light intensity, β is the real-time tilt angle, δ is the solar declination, is the local latitude, λ is the surface irradiance distribution entropy value is the weight coefficient of, χ i is the data ratio of the i-th irradiance sensor.

[0096] S23. Send the real-time azimuth angle and real-time tilt angle adjustment instructions to the bracket driving device, and monitor the power generation power increase rate after adjustment in real time. When the power generation power increase rate is lower than the preset threshold, trigger the following adaptive parameter adjustment mechanism.

[0097] S24. Dynamically adjust the duty cycle to change the adjustment speed according to the linear relationship between the PWM duty cycle and the adjustment speed of the bracket driving device, where the duty cycle adjustment amount is determined by the gradient descent algorithm.

[0098] S25. Decay the angle increment exponentially according to the set adjustment step and adjustment times, so as to gradually approach the optimal tilt angle and azimuth angle in multiple adjustments.

[0099] In a specific embodiment, assume that the power generation power before adjustment is P 0 , and the power generation power after adjustment is P 1 , define the power generation power increase rate η = (p 1 -p 0 ) / p 0, if it is found that the power generation power improvement rate does not reach the expected set value, the control center automatically adjusts the adjustment parameters. For example, by adjusting the duty cycle D of the pulse width modulation (PWM) signal of the bracket drive device to change the adjustment speed (adjustment speed v = kD, where k is the speed coefficient and is related to the performance of the bracket drive device), and adjusting the angle increment Δβ for each adjustment (initially set as Δβ 0 , if the power generation power improvement does not meet the expectation, according to Δβ n+1 =Δβ n ×0.9 rule gradually decreases, n is the number of adjustments) to control the adjustment amplitude to ensure that the adjustment effect is always in the optimal state. This adaptive angle adjustment strategy enables the photovoltaic panels to quickly and accurately adjust to the optimal power generation angle under different weather conditions (such as different light intensities and atmospheric transparencies in sunny days, cloudy days, etc.) and environments (such as the change of the sun's trajectory caused by seasonal changes), effectively improving the power generation efficiency of the photovoltaic power generation system and providing more stable power support for the entire collaborative system.

[0100] S26. Encode the adjusted adjustment speed, azimuth angle, and tilt angle into adjustment instructions to obtain a multi-dimensional adjustment instruction set.

[0101] S27. Perform feasibility verification through a preset mechanical motion constraint condition (such as including the maximum angular velocity and acceleration limit of the bracket) instruction set. If it exceeds the mechanical limit, scale the adjustment speed and angle increment proportionally, send them to the bracket drive device to perform a two-degree-of-freedom pose adjustment, and accept real-time feedback of the actual angle and power generation power.

[0102] S3. Calculate the electricity self-sufficiency rate based on the data set. When the self-sufficiency rate is lower than the critical threshold, perform elastic adjustment of the discharge depth constraint of the energy storage unit and dynamic priority allocation of the power of non-critical process equipment, and trigger a compensation strategy for correcting the working point of the photovoltaic panel and reallocating the load based on the real-time monitoring of the power deviation to form a dynamic balance of power distribution.

[0103] Furthermore, as Figure 4 shown, step S3 includes:

[0104] S31. Calculate the electricity self-sufficiency rate through the photovoltaic power generation efficiency data obtained based on the data set and the total power of all process equipment. When it is detected that the electricity self-sufficiency rate is lower than the preset critical threshold, trigger the power supply and demand imbalance control process.

[0105] In a specific embodiment, the control center first performs an energy consumption analysis on each process equipment. Let the real-time power of the i-th equipment be P i (i = 1, 2, ……, n, n is the total number), then the total real-time power At the same time, obtain the real-time power generation power P of the photovoltaic panel pvand the real-time remaining power Q of the storage battery and the rated capacity Q of the storage battery rated 。

[0106] Define the power self-sufficiency rate When α≥1, it means that the photovoltaic power generation is sufficient. At this time, the power is preferentially supplied to each electrical equipment in the waterworks, and the excess power ΔQ = P pv -P total is stored in the storage battery. The charging efficiency η of the storage battery needs to be considered during the storage process c , and the actual stored power ΔQ actual =ΔQ×η c 。

[0107] When α<1, the photovoltaic power generation is insufficient, triggering the multi-level regulation process of power supply and demand imbalance, and synchronously activating the discharge constraint adjustment of the energy storage unit, the elastic distribution of the power of non-critical equipment, and the correction logic of the photovoltaic operating point.

