Intelligent supervision and control system for steam recompression mother liquor wastewater treatment

Abstract

The invention discloses an intelligent supervision and regulation system for steam recompression mother liquor wastewater treatment, which relates to the technical field of production monitoring and is characterized in that a plurality of water quality parameters are monitored and analyzed in real time by integrating a water quality monitoring module, a data fusion module, a flow monitoring module, a control center, an automatic regulation module and a feedback control module; the data fusion module uses a machine learning algorithm to train historical data and performs abnormity prediction and water quality fluctuation identification based on real-time data, the control center combines flow and water quality prediction data to calculate the adjustment demand of the wastewater treatment equipment and generate an adjustment instruction, and the automatic adjustment module dynamically optimizes the operation state of the equipment according to the instruction. The feedback control module compares the real-time water quality data with the adjusted water quality, generates a feedback signal and further optimizes an adjustment instruction, so that the accuracy and stability of equipment adjustment in the wastewater treatment process are ensured, deposition or volatilization of heavy metals or organic compounds is effectively prevented, the water quality is ensured to reach the standard, and the environmental influence is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of production monitoring, and particularly relates to an intelligent supervision and regulation system for steam recompression mother liquor wastewater treatment. Background Art

[0002] Intelligent supervision and regulation of steam recompression mother liquor wastewater treatment refers to a management method in which, during the treatment process of mother liquor wastewater generated in the steam recompression process, intelligent technologies are used to conduct real-time monitoring, data analysis, and automatic adjustment of the wastewater treatment. Through an intelligent system, such as sensors, automatic control, and a data analysis platform, the water quality parameters of the wastewater (such as pH value, temperature, chemical oxygen demand, etc.) can be monitored in real time, and the operating status of the wastewater treatment equipment can be automatically adjusted according to the data to ensure that the wastewater meets the discharge standards or is reused.

[0003] The existing technologies have the following deficiencies:

[0004] In the wastewater treatment of chemical plants, the wastewater may contain a large amount of heavy metal ions, volatile organic compounds (VOCs), and other components, and these components will cause water quality fluctuations with the change of flow rate. If the system only adjusts the equipment according to the change of flow rate and ignores the changes of these complex components in the wastewater, it may lead to insufficient or excessive adjustment of the equipment, thus failing to ensure that the water quality meets the standards. Heavy metal ions or organic compounds may deposit or volatilize during the treatment process, affecting the environment. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent supervision and regulation system for steam recompression mother liquor wastewater treatment to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An intelligent supervision and regulation system for steam recompression mother liquor wastewater treatment, including a water quality monitoring module, a data fusion module, a flow rate monitoring module, a control center, an automatic adjustment module, and a feedback control module;

[0007] The water quality monitoring module is used to monitor multiple water quality data in the wastewater in real time, including chemical oxygen demand, dissolved oxygen, pH value, temperature, and heavy metal concentration;

[0008] The data fusion module is used to perform fusion processing on the water quality data, and use machine learning algorithms to train the historical water quality data and conduct anomaly prediction based on real-time data;

[0009] The flow rate monitoring module is used to monitor the wastewater flow rate in real time and transmit the flow rate data to the control center;

[0010] The control center is used to calculate the adjustment requirements of the wastewater treatment equipment through a preset algorithm based on the water quality anomaly prediction data and the flow rate data, and generate adjustment instructions;

[0011] An automatic adjustment module that performs automatic adjustment by executing adjustment instructions, including dynamically adjusting the working state of the treatment equipment according to the change in wastewater flow rate and the prediction result of water quality data;

[0012] A feedback control module that generates a feedback signal by comparing real-time water quality data with the adjusted water quality to further optimize the adjustment instructions.

[0013] Preferably, the sensors used in the water quality monitoring module include: a photometric sensor, an electrochemical sensor, and a temperature sensor.

[0014] Preferably, the data fusion module receives real-time data from the water quality monitoring module, performs time synchronization and standardization processing on the data of different sensors, uses Kalman filtering technology to denoise the water quality data, fuses the signals of each sensor, applies the weighted average method to assign weights to the data of each sensor, introduces a machine learning algorithm to train the historical water quality data, and extracts abnormal features of water quality changes, including water quality parameter change rate features and water quality parameter fluctuation period features.

[0015] Preferably, a water quality change rate anomaly score is generated according to the water quality parameter change rate feature. The generation method is as follows: collect and organize the required water quality parameters, set the measured value of each water quality parameter at time t as x(t). The change rate of the water quality parameter refers to the degree of change of the water quality parameter value per unit time. Set the historical change rate of a certain water quality parameter as , calculate its mean and standard deviation, and calculate the standardized change rate at the current moment as the water quality change rate anomaly score.

[0016] Preferably, a water quality periodic fluctuation score is generated according to the water quality parameter fluctuation period feature. The generation method is as follows: preprocess the original water quality data and present it in the form of a time series. Decompose the water quality time series signal into multiple intrinsic mode functions IMF through empirical mode decomposition. Each IMF represents a fluctuation component of a different frequency. Apply the Hilbert transform to each IMF to calculate its instantaneous amplitude and instantaneous frequency. For each IMF, calculate the standard deviation of its instantaneous frequency and the average value of its instantaneous amplitude. Calculate the ratio of the standard deviation of the instantaneous frequency of each IMF to the average value of the instantaneous amplitude as the water quality periodic fluctuation score of each IMF. Since the water quality fluctuation is jointly affected by multiple IMF components, weight the periodic fluctuation scores of each IMF and average them to obtain the comprehensive water quality periodic fluctuation score.

