An energy-saving optimization method and system for reverse osmosis chemical water production based on data analysis

Abstract

The present invention relates to the field of energy-saving optimization technologies, and specifically to an energy-saving optimization method and system for reverse osmosis chemical water production based on data analysis. By performing search processing on the target product water quality characteristic data collected and the performance characteristic data of different reverse osmosis membrane types, target reverse osmosis membrane type data is generated, and data matching is performed with the production characteristic data of different reverse osmosis membrane types to generate standard production characteristic data of the water production equipment. Then, a difference processing is carried out with the real-time production characteristic data of the water production equipment collected to generate real-time production deviation data of the water production equipment, and a numerical comparison is made with the set deviation threshold to generate real-time operation status analysis data of the water production equipment. If it is normal, the operation is ended; if it is abnormal, real-time abnormal production characteristic data of the water production equipment is generated, real-time operation status adjustment data of the water production equipment is constructed, and at the same time, a water production equipment production data adjustment operation is executed to achieve precise control of the water production equipment and energy-saving optimization of the reverse osmosis water production process.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving optimization, and particularly to a method and system for energy-saving optimization of reverse osmosis chemical water production based on data analysis. Background Art

[0002] Reverse osmosis technology is an important water production method widely used in industrial production and domestic water treatment. During the process of reverse osmosis chemical water production, a large amount of energy is consumed, and in the existing technology, the production data of the water production process is often not analyzed in real time, resulting in more unnecessary energy consumption.

[0003] The Chinese invention patent with the publication number CN111681126B introduces an intelligent control system and method based on the energy efficiency evaluation of a water treatment lift pump group. The first parameters of a water treatment plant are collected in real time by a data acquisition module and transmitted to a human-computer interaction module for dynamic display and stored in a data storage module; the first parameters in the data storage module are called and the preset second parameters are obtained from the human-computer interaction module; the second parameters are analyzed, with the highest pump group operation efficiency as the goal, the optimal operation conditions corresponding to the lift pump group are selected, and the selection result is stored in the data storage module and output to the human-computer interaction module for display at the same time; the pump group control module adjusts the lift pump group according to the selection result; realizing the intelligent control of the lift pump, while ensuring the energy-saving, optimization, and automatic operation of the lift pump group in the water treatment plant, improving the intelligent level of the water treatment plant, but only by retrieving the parameters matching the collected parameters from the preset parameters and performing data analysis, the accuracy of the analysis result cannot be guaranteed. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] To solve the deficiencies in the background art, the present invention provides a method and system for energy-saving optimization of reverse osmosis chemical water production based on data analysis, realizing the precise control of water production equipment and the energy-saving optimization of the reverse osmosis water production process.

[0006] (II) Technical Solutions

[0007] A method for energy-saving optimization of reverse osmosis chemical water production based on data analysis includes the following steps:

[0008] S1. Collect the water quality characteristic data of the target product water;

[0009] S2. Perform target reverse osmosis membrane type data search processing on the water quality characteristic data of the target product water and the performance characteristic data of different reverse osmosis membrane types, and generate target reverse osmosis membrane type data according to the matching result;

[0010] S3. Establish the production characteristic data of different reverse osmosis membrane types;

[0011] S4. Match the target reverse osmosis membrane type data with the production characteristic data of different reverse osmosis membrane types to generate the standard production characteristic data of the water treatment equipment.

[0012] S5. Collect the real-time production characteristic data of the water treatment equipment, and perform a difference operation on the standard production characteristic data and the real-time production characteristic data of the water treatment equipment to generate the real-time production deviation data of the water treatment equipment.

[0013] S6. Set a deviation threshold, compare the real-time production deviation data of the water treatment equipment with the deviation threshold, and generate the real-time operation state analysis data of the water treatment equipment according to the result of the numerical comparison. If the real-time operation state analysis data of the water treatment equipment is normal, end the current real-time operation state analysis task of the water treatment equipment.

[0014] S7. If the real-time operation state analysis data of the water treatment equipment is abnormal, generate the real-time abnormal production characteristic data of the water treatment equipment, construct the real-time operation state adjustment data based on the real-time abnormal production characteristic data and the standard production characteristic data of the water treatment equipment, and execute the production data adjustment task of the water treatment equipment.

[0015] Through the search process of the collected target product water quality characteristic data and the performance characteristic data of different reverse osmosis membrane types, the present invention generates the target reverse osmosis membrane type data, performs reverse osmosis membrane type matching on the established production characteristic data of different reverse osmosis membrane types to generate the standard production characteristic data of the water treatment equipment, collects the real-time production characteristic data of the water treatment equipment, performs a difference operation on the standard production characteristic data and the real-time production characteristic data of the water treatment equipment to generate the real-time production deviation data of the water treatment equipment, and compares it with the set deviation threshold. According to the result of the numerical comparison, the real-time operation state analysis data of the water treatment equipment is generated. If it is normal, end the current real-time operation state analysis task of the water treatment equipment; if it is abnormal, generate the real-time abnormal production characteristic data of the water treatment equipment, construct the real-time operation state adjustment data, and at the same time execute the production data adjustment task of the water treatment equipment, realizing the precise control of the water treatment equipment and the energy-saving optimization of the reverse osmosis water production process.

[0016] Preferably, the specific steps for collecting the target product water quality characteristic data are as follows:

[0017] S11. Online collect the product water quality characteristic data required for production by the current enterprise through the product water data management platform to generate the target product water quality characteristic data A. The product water quality characteristic data includes but is not limited to the product water conductivity, product water hardness, product water pH value, and product water suspended solid content.

[0018] Preferably, the specific steps of performing target reverse osmosis membrane type data search processing on the water quality characteristic data of the target product water and the performance characteristic data of different reverse osmosis membrane types, and generating target reverse osmosis membrane type data according to the matching result are as follows:

[0019] S21. Establish a performance characteristic data set B of different reverse osmosis membrane types = {b1, b2, …, b i , …, b k}, where b i represents the performance characteristic data of the i-th type of reverse osmosis membrane, k represents the total number of performance characteristic data of different reverse osmosis membrane types, the reverse osmosis membrane types include but are not limited to cellulose acetate membranes, polyamide membranes, polysulfone porous membranes, and composite membranes, and the performance characteristic data include but are not limited to water flux, antimicrobial performance, chemical stability, and desalination performance.

