Evaporation energy-saving adaptive control method and system based on multi-parameter analysis

Abstract

The present application provides an evaporation energy-saving adaptive control method and system under multi-parameter analysis, which relates to the field of data processing technology. The method obtains the evaporation control parameter space of a single-effect evaporator and randomly selects multiple initial evaporation control parameters that meet the uniform distribution constraint; based on the solution properties, environmental parameters and expected concentration index of the brine to be evaporated, the evaporation efficiency prediction of multiple initial evaporation control parameters at multiple nodes in a predetermined time zone is performed, multiple predicted evaporation efficiency sets are obtained, and multiple evaporation fitnesses are evaluated; with the evaporation control parameter space as a constraint, the evaporation control parameters are optimized according to the multiple evaporation fitnesses, the optimal evaporation control parameters are output, and the single-effect evaporator is controlled to perform evaporation operations. The present application solves the technical problem that the existing technology lacks a multi-parameter collaborative optimization method, resulting in high energy consumption and poor adaptability to environmental changes during the evaporation of brine, and achieves the technical effect of improving evaporation efficiency and reducing evaporation energy consumption.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for adaptively controlling evaporation energy saving under multi-parameter analysis. Background Art

[0002] Brine evaporation is a key link in the chlor-alkali chemical industry. Chloride ions and hydroxide ions in brine are transferred and combined through a single-effect evaporator to produce chlorine, hydrogen and sodium hydroxide.

[0003] Currently, energy-saving control methods for brine evaporation are typically based on a simple analysis of the evaporator's operating conditions, followed by empirical parameter adjustments or single-variable optimization, such as fixed temperature, pressure, or flow control. However, this control method based on a single parameter or empirical rules has significant limitations. On the one hand, it is unable to effectively exploit the synergistic effects between multiple evaporation control parameters, resulting in insufficient overall optimization capabilities. On the other hand, it has poor adaptability to changes in environmental conditions (such as initial solution concentration, external temperature and humidity, etc.), making it impossible to accurately adjust the evaporation process according to actual operating conditions. This makes it difficult to achieve optimal evaporation efficiency, resulting in high energy consumption and difficult to ensure the stability of the production process, which is not conducive to the sustainable development of the chlor-alkali chemical industry. Summary of the Invention

[0004] This application provides an evaporation energy-saving adaptive control method and system under multi-parameter analysis, which solves the technical problems in the prior art that the energy consumption during brine evaporation is high and the adaptability to environmental changes is poor due to the lack of a multi-parameter collaborative optimization method, and achieves the technical effect of improving evaporation efficiency and reducing evaporation energy consumption.

[0005] In view of the above problems, on the one hand, the present application provides an evaporation energy-saving adaptive control method under multi-parameter analysis, the method comprising: obtaining the evaporation control parameter space of a single-effect evaporator, and randomly selecting multiple initial evaporation control parameters that satisfy uniform distribution constraints; based on the solution properties, environmental parameters and expected concentration indicators of the brine to be evaporated, performing evaporation efficiency prediction of the multiple initial evaporation control parameters at multiple nodes in a predetermined time zone, obtaining multiple predicted evaporation efficiency sets, and evaluating to obtain multiple evaporation fitnesses; with the evaporation control parameter space as a constraint, optimizing the evaporation control parameters according to the multiple evaporation fitnesses, and outputting the optimal evaporation control parameters, wherein parameter optimization is performed according to a dynamic optimization direction and an adaptive optimization step length, and the dynamic optimization direction is adjustment towards the best or adjustment away from the worst; within the predetermined time zone, controlling the single-effect evaporator to perform evaporation operations according to the optimal evaporation control parameters.

[0006] On the other hand, the present application also provides an evaporation energy-saving adaptive control system under multi-parameter analysis, the system including: an initial evaporation control parameter selection module for obtaining the evaporation control parameter space of the single-effect evaporator and randomly selecting multiple initial evaporation control parameters that meet the uniform distribution constraint; an evaporation efficiency prediction and evaluation module for performing evaporation efficiency prediction of the multiple initial evaporation control parameters at multiple nodes in a predetermined time zone based on the solution properties, environmental parameters and expected concentration indicators of the brine to be evaporated, obtaining multiple predicted evaporation efficiency sets, and evaluating multiple evaporation fitnesses; an evaporation control parameter optimization module for optimizing the evaporation control parameters based on the multiple evaporation fitnesses with the evaporation control parameter space as a constraint, and outputting the optimal evaporation control parameters, wherein the parameter optimization is performed according to the dynamic optimization direction and the adaptive optimization step size, and the dynamic optimization direction is adjustment towards the best or adjustment away from the worst; an evaporation control module for controlling the single-effect evaporator to perform evaporation operations according to the optimal evaporation control parameters within the predetermined time zone.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Obtaining the evaporation control parameter space for a single-effect evaporator determines the scope for subsequent optimization. Using a random selection method that satisfies uniform distribution constraints, this method comprehensively covers possible parameter combinations, avoids biased parameter selection, and provides more possibilities for finding the global optimal solution. By comprehensively considering the solution properties of the brine to be evaporated, environmental parameters, and desired concentration indicators, the evaporation efficiency prediction more realistically reflects the complexities of the actual evaporation process. Evaluating the predicted evaporation efficiency yields multiple evaporation fitnesses, which quantify the performance of different parameter combinations in actual evaporation scenarios and provide guidance for subsequent parameter optimization. Based on the evaporation fitnesses obtained in the previous step, parameter optimization is performed within the constraints of the parameter space to find the optimal evaporation control parameters. The introduction of dynamic optimization directions and adaptive optimization step sizes allows for more flexible response to varying environmental and conditional conditions, enabling more efficient and accurate identification of the optimal evaporation control parameters. Within a predetermined time zone, the single-effect evaporator is controlled according to the optimal evaporation control parameters for evaporation. The resulting optimal evaporation control parameters are then applied to the actual evaporation process, ensuring that the evaporator operates according to the optimal parameter combination, thereby achieving an energy-efficient and efficient evaporation process.

[0009] In summary, the present application can comprehensively consider the evaporation control parameters, comprehensively consider multiple factors to perform accurate efficiency prediction and fitness evaluation, and find the optimal parameters through dynamic optimization, thereby improving the evaporation efficiency of the single-effect evaporator, achieving the goal of energy saving and consumption reduction, and being able to better adapt to various changes in the chemical production process, thereby improving the stability of the production process and ensuring the stability of product quality.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 Schematic diagram of the process of the adaptive control method for evaporation energy saving under multi-parameter analysis provided in an embodiment of the present application.

[0012] Figure 2 A schematic diagram of a process for obtaining multiple predicted evaporation efficiency sets in the evaporation energy-saving adaptive control method under multi-parameter analysis provided in an embodiment of the present application.

[0013] Figure 3 A schematic diagram of a process for obtaining optimal evaporation control parameters in the evaporation energy-saving adaptive control method under multi-parameter analysis provided in an embodiment of the present application.

[0014] Figure 4 Schematic diagram of the structure of the evaporation energy-saving adaptive control system under multi-parameter analysis provided in an embodiment of the present application.

[0015] Description of reference numerals: initial evaporation control parameter selection module 10 , evaporation efficiency prediction and evaluation module 20 , evaporation control parameter optimization module 30 , evaporation control module 40 . DETAILED DESCRIPTION

[0016] The embodiments of the present application provide an evaporation energy-saving adaptive control method and system under multi-parameter analysis, thereby solving the technical problems in the prior art, such as high energy consumption and poor adaptability to environmental changes during salt water evaporation due to the lack of a multi-parameter collaborative optimization method, and achieving the technical effect of improving evaporation efficiency and reducing evaporation energy consumption.