[0017] Preferably, the control center receives the water quality change rate anomaly score, the water quality periodic fluctuation score, and the flow data, and uses them as input items for fuzzy logic reasoning;

[0018] Take the adjustment requirements of the wastewater treatment equipment as the output items of fuzzy logic;

[0019] Convert the input data into fuzzy sets and construct a fuzzy rule base to describe the fuzzy relationship between the input and the output;

[0020] Use the fuzzy inference method to perform inference based on the fuzzy values of the input items and the rule base, and obtain the fuzzy values of each output item;

[0021] For each rule, match the fuzzy value of the input with the conditions in the rule base and obtain a fuzzy output. During the inference process, the inference results of each rule will be weighted according to the matching degree between the input fuzzy value and the rule;

[0022] The result obtained after inference is a fuzzy result, which needs to be converted into a clear adjustment requirement value through the defuzzification process; perform a weighted average on the output values of all rules to obtain the final output value, that is, the specific adjustment intensity required by the wastewater treatment equipment;

[0023] The control center generates specific adjustment instructions according to the calculated adjustment requirements.

[0024] Preferably, the automatic adjustment module receives adjustment instructions from the control center, analyzes the instruction content, and adjusts the working states of the reaction tank, aeration system, sedimentation tank, and dosing equipment in real time.

[0025] Preferably, the feedback control module collects the water quality data in the wastewater in real time and compares it with the adjusted water quality, calculates the deviation value, and generates a feedback signal according to the deviation value between the water quality data and the target value, including when the error is greater than the set threshold, at this time, increase the adjustment intensity; when the error is less than or equal to the set threshold, at this time, reduce the adjustment intensity or stop the adjustment operation.

[0026] In the above technical solution, the technical effects and advantages provided by the present invention:

[0027] 1. By integrating a water quality monitoring module, a data fusion module, a flow monitoring module, a control center, an automatic adjustment module, and a feedback control module, the system of the present invention can monitor multiple water quality parameters (such as COD, DO, pH value, temperature, heavy metal concentration, etc.) in the wastewater in real time, and combine the characteristics of the water quality parameter change rate and the fluctuation period characteristics, and accurately predict the water quality change through machine learning and fuzzy logic inference to realize dynamic adjustment of the working state of the equipment. This system not only optimizes the adjustment requirements of the wastewater treatment equipment, but also effectively avoids the problems of over-adjustment or under-adjustment caused by ignoring water quality fluctuations, ensuring the stable and efficient operation of the wastewater treatment process.

[0028] 2. The intelligent supervision and regulation system of the present invention enables the equipment adjustment to have higher flexibility and accuracy through the collection and fusion analysis of real-time data and in combination with the adaptive control algorithm. The feedback control module generates a feedback signal and optimizes the adjustment strategy by comparing with the adjusted water quality data, thereby realizing the adaptive optimization of the system. The application of this system effectively reduces the risk of deposition or volatilization of harmful components in the wastewater, improves the environmental protection effect of wastewater treatment, ensures that the treated water quality meets the expected standards, and significantly enhances the automation and intelligent level of the wastewater treatment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0030] Figure 1 It is the system mind map of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] Embodiment, please refer to Figure 1 As shown, an intelligent supervision and regulation system for steam recompression mother liquor wastewater treatment in this embodiment includes a water quality monitoring module, a data fusion module, a flow rate monitoring module, a control center, an automatic adjustment module, and a feedback control module;

[0033] The water quality monitoring module is used to monitor multiple water quality data in the wastewater in real time, including chemical oxygen demand, dissolved oxygen, pH value, temperature, and heavy metal concentration;

[0034] The data fusion module is used to perform fusion processing on the water quality data, train the historical water quality data using machine learning algorithms, and perform anomaly prediction based on real-time data;

[0035] The flow rate monitoring module is used to monitor the wastewater flow rate in real time and transmit the flow rate data to the control center;

[0036] The control center is used to calculate the adjustment requirements of the wastewater treatment equipment through a preset algorithm based on the water quality anomaly prediction data and the flow rate data, and generate an adjustment instruction;

[0037] An automatic adjustment module that performs automatic adjustment by executing adjustment instructions, including dynamically adjusting the working state of the treatment equipment according to the change in wastewater flow rate and the prediction result of water quality data;

[0038] A feedback control module that generates a feedback signal by comparing the real-time water quality data with the adjusted water quality to further optimize the adjustment instructions.

[0039] The water quality monitoring module needs to monitor the following key water quality parameters in the wastewater in real time:

[0040] Chemical Oxygen Demand (COD): Chemical Oxygen Demand (COD) reflects the content of organic matter in the wastewater and is an important indicator for measuring the degree of wastewater pollution. The higher the COD value, the higher the content of organic matter in the wastewater and the greater the treatment difficulty. COD sensors generally use photometric method, chemical analysis method or electrochemistry method to measure.

[0041] Dissolved Oxygen (DO): Dissolved oxygen is an important indicator of the water body's self-purification ability and affects the microbial activities in the wastewater treatment process, especially in the biological treatment stage. DO sensors usually work based on electrochemical principles (such as polarography or amperometry), and measure the DO value through the relationship between current and dissolved oxygen concentration.

[0042] pH value: The pH value indicates the acidity and alkalinity of the wastewater and affects many chemical reactions and biodegradation processes. pH sensors use the glass electrode principle to be able to detect the acidity and alkalinity of the water sample in real time and provide a voltage signal related to the hydrogen ion concentration.

[0043] Temperature: Temperature is a very important parameter in wastewater treatment. Temperature changes will affect the rate of chemical reactions and the metabolic activities of microorganisms. Temperature sensors usually use thermocouple or thermistor technology to measure the wastewater temperature and provide real-time feedback on the impact of ambient temperature changes on the treatment process.

[0044] Heavy metal concentration: Heavy metals (such as lead, cadmium, chromium, mercury, etc.) are common pollutants in industrial wastewater. Exceeding the standard concentration will seriously endanger the environment and ecological system. Heavy metal sensors usually use electrochemistry analysis method (such as voltammetry or potentiometry) or spectroscopy analysis method (such as atomic absorption spectroscopy) to measure the concentration of various heavy metal ions in water.

