A Smart Control Method for Regenerating Condensate Polishing Resin

Abstract

This invention discloses an intelligent control method for resin regeneration in condensate polishing, relating to the field of condensate polishing. The method includes: numbering and identifying the resin to be used; tracking the flow path based on the resin number and valve on / off status set, and recording the resin flow path information; monitoring and acquiring the mixed bed effluent status data stream, and predicting the regeneration cycle by combining the resin flow path information and historical resin effluent cycle data; controlling resin delivery and regeneration based on resin regeneration condition parameters, acquiring resin liquid level images, and calculating resin volume content information; performing ratio stability and regeneration energy consumption analysis, determining resin ratio replenishment parameters and resin regeneration energy consumption parameters, and implementing energy-saving control for resin regeneration. This method solves the technical problems of inaccurate regeneration cycle prediction, unstable resin ratio, and high regeneration energy consumption in existing resin regeneration control methods, achieving the technical effect of improving the accuracy and stability of resin regeneration control and reducing regeneration energy consumption.

Description

Technical Field

[0001] This application relates to the field of condensate polishing, and in particular to an intelligent control method for regenerating condensate polishing resin. Background Technology

[0002] The regeneration control of condensate polishing resin is crucial for ensuring the stable operation of water treatment systems and achieving energy conservation and consumption reduction. Currently, the main method for solving the problem of condensate polishing resin regeneration control is to rely on experience-based judgment and timed control for resin delivery and regeneration. However, this method often leads to significant differences in resin regeneration cycles, unstable resin ratios, and high regeneration energy consumption due to the lack of real-time monitoring data and intelligent control methods.

[0003] At present, the regeneration control of condensate polishing resin has technical problems such as large differences in regeneration cycle, unstable resin ratio and high regeneration energy consumption. Summary of the Invention

[0004] This application provides an intelligent control method for resin regeneration in condensate polishing. This method employs techniques such as numbering and tracking the resin's flow path, real-time monitoring of the mixed bed effluent status, and prediction of the regeneration cycle based on historical data. Resin delivery and regeneration are controlled according to the prediction results. Simultaneously, real-time acquisition of resin surface images is used to calculate volumetric content. Finally, ratio stabilization and regeneration energy consumption analysis are performed for energy-saving control. These techniques achieve the technical effects of improving the accuracy and stability of resin regeneration control and reducing regeneration energy consumption.

[0005] This application provides an intelligent control method for resin regeneration in condensate polishing, comprising: numbering and identifying N resins to be used to obtain N resin numbering information; tracking the flow path of the N resins to be used based on the N resin numbering information and the valve on / off status set of the condensate polishing system, and recording the N resin flow path information; real-time monitoring and acquisition of mixed bed effluent status data stream, and combining the N resin flow path information, the mixed bed effluent status data stream, and historical resin effluent cycle data to predict the regeneration cycle and obtain N resin regeneration condition parameters; performing resin delivery and regeneration control based on the N resin regeneration condition parameters, while simultaneously acquiring resin liquid level images in real time using a sight glass acquisition device and calculating the resin volume content information of the resin liquid level images; performing ratio stability and regeneration energy consumption analysis based on the resin volume content information, determining resin ratio replenishment parameters and resin regeneration energy consumption parameters, and performing resin regeneration energy-saving control through the resin ratio replenishment parameters and resin regeneration energy consumption parameters.

[0006] In a possible implementation, obtaining N resin numbering information involves the following processing: acquiring a resin numbering demand target; parsing the resin numbering demand target to determine numbering element information, which includes resin type, resin application batch, and system storage location; classifying each resin information among the N resins to be applied using the numbering element information to obtain N resin numbering element parameters; designing numbering rules based on the numbering element information to build a resin numbering system, which includes numbering order and numbering identifier; and numbering and identifying each resin parameter among the N resin numbering element parameters according to the resin numbering system to obtain the N resin numbering information.

[0007] In a possible implementation, the recording of N resin flow path information involves the following processes: initializing and obtaining the initial position information of the N resins to be applied; building a flow path tracking system based on the valve distribution structure information of the condensate polishing system, and inputting the initial position information of the N resins into the flow path tracking system; parsing the flow path of the flow path tracking system based on the valve on / off state set to obtain a resin predicted flow path set; and combining the N resin number information, the N resin initial position information, and the resin predicted flow path set to track the flow path of the N resins to be applied, thereby obtaining N resin flow path information.

[0008] In a possible implementation, the process of obtaining N resin flow path information involves performing the following steps: determining N resin flow status information based on the N resin number information and the N resin initial position information; tracking and recording the paths of the N resins to be applied according to the N resin number information and the N resin flow status information to obtain N resin flow monitoring path information; and performing intersection matching between the predicted resin flow path set and the N resin flow monitoring path information to determine the N resin flow path information.

