A direct shower type waste heat recovery acidic water treatment method

Abstract

The application relates to the technical field of water treatment, and discloses a direct-shower type waste heat recovery acid water treatment method. The method comprises the following steps: a pH value differential sensor group and an electric conductivity sensor are arranged at the interface of a buried pipe cold storage system and a direct-shower type waste heat recovery device, real-time monitoring is conducted on the whole process of acid water treatment, acid water quality change data are obtained, the acid water quality change data and system operation parameters are subjected to filtering treatment and working condition matching analysis, a cold storage-acid water treatment collaborative mode is obtained, heat chemical coupling analysis is conducted through a hyperboloid mapping network, corrosion risk assessment results are obtained, a double constraint optimization model of heat exchange efficiency and pH value adjustment is executed according to the corrosion risk assessment results, and an anti-corrosion control strategy is output. The application can accurately capture the complex nonlinear relationship between pH value change and temperature gradient, greatly improves the accuracy of corrosion risk prediction, and effectively avoids damage of equipment caused by corrosion.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of water treatment, in particular to a direct-shower type waste heat recovery acid water treatment method. BACKGROUND

[0002] With the continuous improvement of energy efficient utilization and environmental protection requirements in industrial production process, waste heat recovery technology is widely used in various industries. Especially in the metallurgical, chemical and power industries, a large amount of acid wastewater generated in high-temperature production process not only contains a large amount of waste heat, but also has high corrosiveness. The traditional waste heat recovery system is difficult to effectively cope with the corrosion problem of acid water. Although the existing underground pipe cold storage technology can realize cross-seasonal utilization of energy, when combined with acid water waste heat recovery, there is a contradiction between heat exchange efficiency and material corrosion. The current industry solution mainly adopts the method of adding an intermediate heat exchange link to isolate the acid medium, but this method significantly reduces the energy utilization efficiency.

[0003] The traditional acid water waste heat recovery system mainly adopts a fixed parameter control strategy, which lacks real-time response capability to the changes of pH value and temperature field distribution of acid water, resulting in that the system operating parameters are difficult to adapt to the changes of working conditions. At the same time, the existing monitoring system has limited corrosion risk assessment capability in the acid water treatment process, and cannot realize multi-objective collaborative optimization, so that the system is often in a suboptimal operating state. In addition, the traditional control method has insufficient data accumulation and learning ability in the long-term operation of the system, and it is difficult to effectively cope with the problems caused by equipment aging and performance degradation, which restricts the stability and service life of the system. SUMMARY

[0004] The application provides a direct-shower type waste heat recovery acid water treatment method, which can accurately capture the complex nonlinear relationship between pH value change and temperature gradient, greatly improve the accuracy of corrosion risk prediction, and effectively avoid damage to equipment caused by corrosion.

[0005] In a first aspect, the application provides a direct-shower type waste heat recovery acid water treatment method, which comprises:

[0006] A pH value differential sensor group and an electrical conductivity sensor are arranged at the interface between the underground pipe cold storage system and the direct-shower type waste heat recovery device to monitor the whole process of acid water treatment in real time, and obtain acid water quality change data;

[0007] The acid water quality change data and system operating parameters are subjected to filtering processing and working condition matching analysis to obtain a cold storage-acid water treatment collaborative mode;

[0008] The cold storage-acid water treatment collaborative mode and underground cold storage state data are input into a hyperboloid mapping network for thermally-chemically coupled analysis to obtain a corrosion risk assessment result;

[0009] According to the corrosion risk assessment result, a double constraint optimization model of heat exchange efficiency and pH value adjustment is executed, and an anti-corrosion control strategy is output.

[0010] In the technical scheme provided in the application, high-precision monitoring devices are arranged at the interfaces of the buried pipe cold storage system and the direct shower type waste heat recovery device, real-time monitoring of the whole process is realized, and the monitoring precision and data reliability are significantly improved. The hyperbolic surface mapping network used for thermally-chemically coupled analysis can accurately capture the complex nonlinear relationship between pH value change and temperature gradient, greatly improving the accuracy of corrosion risk prediction and effectively avoiding damage to equipment caused by corrosion. By establishing a double constraint optimization model of heat exchange efficiency and pH value adjustment, a balance between energy utilization efficiency, acid water treatment effect and equipment corrosion protection is realized, and the corrosion rate is controlled within a safe range by using a two-stage pH value control of coarse adjustment and fine adjustment based on the anti-corrosion control strategy of risk assessment. The cold storage-acid water treatment collaborative mode constructed by the application fully utilizes the complementary advantages of the buried pipe cold storage system and the direct shower type waste heat recovery device in energy and function, significantly reduces the system operation cost, reduces the amount of chemical reagents, and improves the waste heat recovery rate. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0012] Figure 1 An embodiment of the direct shower type waste heat recovery acid water treatment method in the embodiments of the application is shown in the figure. DETAILED DESCRIPTION

[0013] The embodiments of the application provide a direct shower type waste heat recovery acid water treatment method. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0014] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 An embodiment of the direct shower type waste heat recovery acid water treatment method in the present application includes:

[0015] Step S101, a pH differential sensor group and an electrical conductivity sensor are arranged at the interface of the underground pipe cold storage system and the direct shower type waste heat recovery device to monitor the entire acid water treatment process in real time and obtain acid water quality change data;

[0016] It can be understood that the execution subject of the present application can be a direct shower type waste heat recovery acid water treatment system, and can also be a terminal or a server, which is not limited here. The server is taken as an example for description of the embodiments of the present application.

[0017] Specifically, a pH differential sensor group and an electrical conductivity sensor are arranged at the interface of the underground pipe cold storage system and the direct shower type waste heat recovery device to monitor the entire acid water treatment process in real time. A first pH sensor and a first electrical conductivity sensor are installed between the water outlet of the underground pipe cold storage system and the water inlet of the direct shower type waste heat recovery device to construct an inlet parameter monitoring point, obtain inlet characteristic data of the acid water, and reflect the basic water quality information of the acid water before entering the waste heat recovery device. A second pH sensor and a second electrical conductivity sensor are installed between the water outlet of the direct shower type waste heat recovery device and the inlet of the acid water collection tank to construct an outlet parameter monitoring point, obtain outlet characteristic data of the acid water, and reflect the water quality change of the acid water after being treated by the waste heat recovery device. The acid water inlet characteristic data and the acid water outlet characteristic data are differentially calculated to obtain pH differential ΔpH and electrical conductivity differential ΔEC values. Through differential calculation, the change of the water quality in the treatment process is reflected, and the change trend of the acid water in the water treatment process is identified. The differential data are associated with the liquid level sensor and the temperature sensor data in the acid water collection tank for correlation analysis to form a multi-dimensional water quality parameter matrix. The multi-dimensional water quality parameter matrix contains the changes of pH and electrical conductivity, and also includes liquid level and temperature and other factors affecting the water quality change. The multi-dimensional water quality parameter matrix is arranged in time sequence, and a sliding window algorithm is applied for processing to extract the dynamic change trend in the time sequence, eliminate the influence of part of short-term fluctuations, obtain more stable and regular water quality change data, reflect the instantaneous change of the acid water quality, and reveal the long-term trend of the water quality in the treatment process to help realize continuous monitoring and adjustment of the water quality. The dynamic water quality change trend data are compared and analyzed with a preset acid water treatment standard range, and abnormal points are marked. The comparison and analysis process can quickly identify whether the water quality change exceeds the normal range, so that measures can be taken in time to deal with the problems.

