Waste Hydrofluoric Acid and Leachate Co-treatment System

Abstract

The present invention discloses a co-treatment system for waste hydrofluoric acid and leachate, which relates to the technical field of industrial waste liquid treatment. By introducing a heat release rate calculation module, a heat conduction efficiency monitoring module for the cooling system, an efficiency anomaly index calculation module, and a risk level classification and treatment module, and using high-precision sensors and real-time data analysis technology, it accurately monitors the heat changes during the co-treatment process of waste hydrofluoric acid and leachate and the heat dissipation capacity of the cooling system. By calculating and analyzing the temperature data weight coefficients in each time period, it timely identifies system anomalies and generates warning signals, and finally classifies the risk levels into different states to achieve efficient and stable temperature control, ensure the safe operation of the system under high heat loads, and prevent the occurrence of temperature runaway and equipment damage accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial waste liquid treatment, and particularly to a co-treatment system for waste hydrofluoric acid and leachate. Background Art

[0002] In the process of industrial production, hydrofluoric acid is widely used as an important chemical raw material in the metallurgy, chemical industry, glass manufacturing, and electronics industries. However, the use of hydrofluoric acid generates a large amount of waste hydrofluoric acid liquid waste, which contains high concentrations of fluorides and other harmful substances. If not properly treated and discharged into the environment, it will seriously harm the ecological system and human health. Traditional methods for treating waste hydrofluoric acid mostly use lime neutralization precipitation method, calcium salt precipitation method, etc. Although they can remove some fluoride ions, there are problems such as a large amount of sediment production, high treatment cost, and secondary pollution. In addition, leachate is a kind of wastewater containing complex organic matter and inorganic salts generated by landfills. Its composition is complex and toxic, and it is difficult to treat. Conventional treatment processes have low removal efficiency for fluorides and are difficult to meet the increasingly strict emission standards. Therefore, it is particularly urgent to develop an efficient co-treatment technology for waste hydrofluoric acid and leachate.

[0003] The co-treatment system for waste hydrofluoric acid and leachate aims to simultaneously treat the two highly polluted wastewaters through resource-based and harmless means, thereby achieving efficient removal of pollutants and resource recovery and utilization. This technology can convert the fluorides in waste hydrofluoric acid into utilizable fluorine resources, reduce secondary pollution during the treatment process, and lower the total treatment cost. At the same time, by optimizing the reaction conditions and process flow, and using the organic and inorganic components in the leachate to interact with the hydrofluoric acid waste liquid, the treatment efficiency of the system and the removal effect of fluorides can be further improved.

[0004] The existing technologies have the following deficiencies:

[0005] During the co-treatment process of waste hydrofluoric acid and leachate, some chemical components in the leachate (such as organic matter, metal ions, etc.) may react with the hydrofluoric acid waste liquid to generate highly exothermic reactions, especially under high-concentration or large-scale treatment conditions. If the cooling system in the treatment system fails, the accumulated reaction heat may cause the local temperature to be too high, thereby triggering thermal runaway. And thermal runaway may cause the system equipment materials (such as reactors, pipelines, etc.) to undergo rapid thermal expansion or rupture, and even trigger explosion accidents. Summary of the Invention

[0006] The purpose of the present invention is to provide a co-treatment system for waste hydrofluoric acid and leachate to solve the deficiencies in the background art.

[0007] To achieve the above object, the present invention provides the following technical solution: a co-treatment system for waste hydrofluoric acid and leachate, including a heat release rate calculation module, a heat conduction efficiency monitoring module for the cooling system, an efficiency anomaly index calculation module, and a risk level classification and processing module;

[0008] Heat release rate calculation module: Install a high-precision heat flux sensor in the reactor for the co-treatment of waste hydrofluoric acid and leachate to monitor the heat change generated by the reaction in real time, obtain the heat output data in the reactor through the heat flux sensor, calculate the heat release rate per unit time, transmit the monitored heat release rate data to the control system, and predict the change trend of the heat release rate;

[0009] Cooling system heat conduction efficiency monitoring module: Install temperature sensors and flow meters in different links of the cooling system to monitor the temperature change and flow rate of the cooling medium in real time. Combine the heat dissipation calculation formula to obtain the real-time heat conduction efficiency of the cooling system. After analyzing the fluctuation of the heat conduction efficiency within a fixed time period, evaluate whether the cooling system can operate effectively under the heat load;

