High-salt complex wastewater reduction treatment method and system based on big data

Abstract

The invention provides a high-salt complex wastewater reduction treatment method and system based on big data. The method comprises the steps that impurities in wastewater are removed through a pretreatment system; a big data acquisition module is used for acquiring inlet water quality indexes, operation parameters of an electric drive membrane and an MVR concentration unit and environmental fluctuation parameters in real time, and real-time input data is obtained; inputting the real-time input data into a pre-trained water quality concentration coupling model in real time, and predicting an optimal deep concentration end point; according to the prediction result of the water quality concentration coupling model, dynamically adjusting the operation pressure, temperature and / or circulation ratio of the electrically driven membrane and the MVR concentration unit to realize deep concentration. The device realizes zero discharge of high-salinity wastewater, adapts to water quality change, improves the treatment efficiency and reduces the operation cost.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and system for reducing the volume of complex high-salt wastewater based on big data. Background Technology

[0002] With rapid industrial development, water pollution caused by the discharge of high-salinity wastewater, characterized by high salt content and complex composition, has become a serious problem. High-salinity wastewater refers to wastewater with a total dissolved solids (TDS) mass fraction of 3.5% or higher. It mainly originates from industrial wastewater generated in the chemical, pharmaceutical, and dyeing industries. This high-salinity wastewater contains a large amount of organic and inorganic salts, such as Ca2+, Mg2+, Cl-, and Na+ ions. Direct discharge into receiving water bodies will result in high salinity, damage to the soil, and negatively impact the normal growth and reproduction of aquatic organisms and plants. Furthermore, the high salt concentration will significantly inhibit the growth of microorganisms in subsequent biological treatment processes at wastewater treatment plants. Therefore, developing economical and efficient desalination technologies for high-salinity wastewater is a bottleneck problem encountered in my country's efforts to achieve resource recycling of high-salinity wastewater.

[0003] High-salinity, complex wastewater is one of the most difficult types of wastewater to treat in the industrial sector, characterized by high salinity, complex composition, and large fluctuations in water quality. Currently, the mainstream processes in the industry include evaporation crystallization salt method, SBR process, and microbial method. However, none of these existing technologies can accurately control the final treatment of high-salinity wastewater to achieve zero discharge. They are also difficult to adapt to changes in water quality, resulting in low treatment efficiency and high operating costs.

[0004] Therefore, the urgent technical problem to be solved is: how to provide a method and system for reducing the volume of high-salt complex wastewater based on big data, so as to achieve zero discharge of high-salt wastewater, adapt to changes in water quality, improve treatment efficiency, and reduce operating costs. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for reducing the volume of high-salt complex wastewater based on big data, so as to achieve zero discharge of high-salt wastewater, adapt to changes in water quality, improve treatment efficiency, and reduce operating costs.

[0006] To achieve the above objectives, as a first aspect of this application, this application provides a method for reducing the volume of high-salt complex wastewater based on big data. The method includes: removing impurities from the wastewater through a pretreatment system; using a big data acquisition module to collect in-water quality indicators, operating parameters of the electrically driven membrane and MVR thickening unit, and environmental fluctuation parameters in real time to obtain real-time input data; inputting the real-time input data into a pre-trained water quality thickening coupling model to predict the optimal deep thickening endpoint; and dynamically adjusting the operating pressure, temperature, and / or circulation rate of the electrically driven membrane and MVR thickening unit based on the prediction results of the water quality thickening coupling model to achieve deep thickening.

[0007] The above-mentioned method for reducing the volume of high-salt complex wastewater based on big data further includes: sending the highly concentrated brine to a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate; and sending the sodium sulfate-rich concentrate and sodium chloride-rich concentrate to an evaporation crystallization unit to produce sodium sulfate and sodium chloride, respectively.

[0008] The above-mentioned method for reducing the volume of high-salt complex wastewater based on big data further includes: establishing a big data closed-loop feedback mechanism to continuously learn and optimize the parameters of the water quality concentration coupling model with preset conditions as the target.

