Sewage treatment operation cost optimization method and system based on big data

By collecting real-time data in sewage treatment plants, establishing a corresponding relationship between load and resource consumption, and performing cross-combination mapping and automated adjustments, the problem of cost estimation deviation caused by water quality fluctuations is resolved, and accurate cost management and optimal resource allocation are achieved.

CN120764984AActive Publication Date: 2025-10-10HANGZHOU KAIYUAN ENVIRONMENTAL PROTECTION ENG
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202511293810.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-11
Publication Date
2025-10-10
Estimated Expiration
2045-09-11

AI Technical Summary

Technical Problem

When faced with changes in water quality and quantity, existing sewage treatment plants have difficulty achieving resource utilization efficiency, lack of targeted cost optimization, and are unable to achieve cost optimization while ensuring that the effluent meets standards.

Method used

By collecting real-time operating data from sewage treatment plants, establishing a corresponding relationship between sewage treatment load and resource consumption, and performing cross-combination mapping of the time dimension and the water quality change dimension, an operating cost curve is generated. Based on the cost deviation data, the linkage adjustment time point of the process parameters is determined to achieve automated adjustment.

Benefits of technology

It realizes real-time monitoring and accurate prediction of sewage treatment operating costs, improves the adaptability and accuracy of cost management, reduces overall operating costs, and enhances the automation level of system operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120764984A_ABST
    Figure CN120764984A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of sewage treatment, in particular to a sewage treatment operation cost optimization method and system based on big data. The method comprises the following steps: acquiring real-time operation data, calculating the processing cost in a segmented manner, establishing a corresponding relation between sewage treatment load and resource consumption, generating an operation cost curve, comparing the operation cost curve with a preset threshold value, determining a linkage adjustment time point of process parameters according to a cost fluctuation curve, sending an adjustment instruction, and recording the process parameters meeting emission standards. According to the invention, dynamic optimization of sewage treatment operation cost and precise regulation and control of process parameters can be realized, the sewage treatment efficiency is improved, and the operation cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a method and system for optimizing sewage treatment operating costs based on big data. Background Art

[0002] As a crucial component of environmental protection, wastewater treatment's operating costs have long been a focus of industry attention. With accelerating urbanization and increasing environmental protection requirements, wastewater treatment plants face the challenges of large treatment volumes, high energy consumption, and persistently high operating costs. Traditional wastewater treatment plants typically operate using fixed process parameters, making them unable to adapt to load fluctuations caused by changes in water quality and quantity, resulting in wasted resources.

[0003] In recent years, the application of big data technology in industrial operation optimization has become increasingly widespread, providing new optimization strategies for wastewater treatment. By collecting and analyzing real-time data from the wastewater treatment process and establishing a model for the relationship between load and cost, more refined operational management can be achieved. However, current wastewater treatment operation cost optimization still has many shortcomings.

[0004] Existing technologies lack precise analysis of the cost structure under varying sewage treatment loads, making cost optimization untargeted and difficult to identify optimal operating conditions. Existing technologies also fail to adjust process parameters in real time based on changes in water quality and quantity, resulting in inefficient resource utilization under load fluctuations. Existing technologies also lack correlation analysis between process parameters and effluent quality, making it impossible to optimize costs while ensuring effluent quality meets standards, leading to an imbalance between treatment effectiveness and economic benefits. Summary of the Invention

[0005] The embodiments of the present invention provide a method and system for optimizing sewage treatment operation costs based on big data, which can at least solve some of the problems existing in the prior art.

[0006] A first aspect of an embodiment of the present invention provides a method for optimizing sewage treatment operation costs based on big data, comprising: Collecting real-time operation data of the sewage treatment plant, calculating the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtaining load-cost relationship data; Based on the load-cost relationship data, the sewage treatment load is cross-mapped in the time dimension and the water quality change dimension to establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption; Generating an operating cost curve for the sewage treatment system according to the corresponding relationship, and comparing the operating cost curve with a preset cost threshold curve to obtain cost deviation data; generating a cost fluctuation curve based on the cost deviation data, and determining a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve; Generate a process parameter adjustment instruction according to the linkage adjustment time point, and send the process parameter adjustment instruction to the execution end of the sewage treatment equipment; Receive the effluent water quality data returned by the execution end of the sewage treatment equipment, and record the corresponding process parameters when the effluent water quality data meets the discharge standard in the sewage treatment operation database.

[0007] Collect real-time operation data of the sewage treatment plant, calculate the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtain load-cost relationship data, including: Collecting real-time operating data of the sewage treatment plant, extracting characteristic parameters of sewage treatment load based on the real-time operating data, and constructing a real-time curve of sewage treatment load; Segmenting the real-time curve of sewage treatment load in the time dimension to obtain a mapping relationship between time periods and load changes; Obtaining equipment operating parameters within the time period, calculating energy consumption, agent usage, and equipment operating time within the time period, and generating an operating cost calculation factor; Associating the operating cost calculation factor with the time period to obtain initial cost distribution data; Extracting change characteristic values ​​of sewage treatment load and operating cost based on the initial cost distribution data, and dividing the initial cost distribution data into a plurality of treatment intervals according to the change characteristic values; The average load value and the average cost value in each processing interval are calculated, and the average load value and the average cost value are associated and paired to obtain load-cost relationship data.

[0008] Based on the load-cost relationship data, the sewage treatment load is cross-mapped in the time dimension and the water quality change dimension to establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption, including: Generating time-scaled sequence distribution data based on the load-cost relationship data, and segmenting the sequence distribution data according to dynamic time windows to generate time slice data of the load cost; Acquire inlet water quality monitoring data for a period corresponding to the time slice data, and extract water quality change parameters from the inlet water quality monitoring data to obtain a water quality fluctuation characteristic curve; Dividing the water quality fluctuation characteristic curve into multiple fluctuation intervals, calculating the coordinated change characteristic value of the water quality parameters in each interval, and compensating the water quality characteristics at the interval boundary according to the difference value of the coordinated change characteristic value of adjacent intervals to generate a water quality fluctuation characteristic curve; Reconstructing the time slice data and the water quality fluctuation characteristic curve to generate a two-dimensional characteristic matrix; Determining a two-layer recursive mapping structure based on the two-dimensional feature matrix, determining a fluctuation compensation threshold in the two-layer recursive mapping structure, and processing the two-dimensional feature matrix according to the fluctuation compensation threshold to generate multi-dimensional mapping data; A corresponding relationship between sewage treatment load and comprehensive resource consumption is established based on the multi-dimensional mapping data.

[0009] Determining a two-layer recursive mapping structure based on the two-dimensional feature matrix, determining a fluctuation compensation threshold in the two-layer recursive mapping structure, and processing the two-dimensional feature matrix according to the fluctuation compensation threshold to generate multi-dimensional mapping data, including: Extracting time series fluctuation characteristics of load data and cost data based on the two-dimensional feature matrix, and calculating the change gradients of the load data and the cost data in different time segments; Dividing the change gradients of the different time periods into different fluctuation intervals according to the fluctuation intensity, and calculating the correlation coefficient between the load data and the cost data in each of the fluctuation intervals; Determining the data correlation degree of each fluctuation interval according to the correlation coefficient, and using the data correlation degree as a weight coefficient to determine a two-layer recursive mapping structure of the load data and the cost data; In the double-layer recursive mapping structure, a fluctuation compensation threshold is determined based on the correlation coefficient and the weight coefficient, and the fluctuation compensation threshold is used to characterize the data conversion intensity between different fluctuation intervals; According to the fluctuation compensation threshold, the load data and cost data in the two-dimensional feature matrix are recursively mapped and calculated in different regions. At the boundary positions of adjacent fluctuation intervals, data smoothing transition processing is performed based on the weight coefficient. A mapping correction coefficient is obtained based on the weight coefficient and the fluctuation compensation threshold. According to the mapping correction coefficient, the load and cost data are adjusted in different regions to generate multi-dimensional mapping data.

