A wastewater zero discharge treatment method

Abstract

The present application relates to a kind of wastewater zero discharge treatment method, belong to water treatment and purification field, the method includes: using the discharge treatment mechanism including activated carbon adsorption device, electrodialysis device and membrane distillation device;Traversal the numerical combination of the specific value of three parameters of set activated carbon concentration, set current value and set membrane thickness to obtain each three-parameter value combination, intelligently predict the backwater water consumption ratio and the volume of concentrated crystalline solid corresponding to each three-parameter value combination;The three-parameter value combination corresponding to the backwater water consumption ratio exceeding limit is used as zero discharge treatment configuration data.Through the present application, in view of the technical problem that zero discharge treatment configuration data needs to be analyzed by repeated load cumbersome debugging test in the prior art, the discharge treatment analysis model of customized structure design can be introduced to intelligently predict the backwater water consumption ratio and the volume of concentrated crystalline solid corresponding to each three-parameter value combination, thereby solving the above technical problems.

Description

Technical Field

[0001] This invention relates to the field of water treatment and purification, and more particularly to a method for zero-discharge wastewater treatment. Background Technology

[0002] Zero wastewater discharge refers to the process where industrial water produced by a factory is highly concentrated to remove salt and pollutants. All (over 99%) of the concentrated wastewater is then recycled or reused, or filtered out using a filter press to remove water-insoluble substances before recycling. No waste liquid is discharged from the factory. Salts and pollutants in the water are concentrated and crystallized, or the filter press residue is discharged as solids and sent to a landfill or recycled as useful chemical raw materials. Achieving zero wastewater discharge typically requires at least two key steps: pretreatment of the concentrated wastewater and concentration crystallization to obtain reclaimed water and concentrated crystalline solids, respectively.

[0003] For example, Chinese invention patent publication CN108117223A proposes a method for zero-discharge treatment of saline wastewater, which includes the following steps: (1) pretreatment; (2) reverse osmosis treatment; (3) biochemical treatment; (4) electrodialysis concentration; and (5) cyclic crystallization. Compared with the prior art, the zero-discharge salt separation treatment process for saline wastewater provided by the present invention achieves zero or near-zero discharge of coal chemical wastewater while improving the salt recovery rate and recovering high-quality sodium sulfate, mirabilite, and sodium chloride, realizing the comprehensive utilization of crystalline salt. The membrane treatment unit process is stable, has a long operating cycle, low cost, and good overall economic efficiency.

[0004] For example, Chinese invention patent publication CN110563227A discloses a zero-discharge wastewater treatment device. This device includes a wastewater tank, an integrated air-source backwash cleaning machine for the wastewater tank, an intelligent integrated air-source backwash filtration cleaning and dirt collection machine, a terahertz phonon resonant ring, a water softening device, a fine filtration device, a primary sedimentation filtration device, and a secondary sedimentation filtration device. This invention provides a suitable zero-discharge wastewater treatment solution for industrial plants, adapting to local conditions. This invention can be applied to almost all saline wastewater treatment. It achieves the lowest investment, lowest energy consumption, and simplest system, meeting the requirements for zero-discharge industrial wastewater, without secondary pollution, and is easy to promote and apply in the field of saline industrial wastewater treatment. Furthermore, this invention is a purely physical zero-discharge wastewater treatment solution, avoiding pollution from chemical agents added during wastewater treatment.

[0005] However, the above technical solutions only involve a detailed description of the specific steps or structures for zero wastewater discharge treatment. In reality, to achieve true zero wastewater discharge treatment, i.e., the percentage of recycled water to the initially treated wastewater is over 99%, it is necessary to repeatedly and tediously debug and test the configuration parameters corresponding to each specific step or structure. Based on the actual discharge treatment results, the combination of configuration parameters that can achieve the zero wastewater discharge treatment effect is finally determined. Obviously, this repeated and tedious debugging and testing process to find the optimal combination of configuration parameters consumes a lot of labor, time, and economic costs. At the same time, during the debugging and testing process, unqualified wastewater discharge is inevitable. Summary of the Invention

[0006] To address the technical problems in existing technologies, this invention provides a zero-discharge wastewater treatment method. Based on a customized structural design-based wastewater treatment analysis model and targeted selection of multiple fundamental information, and targeting a wastewater treatment system employing activated carbon adsorption, electrodialysis, and membrane distillation devices, this method sequentially performs activated carbon adsorption, electrodialysis, distillation, and membrane separation operations on industrial wastewater from a target steel plant. To obtain specific combinations of values ​​for three parameters—set activated carbon concentration, set current value, and set membrane thickness—that meet the zero-discharge wastewater treatment conditions, the method iteratively selects values ​​for these three parameters to obtain the corresponding values. The parameter value combinations are input into the emission treatment analysis model in stages to obtain the corresponding water reuse ratio and concentrated crystal solid volume for each three-parameter value combination. The three-parameter value combinations with a water reuse ratio greater than 99% are used as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant. This facilitates the subsequent execution of priority parameter configuration, thereby directly obtaining the specific value combinations of the three parameters that meet the wastewater zero-discharge treatment conditions without performing a large number of emission effect test treatments. This improves treatment efficiency, reduces treatment costs, and avoids unqualified wastewater discharges during the testing process.

[0007] According to the present invention, a method for zero-discharge wastewater treatment is provided, the method comprising:

[0008] An emission treatment system comprising activated carbon adsorption devices, electrodialysis devices, and membrane distillation devices is used to sequentially perform activated carbon adsorption, electrodialysis, distillation, and membrane separation operations on industrial wastewater generated by the target steel plant to obtain recycled water and concentrated crystalline solids. The activated carbon adsorption devices use activated carbon with a set concentration in g / L to separate dissolved organic carbon from the industrial wastewater. The electrodialysis devices use a DC power supply with a set current value in mA to separate inorganic salts from the industrial wastewater. The membrane distillation devices use a reverse osmosis membrane with a set membrane thickness in millimeters to separate organic salts and macromolecular organic matter from the industrial wastewater.