[0017] Example 1, as Figure 1 As shown, the embodiment of the present application provides an evaporation energy-saving adaptive control method under multi-parameter analysis, the method comprising:

[0018] Step S1: Obtain the evaporation control parameter space of the single-effect evaporator, and randomly select multiple initial evaporation control parameters that meet the uniform distribution constraint.

[0019] Specifically, the evaporation control parameter space refers to the set of possible ranges of control parameters that affect the evaporation process in a single-effect evaporator. The uniform distribution constraint is a restriction on the random selection of initial evaporation control parameters. This constraint requires that these initial parameters be uniformly distributed across the entire parameter space to ensure that all possible parameter combinations are covered.

[0020] The control system of the interactive single-effect evaporation controller collects historical control records and extracts all control parameters that may affect the evaporation process, such as steam supply, liquid inlet flow rate, liquid outlet flow rate, steam temperature, and steam pressure. Based on historical data and equipment manuals, the range of values ​​for each parameter is determined, thus generating the evaporation control parameter space. Next, a random number generator is used to randomly select multiple initial parameter combinations within this parameter space, ensuring that these parameter combinations are evenly distributed throughout the space. This allows for a comprehensive assessment of the impact of different parameters on evaporation efficiency.

[0021] By randomly selecting initial evaporation control parameters that meet the uniform distribution constraint in the evaporation control parameter space, all possible parameter combinations are covered, avoiding the limitations of parameter selection caused by human experience or traditional fixed value methods, and providing rich basic data for subsequently finding the global optimal evaporation control parameters.

[0022] Step S2: Based on the solution properties, environmental parameters and expected concentration index of the brine to be evaporated, perform evaporation efficiency prediction at multiple nodes in a predetermined time zone based on the multiple initial evaporation control parameters, obtain multiple predicted evaporation efficiency sets, and evaluate to obtain multiple evaporation fitnesses.

[0023] Specifically, solution properties refer to the chemical and physical characteristics of the brine to be evaporated, such as salt concentration and viscosity. Environmental parameters include the operating environment's temperature, humidity, and atmospheric pressure. The desired concentration index refers to the desired concentration level of the brine during the evaporation process. Using a computational model or simulation software, the evaporation efficiency of each initial evaporation control parameter combination is predicted based on the solution properties, environmental parameters, and desired concentration index of the brine to be evaporated. This evaporation efficiency prediction is performed at multiple nodes in a predetermined time zone (e.g., one node every hour throughout the day, for a total of 24 nodes) to simulate the dynamics of the evaporation process. The predicted results are then used to evaluate the performance of each control parameter combination in the actual evaporation process, resulting in the evaporation fitness of each of the multiple initial evaporation control parameters. This evaporation fitness is a comprehensive evaluation metric for different initial evaporation control parameters, taking into account solution properties, environmental parameters, and desired concentration index. It reflects the performance of each parameter combination in the actual evaporation process.

[0024] By comprehensively predicting and evaluating the evaporation efficiency based on multiple factors, we can more accurately evaluate the advantages and disadvantages of different initial evaporation control parameters, obtain evaluation results that are more in line with the actual needs of the evaporation process, provide a reliable basis for subsequent parameter optimization, and improve the accuracy and practicality of the entire evaporation control scheme.

[0025] Step S3: Taking the evaporation control parameter space as a constraint, optimizing the evaporation control parameters according to the multiple evaporation fitnesses, and outputting the optimal evaporation control parameters, wherein the parameter optimization is performed according to a dynamic optimization direction and an adaptive optimization step size, and the dynamic optimization direction is an optimization-oriented adjustment or an optimization-avoidance adjustment.

[0026] Specifically, dynamic optimization direction refers to the flexible adjustment of the optimization direction during the optimization process based on the current evaporation fitness. This can be either an optimization-oriented adjustment or an optimization-avoidance adjustment. An optimization-oriented adjustment is to adjust parameters in the direction of improving evaporation fitness (such as higher evaporation efficiency, closer to the desired concentration index, etc.); an optimization-avoidance adjustment is to avoid adjusting parameters in the direction of worsening evaporation fitness. The adaptive optimization step size is the magnitude of each parameter adjustment during the optimization process. This step size is not fixed, but is adapted based on specific circumstances (such as the current parameter position, the changing trend of evaporation fitness, etc.). For example, in an area close to the optimal solution, a smaller optimization step size may be required to more accurately find the optimal solution; in an area far from the optimal solution, a larger optimization step size can be used to speed up the optimization process.

[0027] The evaporation control parameter space obtained in step S1 is used as a constraint condition, that is, to ensure that the parameters in the optimization process are always within this legal value range. According to the multiple evaporation fitness obtained in step S2, an optimization algorithm is used to perform optimization to determine the optimal evaporation control parameters. This optimal evaporation control parameter is the optimal solution obtained through the optimization process, which can achieve the parameter setting with the highest efficiency and lowest energy consumption under specific working conditions. The optimization process can use genetic algorithms, particle swarm optimization algorithms, etc. During the optimization process, the parameters are adjusted according to the dynamic optimization direction and the adaptive optimization step length. For example, the dynamic optimization direction can be determined based on the comparison result of the current fitness and the previous round of fitness, and the adaptive optimization step length can be determined based on factors such as the estimated distance between the current parameter and the optimal parameter, the rate of change of fitness, etc.

[0028] The combination of dynamic optimization direction and adaptive optimization step size enables the optimization process to converge quickly to the optimal solution and to adjust parameters more finely when approaching the optimal solution, thereby improving the efficiency and accuracy of the optimization process and finding the optimal evaporation control parameters in the parameter space more efficiently and accurately, thus providing the optimal parameter combination for achieving efficient and energy-saving evaporation operations.

[0029] Step S4: within the predetermined time zone, controlling the single-effect evaporator to perform evaporation according to the optimal evaporation control parameters.

[0030] Specifically, the predetermined time zone refers to a pre-set time range during the evaporation operation. The optimal evaporation control parameters output from step S3 are input into the single-effect evaporator's control system, which can be an automated control system based on a PLC (Programmable Logic Controller) or a DCS (Distributed Control System). Within the predetermined time zone, the automated control system controls the evaporator's operation based on these optimal evaporation control parameters, ensuring that the evaporator operates in optimal working order. This achieves an efficient evaporation process, improves evaporation efficiency, reduces energy consumption, and consistently achieves the desired concentration index.

[0031] Furthermore, step S1 includes:

[0032] Step S11: obtaining an evaporation control parameter space of a single-effect evaporator, wherein the evaporation control parameters include steam supply, liquid inlet flow, liquid outlet flow, steam temperature, and steam pressure.

[0033] Step S12: Randomly select a first evaporation control parameter in the evaporation control parameter space and set it as the first initial evaporation control parameter. Randomly select a second evaporation control parameter again. If the Euclidean distance between the second evaporation control parameter and the first initial evaporation control parameter is greater than a predetermined distance threshold, set the second evaporation control parameter as the second initial evaporation control parameter.

[0034] Step S13: Continue to randomly select a third evaporation control parameter. If the Euclidean distance between the third evaporation control parameter and the first initial evaporation control parameter is greater than the predetermined distance threshold and the Euclidean distance between the third evaporation control parameter and the second initial evaporation control parameter is greater than the predetermined distance threshold, set the third evaporation control parameter as the third initial evaporation control parameter, iterate until a predetermined number is met, and output the multiple initial evaporation control parameters.

[0035] Specifically, steam supply refers to the amount of steam supplied to the single-effect evaporator to heat the brine and promote its evaporation. The inlet flow rate is the flow rate of the brine solution entering the single-effect evaporator, which affects the liquid level and residence time of the solution within the evaporator. The outlet flow rate is the flow rate of the solution flowing out of the single-effect evaporator and is related to factors such as the inlet flow rate and evaporation rate. The steam temperature is the temperature of the supplied steam, and different steam temperatures affect the heat transfer efficiency within the evaporator. The steam pressure is the pressure of the steam, which affects the energy transfer efficiency of the steam within the evaporator.