[0010] Efficiency anomaly index calculation module: Divide the co-treatment process of waste hydrofluoric acid and leachate into several time periods. According to the change trend of the heat release rate and the fluctuation of the heat conduction efficiency within each time period, determine the weight coefficient of the temperature data within different time periods in the co-treatment process of waste hydrofluoric acid and leachate, and perform weighted average calculation on the weight coefficients of the temperature data within different time periods to calculate the anomaly index of the cooling system;

[0011] Risk level classification and processing module: After comparing the calculated anomaly index of the cooling system with the gradient standard threshold, divide the temperature runaway risk in the co-treatment process of waste hydrofluoric acid and leachate into different levels, divide it into normal operation state, possible normal operation state and overheat operation state, and perform corresponding processing. The gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold.

[0012] Preferably, in the heat release rate calculation module, based on the result of model fitting, generate a prediction curve of the heat release rate, and generate a heat release rate anomaly index by analyzing the change trend of the heat release rate within different time periods. The method for obtaining the heat release rate anomaly index is as follows:

[0013] Mark the change points of the prediction curve of the heat release rate, obtain the model of the heat release rate changing with time. If the change of the heat release rate conforms to the normal distribution, the expression is: ; where HGR(t) is the heat release rate at time point t, is the expected value of the heat release rate at time point t, Construct a Bayesian model for the variance of the heat release rate, and calculate the probability of abnormal change of the heat release rate according to the change points of the prediction curve; initialize the prior probability P(θ) as: ; where T is the total length of the time series; calculate the likelihood function , and the expression is: ; is the expected value of the heat release rate, is the variance of the heat release rate; according to Bayes' theorem, combine the prior probability and the likelihood function to calculate the posterior probability of the system state change at time point t, and the expression: ; in the formula, is the normalization constant; calculate the heat release rate anomaly index, and the expression is: ; in the formula, FD is the heat release rate anomaly index.

[0014] Preferably, in the cooling system heat conduction efficiency monitoring module, after analyzing the fluctuation of the heat conduction efficiency within a fixed time period, a heat conduction efficiency fluctuation index is generated. The method for obtaining the heat conduction efficiency fluctuation index is:

[0015] Within a fixed time period T, the heat conduction efficiency CTE of the cooling system is monitored in real time through a temperature sensor and a flowmeter to generate a time series data set: ; where represents the heat conduction efficiency at the nth time point. Select the decay factor λ, and according to the formula of exponential weighted moving average, calculate the smoothed value at each time point, that is, the weighted average of the current heat conduction efficiency, and the formula is: ; is the exponential weighted moving average value at time point ; calculate the actual heat conduction efficiency at each time point and the residual between the exponential weighted moving average value . The residual represents the degree to which the actual value deviates from the predicted smoothed value, and the expression is: ; calculate the heat conduction efficiency fluctuation index according to the residual, and the expression is: ; in the formula, n is the number of data points within the analysis time period, and ED is the heat conduction efficiency fluctuation index.

[0016] Preferably, in the efficiency anomaly index calculation module, the heat release rate anomaly index and the heat conduction efficiency fluctuation index obtained in each time period are converted into feature vectors, and the feature vectors are used as the input of the machine learning model. The machine learning model takes the weight coefficient value label of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate predicted by each group of feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the weight coefficient value labels of the temperature data in each time period during all co-treatment processes of waste hydrofluoric acid and leachate as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence and then the model training is stopped. The weight coefficient value of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate is determined according to the model output result. Among them, the machine learning model is a polynomial regression model; and the weighted average calculation of the weight coefficients of the temperature data in different time periods is performed to calculate the anomaly index of the cooling system.

[0017] Preferably, in the risk level classification and processing module, the obtained anomaly index of the cooling system is compared with the gradient standard thresholds. The gradient standard thresholds include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold. The anomaly index of the cooling system is compared with the first standard threshold and the second standard threshold respectively;

[0018] If the anomaly index of the cooling system is greater than the second standard threshold, it indicates that the temperature control effect during the co-treatment process of waste hydrofluoric acid and leachate is poor. At this time, a first-level warning signal is generated, it is classified as an overheating operation state, and emergency measures are taken immediately;

[0019] If the anomaly index of the cooling system is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it indicates that the temperature control effect during the co-treatment process of waste hydrofluoric acid and leachate is average. At this time, a second-level warning signal is generated, it is classified as a possible normal operation state, and preventive intervention is carried out;

[0020] If the anomaly index of the cooling system is less than the first standard threshold, it indicates that the temperature control effect during the co-treatment process of waste hydrofluoric acid and leachate is good. At this time, no warning signal is generated, it is classified as a normal operation state, indicating that the cooling system operates stably and no intervention is required.