[0108] S32. According to the dynamic relationship between the current remaining power and the rated capacity of the energy storage unit, calculate the actual depth of discharge. If the actual depth of discharge exceeds the set maximum depth of discharge constraint threshold, the discharge power is dynamically compressed according to the preset safety margin ratio, and an energy storage unit discharge power adjustment instruction is generated.

[0109] Calculate the actual depth of discharge according to the dynamic ratio of the current remaining power of the storage battery to the rated capacity (Q remaining is the current remaining power of the storage battery), to ensure the life of the storage battery, set the maximum depth of discharge DOD max , when DOD>DOD max , then the discharge power is dynamically compressed according to the safety margin ratio to generate an energy storage unit discharge power adjustment instruction P' c =λ 0 ·P current , P current is the current power of the energy storage unit, and ensure that the instruction value does not exceed the maximum allowable discharge power limit calculated based on the maximum depth of discharge constraint threshold.

[0110] S33. Dynamically reduce or delay the power demand of the corresponding non-critical equipment according to the preset non-critical equipment priority coefficient, and preferentially maintain the power supply continuity of the key process equipment to generate an equipment power adjustment instruction.

[0111] At the same time, the power of non-critical equipment needs to be adjusted according to the priority of each electrical equipment. Let the priority coefficient of non-critical equipment be k j (j = 1, 2,..., m, m is the number of non-critical equipment, 0<k j <1, the lower the priority, the smaller k j is), according to the weight ratio Dynamically allocate power reduction and generate device power adjustment instructions P' j =P j ·(1-τ j ΔP gap ), ΔP gap The difference between the total power demand and the photovoltaic power generation is dynamically reduced to ensure the normal operation of key equipment and prevent the battery from over-discharging.

[0112] S34. Monitor the deviation between the actual power and the expected power of each process equipment in real time. If the deviation exceeds the allowable threshold, perform the following operations simultaneously: Analyze the equivalent series resistance and parallel resistance corresponding to the maximum power point based on the photovoltaic panel characteristic curve and photovoltaic power generation efficiency data, and drive the photovoltaic panel working point to shift toward the maximum power output area by dynamically adjusting the resistance value; and, reallocate the remaining load capacity according to the non-critical equipment priority coefficient and the real-time power gap ratio, and generate a load redistribution compensation instruction.

[0113] During the power distribution process, the control center monitors the voltage U of each device in real time. i and current I i Calculate the actual power P i '=U i I i , and the expected power P i For comparison, if the deviation ΔP i =|P i '-P i |>ΔP max (ΔP max is the set maximum power deviation allowable value), the power supply is determined to be fluctuating or abnormal, and the real-time dynamic power dispatch mechanism is immediately activated to quickly adjust the power distribution strategy, such as:

[0114] (1) Dynamic correction of the photovoltaic operating point: Based on the piecewise linearization model of the photovoltaic panel characteristic curve, the equivalent series resistance and parallel resistance corresponding to the maximum power point are analyzed, and the resistance value is dynamically adjusted to drive the operating point to shift to the maximum power output area.

[0115] (2) Load redistribution compensation: Based on the priority coefficient k of non-critical equipment j Ratio to real-time power shortage Generate load redistribution compensation command {ΔP j =ΔP gap γ j} and update the device power allocation queue.

[0116] S35. Continuously monitor the adjusted power self - sufficiency rate, depth of discharge, and power deviation parameters. If any parameter fails to return to the equilibrium range, iteratively optimize and adjust the energy storage discharge power threshold, non - critical equipment priority weight coefficient, and PV operating point correction step through the adaptive learning model to form a closed - loop feedback dynamic equilibrium mechanism for power distribution. At the same time, upload the power distribution and scheduling information to the cloud platform in real - time for managers to conduct remote monitoring and analysis, and promptly discover and solve potential problems. This algorithm can effectively balance the photovoltaic power generation and the water plant's electricity demand, ensure the stable operation of the system, and improve energy utilization efficiency.

[0117] S4. By constructing a water quality and energy consumption prediction model, generate parameter optimization instructions for process equipment driven by closed - loop feedback, synchronously associate the power distribution status, and form a coordinated convergence of water treatment efficiency, energy consumption indicators, and power distribution schemes by adjusting the optimization step of the parameter optimization instructions and reconstructing the power distribution plan.