[0009] Acquire multiple operational scenario data for the target steel plant;

[0010] The specific combinations of values ​​for the three parameters—activated carbon concentration, current value, and membrane thickness—are iterated to obtain various combinations of three-parameter values. Each combination of three-parameter values, multiple operating scenario data of the target steel plant, the production flow rate of the industrial wastewater from the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant are input into the emission treatment analysis model to obtain the proportion of recycled water and the volume of concentrated crystallized solids corresponding to each combination of three-parameter values.

[0011] The combination of three parameters with a corresponding return water usage ratio greater than 99% is used as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant by the emission treatment agency.

[0012] Compared with the prior art, the present invention has at least the following five key inventive points:

[0013] The first inventive point: For an industrial wastewater treatment scenario where an industrial wastewater from a target steel plant is treated using an emission treatment apparatus employing activated carbon adsorption, electrodialysis, and distillation / membrane separation, the invention aims to obtain specific combinations of three parameters—set activated carbon concentration, set current value, and set membrane thickness—that meet the zero-discharge treatment conditions. These three parameters are iterated through to obtain various combinations, and each combination is input into the emission treatment analysis model to obtain the corresponding reclaimed water usage ratio and concentrated crystallized solid volume. The combination of three parameters with a reclaimed water usage ratio greater than 99% is used as the zero-discharge treatment configuration data for the industrial wastewater from the target steel plant. This facilitates subsequent priority parameter configuration, allowing for direct acquisition of specific combinations of three parameters that meet the zero-discharge treatment conditions without requiring numerous emission effect tests.

[0014] The second point of invention: different target steel plants have different customized emission treatment analysis models. Specifically, the emission treatment analysis model is a deep neural network after each training. The deep neural network includes a single input layer, a single output layer and multiple hidden layers. The number of training times of the deep neural network is positively correlated with the steel production per unit time of the target steel plant. The customized structure of the above emission treatment analysis model ensures the reliability and stability of the emission treatment effect data corresponding to each combination of three parameter values, namely the proportion of recycled water and the volume of concentrated crystallized solids.

[0015] The third invention point: To intelligently predict the emission treatment effect data corresponding to each combination of three parameters, a number of basic information items were specifically selected. These include each combination of three parameters, multiple operating scenario data of the target steel plant, the production flow rate of the industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant. The multiple operating scenario data of the target steel plant include the steel production per unit time, floor area, number of workers, working temperature of the steelmaking furnace, working temperature of the rolling mill, pressure of the rolls used for rolling, casting speed of the billet during the continuous casting process, upper limit value of carbon content in the steel body, and lower limit value of carbon content in the steel body. The targeted selection of the above-mentioned basic information items further ensures the reliability and stability of the emission treatment effect data corresponding to each combination of three parameters, namely the proportion of recycled water and the volume of concentrated crystallized solids.

[0016] The fourth invention point: In each training iteration of the deep neural network, the proportion of recycled water and the volume of concentrated crystallized solids corresponding to a known combination of three parameters are used as two outputs of the deep neural network. The three parameter combinations, multiple operational scenario data of the target steel plant, the production flow rate of industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater produced by the target steel plant are used as multiple inputs of the deep neural network to complete the training of the deep neural network, thereby ensuring the training effect of each iteration of the deep neural network.

[0017] The fifth invention point: When the numerical values ​​of multiple operating scenario data of the target steel plant change, the changed numerical values ​​of the multiple operating scenario data of the target steel plant are input into the emission treatment analysis model to obtain new zero-emission treatment configuration data for the industrial wastewater generated by the target steel plant corresponding to the changed numerical values ​​of the multiple operating scenario data of the target steel plant, thereby realizing the dynamic updating of zero-emission treatment configuration data based on changes in the emission environment. Attached Figure Description

[0018] The embodiments of the present invention will now be described with reference to the accompanying drawings, wherein:

[0019] Figure 1 This is a schematic diagram of the working scenario of the zero-discharge wastewater treatment method according to the present invention.

[0020] Figure 2 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 1 of the present invention.

[0021] Figure 3 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 2 of the present invention.

[0022] Figure 4 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 3 of the present invention.

[0023] Figure 5 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 4 of the present invention.

[0024] Figure 6 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 5 of the present invention.

[0025] Figure 7 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 6 of the present invention. Detailed Implementation

[0026] like Figure 1 The diagram shows a working scenario of a zero-discharge wastewater treatment method according to the present invention.

[0027] The specific technical process of this invention is as follows:

[0028] Technical Process A: Design a customized emission treatment mechanism for the target steel plant, the emission treatment mechanism including activated carbon adsorption devices, electrodialysis devices and membrane distillation devices;

[0029] Specifically, the activated carbon adsorption device, the electrodialysis device, and the membrane distillation device sequentially perform activated carbon adsorption, electrodialysis, and distillation and membrane separation operations on the industrial wastewater generated by the target steel plant to obtain recycled water and concentrated crystalline solids.

[0030] More specifically, the activated carbon adsorption device uses activated carbon with a set concentration in g / L to separate dissolved organic carbon in industrial wastewater; the electrodialysis device uses a DC power supply with a set current value in mA to separate inorganic salts in industrial wastewater; and the membrane distillation device uses a reverse osmosis membrane with a set membrane thickness in millimeters to separate organic salts and macromolecular organic matter in industrial wastewater.

[0031] Here, the specific combination of the three parameters—activated carbon concentration, current value, and membrane thickness—is uncertain. Optimization of this combination is necessary to achieve true zero-discharge wastewater treatment. The activated carbon concentration should be set between 0-5 g / L, the current value between 5-600 mA, and the membrane thickness between 0.1-0.5 mm. Optimization of the combination of these values ​​must be performed within these ranges.