[0036] Consult the single-effect evaporator's equipment manual to obtain the evaporation control parameter space, including the ranges for control parameters such as steam supply, liquid inlet flow, liquid outlet flow, steam temperature, and steam pressure. For example, for a certain model of single-effect evaporator, the steam supply range is 5 to 20 kg / h, the liquid inlet flow range is 3 to 10 cubic meters / h, and the liquid outlet flow rate varies within a certain range based on factors such as the liquid inlet flow and evaporation rate. The steam temperature range is 100 to 150°C, and the steam pressure range is 100 to 500 kPa. These ranges together constitute the evaporation control parameter space, providing a complete range framework for subsequent selection of initial evaporation control parameters. This helps to comprehensively consider various possible parameter combinations and avoid missing important parameter values.

[0037] A first evaporation control parameter is randomly selected from the evaporation control parameter space and set as the first initial evaporation control parameter. A second evaporation control parameter is then randomly selected, and the Euclidean distance between the first and second initial evaporation control parameters is calculated. Each evaporation control parameter can be considered a dimension of a vector. The Euclidean distance between the vectors corresponding to the first and second initial evaporation control parameters is calculated using the Euclidean distance calculation formula and compared with a predetermined distance threshold. This predetermined distance threshold is a pre-set Euclidean distance value used to determine whether the randomly selected evaporation control parameters are sufficiently dispersed. If the Euclidean distance between the second evaporation control parameter and the first initial evaporation control parameter is greater than the predetermined distance threshold, the second evaporation control parameter is set as the second initial evaporation control parameter. Conversely, if the Euclidean distance between the second evaporation control parameter and the first initial evaporation control parameter is less than or equal to the predetermined distance threshold, the second evaporation control parameter is discarded, and a new evaporation control parameter is selected for determination. By setting the Euclidean distance judgment condition, the selected initial evaporation control parameters have a certain degree of dispersion, avoiding the selection of overly close parameter combinations. This ensures more comprehensive coverage of the evaporation control parameter space and increases the likelihood of finding a global optimal solution.

[0038] After determining the first and second initial evaporation control parameters, a third evaporation control parameter is randomly selected. The Euclidean distance between the third evaporation control parameter and the first and second initial evaporation control parameters is then calculated. If the Euclidean distance between the third evaporation control parameter and both parameters is greater than a predetermined distance threshold, the third evaporation control parameter is set as the third initial evaporation control parameter. Otherwise, the third evaporation control parameter is discarded, and a new evaporation control parameter is selected from the evaporation control parameter space for distance calculation and judgment. This iterative method continuously randomly selects evaporation control parameters and performs distance judgment to determine new initial evaporation control parameters until a predetermined number is met. This iterative selection method ensures that the multiple selected initial evaporation control parameters have good dispersion within the evaporation control parameter space, enabling a broader exploration of the parameter space. This provides more diverse and representative initial parameters for subsequent evaporation efficiency prediction and optimization operations, thereby increasing the probability of finding the optimal evaporation control parameters for the entire technical solution.

[0039] Further, such as Figure 2 As shown, step S2 includes:

[0040] Step S21: collecting solution properties and environmental parameters of the brine to be evaporated, wherein the solution properties include solution type, initial concentration and initial temperature, and the environmental parameters include ambient temperature and ambient humidity.

[0041] Step S22: Using the solution properties, environmental parameters, and desired concentration indicators as conditional constraints, the property characteristics of the single-effect evaporator as equipment constraints, and evaporation control as a guide, a sample evaporation control parameter set and a sample evaporation time set are retrieved through big data retrieval, and the evaporation efficiency under different sample evaporation control parameters and different sample evaporation times is marked to obtain a sample evaporation efficiency set.

[0042] Step S23: training an integrated learning operator based on the sample evaporation control parameter set, the sample evaporation time set, and the sample evaporation efficiency set until convergence to obtain an evaporation efficiency prediction plug-in, wherein the integrated learning operator includes at least a random forest, a BP neural network, and a support vector machine.

[0043] Step S24: Determine multiple evaporation times based on the multiple nodes in the predetermined time zone, use the evaporation efficiency prediction plug-in to perform evaporation efficiency prediction for the multiple initial evaporation control parameters under the multiple evaporation times, and output multiple predicted evaporation efficiency sets, where the evaporation time is the time interval between the node and the start time.

[0044] Specifically, the interactive control system or production task acquires the solution properties and environmental parameters of the brine to be evaporated. Solution properties include solution type, initial concentration, and initial temperature, while environmental parameters include ambient temperature and humidity. Solution type refers to the specific composition of the brine to be evaporated, such as sodium chloride brine, potassium chloride brine, and other salt solutions. Different solution types exhibit different physical and chemical properties during the evaporation process, which can affect evaporation efficiency. Initial concentration refers to the solute concentration of the brine before evaporation begins. This concentration affects the driving force for mass transfer during evaporation. Initial temperature refers to the temperature at which evaporation begins. Higher temperatures increase the kinetic energy of water molecules, which, to a certain extent, facilitates water evaporation. Ambient temperature refers to the temperature of the environment surrounding the evaporator. Ambient temperature is closely related to heat transfer during the evaporation process. For example, in a high-temperature environment, the rate of heat dissipation from evaporating brine to the environment is relatively slow, potentially facilitating evaporation. Ambient humidity refers to the water vapor content in the ambient air, typically expressed as relative humidity. Higher relative humidity indicates a closer saturation state, which is less conducive to water evaporation.

[0045] The sample evaporation control parameter set refers to a collection of evaporation control parameters collected from historical data. The sample evaporation time set refers to a collection of evaporation times corresponding to the sample evaporation control parameters. The sample evaporation efficiency set is a set of annotated evaporation efficiencies under different sample evaporation control parameters and sample evaporation times. The properties of a single-effect evaporator include its volume, heating method, and material. Using the collected solution properties, environmental parameters, and desired concentration indicators as constraints, the single-effect evaporator's properties serve as equipment constraints, and evaporation control as a guide, a search is performed on a big data platform (such as a chemical industry database or a large amount of evaporation process data accumulated within the enterprise). For example, from the evaporation process data accumulated by a chemical enterprise over many years, evaporation process data is selected that meets the following conditions: the solution type is sodium chloride brine, the initial concentration is within a certain range, and the ambient temperature and humidity are within specific ranges. The evaporation control parameters and evaporation times from this data are extracted to form a sample evaporation control parameter set and a sample evaporation time set. The evaporation efficiencies of these samples are then annotated based on actual production records or experimental data to obtain a sample evaporation efficiency set. By integrating various constraints to obtain relevant data from big data, a sample evaporation control parameter set, a sample evaporation time set, and a sample evaporation efficiency set are constructed, providing a rich data source for training the evaporation efficiency prediction model. This enables the model to learn the evaporation laws under different conditions, thereby improving the accuracy and reliability of the model prediction.

