Evaporation energy-saving optimization method and system based on intelligent control

Abstract

The present invention discloses an evaporation energy-saving optimization method and system based on intelligent control, and relates to the field of data processing technology. The method comprises: collecting the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, and obtaining the characteristic information of the evaporation liquid; performing evaporation energy-saving fuzzy prediction according to the characteristic information of the evaporation liquid, and obtaining the fuzzy energy-saving coefficient; combining the fuzzy energy-saving coefficient, constructing an evaporation energy-saving function that uses mechanical vapor recompression for evaporation energy-saving control; optimizing the evaporation energy-saving control parameters according to the evaporation energy-saving function, and obtaining the optimized evaporation energy-saving control parameter space; in the optimized evaporation energy-saving control parameter space, selecting the optimal evaporation energy-saving control parameters according to the fuzzy energy-saving coefficient, and performing evaporation energy-saving control. The technical problems of high energy consumption and poor energy-saving effect in the traditional evaporation process are solved, and the technical effect of reducing energy consumption and improving energy-saving efficiency is achieved through mechanical vapor recompression technology and intelligent control algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an evaporation energy-saving optimization method and system based on intelligent control. Background Art

[0002] With the continuous development of industrial production, the evaporation process, as a key link in many industrial fields, has become increasingly prominent in terms of energy consumption. As a key step in many industrial production links, such as chemical, pharmaceutical, and food processing industries, the energy consumption of the evaporation process often accounts for a large proportion of the total energy consumption of production. Traditional evaporation processes often use a single heat source to directly heat the evaporation, which not only has high energy consumption, but also has low thermal efficiency, resulting in a large amount of energy waste and environmental pollution. In order to meet this challenge, the development of efficient and energy-saving evaporation technology has become an industry consensus. Among them, Mechanical Vapor Recompression (MVR) technology, as an advanced evaporation energy-saving technology, recycles the secondary steam generated during the evaporation process, compresses and heats it with a compressor, and then reuses it as a heat source, realizing the recycling of heat energy and significantly reducing energy consumption and operating costs. However, the operating efficiency of the MVR system is affected by many factors, such as evaporation volume, operating conditions, etc. How to achieve intelligent control and optimization of the evaporation process based on these conditions has become the key to further improving energy-saving effects. Summary of the invention

[0003] The present application provides an evaporation energy-saving optimization method and system based on intelligent control, which solves the technical problems of high energy consumption and poor energy-saving effect in the traditional evaporation process.

[0004] In view of the above problems, the present application provides an evaporation energy-saving optimization method and system based on intelligent control.

[0005] In a first aspect of the present application, an evaporation energy-saving optimization method based on intelligent control is provided, the method comprising:

[0006] The composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated are collected to obtain the characteristic information of the evaporation liquid; according to the characteristic information of the evaporation liquid, fuzzy prediction of evaporation energy saving is performed to obtain a fuzzy energy saving coefficient; in combination with the fuzzy energy saving coefficient, an evaporation energy saving function for evaporation energy saving control using mechanical vapor recompression is constructed; according to the evaporation energy saving function, evaporation energy saving control parameters are optimized to obtain an optimized evaporation energy saving control parameter space, wherein, in the optimization process, evaporation energy saving parameters and compression energy consumption parameters are predicted for optimization; in the optimized evaporation energy saving control parameter space, according to the fuzzy energy saving coefficient, the optimal evaporation energy saving control parameters are selected to perform evaporation energy saving control.

[0007] The second aspect of the present application provides an evaporation energy-saving optimization system based on intelligent control, the system comprising:

[0008] An information acquisition module, the information acquisition module is used to collect the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, and obtain the evaporation liquid characteristic information; a prediction module, the prediction module is used to perform evaporation energy-saving fuzzy prediction according to the evaporation liquid characteristic information, and obtain the fuzzy energy-saving coefficient; a function construction module, the function construction module is used to construct an evaporation energy-saving function for evaporation energy-saving control using mechanical vapor recompression in combination with the fuzzy energy-saving coefficient; an optimization module, the optimization module is used to optimize the evaporation energy-saving control parameters according to the evaporation energy-saving function, and obtain an optimized evaporation energy-saving control parameter space, wherein, in the optimization process, the evaporation energy-saving parameters and the compression energy consumption parameters are predicted to be optimized; a control module, the control module is used to select and obtain the optimal evaporation energy-saving control parameters according to the fuzzy energy-saving coefficient in the optimized evaporation energy-saving control parameter space, and perform evaporation energy-saving control.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By collecting the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, the characteristic information of the evaporation liquid is obtained. Then, according to the characteristic information of the evaporation liquid, fuzzy prediction of evaporation energy saving is carried out to obtain the fuzzy energy saving coefficient; combined with the fuzzy energy saving coefficient, an evaporation energy saving function using mechanical vapor recompression for evaporation energy saving control is constructed. Then, according to the evaporation energy saving function, the evaporation energy saving control parameters are optimized to obtain the optimized evaporation energy saving control parameter space, wherein, in the optimization process, the evaporation energy saving parameters and the compression energy consumption parameters are predicted for optimization. Finally, in the optimized evaporation energy saving control parameter space, according to the fuzzy energy saving coefficient, the optimal evaporation energy saving control parameters are selected to perform evaporation energy saving control. The technical problems of high energy consumption and poor energy saving effect in the traditional evaporation process are solved, and the technical effect of reducing energy consumption and improving energy saving efficiency is achieved through mechanical vapor recompression technology and intelligent control algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of an evaporation energy-saving optimization method based on intelligent control provided in an embodiment of the present application.