[0032] In existing technologies, it is necessary to repeatedly and tediously debug and test these three configuration parameters, and finally determine the combination of each configuration parameter that can achieve the zero wastewater discharge treatment effect based on the actual discharge treatment results. Obviously, this repeated and tedious debugging and testing process of finding the best configuration parameter combination consumes a lot of labor, time and economic costs. At the same time, unqualified wastewater discharge is inevitable during the debugging and testing process. This invention will use an intelligent prediction mode to predict the various wastewater discharge treatment effects obtained by applying each configuration parameter combination to the customized structure discharge treatment mechanism of the target steel plant, and then directly obtain the configuration parameter combination that achieves the wastewater discharge treatment effect to meet the wastewater zero discharge treatment requirements, so as to facilitate the subsequent on-site configuration operation of the customized structure discharge treatment mechanism to achieve the zero wastewater discharge treatment of the target steel plant.

[0033] Technical Process B: To intelligently predict the emission treatment effect data corresponding to each combination of three parameter values, a customized emission treatment analysis model is designed.

[0034] For example, the emission treatment analysis model is a deep neural network after each training iteration. The deep neural network includes a single input layer, a single output layer, and multiple hidden layers. The number of training iterations of the deep neural network is positively correlated with the steel production per unit time of the target steel plant, thereby designing emission treatment analysis models with different customized structures for different target steel plants.

[0035] For example, in each training iteration of the deep neural network, the proportion of recycled water and the volume of concentrated crystallized solids corresponding to a known combination of three parameters are used as two outputs of the deep neural network. The three parameter combinations, multiple operational scenario data of the target steel plant, the production flow rate of industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater produced by the target steel plant are used as multiple inputs of the deep neural network to complete the training of the deep neural network, thereby ensuring the training effect of each training iteration of the deep neural network.

[0036] In this way, by customizing the structure of the above emission treatment analysis model, the reliability and stability of the emission treatment effect data corresponding to each combination of three parameter values, namely the proportion of recycled water and the volume of concentrated crystallized solids, are guaranteed.

[0037] Technical Process C: To intelligently predict the emission treatment effect data corresponding to each combination of three parameter values, multiple basic information items were specifically selected;

[0038] For example, the multiple basic information specifically includes each combination of three parameter values, multiple operating scenario data of the target steel plant, production flow rate of industrial wastewater of the target steel plant, organic carbon concentration, inorganic salt concentration, organic salt concentration and macromolecular organic matter concentration of industrial wastewater generated by the target steel plant.

[0039] like Figure 1 As shown, the multiple basic information includes three types of information. The first type is the combination of three parameter values ​​used in the current test. The second type is multiple operating scenario data of the target steel plant. The third type is various industrial wastewater related data of the target steel plant, including the production flow rate of industrial wastewater of the target steel plant, the organic carbon concentration, inorganic salt concentration, organic salt concentration and macromolecular organic matter concentration of industrial wastewater generated by the target steel plant.

[0040] As a further example, the multiple operational scenario data of the target steel plant include the steel output per unit time, floor area, number of workers, working temperature of the steelmaking furnace, working temperature of the rolling mill, pressure of the rolls used for rolling, casting speed of the billet during the continuous casting process, upper limit value of carbon content of steel body and lower limit value of carbon content of steel body.

[0041] In this way, by making targeted selections of the above-mentioned basic information, the reliability and stability of the emission treatment effect data corresponding to each combination of three parameters, namely the proportion of recycled water and the volume of concentrated crystallized solids, are further guaranteed.

[0042] Technical Process D: The emission treatment analysis model adopts Technical Process B for the customized structural design of the target steel plant. Based on multiple basic information selected in Technical Process C, it performs intelligent prediction of the emission treatment effect data corresponding to each specific combination of three parameters: set activated carbon concentration, set current value, and set membrane thickness for the emission treatment mechanism of the customized structure of the target steel plant designed in Technical Process A.

[0043] like Figure 1 As shown, for the current combination of three parameters used in the test, the system intelligently predicts the corresponding emission treatment effect data, including two data points: the first is the proportion of recycled water and the second is the volume of concentrated crystallized solids.

[0044] Technical Process E: Based on the specific numerical combinations obtained from Technical Process D, each set of emission treatment effect data is obtained to achieve the specific numerical combinations that meet the requirements for zero wastewater discharge treatment.

[0045] Specifically, the emission treatment effect data corresponding to each specific numerical combination is the proportion of recycled water and the volume of concentrated crystallized solid obtained by applying the specific numerical combination to the emission treatment agency. The specific numerical combination with a recycled water proportion greater than 99% is used as the zero-emission treatment configuration data of the emission treatment agency for the industrial wastewater generated by the target steel plant, so as to facilitate the subsequent execution of priority parameter configuration.

[0046] Technical Process F: When the numerical values ​​of multiple operating scenario data of the target steel plant change, the numerically changed multiple operating scenario data of the target steel plant are input into the emission treatment analysis model to obtain new zero-emission treatment configuration data for the industrial wastewater generated by the target steel plant, corresponding to the numerically changed multiple operating scenario data of the target steel plant.

[0047] This enables dynamic updates of zero-emission treatment configuration data based on changes in the emission environment of the target steel plant.

[0048] Therefore, compared with the prior art, the present invention can directly obtain the specific value combination of the three parameters that meet the conditions for zero wastewater discharge treatment without performing a large number of discharge effect tests. This improves treatment efficiency, reduces treatment costs, and avoids unqualified wastewater discharge during the testing process.

[0049] The key points of this invention are: traversing and combining the specific values ​​of three parameters—set activated carbon concentration, set current value, and set membrane thickness—within their respective value ranges to obtain each specific value combination; intelligent prediction of the wastewater discharge treatment effect of each specific value combination; direct acquisition of specific value combinations that meet the conditions for zero wastewater discharge treatment; a customized structural design for discharge treatment analysis model; and targeted selection of multiple basic information.