[0021] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0022] 1. The present invention realizes precise monitoring and intelligent management in the collaborative treatment process of waste hydrofluoric acid and leachate by integrating a heat release rate calculation module, a cooling system heat conduction efficiency monitoring module, an efficiency anomaly index calculation module, and a risk level classification and handling module. By real-time monitoring the heat release rate and the heat conduction efficiency of the cooling system, and combining with a machine learning model to predict and optimize the weight coefficients of temperature data in each time period, the system operation status is effectively evaluated, and an anomaly index is generated. By analyzing these key data, the system can predict the risk of temperature runaway and take targeted preventive and emergency measures according to the risk levels (normal operation, possible normal operation, overheat operation) to ensure the safety and efficiency of the system.

[0023] 2. The present invention not only improves the temperature control accuracy in the treatment process of waste hydrofluoric acid and leachate, but also significantly reduces the risk of equipment damage or safety accidents caused by temperature runaway. Through an automated early warning system and multi-level risk management, operators can timely obtain the system status and make corresponding interventions to ensure the stable operation of the cooling system under different loads, thereby improving the treatment efficiency, extending the equipment life, and reducing energy consumption and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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 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.

[0025] Figure 1 It is a flowchart of the method of the present invention.

[0026] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] 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 with reference to 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. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0028] Embodiment, please refer to Figure 1 and 2 As shown, the collaborative treatment system of waste hydrofluoric acid and leachate in this embodiment includes a heat release rate calculation module, a cooling system heat conduction efficiency monitoring module, an efficiency anomaly index calculation module, and a risk level classification and handling module;

[0029] Heat release rate calculation module: Install a high-precision heat flux sensor in the reactor for the co-treatment of waste hydrofluoric acid and leachate to monitor the heat change generated by the reaction in real time, obtain the heat output data in the reactor through the heat flux sensor, calculate the heat release rate per unit time, transmit the monitored heat release rate data to the control system, and predict the change trend of the heat release rate;

[0030] Cooling system heat conduction efficiency monitoring module: Install temperature sensors and flow meters in different parts of the cooling system to monitor the temperature change and flow rate of the cooling medium in real time. Combine the heat dissipation calculation formula to obtain the real-time heat conduction efficiency of the cooling system. After analyzing the fluctuation of the heat conduction efficiency within a fixed time period, evaluate whether the cooling system can operate effectively under the heat load;

[0031] Efficiency anomaly index calculation module: Divide the co-treatment process of waste hydrofluoric acid and leachate into several time periods. According to the change trend of the heat release rate and the fluctuation of the heat conduction efficiency in each time period, determine the weight coefficient of the temperature data in different time periods during the co-treatment process of waste hydrofluoric acid and leachate, and calculate the anomaly index of the cooling system after weighted average calculation of the weight coefficients of the temperature data in different time periods;

[0032] Risk level classification and processing module: After comparing the calculated anomaly index of the cooling system with the gradient standard threshold, classify the temperature runaway risk during the co-treatment process of waste hydrofluoric acid and leachate into different levels, which are classified into normal operation state, possible normal operation state and overheat operation state, and perform corresponding processing. The gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold.

[0033] In the reaction heat rate calculation module, select a suitable heat flux sensor according to the operating conditions of the reactor (such as temperature range, chemical environment, reactor material, etc.). Usually, a sensor type that can withstand high temperatures and resist corrosion is required to adapt to the chemical environment of hydrofluoric acid and leachate. Ensure that the selected sensor has sufficient accuracy to detect subtle heat changes. Usually, the sensor is required to have high sensitivity and fast response ability. Confirm that the sensor size matches the reserved installation interface of the reactor to ensure safe and firm installation in the reactor. Select a key position that can accurately reflect the temperature and heat change in the reactor to install the sensor, usually in the most active area of the heat flux in the reactor. Avoid installing the sensor near the cooling wall or dead end to avoid affecting data accuracy. For large reactors, it may be necessary to install heat flux sensors at multiple positions to obtain more comprehensive heat flux data and achieve multi-point monitoring.