[0018] Step S102, filtering and working condition matching analysis are performed on the acid water quality change data and system operation parameters to obtain a cold storage-acid water treatment collaborative mode;

[0019] Specifically, the pH value and conductivity data in the acid water quality change data are time series reorganized to generate an initial water quality feature sequence, reflecting the water quality fluctuation of the acid water in the treatment process. At the same time, in order to better understand the actual situation of system operation, the temperature sensor and pressure sensor in the ground pipe cold storage system are preprocessed to obtain a system operation feature sequence. The initial water quality feature sequence and the system operation feature sequence are combined to obtain an original coupled data matrix. The data matrix combines the change information of the acid water quality and the running state of the system, and can provide a more comprehensive system operation situation. Since the data contains certain noise, an adaptive Kalman filter algorithm is used to dynamically suppress the noise of the original coupled data matrix to reduce unnecessary interference. Through this process, a low-noise data stream is obtained to ensure the accuracy and reliability of the data. According to the time sequence relationship between the pH value in the low-noise data stream and the system temperature and pressure change, a multivariate transfer function is constructed to obtain an acid-base-temperature-pressure response model, describing the mutual relationship between the acid water quality change and the temperature and pressure change of the ground pipe cold storage system. The acid-base-temperature-pressure response model is parameter identified and sensitivity analyzed to extract the target influence factor and its quantitative relationship, which helps to identify the key factors affecting the water quality change and system operation, and to quantitatively analyze the change law of these factors to obtain acid-base balance correlation data. Through these correlation data, the interaction between different factors is understood. Based on the acid-base balance correlation data, the refrigerant-acid water heat transfer index and the pH value adjustment coefficient are calculated, and the working condition matching analysis is performed. Through this analysis, according to the water quality change and system operation state under different working conditions, the collaborative mode of cold storage and acid water treatment is optimized to ensure the optimal operation of the system under different working conditions.

[0020] In this embodiment, key parameters are extracted from the acid-base balance correlation data, including temperature difference, pH change rate and conductivity change value. These three parameters are important indicators reflecting water quality dynamics and heat transfer efficiency. By combining with the heat exchange theoretical model, a heat transfer efficiency function based on the coupling of water quality and thermodynamics is constructed. This function comprehensively reflects the energy exchange efficiency between the acidic water and the refrigerant in the direct shower heat recovery device, calculates the refrigerant-acidic water heat transfer index, and provides quantitative basis for evaluating the system thermal energy recovery performance. In order to realize the stable regulation and control of water quality, based on the deviation information between the current pH value recorded in the acid-base balance correlation data and the target pH value set by the system, a self-adaptive adjustment algorithm is executed through dynamic tracking and error feedback mechanism, and then the pH value adjustment coefficient is calculated. This coefficient represents the response intensity and adjustment rate of the system to the neutralization adjustment of acidic water, and is a key control parameter for maintaining the chemical stability of the system. The obtained refrigerant-acidic water heat transfer index and pH value adjustment coefficient are combined with the operating state parameters (such as current cooling load, flow rate, pressure, etc.) of the ground heat storage system to form a working condition matching degree matrix. This matrix reflects the comprehensive performance of the system under various operating conditions. In order to identify the system operating mode and classify it, fuzzy clustering analysis method is applied to the working condition matching degree matrix, so that each operating state is fuzzy classified according to similarity, forming the system operating condition classification. On the basis of the classified operating state, a state transition probability matrix is constructed to quantify the possibility of the system switching from one operating mode to another. Markov decision process is applied to optimize the strategy of all possible states, find the behavior selection with the maximum long-term benefit in each state, and obtain the optimal strategy function. Based on this, a mode switching decision table is formed. The mode switching decision table is matched with the refrigerant-acidic water heat transfer index and the pH value adjustment coefficient at the parameter level, and the calculation and fusion analysis are performed to determine the optimal cooperative operation strategy under different system states and water quality conditions, and the final cold storage-acid water treatment cooperative mode is output. This mode can realize the dynamic balance between heat recovery efficiency and water quality safety control, so that the system can maintain high efficiency and stable operation state under complex and changing working conditions.

[0021] In step S103, the cold storage-acid water treatment cooperative mode and the underground cold storage state data are input into the hyperboloid mapping network for thermally-chemically coupled analysis, and the corrosion risk assessment result is obtained.

[0022] Specifically, the core parameters representing the system operation characteristics are extracted from the constructed cold storage-acid water treatment collaborative mode, including the working condition type parameters for characterizing the operation category, the heat exchange performance indicators for measuring the system energy efficiency, and the pH adjustment quantitative values reflecting the chemical adjustment behavior. These parameters together constitute the collaborative mode feature data, which are used to describe the dynamic state of the system at both thermal and chemical levels. At the same time, in order to comprehensively reflect the underground environmental conditions, the soil temperature distribution and local heat flux density data are collected in real time from the temperature sensors arranged in the buried pipe sleeve heat exchanger buried area, which constitute the underground cold storage state data, representing the potential influence of the underground thermal physical background on the heat exchange process and chemical reaction. The above collaborative mode feature data and underground cold storage state data are input into the hyperbolic surface mapping network, and through the hyperbolic embedding layer, the Euclidean space features are nonlinearly mapped to the hyperbolic space, so that the originally high-dimensional and complex physical and chemical variables are compressed into nonlinear dimensionality reduction representations with better expressiveness. This mapping can enhance the geometric expression of data and maintain the structural relationship between multivariate, providing more compact feature representation for subsequent analysis. The nonlinear dimensionality reduction representation is input into the thermo-chemical coupling layer of the network, where the hyperbolic convolution operation is performed to extract the interaction features between the dynamic changes of the pH value of the acid water and the underground temperature gradient, and to construct the key physical-chemical coupling factors in the corrosion process. Finally, the corrosion driving factors are output, which are the basic sources of the potential corrosion risk of the system. The corrosion driving factors are transmitted to the risk quantification layer of the hyperbolic surface mapping network, and through multidimensional feature fusion and electrochemical model parameter calculation, the corrosion reaction activity on the material and environment interface is quantitatively calculated, and the spatially discretized corrosion rate distribution is obtained. This corrosion rate distribution reflects the intensity difference of corrosion at different positions, and serves as the basis for time extrapolation. In order to predict the corrosion evolution trend in the future period of time, the corrosion rate distribution is time series extrapolated, and the extrapolation result is compared with the corrosion resistance threshold of the used material. Through the distance measurement function in the hyperbolic space, it is evaluated whether the corrosion rate approaches or exceeds the safety boundary of the material, and the corresponding corrosion risk level is calculated, and finally the corrosion risk assessment result of the system is output.

[0023] Step S104, according to the corrosion risk assessment result, execute the double constraint optimization model of heat exchange efficiency and pH value adjustment, output the anti-corrosion control strategy.