[0050] The zero-discharge wastewater treatment method of the present invention will now be described in detail by way of examples.

[0051] Example 1

[0052] Figure 2 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 1 of the present invention.

[0053] like Figure 2 As shown, the zero-discharge wastewater treatment method includes the following specific steps:

[0054] Step 201: Using a discharge treatment device including activated carbon adsorption device, electrodialysis device and membrane distillation device, the industrial wastewater generated by the target steel plant is subjected to activated carbon adsorption operation, electrodialysis operation and distillation and membrane separation operation in sequence to obtain recycled water and concentrated crystalline solids. The activated carbon adsorption device uses activated carbon with a set activated carbon concentration in g / L to separate dissolved organic carbon in the industrial wastewater. The electrodialysis device uses a DC power supply with a set current value in mA to separate inorganic salts in the industrial wastewater. The membrane distillation device uses a reverse osmosis membrane with a set membrane thickness in millimeters to separate organic salts and macromolecular organic matter in the industrial wastewater.

[0055] For example, the emission treatment device may also include a parameter configuration interface for connecting to the activated carbon adsorption device, the electrodialysis device and the membrane distillation device respectively, so as to configure the specific values ​​of the three parameters of setting the activated carbon concentration, setting the current value and setting the membrane thickness respectively for the activated carbon adsorption device, the electrodialysis device and the membrane distillation device.

[0056] Step 202: Obtain multiple operational scenario data for the target steel plant;

[0057] Specifically, the multiple operational scenario data of the target steel plant reflect the emission environment of the target steel plant. When any value of any operational scenario data changes, it can be determined that the emission environment of the target steel plant has changed. Obviously, under different emission environments, even if the same emission treatment facility is used, the specific combination of the above three parameters to achieve zero wastewater discharge treatment may be different.

[0058] In subsequent steps of this invention, when the numerical values ​​of multiple operating scenario data of the target steel plant change, the numerically changed multiple operating scenario data of the target steel plant are input into the emission treatment analysis model to obtain new zero-emission treatment configuration data for the industrial wastewater generated by the target steel plant corresponding to the numerically changed multiple operating scenario data of the target steel plant. In this way, the zero-emission treatment configuration data based on the change in the emission environment of the target steel plant can be dynamically updated.

[0059] Step 203: Iterate through the specific value combinations of the three parameters, namely, the set activated carbon concentration, the set current value, and the set membrane thickness, to obtain various three-parameter value combinations. Input each three-parameter value combination, multiple operating scenario data of the target steel plant, the production flow rate of the industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model to obtain the reclaimed water ratio and concentrated crystallized solid volume corresponding to each three-parameter value combination.

[0060] Specifically, the traversal of the specific values ​​of the above three parameters needs to be performed within their respective value ranges;

[0061] Step 204: Use the combination of three parameters with a return water usage ratio greater than 99% as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant by the emission treatment agency;

[0062] Specifically, the requirement for zero-discharge treatment of industrial wastewater is that the proportion of recycled water is greater than 99%. Obviously, there may be more than one combination of the three parameters for the proportion of recycled water being greater than 99%.

[0063] Among them, the target steel plant's multiple operational scenario data include the target steel plant's steel output per unit time, floor area, number of workers, working temperature of the steelmaking furnace, working temperature of the rolling mill, pressure of the rolls used for rolling, casting speed of the billet during the continuous casting process, upper limit value of carbon content in steel, and lower limit value of carbon content in steel.

[0064] Among them, the activated carbon concentration is set to a range of 0-5 g / L, the current value is set to a range of 5-600 mA, and the membrane thickness is set to a range of 0.1-0.5 mm.

[0065] Wherein, the proportion of recycled water usage corresponding to each combination of three parameters is the percentage of recycled water usage obtained after the emission treatment mechanism configured with the three parameter value combination performs emission treatment on the industrial wastewater generated by the target steel plant relative to the industrial wastewater generated by the target steel plant.

[0066] Wherein, the volume of concentrated crystalline solid corresponding to each combination of three parameter values ​​is the volume of concentrated crystalline solid obtained after the discharge treatment mechanism configured with the three parameter value combination performs discharge treatment on the industrial wastewater generated by the target steel plant;

[0067] In this way, most of the industrial wastewater that has undergone zero-discharge treatment is reused as recycled water, while a small portion, namely concentrated crystallized solids, is discharged from the plant in solid form and sent to a landfill for disposal or recycled as a useful chemical raw material, thus achieving the goal of zero-discharge treatment for steel plants with no waste liquid discharge.

[0068] Among them, the emission treatment analysis model is a deep neural network after each training. The deep neural network includes a single input layer, a single output layer and multiple hidden layers, and the number of training times of the deep neural network is positively correlated with the steel output per unit time of the target steel plant.

[0069] Specifically, the positive correlation between the number of training iterations of the deep neural network and the steel output per unit time of the target steel plant includes: 500,000 tons of steel output per unit time for the target steel plant, 500 training iterations for the deep neural network; 800,000 tons of steel output per unit time for the target steel plant, 800 training iterations for the deep neural network; 1,200,000 tons of steel output per unit time for the target steel plant, 1,200 training iterations for the deep neural network; 1,800,000 tons of steel output per unit time for the target steel plant, 1,800 training iterations for the deep neural network, and so on.

[0070] In each training iteration of the deep neural network, the proportion of recycled water and the volume of concentrated crystallized solids corresponding to a known combination of three parameters are used as two outputs of the deep neural network. The three parameter combinations, multiple operational scenario data of the target steel plant, the production flow rate of industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater produced by the target steel plant are used as multiple inputs of the deep neural network to complete the training of the deep neural network.

[0071] Example 2

[0072] Figure 3 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 2 of the present invention.