[0009] In a possible implementation, the process of obtaining N resin regeneration condition parameters involves the following steps: First, based on the historical resin effluent cycle data, historical effluent cycle data for the N resins to be applied is obtained. This historical effluent cycle data includes mixed bed effluent status data, resin flow path data, and corresponding resin regeneration cycle data. Second, a recurrent neural network structure is used to identify and train the historical effluent cycle data of the N resins to be applied, constructing a resin regeneration cycle prediction network. Third, based on the resin regeneration cycle prediction network, effluent cycle prediction is performed on the N resin flow path information and the mixed bed effluent status data stream, outputting N predicted resin regeneration cycles. Fourth, regeneration condition analysis is performed on each of the N predicted resin regeneration cycles to obtain N resin regeneration condition parameters.

[0010] In a possible implementation, after obtaining N resin regeneration condition parameters, the following processing is performed: based on the N resins to be applied, historical regeneration data mining is performed to construct N resin regeneration control spaces, the N resin regeneration control spaces including resin regeneration cycle data, regeneration condition parameters, and corresponding regeneration effect data; based on the N resin regeneration control spaces, regeneration condition analysis is performed on the predicted regeneration cycles of the N resins to obtain N resin regeneration parameter selection thresholds; within the N resin regeneration parameter selection thresholds, global comparison and optimization are performed to obtain the N resin regeneration condition parameters.

[0011] In a possible implementation, the calculation of the resin volume content information of the resin surface image involves the following processing: converting the resin surface image into a resin surface grayscale image, and performing filtering, noise reduction, and contrast enhancement on the resin surface grayscale image to obtain a standard resin surface grayscale image; using the Sobel operator to perform edge detection on the standard resin surface grayscale image to determine the resin surface edge information; extracting contours from the standard resin surface grayscale image according to the resin surface edge information, and performing region filling based on the extracted contour information to obtain a resin region information set; calculating and obtaining the total area information of the resin region information set, and performing proportional calculation on the total area information based on the total volume information of the resin bed to determine the resin volume content information of the resin surface image.

[0012] In a possible implementation, determining the resin ratio supplementation parameters and resin regeneration energy consumption parameters involves the following processes: obtaining a set of factors influencing resin regeneration; performing a ratio stability analysis based on the set of factors to obtain a resin ratio volume standard; performing a ratio supplementation analysis on the resin volume content information based on the resin ratio volume standard to determine the resin ratio supplementation parameters; obtaining the theoretical acid-base content and theoretical demineralized water content for resin regeneration; and calculating the regeneration energy consumption based on the resin volume content information to determine the resin regeneration energy consumption parameters.

[0013] In a possible implementation, determining the resin ratio replenishment parameters involves the following processes: obtaining the standard volume of anion resin V0 and the standard volume of cation resin V2 based on the resin ratio volume standard; determining the volume content of anion resin V1 and the volume content of cation resin V3 based on the resin volume content information; calculating resin deviations for the standard volume of anion resin V0 and the volume content of anion resin V1, as well as the standard volume of cation resin V2 and the volume content of cation resin V3, to determine the deviation volume of anion resin and the deviation volume of cation resin; and performing a resin replenishment early warning analysis based on the deviation volume of anion resin and the deviation volume of cation resin to determine the resin ratio replenishment parameters.

[0014] In a possible implementation, the following process is performed: the condensate polishing system consists of a polishing system and a resin regeneration system, wherein the polishing system includes a high-speed mixed bed, a bypass and recirculation system, and the resin regeneration system includes a cation regeneration tower, an anion regeneration tower, a resin separation tower and an acid / alkali metering tank.

[0015] This application proposes an intelligent control method for resin regeneration in condensate polishing. First, N resins to be used are numbered and identified, resulting in N resin numbering information. Then, based on these N resin numbering information and the valve on / off status set of the condensate polishing system, the flow path of each resin is tracked and recorded. Next, the mixed bed effluent status data stream is monitored and acquired in real time. Combining the N resin flow path information, the mixed bed effluent status data stream, and historical resin effluent cycle data, the regeneration cycle is predicted, yielding N resin regeneration condition parameters. Resin delivery and regeneration control are then performed based on these parameters. Simultaneously, a sight glass acquisition device acquires real-time resin liquid level images and calculates the resin volume content information from these images. Finally, based on the resin volume content information, ratio stability and regeneration energy consumption analysis are performed to determine resin ratio replenishment parameters and resin regeneration energy consumption parameters. These parameters are then used for energy-saving resin regeneration control. This method achieves the technical effects of improving the accuracy and stability of resin regeneration control and reducing regeneration energy consumption. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a schematic flowchart of an intelligent control method for regenerating condensate polishing resin, provided in an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating the recording of N resin flow path information in an intelligent control method for resin regeneration in condensate polishing provided in an embodiment of this application. Detailed Implementation

[0019] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] In the following description, references to "some embodiments" describe a subset of all possible embodiments; however, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. 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 not explicitly listed or inherent to such processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0022] This application provides an intelligent control method for regenerating condensate polishing resin, such as... Figure 1 As shown, the method includes:

[0023] Step S100: Number and label the N resins to be applied to obtain N resin number information.

[0024] Specifically, each resin to be applied is uniquely identified using methods such as barcodes, QR codes, RFID tags, or digital codes. These identifiers are affixed or embedded in the resin packaging or container, and a dedicated scanning device or reader is used to record the serial number information of each resin. Here, N resins to be applied refers to the total number of resins requiring condensate polishing, where N is a natural number. The resin serial number information is a unique identifier for each resin, used for subsequent tracking and management.