[0045] In order to comprehensively and accurately monitor multiple water quality parameters in the wastewater, the water quality monitoring module uses at least two different types of sensors. These sensors include:

[0046] Photometric sensor: Used to measure the concentration of COD and certain heavy metal ions. The photometric sensor estimates the concentration of dissolved substances by emitting a light beam and measuring the amount of light absorbed by the wastewater sample. This sensor has high sensitivity and accuracy, and is especially suitable for measuring colored or dissolved substances.

[0047] Electrochemical sensor: Used to measure the concentration of DO, pH value and certain heavy metal ions. The electrochemical sensor measures water quality indicators by forming an electric current or potential difference between the electrode and the water sample. For example, the DO sensor is based on the polarographic method principle, and the pH sensor is based on the glass electrode principle. The electrochemical sensor has the characteristics of fast response speed and low maintenance cost, and is suitable for long-term online monitoring.

[0048] Temperature sensor: Generally, thermocouples or thermistors (NTC) are used to measure the temperature of wastewater. The thermocouple estimates the temperature by measuring the voltage change at the junction of two different metals, while the thermistor measures based on the characteristic that the resistance changes with temperature.

[0049] Each sensor transmits the real-time collected water quality data to the data fusion module. The specific steps are as follows:

[0050] Data acquisition: The water quality monitoring module simultaneously acquires data through various sensors to ensure that multiple parameters can be obtained in real-time synchronization. These sensors use digital output methods to transmit data to the central processing unit to ensure the accuracy and reliability of the data.

[0051] Data conversion and filtering: The data from the sensors usually needs to be preliminarily converted and filtered to remove noise and interference. For data such as COD and DO, digital filtering techniques are used to process the signals to ensure that the collected values are stable and accurate.

[0052] Data fusion and synchronization: The values from multiple sensors need to be fused through Kalman filtering or weighted averaging methods to ensure the accuracy of the data for each water quality parameter. These fused data will serve as the basis for further analysis and device adjustment.

[0053] The sensors in the water quality monitoring module transmit the collected data to the data fusion module or the central control system through wireless or wired communication protocols (such as Modbus, RS485, LoRa, NB-IoT, etc.). These data are monitored and processed in real-time to make adjustment decisions in a timely manner.

[0054] Wireless communication: For areas far from the control center or with poor environmental conditions, wireless transmission technologies (such as LoRa, NB-IoT) can be used for long-distance data transmission to ensure that the system can be monitored over a large area.

[0055] Wired communication: For areas with high requirements for data transmission reliability, the Modbus or RS485 protocol is used for data transmission to ensure the stability and reliability of the system.

[0056] In this application, the water quality monitoring module uses different types of sensors (such as electrochemical sensors, photometric sensors, and temperature sensors) to monitor multiple water quality parameters in wastewater in real time, such as COD, DO, pH value, temperature, heavy metal concentration, etc., and ensures the accuracy of the data through data fusion technology. The data is transmitted to the central control system through wireless or wired communication protocols to support real-time monitoring and intelligent regulation, ensuring the efficiency and stability during the wastewater treatment process.

[0057] The data fusion module adopts multi-sensor data fusion technology, which optimizes the accuracy and reliability of water quality data through the following steps:

[0058] Data synchronization and standardization: First, the data from different sensors is synchronized in time to ensure that the output data of different sensors can be compared and processed at the same time point. Then, data standardization processing is carried out to eliminate the dimensional differences between different sensors, enabling the data to be effectively fused.

[0059] Kalman filtering: Kalman filtering technology is widely used in the fusion process of real-time data. This algorithm estimates the current state and updates the state variables of the system by combining the dynamic model of the system and sensor data. Through Kalman filtering, the system can weight the data of different sensors, eliminate noise, and obtain more accurate water quality parameters.

[0060] Weighted average method: For multi-source data fusion, the weighted average method is adopted, assigning different weights to the signals of different sensors. The weight allocation is based on the accuracy, reliability of the sensors, and the current environmental conditions. The weighted average method can integrate the advantages of each sensor and improve the overall data accuracy.

[0061] Time series data fusion: For time series data, the data fusion module uses time series analysis methods (such as weighted moving average method, exponential smoothing method, etc.) to smooth the data fluctuations and extract effective signals. This is particularly important for parameters in water quality that change rapidly (such as DO, pH, etc.), and can eliminate the impact of instantaneous fluctuations on system decision-making in real time.

[0062] The data fusion module enhances the adaptability of the wastewater treatment system to complex water quality changes by introducing machine learning (ML) algorithms. The specific steps are as follows:

[0063] Historical data training: First, use the historical water quality data in the wastewater treatment process to train the machine learning model. The historical data includes water quality indicators (such as COD, DO, pH, etc.), equipment operation parameters, wastewater flow rate, and abnormal event data (such as sudden water quality changes, equipment failures, etc.). Through data preprocessing, feature extraction and selection, the machine learning model can learn the laws and potential relationships of water quality changes.

[0064] Feature extraction and selection: The machine learning model is trained by extracting key features from the data, including using the change rate features of water quality parameters and the fluctuation period features of water quality parameters. Based on these features, the model can better capture the patterns of water quality changes and identify the omens of water quality anomalies.

[0065] Abnormal prediction: Using the trained machine learning model, the data fusion module can perform water quality anomaly prediction based on real-time data. The model predicts the water quality changes in the short term in the future through the real-time input water quality parameters, identifies possible abnormal situations (such as a sharp increase in COD value, a decrease in DO value, etc.), and issues early warnings through abnormal prediction to avoid excessive emissions in the wastewater treatment system.

[0066] The change rate feature of water quality parameters refers to the change amplitude of water quality parameters (such as COD, DO, pH, etc.) within a unit time. This feature can reveal sudden changes or abnormal fluctuations in water quality and is an important indicator for detecting abnormal changes in the wastewater treatment process. Especially in the treatment of vapor recompression mother liquor wastewater, water quality parameters may be affected by sudden changes in pollution sources or equipment failures, resulting in rapid parameter changes. The change rate feature can quickly capture this change and issue a warning.