[0118] Further, as Figure 5 shown, step S4 includes:

[0119] S41. Based on the correlation between historical water quality parameters and sewage treatment volume, construct a sewage treatment volume prediction model through multiple linear regression algorithms, and simultaneously combine the dynamic relationship between process equipment energy consumption data and sewage treatment volume to establish an energy consumption demand prediction model to generate a process parameter optimization instruction set.

[0120] Specifically, use big data analysis and artificial intelligence algorithms to process the collected operation data of the water plant's process equipment and the power generation data of distributed photovoltaic power generation equipment. Assume that the sewage treatment volume under different water quality parameters x k (such as COD value, ammonia nitrogen content, etc., k = 1, 2, …… p, p is the number of water quality parameter types) in historical data is y k , establish a prediction model (where β 0 , β k are regression coefficients) through multiple linear regression algorithms, input the x k value according to the real - time water quality situation to predict the sewage treatment volume y at different times. At the same time, according to the relationship between historical energy consumption data and treatment volume;

[0121] and, establish an energy consumption prediction model E = γ 0 +γ 1 y (γ 0 , γ 1 are coefficients) to predict the energy consumption demand E and provide a basis for power distribution and equipment regulation.

[0122] S42. Associate the process parameter optimization instruction set with the current power distribution status to mark the feasible execution interval of the process parameter optimization instruction set.

[0123] In this step, the process parameter optimization instruction set is dynamically coupled with the current power distribution state. By analyzing the remaining power of the energy storage unit, the real-time power generation of the photovoltaic, and the equipment priority weight, the feasible execution interval of each process optimization instruction is marked, and this interval meets the dynamic balance between power supply capacity and process requirements.

[0124] S43. According to the feasible execution interval of the parameter optimization instruction, based on the non-critical equipment priority coefficient and the energy storage discharge depth constraint, construct a power distribution weight matrix to make the power distribution scheme match the energy demand of the process parameter optimization instruction in real time.

[0125] According to the non-critical equipment priority coefficient matrix k j and the energy storage discharge depth constraint DOD max , construct a dynamic power distribution weight matrix W = [w ij , where the weight factor w ij is dynamically adjusted according to the following rules:

[0126] Assign a fixed high weight to the key process equipment to ensure its power supply priority.

[0127] The weight w ij of the non-critical equipment is j positively correlated with its priority coefficient k and the real-time power gap ratio.

[0128] The weight of the energy storage discharge power is dynamically scaled according to the remaining margin of DOD max to extend the battery life.

[0129] S44. During the optimization period, monitor the water quality treatment efficiency deviation, unit energy consumption index, and power supply and demand deviation in real time. If any index exceeds the preset threshold, trigger the following iterative optimization until the water quality treatment efficiency deviation, unit energy consumption index, and power supply and demand deviation all converge to the preset optimization interval:

[0130] (1) Update the regression coefficient of the water quality prediction model and the proportional coefficient of the energy consumption prediction model.

[0131] (2) Use the treatment effect deviation amount as the regulation factor, combine with the historical optimization step size, and adaptively adjust the optimization step size through linear superposition. At the same time, according to the corrected optimization step size, adjust the process parameter optimization instruction set proportionally; for example, for the adjustment of the aeration volume, correct the aeration volume according to the deviation ΔZ at a certain ratio ρ, that is (take the minus sign when Z actucl > Z traget , and take the plus sign vice versa), and perform regulation again until the best energy conservation, emission reduction, and treatment efficiency goals are achieved.

[0132] (3) Regenerate the process parameter optimization instruction set.

[0133] Moreover, the method provided by the present invention further includes: continuously acquiring the operating condition parameters of the process equipment and historical maintenance records, constructing a multi-dimensional feature vector including vibration frequency, energy consumption efficiency, and temperature change rate; inputting the multi-dimensional feature vector into a pre-trained neural network model to output the real-time health index of the equipment, and predicting the remaining service life based on time series analysis; when it is detected that the equipment operating parameters deviate from the preset operating threshold range, or the predicted remaining service life is lower than the preset life critical value, sending a warning message including the equipment ID, abnormal type, warning level, and recommended maintenance measures to the management personnel; dynamically generating a maintenance priority queue according to the warning level, equipment operating load, and available maintenance resource information, and automatically allocating the maintenance time window and resource scheduling plan.