[0024] Specifically, the risk level in the corrosion risk assessment result is standardized and mapped to corresponding corrosion protection constraints, including upper limit control of corrosion rate, critical range of pH value change, and maximum stress value allowed by key components of the system, etc. Through this conversion process, the originally qualitative or graded corrosion risk information enters the calculable optimization framework and becomes the basis condition for subsequent modeling. In establishing the optimization model, corrosion protection constraints are used as hard boundaries to construct a composite objective function containing multiple system operation objectives. Among them, the energy utilization efficiency objective function is used to evaluate the heat exchange efficiency generated by unit energy consumption of the system; the acid water treatment efficiency objective function measures the reaction completion degree and water quality stability of the acid water neutralization process; and the system operation cost objective function considers the influence of factors such as reagent dosage, equipment operation load, and maintenance frequency on the overall cost. The three objective functions are integrated to form an optimization objective model, ensuring the balance between operation efficiency and economy while ensuring the safety of the system's corrosion protection. A control parameter space is defined, which covers adjustable operating variables such as cooling liquid flow rate, pH adjuster dosage rate, heat exchanger inlet and outlet temperature difference set value, etc. Based on the defined control parameter space and the composite objective model, a non-dominated sorting genetic algorithm is introduced for multi-objective optimization solution. This algorithm continuously generates candidate solutions through simulation of the evolution process, and selects non-dominated solutions in three target dimensions to form a Pareto optimal solution set, i.e. the optimal control combination set in all trade-off states. Since each solution in the Pareto solution set performs differently in different target dimensions, a fuzzy membership function is used to evaluate the satisfaction degree of each solution. The fuzzy membership function gives a satisfaction score between 0 and 1 according to the closeness between the actual value and the expected value of each objective function. The control parameter combination with the highest overall satisfaction degree is selected as the optimal control solution for system operation through weighting or normalization processing. In obtaining the optimal control parameter combination, the pH value adjustment process is refined into two stages, namely the coarse adjustment stage and the fine adjustment stage. In the coarse adjustment stage, a larger adjustment step is used according to the deviation amplitude to quickly adjust the pH value to the target range; in the fine adjustment stage, a smaller pH adjustment coefficient is used to control the pH value in a more detailed manner, ensuring that the system does not overshoot or fluctuate. The entire adjustment process is based on real-time feedback data of the system to dynamically adjust the adjustment amplitude and period. Finally, a complete corrosion protection control strategy is automatically generated by combining the heat exchange efficiency control requirements and the pH value fine adjustment logic.

[0025] The key operating information, including real-time temperature, pressure, flow rate and acidity data, is collected from the target monitoring points set in the ground pipe cold storage system. These parameters constitute the multivariate input of the current system operating state. The original real-time state parameters are preprocessed, including outlier rejection, data smoothing, missing value interpolation, etc. At the same time, all parameters are converted to the same interval using the normalization method to obtain a stable and consistent system current operating state matrix. On this basis, combined with the optimal control parameter combination in the previously constructed anti-corrosion control strategy, the system current operating state matrix and the control strategy parameters are combined to construct an upper agent input vector. This vector reflects the physical operating state of the system and incorporates strategic control information, with the ability to describe the global control logic. In order to avoid the interference of redundant features on subsequent modeling, a feature selection algorithm is used to screen the agent input vector, extract key variables highly related to control behavior, and eliminate noise features and weakly correlated features, obtaining agent layer decision data with strong predictive ability and control direction. The agent layer decision data is analyzed by the upper decision function for global strategy analysis. The upper decision function is based on the reinforcement learning value function, support vector regressor or adaptive fuzzy logic model, and the goal is to identify the optimal adjustment direction while maintaining system stability and efficiency. By calculating the influence weight of each input feature on the system performance index (such as heat exchange efficiency, corrosion risk, pH stability, etc.), the adjustment direction of the system at the current time is output, i.e. to determine whether to strengthen the pH neutralization reaction, speed up heat release, or reduce system operating load, etc. According to the system adjustment direction output by the upper strategy analysis function, the specific control variables required for optimization in this round of regulation are further refined and optimized in the execution layer, such as refrigerant circulation flow rate, acid-base regulator concentration, valve opening degree or heat exchanger inlet and outlet temperature difference control value, etc. Through this process, precise direct-fall heat recovery control parameters are finally output, achieving multi-objective adaptive regulation under dynamic and complex working conditions.

[0026] In the embodiment of the present application, by setting a high-precision monitoring device at the interface between the underground pipe cold storage system and the direct shower heat recovery device, real-time monitoring of the entire treatment process is realized, and the monitoring accuracy and data reliability are significantly improved. The use of a hyperbolic surface mapping network for thermochemical coupling analysis can accurately capture the complex nonlinear relationship between pH value changes and temperature gradients, significantly improving the accuracy of corrosion risk prediction and effectively avoiding damage to equipment caused by corrosion. By establishing a dual-constraint optimization model of heat exchange efficiency and pH value adjustment, a balance between energy utilization efficiency, acid water treatment effect, and equipment corrosion protection is achieved, and the corrosion rate is effectively reduced within a safe range based on the two-stage pH value control of coarse adjustment and fine adjustment in the corrosion control strategy based on risk assessment. The cold storage-acid water treatment collaborative mode constructed by the present application fully utilizes the complementary advantages of energy and function of the underground pipe cold storage system and the direct shower heat recovery device, significantly reduces the system operation cost, reduces the amount of chemical reagents, and improves the heat recovery rate.

[0027] In a specific embodiment, the process of step S101 can specifically include the following steps:

[0028] A first pH value sensor and a first electrical conductivity sensor are installed between the water outlet of the underground pipe cold storage system and the water inlet of the direct shower heat recovery device to construct an inlet water parameter monitoring point and obtain acid water inlet characteristic data;

[0029] A second pH value sensor and a second electrical conductivity sensor are installed between the water outlet of the direct shower heat recovery device and the inlet of the acid water collection tank to construct an outlet water parameter monitoring point and obtain acid water outlet characteristic data;

[0030] The acid water inlet characteristic data and the acid water outlet characteristic data are differentially calculated to obtain pH value difference ΔpH and electrical conductivity difference ΔEC values;

[0031] The pH value difference ΔpH and the electrical conductivity difference ΔEC values are associated with the liquid level sensor and the temperature sensor data in the acid water collection tank for correlation analysis to obtain a multi-dimensional water quality parameter matrix;

[0032] The multi-dimensional water quality parameter matrix is arranged according to time sequence and processed by a sliding window algorithm to obtain dynamic water quality change trend data;

[0033] The dynamic water quality change trend data is compared and analyzed with the preset acid water treatment standard range and marked for abnormal points to obtain acid water quality change data.