[0034] The high-precision heat flux sensor installed inside the reactor monitors the heat change generated by the reaction in real time. The sensor converts the heat flux data into an electrical signal, representing the heat output generated during the reaction process. The system should set a suitable sampling frequency to ensure accurate recording of heat changes (such as once per second or once per minute). Calculate the heat release rate per unit time. The heat release rate formula is: ; where HGR is the heat release rate per unit time (unit: W or J / s), representing the heat generated by the reaction per second. ΔQ is the heat change monitored by the sensor (unit: J). Δt: time interval (unit: s), representing the sampling period of the heat change. Within each time period (Δt), the corresponding heat release rate HGR is calculated through the collected heat flux data ΔQ. The HGR data at each time point is recorded to form time series data. Transmit the heat release rate data calculated within each time period to the central control system by wired or wireless means. Ensure stable and delay-free data transmission. In the control system, the heat release rate data is displayed and stored in real time for analysis and trend prediction. The control system interface can dynamically display the change curve of the heat release rate over time.

[0035] When the change in the heat release rate is relatively stable, use linear regression to predict future trends.

[0036] Polynomial regression: For complex heat flux changes, quadratic or polynomial fitting can be used to more accurately capture the fluctuation characteristics.

[0037] Exponential smoothing method: If there is a significant time correlation in the data, the exponential smoothing method can be used to predict the future heat release trend.

[0038] Machine learning model: For complex reactions, machine learning algorithms (such as time series prediction models like LSTM) may be required for multi-dimensional trend prediction.

[0039] Based on the results of model fitting, generate a prediction curve of the heat release rate. After analyzing the change trend of the heat release rate in different time periods, generate a heat release rate anomaly index. The method for obtaining the heat release rate anomaly index is:

[0040] Mark the change points of the prediction curve of the heat release rate to obtain the model of the heat release rate changing with time. If the change in the heat release rate conforms to a normal distribution, the expression is: ; where HGR(t) is the heat release rate at time point t, is the expected value of the heat release rate at time point t, is the variance of the heat release rate, representing the fluctuation range. Construct a Bayesian model and calculate the probability of abnormal change in the heat release rate based on the change points of the prediction curve; Initialize the prior probability P(θ) as: ; where T is the total length of the time series, indicating that each time point has an equal probability of change; calculate the likelihood function , and the likelihood function P(HGR(t)|θ) reflects whether the heat release rate at the current time point conforms to the prediction model under a given state. The expression is: ; is the expected value of the heat release rate, is the variance of the heat release rate; according to Bayes' theorem, combining the prior probability and the likelihood function, calculate the posterior probability of the system state change at time point t. The expression is: ; In the formula, is the normalization constant, used to ensure that the sum of the posterior probabilities is 1; calculate the heat release rate anomaly index. The expression is: ; In the formula, FD is the heat release rate anomaly index.

[0041] When the heat release rate anomaly index is larger, it indicates that the change trend of the heat release rate is more unstable, and the possibility of abnormality is higher. This means that there may be a sudden and drastic change in the heat release during the reaction process, such as an intensification of the reaction or an increase in heat fluctuations caused by accidental factors. The increase in the fluctuation of the heat release rate indicates that the reaction system may be on the verge of getting out of control, the temperature rises faster, and the cooling system may not be able to respond to heat accumulation in time, posing a risk of temperature runaway. Therefore, the larger the anomaly index, the worse the temperature stability, and the safety of the system may also be threatened, and emergency measures need to be taken to stabilize the system operation.

[0042] When the heat release rate anomaly index is smaller, it indicates that the change trend of the heat release rate is smoother, and the system is in a normal operating state. The heat release during the reaction process conforms to the expected stable pattern. The smaller fluctuation of the heat release rate indicates good temperature control, and the cooling system can effectively regulate the heat generated during the reaction process. The system is in a state of high temperature stability. At this time, the system operation is safe and controllable, the temperature is maintained within a safe range, the reaction process tends to be stable, and no additional intervention measures are required.