[0067] The intelligent supervision and regulation system for vapor recompression mother liquor wastewater treatment of the present invention can timely detect sharp changes in wastewater flow rate and water quality by obtaining the change rate feature of water quality parameters in real time, thereby triggering the adjustment mechanism and avoiding abnormal emissions or efficiency reduction caused by the wastewater treatment system's failure to respond to sudden water quality changes in a timely manner. This feature is crucial for the intelligent warning and adjustment of the system, especially in improving the treatment efficiency and stability when dealing with complex water quality.

[0068] Generate a water quality change rate anomaly score according to the change rate feature of water quality parameters. The generation method is as follows:

[0069] Collect and organize the required water quality parameters, including data such as COD, DO, pH, etc. Usually, these data are collected in real time by sensors at different time points. Set the measured value of each water quality parameter at time t as x(t). Clean the original data to remove noise and outliers to ensure the accuracy of the data. It may be necessary to interpolate or smooth the data to eliminate the impact of instantaneous fluctuations on the results.

[0070] The change rate of water quality parameters refers to the degree of change in the value of water quality parameters per unit time. Assuming that the water quality parameter x(t) is the value at time t and x(t−1) is the value at time t−1, the change rate R(t) can be defined as: where: R(t) is the water quality change rate, the change rate at time t, x(t) is the value of the water quality parameter at time t (such as COD, DO, pH, etc.). x(t−1) is the value of the water quality parameter at time t−1. Δt is the time interval (usually 1 hour or minute, specifically determined according to the sampling frequency).

[0071] The change rate itself is the degree of change in water quality parameters. If the change rate at a certain moment is too large, it may mean that the water quality has changed abnormally. In order to quantify the abnormal degree of water quality change, the present invention can adopt a standardization method to compare the change rate with the normal range of historical data.

[0072] The standardized change rate can define a threshold range by calculating the mean and standard deviation of historical data. Assuming that the historical change rate of a certain water quality parameter is , calculate its mean and standard deviation , and calculate the standardized change rate at the current moment as the abnormal score of the water quality change rate. The expression is: .

[0073] A threshold Zthreshold can be set. When exceeds this threshold, it is considered that the water quality change is abnormal. Abnormal identification:

[0074] If >Zthreshold, it is considered that the water quality change at the current moment t is abnormal and a warning is triggered.

[0075] If ≤Zthreshold, it is considered that the water quality change is within the normal range and no warning needs to be triggered.

[0076] The periodic fluctuation characteristics of water quality parameters refer to the regular fluctuations of certain indicators (such as DO, COD, etc.) in wastewater during the wastewater treatment process. For example, the value of dissolved oxygen (DO) in wastewater will show periodic rises and falls during the aeration stage. This periodic change is usually caused by the normal operation of the treatment process or equipment. However, if the periodic pattern of water quality deviates, it may indicate equipment failure or water quality abnormality.

[0077] In the intelligent supervision and regulation system of the present invention, by monitoring the periodic changes of water quality parameters in wastewater, it is possible to determine whether there are fluctuations that do not conform to normal operations. If the periodic fluctuations are abnormal (such as a change in the fluctuation frequency of the DO concentration or an abnormal amplitude of the periodic fluctuation of COD), the system can predict potential equipment failures or pollutant fluctuations based on the abnormal periodic changes, and thus take corresponding measures in advance to adjust equipment parameters or optimize the treatment process. This feature plays an important role in the intelligent system's prediction and response to complex water quality changes, especially in the process of treating steam recompression mother liquor wastewater.

[0078] Generate a water quality periodic fluctuation score based on the fluctuation period characteristics of water quality parameters. The generation method is as follows:

[0079] Preprocess the original water quality data to remove noise and outliers. Water quality data is usually presented in the form of a time series, such as the time-varying data of parameters such as COD, DO, and pH. The preprocessing process includes denoising, smoothing, filling missing values, etc., to ensure the accuracy and continuity of the data.

[0080] Decompose the water quality time series signal into multiple intrinsic mode functions IMF through empirical mode decomposition. Each IMF represents a fluctuation component with a different frequency. The expression is: ; where y(t) is the original water quality time series, is the i-th intrinsic mode function IMF, r(t) is the residual term, usually representing the trend term, is the total number of intrinsic mode functions IMF; Apply the Hilbert transform to each IMF. The expression is: ; where, is the Hilbert transform of the IMF, obtaining the orthogonal part of the signal, and j is the imaginary unit. Calculate its instantaneous amplitude and instantaneous frequency. The instantaneous amplitude represents the fluctuation intensity, ; The instantaneous frequency represents the periodicity of the fluctuation, ; where arg represents the phase angle of the complex number.

[0081] For each IMF, calculate the standard deviation of its instantaneous frequency to represent the stability of the frequency fluctuation; calculate the average value of the instantaneous amplitude to represent the intensity of the fluctuation. Calculate the ratio of the standard deviation of the instantaneous frequency of each IMF to the average value of the instantaneous amplitude as the water quality periodic fluctuation score of each IMF. Since the water quality fluctuation is jointly affected by multiple IMF components, the periodic fluctuation scores of each IMF can be weighted and averaged to obtain a comprehensive water quality periodic fluctuation score, representing the overall periodic fluctuation degree of the water quality.

[0082] The main function of the flow monitoring module is to measure the wastewater flow rate in real time and ensure the high accuracy and reliability of the data. These flow data are not only used to judge the influent and effluent volumes of the wastewater, but also for evaluating the working load of the wastewater treatment equipment, adjusting the treatment capacity, and optimizing the operation efficiency of the system.