[0009] The above-described method for reducing the volume of high-salt complex wastewater based on big data includes the following steps: inputting real-time input data into a pre-trained water quality concentration coupling model to predict the optimal concentration endpoint. These steps include: inputting real-time input data into the pre-trained water quality concentration coupling model to obtain the model output data; establishing the objective function and constraints; and solving for the optimal concentration endpoint based on the objective function, constraints, and model output data.

[0010] The above-mentioned method for reducing the volume of high-salt complex wastewater based on big data involves transforming the optimal deep concentration endpoint into the operating volume, and optimizing the parameters of the electrically driven membrane and MVR evaporator based on the operating volume.

[0011] The above-described method for reducing the volume of complex high-salt wastewater based on big data includes the following steps: feeding the highly concentrated brine into a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate. This process involves: feeding the highly concentrated brine into the cryogenic nanofiltration coupled salt separation system; adjusting the freezing temperature of the cryogenic nanofiltration coupled salt separation system through supersaturation control; and the cryogenic nanofiltration coupled salt separation system producing two liquid streams: sodium sulfate-rich concentrate and sodium chloride-rich concentrate.

[0012] The above-described method for reducing the volume of high-salt complex wastewater based on big data includes the following steps: feeding concentrated sodium sulfate solution and concentrated sodium chloride solution into an evaporation and crystallization unit to produce sodium sulfate and sodium chloride, respectively. This includes feeding concentrated sodium sulfate solution into a sodium sulfate evaporator to produce sodium sulfate; and feeding concentrated sodium chloride solution into a sodium chloride evaporator to produce sodium chloride.

[0013] As a second aspect of this application, a high-salt complex wastewater reduction treatment system based on big data is provided. This system executes the aforementioned high-salt complex wastewater reduction treatment method based on big data. The system includes: a pretreatment system for removing impurities from the wastewater; a big data acquisition module for real-time acquisition of influent water quality indicators, operating parameters of the electrically driven membrane and MVR thickening unit, and environmental fluctuation parameters to obtain real-time input data; a prediction module for inputting the real-time input data into a pre-trained water quality thickening coupling model to predict the optimal deep thickening endpoint; and a dynamic adjustment module for dynamically adjusting the operating pressure, temperature, and / or circulation rate of the electrically driven membrane and MVR thickening unit based on the prediction results of the water quality thickening coupling model to achieve deep thickening.

[0014] The high-salt complex wastewater reduction treatment system based on big data, as described above, further includes: an acquisition module for sending the deeply concentrated high-concentration brine into a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate; and an output module for sending the sodium sulfate-rich concentrate and sodium chloride-rich concentrate into an evaporation crystallization unit to produce sodium sulfate and sodium chloride, respectively.

[0015] The high-salt complex wastewater reduction treatment system based on big data, as described above, further includes an optimization module for establishing a big data closed-loop feedback mechanism to continuously learn and optimize the parameters of the water concentration coupling model under preset conditions.

[0016] The beneficial effects achieved by this application are as follows: (1) This application achieves near-zero discharge of high-salt wastewater through a fully enclosed chain of pretreatment, electro-driven membrane, MVR deep concentration, cryogenic nanofiltration for salt separation, and evaporation crystallization.

[0017] (2) This application adjusts the current, temperature and circulation rate in real time to adapt to water quality fluctuations and improve operational stability.

[0018] (3) This application improves the cold nanofiltration coupled salt separation process Separation coefficient, reducing the rate of mixed salts.

[0019] (4) This application sets a device health penalty term in the objective function to limit the current density and compressor speed in real time, thereby extending the device life and improving the reliability of device operation. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0021] Figure 1 This is a flowchart illustrating a method for reducing the volume of complex high-salt wastewater based on big data, as described in an embodiment of this application.