[0034] Specifically, a first pH sensor and a first conductivity sensor are installed between the outlet of the ground heat exchanger and the inlet of the direct shower heat recovery device to construct an inlet water parameter monitoring point. This monitoring point captures the water quality state of the acidic water discharged from the ground heat exchanger before entering the direct shower device in real time, where the pH sensor measures the acid-base strength of the inlet water, and the conductivity sensor is used to sense the ion concentration level in the water body, both of which cooperatively construct the basic feature data set of the inlet water quality. At the same time, a second pH sensor and a second conductivity sensor are installed between the outlet of the direct shower heat recovery device and the inlet of the acidic water collection tank to construct an outlet water parameter monitoring point, realizing continuous monitoring of the pH and conductivity of the treated acidic water. This arrangement ensures that any changes in water quality during the passage through the direct shower device can be captured. Through the above sensor arrangement, a complete inlet and outlet water quality data stream is obtained, and the inlet and outlet water characteristic data are differentially calculated based on this to obtain pH differential ΔpH and conductivity differential ΔEC values. These two differential values reflect the adjustment and purification effect of the direct shower heat recovery device on the acidic water during the treatment process, where ΔpH is used to represent the degree of change in hydrogen ion concentration in the water body, reflecting the acid-base adjustment ability; ΔEC quantifies the ion migration behavior, revealing the removal or change trend of salts, metal ions or other conductive factors in the system. Based on the obtained ΔpH and ΔEC, the liquid level data and temperature data in the acidic water collection tank are simultaneously acquired, with a liquid level sensor and a temperature sensor installed inside the collection tank. The liquid level data are used to infer the balance between the inflow and outflow rates, thereby indirectly determining the treatment load and storage capacity; the temperature data reveal the heat exchange behavior between the water quality and the environment, and are related to the change in heat recovery efficiency. The four types of heterogeneous data ΔpH, ΔEC, liquid level, and temperature are fused through time sequence synchronization, data alignment, and unified dimension processing to construct a multi-dimensional water quality parameter matrix. This matrix records the state characteristics of the current system water quality in each sampling period and forms a time series data framework with dynamic change ability. To reveal the change trend of the acidic water quality during operation, the above multi-dimensional water quality parameter matrix is sequentially arranged in time series to construct a feature sequence reflecting the system operation history. To avoid the influence of short-term disturbances or outliers on trend judgment, a sliding window algorithm is introduced for data processing based on the sequence. The sliding window algorithm considers the influence of window length and step size on the sensitivity and stability of trend extraction results. It extracts local data segments on consecutive time slices and performs aggregation, smoothing, or coefficient of variation analysis on the data in the segments to form a set of state curves that slide with time. This method can eliminate the risk of misjudgment caused by short-term high-frequency disturbances and effectively capture medium and long-term trend changes, which helps to identify potential water quality hazards such as accelerated corrosion, pH fluctuation instability, and cumulative rise in conductivity. The dynamic water quality change trend data generated based on the sliding window algorithm are compared and analyzed with the preset acidic water treatment standard range item by item.The standard range usually includes the upper and lower limits of the specified pH value, the conductivity threshold, the temperature limit and the liquid level warning line, etc., for determining whether the current operation of the system is in a safe, stable and controllable working condition. The comparison analysis process realizes dynamic error discrimination by setting threshold functions and tolerance ranges, and marks each data segment that does not meet the preset standards as abnormal. The abnormal marking includes light fluctuation prompt, serious deviation warning and trend deterioration warning, etc. levels, and generates event labels according to the deviation degree. These abnormal points are defined as acid water quality change data together with all trend data.

[0035] In a specific embodiment, the process of performing step S102 can specifically include the following steps:

[0036] The pH value and conductivity in the acid water quality change data are time series reorganized to obtain an initial water quality feature sequence, and the temperature sensor and pressure sensor in the buried pipe cold storage system are real-time data preprocessed to obtain a system operation feature sequence;

[0037] The initial water quality feature sequence and the system operation feature sequence are combined to obtain an original coupled data matrix;

[0038] An adaptive Kalman filter algorithm is used to suppress dynamic noise of the original coupled data matrix to obtain a low-noise data stream;

[0039] A multivariate transfer function is constructed according to the time sequence relationship between the pH value and the system temperature and pressure changes in the low-noise data stream to obtain an acid-base-temperature-pressure response model;

[0040] Parameter identification and sensitivity analysis are performed on the acid-base-temperature-pressure response model to extract target influence factors and their quantitative relationships to obtain acid-base balance correlation data;

[0041] Based on the acid-base balance correlation data, the refrigerant-acid water heat exchange index and the pH value adjustment coefficient are calculated, and working condition matching analysis is performed to obtain a cold storage-acid water treatment collaborative mode.

[0042] Specifically, the core variables in the acid water quality change data, pH and conductivity, were time-series reorganized. By reorganizing these two key water quality parameters in chronological order, an initial water quality feature sequence reflecting the trend of water quality change was constructed. This sequence preserved the change trajectory of each variable in consecutive time slices and ensured that each dimension feature had the same measurement scale through standardization processing. At the same time, in order to comprehensively evaluate the driving effect of system operating conditions on water quality response, real-time operating data were obtained from temperature sensors and pressure sensors deployed in the middle of the underground pipe cold storage system. These raw data were preprocessed after collection, including denoising, outlier removal, trend smoothing, normalization processing, and missing data interpolation, to generate a system operating feature sequence. This sequence depicted the system's operating state in a given time period in the form of a continuous and uninterrupted data stream, especially in terms of temperature gradient and pressure fluctuation. This operating feature sequence and the initial water quality feature sequence complement each other, with the former representing the physical state and the latter reflecting the chemical properties. The fusion of the two becomes the basis for subsequent thermal-chemical coupling analysis. After synchronizing and structurally matching the initial water quality feature sequence and the system operating feature sequence in the time dimension, the original coupled data matrix was constructed, with each row corresponding to a time slice and each column corresponding to a variable, covering the state values of pH, conductivity, system temperature, and pressure at each time. The adaptive Kalman filter algorithm was used to dynamically suppress noise in the original coupled data matrix. This algorithm establishes a state prediction model and an observation model and automatically adjusts the noise covariance matrix based on the prediction error to achieve the optimal estimation of the system's true state. The filtering process preserves the dynamic change trend of the data and suppresses non-structural noise caused by mutations, electromagnetic interference, or sensor drift, resulting in a low-noise data stream. Based on the low-noise data stream, the dynamic response relationship between pH change and system temperature and pressure was analyzed, and a multivariate transfer function model was constructed. The transfer function model is a mathematical tool used to represent the dynamic causal relationship between input and output variables. In this model, system temperature and pressure are input variables, and pH is an output variable. Model parameters are solved through least squares estimation, recursive least squares, or frequency domain fitting methods. This acid-base-temperature-pressure response model reveals the influence path of thermal drive on acid-base regulation behavior and quantifies the transfer delay and gain effect of temperature gradient and pressure fluctuation on pH stability. By establishing this model, a causal mapping from physical state to chemical change is achieved. The acid-base-temperature-pressure response model was subjected to parameter identification and sensitivity analysis. Parameter identification obtained the quantitative influence coefficient of each control parameter on the pH output through the least error inversion method, while sensitivity analysis identified the most sensitive input factor to pH regulation during system operation through partial derivatives, perturbation response method, or Sobol global sensitivity analysis.The results of this process are summarized as acid-base balance correlation data, which include the weight contribution of each input parameter, the nonlinear interaction between variables, and the regulation amplitude of the stable operation interval. These data reflect the coupling characteristics between the physical system operating state and the acid water treatment capacity. Based on the acid-base balance correlation data, the working condition adaptability analysis and performance index quantification are carried out. The refrigerant-acid water heat exchange index is calculated, which is based on the heat exchange capacity between the refrigerant and the acid water under the condition of unit temperature difference, considering factors such as temperature gradient, pH response speed and fluid heat conduction capacity, reflecting the thermal conversion efficiency of the system. At the same time, combined with the current pH regulation dynamic response range and regulation speed of the system, the pH value regulation coefficient can be calculated, which reflects the required regulation energy consumption and response time for the system to recover to the target pH interval under unit disturbance, indirectly quantifying the control ability of the system chemical stability. The heat exchange index and the pH value regulation coefficient are input into the working condition matching analysis module, and through the matching degree score with different historical working conditions, the closest running mode of the system is identified, and the optimal cooperative strategy is selected according to the preset rules, and finally the cold storage-acid water treatment cooperative mode is obtained.