[0073] like Figure 3 As shown, with Figure 2 Unlike the previous embodiment, after using the combination of three parameters with a corresponding return water usage ratio greater than 99% as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant, i.e. after step S204, the method further includes:

[0074] Step S205: Using zero-emission treatment configuration data, configure the specific values ​​of three parameters for the activated carbon adsorption device, electrodialysis device, and membrane distillation device of the emission treatment unit: set activated carbon concentration, set current value, and set membrane thickness.

[0075] Specifically, the parameter configuration interface within the emission treatment device can be used to connect to the activated carbon adsorption device, the electrodialysis device, and the membrane distillation device respectively, so as to configure the specific values ​​of the three parameters of the activated carbon adsorption device, the electrodialysis device, and the membrane distillation device respectively.

[0076] The configuration of setting the specific values ​​of three parameters—activated carbon concentration, set current value, and set membrane thickness—for the activated carbon adsorption device, electrodialysis device, and membrane distillation device of the emission treatment mechanism using zero-emission treatment configuration data includes: when there is more than one zero-emission treatment configuration data, selecting any zero-emission treatment configuration data to configure the specific values ​​of the three parameters—activated carbon concentration, set current value, and set membrane thickness—for the activated carbon adsorption device, electrodialysis device, and membrane distillation device of the emission treatment mechanism.

[0077] Example 3

[0078] Figure 4 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 3 of the present invention.

[0079] like Figure 4 As shown, with Figure 2 Unlike the previous embodiment, after using the combination of three parameters with a corresponding return water usage ratio greater than 99% as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant, i.e. after step S204, the method further includes:

[0080] Step S206: Receive zero-emission treatment configuration data and wirelessly transmit the zero-emission treatment configuration data to a remote wastewater zero-emission management server via a wireless communication network.

[0081] For example, receiving zero-emission treatment configuration data and wirelessly transmitting the zero-emission treatment configuration data to a remote wastewater zero-emission management server via a wireless communication network includes: the wireless communication network being based on a frequency division duplex communication mechanism or a time division duplex communication mechanism.

[0082] Example 4

[0083] Figure 5 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 4 of the present invention.

[0084] like Figure 5 As shown, with Figure 2 Unlike the previous embodiment, after using the combination of three parameters with a corresponding return water usage ratio greater than 99% as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant, i.e. after step S204, the method further includes:

[0085] Step S207: Receive zero-emission treatment configuration data and use a field display mechanism to display the zero-emission treatment configuration data on-site;

[0086] For example, receiving zero-emission treatment configuration data and displaying the zero-emission treatment configuration data on-site using an on-site display mechanism includes: the on-site display mechanism being an LCD display array, an LED display array, or a giant screen display.

[0087] Example 5

[0088] Figure 6 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 5 of the present invention.

[0089] like Figure 6 As shown, with Figure 2 Unlike the previous embodiment, after using the combination of three parameters with a corresponding return water usage ratio greater than 99% as the zero-discharge treatment configuration data for the industrial wastewater generated by the target steel plant, i.e. after step S204, the method further includes:

[0090] Step S208: When the numerical values ​​of multiple operating scenario data of the target steel plant change, the numerically changed multiple operating scenario data of the target steel plant are input into the emission treatment analysis model to obtain new zero-emission treatment configuration data for industrial wastewater generated by the target steel plant corresponding to the numerically changed multiple operating scenario data of the target steel plant.

[0091] Specifically, when multiple operational scenario data of the target steel plant change numerically, the changed operational scenario data of the target steel plant is input into the emission treatment analysis model to obtain new zero-emission treatment configuration data for the industrial wastewater generated by the target steel plant, corresponding to the changed operational scenario data. This includes: if more than one operational scenario data of the target steel plant changes numerically, it can be determined that multiple operational scenario data of the target steel plant have changed numerically, and the zero-emission treatment configuration data needs to be re-analyzed.

[0092] Example 6

[0093] Figure 7 This is a flowchart illustrating the steps of a zero-discharge wastewater treatment method according to Embodiment 6 of the present invention.

[0094] like Figure 7 As shown, with Figure 2 Unlike the previous embodiment, after acquiring multiple operational scenario data of the target steel plant, i.e., after step S202, the method further includes:

[0095] Step S209: Perform training on the deep neural network to obtain the deep neural network after each training and use it as the output of the emission treatment analysis model. The number of training sessions of the deep neural network is positively correlated with the steel output per unit time of the target steel plant.

[0096] Specifically, the deep neural network is trained multiple times to obtain the trained deep neural network, which is then used as the output of the emission treatment analysis model. The number of training iterations of the deep neural network is positively correlated with the steel output per unit time of the target steel plant, including: 500,000 tons of steel output per unit time for the target steel plant, 800,000 tons of steel output per unit time for the target steel plant, 1,200,000 tons of steel output per unit time for the target steel plant, 1,800,000 tons of steel output per unit time for the target steel plant, and so on.

[0097] Next, the various method embodiments of the present invention will be described in detail.

[0098] In the wastewater zero-discharge treatment method according to various embodiments of the present invention:

[0099] The data includes the target steel plant's steel output per unit time, floor area, number of workers, furnace operating temperature, rolling mill operating temperature, pressure of the rolls used for rolling, billet casting speed during the continuous casting process, upper limit value of steel carbon content, and lower limit value of steel carbon content. These data serve as multiple operational scenario data for the target steel plant, including: the upper limit value of steel carbon content in the target steel plant is 0.35%, and the lower limit value of steel carbon content in the target steel plant is 0.25%.

[0100] The multiple operational scenario data of the target steel plant here reflect the operational scenarios of the target steel plant. If more than one operational scenario data changes, it can be determined that multiple operational scenario data of the target steel plant have changed, and the zero-emission treatment configuration data needs to be re-analyzed.

[0101] The emission treatment analysis model is a deep neural network that has been trained multiple times. The deep neural network includes a single input layer, a single output layer, and multiple hidden layers. The number of times the deep neural network is trained is positively correlated with the steel output per unit time of the target steel plant: the higher the steel output per unit time of the target steel plant, the more times the deep neural network corresponding to the steel output per unit time of the target steel plant is trained.