[0025] In one possible implementation, obtaining N resin number information, step S100 further includes step S110: acquiring resin number requirement targets, parsing the resin number requirement targets, and determining number element information, which includes resin type, resin application batch, and system storage location. Specifically, specific requirements for resin numbers are collected through system input, user interface interaction, or preset configuration files, such as what information needs to be included for management and tracking. The collected requirements are analyzed in detail to clarify the elements that must be included in the number and the optional elements. Based on the parsing results, the basic constituent elements of the number are determined, such as resin type (cationic resin, anion resin, etc.), resin application batch (production batch or usage sequence), and system storage location (specific storage container or area).

[0026] Step S120: Classify the information of each resin among the N resins to be applied using the numbering element information to obtain N resin numbering element parameters. Specifically, based on the numbering element information, classify and organize the relevant information (such as type, batch, storage location) of each resin to be applied, and generate a parameter set containing all necessary numbering elements for each resin. These parameters are used for numbering and identification.

[0027] Step S130: Based on the numbering element information, design numbering rules and build a resin numbering system. The resin numbering system includes numbering sequence and numbering identifier. Specifically, based on the numbering element information, formulate the rules for number composition, such as the length of the number, the order of the elements, and the range of characters or numbers used. Systematize the numbering rules to form a complete numbering system, including the numbering generation method, interpretation method, and possible variations.

[0028] Step S140: Number and identify each resin parameter among the N resin numbering element parameters according to the resin numbering system to obtain the N resin numbering information. Specifically, based on the established resin numbering system, number the numbering element parameters of each resin to generate a unique resin number. After numbering all resins, a complete resin numbering information set is formed for subsequent management and tracking. This implementation method, by clearly defining numbering requirements, determining numbering elements, designing numbering rules, and building a numbering system, achieves the systematic generation of resin numbering information and reduces the possibility of human error, providing strong support for the effective management and tracking of resins.

[0029] Step S200: Based on the N resin number information and the valve switch status set of the condensate polishing system, the flow path of the N resins to be applied is tracked, and the flow path information of the N resins is recorded.

[0030] Specifically, IoT technologies, such as sensors and RFID readers, are used in conjunction with the valve on / off status of the condensate polishing system to track the resin's flow path in the system in real time. The flow path of each resin is recorded through a database or data management system, including its starting position, the valves it passes through, and its destination. The valve on / off status set refers to the set of on / off states of all valves in the condensate polishing system, used to determine the resin's flow direction. The flow path information refers to the complete record of the resin's flow path from start to finish within the system.

[0031] In one possible implementation, step S200 further includes step S210, wherein the condensate polishing system comprises a polishing system and a resin regeneration system, wherein the polishing system includes a high-speed mixed bed, a bypass and recirculation system, and the resin regeneration system includes a cation regeneration tower, an anion regeneration tower, a resin separation tower and an acid / alkali metering tank.

[0032] Specifically, the condensate polishing system is clearly divided into two main parts: the polishing system and the resin regeneration system. The high-speed mixed bed in the polishing system is a highly efficient water treatment device that removes ions and impurities from the water through the adsorption and exchange of resin; it is the core equipment for polishing. The bypass in the polishing system is a backup or auxiliary flow path set up outside the main flow path. It provides a bypass path for condensate when the high-speed mixed bed requires maintenance or malfunctions, ensuring system continuity. The recirculation system in the polishing system is a circulation pipeline system that returns a portion of the treated condensate to the mixed bed inlet, used to improve treatment efficiency and resin utilization.

[0033] The cation exchange resin regeneration tower in the resin regeneration system is used to regenerate cation exchange resins, restoring their exchange capacity through chemical methods. The anion exchange resin regeneration tower is used to regenerate anion exchange resins, similarly restoring their exchange capacity through chemical methods. The resin separation tower separates the cation and anion resins in the mixed bed before regeneration, allowing for separate regeneration of each resin. The acid / alkali metering tank stores and measures the acid / alkali solutions used for resin regeneration, ensuring the accuracy and controllability of the regeneration process.

[0034] The aforementioned components are integrated through pipes, valves, pumps, and other equipment to form a complete condensate polishing system. Sensors and monitoring devices are installed at key locations to monitor the system's operating status and parameters in real time, transmitting the data to the control system for analysis and processing. The control system (such as PLC or DCS) enables automated operation and coordinated operation of the various devices. This approach, by clearly defining the various components of the system and their connections, determines the composition and function of the condensate polishing system, thus establishing the foundation for resin flow path tracking and regeneration control.

[0035] like Figure 2 As shown, in one possible implementation, the step S200 of recording N resin flow path information further includes step S220, which initializes and obtains the initial position information of the N resins to be applied. Specifically, a one-time information entry process is performed when the system is started or when the resin is first introduced into the system. The initial storage position or state of each resin in the system is obtained through manual input, automatic scanning (such as using RFID tags), or system presets.