[0013] Figure 2 A schematic diagram of the structure of an evaporation energy-saving optimization system based on intelligent control provided in an embodiment of the present application.

[0014] Explanation of the accompanying drawings: information collection module 11, prediction module 12, function construction module 13, optimization module 14, control module 15. DETAILED DESCRIPTION

[0015] The present application solves the technical problems of high energy consumption and poor energy-saving effect in the traditional evaporation process by providing an evaporation energy-saving optimization method and system based on intelligent control.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides an evaporation energy-saving optimization method based on intelligent control, wherein the method includes:

[0019] The composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated are collected to obtain the characteristic information of the evaporation liquid.

[0020] Evaporation liquid refers to the liquid used in the evaporation process (such as cleaning agents, scale inhibitors, etc.). The composition information of the evaporation liquid includes the chemical composition, density, viscosity, surface tension, pH value, etc. of the evaporation liquid. The evaporation amount refers to the amount of water lost from the surface of the liquid due to evaporation within a certain period of time. The evaporation amount information reflects the demand and scale of the evaporation process, including the target evaporation amount, actual evaporation rate, evaporation time, and evaporation efficiency. By collecting the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, the evaporation liquid characteristic information can be formed. The evaporation liquid characteristic information includes the main components of the evaporation liquid and its concentration, physical properties (such as density, viscosity, surface tension), and evaporation performance. The evaporation liquid characteristic information not only describes the basic properties of the evaporation liquid, but also reflects the demand and status of the evaporation process.

[0021] According to the evaporative liquid characteristic information, fuzzy prediction of evaporation energy saving is performed to obtain a fuzzy energy saving coefficient.

[0022] According to the characteristic information of the evaporating liquid, fuzzy prediction of evaporation energy saving is performed to obtain the fuzzy energy saving coefficient. Specifically, the fuzzy energy saving coefficient of the evaporating liquid using mechanical vapor recompression energy saving in historical time is obtained by matching the characteristic information of the evaporating liquid from big data, such as the average percentage of evaporation energy saving.

[0023] Furthermore, according to the evaporative liquid characteristic information, evaporation energy saving fuzzy prediction is performed to obtain a fuzzy energy saving coefficient, including:

[0024] According to the energy-saving evaporation data records in the historical time, a sample evaporation liquid characteristic information set is collected; the historical average energy-saving coefficient when each sample evaporation liquid characteristic information is collected for energy-saving evaporation, and a sample fuzzy energy-saving coefficient set is obtained; the sample evaporation liquid characteristic information set and the sample fuzzy energy-saving coefficient set are used to construct an evaporation energy-saving fuzzy predictor; the evaporation energy-saving fuzzy predictor is used to perform evaporation energy-saving fuzzy prediction on the evaporation liquid characteristic information to obtain a fuzzy energy-saving coefficient.

[0025] Preferably, characteristic information of each evaporation liquid is extracted from the energy-saving evaporation data records in the historical time to form a sample evaporation liquid characteristic information set; for each sample in the sample evaporation liquid characteristic information set, the historical average energy-saving coefficient when the energy-saving evaporation is performed is found, and the historical average energy-saving coefficient can be obtained by comparing the actual energy consumption with the theoretical minimum energy consumption, and these historical average energy-saving coefficients are sorted into a sample fuzzy energy-saving coefficient set corresponding to the corresponding sample evaporation liquid characteristic information set; the sample evaporation liquid characteristic information set and the sample fuzzy energy-saving coefficient set are used to construct an evaporation energy-saving fuzzy predictor; the evaporation liquid characteristic information to be predicted is input into the constructed evaporation energy-saving fuzzy predictor to obtain the fuzzy energy-saving coefficient.

