Water purification equipment control optimization system based on internet of things

Abstract

An IoT-based water purification equipment control and optimization system relates to the field of equipment optimization technology. It acquires physical information of the water purification equipment and constructs a physical model; obtains pre-purification and post-purification data and constructs a simulation model to obtain membrane performance parameters; acquires membrane flux, recovery rate, and rejection rate at the same time; adjusts the differential pressure, membrane flux, and recovery rate at the same time in the simulation model to obtain the clogging coefficient; and constructs a clogging assessment model based on the membrane performance parameters. It determines whether a membrane leakage fault exists based on the rejection rate and replaces the affected membrane; uses the clogging assessment model to obtain a predicted clogging coefficient; and determines whether a membrane clogging fault exists based on the predicted clogging coefficient and flushes the affected membrane. This system can reflect the operating status of RO membrane elements from different perspectives, which is beneficial for extending the working time of RO membrane elements and reducing the total cost of water purification.

Description

Technical Field

[0001] This invention relates to the field of equipment optimization technology, specifically an Internet of Things-based water purification equipment control optimization system. Background Technology

[0002] Control optimization of water purification equipment is an innovative solution that comprehensively utilizes technologies such as the Internet of Things, big data, and cloud computing to achieve intelligent and refined control and management of water purification equipment. It breaks the limitations of the traditional isolated operation of water purification equipment and significantly improves the operating efficiency, water quality stability, and user experience of water purification equipment through real-time data interaction and analysis.

[0003] The reverse osmosis system, especially the RO membrane element, plays a major role in water purification. It can filter out most impurities and pollutants in the raw water. Existing technologies often emphasize the overall optimization of the water purification equipment, while neglecting the detailed optimization of important components. They fail to analyze and predict the operating status and potential blockage of the RO membrane element by comprehensively considering data from different perspectives, which results in the failure to effectively extend its service life and increase the overall water purification cost. In order to address the shortcomings of existing technologies, this invention provides a water purification equipment control and optimization system based on the Internet of Things. Summary of the Invention

[0004] The purpose of this invention is to provide a water purification equipment control and optimization system based on the Internet of Things.

[0005] The objective of this invention can be achieved through the following technical solution: a water purification equipment control and optimization system based on the Internet of Things, comprising the following modules:

[0006] The data acquisition module is used to acquire the physical information of the water purification equipment and build a physical model, acquire the pre-purification and post-purification data of the water purification equipment, and build a simulation model to obtain membrane performance parameters.

[0007] The data analysis module is used to obtain the membrane flux, recovery rate, and rejection rate at the same time based on the pre-purification and post-purification data of the water purification equipment.

[0008] The data simulation module is used to adjust the pressure difference, membrane flux, and recovery rate at the same time in the simulation model, and obtain the corresponding blockage coefficient.

[0009] The data evaluation module is used to construct a blockage evaluation model for water purification equipment based on pressure difference, membrane flux, recovery rate, and blockage coefficient at different times, combined with membrane performance parameters.

[0010] The data optimization module is used to determine whether there is a membrane leakage fault based on the rejection rate and replace it. It uses a blockage assessment model to obtain a predicted blockage coefficient, and determines whether there is a membrane blockage fault based on the predicted blockage coefficient and flushes it.

[0011] Furthermore, the process of acquiring physical information about the water purification equipment and constructing a physical model includes:

[0012] The water purification equipment refers to the equipment that converts raw water into purified water that meets the requirements of a specific purpose, and the physical information refers to the physical structural dimensions of each component of the reverse osmosis system in the water purification equipment.

[0013] The reverse osmosis system includes a high-pressure pump, RO membrane elements, membrane housing, online conductivity meter, and flushing device. A corresponding physical model is constructed using 3D modeling tools based on the acquired physical information.

[0014] Furthermore, the process of acquiring pre- and post-purification data from the water purification equipment and constructing a simulation model to obtain membrane performance parameters includes:

[0015] The pre-net data refers to the parameter values ​​corresponding to the water quality parameters, pollutant parameters, influent flow rate, temperature, and pressure of the raw water before it is treated by the RO membrane element in the reverse osmosis system.

[0016] The working process of the reverse osmosis system is simulated using simulation software based on the physical model of the reverse osmosis system to obtain the corresponding simulation model. The obtained net pre-data is uploaded to the simulation model for synchronization, and the membrane characteristic parameters of the RO membrane element in the simulation model are adjusted.