[0134] It should be clear that referring to Figure 6 , in the above steps, S1 is the basis of the entire collaborative system, and S1 provides key data support for subsequent S2, S3, and S4. By constructing a unified data acquisition network, various operating data of the water plant process equipment and distributed photovoltaic power generation equipment are accurately and quickly transmitted to the control center, and after preprocessing, high-quality data is provided for subsequent analysis and decision-making. For example, in S2, the adjustment of the angle of the photovoltaic panel needs to be based on the collected power generation data, time data (used to calculate the hour angle), and local longitude and latitude data, etc.; in S3, the power distribution and scheduling depend on the operating state data of each electrical equipment, the power generation data of the photovoltaic panel, and the battery state data, etc.; in S4, the equipment regulation and optimization are based on the collected water quality data, treated water volume data, and equipment operating data, and synchronously associated with the power distribution state, etc.

[0135] The execution effect of S2 will affect the power generation power of the photovoltaic panel in S3, and thus affect the power distribution and scheduling strategy. Reasonably adjusting the angle of the photovoltaic panel can improve the power generation efficiency, increase the power generation amount of the photovoltaic power generation, provide more power resources during power distribution, affect the calculation of the power self-sufficiency rate and the power supply decision (such as determining whether to give priority to power supply or draw power from the battery), and at the same time, the power generation power data monitored in real time during the adjustment process of S2 will also be fed back to the data acquisition and transmission link of S1 as data supplement and verification, so that the control center can better master the operating conditions of the photovoltaic power generation equipment.

[0136] S3 and S4 are interrelated. S3 provides stable power supply for S4 to ensure that the power consumption requirements during equipment regulation are met. For example, during the equipment regulation process, if the power supply is unstable, it will cause the equipment to be unable to adjust parameters as expected, affecting the regulation effect. And the information such as the operating state and energy consumption change of the equipment in S4 will be fed back to S3, affecting the adjustment of the power distribution strategy. For example, when the equipment adjusts the aeration volume according to the water quality change, resulting in an increase in energy consumption, S3 needs to monitor this change in real time and adjust the power supply accordingly to ensure the overall stable operation of the system.

[0137] Additionally, an embodiment of the present invention further provides a full-cycle collaborative optimization system for a water treatment process chain and an energy system, including:

[0138] A data acquisition and processing module, configured to acquire and process multi-dimensional data including process equipment condition parameters, water quality treatment data, photovoltaic power generation efficiency, and energy storage unit status to obtain a data set.

[0139] A photovoltaic panel adjustment module, configured to construct a two-degree-of-freedom adjustment model for the photovoltaic panel according to the acquired astronomical time sequence parameters and local meteorological disturbance factors, and introduce power generation power feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panel with different environmental conditions.

[0140] A power distribution module, configured to calculate the electricity self-sufficiency rate based on the data set. When the self-sufficiency rate is lower than the critical threshold, perform elastic adjustment of the discharge depth constraint of the energy storage unit and dynamic priority allocation of the power of non-critical process equipment, and trigger a compensation strategy for correcting the operating point of the photovoltaic panel and reallocating the load based on real-time monitoring of the power deviation to form a dynamic balance of power distribution.

[0141] A collaborative optimization module, configured to generate parameter optimization instructions for process equipment driven by closed-loop feedback by constructing a water quality and energy consumption prediction model, synchronously associate the power distribution state, and form a collaborative convergence of water quality treatment efficiency, energy consumption index, and power distribution scheme by adjusting the optimization step size of the parameter optimization instructions and reconstructing the power distribution scheme.

[0142] Then, an embodiment of the present invention provides a full-cycle collaborative optimization device for a water treatment process chain and an energy system, including:

[0143] A multi-dimensional data perception network, including a sensor group deployed on process equipment, a power generation monitoring unit deployed on distributed photovoltaic power generation equipment, and a status monitoring unit deployed on the energy storage unit, for real-time collecting process condition parameters, water quality indicators, photovoltaic power generation efficiency, and energy storage unit status data.

[0144] A control center, communicatively connected to the multi-dimensional data perception network, for executing the full-cycle collaborative optimization method for the water treatment process chain and the energy system as described above.

[0145] And a cloud platform, which is bidirectionally connected to the control center, process equipment, and distributed photovoltaic power generation equipment, is used to store and analyze historical operation data and send optimization suggestions to the control center.

[0146] Among them, the multi-dimensional data perception network, control center, and cloud platform constitute a cloud-edge collaborative architecture to achieve full-cycle collaborative processing of data collection, real-time control, and parameter optimization.

[0147] It should be understood that the process equipment includes a sewage pretreatment tank, a biochemical treatment area, and an effluent detection area. The biochemical treatment area includes an anoxic tank, an aerobic tank, and a clarifier; the distributed photovoltaic power generation equipment includes photovoltaic panels and a battery pack electrically connected to the photovoltaic panels.