[0083] The flow monitoring module usually consists of a set of dedicated sensors and measuring devices for collecting wastewater flow data. Common flow measurement techniques include:

[0084] Electromagnetic flowmeter: The electromagnetic flowmeter works based on Faraday's law of electromagnetic induction. When the fluid passes through the flowmeter, the flow of the fluid generates a voltage in the conductive fluid. The electromagnetic flowmeter calculates the flow rate by measuring the voltage. It is suitable for measuring conductive fluids (such as wastewater), has high accuracy, and is less affected by factors such as the temperature and pressure of the fluid. It is widely used for measuring wastewater flow rates, especially when the water contains suspended solids, sediment, and other particulate matter.

[0085] Ultrasonic flowmeter: The ultrasonic flowmeter calculates the flow rate by sending and receiving ultrasonic signals and using the propagation speed of the waves. It is divided into time-difference type and frequency-difference type, and the time-difference type is suitable for non-contact measurement. It is suitable for non-contact measurement, is not affected by the physical properties of the fluid such as conductivity and density, and is suitable for measuring the flow rates of various wastewaters, especially in situations where it has no impact on the pipeline.

[0086] Vortex flowmeter: The vortex flowmeter measures the flow rate by using the vortex street effect generated when the fluid flows through an obstacle. The frequency of the vortex street is proportional to the flow velocity. It has no moving parts and is suitable for measuring the flow rates of high-viscosity liquids, gases, and steam. It is suitable for flow monitoring in wastewater treatment, especially when treating wastewater with solid particles.

[0087] The flow sensor collects the flow data in real time and records the flow values at regular time intervals (such as every second or every minute). These data are usually sent to the data acquisition system through the analog or digital output port of the sensor.

[0088] The original flow data may contain noise, interference, or sensor errors, so preprocessing operations such as filtering, smoothing, and denoising are required to ensure the accuracy and stability of the data.

[0089] The flow monitoring module transmits the collected flow data to the control center through a communication network. The data transmission method can be selected according to actual needs:

[0090] Wired transmission protocol: Common wired communication protocols include Modbus, RS485, Ethernet, etc. The data transmission is stable and reliable, and is suitable for industrial environments with long-term operation.

[0091] Wireless Transmission: Wireless communication technologies such as LoRa, NB-IoT, Wi-Fi, etc. are widely used in the remote transmission of traffic data. It is easy to install and is especially suitable for areas far from the central control system. Wireless traffic transmission can reduce wiring costs and improve system flexibility.

[0092] The real-time and reliability of data transmission are very important. It is necessary to ensure that data will not be lost during the transmission process, and the transmission delay should be minimized as much as possible in order to adjust the working state of the processing equipment in real time.

[0093] The traffic data collected and transmitted is sent to the control center or cloud platform. The control center can receive the traffic data in real time and store it in the database. The control center can display the traffic data through the SCADA system, monitoring software or cloud platform.

[0094] The control center can analyze the changing trend of water quality flow in real time. By combining with water quality monitoring data, it can judge the load situation of the wastewater treatment equipment. If the flow exceeds the set threshold, the system will issue an alarm, indicating that the processing capacity of the processing equipment needs to be adjusted to prevent insufficient processing capacity or overload.

[0095] The flow monitoring module provides real-time flow data for the wastewater treatment system, helping the operators to monitor the inflow and outflow of wastewater and understand the operating status of the treatment process. The flow data provides key information for the wastewater treatment equipment. When the flow changes drastically (such as a sudden increase or decrease), the system will automatically adjust the operating status of the reaction tank, aeration equipment, filtration equipment, etc. to ensure the stability and efficiency of the wastewater treatment process.

[0096] If abnormal flow is detected (such as overload or stagnation), the system will automatically send an alarm notification to prompt the operator to take corresponding measures to avoid failures of the wastewater treatment facilities or excessive pollutant emissions.

[0097] The flow monitoring module records the flow data, providing a basis for daily management, facilitating the operators and managers to generate periodic reports and helping to make long-term decisions.

[0098] The control center will first receive the following three types of input data:

[0099] Abnormal Score of Water Quality Change Rate: The abnormal score of water quality change rate calculated through the aforementioned steps (based on the standardized value of water quality change rate), which is used to represent the degree of drastic change in water quality.

[0100] Water Quality Periodic Fluctuation Score: The water quality periodic fluctuation score obtained through Hilbert-Huang Transform (HHT), which reflects whether there are obvious periodic fluctuations in water quality.

[0101] Flow data: The flow data of wastewater reflects the speed and volume of wastewater inflow or outflow, directly affecting the load of wastewater treatment equipment.

[0102] These data will be used as input items for fuzzy logic reasoning. They represent the degree of abnormality of water quality changes, the stability of periodic fluctuations, and the magnitude of wastewater flow respectively.

[0103] In a fuzzy logic system, it is first necessary to convert the input data into fuzzy sets. This process is called fuzzification.

[0104] Fuzzification of the abnormal score of water quality change rate: According to the range of the score value, it is converted into a fuzzy set. For example, if the score is high, it indicates a large abnormality, and it can be divided into "high abnormality", "medium abnormality" or "low abnormality".

[0105] Fuzzification of the water quality periodic fluctuation score: Similarly, by setting the threshold range of the score, it is fuzzified into fuzzy sets such as "high fluctuation", "medium fluctuation" or "low fluctuation".

[0106] Fuzzification of flow data: According to the magnitude of the wastewater flow, fuzzy sets of flow can be set, such as "high flow", "medium flow" and "low flow". The fuzzification of flow data is carried out according to the numerical magnitude of the flow and the standard of historical data.

[0107] The core of the fuzzy logic control system is the rule base, which is designed based on expert experience or historical data. Each rule describes the fuzzy relationship between the input and the output. For example:

[0108] If the abnormal score of water quality change rate is "high abnormality", and the water quality periodic fluctuation score is "low fluctuation", and the flow is "high flow", then the adjustment requirement of the wastewater treatment equipment may be "high adjustment".