[0022] Figure 2 This is a schematic diagram of a high-salt complex wastewater reduction treatment system based on big data, according to an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0024] like Figure 1 As shown, this application provides a method for reducing the volume of high-salt, complex wastewater based on big data. The method includes: Step S1: Remove impurities from wastewater using a pretreatment system.

[0025] Specifically, the pretreatment system removes impurities such as organic matter and suspended solids from the wastewater.

[0026] Step S2: Use the big data acquisition module to collect influent water quality indicators, operating parameters of the electro-driven membrane and MVR concentration unit, and environmental fluctuation parameters in real time to obtain real-time input data.

[0027] Among them, the following water quality indicators were collected at the outlet of the raw water booster pump: chemical oxygen demand (COD), ammonia nitrogen, total phosphorus, total nitrogen, alkalinity, hardness, pH value, suspended solids, temperature, and supersaturation index. , , wait.

[0028] The function of the electro-driven membrane is to allow only charged ions to pass through the membrane under a direct current electric field, while almost preventing water molecules from passing through, thereby separating the raw water into low-salt fresh water and highly concentrated brine.

[0029] The MVR concentration unit is used to further evaporate and concentrate "already salty water" into an ultra-high concentration liquid that is "close to saturation and about to precipitate salt," while consuming almost no external steam, thus achieving energy saving and scale reduction.

[0030] The operating parameters for electrically driven membranes include: total membrane stack current, total membrane stack voltage, inlet flow rate, average membrane stack temperature, current density, and membrane surface velocity. The operating parameters for the MVR concentration unit include: secondary steam temperature, secondary steam pressure, inlet steam flow rate, motor current, motor power, and heat transfer coefficient. Environmental fluctuation parameters include: inlet water temperature, ambient temperature, humidity, and wind speed.

[0031] Step S3: Input the real-time input data into the pre-trained water concentration coupling model to predict the optimal concentration depth endpoint.

[0032] Step S3 includes: Step S310: Input the real-time input data into the pre-trained water concentration coupling model in real time and obtain the model output data.

[0033] The model output data includes: concentration ratio, salt content, energy consumption, etc. The concentration ratio is the amplification factor of total dissolved solids (TDS) on the concentrate side relative to the TDS on the feed water side.

[0034] Step S320: Establish the objective function and constraints.

[0035] The objective function is: ; ; .

[0036] Where max represents taking the maximum value, X represents the objective function; NS represents the concentration ratio, and Ed represents the comprehensive energy consumption per unit of water. Rz represents the predicted salt content (%). Indicates the concentration ratio weight; Indicates the weight of comprehensive energy consumption per unit of water; a4 represents the weight of the predicted salt content; a4 represents the weight of the equipment health penalty item. For example, a4=0.1. Both A4 and A4 can be self-refreshed through reinforcement learning, and the objective function can automatically evolve with the carbon market, electricity prices, and equipment aging to achieve a "self-optimization" closed loop.

[0037] in, , This indicates the total dissolved solids concentration in the influent (raw water). This indicates the total dissolved solids concentration of the effluent after concentration by an electrically driven membrane and an MVR concentration unit.

[0038] in, JL represents the feed flow rate; Indicates electro-driven membrane ( Real-time DC power consumption of the membrane stack; This indicates the real-time shaft power of the mechanical vapor recompression evaporator (compressor + circulating pump).

[0039] Where C1 represents the current electricity price in the plant area; C2 represents the current steam price per unit in the plant area; Q represents the carbon price; and kp represents the carbon emission factor converted from the electricity price (the carbon emission factor corresponding to the consumption of 1 MWh of electricity). Emissions); Ep represents the measured electricity consumption of the system during the statistical period; ks represents the carbon emission factor converted from steam price (the carbon emission factor corresponding to the consumption of 1 ton of low-pressure saturated steam). Emissions); Es represents the measured mass of make-up steam in the MVR evaporator during the same period (approximately 0 during normal MVR operation, and >0 during startup or winter peak).