[0148] In a specific embodiment, a distributed photovoltaic power generation and process water treatment collaborative system for a water plant includes the water plant process equipment and distributed photovoltaic power generation equipment. The process equipment includes a sewage pretreatment tank, a biochemical treatment area, and an effluent detection area. The biochemical treatment area consists of an anoxic tank, an aerobic tank, and a clarifier. The distributed photovoltaic power generation equipment includes photovoltaic power generation panels, a battery connected to the photovoltaic power generation panels, and a photovoltaic power generation panel control center. Each treatment device and detection device in the water plant process equipment transmits information to the photovoltaic power generation panel control center and the cloud platform respectively. Among them, the water plant process equipment obtains solar energy in a way that collaborates with the distributed photovoltaic power generation equipment. The distributed photovoltaic power generation and process water treatment collaborative system for a water plant constructed by the present invention adjusts the slope angle of the power generation panel while generating sewage treatment so that it faces the sun directly, thereby increasing the power generation. Moreover, through the distributed photovoltaic power generation system, the electricity consumed in the production process of the water plant can be locally digested, and the electrical equipment can be locally regulated, greatly improving the overall efficiency of the system.

[0149] Furthermore, an embodiment of the present invention provides a computer-readable medium on which computer-executable instructions are stored. When the executable instructions are executed by a processor, the full-cycle collaborative optimization method based on the water treatment process chain and energy system as described above is implemented.

[0150] In summary, an embodiment of the present invention provides a full-cycle collaborative optimization method, system, device, and medium for a water treatment process chain and an energy system. The present invention constructs a deep coupling framework for the water plant process equipment and the distributed photovoltaic power generation system, and through a data interaction protocol and an energy coupling interface, realizes the real-time association of the operation state of the process chain and the photovoltaic power generation efficiency, forming a full-cycle collaborative optimization system of energy supply - process treatment - environmental feedback, which is specifically achieved through the following points:

[0151] (1) Based on low-power sensors and wireless ad-hoc network technology (or industrial Ethernet), real-time collect the operating condition parameters of process equipment (energy consumption, water quality indicators, etc.) and photovoltaic power generation efficiency data (power generation power, energy storage status, etc.) to form a highly reliable and low-latency unified data stream. This network provides multi-dimensional data support for intelligent decision-making, and its transmission efficiency and stability directly affect the collaborative optimization effect.

[0152] (2) According to astronomical timing parameters (solar declination, hour angle) and local meteorological disturbance factors (light intensity, atmospheric transparency), construct a double-degree-of-freedom adjustment model for photovoltaic panels, and dynamically correct the spatial attitude (tilt angle, azimuth angle) of photovoltaic panels through real-time power generation power feedback to achieve adaptive matching with dynamic environmental conditions.

[0153] (3) Dynamically determine the power supply and demand status by calculating the ratio of photovoltaic power generation power to the total power of process equipment in real time (electricity self-sufficiency rate); when the electricity self-sufficiency rate is lower than the critical threshold or it is detected that the power deviation exceeds the limit, simultaneously execute the adjustment of the energy storage discharge depth constraint, the priority power distribution of non-critical equipment, and the correction of the photovoltaic operating point to ensure that each electrical equipment always obtains a stable power supply. This not only avoids equipment failures or production interruptions caused by unstable power, but also improves the energy utilization efficiency of the entire system, enabling reasonable distribution and effective utilization of electric energy; at the same time, upload the power dispatching data to the cloud platform in real time to support remote decision-making analysis and anomaly warning.

[0154] (4) Use big data analysis and artificial intelligence algorithms to adjust the operating parameters of water treatment plant process equipment (such as the aeration volume of aerobic tanks, the start-stop frequency of grille machines, etc.) in real time according to the water quality changes (such as COD value, ammonia nitrogen content, etc.) and the prediction results of sewage treatment volume. This data-driven remote control method can make the equipment operation more accurately adapt to the actual production needs, improve the treatment efficiency, and ensure the stable compliance of water quality. For example, adjust the aeration volume in a timely manner according to real-time water quality data, avoid energy waste on the premise of ensuring the treatment effect, and achieve energy conservation and emission reduction.

[0155] The equipment of the present invention is provided with a closed-loop feedback mechanism in multiple links. Through continuous cyclic feedback and adjustment, it can gradually approach the optimal value, keep the entire water treatment process in the optimal operating state and the power supply and demand balanced, thereby continuously improving the water quality treatment effect, reducing the pollutant content of the effluent, and meeting more stringent environmental protection requirements.