[0109] If the abnormal score of water quality change rate is "low abnormality", and the water quality periodic fluctuation score is "high fluctuation", and the flow is "medium flow", then the adjustment requirement of the wastewater treatment equipment is "medium adjustment".

[0110] If the abnormal score of water quality change rate is "medium abnormality", and the water quality periodic fluctuation score is "medium fluctuation", and the flow is "low flow", then the adjustment requirement of the wastewater treatment equipment is "low adjustment".

[0111] These rules will be continuously adjusted according to the actual application requirements to ensure that reasonable adjustment instructions can be generated according to different situations.

[0112] Using fuzzy inference methods (such as Mamdani inference method), reasoning is carried out according to the fuzzy values of the input items and the rule base to obtain the fuzzy values of each output item.

[0113] For each rule, the input fuzzy values are matched with the conditions in the rule base, and a fuzzy output is obtained. For example, in the rule base, there may be a rule like "If the water quality change rate is 'high anomaly' and the flow rate is 'high flow rate', then the adjustment requirement is 'high adjustment'". When the actual water quality change rate score is 'high anomaly' and the flow rate is 'high flow rate', the rule is triggered and gives a fuzzy output of 'high adjustment'.

[0114] During the reasoning process, the reasoning results of each rule are weighted according to the matching degree between the input fuzzy values and the rules.

[0115] The result obtained after reasoning is a fuzzy result, which needs to be converted into a clear adjustment requirement value through a defuzzification process. Common defuzzification methods include the Centroid Method.

[0116] The output values of all rules are weighted and averaged to obtain the final clear output value. For example, if the output probability of 'high adjustment' is 0.8, the output probability of'medium adjustment' is 0.15, and the output probability of 'low adjustment' is 0.05, a clear numerical value representing the final adjustment requirement is calculated through weighted averaging.

[0117] This clear adjustment requirement value represents the specific adjustment intensity required by the wastewater treatment equipment, such as increasing or decreasing the aeration volume, chemical dosage, pumping flow rate, etc.

[0118] Finally, the control center generates specific adjustment instructions based on the calculated adjustment requirements. These instructions include:

[0119] Equipment adjustment instructions: According to the adjustment requirements, the control system can adjust the working state of the wastewater treatment equipment. For example, increasing or decreasing the aeration volume, adjusting the water flow rate in the reaction tank, adjusting the chemical dosage of the chemical dosing equipment, etc.

[0120] Alarm and early warning: If the system determines that the adjustment requirement is high or the fluctuation is large, the system will trigger an early warning or alarm signal to notify the operator to take measures in a timely manner.

[0121] The control center sends the adjustment instructions to the relevant equipment (such as the reaction tank, aeration system, chemical dosing equipment, etc.) and monitors the feedback data of the equipment. If the system detects that the actual effect does not meet the expectations (such as the water quality has not improved or the treatment equipment has not reached the set parameters), the fuzzy logic rules and adjustment strategies will be adjusted to further optimize the adjustment process.

[0122] In this application, through fuzzy logic reasoning, the control center can calculate the adjustment requirements of the wastewater treatment equipment in real time based on the abnormal score of the water quality change rate, the score of the water quality periodic fluctuation, and the flow data. Fuzzy logic generates specific adjustment instructions by reasoning and defuzzifying the input fuzzy data, ensuring the efficient and stable operation of the wastewater treatment system. This method improves the adaptability and decision-making ability of the system to the complex and dynamically changing wastewater treatment environment.

[0123] The automatic adjustment module first receives the adjustment instructions from the control center. The adjustment instructions usually include specific adjustment requirements, such as: increasing or decreasing the water flow rate in the reaction tank, adjusting the power of the aeration system, changing the dosage of chemicals, etc. The control center generates adjustment instructions based on information such as wastewater flow rate, abnormal score of water quality change rate, and score of water quality periodic fluctuation, and transmits them to the automatic adjustment module.

[0124] The automatic adjustment module executes the adjustment operation by controlling each link of the wastewater treatment equipment according to the received adjustment instructions. The adjustment process is based on the monitoring of real-time data, the prediction of historical data, and the preset control strategy to ensure that the equipment can quickly respond to water quality changes and flow fluctuations. The main adjustment methods include the following aspects:

[0125] According to the change in wastewater flow rate: The wastewater flow rate is one of the important input parameters of the treatment system. The change in wastewater flow rate may be caused by seasonal changes, production activity changes, or emergencies. The automatic adjustment module monitors the flow data (such as influent flow rate, effluent flow rate, etc.) and adjusts the treatment capacity of the equipment according to the instructions of the control center. For example, when the flow rate increases, the module may increase the treatment capacity of the reaction tank or sedimentation tank, or start standby equipment to prevent overloading of treatment.

[0126] Real-time response: When the flow rate change exceeds the set threshold, the automatic adjustment module can dynamically adjust the flow path and flow rate by adjusting the power of the pump station or the opening degree of the flow distribution valve to ensure that the wastewater treatment facilities do not operate overloaded.

[0127] According to the prediction result of water quality change: The change in water quality parameters (such as chemical oxygen demand COD, dissolved oxygen DO, pH, etc.) is an important basis for adjusting the wastewater treatment equipment. The automatic adjustment module analyzes the fluctuation of water quality in real time based on the water quality data prediction result provided by the control center. For example, when the water quality changes sharply (such as a large increase in COD value or a sharp decrease in DO value), the system will automatically start additional treatment links or adjust the working state of the existing links.

[0128] Adjust specific equipment: For example, based on the prediction result of water quality change, the automatic adjustment module may adjust the power of the aeration system to increase the concentration of dissolved oxygen in the reaction tank; or adjust the dosage of the dosing system to increase the addition amount of flocculant or disinfectant to optimize the water quality.

[0129] Adjustment reaction tank: In the water treatment process, the working state of the reaction tank is closely related to the water quality, especially the dissolved oxygen (DO) and the biological reaction rate. The automatic adjustment module will adjust the aeration volume based on the real-time monitored DO value to ensure the activity of microorganisms. If the DO value is low, the system will automatically increase the aeration volume to promote the biodegradation process.