[0043] Cooling system heat conduction efficiency monitoring module: Install temperature sensors and flow meters at different links of the cooling system to monitor the temperature change and flow of the cooling medium in real time. Combine the heat dissipation calculation formula to obtain the real-time heat conduction efficiency of the cooling system. After analyzing the fluctuation of the heat conduction efficiency within a fixed time period, evaluate whether the cooling system can operate effectively under the heat load.

[0044] Select suitable temperature sensors and flow meters to ensure that their accuracy and response speed meet the requirements of the cooling system. Temperature sensors should be installed at the inlet and outlet of the cooling system to measure the temperature difference of the cooling medium when it enters and leaves the cooling system. Installed in the circulating pipeline of the coolant to monitor the flow rate of the cooling medium and ensure accurate acquisition of flow data.

[0045] The temperature sensors should be installed at the inlet and outlet of the cooling medium respectively to accurately measure the temperature difference between the inlet and outlet of the coolant. The flow meter is installed in the main circulation pipeline of the cooling medium to ensure real-time acquisition of the flow rate.

[0046] The temperature sensors continuously monitor the inlet temperature Tin and outlet temperature Tout of the cooling medium. The system needs to continuously record these data to ensure real-time understanding of the heat absorbed or released by the coolant in the cooling system. The flow meter continuously monitors the flow rate of the cooling medium (unit: kg / s) and records the flow velocity of the coolant. The flow rate data is combined with the temperature data to calculate the heat dissipation of the cooling system.

[0047] The heat transfer efficiency represents the amount of heat removed by the cooling system per unit time, which can usually be calculated by the mass flow rate, specific heat capacity, and temperature change of the coolant.

[0048] The basic formula for the heat transfer efficiency CTE is: ; where The flow rate of the cooling medium, in kg / s, represents the mass of the coolant flowing through the cooling system per second. is the specific heat capacity of the cooling medium, in J / (kg·K), representing the amount of heat required for a unit mass of the coolant to increase by 1 degree Celsius. The specific heat capacity of common coolants (such as water) is approximately 4184 J / (kg·K). ΔT = Tin - Tout is the temperature difference between the inlet and outlet of the cooling medium, in K (or °C), representing the heat absorbed by the coolant in the cooling system. The unit of CTE: Through the above formula, the unit of CTE (the heat transfer efficiency of the cooling system) is watt (W), representing the amount of heat removed from the system per second.

[0049] After analyzing the fluctuations of the heat transfer efficiency over a fixed time period, a heat transfer efficiency fluctuation index is generated to evaluate whether the cooling system can operate effectively under the heat load. The method for obtaining the heat transfer efficiency fluctuation index is:

[0050] Within a fixed time period T (such as per second, per minute), the heat transfer efficiency CTE of the cooling system is continuously monitored through temperature sensors and flow meters to generate a time series data set: ; where Denote the heat conduction efficiency at the nth time point. Select the decay factor λ. In the exponentially weighted moving average, λ is the decay coefficient, which determines the influence degree of the data at each time point on the overall fluctuation. The value range of λ is (0, 1): A larger λ value (such as 0.7 or 0.8) makes the influence of the most recent data on the average value greater, which is suitable for capturing short-term fluctuations. A smaller λ value (such as 0.1 or 0.2) gives a higher weight to historical data and is suitable for analyzing long-term trends. According to the formula of the exponentially weighted moving average, calculate the smoothed value at each time point , that is, the weighted average of the current heat conduction efficiency. The formula is: ; is the exponentially weighted moving average value at time point (the smoothed value of the previous time point). Calculate the actual heat conduction efficiency at each time point and the exponentially weighted moving average value The residual between them. The residual represents the degree to which the actual value deviates from the predicted smoothed value and reflects the magnitude of the fluctuation. The expression is: ; Calculate the heat conduction efficiency fluctuation index according to the residual. The expression is: ; In the formula, n is the number of data points within the analysis time period, and ED is the heat conduction efficiency fluctuation index.

[0051] When the heat conduction efficiency fluctuation index is larger, it indicates that the heat conduction efficiency of the cooling system has large fluctuations in different time periods, suggesting that the system performs unstably when coping with the heat load. This instability may mean that the heat dissipation capacity of the cooling system cannot match the heat load, resulting in inconsistent heat dissipation effects at different time points. As the fluctuation index increases, the system may not be able to remove the generated heat in a timely and effective manner, and thus problems such as temperature fluctuations, decreased cooling efficiency, or equipment overheating may occur. Therefore, a larger fluctuation index usually means that the cooling system operates poorly under the heat load and there are potential risks of low efficiency and temperature out of control.