[0017] The membrane characteristic parameters include membrane permeability, solute permeability, and membrane surface roughness. Simulated post-purification data in the simulation model are obtained under different values ​​of membrane characteristic parameters. When the obtained simulated post-purification data is the same as the post-purification data at the corresponding time of the synchronized pre-purification data, the membrane characteristic parameter with the corresponding value in the simulation model at this time is used as the membrane performance parameter of the water purification equipment.

[0018] Furthermore, the process of obtaining membrane flux, recovery rate, and retention rate at the same time point based on pre- and post-purification data from the water purification equipment includes:

[0019] Set an analysis cycle. When an analysis cycle is completed, obtain the corresponding membrane flux J based on the pre-net and post-net data at that time. w and recovery rate R e ;

[0020]

[0021] Q p The permeate flow rate in the purified data is A, where A is the effective area of ​​the RO membrane element, and Q is Q.f This refers to the influent flow rate in the pre-net data;

[0022] The rejection rate refers to the changes in water quality parameters and pollutant parameters before and after the RO membrane element. The parameter values ​​of individual parameters in the pre-cleaning and post-cleaning data are denoted as C, respectively. f and C p Obtain the retention rate R of this single parameter at the corresponding time. j ;

[0023]

[0024] The retention rates of other parameters in the water quality parameters and pollutant parameters were obtained separately.

[0025] Furthermore, the process of adjusting the pressure difference, membrane flux, and recovery rate at the same moment in the simulation model and obtaining the corresponding blocking coefficient includes:

[0026] In the simulation model, each parameter in the pre-net data is adjusted to obtain simulated pre-net data, and the corresponding simulated post-net data is obtained. Based on the simulated pre-net data and simulated post-net data at the same time, the corresponding membrane flux and recovery rate are obtained.

[0027] Based on the simulated net post-processing data and its membrane flux and recovery rate at the same time point, the blockage coefficient S of the RO membrane element at the corresponding time point is obtained. z ;

[0028]

[0029] P n J represents the pressure difference in the simulated net post-processing data at the corresponding time point. n R n P0, J0, and R0 represent the membrane flux and recovery rate at the corresponding time points, respectively, and are the preset initial pressure difference, initial membrane flux, and initial recovery rate.

[0030] In the simulation model, the pressure difference, membrane flux, recovery rate and blockage coefficient at different times were obtained.

[0031] Furthermore, the process of constructing a clogging assessment model for the water purification equipment based on pressure difference, membrane flux, recovery rate, and clogging coefficient at different times, combined with membrane performance parameters, includes:

[0032] Based on the pressure difference, membrane flux, recovery rate and the blockage coefficient at different times obtained in the simulation model, a blockage evaluation set is generated by combining the membrane performance parameters of the water purification equipment in the simulation model, and it is divided into training set and test set.

[0033] A convolutional neural network is constructed, with the pressure drop, membrane flux, recovery rate and membrane performance parameters at different times in the training set as the input data of the convolutional neural network, and the blocking coefficient corresponding to the next time step in the training set as the output data of the convolutional neural network.

[0034] The convolutional neural network is trained to obtain an initial convolutional neural network. The initial convolutional neural network is then validated using a test set. The initial convolutional neural network whose output is less than or equal to a preset test error threshold is used as the blockage evaluation model for the water purification equipment.

[0035] Furthermore, the process of determining whether a membrane leakage fault exists based on the retention rate and replacing it accordingly includes:

[0036] Set a retention rate threshold, compare the current retention rate of each water quality parameter and pollutant parameter with the set retention rate threshold, and when the retention rate of at least one parameter is greater than the retention rate threshold, it is determined that there is a membrane leakage fault in the RO membrane element of the water purification equipment, generate a leakage alarm signal and feed it back to the relevant personnel to prompt them to replace the RO membrane element.

[0037] Furthermore, the process of obtaining a predicted blockage coefficient using a blockage assessment model, determining the presence of membrane blockage faults based on the predicted blockage coefficient, and flushing the membrane includes:

[0038] Input the current pressure difference, membrane flux, recovery rate, and membrane performance parameters of the water purification equipment into the blockage assessment model to obtain the corresponding predicted blockage coefficient Sy, and set the blockage coefficient range [Smin, Smax].

