Method and device for controlling operation of sewage electrolysis device, electronic equipment and medium

Abstract

The application provides a sewage electrolysis device operation control method and device, electronic equipment and medium. The method comprises the following steps: S1: setting circulation flow parameters of multiple groups of sewage electrolysis devices, and obtaining corresponding input parameters; S2: inputting the parameters in step S1 into a preset neural network model to predict electronic efficiency of electrolytic removal of organic matter and output; obtaining a maximum value in the electronic efficiency prediction value; S3: calculating an actual value of the electronic efficiency of electrolytic removal of organic matter under the maximum value of the electronic efficiency prediction value, and an error between the electronic efficiency prediction value and the actual value of the electronic efficiency under the circulation flow condition; S4: stopping iteration when the error meets a preset condition, and taking the circulation flow value under the condition of the maximum value in the electronic efficiency prediction value as an optimal circulation flow parameter; otherwise, returning to iteration; and S5: performing electrolysis operation on sewage with the optimal circulation flow parameter. The application can solve the problem of how to accurately balance and control the degree of oxidative degradation of organic pollutants.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water treatment, in particular to a sewage electrolysis device operation control method and device, electronic equipment and medium. BACKGROUND

[0002] Electrolytic oxidation is a kind of advanced oxidation technology for degrading organic matter and ammonia nitrogen in water. The use of different electrode materials and different structures has always been a research hotspot. Among them, boron-doped diamond-coated electrodes can operate at a higher voltage without mainly generating oxygen evolution reaction when degrading organic matter due to their extremely high oxygen evolution potential and extremely low hydrogen evolution potential, thus having higher organic matter degradation efficiency and wider organic matter degradation capacity. In practical engineering applications, since boron-doped diamond-coated electrodes are very expensive, it is one of the main considerations to maximize the water treatment capacity per unit area of the electrode and reduce the investment cost of the electrode. Excessive electrolysis not only wastes energy to produce additional hydrogen and chlorine, but also leads to excessive oxidation in the effluent, manifested as high oxidation-reduction potential and high residual chlorine content, which seriously endangers the safety of subsequent treatment equipment such as membrane filtration, adsorption resin, and ion exchange resin. Therefore, how to accurately balance and control the degree of oxidative degradation of organic pollutants and avoid excessive electrolysis is a pressing problem. SUMMARY

[0003] The present application provides a sewage electrolysis device operation control method and device, electronic equipment and medium to solve the problem of how to accurately balance and control the degree of oxidative degradation of organic pollutants.

[0004] In a first aspect, the present application provides a sewage electrolysis device operation control method, comprising the following steps:

[0005] S1: setting the circulation flow rate parameters of multiple groups of sewage electrolysis devices, and obtaining one or more of the corresponding voltage, current, power consumption, influent flow rate, influent organic matter content, influent oxidation-reduction potential, effluent organic matter content, and effluent oxidation-reduction potential parameters;

[0006] S2: inputting the parameters in step S1 into a preset neural network model to predict the electronic efficiency of electrolytic removal of organic matter, outputting an electronic efficiency prediction value, and obtaining the maximum value of the electronic efficiency prediction value;

[0007] S3: calculating the actual value of the electronic efficiency of electrolytic removal of organic matter under the maximum value of the circulation flow rate of the electronic efficiency prediction value, and the error between the electronic efficiency prediction value and the actual value of the electronic efficiency under this condition;

[0008] S4: stopping iteration when the error meets a preset condition, and taking the circulation flow value under the maximum value in the electronic efficiency prediction value as the optimal circulation flow parameter; otherwise, discarding the maximum value, selecting the maximum value in the remaining electronic efficiency prediction value, and returning to step S3 for iteration;

[0009] S5: adjusting the circulation flow parameter of the sewage electrolysis device to the optimal circulation flow parameter, and performing electrolysis operation on sewage.

[0010] Preferably, in step S1, a plurality of circulation flow parameters of the sewage electrolysis device are set, including setting a basic circulation flow value and selecting a plurality of values uniformly distributed before and after the basic circulation flow value as circulation flow setting values, wherein the basic circulation flow value and the circulation flow setting values together constitute the plurality of circulation flow parameters of the sewage electrolysis device.