[0040] Where RD represents the device health penalty value; ; Where i represents the current operating current density, i is equal to the real-time DC current of the electrically driven membrane (ED / EDR) stack divided by the effective membrane area; ie represents the rated current density, the maximum long-term operating current density allowed by the membrane manufacturer or design; N represents the current compressor speed, i.e. the real-time speed of the MVR main impeller; Ne represents the rated speed.

[0041] As shown in the objective function above, this application calculates C1 / C2 in real time for online calculation of the electricity-steam price ratio, thereby allowing the objective function weights to drift in real time with energy prices, achieving adaptive optimization for cost savings and conserving currently expensive resources. This application features real-time drift of the carbon-electricity-steam trivalent price, with kp and ks periodically updated based on the park's carbon trading price and the electricity-steam price ratio. The system automatically biases towards the cheapest energy source, reducing the annual comprehensive operating cost. This application employs an exponentially increasing high-intensity operating penalty in its RD (Reverse Energy) mechanism, reducing membrane stack current and extending the MVR impeller overhaul cycle.

[0042] The constraints of the objective function are: ; ; Indicates the nucleation induction period; The freezing section does not crystallize prematurely; ; Leave a 10% safety margin to ensure that the crystal does not explode instantly.

[0043] Indicates the current absolute temperature (Unit K) represents the total dissolved solids concentration in a concentrated brine system at which the salt that precipitates first reaches saturation. .

[0044] Step S330: Based on the objective function, constraints, and model output data, solve for the optimal depth concentration endpoint.

[0045] Specifically, the data output from the water concentration coupling model is fed into the objective function, with X treated as... A univariate function; using the golden ratio search in The interval converges after 15 iterations (< 40 ms); return the optimal value. Optimal To predict the optimal deep concentration endpoint, i.e., to solve the objective function with scaling / energy consumption constraints every half minute, the calculated total dissolved solids (TDS) is immediately converted into current and evaporation temperature setpoints, so that the system always operates at the edge of "most concentrated but no crystallization".

[0046] Step S340: The optimal depth concentration endpoint is converted into the operating volume, and the parameters of the electrically driven membrane and MVR evaporator are optimized based on the operating volume.

[0047] The process involves periodically acquiring ion concentration data, calculating the supersaturation index SI based on the ion concentration data, and using the classical nucleation theory (CNT) formula to calculate the nucleation induction period t_ind.

[0048] ; Where IAP represents the ion activity product; Ksp represents the solubility product constant.

[0049] Wherein, IAP is the product of online ion concentration and online ion activity coefficient. The supersaturation index SI is used as a scaling / crystallization criterion.

[0050] Among them, if the supersaturation index SI > 0.8 and the nucleation induction period If so, the control policy will be triggered.

[0051] Among them, the optimal deep concentration endpoint is predicted to be such that the TDS (total dissolved solids) of the concentrated brine is ≥18%.

[0052] The water concentration coupling model uses the classical nucleation theory (CNT) formula to calculate the nucleation induction period. If SI>0.8 and the nucleation induction period≤30 min, the trigger control strategy is to reduce the DC current of the electrically driven membrane (ED / EDR) stack in advance or reduce the evaporation temperature of the circulating concentrated brine in the MVR concentration unit (MVR evaporator) in advance.

[0053] Specifically, the optimal depth concentration endpoint is transformed into operational quantities such as current, temperature, and speed that can be written into the PLC through online mapping.

[0054] Specifically, optimizing the parameters of the electrically driven membrane and MVR evaporator based on the operating volume includes: Electrically driven membrane (ED / EDR) side: DC current setting value, current ramp time constant.

[0055] MVR evaporator side: evaporation temperature setpoint, speed setpoint, or vapor compression temperature rise.

[0056] Step S4: Based on the prediction results of the water concentration coupling model, dynamically adjust the operating pressure, temperature and / or circulation rate of the electrically driven membrane and the MVR concentration unit to achieve deep concentration.

[0057] Among them, the electro-driven membrane is a combination structure of electrodialysis and special ion exchange membrane.