[0039] The obtained predicted blockage coefficient is compared with the blockage coefficient range. When Sy≤Smin, it is determined that there is no membrane blockage fault in the RO membrane element of the water purification equipment, and no other operation is performed on it.

[0040] When Smin < Sy < Smax, it is determined that the RO membrane element of the water purification equipment has a slight membrane blockage fault, and the flushing device is controlled to flush the RO membrane element with water. When Sy ≥ Smax, it is determined that the RO membrane element of the water purification equipment has a serious membrane blockage fault, and the flushing device is controlled to flush the RO membrane element with chemicals.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] This invention constructs a corresponding simulation model by acquiring different data of the reverse osmosis system in the water purification equipment before and after water purification. The membrane characteristic parameters in the simulation model are used as the membrane performance parameters of the current water purification equipment. This is beneficial for obtaining the real-time performance of the RO membrane element in the current water purification equipment. By incorporating this into the basis of subsequent evaluation, the accuracy of data evaluation can be improved.

[0043] By obtaining the membrane flux, recovery rate, and rejection rate of the water purification equipment at the same time, the operating status of its RO membrane element can be reflected from different perspectives. The blockage coefficient can be obtained for comprehensive evaluation of the blockage of the RO membrane element. The blockage evaluation model of the water purification equipment can be constructed based on the correspondence of various parameters at different times. The predicted blockage coefficient for the next analysis cycle can be obtained based on the current parameters, providing an effective way to predict the blockage of the RO membrane element.

[0044] By setting the rejection rate threshold and the blockage coefficient range, the possible failures of RO membrane elements can be divided into two types: leakage and blockage. By selecting to replace or clean them, it is beneficial to extend the working time of RO membrane elements and reduce the total cost of water purification equipment. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the modules of the present invention. Detailed Implementation

[0046] like Figure 1 As shown, an IoT-based water purification equipment control and optimization system includes the following modules:

[0047] The data acquisition module is used to acquire the physical information of the water purification equipment and build a physical model, acquire the pre-purification and post-purification data of the water purification equipment, and build a simulation model to obtain membrane performance parameters.

[0048] The data analysis module is used to obtain the membrane flux, recovery rate, and rejection rate at the same time based on the pre-purification and post-purification data of the water purification equipment.

[0049] The data simulation module is used to adjust the pressure difference, membrane flux, and recovery rate at the same time in the simulation model, and obtain the corresponding blockage coefficient.

[0050] The data evaluation module is used to construct a blockage evaluation model for water purification equipment based on pressure difference, membrane flux, recovery rate, and blockage coefficient at different times, combined with membrane performance parameters.

[0051] The data optimization module is used to determine whether there is a membrane leakage fault based on the rejection rate and replace it. It uses a blockage assessment model to obtain a predicted blockage coefficient, and determines whether there is a membrane blockage fault based on the predicted blockage coefficient and flushes it.

[0052] It should be further explained that, in the specific implementation process, the process of obtaining the physical information of the water purification equipment and constructing a physical model includes:

[0053] The water purification equipment refers to equipment that converts raw water into purified water that meets the requirements of a specific purpose. It mainly includes three process steps: pretreatment, core treatment, and post-treatment. The purpose of this invention is to optimize the control of the core treatment step, so only the equipment corresponding to the core treatment step will be discussed.

[0054] The core treatment refers to the removal of dissolved salts, ions, organic matter, microorganisms, viruses, etc. from water to achieve the requirements of high-purity water. This is specifically achieved through a reverse osmosis (RO) system, which includes a high-pressure pump, RO membrane elements, membrane housing, online conductivity meter, and flushing device.

[0055] The high-pressure pump is used to provide the required high pressure for the reverse osmosis system. The RO membrane element is a key filtration unit, generally a spiral wound membrane. The membrane housing is a container used to load the RO membrane element and withstand high pressure. The online conductivity meter is used to monitor the conductivity of the permeate in real time. The flushing device is used to periodically flush or chemically clean the RO membrane element to restore membrane performance.

[0056] The physical information refers to the relevant data of the physical model necessary for constructing the core treatment process of the water purification equipment. Specifically, it is the physical structural dimensions of each component of the reverse osmosis system. The corresponding physical model is constructed using a 3D modeling tool based on the acquired physical information.