[0010] Generating an operating cost curve for the sewage treatment system according to the corresponding relationship, and comparing the operating cost curve with a preset cost threshold curve to obtain cost deviation data, including: Connecting the operating cost data of the sewage treatment system at different time points according to the corresponding relationship to form an operating cost curve, and calculating the operating cost curve to determine the operating cost fluctuation characteristic points; Dividing the operating cost curve into different cost intervals based on the operating cost fluctuation characteristic points, and calculating the data dispersion within each cost interval; Extracting a cost data sequence under a target operating condition from historical operating data, connecting the cost data sequence to generate a preset cost threshold curve, and setting a fluctuation tolerance range for the preset cost threshold curve based on the data dispersion; An initial deviation value is obtained based on the operating cost curve and the preset cost threshold curve, a time period is divided into a stable period and a fluctuating period according to the initial deviation value, an overlap between the cost data in the fluctuating period and the fluctuation tolerance range is calculated, and a fluctuation period weight coefficient is generated; The data association strength between adjacent time periods is calculated based on the fluctuation segment weight coefficient, and the cost data in the fluctuation segment is processed according to the data association strength and the initial deviation value to obtain cost deviation data.

[0011] Generating a cost fluctuation curve based on the cost deviation data, and determining a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve, including: Determining positive deviation values ​​and negative deviation values ​​in the cost deviation data, and connecting the positive deviation values ​​and the negative deviation values ​​in chronological order to generate a cost fluctuation curve; Extracting inflection point data from the cost fluctuation curve, calculating a slope change trend of the inflection point data, and determining candidate peak points and candidate trough points based on the slope change trend; Calculating the fluctuation period and fluctuation amplitude between adjacent candidate peak points and candidate trough points, and screening out fluctuation characteristic points according to the fluctuation period and fluctuation amplitude; Extracting water quality parameters and process parameters in the interval before and after the fluctuation characteristic point, and calculating the change gradient of the water quality parameters; Dividing the change gradient of the water quality parameter into different change intervals according to the intensity, and calculating the parameter response characteristics in different change intervals respectively; The load transfer relationship between the treatment units of the sewage treatment process is extracted based on the parameter response characteristics, the load transfer relationship is combined with the change gradient of the water quality parameters to generate a load response sequence, and the linkage adjustment time point of the process parameters is determined according to the load response sequence.

[0012] Extracting the load transfer relationship between the treatment units of the sewage treatment process based on the parameter response characteristics, combining the load transfer relationship with the change gradient of the water quality parameter to generate a load response sequence, and determining the linkage adjustment time point of the process parameters according to the load response sequence, including: determining a process parameter change trend curve between adjacent processing units based on the parameter response characteristics, determining an inflection point position of the process parameter change trend curve as a load transfer node, and obtaining an initial load transfer relationship based on a time interval of the load transfer node; Dividing the initial load transfer relationship into different transfer intervals according to the process flow of the processing unit, and calculating the parameter response time in each transfer interval; Determine a period during which the gradient of the water quality parameter change is greater than a first gradient threshold as a rapid response interval, and determine a period during which the gradient of the water quality parameter change is less than a second gradient threshold as a delayed response interval; Calculating the load accumulation rate in each of the transfer intervals according to the distribution characteristics of the fast response interval and the delayed response interval to generate a load response sequence; The load accumulation rate in the load response sequence is combined with the parameter response duration to determine the temporal correlation of process parameter adjustment, and the load mutation position and the load gradual change position are marked in the temporal correlation. The linkage adjustment time point of the process parameter is generated according to the load mutation position and the load gradual change position.

[0013] A second aspect of an embodiment of the present invention provides a sewage treatment operation cost optimization system based on big data, comprising: The first unit is used to collect real-time operation data of the sewage treatment plant, calculate the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtain load-cost relationship data; The second unit is used to cross-map the sewage treatment load in the time dimension and the water quality change dimension based on the load-cost relationship data, and establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption; A third unit is configured to generate an operating cost curve of the sewage treatment system according to the corresponding relationship, and compare the operating cost curve with a preset cost threshold curve to obtain cost deviation data; A fourth unit is configured to generate a cost fluctuation curve based on the cost deviation data, and determine a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve; A fifth unit is configured to generate a process parameter adjustment instruction according to the linkage adjustment time point, and send the process parameter adjustment instruction to an execution end of the sewage treatment equipment; The sixth unit is used to receive the effluent water quality data returned by the execution end of the sewage treatment equipment, and record the corresponding process parameters when the effluent water quality data meets the discharge standard into the sewage treatment operation database.

[0014] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0015] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0016] The present invention establishes an accurate correspondence between sewage treatment load and resource consumption through big data analysis, realizes real-time monitoring and accurate prediction of sewage treatment operating costs, effectively identifies cost fluctuation patterns and determines the best adjustment time, thereby reducing overall operating costs.

[0017] The use of load-cost relationship data for cross-combination mapping of the time dimension and the water quality change dimension solves the problem of cost estimation deviation caused by water quality fluctuations that traditional methods are unable to cope with, improves the adaptability and accuracy of cost management, and enables the sewage treatment system to achieve optimal resource allocation while ensuring that the effluent meets the standards.

[0018] Through the intelligent determination of the linkage adjustment time point and the automatic adjustment of the process parameters, human intervention is reduced, the automation level of the system operation is improved, and data can be accumulated according to the actual processing effect, and the processing process can be gradually optimized to form a benign cost optimization cycle mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a method for optimizing sewage treatment operation costs based on big data according to an embodiment of the present invention.

[0020] Figure 2 The figure is a flowchart of determining cost deviation data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 making creative efforts shall fall within the scope of protection of the present invention.

[0022] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0023] Figure 1 FIG. 1 is a flow chart of a method for optimizing the operation cost of sewage treatment based on big data according to an embodiment of the present invention. Figure 1 As shown, the method includes: Collecting real-time operation data of the sewage treatment plant, calculating the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtaining load-cost relationship data; Based on the load-cost relationship data, the sewage treatment load is cross-mapped in the time dimension and the water quality change dimension to establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption; Generating an operating cost curve for the sewage treatment system according to the corresponding relationship, and comparing the operating cost curve with a preset cost threshold curve to obtain cost deviation data; generating a cost fluctuation curve based on the cost deviation data, and determining a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve; Generate a process parameter adjustment instruction according to the linkage adjustment time point, and send the process parameter adjustment instruction to the execution end of the sewage treatment equipment; Receive the effluent water quality data returned by the execution end of the sewage treatment equipment, and record the corresponding process parameters when the effluent water quality data meets the discharge standard in the sewage treatment operation database.

[0024] Distributed data acquisition terminals can collect real-time operational data from each treatment unit within a sewage treatment plant, including but not limited to influent flow, water quality indicators (ammonia nitrogen, total nitrogen, total phosphorus, etc.), dissolved oxygen, pH, temperature, conductivity, sludge concentration, the operating status of various equipment, energy consumption data, and chemical dosage. For example, a sewage treatment plant with a capacity of 100,000 tons / day collects data every five minutes, generating approximately 28,800 data points daily. The collected data is transmitted to a server in a data processing center via an industrial-grade wireless or wired network. After data cleaning and outlier processing, it is stored in a time series database.

[0025] The collected real-time operating data is used to calculate treatment costs by segment according to the sewage treatment load. The sewage treatment load is divided into intervals based on the percentage of influent flow to the designed treatment capacity, such as 0-20%, 20%-40%, 40%-60%, 60%-80%, 80%-100%, and greater than 100%. Within each load interval, the electricity cost, chemical cost, labor cost, equipment maintenance cost, and other costs per unit of treatment volume (e.g., per cubic meter of sewage) are calculated, and these cost items are aggregated to obtain the total treatment cost. For example, within the 40%-60% load interval, the electricity cost is 0.25 yuan / m³, the chemical cost is 0.18 yuan / m³, the labor cost is 0.12 yuan / m³, the equipment maintenance cost is 0.08 yuan / m³, and the total treatment cost is 0.63 yuan / m³. In this way, the relationship between different load intervals and treatment costs is established.

[0026] Based on load-cost relationship data, the sewage treatment load is cross-mapped across time and water quality variations to establish a corresponding relationship between sewage treatment load and comprehensive resource consumption. In the time dimension, factors such as electricity price differences (such as peak and off-peak electricity prices), seasonal variations (such as the impact of temperature on biochemical reaction rates), and holiday effects (such as reduced discharge volume in industrial areas during holidays) can be considered. In the water quality dimension, the impact of changes in influent, ammonia nitrogen, total nitrogen, and total phosphorus on treatment costs is considered. Using data mining and statistical analysis methods, treatment cost coefficients are calculated for different time periods and water quality conditions. Through this cross-combination of time and water quality variations, a refined model for the corresponding relationship between sewage treatment load and comprehensive resource consumption has been established.