[0058] The electrodialysis and special ion exchange membrane combination structure includes an electrodialysis structure and a special ion exchange membrane structure. The electrodialysis structure consists of an anode plate, dozens to hundreds of pairs of repeatedly stacked "cation membrane-separator-anion membrane-separator" units, and a cathode plate, all secured together by clamping plates to form an ED membrane stack. The special ion exchange membrane (homogeneous membrane) uses sulfonic acid type (cation membrane) / quaternary ammonium type (anion membrane) cross-linked polystyrene as its substrate. This special ion exchange membrane offers the following advantages: high COD (chemical oxygen demand) resistance, reducing organic matter adsorption; high hardness resistance, inhibiting CaSO4 crystal growth; and resistance to hydrolysis during pH adjustment and scale prevention on the concentrate side.

[0059] As a specific embodiment of the present invention, the MVR evaporation temperature is adjusted according to the following formula: ; Where TM represents the target evaporation temperature of the evaporator at the current moment; TB represents the reference evaporation temperature; and Vt represents the temperature feedback coefficient. Indicates the supersaturation index of sodium sulfate; Calculate based on the above formula ,like The temperature began to drop.

[0060] As a specific embodiment of the present invention, the cycle ratio is adjusted according to the following formula: ; Wherein, Ql represents the current set value of the circulating concentrate flow rate, which is sent to the frequency converter of the circulating pump; Qd represents the rated circulating flow rate of the heat exchanger; TDSt represents the optimal depth concentration endpoint; and TDSn represents the measured total dissolved solids (TDS) at the evaporator outlet.

[0061] As a specific embodiment of the present invention, the calculation formula for the ED side pressure correction is as follows: ; Where, ΔP ED(t) ΔI(t) represents the pressure correction required on the concentrate side at the current moment; ΔI(t) represents the current density increment. ; Indicates the target current density; This represents the measured current density; dh represents the current dynamic viscosity of the concentrate; dh represents the hydraulic diameter of the baffle mesh; ρ represents the density of the concentrate.

[0062] As a specific embodiment of the present invention, the calculation formula for the MVR side pressure correction is as follows: ; Where, ΔP MVR(t) This indicates the amount of secondary steam back pressure that needs to be increased at the current moment; TDSt indicates the optimal deep concentration endpoint; TDSn indicates the measured total dissolved solids at the evaporator outlet; Pn indicates the evaporator design back pressure.

[0063] Step S5: The highly concentrated brine is fed into a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate.

[0064] The role of the cryogenic nanofiltration coupled salt separation system is to first separate sodium sulfate, then sodium chloride, to obtain concentrated sodium sulfate and concentrated sodium chloride solutions, thus achieving... High-precision separation enables selective separation of monovalent / divalent ions, reducing the impurity salt rate in subsequent evaporation and crystallization to <5%.

[0065] Step S5 includes: Step S510: The highly concentrated brine is sent into a cryogenic nanofiltration coupled salt separation system.

[0066] Step S520: The freezing temperature of the cryogenic nanofiltration coupled salt separation system is adjusted by supersaturation control.

[0067] The supersaturation control is as follows: ; Where Tc represents the target evaporation temperature setpoint in the cryogenic nanofiltration coupled salt separation system; This represents the real-time supersaturation index of sodium sulfate. The target evaporation temperature of the cryogenic nanofiltration coupled salt separation system is set based on the calculated Tc.

[0068] In step S530, the cryogenic nanofiltration coupled salt separation system produces two liquid streams: a sodium sulfate-rich concentrate and a sodium chloride-rich concentrate.

[0069] In step S6, the concentrated sodium sulfate solution and the concentrated sodium chloride solution are respectively sent to the evaporation and crystallization unit to produce sodium sulfate and sodium chloride.

[0070] Step S6 includes: In step S610, the concentrated sodium sulfate solution is fed into a sodium sulfate evaporator to produce sodium sulfate.