[0057] It should be further explained that, in the specific implementation process, the process of obtaining pre- and post-purification data from the water purification equipment and constructing a simulation model to obtain membrane performance parameters includes:

[0058] The pre-net data refers to the parameter values ​​corresponding to the water quality parameters, pollutant parameters, influent flow rate, temperature, and pressure of the raw water before it is treated by the RO membrane element in the reverse osmosis system.

[0059] The water quality parameters include TDS and Ca. 2+ Mg 2+ SO4 2- HCO3 - SiO2, the pollutant parameters include TOC, turbidity, SDI 15 Microbial ATP value;

[0060] The post-treatment data refers to the water quality parameters, pollutant parameters, permeate flow rate, conductivity, and pressure difference of the purified water after treatment by the RO membrane element in the reverse osmosis system.

[0061] The working process of the reverse osmosis system is simulated using simulation software based on the physical model of the reverse osmosis system to obtain the corresponding simulation model. The obtained net pre-data is uploaded to the simulation model for synchronization, and the membrane characteristic parameters of the RO membrane element in the simulation model are adjusted.

[0062] The membrane characteristic parameters include membrane permeability, solute permeability, and membrane surface roughness. Simulated post-purification data in the simulation model are obtained under different values ​​of membrane characteristic parameters. When the obtained simulated post-purification data is the same as the post-purification data at the corresponding time of the synchronized pre-purification data, the membrane characteristic parameter with the corresponding value in the simulation model at this time is used as the membrane performance parameter of the water purification equipment.

[0063] It should be further explained that, in the specific implementation process, the process of obtaining the membrane flux, recovery rate, and retention rate at the same moment based on the pre-purification and post-purification data of the water purification equipment includes:

[0064] The analysis cycle is set, and when an analysis cycle is reached, the corresponding membrane flux and recovery rate are obtained based on the pre-net and post-net data at the corresponding time point, and are denoted as J. w and R e ;

[0065]

[0066] Among them, Q p The permeate flow rate in the purified data is A, where A is the effective area of ​​the RO membrane element, and Q is Q. f This refers to the influent flow rate in the pre-net data;

[0067] The rejection rate refers to the changes in various water quality parameters and pollutant parameters before and after the RO membrane element. Taking a single parameter as an example, its parameter value in the pre-net data is denoted as C. f Let its parameter value in the net data be denoted as C. p Obtain the retention rate of this single parameter at the corresponding time, denoted as R. j ;

[0068]

[0069] The same method was used to obtain the retention rates of various water quality parameters and pollutant parameters.

[0070] It should be further explained that, in the specific implementation process, the process of adjusting the pressure difference, membrane flux, and recovery rate at the same moment in the simulation model and obtaining the corresponding blocking coefficient includes:

[0071] In the simulation model, each parameter in the pre-net data is adjusted and the corresponding simulated post-net data is obtained. The pre-net data under each adjustment is marked as simulated pre-net data. The corresponding membrane flux and recovery rate are obtained based on the simulated pre-net data and simulated post-net data at the same time.

[0072] Based on the simulated net post-flux data and membrane flux and recovery rate at the same time point, the blockage coefficient of the RO membrane element at the corresponding time point is obtained, denoted as S. z ;

[0073]

[0074] Among them, P n J represents the pressure difference in the simulated net post-processing data at the corresponding time point. n R n P0, J0, and R0 represent the membrane flux and recovery rate at the corresponding time points, respectively, and are the preset initial pressure difference, initial membrane flux, and initial recovery rate.

[0075] Using the same method, the pressure difference, membrane flux, recovery rate and their corresponding blockage coefficients at different times were obtained in the simulation model.

[0076] It should be further explained that, in the specific implementation process, the process of constructing a blockage assessment model for the water purification equipment based on pressure difference, membrane flux, recovery rate, and blockage coefficient at different times, combined with membrane performance parameters, includes:

[0077] Based on the pressure difference, membrane flux, recovery rate and the blockage coefficient at different times obtained in the simulation model, a blockage evaluation set is generated by combining the membrane performance parameters of the water purification equipment in the simulation model, and it is divided into training set and test set.

[0078] A convolutional neural network is constructed, with the pressure drop, membrane flux, recovery rate and membrane performance parameters at different times in the training set as the input data of the convolutional neural network, and the blocking coefficient corresponding to the next time step in the training set as the output data of the convolutional neural network.