[0027] Based on the established correspondence model, an operating cost curve for the sewage treatment system is generated. This curve uses time as the horizontal axis and the cost per unit of treatment volume as the vertical axis, showing the changes in the operating cost of the sewage treatment system at different time points. A preset cost threshold curve is also loaded, representing the theoretically optimal treatment cost curve under current water quality and quantity conditions. By comparing the actual operating cost curve with the preset cost threshold curve, the cost deviation data for each time point is calculated. For example, at 08:00 on a certain day, the actual operating cost was 0.68 yuan / m³, while the preset cost threshold was 0.62 yuan / m³. The cost deviation was 0.06 yuan / m³, with a deviation rate of 9.68%.

[0028] Based on cost deviation data, a cost fluctuation curve is generated. This curve reflects the changing trend of processing cost deviation over time. Data analysis algorithms are used to identify peaks and troughs on the cost fluctuation curve. These characteristic points often correspond to time points when process parameters require adjustment. Peaks indicate high costs, requiring adjustment of process parameters to reduce costs; troughs indicate relatively low costs and can be used as reference points for optimization. Threshold conditions are set. For example, when the cost deviation rate exceeds 8% for three consecutive sampling cycles, it is marked as a peak point requiring adjustment; when the cost deviation rate is below 2% for five consecutive sampling cycles, it is marked as a trough point for optimization reference. Through this characteristic point identification, the time points for coordinated adjustment of process parameters are determined.

[0029] Generate process parameter adjustment instructions based on the determined linkage adjustment time point. Calculate the adjustment direction and amplitude of each process parameter based on historical optimization experience and machine learning models. The adjusted process parameters include, but are not limited to: aeration volume, reflux ratio, reagent dosage, hydraulic retention time, etc. For example, when it is detected that the dissolved oxygen concentration in a certain aeration tank is continuously higher than 2.5 mg / L and the processing load is low, an instruction to reduce the aeration volume will be generated, such as "Adjust the aeration fan frequency of aeration tank No. 2 from 45 Hz to 40 Hz." These process parameter adjustment instructions are sent to the execution end of the sewage treatment equipment through the industrial control network. After receiving the instructions, the execution end adjusts the equipment according to the specified parameters and feeds back the adjustment results to the intelligent cost optimization system.

[0030] Receive effluent water quality data returned by the sewage treatment equipment execution end, including emission indicators such as ammonia nitrogen, total nitrogen, and total phosphorus. Compare this effluent water quality data with the emission standards to determine whether it meets the emission requirements. If the effluent water quality data meets the emission standards, record the current process parameters (such as aeration volume, recirculation ratio, and reagent dosage) in the sewage treatment operation database as a successful optimization case. For example, after a certain optimization adjustment, the ammonia nitrogen is 1.8 mg / L (standard value ≤ 5 mg / L), the total nitrogen is 12.5 mg / L (standard value ≤ 15 mg / L), and the total phosphorus is 0.4 mg / L (standard value ≤ 0.5 mg / L). This set of process parameters is determined to be valid and stored in the database.

[0031] Through the above, intelligent monitoring and optimization adjustment of the operating costs of sewage treatment plants are realized, and the comprehensive cost of sewage treatment is reduced while ensuring that the effluent water quality meets the standards.

[0032] In an optional embodiment, real-time operation data of a sewage treatment plant is collected, and the treatment cost is calculated segment by segment based on the sewage treatment load to obtain load-cost relationship data, including: Collecting real-time operating data of the sewage treatment plant, extracting characteristic parameters of sewage treatment load based on the real-time operating data, and constructing a real-time curve of sewage treatment load; Segmenting the real-time curve of sewage treatment load in the time dimension to obtain a mapping relationship between time periods and load changes; Obtaining equipment operating parameters within the time period, calculating energy consumption, agent usage, and equipment operating time within the time period, and generating an operating cost calculation factor; Associating the operating cost calculation factor with the time period to obtain initial cost distribution data; Extracting change characteristic values ​​of sewage treatment load and operating cost based on the initial cost distribution data, and dividing the initial cost distribution data into a plurality of treatment intervals according to the change characteristic values; The average load value and the average cost value in each processing interval are calculated, and the average load value and the average cost value are associated and paired to obtain load-cost relationship data.

[0033] The present invention collects real-time operation data and analyzes the relationship between load and cost to provide data support for the optimized operation of sewage treatment plants.

[0034] The system continuously collects operational parameter data for each treatment unit, including influent flow, water quality indicators, effluent quality, equipment operating status, and energy consumption. This data is recorded every five minutes by the data acquisition module and stored in a database. For example, data collected from January 1 to January 31, 2023, for a sewage treatment plant included an average daily influent flow of 25,000 cubic meters per day, an influent COD concentration of 350 mg / L, and an NH3-N concentration of 35 mg / L.

[0035] Based on the collected real-time operational data, characteristic parameters of the sewage treatment load are extracted. These load parameters primarily include hydraulic load and pollutant load. Hydraulic load is represented by the influent flow rate, while pollutant load is calculated by multiplying the pollutant concentration by the flow rate. For example, if the influent flow rate at a certain moment is 1,200 cubic meters per hour and the COD concentration is 380 mg / L, the COD load is 456 kg / hour. These load parameters are arranged chronologically to construct a real-time sewage treatment load curve, visually displaying how the load changes over time.

[0036] The real-time sewage treatment load curve is segmented along the time dimension. This segmentation method uses a load fluctuation threshold method, whereby any load change exceeding a preset threshold (e.g., 20%) is marked as a segmentation point. For example, for the aforementioned sewage treatment plant, a day might be divided into a low-load period in the early morning (0:00-6:00, with an average load of 55% of the design load), a high-load period in the morning (6:00-12:00, with an average load of 85% of the design load), a medium-load period in the afternoon (12:00-18:00, with an average load of 75% of the design load), and a fluctuating load period in the evening (18:00-24:00, with the load gradually decreasing from 90% to 60%). This segmentation establishes a mapping between time periods and load changes.

[0037] For each defined time period, equipment operating parameters are obtained. These parameters include aeration equipment power and operating time, pump start / stop status and power, and dosing equipment operation records. Based on these parameters, energy consumption, chemical usage, and equipment operating hours for that time period are calculated. For example, during the morning peak load period (6:00-12:00), the aeration fan averages 200kW power and runs for 6 hours, resulting in a total power consumption of 1200kWh. The PAC dosage is 150kg, and the PAM dosage is 10kg. The main equipment operates for a total of 72 equipment hours. These consumption values ​​are multiplied by the corresponding unit prices (e.g., electricity price 0.8 yuan / kWh, PAC price 2000 yuan / ton, PAM price 15,000 yuan / ton) to obtain operating cost calculation factors, including 960 yuan for electricity, 350 yuan for chemical usage, and an estimated 100 yuan for equipment maintenance.

[0038] The operating cost calculation factors are associated with the corresponding time periods to form initial cost distribution data. This data includes the load levels and corresponding operating costs for different time periods. For example, the cost of the early morning low load period (55% load) is 580 yuan, the morning high load period (85% load) is 1410 yuan, the afternoon medium load period (75% load) is 1050 yuan, and the evening fluctuating load period (75% average load) is 980 yuan.

[0039] Based on the initial cost distribution data, we further extract characteristic values ​​for the changes in wastewater treatment load and operating costs. These characteristic values ​​primarily include the load change rate and the cost change rate, calculated by the difference in data between adjacent time points. Based on these characteristic values, we use cluster analysis to divide the initial cost distribution data into multiple treatment intervals. In this example, the data can be divided into three main intervals: low load (40%-60%), medium load (60%-80%), and high load (80%-100%).

[0040] For each processing interval, calculate the average load and average cost for all data points within that interval. For example, the average load in the low-load interval (40%-60%) is 55%, with an average cost of 600 yuan / hour; the average load in the medium-load interval (60%-80%) is 70%, with an average cost of 1,000 yuan / hour; and the average load in the high-load interval (80%-100%) is 90%, with an average cost of 1,500 yuan / hour. These average load and average cost values ​​are then correlated and paired to generate the final load-cost relationship data.