[0026] Furthermore, the sample evaporation liquid characteristic information set and the sample fuzzy energy-saving coefficient set are used to construct an evaporation energy-saving fuzzy predictor, including:

[0027] The sample evaporation liquid feature information set is clustered to obtain multiple sample clustering evaporation liquid feature information sets, and the sample fuzzy energy-saving coefficient set is mapped and divided to obtain multiple sample clustering fuzzy energy-saving coefficient sets; the multiple sample clustering evaporation liquid feature information sets are respectively used as inputs, and the multiple sample clustering fuzzy energy-saving coefficient sets are respectively used as outputs to train multiple evaporation energy-saving fuzzy prediction branches; the multiple evaporation energy-saving fuzzy prediction branches are integrated to obtain an evaporation energy-saving fuzzy predictor.

[0028] Preferably, according to the characteristics of the sample evaporation liquid characteristic information set, a suitable clustering algorithm (such as K-means, hierarchical clustering, DBSCAN, etc.) is selected for cluster analysis, such as clustering parameters of similar evaporation liquid characteristic parameters such as multiple data with similar components and similar evaporation amounts, and then obtaining multiple sample cluster evaporation liquid characteristic information sets, and the samples within each cluster have high similarity in evaporation liquid characteristics; according to the clustering results, the energy-saving coefficients in the sample fuzzy energy-saving coefficient set are mapped to the corresponding sample clusters, that is, for each cluster, the fuzzy energy-saving coefficients of all samples belonging to the cluster are collected to form a sample cluster of the cluster. class fuzzy energy-saving coefficient set; for each sample clustering evaporation liquid feature information set, take it as input and the corresponding sample clustering fuzzy energy-saving coefficient set as output, train an evaporation energy-saving fuzzy prediction branch, and obtain multiple evaporation energy-saving fuzzy prediction branches after the training is completed; integrate multiple evaporation energy-saving fuzzy prediction branches by selecting appropriate integration strategies (such as weighted average, voting mechanism, stack integration, etc.), combine multiple evaporation energy-saving fuzzy prediction branches into a complete evaporation energy-saving fuzzy predictor according to the selected integration strategy, and use the constructed evaporation energy-saving fuzzy predictor to perform energy-saving prediction on the evaporation liquid feature information to obtain the fuzzy energy-saving coefficient.

[0029] In combination with the fuzzy energy-saving coefficient, an evaporation energy-saving function using mechanical vapor recompression for evaporation energy-saving control is constructed.

[0030] Mechanical vapor recompression is to compress the steam generated during evaporation to increase its temperature and pressure, and then reuse this high-temperature and high-pressure steam as the heat source of the evaporator to achieve energy saving. Combined with the fuzzy energy saving coefficient, an evaporation energy saving function using mechanical vapor recompression for evaporation energy saving control is constructed.

[0031] Furthermore, in combination with the fuzzy energy-saving coefficient, an evaporation energy-saving function using mechanical vapor recompression for evaporation energy-saving control is constructed, including:

[0032] According to the fuzzy energy-saving coefficient, the energy-saving weight and the scaling weight are set; according to the energy-saving weight and the scaling weight, an evaporation energy-saving function is constructed for the purpose of improving the evaporation energy-saving degree and reducing the scaling of the steam compressor, as shown in the following formula: ; Among them, ENS is energy-saving adaptability, is the energy saving weight, is the scaling weight, It is the energy-saving parameter under the evaporation energy-saving control parameter. is the energy consumption parameter of the steam compressor under the evaporation energy saving control parameter, is the preset energy consumption parameter, and G is the fouling parameter of the steam compressor under the evaporation energy-saving control parameter.

[0033] Preferably, the energy-saving weight and the scaling weight are set according to the fuzzy energy-saving coefficient and combined with expert experience. A higher fuzzy energy-saving coefficient indicates a greater energy-saving potential, and the energy-saving weight can be increased accordingly. For example, the fuzzy energy-saving coefficient can be directly used as the energy-saving weight, and 1-energy-saving weight is the scaling weight. According to the energy-saving weight and scaling weight, an evaporation energy-saving function is constructed for the purpose of improving the evaporation energy-saving degree and reducing the scaling of the steam compressor: ; Among them, ENS is energy-saving adaptability, is the energy saving weight, is the scaling weight, It is the energy-saving parameter under the evaporation energy-saving control parameter, representing the energy-saving effect achieved under the specific evaporation energy-saving control parameter. is the energy consumption parameter of the steam compressor under the evaporation energy-saving control parameter, which means the energy consumed by the steam compressor under the same evaporation energy-saving control parameter. It is a preset energy consumption parameter, representing a benchmark value, used to To compare and evaluate the energy-saving effect, G is the scaling parameter of the steam compressor under the evaporation energy-saving control parameters, which represents the scaling degree of the steam compressor under specific evaporation energy-saving control parameters.