[0156] Since the system / device described in the above embodiments of the present invention is the system / device adopted for implementing the method in the above embodiments of the present invention, based on the method described in the above embodiments of the present invention, those skilled in the art can understand the specific structure and deformation of the system / device, so it will not be elaborated here. Any system / device adopted by the method in the above embodiments of the present invention belongs to the scope protected by the present invention.

[0157] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0158] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems) and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions.

[0159] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a claim listing several means, several of these means can be embodied by the same piece of hardware. The use of the terms first, second, third, etc. is only for convenience of expression and does not denote any order. These terms can be understood as part of the name of the element.

[0160] In addition, it should be noted that in the description of this specification, the description of terms such as "an embodiment", "some embodiments", "embodiments", "examples", "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0161] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications after learning the basic creative concept. Therefore, the claims should be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0162] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention should also cover these modifications and variations.

Claims

1. A full-cycle collaborative optimization method for a water treatment process chain and an energy system, characterized in that: include: Acquire and process multidimensional data including process equipment operating parameters, water quality treatment data, photovoltaic power generation efficiency and energy storage unit status to obtain a data set; Based on the acquired astronomical time series parameters and local meteorological disturbance factors, a dual-degree-of-freedom adjustment model for photovoltaic panels is constructed, and power generation feedback is introduced during the adjustment process to achieve real-time matching of the spatial attitude of photovoltaic panels with different environmental conditions. The power self-sufficiency rate is calculated based on the data set. When the self-sufficiency rate is lower than the critical threshold, the discharge depth constraint of the energy storage unit is adjusted flexibly and the power priority of non-critical process equipment is dynamically allocated. The compensation strategy of photovoltaic panel working point correction and load redistribution is triggered based on real-time monitoring of power deviation to form a dynamic balance of power distribution. By constructing a water quality and energy consumption prediction model, parameter optimization instructions for process equipment driven by closed-loop feedback are generated, and the power distribution status is synchronously associated. By adjusting the optimization step size of the parameter optimization instructions and the power distribution plan reconstruction, the coordinated convergence of water quality treatment efficiency, energy consumption indicators and power distribution plan is achieved.

2. The full-cycle collaborative optimization method of the water treatment process chain and the energy system according to claim 1, characterized in that: Acquire and process multi-dimensional data including process equipment operating parameters, water quality treatment data, photovoltaic power generation efficiency and energy storage unit status, and obtain data sets including: Through a unified data collection network built on the Internet of Things, using wireless ad hoc networks or industrial Ethernet communication protocols, synchronously collect the operating parameters of process equipment, water quality treatment data, and the power generation efficiency data and energy storage unit status data of distributed photovoltaic power generation equipment; All collected data are filtered for noise, filled with missing values, and corrected for outliers. The data is aligned in time and space based on timestamps and device identifiers to generate an intermediate data set associated with the time series. Through data fusion, the format of heterogeneous data in the intermediate data set is unified, and a standardized data set with device ID, timestamp, and data category as joint primary keys is constructed and stored in the database.

3. The full-cycle collaborative optimization method of the water treatment process chain and energy system according to claim 1, characterized in that: According to the acquired astronomical time series parameters and local meteorological disturbance factors, a dual-degree-of-freedom adjustment model for photovoltaic panels is constructed, and power generation feedback is introduced during the adjustment process to achieve real-time matching of the spatial attitude of photovoltaic panels with different environmental conditions, including: Acquire astronomical time series parameters including solar declination angle, local latitude and solar hour angle, and synchronously acquire local meteorological disturbance factors including irradiance data of photovoltaic panel surface irradiance sensor, cloud coverage and light intensity parameters; In the pre-built photovoltaic panel dual-degree-of-freedom adjustment model, the theoretical azimuth is calculated according to the solar hour angle, and the meteorological disturbance correction term is superimposed to generate the real-time azimuth. The initial tilt angle is calculated according to the solar declination angle, local latitude and solar hour angle, and the surface irradiance distribution entropy value determined by the data ratio of the irradiance sensor is introduced for compensation to obtain the real-time tilt angle. Send real-time azimuth and tilt angle adjustment instructions to the bracket drive device, and monitor the adjusted power generation rate in real time. When the power generation rate is lower than the preset threshold, the following adaptive parameter adjustment mechanism is triggered: According to the linear relationship between the PWM duty cycle and the adjustment speed of the bracket driving device, the duty cycle is dynamically adjusted to change the adjustment speed, wherein the duty cycle adjustment amount is determined by gradient descent; The angle increment is attenuated exponentially according to the set adjustment step length and adjustment times, so as to gradually approach the optimal tilt angle and azimuth angle in multiple adjustments; The adjusted adjustment speed, azimuth angle and tilt angle are encoded as adjustment instructions to obtain a multi-dimensional adjustment instruction set; The feasibility of the instruction set is verified through the preset mechanical motion constraints. If the mechanical limit is exceeded, the speed and angle increment are adjusted proportionally and sent to the bracket drive device to perform dual-degree-of-freedom posture adjustment, and receive real-time feedback of the actual angle and power generation; Among them, the double-degree-of-freedom adjustment model of the photovoltaic panel is: Where α is the real-time azimuth, ω is the theoretical azimuth determined by the solar hour angle, and Δα corr is the meteorological disturbance correction term generated by the weighted function of cloud coverage and light intensity change, β is the real-time tilt angle, δ is the solar declination, is the local latitude, λ is the entropy value of surface irradiance distribution The weight coefficient, χ i is the data proportion of the i-th irradiance sensor.