[0041] The load-cost relationship data obtained above can intuitively reflect the cost efficiency of sewage treatment at different load levels. For example, the data shows that when the load increases from 55% to 70%, the cost increases by approximately 67%, and when the load increases from 70% to 90%, the cost increases by approximately 50%. This indicates that the sewage treatment plant has good cost-effectiveness when operating in the medium load range. Based on this data, sewage treatment plant managers can optimize scheduling strategies, such as minimizing high-load operation during periods of high electricity prices or adjusting the influent flow rate to maintain the treatment load within the most cost-effective range.

[0042] In addition, based on the load-cost relationship data and combined with external factors such as historical weather data and holiday information, load forecasting models and cost forecasting models can be established to provide more comprehensive decision-making support for the operation optimization and cost control of sewage treatment plants.

[0043] In an optional embodiment, based on the load-cost relationship data, the sewage treatment load is cross-mapped in the time dimension and the water quality change dimension to establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption, including: Generating time-scaled sequence distribution data based on the load-cost relationship data, and segmenting the sequence distribution data according to dynamic time windows to generate time slice data of the load cost; Acquire inlet water quality monitoring data for a period corresponding to the time slice data, and extract water quality change parameters from the inlet water quality monitoring data to obtain a water quality fluctuation characteristic curve; Dividing the water quality fluctuation characteristic curve into multiple fluctuation intervals, calculating the coordinated change characteristic value of the water quality parameters in each interval, and compensating the water quality characteristics at the interval boundary according to the difference value of the coordinated change characteristic value of adjacent intervals to generate a water quality fluctuation characteristic curve; Reconstructing the time slice data and the water quality fluctuation characteristic curve to generate a two-dimensional characteristic matrix; Determining a two-layer recursive mapping structure based on the two-dimensional feature matrix, determining a fluctuation compensation threshold in the two-layer recursive mapping structure, and processing the two-dimensional feature matrix according to the fluctuation compensation threshold to generate multi-dimensional mapping data; A corresponding relationship between sewage treatment load and comprehensive resource consumption is established based on the multi-dimensional mapping data.

[0044] This embodiment establishes a corresponding relationship between sewage treatment load and comprehensive resource consumption by performing cross-combination mapping in the time dimension and the water quality change dimension, thereby achieving accurate resource allocation in the sewage treatment process.

[0045] During implementation, the first step is to collect six months of operational data from the sewage treatment plant, including cost factor data such as electricity consumption, chemical input, and equipment operating time, as well as sewage treatment load data for the corresponding time period. Based on this data, time-scaled sequence distribution data is generated. For example, for electricity consumption data, hourly sampling is performed to obtain approximately 4,320 data points (6 months × 30 days × 24 hours). For chemical input, statistics are collected based on each dose record to form a time series. This sequence distribution data is then segmented using a sliding time window method, with a window size set to 12 hours and a step size of 4 hours, to generate time-sliced ​​load cost data. In practice, a typical time-sliced ​​dataset contains approximately 1,080 slices (4,320 ÷ 4), each of which contains multidimensional data such as sewage treatment volume, electricity consumption, and chemical input during that time period.

[0046] Obtain influent water quality monitoring data for the time period corresponding to the time slice data, focusing on key water quality indicators such as COD, ammonia nitrogen, total phosphorus, and pH. Extract water quality variation parameters from this monitoring data, such as the COD fluctuation amplitude, the ammonia nitrogen change rate, and the pH fluctuation range. Use these parameters to plot a water quality fluctuation characteristic curve. For example, within a week, the COD of a sewage treatment plant fluctuated from 350mg / L to 520mg / L and then dropped to 280mg / L, and the ammonia nitrogen fluctuated from 40mg / L to 25mg / L and then rose to 45mg / L. By analyzing the changing trends of these data, a corresponding water quality fluctuation characteristic curve can be generated.

[0047] The water quality fluctuation characteristic curve is divided into multiple fluctuation intervals. A threshold is typically set based on the fluctuation amplitude. When the change in a particular indicator exceeds the set threshold, a new fluctuation interval is marked. For the COD data described above, it might be divided into three intervals: an ascending interval (350 mg / L to 520 mg / L), a descending interval (520 mg / L to 280 mg / L), and a stable interval (fluctuating around 280 mg / L). Within each interval, the co-variation characteristic values ​​of the water quality parameters are calculated, such as the correlation between COD and ammonia nitrogen, or the co-variation characteristics of total phosphorus and pH. At the boundary between adjacent intervals, such as the 520 mg / L point where COD transitions from rising to falling, the difference between the co-variation characteristic values ​​of the preceding and following intervals is calculated. When the difference exceeds a set threshold (e.g., 30%), compensation is applied to the water quality characteristics at that boundary. This compensation method uses a weighted average of the preceding and following data, with the weight determined by the slope of the change. This smoothes the data at the sudden change, generating a water quality fluctuation characteristic curve that better reflects reality.

[0048] The time-sliced ​​data and the water quality fluctuation characteristic curve are reconstructed to generate a two-dimensional feature matrix. The rows of this matrix represent the time dimension, and the columns represent the water quality variation dimension. Each element of the matrix contains the sewage treatment load and resource consumption data for the corresponding time and water quality conditions. For example, the element (t1, q1) in the matrix contains data such as sewage treatment volume, electricity consumption, and chemical dosage at time t1 and water quality characteristic q1.

[0049] Based on the two-dimensional feature matrix, a two-layer recursive mapping structure is determined. The first-layer mapping focuses on the time dimension, analyzing the impact of different time periods (such as morning peak and nighttime trough) on resource consumption; the second-layer mapping focuses on the water quality dimension, analyzing the impact of different water quality conditions (such as high COD and low ammonia nitrogen) on resource consumption. In the two-layer recursive mapping structure, the fluctuation compensation threshold is determined to be 15%. When the resource consumption fluctuation in a certain period of time or under certain water quality conditions exceeds this threshold, the compensation mechanism is triggered. The two-dimensional feature matrix is ​​processed according to the fluctuation compensation threshold to generate multi-dimensional mapping data. This data not only includes the impact of the two dimensions of time and water quality, but also takes into account the influence of external factors such as equipment status and temperature to form a more comprehensive mapping relationship.

[0050] Based on multi-dimensional mapping data, a corresponding relationship between sewage treatment load and comprehensive resource consumption was ultimately established. For example, when the influent COD is 400 mg / L, ammonia nitrogen is 35 mg / L, and the average daily water volume is 50,000 tons, the estimated electricity consumption is 12,000 kWh / day, the PAC dosage is 300 kg / day, and the PAM dosage is 15 kg / day. This corresponding relationship can be used to predict resource demand under different load conditions, optimize resource allocation, and reduce operating costs. Practical applications have verified that the corresponding relationship established by this method has a prediction accuracy of 92%, improving resource utilization efficiency by 15% and saving approximately 10% in operating costs compared to traditional methods.

[0051] In an optional embodiment, a two-layer recursive mapping structure is determined based on the two-dimensional feature matrix, a fluctuation compensation threshold is determined in the two-layer recursive mapping structure, and the two-dimensional feature matrix is ​​processed according to the fluctuation compensation threshold to generate multi-dimensional mapping data, including: Extracting time series fluctuation characteristics of load data and cost data based on the two-dimensional feature matrix, and calculating the change gradients of the load data and the cost data in different time segments; Dividing the change gradients of the different time periods into different fluctuation intervals according to the fluctuation intensity, and calculating the correlation coefficient between the load data and the cost data in each of the fluctuation intervals; Determining the data correlation degree of each fluctuation interval according to the correlation coefficient, and using the data correlation degree as a weight coefficient to determine a two-layer recursive mapping structure of the load data and the cost data; In the double-layer recursive mapping structure, a fluctuation compensation threshold is determined based on the correlation coefficient and the weight coefficient, and the fluctuation compensation threshold is used to characterize the data conversion intensity between different fluctuation intervals; According to the fluctuation compensation threshold, the load data and cost data in the two-dimensional feature matrix are recursively mapped and calculated in different regions. At the boundary positions of adjacent fluctuation intervals, data smoothing transition processing is performed based on the weight coefficient. A mapping correction coefficient is obtained based on the weight coefficient and the fluctuation compensation threshold. According to the mapping correction coefficient, the load and cost data are adjusted in different regions to generate multi-dimensional mapping data.

[0052] In this implementation, the process of determining a two-layer recursive mapping structure based on a two-dimensional feature matrix involves a series of data processing steps. The two-dimensional feature matrix contains load data and cost data, which reflect the temporal variation characteristics of energy consumption and economic costs. Processing this data requires first extracting its temporal fluctuation characteristics and calculating the gradient of variation across different time segments.