[0079] The convolutional neural network is trained to obtain an initial convolutional neural network. The initial convolutional neural network is then validated using a test set. The initial convolutional neural network whose output is less than or equal to a preset test error threshold is used as the blockage evaluation model for the water purification equipment.

[0080] It should be further explained that, in the specific implementation process, the process of determining whether there is a membrane leakage fault based on the rejection rate and replacing it includes:

[0081] Set a retention rate threshold, compare the current retention rate of each water quality parameter and pollutant parameter with the set retention rate threshold, and when the retention rate of at least one parameter is greater than the retention rate threshold, it is determined that there is a membrane leakage fault in the RO membrane element of the water purification equipment, and a corresponding leakage alarm signal is generated. The generated leakage alarm signal is fed back to relevant personnel to prompt them to inspect and replace the RO membrane element in a timely manner.

[0082] It should be further explained that, in the specific implementation process, the process of obtaining the predicted blockage coefficient using the blockage assessment model, determining whether membrane blockage fault exists based on the predicted blockage coefficient, and flushing the membrane includes:

[0083] The current pressure difference, membrane flux, recovery rate, and membrane performance parameters of the water purification equipment are input into the clogging assessment model, which then outputs the corresponding predicted clogging coefficient S. y ;

[0084] Set the blocking coefficient range [S] min S max The obtained predicted blocking coefficient is compared with the blocking coefficient range. When S y ≤S min If it is determined that the RO membrane element of the water purification equipment does not have a membrane blockage fault, no other operation is performed on it;

[0085] When S min <S y <S max At that time, it was determined that the RO membrane element of the water purification equipment had a slight membrane blockage fault, and the flushing device was controlled to flush the RO membrane element with water. y ≥S max When it is determined that the RO membrane element of the water purification equipment has a serious membrane blockage fault, the flushing device is controlled to chemically flush the RO membrane element.

[0086] The cleaning includes water cleaning and chemical cleaning, and the membrane blockage faults include no membrane blockage faults, minor membrane blockage faults, and severe membrane blockage faults.

[0087] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A water purification equipment control and optimization system based on the Internet of Things, characterized in that, Includes the following modules: The data acquisition module is used to acquire the physical information of the water purification equipment and build a physical model, acquire the pre-purification and post-purification data of the water purification equipment, and build a simulation model to obtain membrane performance parameters. The data analysis module is used to obtain the membrane flux, recovery rate, and rejection rate at the same time based on the pre-purification and post-purification data of the water purification equipment. The data simulation module is used to adjust the pressure difference, membrane flux, and recovery rate at the same time in the simulation model, and obtain the corresponding blockage coefficient. The data evaluation module is used to construct a blockage evaluation model for water purification equipment based on pressure difference, membrane flux, recovery rate, and blockage coefficient at different times, combined with membrane performance parameters. The data optimization module is used to determine whether there is a membrane leakage fault based on the rejection rate and replace it. It uses a blockage assessment model to obtain a predicted blockage coefficient, and determines whether there is a membrane blockage fault based on the predicted blockage coefficient and flushes it. The process of adjusting the pressure difference, membrane flux, and recovery rate in the simulation model and obtaining the blockage coefficient includes: In the simulation model, each parameter in the pre-net data is adjusted to obtain simulated pre-net data, and the corresponding simulated post-net data is obtained. Based on the simulated pre-net data and simulated post-net data at the same time, the corresponding membrane flux and recovery rate are obtained. Based on the simulated net post-processing data and its membrane flux and recovery rate at the same time point, the blockage coefficient S of the RO membrane element at the corresponding time point is obtained. z ; ； P n J represents the pressure difference in the simulated net post-processing data at the corresponding time point. n R n P0, J0, and R0 represent the membrane flux and recovery rate at the corresponding time points, respectively, and are the preset initial pressure difference, initial membrane flux, and initial recovery rate. In the simulation model, the pressure difference, membrane flux, recovery rate and its blockage coefficient at different times were obtained respectively. The process of constructing a blockage assessment model for water purification equipment includes: Based on the pressure difference, membrane flux, recovery rate and the blockage coefficient at different times obtained in the simulation model, a blockage evaluation set is generated by combining the membrane performance parameters of the water purification equipment in the simulation model, and it is divided into training set and test set. A convolutional neural network is constructed, with the pressure drop, membrane flux, recovery rate and membrane performance parameters at different times in the training set as the input data of the convolutional neural network, and the blocking coefficient corresponding to the next time step in the training set as the output data of the convolutional neural network. The convolutional neural network is trained to obtain an initial convolutional neural network. The initial convolutional neural network is then validated using a test set. The initial convolutional neural network whose output is less than or equal to a preset test error threshold is used as the blockage evaluation model for the water purification equipment.