[0034] According to the evaporation energy-saving function, the evaporation energy-saving control parameters are optimized to obtain an optimized evaporation energy-saving control parameter space, wherein, during the optimization process, the evaporation energy-saving parameters and the compression energy consumption parameters are predicted for optimization.

[0035] According to the evaporation energy-saving function, optimization algorithms such as genetic algorithm and particle swarm optimization algorithm are used to optimize the evaporation energy-saving control parameters. During the optimization process, the evaporation energy-saving parameters and compression energy consumption parameters are predicted and optimized to obtain the optimized evaporation energy-saving control parameter space.

[0036] Furthermore, according to the evaporation energy-saving function, the evaporation energy-saving control parameters are optimized to obtain an optimized evaporation energy-saving control parameter space, including:

[0037] Acquire an evaporation energy-saving control parameter space for evaporation energy saving using mechanical vapor recompression; randomly generate a plurality of first evaporation energy-saving control parameters in the evaporation energy-saving control parameter space; predict and obtain a plurality of first energy-saving parameters and a plurality of first scaling parameters based on the plurality of first evaporation energy-saving control parameters and in combination with the evaporation liquid characteristic information, wherein the energy-saving prediction path and the scaling prediction path are trained by collecting a sample evaporation liquid characteristic information set, a sample energy-saving parameter set and a sample scaling parameter set, and predicting and obtaining a plurality of first energy-saving parameters and a plurality of first scaling parameters; acquire a plurality of first energy consumption parameters of the compressor under the plurality of first evaporation energy-saving control parameters, and conclude The multiple first energy-saving parameters and the multiple first scaling parameters are combined, and based on the evaporation energy-saving function, multiple first energy-saving fitness degrees are calculated; according to the multiple first energy-saving fitness degrees, the multiple first evaporation energy-saving control parameters are clustered to obtain multiple clustering results, each clustering result includes a cluster center with the largest energy-saving fitness degree and multiple other first evaporation energy-saving control parameters; the multiple clustering results are updated and optimized until convergence, and an optimal clustering result with the largest sum of energy-saving fitness degrees is output; according to the maximum evaporation energy-saving control parameter and the minimum evaporation energy-saving control parameter in the optimal clustering result, an optimized evaporation energy-saving control parameter space is constructed.

[0038] Preferably, evaporation energy-saving control parameters for evaporation energy saving using mechanical vapor recompression are obtained, including evaporation temperature, condensation temperature, subcooling, compressor speed, cooling water flow, vacuum degree, etc., and the value ranges of these parameters constitute an evaporation energy-saving control parameter space; in the evaporation energy-saving control parameter space, a plurality of first evaporation energy-saving control parameter combinations are randomly generated, and each combination represents a possible operating condition; characteristic information of sample evaporation liquid (such as concentration, temperature, pH value, etc.), sample energy-saving parameters (such as energy consumption, evaporation amount, etc.) and sample scaling parameters (such as scaling rate, scaling thickness, etc.) are collected; based on a deep learning model (such as a neural network, a random forest, etc.), a sample evaporation liquid characteristic information set, a sample energy-saving parameter set and a sample scaling parameter set are used as training data to train an energy-saving prediction path and a scaling prediction path; using the trained energy-saving prediction path and scaling prediction path, according to each first evaporation energy-saving control parameter combination and the corresponding evaporation liquid characteristic information, a plurality of first energy-saving parameters and a plurality of first scaling parameters are predicted; for each first evaporation energy-saving control parameter combination, in combination with its corresponding first energy-saving parameter, first The scaling parameters and the first energy consumption parameters of the compressor are used to calculate an energy-saving fitness using the evaporation energy-saving function. This energy-saving fitness is an indicator for evaluating the comprehensive performance of the control parameter combination in terms of energy saving and scaling prevention. According to multiple first energy-saving fitnesses, multiple first evaporation energy-saving control parameters are clustered, and each clustering result includes a cluster center with the largest energy-saving fitness (i.e., the optimal control parameter combination in the cluster) and multiple other first evaporation energy-saving control parameters. Based on the cluster center, the clustering results are updated through an iterative optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) so that the control parameter combination in the cluster is gradually adjusted to a better direction. This process continues until convergence, that is, the clustering results no longer change significantly. After the iterative optimization is completed, the optimal clustering result with the largest sum of energy-saving fitness is output. The optimal clustering result represents the control parameter combination with the best energy-saving and scaling prevention effect that can be achieved under the current evaporating liquid characteristic information. According to the maximum evaporation energy-saving control parameter and the minimum evaporation energy-saving control parameter in the optimal clustering result as the endpoint values ​​of the space, an optimized evaporation energy-saving control parameter space can be constructed.