[0053] To extract time-series fluctuation characteristics, load and cost data for seven consecutive days can be analyzed. For example, load data for a certain regional power grid on weekdays shows peaks in the morning and evening, with a flattening pattern during the afternoon. The gradient reaches 0.35 kW / h from 6:00 AM to 9:00 AM and 0.42 kW / h from 5:00 PM to 8:00 PM. Meanwhile, the gradient of cost data during peak hours is 0.28 yuan / kWh. Weekend load data is relatively flat, with a gradient of no more than 0.18 kW / h.

[0054] After calculating the gradient, the data from different time periods were divided into different fluctuation intervals based on the intensity of the fluctuation. Based on the actual data performance, the gradient was divided into a high fluctuation interval (gradient > 0.3), a medium fluctuation interval (gradient 0.1-0.3), and a low fluctuation interval (gradient < 0.1). Based on this, the correlation coefficient between the load data and the cost data within each fluctuation interval was calculated. Statistical analysis showed that the correlation coefficient for the high fluctuation interval was 0.86, the medium fluctuation interval was 0.72, and the low fluctuation interval was 0.58.

[0055] Based on the calculated correlation coefficient, the data correlation degree for each fluctuation range is determined and used as a weight coefficient to construct a two-layer recursive mapping structure for load data and cost data. The weight coefficient for the high fluctuation range is set to 0.5, the medium fluctuation range is set to 0.3, and the low fluctuation range is set to 0.2. This setting reflects the impact of different fluctuation intensities on load and cost.

[0056] In the constructed double-layer recursive mapping structure, the fluctuation compensation threshold is determined based on the correlation coefficient and the weight coefficient. The fluctuation compensation threshold is used to represent the data conversion strength between different fluctuation intervals. For the high-moderate fluctuation interval transition, it is set to 0.25, and for the moderate-low fluctuation interval transition, it is set to 0.15. For example, when the load data is transferred from the high fluctuation interval to the moderate fluctuation interval, the fluctuation compensation threshold of 0.25 is applied for data adjustment.

[0057] According to the fluctuation compensation threshold, the load data and the cost data in the double-dimensional feature matrix are calculated by recursive mapping in different regions. In the specific implementation, for the load data point in the high fluctuation interval, such as the load value of 125 kW at 7:30 in the morning, the weight coefficient of 0.5 in the high fluctuation interval is applied for mapping calculation, and the mapping value of 62.5 is obtained. At the same time, the corresponding cost data of 0.85 yuan / kWh is processed in the same way to obtain the mapping value of 0.425 yuan / kWh.

[0058] At the boundary position of adjacent fluctuation intervals, data smoothing transition processing is performed based on the weight coefficient. Taking the transition from the high fluctuation interval to the moderate fluctuation interval as an example, at the boundary time point of 9:15, the load data is 110 kW and the cost data is 0.78 yuan / kWh. The weight coefficient of the transition region is obtained by weighted average of the high fluctuation interval weight coefficient (0.5) and the moderate fluctuation interval weight coefficient (0.3), which is 0.42, and is applied to data processing to realize smooth transition.

[0059] Based on the weight coefficient and the fluctuation compensation threshold, the mapping correction coefficient is calculated. In the high fluctuation interval, the mapping correction coefficient is the weighted sum of the weight coefficient and the fluctuation compensation threshold, which is calculated as 0.5x1+0.25x0.3=0.575; in the moderate fluctuation interval, it is 0.3x1+0.25x0.2+0.15x0.3=0.395; in the low fluctuation interval, it is 0.2x1+0.15x0.2=0.23. According to these mapping correction coefficients, the load and cost data are adjusted in different regions.

[0060] In the specific adjustment process, the load data of 125 kW in the high fluctuation interval is adjusted to 71.875 kW by the mapping correction coefficient of 0.575, and the cost data of 0.85 yuan / kWh is adjusted to 0.48875 yuan / kWh. The load data of 95 kW in the moderate fluctuation interval is adjusted to 37.525 kW, and the cost data of 0.65 yuan / kWh is adjusted to 0.25675 yuan / kWh. The load data of 65 kW in the low fluctuation interval is adjusted to 14.95 kW, and the cost data of 0.45 yuan / kWh is adjusted to 0.1035 yuan / kWh.

[0061] Through the aforementioned recursive mapping calculations and adjustments, multi-dimensional mapping data is ultimately generated, encompassing load, cost, and interval-correlation dimensions. This data not only preserves the temporal characteristics of the original load and cost data but also, through the division of fluctuation intervals and correlation analysis, enhances the data's ability to express varying fluctuation intensities, providing richer and more accurate data support for subsequent energy scheduling optimization.

[0062] In an optional embodiment, an operating cost curve of the sewage treatment system is generated according to the corresponding relationship, and the operating cost curve is compared with a preset cost threshold curve to obtain cost deviation data, including: Connecting the operating cost data of the sewage treatment system at different time points according to the corresponding relationship to form an operating cost curve, and calculating the operating cost curve to determine the operating cost fluctuation characteristic points; Dividing the operating cost curve into different cost intervals based on the operating cost fluctuation characteristic points, and calculating the data dispersion within each cost interval; Extracting a cost data sequence under a target operating condition from historical operating data, connecting the cost data sequence to generate a preset cost threshold curve, and setting a fluctuation tolerance range for the preset cost threshold curve based on the data dispersion; An initial deviation value is obtained based on the operating cost curve and the preset cost threshold curve, a time period is divided into a stable period and a fluctuating period according to the initial deviation value, an overlap between the cost data in the fluctuating period and the fluctuation tolerance range is calculated, and a fluctuation period weight coefficient is generated; The data association strength between adjacent time periods is calculated based on the fluctuation segment weight coefficient, and the cost data in the fluctuation segment is processed according to the data association strength and the initial deviation value to obtain cost deviation data.

[0063] This embodiment can effectively monitor the operating costs of the sewage treatment system, promptly detect abnormal cost fluctuations, and provide accurate deviation analysis.

[0064] Figure 2 FIG. 1 is a flow chart of determining cost deviation data according to an embodiment of the present invention. Figure 2 As shown in the figure, the corresponding relationship between the operating parameters and costs of each device in the sewage treatment system can be obtained. These relationships include the mapping of factors such as power consumption, chemical dosage, and equipment maintenance to costs. For example, when the aeration system of a sewage treatment plant consumes 500kWh of electricity, the corresponding electricity cost is 350 yuan; when 200kg of PAC flocculant is added, the corresponding chemical cost is 1200 yuan.

[0065] Based on this correspondence, the operating cost data for the sewage treatment system at different time points can be connected to form an operating cost curve. For example, for a 24-hour day, the operating cost data is recorded every hour: [320 yuan, 335 yuan, 342 yuan, 356 yuan, 380 yuan, 420 yuan, 450 yuan, 470 yuan, 465 yuan, 450 yuan, 430 yuan, 400 yuan, 390 yuan, 385 yuan, 375 yuan, 365 yuan, 370 yuan, 385 yuan, 410 yuan, 430 yuan, 415 yuan, 395 yuan, 370 yuan, 340 yuan]. Connecting these data points in chronological order creates a curve that shows the cost changes over the course of a day.

[0066] Calculate the fluctuation characteristic points of the operating cost curve, that is, points where the rate of cost change changes significantly. By calculating the cost change rate between adjacent time points, when the rate of change exceeds a predetermined threshold (such as 10%), the point is marked as a fluctuation characteristic point. In the above example, the cost increased from 380 yuan to 420 yuan from the 5th to the 6th hour, with a rate of change of 10.5%, so the 6th hour is marked as a fluctuation characteristic point. Similarly, the 7th to 8th hour and the 19th to 20th hour are also marked as fluctuation characteristic points.

[0067] Based on the identified fluctuation characteristic points, the operating cost curve is divided into different cost intervals. For example, the above example can be divided into four intervals: [0-5 hours], [6-12 hours], [13-19 hours], and [20-23 hours]. The dispersion of the data within each interval is calculated, expressed as the ratio of the data standard deviation to the mean. For example, the data for the [0-5 hours] interval is [320 yuan, 335 yuan, 342 yuan, 356 yuan, 380 yuan]. The calculated mean is 346.6 yuan, the standard deviation is 22.5 yuan, and the dispersion is 6.5%. Similarly, the dispersions for the other intervals are calculated to be 7.2%, 5.8%, and 9.1%, respectively.