[0046] The evaporation efficiency prediction plug-in is a tool for predicting evaporation efficiency, trained using an ensemble learning operator. It outputs evaporation efficiency based on input information such as evaporation control parameters and evaporation time. Ensemble learning combines multiple machine learning algorithms to improve prediction performance. Each machine learning algorithm is an ensemble learning operator. In this embodiment, the ensemble learning operators include at least a random forest, a BP neural network, and a support vector machine. Data preprocessing, such as normalization, is performed on the sample evaporation control parameter set, sample evaporation time set, and sample evaporation efficiency set to improve model training. Then, using a machine learning framework (such as the Scikit-learn library in Python), the preprocessed sample evaporation control parameter set, sample evaporation time set, and sample evaporation efficiency set are input into ensemble learning operators such as a random forest, a BP neural network, and a support vector machine for training. During training, model parameters (such as the number of decision trees in the random forest and the weights and biases in the BP neural network) are continuously adjusted. Model convergence is determined by calculating the model error (such as the mean squared error) on the validation set. When the model converges—that is, the model parameters gradually stabilize during the iteration process and the model's prediction results no longer change significantly—these ensemble learning operators are combined to form the evaporation efficiency prediction plug-in. The ensemble learning operator combination process first requires setting a trust weight for each ensemble learning operator. For example, the mean squared error (MSE) can be used as an evaluation metric to assess the training accuracy of each ensemble learning operator on the validation set. Weights are calculated based on the inverse of the MSE, with the ratio of the inverse of the MSE of each ensemble learning operator to the sum of the inverse MSEs of all ensemble learning operators serving as the trust weight for each ensemble learning operator. When using the evaporation efficiency prediction plug-in for prediction, the evaporation control parameters and evaporation time are input into multiple ensemble learning operators to obtain the corresponding multiple predicted evaporation efficiencies. These predicted evaporation efficiencies are then weighted and summed according to the trust weights to obtain the final predicted evaporation efficiency. The evaporation efficiency prediction plug-in integrates the strengths of multiple machine learning algorithms, resulting in higher prediction accuracy and stability. Compared to a single machine learning model, it can better adapt to diverse data distributions and complex evaporation process relationships, providing a strong guarantee for accurate evaporation efficiency prediction.

[0047] Evaporation time refers to the interval from the start time to a specific node within a predetermined time zone. It is a key factor influencing evaporation efficiency. Evaporation efficiency varies at different evaporation times due to the varying progress of the evaporation process. Multiple nodes are determined based on the predetermined time zone. For example, if the predetermined time zone is 24 hours a day, a node is selected every hour, resulting in 24 nodes. For each node, the interval between the start time and the node is calculated as the evaporation time. Multiple initial evaporation control parameters and these evaporation times are then input into the evaporation efficiency prediction plug-in. The plug-in uses an ensemble learning algorithm to predict evaporation efficiency, obtaining the evaporation efficiency for each initial evaporation control parameter at each evaporation time. Finally, multiple predicted evaporation efficiency sets are output, each corresponding to an initial evaporation control parameter and containing the evaporation efficiency for that initial evaporation control parameter at different evaporation times. By predicting the evaporation efficiency of the initial evaporation control parameters at different evaporation times within the predetermined time zone, a comprehensive understanding of the evaporation efficiency of different parameter combinations at different time points is achieved. This provides a rich data foundation for subsequent evaporation fitness evaluation and optimization of evaporation control parameters, facilitating the identification of optimal evaporation control parameters.

[0048] Furthermore, in step S2, multiple evaporation fitnesses are evaluated, including:

[0049] Step S25: randomly selecting a first predicted evaporation efficiency set, performing mean calculation and variance calculation on the first predicted evaporation efficiency set, and determining a first predicted evaporation efficiency mean and a first predicted evaporation efficiency fluctuation coefficient.

[0050] Step S26: A first evaporation fitness is obtained by weighted calculation based on the first predicted evaporation efficiency mean and the first predicted evaporation efficiency fluctuation coefficient, and is added to the multiple evaporation fitnesses, wherein the evaporation fitness is positively correlated with the predicted evaporation efficiency mean and negatively correlated with the predicted evaporation efficiency fluctuation coefficient.

[0051] Specifically, a predicted evaporation efficiency set is randomly selected from multiple predicted evaporation efficiency sets output by the evaporation efficiency prediction plug-in, and is recorded as the first predicted evaporation efficiency set. The arithmetic mean and variance of all predicted evaporation efficiencies in the first predicted evaporation efficiency set are calculated to obtain the first predicted evaporation efficiency mean and the first predicted evaporation efficiency fluctuation coefficient. The predicted evaporation efficiency mean reflects the average level of evaporation efficiency under a set of evaporation control parameters. Variance is a statistic used to measure the degree of dispersion of a set of data and reflects the degree of fluctuation of the predicted evaporation efficiency. For the predicted evaporation efficiency set, the larger the variance, the greater the fluctuation of the evaporation efficiency at different time nodes or conditions. By calculating the predicted evaporation efficiency mean and fluctuation coefficient, we can fully understand the overall level and stability of the evaporation efficiency under a set of evaporation control parameters. The mean provides an average reference value, while the fluctuation coefficient reflects the changes in evaporation efficiency. These two indicators provide an important basis for the subsequent evaluation of evaporation adaptability.

[0052] The purpose of evaporation energy-saving control is to improve evaporation efficiency and the stability of the evaporation process. Based on this goal, a weighted calculation formula is set to perform a weighted calculation on the predicted evaporation efficiency mean and the predicted evaporation efficiency fluctuation coefficient to obtain the evaporation fitness. In this weighted calculation formula, the evaporation fitness is positively correlated with the predicted evaporation efficiency mean and negatively correlated with the predicted evaporation efficiency fluctuation coefficient. For example, the calculation formula can be set as F=a×Eb×V, where F is the evaporation fitness, E is the predicted evaporation efficiency mean, V is the predicted evaporation efficiency fluctuation coefficient, and a and b are weight coefficients, whose values ​​can be customized according to actual conditions. Substitute the first predicted evaporation efficiency mean and the first predicted evaporation efficiency fluctuation coefficient calculated above into this formula to obtain the first evaporation fitness, which is then added to multiple evaporation fitnesses.

[0053] Following the above calculation process, the evaporation fitness corresponding to each of the multiple predicted evaporation efficiency sets is determined, resulting in multiple evaporation fitnesses. This weighted calculation of evaporation fitnesses comprehensively considers both the average level and stability of evaporation efficiency, avoiding focusing solely on the mean efficiency while ignoring fluctuations, or focusing solely on fluctuations while ignoring the efficiency level. This provides a more comprehensive and reasonable evaluation basis for subsequent optimization of evaporation control parameters, helping to identify evaporation control parameters that perform well in terms of both efficiency and stability.

[0054] Further, such as Figure 3 As shown, step S3 includes:

[0055] Step S31: setting the initial evaporation control parameters as the initial solution, arranging the multiple initial evaporation control parameters from large to small according to the multiple evaporation fitnesses, and determining the initial solution sequence.

[0056] Step S32: Set the first P solutions of the initial solution sequence as optimal solutions, and set the last Q solutions as inferior solutions, to obtain P optimal solutions and Q inferior solutions, where Q is N times P, P and Q are both integers, and N is an integer greater than 5.

[0057] Step S33: Randomly cluster the Q inferior solutions according to the P superior solutions to obtain P solution sets, wherein the number of inferior solutions in each solution set is the same.

[0058] Step S34: For the P solution sets, the inferior solution with the smallest fitness in the solution set is set as a differential solution, P differential solution fitnesses are obtained, and P dynamic optimization directions are set according to the P superior solution fitnesses and the P differential solution fitnesses, wherein the dynamic optimization direction is an adjustment toward the optimal solution or an adjustment away from the inferior solution.

[0059] Step S35: According to the P dynamic optimization directions, the inferior solutions in the P solution sets are adjusted according to the adaptive optimization step size to obtain P updated solution sets, and the P updated solution sets are identified. If the fitness of the inferior solution in the updated solution set is greater than the fitness of the superior solution, the superior solution in the solution set is replaced by the inferior solution. If the adjusted inferior solution does not satisfy the evaporation control parameter space, no adjustment is performed.