[0039] Furthermore, the multiple clustering results are updated and optimized until convergence, and an optimal clustering result with the maximum sum of energy-saving fitness is output, including:

[0040] In each clustering result, the cluster center is used as the update direction, and the update step is used to adjust and update other evaporation energy-saving control parameters to obtain multiple updated clustering results; the energy-saving fitness of the evaporation energy-saving control parameters in the multiple updated clustering results is obtained, and the cluster center is updated; the multiple clustering results are continuously updated and optimized until convergence, and the optimal clustering result with the largest sum of energy-saving fitness is output.

[0041] Preferably, for each clustering result, taking the cluster center (i.e., the control parameter combination with the highest energy-saving fitness in the cluster) as a benchmark, a certain update step size is used to adjust other evaporation energy-saving control parameters in the cluster, such as moving a certain distance to the cluster center, thereby obtaining multiple updated clustering results; recalculating the energy-saving fitness of all evaporation energy-saving control parameter combinations in each updated clustering result, finding a new control parameter combination with the highest energy-saving fitness in each updated clustering result, and using it as a new clustering center; repeating the above steps of updating the evaporation energy-saving control parameters, processing the energy-saving fitness of the updated clustering results, and updating the clustering center until a certain convergence condition is met (the change in the cluster center is less than a certain threshold, the improvement in the energy-saving fitness is less than a certain threshold, or a preset number of iterations is reached); when the convergence condition is met, stopping the iteration, and outputting the optimal clustering result with the largest sum of energy-saving fitness.

[0042] In the optimized evaporation energy-saving control parameter space, the optimal evaporation energy-saving control parameter is selected according to the fuzzy energy-saving coefficient to perform evaporation energy-saving control.

[0043] According to the fuzzy energy-saving coefficient, the optimal evaporation energy-saving control parameter is selected in the optimized evaporation energy-saving control parameter space to carry out evaporation energy-saving control.

[0044] Furthermore, in the optimized evaporation energy-saving control parameter space, according to the fuzzy energy-saving coefficient, the optimal evaporation energy-saving control parameter is selected, including:

[0045] According to the fuzzy energy-saving coefficient, setting energy-saving parameter division ratio points;

[0046] The energy-saving parameter division ratio points are adopted to divide and select the optimal evaporation energy-saving control parameters in the optimized evaporation energy-saving control parameter space.

[0047] Preferably, the fuzzy energy-saving coefficient of each sample point is calculated by traversing the optimized evaporation energy-saving control parameter space; a series of energy-saving parameter division ratio points can be set according to the distribution of the fuzzy energy-saving coefficient, such as dividing the value range of the fuzzy energy-saving coefficient into several equally spaced intervals, or dynamically setting it according to the distribution density of the fuzzy energy-saving coefficient, and each interval or density peak point can be used as an energy-saving parameter division ratio point; using the set energy-saving parameter division ratio points, for example, if the fuzzy energy-saving coefficient is 30%, the energy-saving parameter division ratio point is 0.3; according to the ratio points, different selection areas are divided in the optimized evaporation energy-saving control parameter space, for example, if the optimized evaporation energy-saving control parameter space is (X, Y), the optimal evaporation energy-saving control parameter is X+(YX)*30%, that is, 30% of the interval between X and Y, and the fuzzy energy-saving coefficient is selected to obtain the optimal evaporation energy-saving control parameter, thereby minimizing scaling and slowing down aging under the premise of ensuring energy saving.

[0048] In summary, the embodiments of the present application have at least the following technical effects:

[0049] By collecting the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, the characteristic information of the evaporation liquid is obtained. Then, according to the characteristic information of the evaporation liquid, fuzzy prediction of evaporation energy saving is carried out to obtain the fuzzy energy saving coefficient; combined with the fuzzy energy saving coefficient, an evaporation energy saving function using mechanical vapor recompression for evaporation energy saving control is constructed. Then, according to the evaporation energy saving function, the evaporation energy saving control parameters are optimized to obtain the optimized evaporation energy saving control parameter space, wherein, in the optimization process, the evaporation energy saving parameters and the compression energy consumption parameters are predicted for optimization. Finally, in the optimized evaporation energy saving control parameter space, according to the fuzzy energy saving coefficient, the optimal evaporation energy saving control parameters are selected to perform evaporation energy saving control. The technical problems of high energy consumption and poor energy saving effect in the traditional evaporation process are solved, and the technical effect of reducing energy consumption and improving energy saving efficiency is achieved through mechanical vapor recompression technology and intelligent control algorithm.