[0068] Extract the cost data sequence under the target operating condition from the historical operating data. For example, the historical data under the same load conditions is: [325 yuan, 338 yuan, 345 yuan, 352 yuan, 370 yuan, 410 yuan, 445 yuan, 460 yuan, 458 yuan, 442 yuan, 425 yuan, 390 yuan, 382 yuan, 378 yuan, 370 yuan, 360 yuan, 365 yuan, 380 yuan, 405 yuan, 425 yuan, 410 yuan, 390 yuan, 365 yuan, 335 yuan]. Connect these data to generate the preset cost threshold curve.

[0069] Based on the previously calculated data dispersion, a fluctuation tolerance is set for the preset cost threshold curve. The fluctuation tolerance is calculated by adjusting the preset cost threshold at each time point by a ratio equal to 1.5 times the dispersion of the corresponding interval. For example, if the dispersion of the interval [0-5 hours] is 6.5%, the fluctuation tolerance within this interval is ±9.75%. This means that if the preset cost for the first hour is 325 yuan, the fluctuation tolerance range is [293.3 yuan, 356.7 yuan].

[0070] The initial deviation value is calculated based on the operating cost curve and the preset cost threshold curve. This is the difference between the actual cost and the preset cost. For example, if the actual cost in the first hour is 320 yuan and the preset cost is 325 yuan, the initial deviation value is -5 yuan. Based on the size and continuity of the initial deviation value, the time period is divided into a stable period and a fluctuating period. If the initial deviation value exceeds a certain threshold (such as ±5%) for multiple consecutive time points, the period is marked as a fluctuating period; otherwise, it is marked as a stable period.

[0071] Calculate the overlap between the cost data within the fluctuation segment and the fluctuation tolerance range. Overlap is calculated as the ratio of the number of data points within the fluctuation segment that fall within the fluctuation tolerance range to the total number of data points in the segment. For example, if a fluctuation segment contains 5 data points, 3 of which fall within the fluctuation tolerance range, the overlap is 60%. Based on the overlap, a fluctuation segment weight coefficient is generated, which is equal to 1 minus the overlap. In the above example, the fluctuation segment weight coefficient is 40%.

[0072] Calculate the strength of data association between adjacent time periods, that is, the consistency of data trends between adjacent time periods. Association strength is calculated as the similarity in the rate of change between the data points at the end and the beginning of adjacent segments. For example, if the data at the end of the first segment is 380 yuan and the data at the beginning of the second segment is 420 yuan, the rate of change is 10.5%. If the rate of change at the corresponding point in the historical data is 10.8%, the association strength is 97.2%.

[0073] Cost deviation data is processed based on the data association strength and initial deviation value within the fluctuation segment. This process is performed by multiplying the initial deviation value by (1 - association strength) × the fluctuation segment weight coefficient to obtain the corrected cost deviation data. For example, if the initial deviation value of a data point within a fluctuation segment is 15 yuan, the association strength is 90%, and the fluctuation segment weight coefficient is 40%, the corrected cost deviation data is 15 × (1 - 90%) × 40% = 0.6 yuan.

[0074] Through the above, we can accurately analyze the fluctuations in the operating costs of the sewage treatment system, identify abnormal cost changes, and quantify cost deviations, providing data support for the optimized operation of the sewage treatment system.

[0075] In an optional embodiment, generating a cost fluctuation curve based on the cost deviation data, and determining a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve include: Determining positive deviation values ​​and negative deviation values ​​in the cost deviation data, and connecting the positive deviation values ​​and the negative deviation values ​​in chronological order to generate a cost fluctuation curve; Extracting inflection point data from the cost fluctuation curve, calculating a slope change trend of the inflection point data, and determining candidate peak points and candidate trough points based on the slope change trend; Calculating the fluctuation period and fluctuation amplitude between adjacent candidate peak points and candidate trough points, and screening out fluctuation characteristic points according to the fluctuation period and fluctuation amplitude; Extracting water quality parameters and process parameters in the interval before and after the fluctuation characteristic point, and calculating the change gradient of the water quality parameters; Dividing the change gradient of the water quality parameter into different change intervals according to the intensity, and calculating the parameter response characteristics in different change intervals respectively; The load transfer relationship between the treatment units of the sewage treatment process is extracted based on the parameter response characteristics, the load transfer relationship is combined with the change gradient of the water quality parameters to generate a load response sequence, and the linkage adjustment time point of the process parameters is determined according to the load response sequence.

[0076] In this embodiment, cost deviation data can be processed and analyzed. In actual applications, the operating costs of a sewage treatment plant will fluctuate around the standard cost, resulting in positive and negative deviation values. For example, the daily cost deviation data recorded by a sewage treatment plant over a month is as follows: +0.15 yuan / ton on day 1, +0.21 yuan / ton on day 2, +0.08 yuan / ton on day 3, -0.05 yuan / ton on day 4, -0.12 yuan / ton on day 5, and so on. These positive and negative deviation values, arranged in chronological order, are connected to generate a cost fluctuation curve.

[0077] After generating the cost fluctuation curve, extract the inflection point data from the curve. An inflection point is a point where the slope of the curve changes significantly, indicating a turning point in the cost trend. These inflection points are identified by calculating the slope change between adjacent data points. For example, when the slope changes from a positive value to a negative value, it may indicate a candidate peak point; when the slope changes from a negative value to a positive value, it may indicate a candidate trough point. In the above data, candidate peak points and candidate trough points may be identified on the 3rd and 5th days, respectively, because the cost deviation begins to decrease after the 3rd day and begins to increase after the 5th day.

[0078] To identify true fluctuation characteristic points, the fluctuation period and amplitude between adjacent candidate peaks and troughs are calculated. The fluctuation period refers to the time interval from one peak to the next, or from one trough to the next, while the amplitude refers to the cost difference between a peak and the adjacent trough. Threshold conditions are set, such as a fluctuation period greater than 3 days and an amplitude greater than 0.2 yuan / ton to be considered a valid fluctuation characteristic point. This can filter out short-term fluctuations caused by random factors or measurement errors.

[0079] After determining the characteristic points of fluctuation, extract the water quality and process parameters before and after these points. For example, the influent COD and NH3-N concentrations, as well as process parameters such as aeration rate and recirculation ratio, for the three days before and after the peak point are analyzed. Calculate the gradient of the water quality parameters—the rate of change of the parameter per unit time. For example, if the influent COD rises from 350 mg / L to 450 mg / L three days before the peak point, the COD gradient is 33.3 mg / L / day.

[0080] Water quality parameters are divided into different change intervals based on the intensity of their gradients. For example, COD can be divided into a slight change interval (gradient less than 20 mg / L / day), a moderate change interval (20-50 mg / L / day), and a drastic change interval (greater than 50 mg / L / day). For each interval, parameter response characteristics are calculated, including response time, response intensity, and duration. For example, in a moderate COD change interval, it may be found that aeration volume adjustment begins after an average of 1.5 days, with a response intensity of 15% aeration volume adjustment for every 100 mg / L COD change, and a duration of approximately 2 days.

[0081] Based on the parameter response characteristics, the load transfer relationship between the various treatment units of the sewage treatment process is extracted. For example, it may be found that when the influent COD increases, the load of the primary sedimentation tank increases first, then the load of the biological reactor increases, and finally the load of the secondary sedimentation tank increases. These changes occur 0.5 days, 1.5 days, and 2.5 days after the original impact, respectively. These load transfer relationships are combined with the change gradient of the water quality parameters to generate a load response sequence. For example, when the influent COD increases at a rate of 35 mg / L / day, it is expected that the loads of the primary sedimentation tank, biological reactor, and secondary sedimentation tank will increase after 0.5 days, 1.5 days, and 2.5 days, respectively, and the relevant process parameters need to be adjusted accordingly.

[0082] The time points for coordinated adjustment of process parameters can be determined based on the load response sequence. For example, if the influent COD is detected to be increasing at a rate of 35 mg / L / day, it will be recommended to increase the sludge discharge from the primary sedimentation tank after 0.5 days, increase the aeration rate of the biological reactor after 1.2 days, and adjust the return ratio of the secondary sedimentation tank after 2.3 days. The precise determination of these coordinated adjustment time points enables sewage treatment plants to prepare for load changes in advance and pre-adjust process parameters, thereby reducing the impact of water quality fluctuations on effluent quality, while optimizing energy consumption and chemical usage, and reducing operating costs.