[0071] In step S620, the concentrated sodium chloride solution is fed into a sodium chloride evaporator to produce sodium chloride.

[0072] It should be explained that steps S610 and S620 are performed synchronously and in parallel without interfering with each other.

[0073] Step S7: Establish a big data closed-loop feedback mechanism to continuously learn and optimize the parameters of the water concentration coupling model based on preset conditions.

[0074] As a specific embodiment of the present invention, the preset conditions are: salt content <5%; scaling cycle ≥12 days; and the error between predicted and measured TDS ≤3%.

[0075] The process involves using a water concentration coupling model to obtain predicted SI, energy consumption, and impurity rate. The optimizer provides the optimal deep concentration endpoint TDS_target, which is then converted into operational quantities. The PLC executes these operational quantities, and the measured TDS, SI, and energy consumption data are fed back. Incremental learning is triggered every 30 seconds if the error between the predicted and measured TDS exceeds 3% and continues for 3 minutes.

[0076] like Figure 2 As shown, this application provides a high-salinity complex wastewater reduction treatment system 100 based on big data. This system executes the aforementioned high-salinity complex wastewater reduction treatment method based on big data. The system includes:

[0077] Pretreatment system 10 is used to remove impurities from wastewater.

[0078] The big data acquisition module 20 is used to collect influent water quality indicators, operating parameters of the electro-driven membrane and MVR concentration unit, and environmental fluctuation parameters in real time to obtain real-time input data.

[0079] The prediction module 30 is used to input real-time input data into a pre-trained water concentration coupling model to predict the optimal concentration depth endpoint.

[0080] The dynamic adjustment module 40 is used to dynamically adjust the operating pressure, temperature and / or circulation rate of the electrically driven membrane and the MVR concentration unit according to the prediction results of the water concentration coupling model, so as to achieve deep concentration.

[0081] The acquisition module 50 is used to send the highly concentrated brine after deep concentration into a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate.

[0082] The output module 60 is used to send concentrated sodium sulfate solution and concentrated sodium chloride solution into the evaporation and crystallization unit to produce sodium sulfate and sodium chloride, respectively.

[0083] Optimization module 70 is used to establish a big data closed-loop feedback mechanism, which continuously learns and optimizes the parameters of the water quality concentration coupling model based on preset conditions.

[0084] This application also provides a computer storage medium storing computer instructions, which, when invoked, execute the address mapping method for the large-capacity solid-state drive. The computer storage medium includes one or more program instructions, which are executed by a processor to provide a method for reducing the volume of high-salt, complex wastewater based on large data sets.

[0085] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions. When the computer program instructions are executed on a computer, the computer performs the above-described method for reducing the volume of high-salt complex wastewater based on big data.

[0086] This invention provides a processor for processing the above-described method for reducing the volume of complex high-salt wastewater based on big data.

[0087] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0088] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0089] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0090] The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EEPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).

[0091] The beneficial effects achieved by this application are as follows: (1) This application achieves near-zero discharge of high-salt wastewater through a fully enclosed chain of pretreatment, electro-driven membrane, MVR deep concentration, cryogenic nanofiltration for salt separation, and evaporation crystallization.

[0092] (2) This application adjusts the current, temperature and circulation rate in real time to adapt to water quality fluctuations and improve operational stability.

[0093] (3) This application improves the cold nanofiltration coupled salt separation process Separation coefficient, reducing the rate of mixed salts.

[0094] (4) This application sets a device health penalty term in the objective function to limit the current density and compressor speed in real time, thereby extending the device life and improving the reliability of device operation.

[0095] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0096] In the description of this application, the word "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0097] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for reducing the volume of high-salinity, complex wastewater based on big data, characterized in that: The method includes: Impurities in wastewater are removed through a pretreatment system; The big data acquisition module is used to collect in-water quality indicators, operating parameters of the electro-driven membrane and MVR concentration unit, and environmental fluctuation parameters in real time to obtain real-time input data. Real-time input data is fed into a pre-trained water concentration coupling model to predict the optimal concentration depth endpoint. Based on the prediction results of the water concentration coupling model, the operating pressure, temperature and / or circulation rate of the electrically driven membrane and the MVR concentration unit are dynamically adjusted to achieve deep concentration.