[0043] In a specific embodiment, the process of performing steps based on acid-base balance correlation data to calculate refrigerant-acid water heat exchange index and pH value regulation coefficient, and performing working condition matching analysis to obtain the cold storage-acid water treatment cooperative mode can specifically include the following steps:

[0044] Extract the temperature difference, pH value change rate and conductivity change value from the acid-base balance correlation data, and calculate the heat exchange efficiency through the temperature difference, pH value change rate and conductivity change value to obtain the refrigerant-acid water heat exchange index;

[0045] According to the deviation of the current pH value and the target pH value in the acid-base balance correlation data, adaptive adjustment is performed to obtain the pH value regulation coefficient;

[0046] The refrigerant-acid water heat exchange index, the pH value regulation coefficient and the system operating state parameters form a working condition matching degree matrix, and fuzzy clustering analysis is performed on the working condition matching degree matrix to obtain the system operating condition classification;

[0047] Based on the system operating condition classification, a state transition probability matrix is constructed, and the optimal strategy function is calculated by applying Markov decision process to obtain a mode switching decision table;

[0048] The mode switching decision table and the refrigerant-acid water heat exchange index, the pH value regulation coefficient are calculated by parameter matching to obtain the cold storage-acid water treatment cooperative mode.

[0049] Specifically, the core variables reflecting the system heat and mass exchange state and chemical reaction efficiency are extracted from the acid-base balance correlation data. The temperature difference represents the thermodynamic driving force in the heat exchange process between the refrigerant and acidic water, which is an important basis for evaluating the heat exchange rate. The pH value change rate characterizes the dynamic adjustment amplitude of the pH value per unit time, revealing the chemical response strength of the acidic water neutralization process. The conductivity change value reflects the trend of ion concentration change in water, which is related to the migration and reaction state of conductive factors such as salt and metal ions in water. These three variables are standardized and synchronized with time to participate in the comprehensive evaluation of heat exchange efficiency as input. The calculation process of heat exchange efficiency is based on these three types of variables to construct a multi-factor function. The temperature difference represents the heat flow intensity, the pH value change rate represents the driving rate of chemical reaction, and the conductivity change value indirectly depicts the physical property change of reaction products. After combining the three, the heat exchange efficiency index function is established. This function adopts a weighted linear model or a nonlinear regression model form, and after parameter identification and weight optimization, a unified quantitative index, the refrigerant-acidic water heat exchange index, is output. This index is dimensionless and has comparability under different operating conditions, reflecting both the heat energy conversion efficiency and the mass transfer ability in the reaction process. At the same time, according to the deviation between the current pH value and the set pH target value recorded in the acid-base balance correlation data, an adaptive adjustment strategy is implemented. This strategy builds a feedback controller to sense the current deviation in real time and determine whether it exceeds the pre-set tolerance range. When the deviation is significant, the system will increase the adjustment amplitude to quickly approach the target pH value. When the deviation is small, the system will enter a fine-tuning state to reduce the fluctuation amplitude to prevent over-adjustment, and calculate a variable that quantifies the adjustment rate and intensity, the pH value adjustment coefficient. The refrigerant-acidic water heat exchange index, the pH value adjustment coefficient, and the system operating state parameters form a working condition matching degree matrix. This matrix organizes data in time slices, with each row corresponding to the current operating time, including heat exchange efficiency, chemical adjustment ability, temperature, pressure, flow rate, conductivity, and other dimensions. Each column represents a working condition variable dimension, and each element of the matrix is used to evaluate the matching degree between the system operating state and the target control interval. To effectively classify the system operating conditions, the fuzzy clustering analysis method is applied to the working condition matching degree matrix. Fuzzy clustering allows each state to belong to multiple categories with different membership degrees, enabling the description of the transition state behavior of the system in the fuzzy boundary region. Through clustering techniques such as fuzzy C-means algorithm or Gaussian mixture model, the operating conditions are divided into several categories, such as high heat exchange and high stability, low heat exchange and high deviation, and medium heat exchange and medium fluctuation, forming a system operating condition classification map. Based on the working condition classification results obtained by fuzzy clustering, a state transition probability matrix is constructed. This matrix takes the working condition categories as state nodes and describes the probability of the system transitioning from one working condition to another between different time slices.The state transition matrix is obtained by calculating the state transition frequency through a sliding window and normalizing it, which is essentially a Markov state transition model with no memory feature and can be used to predict the running trend of the system in the future. On this basis, the Markov decision process model is introduced, and the optimal action strategy under each working condition state is solved by defining the state space, action set, reward function and state transition probability. The optimal policy function is calculated by using the policy iteration or value iteration algorithm, which outputs the control parameter adjustment direction and target combination that should be executed under the current working condition classification, and forms a mode switching decision table accordingly. The decision table takes the working condition classification as the input item, and takes the heat exchange parameter adjustment, pH adjustment priority, energy load adjustment strategy, etc. as the output item, realizing the logical closed loop from state recognition to parameter decision. The mode switching decision table and the calculated refrigerant-acid water heat exchange index and pH value adjustment coefficient are cascaded and conditionally matched for parameter calculation. The matching process uses heuristic search or fuzzy rule inference system to select the optimal strategy path and dynamically adjust the control parameters according to the comprehensive score of the heat exchange intensity and adjustment capacity under the current working condition, and finally outputs the cold storage-acid water treatment collaborative mode suitable for the current thermally-chemical state.

[0050] In a specific embodiment, the process of performing step S103 can specifically include the following steps:

[0051] According to the cold storage-acid water treatment collaborative mode, the working condition type parameters, heat exchange performance indicators and pH adjustment quantitative values are extracted as collaborative mode feature data;

[0052] The soil temperature distribution and heat flux density data are collected from the temperature sensors of the buried pipe jacket type heat exchanger buried position as underground cold storage state data;

[0053] The collaborative mode feature data and underground cold storage state data are input into the hyperbolic embedding layer of the hyperbolic surface mapping network, and the Euclidean space features are mapped to hyperbolic space through the hyperbolic embedding layer to obtain a nonlinear dimensionality reduction representation;

[0054] The nonlinear dimensionality reduction representation is input into the thermally-chemical coupling layer of the hyperbolic surface mapping network, and the interactive features between the pH value change and the temperature gradient are extracted through the thermally-chemical coupling layer to obtain a corrosion driving factor;

[0055] The corrosion driving factor is input into the risk quantification layer of the hyperbolic surface mapping network, and the electrochemical reaction activity of the material-environment interface is calculated through the risk quantification layer to obtain a spatially-discretized corrosion rate distribution;

[0056] The corrosion rate distribution is extrapolated in time series and compared with the material corrosion resistance threshold, and the risk level is calculated through the hyperbolic distance metric function to obtain a corrosion risk assessment result.