[0020] S22. Perform target reverse osmosis membrane type data search processing on the water quality characteristic data A of the target product water and the performance characteristic data of different reverse osmosis membrane types in the performance characteristic data set of different reverse osmosis membrane types through a water wave optimization algorithm, search for the performance characteristic data of different reverse osmosis membrane types that match successfully with the water quality characteristic data A of the target product water, and perform data identification on the reverse osmosis membrane type corresponding to the performance characteristic data of different reverse osmosis membrane types to generate target reverse osmosis membrane type data C;

[0021] S221. Construct a reverse osmosis membrane type search water wave population, set the scale of the reverse osmosis membrane type search water wave population as M, the current iteration number as t, the maximum iteration number as t max and the search space dimension of the performance characteristic data of different reverse osmosis membrane types as P;

[0022] Use the performance characteristic data set of different reverse osmosis membrane types as the search space of the performance characteristic data of different reverse osmosis membrane types, randomly generate M performance characteristic data of different reverse osmosis membrane types in the search space of the performance characteristic data of different reverse osmosis membrane types, each performance characteristic data of different reverse osmosis membrane types corresponds to an individual of the reverse osmosis membrane type search water wave, and initialize the initial position set of the reverse osmosis membrane type search water wave population as X = {X1, X2, …, X i , …, X M}, where X i represents the initial position of the i-th individual of the reverse osmosis membrane type search water wave;

[0023] S222. Calculate the fitness function values of each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population, arrange each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population in descending order according to the fitness function values, and select the reverse osmosis membrane type search water wave individual with the highest fitness function value as the current optimal individual; the fitness function formula is as follows:

[0024]

[0025] Among them, Fit i represents the fitness function value of the i-th reverse osmosis membrane type search water wave individual; x i represents the ability of the i-th reverse osmosis membrane type search water wave individual to process raw water corresponding to different reverse osmosis membrane type performance characteristic data so that the raw water reaches the target product water quality characteristic data; φ represents the correction value;

[0026] S223. Each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population performs a propagation operation in the search space of different reverse osmosis membrane type performance characteristic data for position update; the position update formula is as follows:

[0027]

[0028] Among them, and X ij respectively represent the position after and before the position update of the i-th reverse osmosis membrane type search water wave individual, rand1 represents a random number uniformly distributed between [-1, 1], λ i represents the wavelength of the i-th reverse osmosis membrane type search water wave individual, ub j and lb j respectively represent the upper and lower bounds of the j-th dimension search space of different reverse osmosis membrane type performance characteristic data;

[0029] S224. If the fitness function value of the reverse osmosis membrane type search water wave individual after position update is greater than the fitness function value of the current optimal individual, then use this reverse osmosis membrane type search water wave individual to replace the current optimal individual, and perform a breaking wave operation in the search space of different reverse osmosis membrane type performance characteristic data for position update; the position update formula is as follows:

[0030]

[0031] Among them, rand2 represents a Gaussian random number obeying (0, 1), and α represents the breaking wave coefficient;

[0032] If the fitness function value of the reverse osmosis membrane type search water wave individual after position update is less than or equal to the fitness function value of the current optimal individual, subtract 1 from the wave height h of the reverse osmosis membrane type search water wave individual;

[0033] S225. If the wave height h of the reverse osmosis membrane type search water wave individual is equal to 0, the reverse osmosis membrane type search water wave individual performs a refraction operation in the search space of different reverse osmosis membrane type performance characteristic data for position update; otherwise, directly proceed to S226; the position update formula is as follows:

[0034]

[0035] where, X best represents the position of the current optimal individual, and N(μ,σ) represents a Gaussian random number with a mean of μ and a variance of σ;

[0036] S226. Calculate the fitness function values of each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population after position update. If the fitness function value of a reverse osmosis membrane type search water wave individual after position update is less than the original fitness function value, replace the original position with the new position; otherwise, retain the original position;

[0037] Re - arrange each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population from largest to smallest according to the fitness function value, and select the reverse osmosis membrane type search water wave individual with the highest fitness function value as the new current optimal individual;

[0038] S227. Update the wavelength of each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population; the wavelength update formula is as follows:

[0039]

[0040] where, and λ i respectively represent the wavelength of the i - th reverse osmosis membrane type search water wave individual after and before update, Fit min and Fit max respectively represent the minimum and maximum fitness function values of each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population;

[0041] S228. Determine whether the current iteration number t is less than the maximum iteration number t max , if the current iteration number t is less than the maximum iteration number t max, the current iteration number t is incremented by 1, and S223 is returned; otherwise, the current optimal individual is used as the global optimal solution, and the performance characteristic data of different reverse osmosis membrane types corresponding to the global optimal solution are retained;

[0042] S229. Identify the reverse osmosis membrane types corresponding to the retained performance characteristic data of different reverse osmosis membrane types to generate the target reverse osmosis membrane type data C;

[0043] S23. If the type of the reverse osmosis membrane installed in the water production equipment matches the target reverse osmosis membrane type data C, directly proceed to S3; otherwise, perform a reverse osmosis membrane replacement operation on the reverse osmosis membrane installed in the water production equipment based on the target reverse osmosis membrane type data C, and proceed to S3 after the reverse osmosis membrane replacement operation is completed.

[0044] Perform a target reverse osmosis membrane type data search process on the target product water quality characteristic data and the performance characteristic data of different reverse osmosis membrane types through the water wave optimization algorithm, accurately retrieve the reverse osmosis membrane most suitable for producing the target product water from the database, ensure the effect and quality of the reverse osmosis membrane for filtering raw water, and at the same time, the water wave optimization algorithm can improve the speed and efficiency of the successful search process, and effectively reduce the response time for obtaining the search results.