[0050] Embodiment 2 is based on the same inventive concept as the evaporation energy-saving optimization method based on intelligent control in the previous embodiment. Figure 2 As shown, the present application provides an evaporation energy-saving optimization system based on intelligent control, wherein the system includes:

[0051] An information acquisition module 11, the information acquisition module 11 is used to collect the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, and obtain the characteristic information of the evaporation liquid; a prediction module 12, the prediction module 12 is used to perform evaporation energy-saving fuzzy prediction according to the evaporation liquid characteristic information, and obtain a fuzzy energy-saving coefficient; a function construction module 13, the function construction module 13 is used to construct an evaporation energy-saving function for evaporation energy-saving control using mechanical vapor recompression in combination with the fuzzy energy-saving coefficient; an optimization module 14, the optimization module 14 is used to optimize the evaporation energy-saving control parameters according to the evaporation energy-saving function, and obtain an optimized evaporation energy-saving control parameter space, wherein, in the optimization process, the evaporation energy-saving parameters and the compression energy consumption parameters are predicted to be optimized; a control module 15, the control module 15 is used to select and obtain the optimal evaporation energy-saving control parameters in the optimized evaporation energy-saving control parameter space according to the fuzzy energy-saving coefficient, and perform evaporation energy-saving control.

[0052] Furthermore, the prediction module 12 is used to perform the following method:

[0053] According to the energy-saving evaporation data records in the historical time, a sample evaporation liquid characteristic information set is collected; the historical average energy-saving coefficient when each sample evaporation liquid characteristic information is collected for energy-saving evaporation, and a sample fuzzy energy-saving coefficient set is obtained; the sample evaporation liquid characteristic information set and the sample fuzzy energy-saving coefficient set are used to construct an evaporation energy-saving fuzzy predictor; the evaporation energy-saving fuzzy predictor is used to perform evaporation energy-saving fuzzy prediction on the evaporation liquid characteristic information to obtain a fuzzy energy-saving coefficient.

[0054] Furthermore, the prediction module 12 is used to perform the following method:

[0055] The sample evaporation liquid feature information set is clustered to obtain multiple sample clustering evaporation liquid feature information sets, and the sample fuzzy energy-saving coefficient set is mapped and divided to obtain multiple sample clustering fuzzy energy-saving coefficient sets; the multiple sample clustering evaporation liquid feature information sets are respectively used as inputs, and the multiple sample clustering fuzzy energy-saving coefficient sets are respectively used as outputs to train multiple evaporation energy-saving fuzzy prediction branches; the multiple evaporation energy-saving fuzzy prediction branches are integrated to obtain an evaporation energy-saving fuzzy predictor.

[0056] Furthermore, the function construction module 13 is used to execute the following method:

[0057] According to the fuzzy energy-saving coefficient, the energy-saving weight and the scaling weight are set; according to the energy-saving weight and the scaling weight, an evaporation energy-saving function is constructed for the purpose of improving the evaporation energy-saving degree and reducing the scaling of the steam compressor, as shown in the following formula: ; Among them, ENS is energy-saving adaptability, is the energy saving weight, is the scaling weight, It is the energy-saving parameter under the evaporation energy-saving control parameter. is the energy consumption parameter of the steam compressor under the evaporation energy saving control parameter, is the preset energy consumption parameter, and G is the fouling parameter of the steam compressor under the evaporation energy-saving control parameter.

[0058] Furthermore, the optimization module 14 is used to perform the following method:

[0059] Acquire an evaporation energy-saving control parameter space for evaporation energy saving using mechanical vapor recompression; randomly generate a plurality of first evaporation energy-saving control parameters in the evaporation energy-saving control parameter space; predict and obtain a plurality of first energy-saving parameters and a plurality of first scaling parameters based on the plurality of first evaporation energy-saving control parameters and in combination with the evaporation liquid characteristic information, wherein the energy-saving prediction path and the scaling prediction path are trained by collecting a sample evaporation liquid characteristic information set, a sample energy-saving parameter set and a sample scaling parameter set, and predicting and obtaining a plurality of first energy-saving parameters and a plurality of first scaling parameters; acquire a plurality of first energy consumption parameters of the compressor under the plurality of first evaporation energy-saving control parameters, and conclude The multiple first energy-saving parameters and the multiple first scaling parameters are combined, and based on the evaporation energy-saving function, multiple first energy-saving fitness degrees are calculated; according to the multiple first energy-saving fitness degrees, the multiple first evaporation energy-saving control parameters are clustered to obtain multiple clustering results, each clustering result includes a cluster center with the largest energy-saving fitness degree and multiple other first evaporation energy-saving control parameters; the multiple clustering results are updated and optimized until convergence, and an optimal clustering result with the largest sum of energy-saving fitness degrees is output; according to the maximum evaporation energy-saving control parameter and the minimum evaporation energy-saving control parameter in the optimal clustering result, an optimized evaporation energy-saving control parameter space is constructed.