[0057] Specifically, in the process of constructing the corrosion risk assessment channel, three types of key feature parameters are extracted from the established cold storage-acidic water treatment collaborative mode. The working condition type parameter is mainly used to represent the control strategy or load mode of the current system operation, such as high load, partial load, and low load conditions, to determine the boundary conditions and control logic of the system operation. The heat exchange performance index quantifies the heat exchange capacity between the acidic water and the refrigerant, reflecting the heat transfer efficiency of the system in unit time. The pH adjustment quantification value, as a numerical parameter reflecting the accuracy of chemical regulation, represents the adjustment intensity and frequency of the system in response to acid-base disturbances. After normalization and time alignment, these three types of parameters are constructed into a collaborative mode feature dataset, which captures the state expression of the system's thermal-chemical coupling behavior in each sampling period. Meanwhile, considering that the efficiency of the heat exchange process and the occurrence of corrosion reactions are highly dependent on the geothermal environment of the heat exchanger, the environmental parameters of the buried pipe casing heat exchanger buried area are collected in real time, especially the soil temperature distribution and heat flux density data. This part of the underground cold storage state data is obtained in real time through a spatial sensing network composed of temperature sensor arrays and heat flux meters, reflecting the thermal conductivity of the underground medium and the heat capacity characteristics in the ground surface heat exchange process. Through interpolation and spatial reconstruction of this type of data, a continuous three-dimensional temperature field and heat flow distribution map are formed, providing a physical field background for subsequent heat-driven process identification. The collaborative mode feature data and underground cold storage state data are input into the hyperbolic embedding layer of the hyperboloid mapping network. This embedding layer maps high-dimensional, unstructured Euclidean space feature data to hyperbolic space with stronger expression ability. Since hyperbolic space has better hierarchical relationship modeling and nonlinear deformation capturing capabilities, it has a significant advantage in dealing with multi-variable, nonlinear, and weakly coupled problems in the system. In the embedding layer, by constructing feature projection functions based on hyperbolic geometry, such as hyperbolic bilinear transformation, hyperbolic activation function, and negative curvature mapping mechanism, the original structural relationship is maintained while the input data is nonlinearly reduced and expressed. The nonlinear reduced representation is input into the core operation module of the hyperboloid mapping network: the thermal-chemical coupling layer, where the model performs hyperbolic convolution operations to extract interactive features of pH value change trends and underground temperature gradient changes by constructing multi-dimensional convolution kernels in the hyperbolic geometric tensor space. The model can identify the dynamic relationship between the time sensitivity of pH change and the spatial continuity of temperature gradient change, quantify the coupling degree, and extract a set of representative corrosion driving factors. The essence of the corrosion driving factor is a set of variables with spatial topological structure and physical quantity interpretation, describing the core influence source of metal corrosion and material degradation in the current operating state of the system. The corrosion driving factors are input into the third functional layer of the network: the risk quantification layer, where the model quantifies and predicts the corrosion possibility by constructing electrochemical reaction activity functions and material interface reaction mechanism models.The layer considers multiple variables such as the surface activity of the metal material, the neutralization reaction rate of acid and alkali, and the conductivity coupling behavior, and outputs the electrochemical reaction activity index of the material-environment interface in combination with the reaction kinetics parameters. Based on the index, the corrosion rate spatial distribution map of the surface of the entire system key component is reconstructed in combination with the spatial coordinates of the surface discretization of the underground heat exchanger, forming a spatially discretized corrosion rate distribution. This distribution is used to identify high-risk corrosion areas and to judge the time and spatial cumulative effect of different operating states on corrosion in the system. The time series of the corrosion rate distribution is extrapolated. By constructing a sliding window-based time series prediction model, the corrosion rate evolution in the future is calculated by interpolating and fitting the corrosion rate trend of the recent several time slices. The extrapolated corrosion rate curve is compared and analyzed with the preset corrosion resistance threshold of the material. When the local rate is about to break through the safety upper limit, the risk level calculation mechanism is triggered by the model. The mechanism relies on a hyperbolic distance measurement function, that is, the geometric distance between the current feature representation and the risk boundary is measured in hyperbolic space. The smaller the distance value, the higher the corrosion risk; if the distance value tends to zero, the corrosion risk is critical. Based on the distance threshold, the corrosion risk assessment results are output, including risk level identification, high-risk area location labeling, and recommended control strategies.

[0058] In a specific embodiment, the process of performing step S104 can specifically include the following steps:

[0059] Converting the risk level in the corrosion risk assessment result into a corrosion protection constraint condition;

[0060] Based on the corrosion protection constraint condition, an optimization target model including an energy utilization efficiency target function, an acid water treatment efficiency target function, and a system operation cost target function is constructed;

[0061] According to the optimization target model, a control parameter space is defined, and a non-dominated sorting genetic solution is performed according to the control parameter space and the optimization target model, to obtain a Pareto optimal solution set;

[0062] The satisfaction degree of each solution in the Pareto optimal solution set is evaluated using a fuzzy membership function to obtain a satisfaction score, and the optimal control parameter combination is selected according to the satisfaction score;

[0063] Based on the optimal control parameter combination, the pH value adjustment process is divided into two stages of coarse adjustment and fine adjustment, different adjustment amplitudes are designed in combination with the pH adjustment coefficient, and an anti-corrosion control strategy is generated.