[0052] When the heat conduction efficiency fluctuation index is smaller, it indicates that the heat conduction efficiency of the cooling system is relatively stable and consistent, suggesting that the system can maintain a stable heat dissipation effect when facing the heat load. A smaller fluctuation index means that the cooling system can continuously and effectively remove heat. Even when the heat load changes, the system can still respond in a timely manner and maintain the stability of the temperature. Therefore, a smaller fluctuation index usually indicates that the cooling system operates well under the heat load, has a high heat dissipation efficiency and the system is stable, and can effectively avoid the risks of severe temperature fluctuations and equipment overheating.

[0053] Efficiency Abnormality Index Calculation Module: Divide the co-treatment process of waste hydrofluoric acid and leachate into several time periods. According to the change trend of the heat release rate and the fluctuation of the heat conduction efficiency in each time period, determine the weight coefficients of the temperature data in different time periods during the co-treatment process of waste hydrofluoric acid and leachate, and calculate the abnormality index of the cooling system after performing weighted average calculation on the weight coefficients of the temperature data in different time periods.

[0054] During the co-treatment process of waste hydrofluoric acid and leachate, in order to better monitor and optimize the treatment effect, it is necessary to divide the entire process into several time periods. Each time period represents different reaction stages or operating conditions, such as the addition, reaction, precipitation, separation, etc. of the waste liquid. During these time periods, key parameters such as reaction temperature, chemical reaction rate, and heat dissipation efficiency of the cooling system can be monitored and adjusted in real time. By segmenting the treatment process, the system performance of each stage can be accurately analyzed, potential problems can be identified, and optimization measures can be taken according to the different working conditions of each time period, so as to ensure the stability and efficiency of the co-treatment process.

[0055] Convert the heat release rate abnormality index and heat conduction efficiency fluctuation index obtained in each time period into feature vectors, and use the feature vectors as the input of the machine learning model. The machine learning model takes predicting the weight coefficient value label of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate as the prediction target, and takes minimizing the sum of the prediction errors of the weight coefficient value labels of the temperature data in all time periods during the co-treatment process of waste hydrofluoric acid and leachate as the training target to train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the weight coefficient values of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate according to the model output results, where the machine learning model is a polynomial regression model; and calculate the abnormality index of the cooling system after performing weighted average calculation on the weight coefficients of the temperature data in different time periods.

[0056] The method for obtaining the weight coefficient values of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate is: Obtain the corresponding function expression from the first feature vector training data of the trained machine learning model: ; where is the output function of the model, FD is the heat release rate abnormality index, ED is the heat conduction efficiency fluctuation index, is the weight coefficient value of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate.

[0057] Risk level classification and handling module: After comparing the calculated abnormal index of the cooling system with the gradient standard threshold values, the risk of temperature runaway during the co-treatment of waste hydrofluoric acid and leachate is classified into different levels, which are classified into normal operation state, possible normal operation state, and overheat operation state, and corresponding treatments are carried out. The gradient standard threshold values include a first standard threshold value and a second standard threshold value, and the first standard threshold value is less than the second standard threshold value.

[0058] Compare the obtained abnormal index of the cooling system with the gradient standard threshold values. The gradient standard threshold values include a first standard threshold value and a second standard threshold value, and the first standard threshold value is less than the second standard threshold value. Compare the abnormal index of the cooling system with the first standard threshold value and the second standard threshold value respectively;

[0059] If the abnormal index of the cooling system is greater than the second standard threshold value, it indicates that the temperature control effect during the co-treatment of waste hydrofluoric acid and leachate is poor. At this time, a first-level warning signal is generated, and it is classified into the overheat operation state. Immediately take emergency measures, such as increasing the flow rate of the cooling system, reducing the reaction rate, or turning on the standby cooling equipment. The monitoring system may be on the verge of temperature runaway, and timely intervention is required to prevent system overload or equipment damage;