[0083] Practice has shown that the time points for the coordinated adjustment of process parameters determined by this method can reduce the fluctuation of effluent quality by about 25% compared with the traditional adjustment method based on experience or fixed time intervals, while reducing energy consumption by about 12% and the use of chemicals by about 15%, thereby significantly improving the stability and economy of sewage treatment.

[0084] In an optional embodiment, based on the parameter response characteristics, a load transfer relationship between each treatment unit of the sewage treatment process is extracted, the load transfer relationship is combined with the change gradient of the water quality parameter to generate a load response sequence, and the linkage adjustment time point of the process parameters is determined according to the load response sequence, including: determining a process parameter change trend curve between adjacent processing units based on the parameter response characteristics, determining an inflection point position of the process parameter change trend curve as a load transfer node, and obtaining an initial load transfer relationship based on a time interval of the load transfer node; Dividing the initial load transfer relationship into different transfer intervals according to the process flow of the processing unit, and calculating the parameter response time in each transfer interval; Determine a period during which the gradient of the water quality parameter change is greater than a first gradient threshold as a rapid response interval, and determine a period during which the gradient of the water quality parameter change is less than a second gradient threshold as a delayed response interval; Calculating the load accumulation rate in each of the transfer intervals according to the distribution characteristics of the fast response interval and the delayed response interval to generate a load response sequence; The load accumulation rate in the load response sequence is combined with the parameter response duration to determine the temporal correlation of process parameter adjustment, and the load mutation position and the load gradual change position are marked in the temporal correlation. The linkage adjustment time point of the process parameter is generated according to the load mutation position and the load gradual change position.

[0085] Online monitoring equipment can be used to collect process parameter data from each treatment unit in a wastewater treatment plant, including influent COD, NH3-N, TN, TP, pH, DO, and MLSS concentrations. The collected data is preprocessed, including outlier removal, data smoothing, and normalization. Time series analysis is then performed on the processed data to extract parameter response characteristics.

[0086] Based on the extracted parameter response characteristics, the process parameter change trend curves between adjacent treatment units are determined. For example, when the influent COD suddenly increases from 200 mg / L to 350 mg / L, the change curves of key parameters in the treatment units such as the anaerobic zone, anoxic zone, aerobic zone and secondary sedimentation tank are recorded. By analyzing these change trend curves, the inflection point position of the curve is determined as the load transfer node. Specifically, the sliding window method is used to calculate the first-order derivative and the second-order derivative. When the absolute value of the second-order derivative is greater than 0.15 and the sign of the first-order derivative changes, the point is marked as an inflection point. For example, in a certain example, the ORP value curve of the anaerobic zone has an inflection point 45 minutes after the influent COD increases, and the NH3-N concentration in the anoxic zone has an inflection point after 75 minutes. The time interval between the two inflection points is 30 minutes, which is the transfer time from the anaerobic zone to the anoxic zone in the initial load transfer relationship.

[0087] The obtained initial load transfer relationship is divided into different transfer intervals according to the process flow of the treatment unit. For example, in an A² / O process, the transfer intervals are divided into four: influent-anaerobic zone, anaerobic zone-anoxic zone, anoxic zone-aerobic zone, and aerobic zone-secondary clarifier. For each transfer interval, the parameter response time is calculated. The parameter response time is defined as the time from the start of the upstream unit parameter change to the stabilization of the downstream unit parameter. In actual cases, the parameter response time from influent-anaerobic zone is approximately 35 minutes, from anaerobic zone-anoxic zone is 45 minutes, from anoxic zone-aerobic zone is 60 minutes, and from aerobic zone-secondary clarifier is 90 minutes.

[0088] The gradient of water quality parameters can be analyzed. By calculating the parameter's rate of change per unit time, periods where the gradient exceeds a first gradient threshold are identified as rapid response intervals, while periods where the gradient is less than a second gradient threshold are identified as delayed response intervals. In practical applications, for the NH3-N parameter, a gradient greater than 0.1 mg / (L•min) is considered a rapid response interval, while a gradient less than 0.02 mg / (L•min) is considered a delayed response interval. For the DO parameter, a gradient greater than 0.05 mg / (L•min) is considered a rapid response interval, while a gradient less than 0.01 mg / (L•min) is considered a delayed response interval.

[0089] Based on the distribution characteristics of the rapid response interval and the delayed response interval, the load accumulation rate within each transfer interval is calculated to generate a load response sequence. The load accumulation rate represents the degree of load accumulation within the treatment unit per unit time. Within the anoxic-aerobic zone transfer interval, the load accumulation rate is calculated by counting the time proportions of the rapid response interval and the delayed response interval, combined with the magnitude of parameter change. For example, when the rapid response interval accounts for 40%, the delayed response interval accounts for 25%, and the average parameter change is 0.8 mg / L, the load accumulation rate within this transfer interval is 0.32 mg / (L·min).

[0090] The load accumulation rate in the load response sequence can be combined with the parameter response duration to determine the temporal correlation of process parameter adjustments. This temporal correlation reflects the temporal dependence of parameter adjustments between different processing units. On the load accumulation rate curve, thresholds are used to identify sudden and gradual load changes. When the load accumulation rate changes by more than 50% within a short period of time (e.g., within 15 minutes), it is marked as a sudden change. When the load accumulation rate changes slowly over a longer period of time (e.g., more than 60 minutes) with a rate of change of no more than 20%, it is marked as a gradual change.

[0091] Based on the marked load mutation position and gradual change position, the linkage adjustment time point of the process parameters is generated. At the mutation position, it is recommended to adjust the parameters in advance before the load is transferred to the downstream unit. The adjustment time point is the mutation position time minus 30% of the parameter response time. At the gradual change position, it is recommended to adjust the parameters synchronously during the load transfer process. The adjustment time point is the gradual change position time plus 10% of the parameter response time. For example, when a sudden change in influent COD is detected, it is recommended to adjust the stirring intensity of the anaerobic zone after 25 minutes, adjust the recirculation ratio of the anoxic zone after 62 minutes, and adjust the aeration volume of the aerobic zone after 108 minutes.

[0092] Through the above, the coordinated operation of various treatment units in the sewage treatment process can be achieved, the system's ability to cope with load shocks can be improved, energy consumption can be reduced, and treatment efficiency can be improved.

[0093] The sewage treatment operation cost optimization system based on big data in an embodiment of the present invention includes: The first unit is used to collect real-time operation data of the sewage treatment plant, calculate the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtain load-cost relationship data; The second unit is used to cross-map the sewage treatment load in the time dimension and the water quality change dimension based on the load-cost relationship data, and establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption; A third unit is configured to generate an operating cost curve of the sewage treatment system according to the corresponding relationship, and compare the operating cost curve with a preset cost threshold curve to obtain cost deviation data; A fourth unit is configured to generate a cost fluctuation curve based on the cost deviation data, and determine a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve; A fifth unit is configured to generate a process parameter adjustment instruction according to the linkage adjustment time point, and send the process parameter adjustment instruction to an execution end of the sewage treatment equipment; The sixth unit is used to receive the effluent water quality data returned by the execution end of the sewage treatment equipment, and record the corresponding process parameters when the effluent water quality data meets the discharge standard into the sewage treatment operation database.

[0094] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0095] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0096] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing sewage treatment operation costs based on big data, characterized in that: include: Collecting real-time operation data of the sewage treatment plant, calculating the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtaining load-cost relationship data; Based on the load-cost relationship data, the sewage treatment load is cross-mapped in the time dimension and the water quality change dimension to establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption; Generating an operating cost curve for the sewage treatment system according to the corresponding relationship, and comparing the operating cost curve with a preset cost threshold curve to obtain cost deviation data; generating a cost fluctuation curve based on the cost deviation data, and determining a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve; Generate a process parameter adjustment instruction according to the linkage adjustment time point, and send the process parameter adjustment instruction to the execution end of the sewage treatment equipment; Receive the effluent water quality data returned by the execution end of the sewage treatment equipment, and record the corresponding process parameters when the effluent water quality data meets the discharge standard in the sewage treatment operation database.