[0045] Preferably, the specific steps for establishing the production characteristic data of different reverse osmosis membrane types are as follows:

[0046] S31. Preset corresponding production characteristic data for each performance characteristic data of different reverse osmosis membrane types in the performance characteristic data set of different reverse osmosis membrane types through the product water preparation data entry interface to obtain the production characteristic data set D of different reverse osmosis membrane types = {d1, d2,..., d i ,…, d k}, where d i represents the i-th production characteristic data of different reverse osmosis membrane types, and the production characteristic data includes raw water temperature, inlet and outlet flow rates, and inlet pressure.

[0047] Preferably, the specific steps for performing a reverse osmosis membrane type matching process on the target reverse osmosis membrane type data and the production characteristic data of different reverse osmosis membrane types to generate the standard production characteristic data of the water production equipment are as follows:

[0048] S41. Traverse all the production feature data of different reverse osmosis membrane types in the production feature dataset of different reverse osmosis membrane types through the iterative deepening search algorithm, search out the production feature data of different reverse osmosis membrane types that match the target reverse osmosis membrane type data and perform data identification, and generate the standard production feature dataset E=(e1, e2, e3) of the water production equipment, where e1, e2, and e3 respectively represent the standard raw water temperature, standard inlet and outlet flow rates, and standard inlet pressure when the water production equipment produces the target product water.

[0049] Through the iterative deepening search algorithm, perform reverse osmosis membrane type matching processing on the target reverse osmosis membrane type data and the production feature data of different reverse osmosis membrane types, quickly and accurately search out the production feature data of different reverse osmosis membrane types that match the target reverse osmosis membrane type data, and provide a data basis for the subsequent analysis of the real-time operation status of the water production equipment.

[0050] Preferably, collect the real-time production feature data of the water production equipment, and the specific steps for generating the real-time production deviation data of the water production equipment by performing a difference operation on the standard production feature data of the water production equipment and the real-time production feature data of the water production equipment are as follows:

[0051] S51. Collect the real-time production data during the operation of the current water production equipment through different sensors to obtain the real-time production feature dataset E'=(e'1, e'2, e'3) of the water production equipment, where e'1, e'2, and e'3 respectively represent the real-time raw water temperature, real-time inlet and outlet flow rates, and real-time inlet pressure during the operation of the current water production equipment, and the different sensors include temperature sensors, pressure sensors, and flow sensors;

[0052] S52. Use the difference formula to perform a numerical difference operation on each standard production feature data in the standard production feature dataset of the water production equipment and the real-time production feature data of the water production equipment corresponding to the digital subscripts in the real-time production feature dataset of the water production equipment to generate the real-time production deviation dataset of the water production equipment where and respectively represent the raw water temperature deviation value, inlet and outlet flow rate deviation value, and inlet pressure deviation value when the water production equipment produces the target product water.

[0053] Preferably, set a deviation threshold, compare the real-time production deviation data of the water production equipment with the deviation threshold, and generate the real-time operation status analysis data of the water production equipment according to the numerical comparison result. If the real-time operation status analysis data of the water production equipment is normal, the specific steps to end the current real-time operation status analysis operation of the water production equipment are as follows:

[0054] S61. Set the raw water temperature deviation threshold as η1, the inlet and outlet flow rate deviation threshold as η2, and the inlet pressure deviation threshold as η3.

[0055] If it indicates that the real-time raw water temperature when the water production equipment produces the target product water is in a normal state; otherwise, it indicates that the real-time raw water temperature when the water production equipment produces the target product water is in an abnormal state.

[0056] If it indicates that the real-time inlet and outlet flow rate when the water production equipment produces the target product water is in a normal state; otherwise, it indicates that the real-time inlet and outlet flow rate when the water production equipment produces the target product water is in an abnormal state.

[0057] If it indicates that the real-time inlet pressure when the water production equipment produces the target product water is in a normal state; otherwise, it indicates that the real-time inlet pressure when the water production equipment produces the target product water is in an abnormal state.

[0058] S62. If the real-time raw water temperature, the real-time inlet and outlet flow rate, and the real-time inlet pressure when the water production equipment produces the target product water are all in a normal state, then output the real-time operation status analysis data of the water production equipment as normal, push the real-time operation status analysis data of the water production equipment to the real-time supervision platform of the water production equipment through the Internet of Things communication network, and end the real-time operation status analysis operation of the water production equipment this time; otherwise, output the real-time operation status analysis data of the water production equipment as abnormal.

[0059] Perform a difference operation on the real-time production characteristic data of the water production equipment and the standard production characteristic data of the water production equipment through a difference formula to generate real-time production deviation data of the water production equipment, and compare the numerical values with the set deviation threshold to scientifically analyze the real-time operation status of the water production equipment. At the same time, during the numerical comparison process, the raw water temperature, the inlet and outlet flow rate, and the inlet pressure of the water production equipment are analyzed separately to realize the real-time monitoring of multiple production data of the water production equipment, ensure that the energy consumption during the operation of the water production equipment is kept within a reasonable range, and effectively avoid additional energy consumption during the production process.

[0060] Preferably, if the real-time operation status analysis data of the water production equipment is abnormal, then generate real-time abnormal production characteristic data of the water production equipment, construct real-time operation status adjustment data of the water production equipment based on the real-time abnormal production characteristic data of the water production equipment and the standard production characteristic data of the water production equipment, and the specific steps for performing the production data adjustment operation of the water production equipment are as follows:

[0061] S71. If the real-time operation status analysis data of the water production equipment is abnormal, then identify the real-time production deviation data of the water production equipment that is in an abnormal state in the real-time production deviation data set of the water production equipment to generate real-time abnormal production characteristic data F of the water production equipmentyichang ;

[0062] S72. Combine the real-time abnormal production characteristic data F of the water production equipment yichang with the standard production characteristic data set E of the water production equipment to generate the real-time operation status adjustment data Q of the water production equipment = (F yichang , E);

[0063] S73. Push the real-time operation status adjustment data Q = (F yichang , E) of the water production equipment to the water production equipment production data adjustment platform through the Internet of Things communication network, and execute the water production equipment production data adjustment operation.