[0064] Specifically, the risk level contained in the corrosion risk assessment result is given in the form of classification labels, distance thresholds or rate intervals. These labels are converted into corrosion protection constraints by setting upper limit corrosion rate values, pH adjustment speed ranges, maximum allowable temperature difference gradients or heat exchanger surface stress limits. On this basis, the corrosion risk of each level is quantified as a specific numerical or logical constraint, serving as a boundary condition in the subsequent optimization process. Within the constraint domain of the corrosion protection constraint, a multi-objective optimization model is constructed to guide the system to seek an optimal balance among multiple performance indicators. The model sets three types of objective functions. The first is the energy utilization efficiency objective function, which aims to minimize the energy consumption per unit of cooling load or heat exchange. The heat exchange efficiency, COP (Coefficient of Performance) or energy consumption per unit of cooling capacity are used as measurement indicators. The second is the acid water treatment efficiency objective function, which emphasizes maintaining the pH value of the acid water within the target interval during system operation, while ensuring reasonable use of chemical neutralizing agents and improving reaction rates. The third is the system operation cost objective function, which considers the total cost of electricity consumption, water consumption, chemical consumption and equipment operation load. This objective plays a decisive role in the economic efficiency of the system. Under the joint action of the three objectives, the constructed optimization model focuses on maximizing system efficiency while ensuring the dynamic balance between corrosion control and economic operation. Based on the optimization objective model, a control parameter space is defined, which includes all key adjustable operating variables of the system, such as refrigerant circulation flow rate, inlet and outlet temperature settings, acid-base addition ratio, heat exchanger operating time interval, pH adjustment threshold upper and lower limits, etc. These variables form a multi-dimensional decision space. To efficiently search for the solution set in the complex, multi-dimensional and non-linear objective function and parameter space, a non-dominated sorting genetic algorithm is introduced as the solver. This algorithm simulates the "selection, crossover and mutation" mechanism in the biological evolution process, selects the non-dominated solutions in each generation of candidate solutions in multiple objective functions, and continuously iterates and optimizes to obtain the Pareto optimal solution set. Each solution in this solution set represents a set of parameter combinations that form an optimal compromise between energy efficiency, acid water treatment efficiency and operating cost. The entire set describes the optimal operating boundary of the system under different emphasis conditions. The satisfaction degree of each candidate solution in the Pareto solution set is evaluated. The fuzzy membership function technique is used, i.e., for each objective function, an ideal value and an acceptable threshold value are set, and the deviation between the target value of each solution and the ideal value is calculated to obtain the membership value in that target dimension. The membership values in all target dimensions are weighted and aggregated to obtain the overall satisfaction score. From all the Pareto solutions, the control parameter combination with the highest satisfaction score is selected as the optimal control solution under the current operating condition, ensuring its strongest overall adaptability in system target satisfaction. The optimal control parameter combination enhances the system's ability to respond quickly and accurately to corrosion conditions and implements phased control of the pH value adjustment process.The pH adjustment process is divided into two stages of coarse adjustment and fine adjustment. The coarse adjustment stage is used to quickly correct the pH deviation. When the system detects that the pH value deviates from the target range, a large adjustment coefficient is enabled to speed up the reaction and quickly return the pH value to the target critical region. When the pH value approaches the target range and enters the fine adjustment stage, the adjustment coefficient is scaled to achieve fine control with a smaller adjustment range, thereby avoiding over-adjustment or oscillation. The adjustment range of the entire phased adjustment strategy is set based on the dynamically adjusted pH adjustment coefficient calculated in the early stage. The coefficient is updated adaptively based on the system response sensitivity, adjustment inertia, and disturbance frequency to ensure both response speed and adjustment accuracy during the adjustment process. Based on the above linkage control logic of coarse adjustment and fine adjustment, a corrosion prevention control strategy is formed that adapts to the current corrosion risk level, energy efficiency target, and economic constraints.

[0065] In a specific embodiment, the direct shower waste heat recovery acid water treatment method further includes the following steps:

[0066] Real-time state parameters including temperature, pressure, flow rate, and acidity are obtained from the target monitoring points of the ground buried pipe cold storage system, and the real-time state parameters are preprocessed and normalized to obtain the current system operating state matrix;

[0067] An upper agent input vector is constructed based on the current system operating state matrix and the control parameter combination in the corrosion prevention control strategy, and target features are extracted through a feature selection algorithm to obtain agent layer decision data;

[0068] Global strategy analysis is performed on the agent layer decision data using an upper decision function to obtain the system adjustment direction, and the execution layer optimization target is determined based on the system adjustment direction to obtain the direct shower waste heat recovery control parameters.

[0069] Specifically, real-time state data including temperature, pressure, flow rate, and acidity from the target monitoring points of the ground heat exchanger system is obtained. These data provide information about the system's operation and are the basis for evaluating and optimizing system performance. By monitoring these state parameters in real time, the system's working state is understood in a timely manner, and potential operational problems such as excessive temperature, unstable flow, or excessive acidity are identified. To ensure the accuracy and effectiveness of subsequent analysis, real-time state parameters are preprocessed and normalized. The preprocessing process includes steps such as outlier detection and removal, data smoothing, and missing value filling to ensure data integrity and consistency. Normalization operation converts each parameter to the same dimension range, such as scaling temperature, pressure, flow rate, and acidity values to the standardized interval [0, 1], ensuring that parameters of different scales are effectively compared and processed in the same data framework. After preprocessing and normalization, the current system operating state matrix is obtained, which records the state information of each monitoring point at a specific time, reflecting the real-time operating state of the system. Based on the current system operating state matrix and the control parameter combination in the corrosion prevention control strategy, an upper agent input vector is constructed, including various system features extracted from the state matrix, such as temperature change rate, pressure fluctuation, flow change amplitude, and acidity dynamic change, etc. At the same time, control parameters in the corrosion prevention control strategy, such as pH adjustment coefficient, flow adjustment range, and temperature adjustment target, are integrated into the input vector. This input vector reflects the physical state of the system and also includes the necessary information for corrosion prevention control. To extract the most influential features for system adjustment, a feature selection algorithm is used to identify the most representative and predictive features from the input features, removing redundant or irrelevant features to reduce computational complexity and improve decision accuracy. Feature selection methods include information gain, variance analysis, and principal component analysis, which automatically select the most valuable features for system adjustment based on data distribution and correlation. Through feature selection, the decision data of the agent layer is obtained. The decision data of the agent layer is input into the upper decision function for global strategy analysis. The goal of the upper decision function is to consider all input data and control targets of the system, and through mathematical models and optimization algorithms, the adjustment direction of the system is obtained. For example, according to the trend of real-time state parameters, it is analyzed whether the current system operation tends to be abnormal or deviates from the optimal working condition, and whether temperature, flow, or pH adjustment is needed. This decision function is based on multi-objective optimization algorithms, machine learning models, or rule engines, dynamically evaluates the current state of the system, and provides reasonable adjustment suggestions. Through global strategy analysis, it is clear which direction the system should adjust to optimize heat exchange, reduce corrosion risk, and ensure long-term stable operation of the system. According to the output of the upper decision function, i.e., the system adjustment direction, the optimization target of the execution layer is determined.The optimization objectives of the execution layer include several aspects, such as optimizing the energy consumption of the system, improving the heat recovery efficiency, ensuring that the pH value is maintained within a reasonable range, and ensuring that the flow and pressure are stable, etc. According to the adjustment direction of the system, the control variables are optimized, such as adjusting the flow according to the requirement of heat exchange efficiency, adjusting the pH value according to the requirement of corrosion protection, adjusting the equipment load according to the temperature change, etc. Through these adjustments, the optimal performance of the system under different operating conditions is ensured, and at the same time, the corrosion risk is reduced, and the service life of the equipment is prolonged. Based on the optimal combination of control parameters, high-efficiency operation and corrosion protection control in the direct shower type waste heat recovery process are realized. The optimization of the control parameter combination needs to consider various objective functions, such as energy utilization efficiency, acid water treatment efficiency and system operation cost, etc., to ensure that the economy and efficiency of the system are maximized under the premise of meeting the corrosion protection requirements. Through step-by-step optimization and real-time adjustment of system parameters, intelligent management and fine regulation of the system are realized, and the overall performance and safety are improved.