2. The method according to claim 1, characterized in that Collect real-time operation data of the sewage treatment plant, calculate the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtain load-cost relationship data, including: Collecting real-time operating data of the sewage treatment plant, extracting characteristic parameters of sewage treatment load based on the real-time operating data, and constructing a real-time curve of sewage treatment load; Segmenting the real-time curve of sewage treatment load in the time dimension to obtain a mapping relationship between time periods and load changes; Obtaining equipment operating parameters within the time period, calculating energy consumption, agent usage, and equipment operating time within the time period, and generating an operating cost calculation factor; Associating the operating cost calculation factor with the time period to obtain initial cost distribution data; Extracting change characteristic values ​​of sewage treatment load and operating cost based on the initial cost distribution data, and dividing the initial cost distribution data into a plurality of treatment intervals according to the change characteristic values; The average load value and the average cost value in each processing interval are calculated, and the average load value and the average cost value are associated and paired to obtain load-cost relationship data.

3. The method according to claim 1, characterized in that Based on the load-cost relationship data, the sewage treatment load is cross-mapped in the time dimension and the water quality change dimension to establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption, including: Generating time-scaled sequence distribution data based on the load-cost relationship data, and segmenting the sequence distribution data according to dynamic time windows to generate time slice data of the load cost; Acquire inlet water quality monitoring data for a period corresponding to the time slice data, and extract water quality change parameters from the inlet water quality monitoring data to obtain a water quality fluctuation characteristic curve; Dividing the water quality fluctuation characteristic curve into multiple fluctuation intervals, calculating the coordinated change characteristic value of the water quality parameters in each interval, and compensating the water quality characteristics at the interval boundary according to the difference value of the coordinated change characteristic value of adjacent intervals to generate a water quality fluctuation characteristic curve; Reconstructing the time slice data and the water quality fluctuation characteristic curve to generate a two-dimensional characteristic matrix; Determining a two-layer recursive mapping structure based on the two-dimensional feature matrix, determining a fluctuation compensation threshold in the two-layer recursive mapping structure, and processing the two-dimensional feature matrix according to the fluctuation compensation threshold to generate multi-dimensional mapping data; A corresponding relationship between sewage treatment load and comprehensive resource consumption is established based on the multi-dimensional mapping data.

4. The method according to claim 3, characterized in that Determining a two-layer recursive mapping structure based on the two-dimensional feature matrix, determining a fluctuation compensation threshold in the two-layer recursive mapping structure, and processing the two-dimensional feature matrix according to the fluctuation compensation threshold to generate multi-dimensional mapping data, including: Extracting time series fluctuation characteristics of load data and cost data based on the two-dimensional feature matrix, and calculating the change gradients of the load data and the cost data in different time segments; Dividing the change gradients of the different time periods into different fluctuation intervals according to the fluctuation intensity, and calculating the correlation coefficient between the load data and the cost data in each of the fluctuation intervals; Determining the data correlation degree of each fluctuation interval according to the correlation coefficient, and using the data correlation degree as a weight coefficient to determine a two-layer recursive mapping structure of the load data and the cost data; In the double-layer recursive mapping structure, a fluctuation compensation threshold is determined based on the correlation coefficient and the weight coefficient, and the fluctuation compensation threshold is used to characterize the data conversion intensity between different fluctuation intervals; According to the fluctuation compensation threshold, the load data and cost data in the two-dimensional feature matrix are recursively mapped and calculated in different regions. At the boundary positions of adjacent fluctuation intervals, data smoothing transition processing is performed based on the weight coefficient. A mapping correction coefficient is obtained based on the weight coefficient and the fluctuation compensation threshold. According to the mapping correction coefficient, the load and cost data are adjusted in different regions to generate multi-dimensional mapping data.

5. The method according to claim 1, wherein Generating an operating cost curve for the sewage treatment system according to the corresponding relationship, and comparing the operating cost curve with a preset cost threshold curve to obtain cost deviation data, including: Connecting the operating cost data of the sewage treatment system at different time points according to the corresponding relationship to form an operating cost curve, and calculating the operating cost curve to determine the operating cost fluctuation characteristic points; Dividing the operating cost curve into different cost intervals based on the operating cost fluctuation characteristic points, and calculating the data dispersion within each cost interval; Extracting a cost data sequence under a target operating condition from historical operating data, connecting the cost data sequence to generate a preset cost threshold curve, and setting a fluctuation tolerance range for the preset cost threshold curve based on the data dispersion; An initial deviation value is obtained based on the operating cost curve and the preset cost threshold curve, a time period is divided into a stable period and a fluctuating period according to the initial deviation value, an overlap between the cost data in the fluctuating period and the fluctuation tolerance range is calculated, and a fluctuation period weight coefficient is generated; The data association strength between adjacent time periods is calculated based on the fluctuation segment weight coefficient, and the cost data in the fluctuation segment is processed according to the data association strength and the initial deviation value to obtain cost deviation data.

6. The method according to claim 1, characterized in that Generating a cost fluctuation curve based on the cost deviation data, and determining a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve, including: Determining positive deviation values ​​and negative deviation values ​​in the cost deviation data, and connecting the positive deviation values ​​and the negative deviation values ​​in chronological order to generate a cost fluctuation curve; Extracting inflection point data from the cost fluctuation curve, calculating a slope change trend of the inflection point data, and determining candidate peak points and candidate trough points based on the slope change trend; Calculating the fluctuation period and fluctuation amplitude between adjacent candidate peak points and candidate trough points, and screening out fluctuation characteristic points according to the fluctuation period and fluctuation amplitude; Extracting water quality parameters and process parameters in the interval before and after the fluctuation characteristic point, and calculating the change gradient of the water quality parameters; Dividing the change gradient of the water quality parameter into different change intervals according to the intensity, and calculating the parameter response characteristics in different change intervals respectively; The load transfer relationship between the treatment units of the sewage treatment process is extracted based on the parameter response characteristics, the load transfer relationship is combined with the change gradient of the water quality parameters to generate a load response sequence, and the linkage adjustment time point of the process parameters is determined according to the load response sequence.

7. The method according to claim 6, characterized in that Extracting the load transfer relationship between the treatment units of the sewage treatment process based on the parameter response characteristics, combining the load transfer relationship with the change gradient of the water quality parameter to generate a load response sequence, and determining the linkage adjustment time point of the process parameters according to the load response sequence, including: determining a process parameter change trend curve between adjacent processing units based on the parameter response characteristics, determining an inflection point position of the process parameter change trend curve as a load transfer node, and obtaining an initial load transfer relationship based on a time interval of the load transfer node; Dividing the initial load transfer relationship into different transfer intervals according to the process flow of the processing unit, and calculating the parameter response time in each transfer interval; Determine a period during which the gradient of the water quality parameter change is greater than a first gradient threshold as a rapid response interval, and determine a period during which the gradient of the water quality parameter change is less than a second gradient threshold as a delayed response interval; Calculating the load accumulation rate within each of the transfer intervals according to the distribution characteristics of the fast response intervals and the delayed response intervals to generate a load response sequence; The load accumulation rate in the load response sequence is combined with the parameter response duration to determine the temporal correlation of process parameter adjustment, and the load mutation position and the load gradual change position are marked in the temporal correlation. The linkage adjustment time point of the process parameter is generated according to the load mutation position and the load gradual change position.

8. A sewage treatment operation cost optimization system based on big data, used to implement the method according to any one of claims 1 to 7, characterized in that: include: The first unit is used to collect real-time operation data of the sewage treatment plant, calculate the treatment cost of the real-time operation data in sections according to the sewage treatment load, and obtain load-cost relationship data; The second unit is used to cross-map the sewage treatment load in the time dimension and the water quality change dimension based on the load-cost relationship data, and establish a corresponding relationship between the sewage treatment load and the comprehensive resource consumption; A third unit is configured to generate an operating cost curve of the sewage treatment system according to the corresponding relationship, and compare the operating cost curve with a preset cost threshold curve to obtain cost deviation data; A fourth unit is configured to generate a cost fluctuation curve based on the cost deviation data, and determine a linkage adjustment time point for process parameters according to peak and trough characteristic points of the cost fluctuation curve; A fifth unit is configured to generate a process parameter adjustment instruction according to the linkage adjustment time point, and send the process parameter adjustment instruction to an execution end of the sewage treatment equipment; The sixth unit is used to receive the effluent water quality data returned by the execution end of the sewage treatment equipment, and record the corresponding process parameters when the effluent water quality data meets the discharge standard into the sewage treatment operation database.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Intelligent control method and control system for sewage treatment based on Internet of Things

    CN121721952A