[0060] If the abnormal index of the cooling system is greater than or equal to the first standard threshold value and less than or equal to the second standard threshold value, it indicates that the temperature control effect during the co-treatment of waste hydrofluoric acid and leachate is average. At this time, a second-level warning signal is generated, and it is classified into the possible normal operation state. The system shows certain fluctuations but does not reach the overheat critical point. The system should be monitored, and the temperature and other key parameters should be closely observed; at the same time, preventive adjustments can be made, such as slightly adjusting the coolant flow rate or reaction conditions, to prevent the system from entering the overheat state;

[0061] If the abnormal index of the cooling system is less than the first standard threshold value, it indicates that the temperature control effect during the co-treatment of waste hydrofluoric acid and leachate is good. At this time, no warning signal is generated, and it is classified into the normal operation state, indicating that the cooling system is operating stably and can cope with the current heat load, and no additional intervention measures are required. Continue with regular monitoring to ensure that the system operates within the safe range.

[0062] It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and relevant personnel can take corresponding treatment measures according to different warning signal levels.

[0063] In this application, the implementation of the risk level classification and early warning system can significantly improve the safety and efficiency in the co-treatment process of waste hydrofluoric acid and leachate. By comparing the abnormal index of the cooling system with the gradient standard threshold, the system can monitor the risk of temperature runaway in real time and automatically generate early warning signals. The first-level early warning signal indicates poor temperature control effect and requires immediate emergency measures to prevent system overheating or equipment damage; the second-level early warning signal indicates general temperature control effect and requires close monitoring and preventive adjustment; if there is no early warning signal, it means the system is operating stably and no additional intervention is required. This hierarchical processing mechanism can effectively avoid temperature runaway, ensure the stable operation of the system under different heat loads, optimize the operation efficiency, and reduce the maintenance cost and accident risk.

[0064] In this embodiment, during the co-treatment process of waste hydrofluoric acid and leachate, first, a high-precision heat flow sensor is installed in the reactor to monitor the heat change generated by the reaction in real time, calculate the heat release rate per unit time, and transmit the data to the control system to predict the change trend of the heat release rate. At the same time, temperature sensors and flow meters are installed at different links of the cooling system to monitor the temperature and flow rate of the cooling medium in real time. Combining with the heat dissipation calculation formula, the real-time heat conduction efficiency is obtained, and the fluctuation situation within a fixed time period is analyzed to evaluate the operation efficiency of the cooling system under the heat load. The system divides the treatment process into several time periods, determines the temperature data weight coefficient of each time period according to the trend of the heat release rate and the fluctuation of the heat conduction efficiency, and calculates the abnormal index of the cooling system through weighted average. Finally, the abnormal index is compared with the gradient standard threshold (including the first and second standard thresholds), and the system risk is divided into three states: normal operation, possible normal operation, and overheating operation, and corresponding treatment measures are taken.

[0065] The above formulas are all calculated by taking the numerical values after dimensionless. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0066] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0067] As described above, the specific implementation manners of the present application are only described, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application.