[0036] Step S230: Based on the valve distribution and structural information of the condensate polishing system, a flow path tracking system is built, and the initial position information of the N resins is input into the flow path tracking system. Specifically, detailed information such as the position, type (e.g., on / off valve, regulating valve), connection method (e.g., series, parallel), and logical relationships between all valves in the system are collected through design drawings and other means. Using the valve distribution and structural information, combined with computer programming and database technology, a system capable of simulating and tracking the resin flow path in the system is constructed. This system has functions such as real-time updating of valve status, calculating possible resin flow paths based on valve status changes, and recording the actual resin flow paths. After the flow path tracking system is built, the initial position information of the N resins obtained earlier is input into the system. This information includes the resin number, initial storage location, and status (e.g., whether it is in use, whether it is in the regeneration process, etc.).

[0037] Step S240: Based on the valve on / off state set, the flow path tracking system performs flow path analysis to obtain a resin predicted flow path set. Specifically, the on / off state of all valves in the system is monitored in real time, and a state dataset is formed. Using the flow path tracking system, combined with the valve on / off state set, possible flow paths of resin in the system are predicted through logical judgment (such as determining which paths are connected based on the valve's open and closed state) or algorithmic calculation (such as using graph theory algorithms to calculate all possible paths of resin from the starting point to the ending point), thus obtaining the resin predicted flow path set.

[0038] Step S250 involves tracking the flow paths of the N resins to be applied by combining the N resin number information, the N resin initial position information, and the predicted flow path set, thereby obtaining N resin flow path information. Specifically, the resin number information, initial position information, and predicted flow path set are associated and integrated. The actual flow path of the resin in the system is updated and recorded in real time using the flow path tracking system. When the valve status changes, the system recalculates the resin flow path based on the new valve status and updates the record, obtaining resin flow path information, including the resin's starting position, the valves it passes through, and the flow time. This implementation method, through initialization, system construction, path parsing, and path tracking, achieves resin flow path tracking in the condensate polishing system, providing strong support for effective resin management and control, and improving management accuracy.

[0039] In one possible implementation, obtaining the N resin flow path information, step S250 further includes step S251, determining the N resin flow status information based on the N resin number information and the N resin initial position information. Specifically, combining the resin number and initial position information, the current flow status of each resin is determined through system logic judgment or algorithm calculation, that is, the current position or state of the resin in the system. The flow status includes: working in a mixed bed, regenerating in a regeneration tower, separating in a separation tower, and being ready for use in a storage area, etc.

[0040] Step S252: The path tracking of the N resins to be applied is recorded according to the N resin number information and the N resin flow status information to obtain N resin flow monitoring path information. Specifically, a flow path tracking system is used to record the resin flow path in the system in real time. The recorded content includes the valves, path nodes, timestamps, etc., that the resin passes through from its initial position to its current position.

[0041] Step S253 involves performing intersection matching between the predicted resin flow path set and the N resin flow monitoring path information to determine the N resin flow path information. Specifically, the predicted flow path set and the monitored flow path information are compared and analyzed to find their intersection or matching parts. Based on the intersection matching result, the actual flow path information of each resin is determined. This implementation method, through steps such as determining flow status information, path tracking records, and intersection matching, achieves accurate tracking and management of the resin flow path in the condensate polishing system.

[0042] Step S300: Real-time monitoring and acquisition of mixed bed effluent status data stream; combining the N resin flow path information, the mixed bed effluent status data stream, and historical resin effluent cycle data to predict the regeneration cycle and obtain N resin regeneration condition parameters.

[0043] Specifically, online monitoring instruments (such as conductivity meters and pH meters) are used to monitor the effluent status of the mixed bed in real time, including conductivity and pH value. Based on machine learning algorithms or statistical models, and combining the mixed bed effluent status data stream, resin flow path information, and historical resin effluent cycle data, the regeneration cycle of each resin is predicted. Based on the prediction results, the regeneration conditions for each resin are determined, i.e., the condition parameters required to trigger resin regeneration, such as regeneration time. The historical resin effluent cycle data is a record of past resin effluent cycles, used for model training and prediction.

[0044] In one possible implementation, obtaining N resin regeneration condition parameters, step S300 further includes step S310, which involves obtaining historical effluent cycle data for the N resins to be used based on the historical resin effluent cycle data. The historical effluent cycle data includes mixed bed effluent status data, resin flow path data, and corresponding resin regeneration cycle data. Specifically, based on the historical resin effluent cycle data, the specific historical effluent cycle data for the N resins to be used is retrieved and extracted. The historical resin effluent cycle data refers to the record of the effluent status (e.g., water quality, flow rate) and regeneration cycle of the resin during use over a past period. The mixed bed effluent status data reflects the water quality after mixed bed treatment. The resin flow path data is a record of the resin's flow path within the system, including flow information from which device to which device. The resin regeneration cycle data refers to the time or volume of water treated from when the resin is put into use until regeneration is required.