[0064] The present invention also includes a reverse osmosis chemical water production energy-saving optimization system based on data analysis, including a target product water quality characteristic data acquisition module, a target reverse osmosis membrane type search module, a production characteristic data establishment module for different reverse osmosis membrane types, a standard production characteristic data matching module for water production equipment, a real-time production deviation data calculation module for water production equipment, a real-time operation status analysis module for water production equipment, and a real-time operation status adjustment data construction module for water production equipment;

[0065] The target product water quality characteristic data acquisition module online acquires the product water quality characteristic data required for current enterprise production through the product water data management platform to generate target product water quality characteristic data;

[0066] The target reverse osmosis membrane type search module performs target reverse osmosis membrane type data search processing on the target product water quality characteristic data and the performance characteristic data of different reverse osmosis membrane types through the water wave optimization algorithm, and generates target reverse osmosis membrane type data according to the search results;

[0067] The production characteristic data establishment module for different reverse osmosis membrane types presets corresponding production characteristic data for the performance characteristic data of different reverse osmosis membrane types through the product water preparation data entry interface to obtain production characteristic data for different reverse osmosis membrane types;

[0068] The standard production characteristic data matching module for water production equipment performs reverse osmosis membrane type matching processing on the target reverse osmosis membrane type data and the production characteristic data of different reverse osmosis membrane types through the iterative deepening search algorithm to generate standard production characteristic data for water production equipment;

[0069] The real-time production deviation data calculation module for water production equipment acquires the real-time production data during the working process of the current water production equipment through different sensors to obtain the real-time production characteristic data of the water production equipment, and performs a difference operation with the standard production characteristic data of the water production equipment to generate real-time production deviation data for the water production equipment;

[0070] The real-time operation status analysis module of the water production equipment compares the real-time production deviation data of the water production equipment with the deviation threshold by setting the deviation threshold, generates real-time operation status analysis data of the water production equipment according to the result of the numerical comparison. If the real-time operation status analysis data of the water production equipment is normal, the real-time operation status analysis operation of the water production equipment for this time is ended;

[0071] When the real-time operation status analysis data of the water production equipment is abnormal, the real-time operation status adjustment data construction module of the water production equipment identifies the real-time production deviation data of the water production equipment in the abnormal state, generates real-time abnormal production characteristic data of the water production equipment, combines the data with the standard production characteristic data set of the water production equipment, generates real-time operation status adjustment data of the water production equipment, and pushes it to the water production data adjustment platform of the water production equipment through the Internet of Things communication network, and at the same time executes the water production data adjustment operation of the water production equipment.

[0072] (III) Beneficial effects

[0073] 1. In the present invention, the water quality characteristic data of the target product water collected is searched and processed with the performance characteristic data of different reverse osmosis membrane types to generate target reverse osmosis membrane type data, and the target reverse osmosis membrane type data is matched with the established production characteristic data of different reverse osmosis membrane types to generate standard production characteristic data of the water production equipment. The real-time production characteristic data of the water production equipment is collected, the difference between the standard production characteristic data of the water production equipment and the real-time production characteristic data of the water production equipment is processed to generate real-time production deviation data of the water production equipment, and the real-time production deviation data is compared with the set deviation threshold. According to the result of the numerical comparison, real-time operation status analysis data of the water production equipment is generated. If it is normal, the real-time operation status analysis operation of the water production equipment for this time is ended; if it is abnormal, real-time abnormal production characteristic data of the water production equipment is generated, real-time operation status adjustment data of the water production equipment is constructed, and at the same time the water production data adjustment operation of the water production equipment is executed, realizing the precise control of the water production equipment and the energy-saving optimization of the reverse osmosis water production process.

[0074] 2. The water wave optimization algorithm is used to search and process the water quality characteristic data of the target product water and the performance characteristic data of different reverse osmosis membrane types to generate target reverse osmosis membrane type data, accurately retrieve the reverse osmosis membrane most suitable for producing the target product water from the database, ensure the effect and quality of filtering the raw water by the reverse osmosis membrane, and at the same time the water wave optimization algorithm can improve the speed and efficiency of the successful search and processing, and effectively reduce the response time for obtaining the search result;

[0075] 3. Through the iterative deepening search algorithm, the target reverse osmosis membrane type data is matched with the production characteristic data of different reverse osmosis membrane types, quickly and accurately searching out the production characteristic data of different reverse osmosis membrane types that match the target reverse osmosis membrane type data, providing a data basis for the subsequent analysis of the real-time operation status of the water production equipment;

[0076] 4. By using the difference formula to perform a difference operation on the real-time production characteristic data of the water production equipment and the standard production characteristic data of the water production equipment, generating the real-time production deviation data of the water production equipment, and comparing the numerical values with the set deviation threshold, scientifically analyzing the real-time operation status of the water production equipment. At the same time, during the numerical comparison process, the raw water temperature, inlet and outlet flow rates, and inlet pressure of the water production equipment are analyzed separately to achieve real-time monitoring of multiple production data of the water production equipment, ensuring that the energy consumption during the operation of the water production equipment is maintained within a reasonable range and effectively avoiding additional energy consumption during the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0078] Figure 1 It is a flowchart of a reverse osmosis chemical water production energy-saving optimization method based on data analysis provided by the present invention;

[0079] Figure 2 It is a schematic diagram of the modules of a reverse osmosis chemical water production energy-saving optimization system provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0080] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0081] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc. indicating the orientation or position relationship are only for the convenience of describing the invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the invention.

[0082] Example 1 is as follows:

[0083] Please refer to Figure 1 , an energy-saving optimization method for reverse osmosis chemical water production based on data analysis, including the following steps:

[0084] S1. Collect the water quality characteristic data of the target product water;

[0085] S11. Online collect the water quality characteristic data of the product water that the current enterprise needs to produce through the product water data management platform, and generate the target product water quality characteristic data A. The product water quality characteristic data includes but is not limited to the product water conductivity, product water hardness, product water pH value, and product water suspended solid content.