[0102] And in the wastewater zero-discharge treatment method according to various embodiments of the present invention:

[0103] Each combination of three parameters, multiple operational scenario data of the target steel plant, the production flow rate of the industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant are input into the emission treatment analysis model to obtain the reclaimed water usage ratio and concentrated crystallized solid volume corresponding to each combination of three parameters. This includes: inputting each combination of three parameters, multiple operational scenario data of the target steel plant, the production flow rate of the industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model, and then running the emission treatment analysis model to obtain the reclaimed water usage ratio and concentrated crystallized solid volume output by the emission treatment analysis model corresponding to each combination of three parameters.

[0104] Specifically, the MATLAB toolbox can be used to input each combination of three parameters, multiple operating scenario data of the target steel plant, the production flow rate of the industrial wastewater of the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model. Then, the emission treatment analysis model can be run to simulate and test the data processing process output by the emission treatment analysis model, which corresponds to the proportion of recycled water and the volume of concentrated crystallized solids for each combination of three parameters.

[0105] The process involves inputting each combination of three parameters, multiple operational scenario data of the target steel plant, the production flow rate of the industrial wastewater from the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model. The emission treatment analysis model is then run to obtain the reclaimed water usage ratio and concentrated crystallization solid volume output by the emission treatment analysis model corresponding to each combination of three parameters. This includes performing numerical normalization on each combination of three parameters, multiple operational scenario data of the target steel plant, the production flow rate of the industrial wastewater from the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant before inputting them in parallel into the emission treatment analysis model.

[0106] The process involves inputting each combination of three parameters, multiple operational scenario data of the target steel plant, the production flow rate of the industrial wastewater from the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model. The emission treatment analysis model is then run to obtain the reclaimed water usage ratio and concentrated crystallized solid volume corresponding to each combination of three parameters output by the emission treatment analysis model. Furthermore, the reclaimed water usage ratio and concentrated crystallized solid volume corresponding to each combination of three parameters output by the emission treatment analysis model are both numerical representations after numerical normalization.

[0107] The process of performing numerical normalization on each combination of three parameters, multiple operational scenario data of the target steel plant, production flow rate of industrial wastewater of the target steel plant, and concentrations of organic carbon, inorganic salts, organic salts and macromolecular organic matter in the industrial wastewater generated by the target steel plant before inputting them into the emission treatment analysis model in parallel includes: the numerical normalization process is a binary numerical conversion process.

[0108] The process of performing numerical normalization on each combination of three parameters, multiple operational scenario data of the target steel plant, production flow rate of industrial wastewater of the target steel plant, and concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant before inputting them into the emission treatment analysis model in parallel also includes: using numerical conversion equipment to perform numerical normalization on each combination of three parameters, multiple operational scenario data of the target steel plant, production flow rate of industrial wastewater of the target steel plant, and concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant.

[0109] The process of numerically normalizing each combination of three parameters, multiple operational scenario data of the target steel plant, production flow rate of industrial wastewater from the target steel plant, and concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant before inputting them into the emission treatment analysis model in parallel also includes: using parallel control equipment to input each combination of three parameters after numerical normalization, multiple operational scenario data of the target steel plant, production flow rate of industrial wastewater from the target steel plant, and concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model in parallel.

[0110] The parallel control device is used to input each combination of three parameters after numerical normalization, multiple operating scenario data of the target steel plant, the production flow rate of industrial wastewater of the target steel plant, and the organic carbon concentration, inorganic salt concentration, organic salt concentration and macromolecular organic matter concentration of industrial wastewater generated by the target steel plant into the emission treatment analysis model in parallel. The parallel control device is connected to the numerical conversion device.

[0111] The parallel control device is used to input each combination of three-parameter values ​​after numerical normalization, multiple operating scenario data of the target steel plant, the production flow rate of industrial wastewater of the target steel plant, and the organic carbon concentration, inorganic salt concentration, organic salt concentration and macromolecular organic matter concentration of industrial wastewater generated by the target steel plant into the emission treatment analysis model in parallel. The parallel control device and the numerical conversion device share the same serial configuration interface.

[0112] For example, the parallel control device and the numerical conversion device sharing the same serial configuration interface includes: the parallel control device and the numerical conversion device sharing the same IIC configuration interface, and the parallel control device and the numerical conversion device having different configuration addresses respectively;

[0113] The method employs a parallel control device to input each combination of three-parameter values ​​after numerical normalization, multiple operational scenario data of the target steel plant, the production flow rate of industrial wastewater from the target steel plant, and the concentrations of organic carbon, inorganic salts, organic salts, and macromolecular organic matter in the industrial wastewater generated by the target steel plant into the emission treatment analysis model in parallel. It also employs different types of CPLD chips to implement the parallel control device and the numerical conversion device respectively.

[0114] Furthermore, the present invention may also reference the following technical contents to further demonstrate the outstanding substantial progress of the present invention:

[0115] The emission treatment analysis model is a deep neural network after each training iteration. The deep neural network includes a single input layer, a single output layer, and multiple hidden layers. The number of training iterations of the deep neural network is positively correlated with the steel output per unit time of the target steel plant, including the number of hidden layers in the deep neural network being positively correlated with the steel output per unit time of the target steel plant.

[0116] For example, a positive correlation between the number of hidden layers in a deep neural network and the steel output per unit time of a target steel plant includes: if the steel output per unit time of the target steel plant is 500,000 tons, the number of hidden layers in the deep neural network is 3; if the steel output per unit time of the target steel plant is 800,000 tons, the number of hidden layers in the deep neural network is 4; if the steel output per unit time of the target steel plant is 1,200,000 tons, the number of hidden layers in the deep neural network is 5; if the steel output per unit time of the target steel plant is 1,800,000 tons, the number of hidden layers in the deep neural network is 6, and so on.