2. The method for reducing the volume of high-salinity, complex wastewater based on big data as described in claim 1, characterized in that, The method also includes: The highly concentrated brine was fed into a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate. The concentrated sodium sulfate solution and the concentrated sodium chloride solution are respectively fed into the evaporation and crystallization unit to produce sodium sulfate and sodium chloride.

3. The method for reducing the volume of high-salinity, complex wastewater based on big data as described in claim 2, characterized in that, The method also includes: Establish a big data closed-loop feedback mechanism to continuously learn and optimize the parameters of the water quality concentration coupling model based on preset conditions.

4. The method for reducing the volume of high-salinity, complex wastewater based on big data as described in claim 1, characterized in that, Real-time input data is fed into a pre-trained water concentration coupling model to predict the optimal concentration depth endpoint, including: Real-time input data is fed into a pre-trained water concentration coupling model to obtain model output data. Establish the objective function and constraints; Based on the objective function, constraints, and model output data, the optimal depth concentration endpoint is determined.

5. The method for reducing the volume of high-salinity, complex wastewater based on big data as described in claim 4, characterized in that, The optimal deep concentration endpoint is converted into the operating volume, and the parameters of the electrically driven membrane and MVR evaporator are optimized based on the operating volume.

6. The method for reducing the volume of high-salinity, complex wastewater based on big data as described in claim 2, characterized in that, The highly concentrated brine is fed into a cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate, including: The highly concentrated brine is then fed into a cryogenic nanofiltration coupled salt separation system. The freezing temperature of the cryogenic nanofiltration coupled salt separation system is adjusted by controlling supersaturation. The cryogenic nanofiltration coupled salt separation system produces two liquid streams: a concentrated sodium sulfate solution and a concentrated sodium chloride solution.

7. The method for reducing the volume of high-salinity, complex wastewater based on big data as described in claim 2, characterized in that, The concentrated sodium sulfate solution and the concentrated sodium chloride solution are respectively fed into the evaporation and crystallization unit to produce sodium sulfate and sodium chloride, including: The concentrated sodium sulfate solution is fed into a sodium sulfate evaporator to produce sodium sulfate. A concentrated sodium chloride solution is fed into a sodium chloride evaporator to produce sodium chloride.

8. A high-salinity, complex wastewater reduction treatment system based on big data, characterized in that: The system performs the method according to any one of claims 1-7, the system comprising: Pretreatment systems are used to remove impurities from wastewater; The big data acquisition module is used to collect in-water quality indicators, operating parameters of the electro-driven membrane and MVR concentration unit, and environmental fluctuation parameters in real time to obtain real-time input data. The prediction module is used to input real-time data into a pre-trained water concentration coupling model to predict the optimal concentration depth endpoint. The dynamic adjustment module is used to dynamically adjust the operating pressure, temperature and / or circulation rate of the electrically driven membrane and the MVR concentration unit based on the prediction results of the water concentration coupling model, so as to achieve deep concentration.

9. The high-salt complex wastewater reduction treatment system based on big data according to claim 8, characterized in that, The system also includes: The acquisition module is used to send the highly concentrated brine after deep concentration into the cryogenic nanofiltration coupled salt separation system to obtain sodium sulfate-rich concentrate and sodium chloride-rich concentrate. The output module is used to feed concentrated sodium sulfate solution and concentrated sodium chloride solution into the evaporation and crystallization unit to produce sodium sulfate and sodium chloride, respectively.

10. The high-salt complex wastewater reduction treatment system based on big data according to claim 9, characterized in that, The system also includes: The optimization module is used to establish a big data closed-loop feedback mechanism, which continuously learns and optimizes the parameters of the water concentration coupling model based on preset conditions.

Images