[0060] Step S36: Continue iterative optimization based on the dynamic optimization direction and the adaptive optimization step size until a predetermined number of iterations is reached, output P current solution sets, select the current solution set with the largest sum of fitness among the P current solution sets as the optimal solution set, and output the optimal solution of the optimal solution set as the optimal evaporation control parameter.

[0061] Specifically, multiple initial evaporation control parameters and their corresponding evaporation fitness are obtained. These initial evaporation control parameters are set as the initial solution. Then, a sorting algorithm (such as bubble sort or quick sort) is used to sort these initial evaporation control parameters from highest to lowest evaporation fitness, obtaining an initial solution sequence. This sorting algorithm prioritizes initial evaporation control parameters with better evaporation fitness, providing a basis for subsequently distinguishing between optimal and inferior solutions, helping to quickly locate potential optimal solution regions and improving optimization efficiency.

[0062] The first P solutions in the initial solution sequence are considered optimal solutions. These solutions have relatively high evaporation fitness and are considered to be the best performing solutions among all the current initial solutions. The last Q solutions are considered inferior solutions. These solutions have relatively low evaporation fitness. P optimal solutions and Q inferior solutions are determined, where Q is N times P, P and Q are both integers, and N is an integer greater than 5. By distinguishing between optimal and inferior solutions, the solution space can be further analyzed and processed. Information from optimal solutions can be used to improve inferior solutions, thereby gradually finding more optimal evaporation control parameters.

[0063] A random number generator is used to randomly cluster the Q inferior solutions, dividing them into P groups. Each group corresponds to a superior solution. The superior solution and its corresponding inferior solutions are then combined to obtain P solution sets. Each solution set contains one superior solution and N inferior solutions (N = Q / P). Random clustering evenly distributes inferior solutions across different solution sets, preventing excessive concentration or dispersion of inferior solutions within certain solution sets. This provides a reasonable basis for grouping inferior solutions within different solution sets based on superior solutions.

[0064] For each solution set, the inferior solutions are traversed and the inferior solution with the lowest fitness is identified as the differential solution. The fitness of the differential solutions in each solution set is then compared with the fitness of the optimal solution. Based on the fitness of the P optimal solutions and the fitness of the P differential solutions, P dynamic optimization directions are set. The dynamic optimization direction can either adjust the inferior solutions toward the optimal solution (i.e., optimal adjustment) or avoid adjusting the inferior solutions toward the inferior solution (i.e., inferior avoidance adjustment). By determining the differential solutions and setting the dynamic optimization direction, a reasonable optimization strategy can be formulated based on the specific circumstances of each solution set, making the optimization process more targeted and improving both efficiency and accuracy.

[0065] Based on the determined dynamic optimization direction, the inferior solutions in each solution set are adjusted according to the adaptive optimization step size to form an updated solution set. If the fitness of the inferior solution in the updated solution set is greater than that of the superior solution, the superior solution is replaced by the inferior solution. During the adjustment process, parameter ranges must be checked before and after the adjustment. If the adjusted inferior solution does not meet the evaporation control parameter space (for example, the steam supply exceeds the maximum allowed by the equipment), the adjustment is not performed. Adjusting inferior solutions based on the dynamic optimization direction and adaptive optimization step size can gradually improve inferior solutions in the solution space, moving them towards a more optimal solution. At the same time, by restricting the adjusted inferior solutions to the evaporation control parameter space, the effectiveness and feasibility of parameter adjustment are guaranteed.

[0066] The predetermined number of iterations is the number of iterations in the optimization process that is pre-set. Iterative optimization is performed based on the dynamic optimization direction and the adaptive optimization step size. Each iteration adjusts the inferior solutions in each solution set according to the determined dynamic optimization direction and the adaptive optimization step size to form an updated solution set. After reaching the predetermined number of iterations, the sum of the fitness of all solutions in each solution set in the current P solution sets is calculated. The solution set with the largest sum of fitness is selected as the optimal solution set, and the optimal solution in the optimal solution set is output as the optimal evaporation control parameter. Through multiple iterative optimizations, the optimal solution can be searched more comprehensively in the solution space, and the optimal solution in the optimal solution set with the largest sum of fitness is finally selected as the optimal evaporation control parameter, which increases the probability of finding the global optimal evaporation control parameter, thereby optimizing the evaporation operation of the single-effect evaporator.

[0067] Furthermore, in step S34, P dynamic optimization directions are set according to the fitness of the P optimal solutions and the fitness of the P poor solutions, including:

[0068] Step S341: randomly selecting a first solution set from the P solution sets, and obtaining a first optimal solution fitness, a first poor solution fitness, and multiple first inferior solution fitnesses of the first solution set.

[0069] Step S342: Calculate the first inferior solution fitness mean of the multiple first inferior solution fitnesses, calculate the absolute values ​​of the deviations between the first superior solution fitness, the first differential solution fitness and the first inferior solution fitness mean, and determine the first superior solution deviation value and the first inferior solution deviation value.

[0070] Step S343: Set a first dynamic optimization direction according to the first optimal solution deviation value and the first inferior solution deviation value, and add it to the P dynamic optimization directions, wherein if the first optimal solution deviation value is greater than or equal to the first inferior solution deviation value, the first dynamic optimization direction is an optimization-oriented adjustment; if the first optimal solution deviation value is less than the first inferior solution deviation value, the first dynamic optimization direction is an inferior-avoidance adjustment.

[0071] Specifically, the specific process of determining the dynamic optimization direction includes: using a random number generator to randomly select a first solution set from P solution sets, and obtaining a first optimal solution fitness, a first differential solution fitness, and multiple first inferior solution fitnesses from the first solution set. The first optimal solution fitness is the fitness corresponding to the optimal solution in the first solution set, that is, the maximum fitness; the first differential solution fitness is the fitness corresponding to the differential solution in the first solution set, that is, the minimum fitness; and the first inferior solution fitness is the fitness corresponding to other solutions except the optimal solution and the differential solution.

[0072] Add the fitness values ​​of all inferior solutions in the first solution set and divide by the number of inferior solutions to obtain the mean fitness value of the first inferior solutions. This means the fitness value of the first inferior solutions reflects the average fitness level of the inferior solutions in the first solution set. Next, calculate the absolute value of the deviation between the fitness value of the first superior solution and the mean fitness value of the first inferior solutions, recorded as the first superior solution deviation value. Calculate the absolute value of the deviation between the fitness value of the first inferior solution and the mean fitness value of the first inferior solutions, recorded as the first inferior solution deviation value. By calculating the mean fitness value of the first inferior solution and the absolute value of the deviation from the fitness values ​​of the superior and inferior solutions, we can quantify the degree of deviation of the superior and inferior solutions from the average level of the inferior solutions, providing a quantitative basis for accurately setting the dynamic optimization direction.

[0073] The calculated deviation value of the first optimal solution is compared with the deviation value of the first inferior solution. If the deviation value of the first optimal solution is greater than or equal to the deviation value of the first inferior solution, the first dynamic optimization direction is set to the optimal adjustment; if the deviation value of the first optimal solution is less than the deviation value of the first inferior solution, the first dynamic optimization direction is set to the inferior adjustment. By setting the first dynamic optimization direction in this way, a reasonable optimization strategy can be formulated based on the deviation of the optimal solutions and inferior solutions in the first solution set from the average level of inferior solutions, thereby improving the optimization efficiency and more quickly moving towards the optimal solution or away from the worst solution.

[0074] The operations from step S341 to step S343 are performed for each solution set in the P solution sets, and a corresponding dynamic optimization direction is set for each solution set.

[0075] Furthermore, the adaptive optimization step length is obtained, including:

[0076] Step S3-1: determining a first optimization fitness of a first direction according to the first dynamic optimization direction, wherein the first optimization fitness is a first optimal solution fitness or a first differential solution fitness.