4. The full-cycle collaborative optimization method of the water treatment process chain and energy system according to claim 1, characterized in that: The power self-sufficiency rate is calculated based on the data set. When the self-sufficiency rate is lower than the critical threshold, the flexible adjustment of the energy storage unit discharge depth constraint and the dynamic allocation of power priority of non-critical process equipment are executed. The compensation strategy of photovoltaic panel working point correction and load redistribution is triggered based on the real-time monitoring of power deviation to form a dynamic balance of power distribution, including: The power self-sufficiency rate is calculated based on the photovoltaic power generation efficiency data obtained from the data set and the total power of all process equipment. When it is detected that the power self-sufficiency rate is lower than the preset critical threshold, the power supply and demand imbalance regulation process is triggered; According to the dynamic relationship between the current remaining power and the rated capacity of the energy storage unit, the actual discharge depth is calculated. If the actual discharge depth exceeds the set maximum discharge depth constraint threshold, the discharge power is dynamically compressed according to the preset safety margin ratio, and a discharge power adjustment instruction of the energy storage unit is generated; According to the preset non-critical equipment priority coefficient, dynamically reduce or delay the power demand of the corresponding non-critical equipment, give priority to maintaining the power supply continuity of key process equipment, and generate equipment power adjustment instructions; Monitor the deviation between the actual power and expected power of each process equipment in real time. If the deviation exceeds the allowable threshold, perform the following operations simultaneously; Based on the photovoltaic panel characteristic curve and photovoltaic power generation efficiency data, the equivalent series resistance value and parallel resistance value corresponding to the maximum power point are analyzed, and the working point of the photovoltaic panel is driven to shift to the maximum power output area by dynamically adjusting the resistance value; Redistribute the remaining load capacity and generate load redistribution compensation instructions based on the priority coefficient of non-critical equipment and the real-time power shortage ratio; The adjusted electricity self-sufficiency rate, discharge depth and power deviation parameters are continuously monitored. If any parameter has not returned to the equilibrium range, the energy storage discharge power threshold, non-critical equipment priority weight coefficient and photovoltaic operating point correction step are iteratively optimized and adjusted through the adaptive learning model to form a closed-loop feedback dynamic balancing mechanism for power distribution.

5. The full-cycle collaborative optimization method of the water treatment process chain and energy system according to claim 1, characterized in that: By building a water quality and energy consumption prediction model, generating closed-loop feedback-driven parameter optimization instructions for process equipment, synchronously linking the power distribution status, and adjusting the optimization step size of the parameter optimization instructions and the power distribution plan reconstruction, the coordinated convergence of water quality treatment efficiency, energy consumption indicators and power distribution plans is achieved, including: Based on the correlation between historical water quality parameters and sewage treatment volume, a water quality treatment volume prediction model is constructed through a multivariate linear regression algorithm. The energy consumption demand prediction model is established by combining the dynamic relationship between process equipment energy consumption data and sewage treatment volume to generate a process parameter optimization instruction set. Associating the process parameter optimization instruction set with the current power distribution state to mark the feasible execution range of the process parameter optimization instruction set; According to the feasible execution range of the parameter optimization instruction, based on the priority coefficient of non-critical equipment and the energy storage discharge depth constraint, the power distribution weight matrix is ​​constructed to match the power distribution plan with the energy demand of the process parameter optimization instruction in real time; During the optimization period, the water quality treatment efficiency deviation, unit energy consumption index and power supply and demand deviation are monitored in real time. If any of the indicators exceeds the preset threshold, the following iterative optimization is triggered until the water quality treatment efficiency deviation, unit energy consumption index and power supply and demand deviation converge to the preset optimization range: Update the regression coefficients of the water quality prediction model and the proportionality coefficients of the energy consumption prediction model; Taking the treatment effect deviation as the control factor and combining the historical optimization step length, the optimization step length is adaptively adjusted through linear superposition, and at the same time, the process parameter optimization instruction set is proportionally adjusted according to the corrected optimization step length; And, regenerate the process parameter optimization instruction set.