[0011] Preferably, in step S1, one or more of the corresponding voltage, current, power consumption, inflow, inflow organic matter content, inflow oxidation-reduction potential, outflow organic matter content, and outflow oxidation-reduction potential parameters are obtained, including: the inflow organic matter content and the outflow organic matter content are obtained by sampling and testing, the inflow is obtained by online flow meter metering, the inflow oxidation-reduction potential and the outflow oxidation-reduction potential are obtained by oxidation-reduction potential analyzer measurement; the voltage, current and power consumption are obtained by measuring the ammeter.

[0012] Preferably, in step S2, the preset neural network model is an error back propagation neural network model.

[0013] Preferably, the error back propagation neural network model comprises two hidden layers and a P-ReLU activation function.

[0014] Preferably, the learning rate of the two hidden layers is adaptively adjusted using the Adam algorithm.

[0015] Preferably, at least the current, inflow, inflow organic matter content, and outflow organic matter content parameters are obtained; in step S3, the inflow organic matter content is the inflow chemical oxygen demand, and the outflow organic matter content is the outflow chemical oxygen demand.

[0016] The calculation formula of the actual value of the electronic efficiency η is:

[0017]

[0018] Wherein, N A is the Avogadro constant, e is the electric charge carried by the elementary charge, I is the current, F is the inflow, COD in is the inflow chemical oxygen demand, COD out is the outflow chemical oxygen demand.

[0019] In a second aspect of the present application, a sewage electrolysis device is provided, comprising:

[0020] The parameter acquisition module is configured to acquire a circulation flow parameter value and acquire one or more of the following parameter values: a corresponding voltage, a current, an electricity consumption, an inflow, an inflow organic matter content, an inflow oxidation-reduction potential, an outflow organic matter content, and an outflow oxidation-reduction potential parameter.

[0021] The prediction module is configured to store a preset neural network model and predict an electronic efficiency of electrolytic removal of organic matter, and output an electronic efficiency prediction value.

[0022] The calculation module is configured to acquire a maximum value in the electronic efficiency prediction value, calculate an actual value of the electronic efficiency of electrolytic removal of organic matter under a circulation flow condition of the maximum value in the electronic efficiency prediction value, and calculate an error between the electronic efficiency prediction value and the actual value of the electronic efficiency under the circulation flow condition.

[0023] The judgment module is configured to judge whether the error meets a preset condition.

[0024] The adjustment module is configured to change the circulation flow parameter when the error does not meet the preset condition, and adjust the circulation flow parameter to an optimal circulation flow parameter when the error meets the preset condition, and perform electrolysis operation on the sewage.

[0025] In a third aspect of the present application, an electronic device is provided, comprising:

[0026] a processor; and

[0027] a memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method.

[0028] In a fourth aspect of the present application, a non-transitory machine-readable storage medium is provided, having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method.

[0029] The technical solution of the present application achieves the following technical effects:

[0030] The present application can solve the problems of low electronic efficiency of electrolytic degradation of organic matter, excessive byproduct reaction residual chlorine, and inaccurate adjustment and control, and can obtain a higher electronic efficiency and finely control the electrolysis degree. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below only are a part of the embodiments of the present application, and all other drawings obtained by those of ordinary skill in the art without creative effort based on the provided drawings are within the scope of the present application.

[0032] Figure 1 A flowchart of a sewage electrolytic device operation control method according to an embodiment of the present application is shown;

[0033] Figure 2 A schematic diagram of a sewage electrolytic device operation control principle according to an embodiment of the present application is shown;

[0034] Figure 3(a) shows a top view of an electrode assembly according to Embodiment One of the present application;

[0035] Figure 3(b) shows a side view of an electrode assembly according to Embodiment One of the present application;

[0036] Figure 4(a) shows a top view of an electrode assembly according to Embodiment Two of the present application;

[0037] Figure 4(b) shows a side view of an electrode assembly according to Embodiment Two of the present application;

[0038] Figure 5 A schematic diagram of a sewage electrolytic device structure according to an embodiment of the present application is shown;

[0039] Figure 6 A schematic diagram of an electronic device structure according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present application more clear, the following will clearly and completely describe the technical solutions of the present application with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of the present application.