[0130] Adjustment sedimentation tank: The sedimentation tank is used to remove solid suspended matters and sediments in the water. According to the changes in flow rate and water quality data, the automatic adjustment module will adjust the water flow path of the sedimentation tank or control the start and stop of the sludge discharge equipment. When the flow rate increases, it may be necessary to allocate more water flow to the sedimentation tank to ensure the effective sedimentation of solid particles.

[0131] According to water quality monitoring data: When the water quality changes, the adjustment of the dosing system can be achieved through the automatic adjustment module. For example, when the COD value is too high, the system will automatically increase the dosage of flocculant or chemical agents to help remove organic pollutants in the water.

[0132] Intelligent adjustment of dosing amount: The automatic adjustment module can intelligently adjust the dosing amount of the agent based on real-time water quality data and prediction results, avoid overdosage or underdosage, and ensure that the water quality meets the requirements.

[0133] The feedback control module is a key component in the wastewater treatment system, responsible for monitoring and optimizing the wastewater treatment process. Its main function is to compare the real-time water quality data with the adjusted water quality, generate a feedback signal, and optimize the adjustment instruction based on this feedback signal. This module uses an adaptive control algorithm to perform dynamic adjustment according to real-time water quality fluctuations and treatment effects, realizing the adaptive optimization of the system.

[0134] The feedback control module first collects real-time water quality data through the water quality monitoring module, such as chemical oxygen demand (COD), dissolved oxygen (DO), pH value, etc. These data reflect the actual state of the water quality in the wastewater treatment process.

[0135] After receiving the adjustment instruction from the control center or the automatic adjustment module, the treatment equipment (such as the aeration system, reaction tank, dosing system, etc.) will make adjustments according to the instruction. The adjusted water quality data reflects the treatment effect of the wastewater after adjustment.

[0136] The feedback control module compares the real-time monitored water quality data with the adjusted water quality data. If the water quality data does not meet the expected standard (for example, the DO value is still lower than the set value, and the COD value has not been reduced to the target level), the system needs to further optimize the adjustment instruction.

[0137] Based on the comparison result, the feedback control module generates a feedback signal to indicate the direction and magnitude of further adjustment required for the regulating device. The feedback signal usually manifests as an adjustment amount or direction (such as increasing the aeration rate, adjusting the chemical dosage, changing the water flow path, etc.).

[0138] For example, when the DO value in the real-time water quality data is lower than the target range, the feedback control module issues a feedback signal to indicate an increase in the aeration rate or adjustment of the working state of the reaction tank.

[0139] The strength of the feedback signal (i.e., the adjustment magnitude) is proportional to the size of the deviation. The larger the deviation (for example, the greater the gap between the DO value and the target value), the greater the strength of the feedback signal, indicating that a larger adjustment is required.

[0140] The feedback control module performs dynamic adjustment according to the fluctuations of real-time water quality data and changes in treatment effects through an adaptive control algorithm. The adaptive control algorithm can optimize the adjustment strategy in real time according to the continuously changing water quality conditions and external environments (such as changes in wastewater flow rate, fluctuations in pollutant concentration, etc.) during the wastewater treatment process, enabling the system to continuously operate efficiently in an unstable or complex environment.

[0141] The adaptive control algorithm first calculates the error between the real-time water quality data and the target water quality. The error is the basis for evaluating whether the water quality meets the standard.

[0142] The algorithm dynamically adjusts the adjustment instruction according to the error value and the preset adjustment rules. For example, when the error is greater than the set threshold, the system increases the adjustment intensity (such as increasing the aeration rate, increasing the chemical dosage, etc.); when the error is less than or equal to the set threshold, the system may reduce the adjustment intensity or stop certain adjustment operations.

[0143] The adaptive control algorithm continuously optimizes its control strategy and improves the adjustment decision through learning historical data and accumulating real-time feedback. It can predict future changes based on past water quality fluctuation patterns and make adjustments in advance.

[0144] Common adaptive control algorithms include:

[0145] PID control algorithm: Although PID control (Proportional-Integral-Derivative control) is a classic control algorithm, in the wastewater treatment process, PID control can be combined with an adaptive mechanism. For example, when the system detects abnormal fluctuations or sudden changes in water quality, the parameters of the PID controller (such as proportional, integral, and derivative gains) are automatically adjusted according to the actual fluctuations, thereby improving the system's response ability.

[0146] Model Predictive Control (MPC): MPC builds a mathematical model of the wastewater treatment system, makes predictions based on real-time data, and adjusts equipment parameters. MPC can predict the trend of water quality changes in advance and perform optimization adjustments before the water quality changes.

[0147] The adaptive control algorithm enables the system to make dynamic adjustments according to factors such as wastewater flow rate, water quality changes, and treatment effects. For example, if the COD value suddenly increases or the water volume increases sharply, the system will automatically adjust the working state of the equipment to avoid untimely treatment or overload.

[0148] As the treatment system continuously optimizes the wastewater treatment effect, the control system will gradually adjust the adjustment parameters and optimize the adaptive control algorithm according to the long-term effect. For example, when the system identifies certain patterns of water quality changes, the control strategy will be optimized for these patterns to make the wastewater treatment process more efficient and stable.

[0149] The automatic adjustment module performs further adjustment operations according to the feedback signal. After the feedback control module generates an optimized adjustment instruction through the adaptive algorithm, the automatic adjustment module transmits it to the equipment to perform adjustment operations (such as adjusting the aeration volume, increasing the chemical dosage, etc.). The system will monitor the treatment effect in real time and continue to adjust according to the feedback signal to form a closed-loop control.

[0150] After each adjustment, the system will continue to monitor the water quality changes, generate new water quality data and adjustment instructions to ensure that every link in the wastewater treatment process is optimized. Over time, through continuous adjustment and feedback, the wastewater treatment process tends to be stable and the efficiency is maximized.