[0117] The positive correlation between the number of hidden layers in the deep neural network and the steel output per unit time of the target steel plant also includes: using a data mapping formula to represent the data mapping relationship between the number of hidden layers in the deep neural network and the steel output per unit time of the target steel plant.

[0118] The data mapping formula used to represent the positive correlation between the number of hidden layers in a deep neural network and the steel output per unit time of a target steel plant includes: in the data mapping formula, the steel output per unit time of the target steel plant is the input data of the data mapping formula;

[0119] The data mapping formula used to represent the positive correlation between the number of hidden layers in a deep neural network and the steel output per unit time of the target steel plant includes the following: In the data mapping formula, the number of hidden layers in the deep neural network corresponding to the steel output per unit time of the target steel plant is the output data of the data mapping formula.

[0120] The foregoing description of exemplary embodiments of the invention is provided for illustrative and descriptive purposes. It is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations will obviously be apparent to those skilled in the art. Exemplary embodiments were chosen and described in order to best illustrate the principles of the invention and its practical application, thereby enabling others skilled in the art to understand the various embodiments and variations of the invention suitable for the contemplated particular purpose. The scope of the invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A wastewater zero liquid discharge treatment method, characterized by, The method comprises: obtaining multiple operating scene data of a target steel plant; traversing a numerical combination of specific values of three parameters of a set activated carbon concentration, a set current value and a set membrane thickness to obtain each three-parameter value combination, inputting each three-parameter value combination, the multiple operating scene data of the target steel plant, a production flow of industrial wastewater of the target steel plant, an organic carbon concentration, an inorganic salt concentration, an organic salt concentration and a macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant into a discharge treatment analysis model to obtain a backwater water usage ratio and a concentrated crystallization solid volume corresponding to each three-parameter value combination; taking the three-parameter value combination corresponding to the backwater water usage ratio greater than 99% as zero-discharge treatment configuration data of the discharge treatment mechanism for the industrial wastewater generated by the target steel plant; wherein the multiple operating scene data of the target steel plant is unit time steel production, floor area, number of workers, steelmaking furnace working temperature, rolling mill working temperature, pressure of a rolling roller used for rolling, casting speed of a casting blank in a continuous casting machine drawing process, upper limit value of steel body carbon content and lower limit value of steel body carbon content of the target steel plant; wherein the discharge treatment analysis model is a deep neural network after each training, the deep neural network comprises a single input layer, a single output layer and multiple hidden layers, and the number of times of training of the deep neural network is positively correlated with the unit time steel production of the target steel plant; wherein the number of layers of the hidden layer in the deep neural network is positively correlated with the unit time steel production of the target steel plant, and a data mapping relationship between the number of layers of the hidden layer in the deep neural network and the unit time steel production of the target steel plant is represented by a data mapping formula; wherein the three parameters of the set activated carbon concentration, the set current value and the set membrane thickness are discharge treatment parameters of three different types of devices in the discharge treatment mechanism including an activated carbon adsorption device, an electrodialysis device and a membrane distillation device; wherein in each training of the deep neural network, the backwater water usage ratio and the concentrated crystallization solid volume corresponding to a known certain three-parameter value combination are taken as two output contents of the deep neural network, and the certain three-parameter value combination, the multiple operating scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant are taken as multiple input contents of the deep neural network, and the training of the deep neural network is completed; wherein the data mapping relationship between the number of layers of the hidden layer in the deep neural network and the unit time steel production of the target steel plant is represented by the data mapping formula, and in the data mapping formula, the unit time steel production of the target steel plant is input data of the data mapping formula, and the number of layers of the hidden layer in the deep neural network corresponding to the unit time steel production of the target steel plant is output data of the data mapping formula.

2. The wastewater zero-discharge treatment method according to claim 1, wherein: The set activated carbon concentration is in the range of 0-5 g / L, the set current value is in the range of 5-600 mA, and the set membrane thickness is in the range of 0.1-0.5 mm; Each three-parameter value combination corresponds to a backwater water proportion, which is the percentage of backwater water in the industrial wastewater generated by the target steel plant after the industrial wastewater is treated by the discharge treatment mechanism configured by the three-parameter value combination. Each three-parameter value combination corresponds to a concentrated crystalline solid volume, which is the volume of concentrated crystalline solid obtained after the industrial wastewater generated by the target steel plant is treated by the discharge treatment mechanism configured by the three-parameter value combination.

3. The wastewater zero discharge treatment method of claim 2, wherein the three parameters of the set activated carbon concentration, the set current value, and the set membrane thickness are discharge treatment parameters of three different types of devices in the discharge treatment mechanism, including an activated carbon adsorption device, an electrodialysis device, and a membrane distillation device, and the discharge treatment parameters include: sequentially performing activated carbon adsorption, electrodialysis, and distillation and membrane separation on the industrial wastewater generated by the target steel plant by using the discharge treatment mechanism including the activated carbon adsorption device, the electrodialysis device, and the membrane distillation device to obtain backwater and concentrated crystalline solid, the activated carbon adsorption device uses activated carbon with a set activated carbon concentration of g / L to separate dissolved organic carbon in the industrial wastewater, the electrodialysis device uses a direct current power source with a set current value of mA to separate inorganic salts in the industrial wastewater, and the membrane distillation device uses a reverse osmosis membrane with a set membrane thickness of mm to separate organic salts and macromolecular organic matter in the industrial wastewater. After the three-parameter value combination corresponding to the backwater water proportion greater than 99% is used as the zero discharge treatment configuration data of the discharge treatment mechanism for the industrial wastewater generated by the target steel plant, the method further includes:

4. The wastewater zero liquid discharge treatment method of claim 3, wherein, The specific values of the three parameters of the set activated carbon concentration, the set current value, and the set membrane thickness are configured for the activated carbon adsorption device, the electrodialysis device, and the membrane distillation device of the discharge treatment mechanism by using the zero discharge treatment configuration data; When there is more than one zero discharge treatment configuration data, any zero discharge treatment configuration data is selected to configure the specific values of the three parameters of the set activated carbon concentration, the set current value, and the set membrane thickness for the activated carbon adsorption device, the electrodialysis device, and the membrane distillation device of the discharge treatment mechanism. After the three-parameter value combination corresponding to the backwater water proportion greater than 99% is used as the zero discharge treatment configuration data of the discharge treatment mechanism for the industrial wastewater generated by the target steel plant, the method further includes:

5. The wastewater zero liquid discharge treatment method of claim 3, wherein, The zero discharge treatment configuration data is received and wirelessly transmitted to a remote wastewater zero discharge management server through a wireless communication network. ​ 6. The wastewater zero-discharge treatment method of claim 3, wherein, After taking the three-parameter value combination corresponding to the water return water usage ratio greater than 99% as the zero-discharge treatment configuration data of the discharge treatment mechanism for the industrial wastewater generated by the target steel plant, the method further comprises: Receiving the zero-discharge treatment configuration data and displaying the zero-discharge treatment configuration data on site by using the on-site display mechanism.

7. The wastewater zero liquid discharge treatment method of claim 3, wherein, After taking the three-parameter value combination corresponding to the water return water usage ratio greater than 99% as the zero-discharge treatment configuration data of the discharge treatment mechanism for the industrial wastewater generated by the target steel plant, the method further comprises: When the multiple operating scenario data of the target steel plant changes in value, input the multiple operating scenario data of the target steel plant after the value change into the discharge treatment analysis model to obtain new zero-discharge treatment configuration data corresponding to the multiple operating scenario data of the target steel plant after the value change.

8. The wastewater zero-discharge treatment method of claim 3, wherein, After obtaining the multiple operating scenario data of the target steel plant, the method further comprises: Performing each training on the deep neural network to obtain the deep neural network after completing each training and outputting the deep neural network as the discharge treatment analysis model, and the number of times of training of the deep neural network is positively correlated with the unit time steel production of the target steel plant.

9. The wastewater zero-discharge treatment method of any one of claims 3-8, wherein: The unit time steel production, the floor area, the number of workers, the steelmaking furnace working temperature, the rolling mill working temperature, the roll pressure for rolling, the casting speed of the casting blank in the continuous casting machine drawing process, the upper limit value of the steel body carbon content, and the lower limit value of the steel body carbon content of the target steel plant are obtained as the multiple operating scenario data of the target steel plant, including: the upper limit value of the steel body carbon content of the target steel plant is 0.35%, and the lower limit value of the steel body carbon content of the target steel plant is 0.25%; Wherein, the discharge treatment analysis model is the deep neural network after completing each training, the deep neural network includes a single input layer, a single output layer and multiple hidden layers, and the number of times of training of the deep neural network is positively correlated with the unit time steel production of the target steel plant, including: the more the unit time steel production of the target steel plant, the more the number of times of training of the deep neural network corresponding to the unit time steel production of the target steel plant.

10. The wastewater zero-discharge treatment method of any one of claims 3-8, wherein: inputting each of the three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant into the discharge treatment analysis model to obtain the backwater water usage ratio and the concentrated crystallization solid volume corresponding to each of the three-parameter value combination output by the discharge treatment analysis model includes: after inputting each of the three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant into the discharge treatment analysis model, running the discharge treatment analysis model to obtain the backwater water usage ratio and the concentrated crystallization solid volume corresponding to each of the three-parameter value combination output by the discharge treatment analysis model; wherein, after inputting each of the three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant into the discharge treatment analysis model, running the discharge treatment analysis model to obtain the backwater water usage ratio and the concentrated crystallization solid volume corresponding to each of the three-parameter value combination output by the discharge treatment analysis model includes: after performing numerical normalization processing on each of the three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant, respectively, and then inputting them into the discharge treatment analysis model in parallel; wherein, after inputting each of the three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant into the discharge treatment analysis model, running the discharge treatment analysis model to obtain the backwater water usage ratio and the concentrated crystallization solid volume corresponding to each of the three-parameter value combination output by the discharge treatment analysis model also includes: the backwater water usage ratio and the concentrated crystallization solid volume corresponding to each of the three-parameter value combination output by the discharge treatment analysis model are in the form of numerical values after numerical normalization processing; wherein, after performing numerical normalization processing on each of the three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant, respectively, and then inputting them into the discharge treatment analysis model in parallel includes: the numerical normalization processing is binary numerical conversion processing; Wherein, the numerical normalization processing of each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant are performed respectively before being input into the discharge treatment analysis model in parallel, further comprising: using a numerical conversion device to perform the numerical normalization processing of each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant; Wherein, the numerical normalization processing of each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant are performed respectively before being input into the discharge treatment analysis model in parallel, further comprising: using a parallel control device to input each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant, which have been processed by numerical normalization, into the discharge treatment analysis model in parallel; Wherein, using a parallel control device to input each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant, which have been processed by numerical normalization, into the discharge treatment analysis model in parallel comprises that the parallel control device is connected with the numerical conversion device; Wherein, using a parallel control device to input each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant, which have been processed by numerical normalization, into the discharge treatment analysis model in parallel further comprises that the parallel control device and the numerical conversion device share the same serial configuration interface; Wherein, using a parallel control device to input each three-parameter value combination, the multiple running scene data of the target steel plant, the production flow of the industrial wastewater of the target steel plant, the organic carbon concentration, the inorganic salt concentration, the organic salt concentration and the macromolecular organic matter concentration of the industrial wastewater generated by the target steel plant, which have been processed by numerical normalization, into the discharge treatment analysis model in parallel further comprises that different types of CPLD chips are used to realize the parallel control device and the numerical conversion device respectively.

Images