2. The IoT-based water purification equipment control and optimization system according to claim 1, characterized in that, The process of acquiring physical information about water purification equipment and constructing a physical model includes: The water purification equipment refers to the equipment that converts raw water into purified water that meets the requirements of a specific purpose, and the physical information refers to the physical structural dimensions of each component of the reverse osmosis system in the water purification equipment. The reverse osmosis system includes a high-pressure pump, RO membrane elements, membrane housing, online conductivity meter, and flushing device. A corresponding physical model is constructed using 3D modeling tools based on the acquired physical information.

3. The IoT-based water purification equipment control and optimization system according to claim 2, characterized in that, The process of acquiring pre-net and post-net data and building a simulation model to obtain membrane performance parameters includes: The pre-net data refers to the parameter values ​​corresponding to the water quality parameters, pollutant parameters, influent flow rate, temperature, and pressure of the raw water before it is treated by the RO membrane element in the reverse osmosis system. The working process of the reverse osmosis system is simulated using simulation software based on the physical model of the reverse osmosis system to obtain the corresponding simulation model. The obtained net pre-data is uploaded to the simulation model for synchronization, and the membrane characteristic parameters of the RO membrane element in the simulation model are adjusted. The membrane characteristic parameters include membrane permeability, solute permeability, and membrane surface roughness. Simulated post-purification data in the simulation model are obtained under different values ​​of membrane characteristic parameters. When the obtained simulated post-purification data is the same as the post-purification data at the corresponding time of the synchronized pre-purification data, the membrane characteristic parameter with the corresponding value in the simulation model at this time is used as the membrane performance parameter of the water purification equipment.

4. The IoT-based water purification equipment control and optimization system according to claim 3, characterized in that, The process of obtaining membrane flux, recovery rate, and rejection rate at the same time includes: Set an analysis cycle. When an analysis cycle is completed, obtain the corresponding membrane flux J based on the pre-net and post-net data at that time. w and recovery rate R e ; ； ； Q p The permeate flow rate in the purified data is A, where A is the effective area of ​​the RO membrane element, and Q is Q. f This refers to the influent flow rate in the pre-net data; The rejection rate refers to the changes in water quality parameters and pollutant parameters before and after the RO membrane element. The parameter values ​​of individual parameters in the pre-cleaning and post-cleaning data are denoted as C, respectively. f and C p Obtain the retention rate R of this single parameter at the corresponding time. j ; ； The retention rates of other parameters in the water quality parameters and pollutant parameters were obtained separately.

5. The IoT-based water purification equipment control and optimization system according to claim 4, characterized in that, The process of determining whether a membrane leakage fault exists based on the retention rate and replacing it includes: Set a retention rate threshold, compare the current retention rate of each water quality parameter and pollutant parameter with the set retention rate threshold, and when the retention rate of at least one parameter is greater than the retention rate threshold, it is determined that there is a membrane leakage fault in the RO membrane element of the water purification equipment, generate a leakage alarm signal and feed it back to the relevant personnel to prompt them to replace the RO membrane element.

6. The IoT-based water purification equipment control and optimization system according to claim 5, characterized in that, The process of obtaining the predicted blockage coefficient, determining the presence of membrane blockage faults, and flushing the membrane includes: Input the current pressure difference, membrane flux, recovery rate, and membrane performance parameters of the water purification equipment into the blockage assessment model to obtain the corresponding predicted blockage coefficient Sy, and set the blockage coefficient range [Smin, Smax]. The obtained predicted blockage coefficient is compared with the blockage coefficient range. When Sy≤Smin, it is determined that there is no membrane blockage fault in the RO membrane element of the water purification equipment, and no other operation is performed on it. When Smin < Sy < Smax, it is determined that the RO membrane element of the water purification equipment has a slight membrane blockage fault, and the flushing device is controlled to flush the RO membrane element with water. When Sy ≥ Smax, it is determined that the RO membrane element of the water purification equipment has a serious membrane blockage fault, and the flushing device is controlled to flush the RO membrane element with chemicals.

Images