[0077] Step S3-2: Calculate the ratios of multiple first inferior solution fitnesses to the first optimal solution fitnesses respectively, and determine multiple compensation coefficients, wherein, if the first optimal solution fitness is the first optimal solution fitness, then the compensation coefficient is the ratio of the first inferior solution fitness to the first optimal solution fitness; if the first optimal solution fitness is the first differential solution fitness, then the compensation coefficient is the ratio of the first differential solution fitness to the first inferior solution fitness.

[0078] Step S3-3: Optimize the initial optimization step length according to the multiple compensation coefficients, determine a first step length set, and add it to the adaptive optimization step length.

[0079] Specifically, for the first solution set selected above, the first optimization fitness of the first direction is determined according to the determined first dynamic optimization direction. If the first dynamic optimization direction is an adjustment towards optimality, then the first optimization fitness is the first optimal solution fitness; if the first dynamic optimization direction is an adjustment away from inferiority, the first optimization fitness is the first inferior solution fitness.

[0080] The fitness of multiple first inferior solutions is obtained, and the ratios of the fitness of the multiple first inferior solutions to the first optimization fitness are calculated respectively. Multiple compensation coefficients are determined. The compensation coefficients reflect the proportional relationship in fitness between the inferior solution and the optimization reference solution (optimal solution or poor solution) and are used to optimize the initial optimization step size. When the first optimization fitness is the first optimal solution fitness, that is, the optimization reference solution is an optimal solution, the compensation coefficient is the ratio of the fitness of the first inferior solution to the fitness of the first optimal solution. When the first optimization fitness is the first poor solution fitness, that is, the optimization reference solution is a poor solution, the compensation coefficient is the ratio of the fitness of the first poor solution to the fitness of the first inferior solution. Calculating the compensation coefficients can quantify the fitness relationship between the inferior solution and the optimization reference solution, providing a basis for adjusting the optimization step size according to different inferior solutions, thereby improving the adaptability and accuracy of the optimization step size setting.

[0081] The first step length set is an optimized set of optimization step lengths obtained by adjusting the initial optimization step length based on multiple compensation coefficients. It includes the optimized optimization step lengths for each inferior solution. The initial optimization step length is the basic parameter adjustment range set at the beginning of the optimization process. It includes the initial adjustment ranges for evaporation control parameters such as steam supply, inlet flow rate, outlet flow rate, steam temperature, and steam pressure. For each solution set, the initial optimization step length is optimized using multiple compensation coefficients. This compensation coefficient is multiplied by the initial optimization step length to determine multiple first step lengths, each corresponding to a inferior solution in the solution set. These first step lengths are aggregated to form a set of first step lengths and added to the adaptive optimization step length to facilitate subsequent optimization of multiple inferior solutions. By optimizing the initial optimization step length based on the compensation coefficients, the optimization step length can be more adaptable to the different inferior solutions, improving optimization accuracy. Different inferior solutions are assigned different optimization step lengths based on their fitness relationship with the reference solution, making the optimization process more rational and efficient.

[0082] In summary, the evaporation energy-saving adaptive control method based on multi-parameter analysis provided in the embodiments of the present application has the following technical effects:

[0083] Obtaining the evaporation control parameter space for a single-effect evaporator determines the scope for subsequent optimization. Using a random selection method that satisfies uniform distribution constraints, this method comprehensively covers possible parameter combinations, avoids biased parameter selection, and provides more possibilities for finding the global optimal solution. By comprehensively considering the solution properties of the brine to be evaporated, environmental parameters, and desired concentration indicators, the evaporation efficiency prediction more realistically reflects the complexities of the actual evaporation process. Evaluating the predicted evaporation efficiency yields multiple evaporation fitnesses, which quantify the performance of different parameter combinations in actual evaporation scenarios and provide guidance for subsequent parameter optimization. Based on the evaporation fitnesses obtained in the previous step, parameter optimization is performed within the constraints of the parameter space to find the optimal evaporation control parameters. The introduction of dynamic optimization directions and adaptive optimization step sizes allows for more flexible response to varying environmental and conditional conditions, enabling more efficient and accurate identification of the optimal evaporation control parameters. Within a predetermined time zone, the single-effect evaporator is controlled according to the optimal evaporation control parameters for evaporation. The resulting optimal evaporation control parameters are then applied to the actual evaporation process, ensuring that the evaporator operates according to the optimal parameter combination, thereby achieving an energy-efficient and efficient evaporation process.

[0084] Overall, the embodiments of the present application can comprehensively consider the evaporation control parameters, comprehensively consider multiple factors to perform accurate efficiency prediction and fitness evaluation, and find the optimal parameters through dynamic optimization, thereby improving the evaporation efficiency of the single-effect evaporator, achieving the goal of energy saving and consumption reduction, and being able to better adapt to various changes in the chemical production process, thereby improving the stability of the production process and ensuring the stability of product quality.

[0085] Example 2, as Figure 4 As shown, the embodiment of the present application provides an evaporation energy-saving adaptive control system under multi-parameter analysis, and the system includes:

[0086] The initial evaporation control parameter selection module 10 is used to obtain the evaporation control parameter space of the single-effect evaporator and randomly select a plurality of initial evaporation control parameters that meet the uniform distribution constraint.

[0087] The evaporation efficiency prediction and evaluation module 20 is used to perform evaporation efficiency prediction at multiple nodes in a predetermined time zone based on the solution properties, environmental parameters and desired concentration index of the brine to be evaporated, obtain multiple predicted evaporation efficiency sets, and evaluate multiple evaporation fitness levels.

[0088] The evaporation control parameter optimization module 30 is used to optimize the evaporation control parameters based on the multiple evaporation fitnesses with the evaporation control parameter space as a constraint, and output the optimal evaporation control parameters. The parameter optimization is performed based on a dynamic optimization direction and an adaptive optimization step size, wherein the dynamic optimization direction is an optimal adjustment or an unfavorable adjustment.

[0089] The evaporation control module 40 is configured to control the single-effect evaporator to perform evaporation according to the optimal evaporation control parameters within the predetermined time zone.

[0090] Furthermore, the initial evaporation control parameter selection module 10 of the embodiment of the present application is used to perform the following steps:

[0091] An evaporation control parameter space of a single-effect evaporator is obtained, wherein the evaporation control parameters include a steam supply rate, a liquid inlet flow rate, a liquid outlet flow rate, a steam temperature, and a steam pressure; a first evaporation control parameter is randomly selected from the evaporation control parameter space and set as a first initial evaporation control parameter; a second evaporation control parameter is randomly selected again, and if a Euclidean distance between the second evaporation control parameter and the first initial evaporation control parameter is greater than a predetermined distance threshold, the second evaporation control parameter is set as the second initial evaporation control parameter; a third evaporation control parameter is continuously randomly selected, and if a Euclidean distance between the third evaporation control parameter and the first initial evaporation control parameter is greater than the predetermined distance threshold and a Euclidean distance between the third evaporation control parameter and the second initial evaporation control parameter is greater than the predetermined distance threshold, the third evaporation control parameter is set as the third initial evaporation control parameter; the selection is iterated until a predetermined number is met, and the multiple initial evaporation control parameters are output.