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0071] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a direct shower type waste heat recovery acid water treatment device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0072] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A direct shower waste heat recovery acidic water treatment method, characterized in that: include: A pH differential sensor group and a conductivity sensor are installed at the interface between the buried pipe cold storage system and the direct-spray waste heat recovery device to monitor the entire acidic water treatment process in real time and obtain data on changes in acidic water quality. Filtering and analyzing the acidic water quality change data and system operating parameters and operating condition matching to obtain a cold storage-acidic water treatment synergistic model; The cold storage-acid water treatment synergistic mode and the underground cold storage state data are input into the hyperbolic mapping network for thermochemical coupling analysis to obtain the corrosion risk assessment result; specifically, the following steps are performed: extracting the working condition type parameters, heat exchange performance indicators and pH adjustment quantitative values ​​as the synergistic mode feature data according to the cold storage-acid water treatment synergistic mode; collecting the soil temperature distribution and heat flux density data from the temperature sensor at the buried position of the buried pipe-in-pipe heat exchanger as the underground cold storage state data; inputting the synergistic mode feature data and the underground cold storage state data into the hyperbolic embedding layer of the hyperbolic mapping network, and mapping the Euclidean space features to the hyperbolic embedding layer through the hyperbolic embedding layer. The nonlinear dimensionality reduction representation is obtained by inputting the nonlinear dimensionality reduction representation into the thermochemical coupling layer of the hyperbolic mapping network, and the interaction characteristics between the pH value change and the temperature gradient are extracted by performing a hyperbolic convolution operation through the thermochemical coupling layer to obtain the corrosion driving factor; the corrosion driving factor is input into the risk quantification layer of the hyperbolic mapping network, and the electrochemical reaction activity of the material-environment interface is calculated through the risk quantification layer to obtain a spatially discretized corrosion rate distribution; the corrosion rate distribution is extrapolated in time series and compared with the corrosion resistance threshold of the material, and the risk level is calculated by a hyperbolic distance metric function to obtain a corrosion risk assessment result; A dual-constraint optimization model of heat exchange efficiency and pH value adjustment is executed according to the corrosion risk assessment result, and an anti-corrosion control strategy is output.

2. The direct-spray waste heat recovery acidic water treatment method according to claim 1, characterized in that: A pH differential sensor group and a conductivity sensor are installed at the interface between the buried pipe cold storage system and the direct shower waste heat recovery device to monitor the entire acidic water treatment process in real time and obtain acidic water quality change data, including: A first pH sensor and a first conductivity sensor are installed between the water outlet of the buried pipe cold storage system and the water inlet of the direct-spray waste heat recovery device to establish an inlet parameter monitoring point and obtain acidic water inlet characteristic data; A second pH sensor and a second conductivity sensor are installed between the water outlet of the direct-spray waste heat recovery device and the inlet of the acidic water collection tank to establish an outlet water parameter monitoring point and obtain acidic water outlet characteristic data; Performing differential calculation on the acidic water inlet characteristic data and the acidic water outlet characteristic data to obtain a pH value difference ΔpH and an electrical conductivity difference ΔEC value; Correlating the pH value difference ΔpH and the conductivity difference ΔEC with the liquid level sensor and temperature sensor data in the acidic water collection tank to obtain a multidimensional water quality parameter matrix; Arranging the multidimensional water quality parameter matrix according to a time series and applying a sliding window algorithm to process it to obtain dynamic water quality change trend data; The dynamic water quality change trend data is compared and analyzed with a preset acidic water treatment standard range, and abnormal points are marked to obtain acidic water quality change data.

3. The direct-spray waste heat recovery acidic water treatment method according to claim 1, characterized in that: The filtering and operating condition matching analysis of the acidic water quality change data and system operating parameters is performed to obtain a cold storage-acidic water treatment collaborative mode, including: The pH value and conductivity in the acidic water quality change data are reorganized into time series to obtain an initial water quality feature sequence, and the temperature sensor and pressure sensor in the buried pipe cold storage system are preprocessed in real time to obtain a system operation feature sequence; Merging the initial water quality characteristic sequence with the system operation characteristic sequence to obtain an original coupling data matrix; Adopting an adaptive Kalman filter algorithm to dynamically suppress noise on the original coupled data matrix to obtain a low-noise data stream; Constructing a multivariable transfer function based on the temporal relationship between the pH value and the system temperature and pressure changes in the low-noise data stream to obtain an acid-base-temperature-pressure response model; Performing parameter identification and sensitivity analysis on the acid-base-temperature-pressure response model, extracting target influencing factors and their quantitative relationships, and obtaining acid-base balance correlation data; The refrigerant-acidic water heat exchange index and pH value adjustment coefficient are calculated based on the acid-base balance correlation data, and an operating condition matching analysis is performed to obtain a cold storage-acidic water treatment synergistic mode.

4. The direct-spray waste heat recovery acidic water treatment method according to claim 3, characterized in that: The refrigerant-acidic water heat exchange index and pH value adjustment coefficient are calculated based on the acid-base balance correlation data, and a working condition matching analysis is performed to obtain a cold storage-acidic water treatment synergistic mode, including: Extracting the temperature difference, pH value change rate, and conductivity change value from the acid-base balance correlation data, and performing heat exchange efficiency calculation based on the temperature difference, pH value change rate, and conductivity change value to obtain a refrigerant-acid water heat exchange index; performing adaptive adjustment according to the deviation between the current pH value and the target pH value in the acid-base balance associated data to obtain a pH value adjustment coefficient; The refrigerant-acid water heat exchange index, the pH value adjustment coefficient and the system operating state parameters are combined into a working condition matching matrix, and a fuzzy cluster analysis is performed on the working condition matching matrix to obtain a system operating condition classification; Based on the classification of the system operating conditions, a state transition probability matrix is ​​constructed, and the optimal strategy function is calculated by applying the Markov decision process to obtain a mode switching decision table; The mode switching decision table is used to perform parameter matching calculation with the refrigerant-acid water heat exchange index and the pH value adjustment coefficient to obtain a cold storage-acid water treatment coordinated mode.

5. The direct-spray waste heat recovery acidic water treatment method according to claim 1, characterized in that: The dual-constraint optimization model for heat exchange efficiency and pH value adjustment is executed according to the corrosion risk assessment result to output an anti-corrosion control strategy, including: Converting the risk level in the corrosion risk assessment result into a corrosion protection constraint condition; Based on the corrosion protection constraints, an optimization target model is constructed, which includes an energy utilization efficiency objective function, an acidic water treatment efficiency objective function, and a system operation cost objective function; Defining a control parameter space according to the optimization target model, and performing a non-dominated sorting genetic solution based on the control parameter space and the optimization target model to obtain a Pareto optimal solution set; Performing a satisfaction evaluation on each solution in the Pareto optimal solution set using a fuzzy membership function to obtain a satisfaction score, and selecting an optimal control parameter combination according to the satisfaction score; Based on the optimal control parameter combination, the pH value adjustment process is divided into two stages: coarse adjustment and fine adjustment. Different adjustment ranges are designed in combination with the pH adjustment coefficient, and an anti-corrosion control strategy is generated.

6. The direct-spray waste heat recovery acidic water treatment method according to claim 1, characterized in that: The direct-spray waste heat recovery acidic water treatment method further comprises: Acquire real-time status parameters including temperature, pressure, flow, and acidity from target monitoring points of the buried pipe cold storage system, and preprocess and normalize the real-time status parameters to obtain the current operating status matrix of the system; Constructing an upper-layer agent input vector based on the current operating state matrix of the system and the control parameters in the anti-corrosion control strategy, and extracting target features through a feature selection algorithm to obtain agent-layer decision data; Applying the upper-layer decision function to the agent-layer decision data to perform global strategy analysis, obtain the system adjustment direction, and determine the execution-layer optimization target according to the system adjustment direction to obtain the direct-spray waste heat recovery control parameters.

Images