[0045] Step S320: A recurrent neural network (RNN) structure is used to label and train the historical effluent cycle data of the N resins to be applied, constructing a resin regeneration cycle prediction network. Specifically, the extracted historical data is cleaned, normalized, or standardized to ensure data quality. A recurrent neural network (RNN) structure, such as a Long Short-Term Memory (LSTM) network or a gated recurrent unit (GRU), is selected, and the preprocessed data is used to supervise the training of the RNN model, enabling it to learn patterns in the historical effluent cycle data.

[0046] Step S330: Based on the resin regeneration cycle prediction network, predict the effluent cycle of the N resin flow path information and the mixed bed effluent status data stream, and output N predicted resin regeneration cycles. Specifically, based on the trained resin regeneration cycle prediction network, predict the effluent cycle of the N resin flow path information and the real-time mixed bed effluent status data stream. Using the real-time acquired resin flow path information and the mixed bed effluent status data stream as input data, use the trained RNN model to predict these input data and output N predicted resin regeneration cycles.

[0047] Step S340 involves analyzing the regeneration conditions based on the predicted regeneration cycles of the N resins to obtain N resin regeneration condition parameters. Specifically, based on the predicted N resin regeneration cycles, combined with the system's operating rules and resin characteristics, the regeneration conditions for each resin are determined, such as regeneration time and the required acid / alkali amounts. This implementation uses a machine learning model to accurately predict the resin regeneration cycle, avoiding premature or delayed regeneration and reducing resource waste. Accurate regeneration cycle prediction allows for reasonable scheduling of regeneration time, extending the mixed bed's effluent cycle and improving the system's operational safety and stability.

[0048] In one possible implementation, obtaining N resin regeneration condition parameters, step S340 further includes step S341, which involves mining historical regeneration data based on the N resins to be applied to construct N resin regeneration control spaces. These N resin regeneration control spaces include resin regeneration cycle data, regeneration condition parameters, and corresponding regeneration effect data. Specifically, regeneration cycle data, regeneration condition parameters (such as regeneration time, acid / alkali concentration, etc.), and corresponding regeneration effect data (such as resin performance recovery degree, effluent quality, etc.) for each resin are extracted from a database or historical records. The extracted data is cleaned to remove outliers and noise, ensuring data accuracy and consistency. Based on the cleaned data, a multi-dimensional control space is constructed for each resin, where each dimension represents a regeneration condition parameter or regeneration effect data, used to describe the relationship between resin regeneration conditions and effects.

[0049] Step S342: Based on the N resin regeneration control spaces, perform regeneration condition analysis on the N predicted regeneration cycles of each resin to obtain N resin regeneration parameter selection thresholds. Specifically, map the predicted regeneration cycle of each resin to its corresponding regeneration control space. Within the regeneration control space, find the matching range of regeneration condition parameters, i.e., the regeneration parameter selection thresholds, according to the predicted regeneration cycle.

[0050] Step S343 involves a global comparison and optimization within the selected thresholds of the N resin regeneration parameters to obtain the N resin regeneration condition parameters. Specifically, based on the goals and constraints of resin regeneration, an objective function is designed to evaluate the regeneration effect under different regeneration condition parameters. A global search algorithm (such as genetic algorithm, particle swarm optimization, etc.) is used to search within the selected thresholds of the regeneration parameters to find the regeneration condition parameters that optimize the objective function. Based on the results of the search algorithm, the regeneration condition parameters are optimized and adjusted to obtain the final resin regeneration condition parameters. This implementation method, through data mining, condition analysis, and global comparison and optimization techniques, achieves accurate analysis and optimization of resin regeneration condition parameters, thereby reducing the cost and energy consumption of resin regeneration and improving the economic efficiency of the system.

[0051] Step S400: Based on the N resin regeneration condition parameters, resin delivery and regeneration control are performed. At the same time, the resin liquid level image is acquired in real time using the sight glass acquisition device, and the resin volume content information of the resin liquid level image is calculated.

[0052] Specifically, based on regeneration condition parameters, the control system automatically adjusts valve opening and closing, pump operation, etc., to realize the resin transportation and regeneration process. Sight glasses are installed on the resin storage tank or regeneration tower, equipped with image acquisition devices (such as cameras) to acquire real-time images of the resin liquid level. Image processing algorithms (such as edge detection, threshold segmentation, etc.) are used to analyze the sight glass images and calculate the volumetric resin content in the storage tank or regeneration tower.

[0053] In one possible implementation, the step S400 of calculating the resin volume content information of the resin surface image further includes step S410, which converts the resin surface image into a grayscale image and performs filtering, noise reduction, and contrast enhancement on the grayscale image to obtain a standard resin surface grayscale image. Specifically, the original color resin surface image is converted into a grayscale image by calculating the weighted average of the red, green, and blue (RGB) values ​​of each pixel. Filters (such as Gaussian filters, median filters, etc.) are applied to smooth the grayscale image, removing noise and unnecessary details. Histogram equalization, linear stretching, or adaptive contrast enhancement are used to improve the contrast of the grayscale image, making the edges of the resin surface clearer. Here, a grayscale image is an image that contains only brightness information and no color information; each pixel is represented by a grayscale value.