[0086] S2. Perform target reverse osmosis membrane type data search processing on the target product water quality characteristic data and the performance characteristic data of different reverse osmosis membrane types, and generate target reverse osmosis membrane type data according to the matching result;

[0087] S21. Establish a performance characteristic data set B of different reverse osmosis membrane types = {b1, b2,..., b i ,…, b k}, where b i represents the performance characteristic data of the i-th type of reverse osmosis membrane, k represents the total number of performance characteristic data of different reverse osmosis membrane types, the reverse osmosis membrane types include but are not limited to cellulose acetate membrane, polyamide membrane, polysulfone porous membrane, and composite membrane, and the performance characteristic data includes but is not limited to water flux, anti-microbial performance, chemical stability, and desalination performance.

[0088] S22. Perform target reverse osmosis membrane type data search processing on the target product water quality characteristic data A and the performance characteristic data of different reverse osmosis membrane types in the performance characteristic data set of different reverse osmosis membrane types through the water wave optimization algorithm, search out the performance characteristic data of different reverse osmosis membrane types that match successfully with the target product water quality characteristic data A, and perform data identification on the reverse osmosis membrane type corresponding to the performance characteristic data of different reverse osmosis membrane types to generate target reverse osmosis membrane type data C;

[0089] S221. Construct a reverse osmosis membrane type search water wave population, set the reverse osmosis membrane type search water wave population size to M, the current iteration number to t, the maximum iteration number to t max and the performance characteristic data search space dimension of different reverse osmosis membrane types to P;

[0090] Taking the performance characteristic data sets of the different reverse osmosis membrane types as the performance characteristic data search spaces of the different reverse osmosis membrane types, randomly generate M performance characteristic data of different reverse osmosis membrane types in the performance characteristic data search spaces of the different reverse osmosis membrane types. Each performance characteristic data of a different reverse osmosis membrane type corresponds to an individual of the reverse osmosis membrane type search water wave. Initialize the initial position set of the reverse osmosis membrane type search water wave population as X = {X1, X2, …, X i , …, X M}, where X i represents the initial position of the i-th individual of the reverse osmosis membrane type search water wave;

[0091] S222. Calculate the fitness function values of each individual of the reverse osmosis membrane type search water wave population in the reverse osmosis membrane type search water wave population. Arrange each individual of the reverse osmosis membrane type search water wave population in the reverse osmosis membrane type search water wave population from largest to smallest according to the fitness function value, and select the individual of the reverse osmosis membrane type search water wave with the highest fitness function value as the current optimal individual. The fitness function formula is as follows:

[0092]

[0093] where Fit i represents the fitness function value of the i-th individual of the reverse osmosis membrane type search water wave; x i represents the ability of the performance characteristic data of the different reverse osmosis membrane types corresponding to the i-th individual of the reverse osmosis membrane type search water wave to process raw water so that the raw water reaches the target product water quality characteristic data; φ represents the correction value;

[0094] S223. Each individual of the reverse osmosis membrane type search water wave population in the reverse osmosis membrane type search water wave population performs a propagation operation in the performance characteristic data search spaces of the different reverse osmosis membrane types to update the position. The position update formula is as follows:

[0095]

[0096] where, and X ij represent the position after and before the position update of the i-th individual of the reverse osmosis membrane type search water wave respectively. rand1 represents a random number uniformly distributed between [-1, 1], and λ i represents the wavelength of the i-th individual of the reverse osmosis membrane type search water wave. ub j and lb j represent the upper and lower bounds of the j-th dimension of the performance characteristic data search space of the different reverse osmosis membrane types respectively;

[0097] S224. If the fitness function value of the water wave individual searched for the reverse osmosis membrane type after position update is greater than the fitness function value of the current optimal individual, then replace the current optimal individual with the water wave individual searched for the reverse osmosis membrane type, and perform a breaking wave operation in the search space of the performance characteristic data of different reverse osmosis membrane types for position update; the position update formula is as follows:

[0098]

[0099] where rand2 represents a Gaussian random number obeying (0,1), and α represents a breaking wave coefficient;

[0100] If the fitness function value of the water wave individual searched for the reverse osmosis membrane type after position update is less than or equal to the fitness function value of the current optimal individual, then perform a subtraction operation of 1 on the wave height h of the water wave individual searched for the reverse osmosis membrane type;

[0101] S225. When the wave height h of the water wave individual searched for the reverse osmosis membrane type is equal to 0, then the water wave individual searched for the reverse osmosis membrane type performs a refraction operation in the search space of the performance characteristic data of different reverse osmosis membrane types for position update, otherwise, directly enter S226; the position update formula is as follows:

[0102]

[0103] where X best represents the position of the current optimal individual, and N(μ,σ) represents a Gaussian random number with a mean of μ and a variance of σ;

[0104] S226. Calculate the fitness function values of each water wave individual searched for the reverse osmosis membrane type in the water wave population of the reverse osmosis membrane type after position update. If the fitness function value of the water wave individual searched for the reverse osmosis membrane type after position update is less than the original fitness function value, then replace the original position with the new position; otherwise, retain the original position;

[0105] Re-arrange each water wave individual searched for the reverse osmosis membrane type in the water wave population of the reverse osmosis membrane type from largest to smallest according to the fitness function value, and select the water wave individual searched for the reverse osmosis membrane type with the highest fitness function value as the new current optimal individual;

[0106] S227. Update the wavelength of each water wave individual searched for the reverse osmosis membrane type in the water wave population of the reverse osmosis membrane type; the wavelength update formula is as follows:

[0107]

[0108] where, and λ irespectively represent the wavelength after and before the update of the i-th reverse osmosis membrane type search water wave individual, Fit min and Fit max respectively represent the minimum value and the maximum value of the fitness function of each reverse osmosis membrane type search water wave individual in the reverse osmosis membrane type search water wave population;

[0109] S228. Determine whether the current iteration number t is less than the maximum iteration number t max , if the current iteration number t is less than the maximum iteration number t max , then the current iteration number t is incremented by 1, and return to S223; otherwise, take the current optimal individual as the global optimal solution, and retain the performance characteristic data of different reverse osmosis membrane types corresponding to the global optimal solution;

[0110] S229. Identify the reverse osmosis membrane types corresponding to the retained performance characteristic data of different reverse osmosis membrane types, and generate the target reverse osmosis membrane type data C;

[0111] S23. If the type of the reverse osmosis membrane installed in the water production equipment matches the target reverse osmosis membrane type data C, directly enter S3; otherwise, perform a reverse osmosis membrane replacement operation on the reverse osmosis membrane installed in the water production equipment based on the target reverse osmosis membrane type data C, and enter S3 after the reverse osmosis membrane replacement operation is completed.