[0092] Furthermore, the evaporation efficiency prediction and evaluation module 20 of the embodiment of the present application is further configured to perform the following steps:

[0093] The solution properties and environmental parameters of the brine to be evaporated are collected, wherein the solution properties include solution type, initial concentration and initial temperature, and the environmental parameters include ambient temperature and ambient humidity; with the solution properties, environmental parameters and desired concentration index as conditional constraints, the property characteristics of the single-effect evaporator as equipment constraints, and evaporation control as a guide, a sample evaporation control parameter set and a sample evaporation time set are retrieved through big data retrieval, and the evaporation efficiency under different sample evaporation control parameters and different sample evaporation times is marked to obtain a sample evaporation efficiency set; an ensemble learning operator is trained based on the sample evaporation control parameter set, the sample evaporation time set and the sample evaporation efficiency set until convergence to obtain an evaporation efficiency prediction plug-in, wherein the ensemble learning operator includes at least a random forest, a BP neural network and a support vector machine; multiple evaporation times are determined according to multiple nodes in the predetermined time zone, and the evaporation efficiency prediction plug-in is used to execute evaporation efficiency prediction of the multiple initial evaporation control parameters under the multiple evaporation times, and output multiple predicted evaporation efficiency sets, wherein the evaporation time is the time interval between the node and the starting time.

[0094] Furthermore, the evaporation efficiency prediction and evaluation module 20 of the embodiment of the present application is further configured to perform the following steps:

[0095] The solution properties and environmental parameters of the brine to be evaporated are collected, wherein the solution properties include solution type, initial concentration and initial temperature, and the environmental parameters include ambient temperature and ambient humidity; with the solution properties, environmental parameters and desired concentration index as conditional constraints, the property characteristics of the single-effect evaporator as equipment constraints, and evaporation control as a guide, a sample evaporation control parameter set and a sample evaporation time set are retrieved through big data retrieval, and the evaporation efficiency under different sample evaporation control parameters and different sample evaporation times is marked to obtain a sample evaporation efficiency set; an ensemble learning operator is trained based on the sample evaporation control parameter set, the sample evaporation time set and the sample evaporation efficiency set until convergence to obtain an evaporation efficiency prediction plug-in, wherein the ensemble learning operator includes at least a random forest, a BP neural network and a support vector machine; multiple evaporation times are determined according to multiple nodes in the predetermined time zone, and the evaporation efficiency prediction plug-in is used to execute evaporation efficiency prediction of the multiple initial evaporation control parameters under the multiple evaporation times, and output multiple predicted evaporation efficiency sets, wherein the evaporation time is the time interval between the node and the starting time.

[0096] Furthermore, the evaporation control parameter optimization module 30 of the embodiment of the present application is further configured to perform the following steps:

[0097] The initial evaporation control parameters are set as the initial solution, and the multiple initial evaporation control parameters are arranged from large to small according to the multiple evaporation fitnesses to determine the initial solution sequence; the first P solutions of the initial solution sequence are set as optimal solutions, and the last Q solutions are set as inferior solutions, and P optimal solutions and Q inferior solutions are obtained, wherein Q is N times of P, P and Q are both integers, and N is an integer greater than 5; the Q inferior solutions are randomly clustered according to the P optimal solutions to obtain P solution sets, wherein the number of inferior solutions in each solution set is the same; for the P solution sets, the inferior solution with the smallest fitness in the solution set is set as a differential solution, and P differential solution fitnesses are obtained, and P dynamic optimization directions are set according to the P optimal solution fitnesses and the P differential solution fitnesses, wherein the dynamic optimization directions are dynamically optimized. The dynamic optimization direction is an adjustment toward the best or an adjustment away from the worst; according to the P dynamic optimization directions, the inferior solutions in the P solution sets are adjusted according to the adaptive optimization step size to obtain P updated solution sets, and the P updated solution sets are identified. If the fitness of the inferior solution in the updated solution set is greater than the fitness of the superior solution, the superior solution in the solution set is replaced by the inferior solution, wherein if the adjusted inferior solution does not satisfy the evaporation control parameter space, no adjustment is performed; based on the dynamic optimization direction and the adaptive optimization step size, iterative optimization is continued until a predetermined number of iterations is reached, P current solution sets are output, the current solution set with the largest sum of fitness in the P current solution sets is selected as the optimal solution set, and the superior solution of the optimal solution set is output as the optimal evaporation control parameter.

[0098] Furthermore, P dynamic optimization directions are set according to the fitness of the P optimal solutions and the fitness of the P poor solutions, and the execution steps include:

[0099] A first solution set is randomly selected from the P solution sets, and a first optimal solution fitness, a first differential solution fitness, and multiple first inferior solution fitnesses of the first solution set are obtained; a first inferior solution fitness mean of the multiple first inferior solution fitnesses is calculated, and the absolute values ​​of the deviations between the first optimal solution fitness, the first differential solution fitness, and the first inferior solution fitness mean are calculated respectively to determine a first optimal solution deviation value and a first inferior solution deviation value; a first dynamic optimization direction is set according to the first optimal solution deviation value and the first inferior solution deviation value, and is added to the P dynamic optimization directions, wherein, if the first optimal solution deviation value is greater than or equal to the first inferior solution deviation value, the first dynamic optimization direction is an optimization-oriented adjustment; if the first optimal solution deviation value is less than the first inferior solution deviation value, the first dynamic optimization direction is an inferiority-avoidance adjustment.

[0100] Furthermore, the evaporation control parameter optimization module 30 of the embodiment of the present application is further configured to perform the following steps:

[0101] Determine the first optimization fitness of the first direction according to the first dynamic optimization direction, wherein the first optimization fitness is the first optimal solution fitness or the first differential solution fitness; calculate the ratios of multiple first inferior solution fitnesses to the first optimization fitness respectively, and determine multiple compensation coefficients, wherein, if the first optimization fitness is the first optimal solution fitness, then the compensation coefficient is the ratio of the first inferior solution fitness to the first optimal solution fitness; if the first optimization fitness is the first differential solution fitness, then the compensation coefficient is the ratio of the first differential solution fitness to the first inferior solution fitness; optimize the initial optimization step size according to the multiple compensation coefficients, determine the first step size set, and add it to the adaptive optimization step size.

[0102] Through the detailed description of the evaporation energy-saving adaptive control method under multi-parameter analysis in the foregoing specification, those skilled in the art can clearly understand the evaporation energy-saving adaptive control system under multi-parameter analysis in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant details can be referred to the description of the method section.

[0103] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The adaptive control method of evaporation energy saving under multi-parameter analysis is characterized in that the method include: Obtain the evaporation control parameter space of the single-effect evaporator and randomly select multiple initial evaporation control parameters that meet the uniform distribution constraint; Based on the solution properties, environmental parameters, and desired concentration index of the brine to be evaporated, performing evaporation efficiency prediction for the multiple initial evaporation control parameters at multiple nodes in a predetermined time zone, obtaining multiple predicted evaporation efficiency sets, and evaluating to obtain multiple evaporation fitnesses; Taking the evaporation control parameter space as a constraint, optimizing the evaporation control parameters according to the multiple evaporation fitnesses, and outputting the optimal evaporation control parameters, wherein the parameter optimization is performed according to a dynamic optimization direction and an adaptive optimization step size, and the dynamic optimization direction is an optimization-oriented adjustment or an optimization-avoidance adjustment; In the predetermined time zone, controlling the single-effect evaporator to perform evaporation operation according to the optimal evaporation control parameter; Among them, multiple evaporation fitnesses are evaluated, including: Randomly selecting a first predicted evaporation efficiency set, performing mean calculation and variance calculation on the first predicted evaporation efficiency set, and determining a first predicted evaporation efficiency mean and a first predicted evaporation efficiency fluctuation coefficient; A first evaporation fitness is obtained by weighted calculation based on the first predicted evaporation efficiency mean and the first predicted evaporation efficiency fluctuation coefficient, and is added to the multiple evaporation fitnesses, wherein the evaporation fitness is positively correlated with the predicted evaporation efficiency mean and negatively correlated with the predicted evaporation efficiency fluctuation coefficient.