[0151] In this application, the feedback control module uses the adaptive control algorithm to dynamically optimize the adjustment instructions of the wastewater treatment equipment based on the comparison of real-time water quality data and the adjusted water quality. Through real-time feedback and adjustment, the system can adaptively respond to various changing factors such as wastewater flow fluctuations and pollutant concentration changes, ensuring the efficiency and stability of the wastewater treatment process. The adaptive control algorithm is dynamically optimized according to the feedback of real-time water quality fluctuations and treatment effects, improving the intelligent level of the treatment system.

[0152] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should be covered within the protection scope of this application.

Claims

1. An intelligent monitoring and control system for steam recompression mother liquor wastewater treatment, characterized in that: It includes water quality monitoring module, data fusion module, flow monitoring module, control center, automatic adjustment module and feedback control module; Water quality monitoring module, used to monitor multiple water quality data in wastewater in real time, including chemical oxygen demand, dissolved oxygen, pH value, temperature and heavy metal concentration; Data fusion module, used to fuse water quality data, train historical water quality data using machine learning algorithms, and make anomaly predictions based on real-time data; Flow monitoring module, used to monitor wastewater flow in real time and transmit flow data to the control center; The control center is used to calculate the regulation requirements of the wastewater treatment equipment through a preset algorithm based on the water quality abnormality prediction data and flow data, and generate regulation instructions; The automatic adjustment module automatically adjusts the working state of the treatment equipment by executing the adjustment instructions, including dynamically adjusting the working state of the treatment equipment according to the changes in wastewater flow and the predicted results of water quality data; The feedback control module compares the real-time water quality data with the adjusted water quality, generates a feedback signal, and further optimizes the adjustment instructions.

2. The intelligent monitoring and control system for treating steam recompression mother liquor wastewater according to claim 1, characterized in that: The sensors used in the water quality monitoring module include: photometric sensors, electrochemical sensors and temperature sensors.

3. The intelligent monitoring and control system for steam recompression mother liquor wastewater treatment according to claim 1 is characterized in that: The data fusion module receives real-time data from the water quality monitoring module, and performs time synchronization and standardization processing on the data of different sensors, uses Kalman filtering technology to denoise the water quality data, fuses the signals of each sensor, applies the weighted average method to assign weights to the data of each sensor, introduces a machine learning algorithm to train the historical water quality data, and extracts abnormal characteristics of water quality changes, including water quality parameter change rate characteristics and water quality parameter fluctuation period characteristics.

4. The intelligent monitoring and control system for treating steam recompression mother liquor wastewater according to claim 3 is characterized in that: The water quality change rate anomaly score is generated according to the water quality parameter change rate characteristics. The generation method is as follows: collect and organize the required water quality parameters, set the measured value of each water quality parameter at time t to be x(t), the change rate of the water quality parameter refers to the degree of change of the water quality parameter value per unit time, and set the historical change rate of a certain water quality parameter to be , calculate its mean and standard deviation, and calculate the standardized change rate at the current moment as the water quality change rate anomaly score.

5. The intelligent monitoring and control system for treating steam recompression mother liquor wastewater according to claim 4, characterized in that: A water quality periodic fluctuation score is generated according to the periodic characteristics of water quality parameter fluctuations. The generation method is as follows: preprocess the original water quality data and present it in the form of a time series. The water quality time series signal is decomposed into multiple intrinsic mode functions IMFs through empirical mode decomposition. Each IMF represents a fluctuation component of a different frequency. The Hilbert transform is applied to each IMF to calculate its instantaneous amplitude and instantaneous frequency. For each IMF, the standard deviation of its instantaneous frequency and the average value of its instantaneous amplitude are calculated. The ratio of the standard deviation of the instantaneous frequency of each IMF to the average value of the instantaneous amplitude is calculated as the water quality periodic fluctuation score of each IMF. Since water quality fluctuations are caused by the joint action of multiple IMF components, the periodic fluctuation scores of each IMF are weighted averaged to obtain a comprehensive water quality periodic fluctuation score.

6. The intelligent monitoring and control system for treating steam recompression mother liquor wastewater according to claim 5, characterized in that: The control center receives the water quality change rate anomaly score, water quality periodic fluctuation score and flow data as input items for fuzzy logic reasoning; The regulation requirements of wastewater treatment equipment are used as the output of fuzzy logic; Convert input data into fuzzy sets and build a fuzzy rule base to describe the fuzzy relationship between input and output; Use fuzzy reasoning method to reason based on the fuzzy value of input item and rule base to get the fuzzy value of each output item; For each rule, the input fuzzy value is matched with the conditions in the rule base and a fuzzy output is obtained. During the reasoning process, the reasoning result of each rule is weighted according to the matching degree between the input fuzzy value and the rule. After inference, the fuzzy result is obtained, which needs to be converted into a clear regulation demand value through the defuzzification process; the output values ​​of all rules are weighted averaged to obtain the final output value, that is, the specific regulation intensity required by the wastewater treatment equipment; The control center generates specific adjustment instructions based on the calculated adjustment requirements.

7. The intelligent monitoring and control system for treating steam recompression mother liquor wastewater according to claim 6, characterized in that: The automatic adjustment module receives adjustment instructions from the control center, analyzes the instruction content, and adjusts the working status of the reaction tank, aeration system, sedimentation tank and dosing equipment in real time.

8. The intelligent monitoring and control system for treating steam recompression mother liquor wastewater according to claim 7, characterized in that: The feedback control module collects water quality data from the wastewater in real time and compares it with the adjusted water quality, calculates the deviation value, and generates a feedback signal based on the deviation value between the water quality data and the target value, including increasing the adjustment intensity when the error is greater than the set threshold; reducing the adjustment intensity or stopping the adjustment operation when the error is less than or equal to the set threshold.

Images