[0060] Furthermore, the optimization module 14 is used to perform the following method:

[0061] In each clustering result, the cluster center is used as the update direction, and the update step is used to adjust and update other evaporation energy-saving control parameters to obtain multiple updated clustering results; the energy-saving fitness of the evaporation energy-saving control parameters in the multiple updated clustering results is obtained, and the cluster center is updated; the multiple clustering results are continuously updated and optimized until convergence, and the optimal clustering result with the largest sum of energy-saving fitness is output.

[0062] Furthermore, the control module 15 is used to execute the following method:

[0063] According to the fuzzy energy-saving coefficient, an energy-saving parameter division ratio point is set; and the energy-saving parameter division ratio point is used to divide and select in the optimized evaporation energy-saving control parameter space to obtain the optimal evaporation energy-saving control parameter.

[0064] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0066] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An evaporation energy-saving optimization method based on intelligent control, characterized in that: The method comprises: Collecting the composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, and obtaining the characteristic information of the evaporation liquid; According to the evaporative liquid characteristic information, fuzzy prediction of evaporation energy saving is performed to obtain a fuzzy energy saving coefficient; In combination with the fuzzy energy-saving coefficient, an evaporation energy-saving function for evaporation energy-saving control using mechanical vapor recompression is constructed; According to the evaporation energy-saving function, the evaporation energy-saving control parameters are optimized to obtain an optimized evaporation energy-saving control parameter space, wherein, during the optimization process, the evaporation energy-saving parameters and the compression energy consumption parameters are predicted for optimization; In the optimized evaporation energy-saving control parameter space, according to the fuzzy energy-saving coefficient, the optimal evaporation energy-saving control parameter is selected to perform evaporation energy-saving control; In which, in combination with the fuzzy energy-saving coefficient, an evaporation energy-saving function using mechanical vapor recompression for evaporation energy-saving control is constructed, including: According to the fuzzy energy-saving coefficient, setting energy-saving weight and scaling weight; According to the energy-saving weight and scaling weight, an evaporation energy-saving function is constructed for the purpose of improving the evaporation energy-saving degree and reducing the scaling of the steam compressor, as shown in the following formula: ； Among them, ENS is energy-saving adaptability, is the energy saving weight, is the scaling weight, It is the energy-saving parameter under the evaporation energy-saving control parameter. is the energy consumption parameter of the steam compressor under the evaporation energy saving control parameter, is the preset energy consumption parameter, and G is the fouling parameter of the steam compressor under the evaporation energy-saving control parameter.

2. The evaporation energy saving optimization method based on intelligent control according to claim 1 is characterized in that: According to the evaporative liquid characteristic information, evaporation energy saving fuzzy prediction is performed to obtain a fuzzy energy saving coefficient, including: According to the energy-saving evaporation data records in the historical period, the characteristic information set of the sample evaporation liquid is collected; Collect the characteristic information of each sample evaporation liquid for energy-saving evaporation, and obtain the sample fuzzy energy-saving coefficient set; Using the sample evaporation liquid characteristic information set and the sample fuzzy energy-saving coefficient set, constructing an evaporation energy-saving fuzzy predictor; The evaporation energy-saving fuzzy predictor is used to perform evaporation energy-saving fuzzy prediction on the evaporation liquid characteristic information to obtain a fuzzy energy-saving coefficient.

3. The evaporation energy saving optimization method based on intelligent control according to claim 2 is characterized in that: The sample evaporation liquid characteristic information set and the sample fuzzy energy-saving coefficient set are used to construct an evaporation energy-saving fuzzy predictor, including: Clustering the sample evaporation liquid characteristic information set to obtain a plurality of sample clustered evaporation liquid characteristic information sets, and mapping and dividing the sample fuzzy energy-saving coefficient set to obtain a plurality of sample clustered fuzzy energy-saving coefficient sets; Using the plurality of sample clustering evaporation liquid feature information sets as inputs and the plurality of sample clustering fuzzy energy-saving coefficient sets as outputs respectively, training a plurality of evaporation energy-saving fuzzy prediction branches; The multiple evaporation energy-saving fuzzy prediction branches are integrated to obtain an evaporation energy-saving fuzzy predictor.