6. The full-cycle collaborative optimization method of the water treatment process chain and energy system according to claim 1, characterized in that: Also includes: Continuously obtain process equipment operating parameters and historical maintenance records to construct a multi-dimensional feature vector including vibration frequency, energy efficiency and temperature change rate; Input the multi-dimensional feature vector into the pre-trained neural network model, output the real-time health index of the equipment, and predict the remaining service life based on time series analysis; When it is detected that the equipment operating parameters deviate from the preset operating threshold range, or the predicted remaining service life is lower than the preset life critical value, an early warning message containing the equipment ID, abnormality type, warning level and recommended maintenance measures will be sent to the management personnel; Based on the warning level, equipment operating load and available maintenance resource information, a maintenance priority queue is dynamically generated, and maintenance time windows and resource scheduling plans are automatically allocated.

7. A full-cycle collaborative optimization system for water treatment process chain and energy system, characterized in that: include: The data acquisition and processing module is used to acquire and process multi-dimensional data including process equipment operating parameters, water quality treatment data, photovoltaic power generation efficiency and energy storage unit status to obtain a data set; Photovoltaic panel adjustment module, which is used to construct a dual-degree-of-freedom adjustment model for photovoltaic panels based on the acquired astronomical timing parameters and local meteorological disturbance factors, and introduce power generation feedback during the adjustment process to achieve real-time matching of the spatial attitude of the photovoltaic panels with different environmental conditions; The power distribution module is used to calculate the power self-sufficiency rate based on the data set. When the self-sufficiency rate is lower than the critical threshold, it performs elastic adjustment of the energy storage unit discharge depth constraint and dynamic priority allocation of power for non-critical process equipment, and triggers the compensation strategy of photovoltaic panel working point correction and load redistribution based on real-time monitoring of power deviation to form a dynamic balance of power distribution; The collaborative optimization module is used to generate parameter optimization instructions for process equipment driven by closed-loop feedback by constructing a water quality and energy consumption prediction model, synchronously associate the power distribution status, and form a collaborative convergence of water quality treatment efficiency, energy consumption indicators and power distribution scheme by adjusting the optimization step size of the parameter optimization instructions and the reconstruction of the power distribution scheme.

8. A full-cycle coordinated optimization device for a water treatment process chain and an energy system, characterized in that: include: Multi-dimensional data perception network, including sensor groups deployed on process equipment, power generation monitoring units deployed on distributed photovoltaic power generation equipment, and status monitoring units deployed on energy storage units, for real-time collection of process parameters, water quality indicators, photovoltaic power generation efficiency, and energy storage unit status data; A control center, connected to the multidimensional data perception network for executing the full-cycle collaborative optimization method of the water treatment process chain and the energy system as described in any one of claims 1 to 6; And, the cloud platform is bidirectionally connected with the control center, process equipment and distributed photovoltaic power generation equipment to store and analyze historical operation data and issue optimization suggestions to the control center; Among them, the multi-dimensional data perception network, control center and cloud platform constitute a cloud-edge collaborative architecture to realize full-cycle collaborative processing of data collection, real-time control and parameter optimization.

9. The full-cycle coordinated optimization device for the water treatment process chain and energy system according to claim 8, characterized in that: The process equipment includes sewage pretreatment tank, biochemical treatment area and effluent detection area. The biochemical treatment area includes anoxic tank, aerobic tank and clarification tank. The distributed photovoltaic power generation equipment includes a photovoltaic panel and a battery group electrically connected to the photovoltaic panel.

10. A computer-readable medium having computer-executable instructions stored thereon, characterized in that: When the executable instructions are executed by the processor, the full-cycle collaborative optimization method based on the water treatment process chain and the energy system as described in any one of claims 1 to 6 is implemented.

Images