[0112] S3. Establish production characteristic data of different reverse osmosis membrane types;

[0113] S31. Preset corresponding production characteristic data for each performance characteristic data of different reverse osmosis membrane types in the performance characteristic data set of different reverse osmosis membrane types through the product water preparation data entry interface, and obtain the production characteristic data set D of different reverse osmosis membrane types = {d1, d2,..., d i ,…, d k}, where d i represents the i-th production characteristic data of different reverse osmosis membrane types, and the production characteristic data includes raw water temperature, inlet and outlet flow rates, and inlet pressure.

[0114] S4. Perform reverse osmosis membrane type matching processing on the target reverse osmosis membrane type data and the production characteristic data of different reverse osmosis membrane types to generate the standard production characteristic data of the water production equipment;

[0115] S41. Traverse all the production feature data of different reverse osmosis membrane types in the production feature dataset of different reverse osmosis membrane types through the iterative deepening search algorithm, search for the production feature data of different reverse osmosis membrane types that match the target reverse osmosis membrane type data and perform data identification to generate the standard production feature dataset E=(e1, e2, e3) of the water production equipment, where e1, e2, and e3 respectively represent the standard raw water temperature, standard inlet and outlet flow rate, and standard inlet pressure when the water production equipment produces the target product water.

[0116] S5. Collect the real-time production feature data of the water production equipment, perform a difference operation on the standard production feature data of the water production equipment and the real-time production feature data of the water production equipment to generate the real-time production deviation data of the water production equipment.

[0117] S51. Collect the real-time production data during the operation of the current water production equipment through different sensors to obtain the real-time production feature dataset E'=(e'1, e'2, e'3) of the water production equipment, where e'1, e'2, and e'3 respectively represent the real-time raw water temperature, real-time inlet and outlet flow rate, and real-time inlet pressure during the operation of the current water production equipment. The different sensors include temperature sensors, pressure sensors, and flow sensors.

[0118] S52. Use the difference formula to perform a numerical difference operation on each standard production feature data in the standard production feature dataset of the water production equipment and the real-time production feature data of the water production equipment corresponding to the digital subscripts in the real-time production feature dataset of the water production equipment to generate the real-time production deviation dataset of the water production equipment. where and respectively represent the raw water temperature deviation value, inlet and outlet flow rate deviation value, and inlet pressure deviation value when the water production equipment produces the target product water.

[0119] S6. Set a deviation threshold, compare the real-time production deviation data of the water production equipment with the deviation threshold, and generate the real-time operation state analysis data of the water production equipment according to the numerical comparison result. If the real-time operation state analysis data of the water production equipment is normal, end the current real-time operation state analysis operation of the water production equipment.

[0120] S61. Set the raw water temperature deviation threshold as η1, the inlet and outlet flow rate deviation threshold as η2, and the inlet pressure deviation threshold as η3.

[0121] If it means that the real-time raw water temperature when the water production equipment produces the target product water is in a normal state; otherwise, it means that the real-time raw water temperature when the water production equipment produces the target product water is in an abnormal state.

[0122] If It indicates that the real-time inlet and outlet flow rates of the water production equipment during the production of the target product water are in a normal state; otherwise, it indicates that the real-time inlet and outlet flow rates of the water production equipment during the production of the target product water are in an abnormal state;

[0123] If It indicates that the real-time inlet pressure of the water production equipment during the production of the target product water is in a normal state; otherwise, it indicates that the real-time inlet pressure of the water production equipment during the production of the target product water is in an abnormal state;

[0124] S62. If the real-time raw water temperature, real-time inlet and outlet flow rates, and real-time inlet pressure of the water production equipment during the production of the target product water are all in a normal state, then output the real-time operation status analysis data of the water production equipment as normal, push the real-time operation status analysis data of the water production equipment to the real-time supervision platform of the water production equipment through the Internet of Things communication network, and end the current real-time operation status analysis operation of the water production equipment; otherwise, output the real-time operation status analysis data of the water production equipment as abnormal.

[0125] S7. If the real-time operation status analysis data of the water production equipment is abnormal, then generate real-time abnormal production characteristic data of the water production equipment, construct real-time operation status adjustment data of the water production equipment based on the real-time abnormal production characteristic data of the water production equipment and the standard production characteristic data of the water production equipment, and perform the water production data adjustment operation of the water production equipment;

[0126] S71. If the real-time operation status analysis data of the water production equipment is abnormal, then identify the real-time production deviation data of the water production equipment in the abnormal state in the real-time production deviation data set of the water production equipment, and generate real-time abnormal production characteristic data F of the water production equipment yichang ;

[0127] S72. Combine the real-time abnormal production characteristic data F of the water production equipment yichang and the standard production characteristic data set E of the water production equipment to generate real-time operation status adjustment data Q=(F yichang , E);

[0128] S73. Push the real-time operation status adjustment data Q=(F yichang , E) of the water production equipment to the water production data adjustment platform through the Internet of Things communication network, and perform the water production data adjustment operation of the water production equipment.