[0054] Step S420: The Sobel operator is used to perform edge detection on the grayscale image of the standard resin liquid surface to determine the edge information of the resin liquid surface. Specifically, the Sobel operator is a discrete differential operator for edge detection that detects edges by calculating the gradient of the image's grayscale values. The Sobel operator includes two filters, one horizontal and one vertical, used to detect horizontal and vertical edges, respectively. The Sobel operator is applied to the grayscale image of the standard resin liquid surface, and the gradient magnitude and direction of each pixel are calculated. The edge position is determined based on the magnitude of the gradient magnitude.

[0055] Step S430: Extract the contour of the standard resin surface grayscale image according to the resin surface edge information, and fill the region based on the extracted contour information to obtain a resin region information set. Specifically, based on the edge detection results, extract the contour of the resin surface using a contour tracking algorithm (such as an eight-neighbor search algorithm). Fill the extracted contour to generate a binary image representing the resin region, where the resin region is white (or 1) and the background is black (or 0).

[0056] Step S440: Calculate the total area information of the resin region information set. Based on the total volume information of the resin bed, perform a proportional calculation on the total area information to determine the resin volume content information of the resin surface image. Specifically, count the number of white (or 1) pixels in the binary image as the total area of ​​the resin region. Obtain the total volume information of the resin bed through design parameters, measurement, or calibration. Calculate the actual volume unit represented by each pixel based on the actual size of the resin bed and the physical size of the pixels in the image. Then, multiply the total area information (number of pixels) of the resin region by the actual volume unit of each pixel to obtain the actual volume of the resin. Finally, divide the actual volume of the resin by the total volume of the resin bed to obtain the resin volume content information. This implementation method, through image preprocessing, edge detection, contour extraction, and region filling, can accurately identify the resin region, thereby improving the accuracy of volume content measurement.

[0057] Step S500: Based on the resin volume content information, perform ratio stability and regeneration energy consumption analysis to determine resin ratio replenishment parameters and resin regeneration energy consumption parameters, and perform resin regeneration energy-saving control through the resin ratio replenishment parameters and resin regeneration energy consumption parameters.

[0058] Specifically, by utilizing resin volumetric content information and comparing it with preset resin ratio standards or historical optimal ratio data, the stability of the current resin ratio is analyzed. Based on the analysis results, if the resin ratio deviates from the preset standard or historical optimal value, the amount of resin to be supplemented or adjusted is calculated to restore or optimize the ratio. This includes determining which type of resin to supplement (e.g., cationic resin, anionic resin), the amount to supplement, and the timing of supplementation. Based on the resin volumetric content information, combined with energy consumption data during the regeneration process (e.g., water consumption, chemical reagent consumption), energy consumption analysis is performed. Through energy consumption analysis, energy consumption indicators under different resin regeneration conditions are determined, such as the resource consumption per unit of resin regeneration. Based on the resin ratio supplementation parameters and resin regeneration energy consumption parameters, the regeneration strategy is adjusted to minimize energy consumption while ensuring the resin regeneration effect. This application employs techniques such as numbering and identifying resins and tracking their flow paths, real-time monitoring of the mixed bed effluent status and prediction of regeneration cycles based on historical data, controlling resin delivery and regeneration based on the prediction results, simultaneously acquiring real-time resin liquid level images to calculate volume content, and finally performing ratio stabilization and regeneration energy consumption analysis for energy-saving control. These techniques achieve the technical effects of improving the accuracy and stability of resin regeneration control and reducing regeneration energy consumption.

[0059] In one possible implementation, the step S500 of determining the resin ratio supplementation parameters and resin regeneration energy consumption parameters further includes step S510: obtaining a set of factors affecting resin regeneration, performing a ratio stability analysis based on the set of factors affecting resin regeneration, and obtaining a resin ratio volume standard. Specifically, various factors affecting resin regeneration are collected through historical data, experimental data, or expert experience, such as resin type, service life, number of regenerations, influent water quality, type and concentration of regenerant, regeneration temperature, and regeneration time. The collected factors are organized to form a set of factors affecting resin regeneration. Based on the characteristics and requirements of resin regeneration, an analytical method is selected, such as statistical analysis, regression analysis, or machine learning. Using the selected analytical method, the set of factors affecting resin regeneration is analyzed to identify the key factors affecting the stability of the resin ratio. Based on the analysis results and combined with the actual needs of resin regeneration, the volume standard of the resin ratio is determined, i.e., the optimal volume ratio that the resin should maintain during the regeneration process.

[0060] Step S520: Based on the resin volume ratio standard, perform a ratio supplement analysis on the resin volume content information to determine the resin ratio supplement parameters. Specifically, obtain the resin volume content information from the resin liquid level image, i.e., the volume proportion of resin in the resin bed. Compare the resin volume content information with the resin volume ratio standard to identify differences. Based on the differences, determine the resin ratio supplement parameters, i.e., the amount of resin volume that needs to be supplemented or adjusted.