2. The evaporation energy-saving adaptive control method based on multi-parameter analysis according to claim 1 is characterized in that: Obtain the evaporation control parameter space of the single-effect evaporator and randomly select multiple initial evaporation control parameters that satisfy the uniform distribution constraint, including: Obtaining an evaporation control parameter space of a single-effect evaporator, wherein the evaporation control parameters include steam supply, liquid inlet flow, liquid outlet flow, steam temperature, and steam pressure; Randomly selecting a first evaporation control parameter from the evaporation control parameter space and setting it as a first initial evaporation control parameter; randomly selecting a second evaporation control parameter again; and if a Euclidean distance between the second evaporation control parameter and the first initial evaporation control parameter is greater than a predetermined distance threshold, setting the second evaporation control parameter as a second initial evaporation control parameter; Continue to randomly select a third evaporation control parameter. If the Euclidean distance between the third evaporation control parameter and the first initial evaporation control parameter is greater than the predetermined distance threshold and the Euclidean distance between the third evaporation control parameter and the second initial evaporation control parameter is greater than the predetermined distance threshold, set the third evaporation control parameter as the third initial evaporation control parameter. Iteratively select until a predetermined number is met, and output the multiple initial evaporation control parameters.

3. The evaporation energy-saving adaptive control method based on multi-parameter analysis according to claim 1 is characterized in that: Based on the solution properties, environmental parameters, and desired concentration index of the brine to be evaporated, evaporation efficiency prediction is performed for the multiple initial evaporation control parameters at multiple nodes in a predetermined time zone to obtain multiple predicted evaporation efficiency sets, including: Collecting solution properties and environmental parameters of the brine to be evaporated, wherein the solution properties include solution type, initial concentration, and initial temperature, and the environmental parameters include ambient temperature and ambient humidity; Using the solution properties, environmental parameters, and desired concentration indicators as conditional constraints, the property characteristics of the single-effect evaporator as equipment constraints, and evaporation control as a guide, a big data search is performed to obtain a sample evaporation control parameter set and a sample evaporation time set, and the evaporation efficiency under different sample evaporation control parameters and different sample evaporation times is annotated to obtain a sample evaporation efficiency set; Training an integrated learning operator based on the sample evaporation control parameter set, the sample evaporation time set, and the sample evaporation efficiency set until convergence to obtain an evaporation efficiency prediction plug-in, wherein the integrated learning operator includes at least a random forest, a BP neural network, and a support vector machine; A plurality of evaporation times are determined based on the plurality of nodes in the predetermined time zone, and the evaporation efficiency prediction plug-in is used to perform evaporation efficiency prediction for the plurality of initial evaporation control parameters under the plurality of evaporation times, and a plurality of predicted evaporation efficiency sets are output, wherein the evaporation time is the time interval between the node and the starting time.

4. The evaporation energy-saving adaptive control method based on multi-parameter analysis according to claim 1 is characterized in that: Taking the evaporation control parameter space as a constraint, optimizing the evaporation control parameters according to the multiple evaporation fitnesses, and outputting the optimal evaporation control parameters, including: The initial evaporation control parameters are set as initial solutions, and the multiple initial evaporation control parameters are arranged from large to small according to the multiple evaporation fitnesses to determine an initial solution sequence; The first P solutions of the initial solution sequence are set as optimal solutions, and the last Q solutions are set as inferior solutions, to obtain P optimal solutions and Q inferior solutions, where Q is N times P, P and Q are both integers, and N is an integer greater than 5; Randomly clustering the Q inferior solutions according to the P superior solutions to obtain P solution sets, wherein the number of inferior solutions in each solution set is the same; For the P solution sets, the inferior solution with the smallest fitness in the solution set is set as a differential solution, the fitness of the P differential solutions is obtained, and P dynamic optimization directions are set according to the fitness of the P superior solutions and the fitness of the P differential solutions, wherein the dynamic optimization direction is an adjustment toward the optimal solution or an adjustment away from the inferior solution; According to the P dynamic optimization directions, the inferior solutions in the P solution sets are adjusted according to the adaptive optimization step size to obtain P updated solution sets, and the P updated solution sets are identified. If the fitness of the inferior solution in the updated solution set is greater than the fitness of the superior solution, the superior solution in the solution set is replaced with the inferior solution. If the adjusted inferior solution does not satisfy the evaporation control parameter space, no adjustment is performed; The iterative optimization is continued based on the dynamic optimization direction and the adaptive optimization step size until a predetermined number of iterations is reached, P current solution sets are output, the current solution set with the largest sum of fitness among the P current solution sets is selected as the optimal solution set, and the optimal solution of the optimal solution set is output as the optimal evaporation control parameter.

5. The evaporation energy-saving adaptive control method based on multi-parameter analysis according to claim 4 is characterized in that: According to the fitness of P optimal solutions and P poor solutions, P dynamic optimization directions are set, including: Randomly selecting a first solution set from the P solution sets, and obtaining a first optimal solution fitness, a first poor solution fitness, and a plurality of first inferior solution fitnesses of the first solution set; Calculate a first inferior solution fitness mean of the multiple first inferior solution fitnesses, calculate the absolute values ​​of deviations between the first superior solution fitness, the first differential solution fitness and the first inferior solution fitness mean, and determine a first superior solution deviation value and a first inferior solution deviation value; A first dynamic optimization direction is set according to the first optimal solution deviation value and the first inferior solution deviation value, and is added to the P dynamic optimization directions. If the first optimal solution deviation value is greater than or equal to the first inferior solution deviation value, the first dynamic optimization direction is an optimization-oriented adjustment; if the first optimal solution deviation value is less than the first inferior solution deviation value, the first dynamic optimization direction is an inferior-avoidance adjustment.

6. The evaporation energy-saving adaptive control method based on multi-parameter analysis according to claim 5 is characterized in that: Get the optimal step length, including: Determining a first optimization fitness of a first direction according to the first dynamic optimization direction, wherein the first optimization fitness is a first optimal solution fitness or a first differential solution fitness; Calculating the ratios of multiple first inferior solution fitnesses to the first optimal solution fitness respectively, and determining multiple compensation coefficients, wherein if the first optimal solution fitness is the first optimal solution fitness, the compensation coefficient is the ratio of the first inferior solution fitness to the first optimal solution fitness; if the first optimal solution fitness is the first differential solution fitness, the compensation coefficient is the ratio of the first differential solution fitness to the first inferior solution fitness; The initial optimization step length is optimized according to the multiple compensation coefficients, and a first step length set is determined and added to the adaptive optimization step length.

7. The evaporation energy-saving adaptive control system under multi-parameter analysis is characterized by: The system is used to execute the evaporation energy-saving adaptive control method under multi-parameter analysis according to any one of claims 1 to 6, comprising: The initial evaporation control parameter selection module is used to obtain the evaporation control parameter space of the single-effect evaporator and randomly select multiple initial evaporation control parameters that meet the uniform distribution constraint; an evaporation efficiency prediction and evaluation module, configured to predict the evaporation efficiency of the multiple initial evaporation control parameters at multiple nodes in a predetermined time zone based on the solution properties, environmental parameters, and desired concentration index of the brine to be evaporated, obtain multiple predicted evaporation efficiency sets, and evaluate and obtain multiple evaporation fitnesses; an evaporation control parameter optimization module, configured to optimize the evaporation control parameters based on the plurality of evaporation fitnesses, taking the evaporation control parameter space as a constraint, and outputting optimal evaporation control parameters, wherein the parameter optimization is performed based on a dynamic optimization direction and an adaptive optimization step length, wherein the dynamic optimization direction is an optimization-oriented adjustment or an optimization-avoidance adjustment; The evaporation control module is used to control the single-effect evaporator to perform evaporation operation according to the optimal evaporation control parameters within the predetermined time zone.

Images