[0129] The second embodiment is as follows:

[0130] Please refer to Figure 2, a reverse osmosis chemical water production energy-saving optimization system based on data analysis, including a target product water quality characteristic data acquisition module, a target reverse osmosis membrane type search module, a production characteristic data establishment module for different reverse osmosis membrane types, a standard production characteristic data matching module for water production equipment, a real-time production deviation data calculation module for water production equipment, a real-time operation status analysis module for water production equipment, and a real-time operation status adjustment data construction module for water production equipment;

[0131] The target product water quality characteristic data acquisition module online acquires the water quality characteristic data of the product water that the current enterprise needs to produce through the product water data management platform, and generates the target product water quality characteristic data;

[0132] The target reverse osmosis membrane type search module performs target reverse osmosis membrane type data search processing on the target product water quality characteristic data and the performance characteristic data of different reverse osmosis membrane types through the water wave optimization algorithm, and generates the target reverse osmosis membrane type data according to the search results;

[0133] The production characteristic data establishment module for different reverse osmosis membrane types presets corresponding production characteristic data for the performance characteristic data of different reverse osmosis membrane types through the product water preparation data entry interface, and obtains the production characteristic data of different reverse osmosis membrane types;

[0134] The standard production characteristic data matching module for water production equipment performs reverse osmosis membrane type matching processing on the target reverse osmosis membrane type data and the production characteristic data of different reverse osmosis membrane types through the iterative deepening search algorithm, and generates the standard production characteristic data of water production equipment;

[0135] The real-time production deviation data calculation module for water production equipment acquires the real-time production data during the working process of the current water production equipment through different sensors, obtains the real-time production characteristic data of the water production equipment, and performs a subtraction operation with the standard production characteristic data of the water production equipment to generate the real-time production deviation data of the water production equipment;

[0136] The real-time operation status analysis module for water production equipment sets a deviation threshold, compares the real-time production deviation data of the water production equipment with the deviation threshold numerically, generates real-time operation status analysis data of the water production equipment according to the numerical comparison result. If the real-time operation status analysis data of the water production equipment is normal, the current real-time operation status analysis operation of the water production equipment is ended;

[0137] When the real-time operation status analysis data of the water production equipment is abnormal, the real-time operation status adjustment data construction module of the water production equipment identifies the real-time production deviation data of the water production equipment in the abnormal state, generates the real-time abnormal production feature data of the water production equipment, combines it with the standard production feature data set of the water production equipment to generate the real-time operation status adjustment data of the water production equipment, and pushes it to the water production data adjustment platform of the water production equipment through the Internet of Things communication network, and at the same time executes the water production data adjustment operation of the water production equipment.

[0138] In the description of this specification, the description with reference to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0139] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and utilize the invention well.

Claims

1. An energy-saving optimization method for reverse osmosis chemical water production based on data analysis, characterized in that, It includes the following steps: S1. Collect the water quality characteristic data of the target product water; S2. Conduct target reverse osmosis membrane type data search processing on the water quality characteristic data of the target product water and the performance characteristic data of different reverse osmosis membrane types, and generate target reverse osmosis membrane type data according to the matching result; S3. Establish the production characteristic data of different reverse osmosis membrane types; S4. Conduct reverse osmosis membrane type matching processing on the target reverse osmosis membrane type data and the production characteristic data of different reverse osmosis membrane types, and generate the standard production characteristic data of the water production equipment; S5. Collect the real-time production characteristic data of the water production equipment, perform a difference operation on the standard production characteristic data of the water production equipment and the real-time production characteristic data of the water production equipment, and generate the real-time production deviation data of the water production equipment; S6. Set a deviation threshold, compare the real-time production deviation data of the water production equipment with the deviation threshold, generate the real-time operation state analysis data of the water production equipment according to the numerical comparison result. If the real-time operation state analysis data of the water production equipment is normal, end the real-time operation state analysis operation of the water production equipment this time; S7. If the real-time operation state analysis data of the water production equipment is abnormal, generate the real-time abnormal production characteristic data of the water production equipment, construct the real-time operation state adjustment data of the water production equipment based on the real-time abnormal production characteristic data of the water production equipment and the standard production characteristic data of the water production equipment, and execute the production data adjustment operation of the water production equipment.

2. The energy-saving optimization method for reverse osmosis chemical water production based on data analysis according to claim 1, characterized in that, The S1 includes the following steps: S11. Online collect the water quality characteristic data of the product water that the current enterprise needs to produce through the product water data management platform, and generate the target product water quality characteristic data A.

3. The energy-saving optimization method for reverse osmosis chemical water production based on data analysis according to claim 2, wherein The S2 includes the following steps: S21. Establish a performance characteristic data set B = {b1, b2, …, b i , …, b k} for different types of reverse osmosis membranes; S22. Conduct target reverse osmosis membrane type data search processing on the target product water quality characteristic data A and the performance characteristic data of different reverse osmosis membrane types in the different reverse osmosis membrane type performance characteristic data set, search out the performance characteristic data of different reverse osmosis membrane types that match successfully with the target product water quality characteristic data A, and mark the reverse osmosis membrane type corresponding to the performance characteristic data of different reverse osmosis membrane types, and generate the target reverse osmosis membrane type data C; S23. If the type of the reverse osmosis membrane installed in the water production equipment matches the target reverse osmosis membrane type data C, directly enter S3; otherwise, perform a reverse osmosis membrane replacement operation on the reverse osmosis membrane installed in the water production equipment based on the target reverse osmosis membrane type data C, and enter S3 after the reverse osmosis membrane replacement operation is completed.