[0061] Step S530: Obtain the theoretical acid / base content and theoretical demineralized water content of the resin. Based on these values, calculate the regeneration energy consumption of the resin volume content information to determine the resin regeneration energy consumption parameters. Specifically, based on the type of resin, regeneration process, and regeneration effect requirements, calculate or consult relevant data to obtain the theoretical acid / base content and demineralized water content required for resin regeneration. The theoretical acid / base content refers to the amount of acid or alkali theoretically required during resin regeneration to restore the resin's exchange capacity. The theoretical demineralized water content refers to the amount of demineralized water theoretically required during resin regeneration to rinse the resin and remove waste generated during regeneration. Based on the theoretical acid / base content and demineralized water content, and combined with the resin volume content information, calculate the resource consumption during regeneration. Based on the results of the regeneration energy consumption calculation, determine the energy consumption parameters for resin regeneration, such as the amount of regeneration resources consumed and the resource consumption cost. This implementation method, by obtaining a set of factors affecting resin regeneration and performing a ratio stability analysis, can identify key factors affecting the stability of the resin ratio, thereby determining the resin ratio volume standard. This helps ensure that the resin maintains a stable volume ratio during regeneration, improving the effect and efficiency of resin regeneration. By obtaining the theoretical acid and alkali content and demineralized water content of the resin, and combining this with the resin volume content information to calculate the regeneration energy consumption, it is possible to accurately control the energy consumption of resin regeneration, reduce energy costs, and improve energy utilization efficiency.

[0062] In one possible implementation, the step S520 of determining the resin proportioning supplementary parameters further includes step S521, obtaining the standard volume of anion resin V0 and the standard volume of cation resin V2 according to the resin proportioning volume standard. Specifically, the standard volumes of anion resin and cation resin are extracted from the resin proportioning volume standard and denoted as V0 and V2, respectively. The standard volume of anion resin V0 refers to the volume of anion resin that should be maintained in the proportioning volume standard. The standard volume of cation resin V2 refers to the volume of cation resin that should be maintained in the proportioning volume standard.

[0063] Step S522: Based on the resin volume content information, determine the anion resin volume content V1 and the cation resin volume content V3. Specifically, based on the resin volume content information, calculate the volume contents of the anion resin and cation resin respectively, and denote them as V1 and V3. The anion resin volume content V1 is the volume percentage of anion resin in the resin bed calculated in real time. The cation resin volume content V3 is the volume percentage of cation resin in the resin bed calculated in real time.

[0064] Step S523: Resin deviation calculations are performed on the standard volume of anion resin V0 and the volume content of anion resin V1, as well as the standard volume of cation resin V2 and the volume content of cation resin V3, to determine the deviation volume of anion resin and cation resin. Specifically, the difference between the standard volume of anion resin V0 and the volume content of anion resin V1 is calculated to obtain the deviation volume of anion resin; similarly, the difference between the standard volume of cation resin V2 and the volume content of cation resin V3 is calculated to obtain the deviation volume of cation resin. The resin deviation volume is the difference between the actual volume content of resin and the standard volume, used to assess the degree of deviation in the resin formulation.

[0065] Step S524: Based on the deviation volume of the anion resin and the deviation volume of the cation resin, a resin replenishment early warning analysis is performed to determine the resin ratio replenishment parameters. Specifically, it is analyzed whether the deviation volume of the anion and cation resin exceeds a preset threshold range. If it does, a replenishment early warning is triggered. Based on the results of the resin replenishment early warning analysis, the type (anion resin or cation resin), amount, and timing of replenishment are determined, forming the resin ratio replenishment parameters, i.e., the parameters for the type, amount, and timing of replenishment of resin determined to maintain or optimize the resin ratio. This implementation method, by real-time monitoring of resin volume content and calculation of deviation, can accurately determine the type and amount of resin to be replenished, avoiding resource waste caused by inaccurate manual judgment. By optimizing the resin ratio, frequent regeneration caused by resin ratio imbalance is reduced, thereby saving the amount of acid, alkali, and demineralized water used.

[0066] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application. In some cases, the actions or steps described in this application can be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for intelligent control of condensate polishing resin regeneration, characterized in that, The method includes: Number and label N resins to be applied to obtain N resin number information; Based on the N resin number information and the valve switch status set of the condensate polishing system, the flow path of the N resins to be applied is tracked, and the flow path information of the N resins is recorded. Real-time monitoring and acquisition of mixed bed effluent status data stream, combined with the N resin flow path information, the mixed bed effluent status data stream and historical resin effluent cycle data, to predict the regeneration cycle and obtain N resin regeneration condition parameters. Resin delivery and regeneration are controlled based on the N resin regeneration condition parameters. At the same time, the resin liquid level image is acquired in real time using a sight glass acquisition device, and the resin volume content information of the resin liquid level image is calculated. Based on the resin volume content information, the ratio stability and regeneration energy consumption analysis are performed to determine the resin ratio replenishment parameters and resin regeneration energy consumption parameters, and the resin regeneration energy-saving control is carried out through the resin ratio replenishment parameters and resin regeneration energy consumption parameters. The obtained N resin regeneration condition parameters include: Based on the historical resin effluent cycle data, the historical effluent cycle data of the N resins to be used are obtained. The historical effluent cycle data includes mixed bed effluent status data, resin flow path data, and corresponding resin regeneration cycle data. A recurrent neural network structure is used to identify and train the historical effluent cycle data of the N resins to be applied, and a resin regeneration cycle prediction network is constructed. Based on the resin regeneration cycle prediction network, the effluent cycle of the N resin flow path information and the mixed bed effluent status data stream is predicted, and N resin regeneration cycles are output. Based on the N predicted regeneration cycles of the resin, the regeneration conditions are analyzed to obtain N resin regeneration condition parameters. The obtained N resin regeneration condition parameters include: Based on the historical regeneration data mining of the N resins to be applied, N resin regeneration control spaces are constructed. The N resin regeneration control spaces include resin regeneration cycle data, regeneration condition parameters and corresponding regeneration effect data. Based on the N resin regeneration control spaces, the regeneration conditions of the N predicted regeneration cycles of the resins are analyzed to obtain the selection thresholds of the N resin regeneration parameters. Global comparison and optimization are performed within the selected thresholds of the N resin regeneration parameters to obtain the N resin regeneration condition parameters.