Claims

1. Waste hydrofluoric acid and leachate co-treatment system, characterized in that: It includes a heat release rate calculation module, a cooling system heat conduction efficiency monitoring module, an efficiency anomaly index calculation module, and a risk level classification and handling module; Heat release rate calculation module: Install a high-precision heat flux sensor in the reactor for the co-treatment of waste hydrofluoric acid and leachate to monitor the heat change generated by the reaction in real time, obtain the heat output data in the reactor through the heat flux sensor, calculate the heat release rate per unit time, transmit the monitored heat release rate data to the control system, and predict the change trend of the heat release rate; Generate a heat release rate anomaly index by analyzing the change trend of the heat release rate in different time periods. The method for obtaining the heat release rate anomaly index is as follows: Mark the change points of the predicted curve of the heat release rate to obtain a model of the heat release rate varying with time. If the change of the heat release rate conforms to a normal distribution, the expression is: ; where HGR(t) is the heat release rate at time point t, is the expected value of the heat release rate at time point t, is the variance of the heat release rate. Construct a Bayesian model and calculate the probability of abnormal change of the heat release rate according to the change points of the predicted curve; Initialize the prior probability P(θ) as: ; where T is the total length of the time series; Calculate the likelihood function , and the expression is: ; is the expected value of the heat release rate, is the variance of the heat release rate; According to Bayes' theorem, combine the prior probability and the likelihood function to calculate the posterior probability of the system state change at time point t. The expression: ; where is the normalization constant; Calculate the heat release rate anomaly index, and the expression is: ; where FD is the heat release rate anomaly index; Cooling system heat conduction efficiency monitoring module: Install temperature sensors and flow meters in different links of the cooling system to monitor the temperature change and flow rate of the cooling medium in real time. Combine the heat dissipation calculation formula to obtain the real-time heat conduction efficiency of the cooling system. After analyzing the fluctuation of the heat conduction efficiency in a fixed time period, evaluate whether the cooling system can operate effectively under the heat load; Generate a heat conduction efficiency fluctuation index by analyzing the fluctuation of the heat conduction efficiency in a fixed time period. The method for obtaining the heat conduction efficiency fluctuation index is as follows: During a fixed time period T, the heat conduction efficiency CTE of the cooling system is monitored in real time through a temperature sensor and a flowmeter, generating a time series data set: ; where represents the heat conduction efficiency at the nth time point. Select the decay factor λ and calculate the smoothed value at each time point according to the formula of exponential weighted moving average , that is, the weighted average of the current heat conduction efficiency. The formula is: ; is the exponential weighted moving average value at time point ; Calculate the actual heat conduction efficiency at each time point and the exponential weighted moving average value The residual between them. The residual represents the degree to which the actual value deviates from the predicted smoothed value. The expression is: ; Calculate the heat conduction efficiency fluctuation index according to the residual. The expression is: ; In the formula, n is the number of data points in the analysis time period, and ED is the heat conduction efficiency fluctuation index; Efficiency anomaly index calculation module: Divide the co-treatment process of waste hydrofluoric acid and leachate into several time periods. According to the change trend of the heat release rate and the fluctuation of the heat conduction efficiency in each time period, determine the weight coefficient of the temperature data in different time periods during the co-treatment process of waste hydrofluoric acid and leachate, and perform weighted average calculation on the weight coefficients of the temperature data in different time periods to calculate the anomaly index of the cooling system; Risk level classification and handling module: After comparing the calculated anomaly index of the cooling system with the gradient standard threshold, classify the temperature runaway risk during the co-treatment process of waste hydrofluoric acid and leachate into different levels, classify it into a normal operation state, a possible normal operation state, and an overheat operation state, and perform corresponding processing. The gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold.

2. The co-treatment system for waste hydrofluoric acid and leachate according to claim 1, characterized in that: In the efficiency anomaly index calculation module, convert the heat release rate anomaly index and the heat conduction efficiency fluctuation index obtained in each time period into feature vectors, use the feature vectors as the input of the machine learning model. The machine learning model takes the prediction of the weight coefficient value label of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate as the prediction target, and takes minimizing the sum of the prediction errors of the weight coefficient value labels of the temperature data in all co-treatment processes of waste hydrofluoric acid and leachate as the training target. Train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the weight coefficient value of the temperature data in each time period during the co-treatment process of waste hydrofluoric acid and leachate according to the model output result. Among them, the machine learning model is a polynomial regression model; and perform weighted average calculation on the weight coefficients of the temperature data in different time periods to calculate the anomaly index of the cooling system.

3. The waste hydrofluoric acid and leachate coordinated treatment system according to claim 2, characterized in that: In the risk level classification and processing module, the obtained abnormal index of the cooling system is compared with the gradient standard threshold values. The gradient standard threshold values include a first standard threshold value and a second standard threshold value, and the first standard threshold value is less than the second standard threshold value. The abnormal index of the cooling system is compared with the first standard threshold value and the second standard threshold value respectively; If the abnormal index of the cooling system is greater than the second standard threshold value, it indicates that the temperature control effect is poor during the co-treatment process of waste hydrofluoric acid and leachate. At this time, a first-level warning signal is generated, and it is classified as an overheated operation state, and emergency measures are taken immediately; If the abnormal index of the cooling system is greater than or equal to the first standard threshold value and less than or equal to the second standard threshold value, it indicates that the temperature control effect is average during the co-treatment process of waste hydrofluoric acid and leachate. At this time, a second-level warning signal is generated, and it is classified as a possible normal operation state, and preventive intervention is carried out; If the abnormal index of the cooling system is less than the first standard threshold value, it indicates that the temperature control effect is good during the co-treatment process of waste hydrofluoric acid and leachate. At this time, no warning signal is generated, and it is classified as a normal operation state, indicating that the cooling system operates stably and no intervention is required.

Images