4. The evaporation energy saving optimization method based on intelligent control according to claim 1 is characterized in that: According to the evaporation energy-saving function, the evaporation energy-saving control parameters are optimized to obtain an optimized evaporation energy-saving control parameter space, including: Obtaining the evaporation energy-saving control parameter space for evaporation energy-saving using mechanical vapor recompression; Randomly generating a plurality of first evaporation energy-saving control parameters in the evaporation energy-saving control parameter space; According to the plurality of first evaporation energy-saving control parameters, in combination with the evaporation liquid characteristic information, a plurality of first energy-saving parameters and a plurality of first scaling parameters are predicted, wherein the plurality of first energy-saving parameters and a plurality of first scaling parameters are predicted by collecting a sample evaporation liquid characteristic information set, a sample energy-saving parameter set and a sample scaling parameter set, training an energy-saving prediction path and a scaling prediction path; Acquire a plurality of first energy consumption parameters of the compressor under the plurality of first evaporation energy-saving control parameters, combine the plurality of first energy-saving parameters and the plurality of first scaling parameters, and calculate and obtain a plurality of first energy-saving adaptability based on the evaporation energy-saving function; Clustering the plurality of first evaporation energy-saving control parameters according to the plurality of first energy-saving fitnesses to obtain a plurality of clustering results, each clustering result including a cluster center with the largest energy-saving fitness and the other plurality of first evaporation energy-saving control parameters; Updating and optimizing the multiple clustering results until convergence, and outputting an optimal clustering result with the largest sum of energy-saving fitness; According to the maximum evaporation energy-saving control parameter and the minimum evaporation energy-saving control parameter in the optimal clustering result, an optimized evaporation energy-saving control parameter space is constructed.

5. The evaporation energy saving optimization method based on intelligent control according to claim 4 is characterized in that: The multiple clustering results are updated and optimized until convergence, and an optimal clustering result with the maximum sum of energy-saving fitness is output, including: In each clustering result, taking the cluster center as the update direction, the update step length is used to adjust and update other evaporation energy-saving control parameters to obtain multiple updated clustering results; Processing and obtaining the energy-saving fitness of evaporation energy-saving control parameters in multiple updated clustering results, and updating the clustering center; Continue to update and optimize multiple clustering results until convergence, and output the optimal clustering result with the largest sum of energy-saving fitness.

6. The evaporation energy saving optimization method based on intelligent control according to claim 1 is characterized in that: In the optimized evaporation energy-saving control parameter space, according to the fuzzy energy-saving coefficient, the optimal evaporation energy-saving control parameter is selected, including: According to the fuzzy energy-saving coefficient, setting energy-saving parameter division ratio points; The energy-saving parameter division ratio points are adopted to divide and select the optimal evaporation energy-saving control parameters in the optimized evaporation energy-saving control parameter space.

7. The evaporation energy-saving optimization system based on intelligent control is characterized by: The system for implementing the evaporation energy-saving optimization method based on intelligent control according to any one of claims 1 to 6 comprises: An information collection module, the information collection module is used to collect composition information and evaporation amount information of the evaporation liquid to be energy-saving evaporated, and obtain characteristic information of the evaporation liquid; A prediction module, the prediction module is used to perform evaporation energy saving fuzzy prediction according to the evaporative liquid characteristic information to obtain a fuzzy energy saving coefficient; A function building module, wherein the function building module is used to build an evaporation energy-saving function for evaporation energy-saving control using mechanical vapor recompression in combination with the fuzzy energy-saving coefficient; An optimization module, wherein the optimization module is used to optimize the evaporation energy-saving control parameters according to the evaporation energy-saving function to obtain an optimized evaporation energy-saving control parameter space, wherein, during the optimization process, the evaporation energy-saving parameters and the compression energy consumption parameters are predicted for optimization; A control module, the control module is used to select and obtain the optimal evaporation energy-saving control parameter in the optimized evaporation energy-saving control parameter space according to the fuzzy energy-saving coefficient, and perform evaporation energy-saving control; The function building module is used to execute the following method: According to the fuzzy energy-saving coefficient, setting energy-saving weight and scaling weight; According to the energy-saving weight and scaling weight, an evaporation energy-saving function is constructed for the purpose of improving the evaporation energy-saving degree and reducing the scaling of the steam compressor, as shown in the following formula: ； Among them, ENS is energy-saving adaptability, is the energy saving weight, is the scaling weight, It is the energy-saving parameter under the evaporation energy-saving control parameter. is the energy consumption parameter of the steam compressor under the evaporation energy saving control parameter, is the preset energy consumption parameter, and G is the fouling parameter of the steam compressor under the evaporation energy-saving control parameter.

Images