2. The intelligent control method for regenerating condensate polishing resin as described in claim 1, characterized in that, The obtained N resin number information includes: Obtain the resin number requirement target, parse the resin number requirement target, and determine the number element information, which includes resin type, resin application batch and system storage location. The resin information among the N resins to be applied is classified using the numbering element information to obtain N resin numbering element parameters; Based on the numbering element information, a numbering rule is designed to build a resin numbering system, which includes a numbering sequence and a numbering identifier. According to the resin numbering system, each resin parameter in the N resin numbering element parameters is numbered and identified to obtain the N resin numbering information.

3. The intelligent control method for regenerating condensate polishing resin as described in claim 1, characterized in that, The recording of N resin flow path information includes: Initialize to obtain the initial position information of the N resins to be applied; Based on the valve distribution structure information of the condensate polishing system, a flow path tracking system is built, and the initial position information of the N resins is input into the flow path tracking system. Based on the valve switch state set, the flow path tracking system is analyzed to obtain the resin predicted flow path set. By combining the N resin number information, the N resin initial position information, and the resin predicted flow path set, the flow path of the N resins to be applied is tracked to obtain the flow path information of the N resins.

4. The intelligent control method for regenerating condensate polishing resin as described in claim 3, characterized in that, The obtained N resin flow path information includes: Based on the N resin number information and the N resin initial position information, determine the N resin flow status information; The path tracking and recording of the N resins to be applied are performed according to the N resin number information and the N resin circulation status information to obtain N resin circulation monitoring path information; The predicted resin flow path set and the N resin flow monitoring path information are intersected and matched to determine the N resin flow path information.

5. The intelligent control method for regenerating condensate polishing resin as described in claim 1, characterized in that, The calculation of the resin volume content information of the resin liquid level image includes: The resin liquid surface image is converted into a resin liquid surface grayscale image, and the resin liquid surface grayscale image is filtered, denoised, and contrast-enhanced to obtain a standard resin liquid surface grayscale image. The Sobel operator is used to perform edge detection on the grayscale image of the standard resin liquid surface to determine the edge information of the resin liquid surface. The standard resin liquid surface grayscale image is contour extracted according to the resin liquid surface edge information, and the region is filled based on the extracted contour information to obtain a resin region information set. The total area information of the resin region information set is calculated, and the total area information is proportionally calculated based on the total volume information of the resin bed to determine the resin volume content information of the resin liquid surface image.

6. The intelligent control method for regenerating condensate polishing resin as described in claim 1, characterized in that, The determination of resin ratio replenishment parameters and resin regeneration energy consumption parameters includes: A set of factors affecting resin regeneration is obtained, and a formulation stability analysis is performed based on the set of factors affecting resin regeneration to obtain the resin formulation volume standard. Based on the resin volume ratio standard, a supplementary analysis of the resin volume content information is performed to determine the supplementary resin ratio parameters. Obtain the theoretical acid-base content and theoretical demineralized water content of the resin for regeneration. Based on the theoretical acid-base content and theoretical demineralized water content of the resin for regeneration, calculate the regeneration energy consumption of the resin volume content information to determine the resin regeneration energy consumption parameters.

7. The intelligent control method for regenerating condensate polishing resin as described in claim 6, characterized in that, The parameters for determining the resin ratio include: Based on the resin mixing volume standard, the standard volume of anion resin V0 and the standard volume of cation resin V2 are obtained. Based on the resin volume content information, the anion resin volume content V1 and the cation resin volume content V3 are determined. Resin deviations were calculated for the standard volume V0 and volume content V1 of the anion resin, and the standard volume V2 and volume content V3 of the cation resin, respectively, to determine the deviation volume of the anion resin and the deviation volume of the cation resin. Based on the deviation volume of the anion resin and the deviation volume of the cation resin, a resin replenishment early warning analysis is performed to determine the resin ratio replenishment parameters.

8. The intelligent control method for regenerating condensate polishing resin as described in claim 1, characterized in that, The condensate polishing system consists of a polishing system and a resin regeneration system. The polishing system includes a high-speed mixed bed, a bypass and recirculation system, and the resin regeneration system includes a cation regeneration tower, an anion regeneration tower, a resin separation tower and an acid / alkali metering tank.

Images