4. A reverse osmosis chemical water production energy-saving optimization method based on data analysis according to claim 3, characterized in that, The S22 includes the following steps: S221. Construct a search water wave population for reverse osmosis membrane types, set the scale of the search water wave population for reverse osmosis membrane types as M, the current iteration number as t, and the maximum iteration number as t max and the search space dimension of performance characteristic data for different reverse osmosis membrane types is P; Take the different reverse osmosis membrane type performance characteristic data set as the search space of the performance characteristic data of different reverse osmosis membrane types, randomly generate M performance characteristic data of different reverse osmosis membrane types in the search space of the performance characteristic data of different reverse osmosis membrane types, and each performance characteristic data of different reverse osmosis membrane types corresponds to a reverse osmosis membrane type search water wave individual; S222. Calculate the fitness function value of each reverse osmosis membrane type search water wave individual, and take the reverse osmosis membrane type search water wave individual with the highest fitness function value as the current optimal individual; S223. Each reverse osmosis membrane type searches for water wave individuals to perform propagation operations for position update; S224. If the fitness function value of a reverse osmosis membrane type search water wave individual after position update is greater than the fitness function value of the current optimal individual, replace the current optimal individual with this reverse osmosis membrane type search water wave individual and perform a breaking wave operation for position update; otherwise, perform a subtraction operation of 1 on the wave height h of this reverse osmosis membrane type search water wave individual; S225. If the wave height h of a reverse osmosis membrane type search water wave individual equals 0, this reverse osmosis membrane type search water wave individual performs a refraction operation for position update; otherwise, directly proceed to S226; S226. Calculate the fitness function values of each reverse osmosis membrane type search water wave individual after position update. If the fitness function value of a reverse osmosis membrane type search water wave individual after position update is less than the original fitness function value, replace the original position with the new position; otherwise, retain the original position; Simultaneously select the reverse osmosis membrane type search water wave individual with the highest fitness function value as the new current optimal individual; S227. Update the wavelength of each reverse osmosis membrane type search water wave individual; S228. Determine whether t is less than t max , if t is less than t max , then increment t by 1 and return to S223; otherwise, take the current optimal individual as the global optimal solution and retain the performance characteristic data of different reverse osmosis membrane types corresponding to the global optimal solution. S229. Identify the reverse osmosis membrane types corresponding to the retained performance characteristic data of different reverse osmosis membrane types to generate the target reverse osmosis membrane type data C.

5. The energy-saving optimization method for reverse osmosis chemical water production based on data analysis according to claim 4, characterized in that, The S3 includes the following steps: S31. Preset corresponding production characteristic data for each different reverse osmosis membrane type performance characteristic data in the different reverse osmosis membrane type performance characteristic data set through the product water preparation data entry interface to obtain a different reverse osmosis membrane type production characteristic data set.

6. A method for optimizing the energy saving of reverse osmosis chemical water production based on data analysis according to claim 5, characterized in that, The S4 includes the following steps: S41. Traverse all different reverse osmosis membrane type production characteristic data in the different reverse osmosis membrane type production characteristic data set through the iterative deepening search algorithm, search for the different reverse osmosis membrane type production characteristic data that matches the target reverse osmosis membrane type data and perform data identification to generate a water production equipment standard production characteristic data set E=(e1, e2, e3), where e1, e2, and e3 respectively represent the standard raw water temperature, standard inlet and outlet flow rate, and standard inlet pressure when the water production equipment produces the target product water.

7. A method for optimizing energy conservation in reverse osmosis chemical water production based on data analysis according to claim 6, characterized in that, The S5 includes the following steps: S51. Collect real-time production data during the operation of the current water production equipment through different sensors to obtain a water production equipment real-time production characteristic data set E'=(e'1, e'2, e'3), where e'1, e'2, and e'3 respectively represent the real-time raw water temperature, real-time inlet and outlet flow rate, and real-time inlet pressure during the operation of the current water production equipment. The different sensors include a temperature sensor, a pressure sensor, and a flow sensor; S52. Use the difference formula to perform a numerical subtraction operation on each standard production characteristic data of the water production equipment in the standard production characteristic data set of the water production equipment and the real-time production characteristic data of the water production equipment with the corresponding digital subscript in the real-time production characteristic data set of the water production equipment, and generate a real-time production deviation data set of the water production equipment Among them, and respectively represent the raw water temperature deviation value, the inlet and outlet flow deviation value, and the inlet pressure deviation value when the water production equipment produces the target product water 8. A reverse osmosis chemical water production energy-saving optimization method based on data analysis according to claim 7, characterized in that, The S6 includes the following steps: S61. Set the raw water temperature deviation threshold as η1, the inlet and outlet flow rate deviation threshold as η2, and the inlet pressure deviation threshold η3; If it indicates that the real-time raw water temperature when the water production equipment produces the target product water is in a normal state; otherwise, it indicates that the real-time raw water temperature when the water production equipment produces the target product water is in an abnormal state; If it indicates that the real-time inlet and outlet flow rates of the water production equipment during the production of the target product water are in a normal state; otherwise, it indicates that the real-time inlet and outlet flow rates of the water production equipment during the production of the target product water are in an abnormal state; If it indicates that the real-time inlet pressure when the water production equipment produces the target product water is in a normal state; otherwise, it indicates that the real-time inlet pressure when the water production equipment produces the target product water is in an abnormal state; S62. If the real-time raw water temperature, real-time inlet and outlet flow rates, and real-time inlet pressure of the water production equipment are all in normal states when producing the target product water, then output the analysis data of the real-time operating state of the water production equipment as normal, push the analysis data of the real-time operating state of the water production equipment to the real-time supervision platform of the water production equipment through the Internet of Things communication network, and end the current analysis operation of the real-time operating state of the water production equipment; otherwise, output the analysis data of the real-time operating state of the water production equipment as abnormal.

9. An energy-saving optimization method for reverse osmosis chemical water production based on data analysis according to claim 8, characterized in that The said S7 includes the following steps: S71. If the real-time operation status analysis data of the water production equipment is abnormal, then the real-time production deviation data of the water production equipment in the abnormal state in is data-identified to generate the real-time abnormal production feature data F of the water production equipment yichang ; S72. Combine the said F yichang with the said E to generate the real-time operation status adjustment data Q=(F yichang , E) of the water production equipment; S73. Push the Q=(F yichang , E) to the production data adjustment platform of the water production equipment through the Internet of Things communication network, and perform the production data adjustment operation of the water production equipment.

10. A system for implementing the reverse osmosis chemical water production energy-saving optimization method based on data analysis as described in any one of claims 1-9.

Images