[0041] The sewage electrolytic device operation control method provided by the present application, referring to Figure 1 , includes the following steps:

[0042] S1: setting the circulation flow rate parameters of multiple groups of sewage electrolytic devices, and obtaining one or more of the corresponding voltage, current, power consumption, influent flow rate, influent organic matter content, influent oxidation-reduction potential, effluent organic matter content, and effluent oxidation-reduction potential parameters;

[0043] In an embodiment of the present application, in the step S1, the circulation flow rate parameters of the multiple sets of sewage electrolytic devices are set, including setting a basic circulation flow rate value, selecting multiple values uniformly distributed before and after the value of the basic circulation flow rate value as circulation flow rate setting values, and the basic circulation flow rate value and the circulation flow rate setting values together constitute the circulation flow rate parameters of the multiple sets of sewage electrolytic devices.

[0044] In an embodiment of the present application, in the step S1, one or more of the corresponding voltage, current, power consumption, inflow flow rate, inflow organic matter content, inflow oxidation-reduction potential, outflow organic matter content, and outflow oxidation-reduction potential parameters are obtained; including that the inflow organic matter content and the outflow organic matter content are obtained by sampling and testing, the inflow flow rate is obtained by metering with an online flow meter, the inflow oxidation-reduction potential and the outflow oxidation-reduction potential are obtained by measurement with an oxidation-reduction potential analyzer; and the voltage, current, and power consumption are obtained by measurement with an electric meter. Further, the online monitoring instrument or the hyperspectral detection equipment or the sampling and testing are used to monitor the inflow and outflow organic matter content of the electrolytic device, the organic matter index can be COD (oxygen demand) or TOC (total organic carbon), the online flow meter or the water pump with a flow meter is used to meter the inflow and circulation water quantity, and the oxidation-reduction potential analyzer is used to measure the inflow and outflow oxidation-reduction potential.

[0045] S2: inputting the parameters in the step S1 into a preset neural network model to predict the electronic efficiency of electrolytic removal of organic matter, outputting an electronic efficiency prediction value, and obtaining a maximum value in the electronic efficiency prediction value;

[0046] In an embodiment of the present application, in the step S2, the preset neural network model is an error back propagation neural network model.

[0047] In an embodiment of the present application, the error back propagation neural network model includes two hidden layers and a P-ReLU activation function. The number of nodes of the hidden layers, the number of partitions, and the learning rate are determined according to the input parameters, the output parameters, and the training condition.

[0048] In an embodiment of the present application, the learning rate of the two hidden layers is self-adaptively adjusted using an Adam algorithm.

[0049] S3: calculating the electronic efficiency actual value of electrolytic removal of organic matter under the condition of the maximum value of the electronic efficiency prediction value, and the error between the electronic efficiency prediction value and the electronic efficiency actual value under the condition;

[0050] In an embodiment of the present application, at least the current, inflow flow rate, inflow organic matter content, and outflow organic matter content parameters are obtained; in the step S3, the inflow organic matter content is the inflow chemical oxygen demand, and the outflow organic matter content is the outflow chemical oxygen demand.

[0051] The calculation formula of the actual value of the electron efficiency is:

[0052]

[0053] Wherein, N A is the Avogadro constant, e is the electric charge carried by the elementary charge, I is the current, F is the water flow, COD in is the organic matter content of the influent, COD out is the chemical oxygen demand of the effluent.

[0054] S4: when the error meets the preset condition, stop iteration, and take the circulation flow value under the maximum value of the predicted value of the electron efficiency as the optimal circulation flow parameter; otherwise, discard the maximum value, select the maximum value of the remaining predicted values of the electron efficiency, return to step S3, and iterate;

[0055] In an embodiment of the present application, when the error meets the preset condition, the iteration is stopped, wherein the preset condition can be a set threshold condition. When the error is less than the preset threshold, for example, the preset threshold is 1%, when the error is less than 1%, it means that the error between the actual value and the predicted value of the electron efficiency reaches the allowable range error, at this time, the iteration is stopped, and the maximum value of the electron efficiency in the error allowable range is obtained.

[0056] Therefore, the accuracy of the predicted value of the electron efficiency parameter of the electrolytic removal of organic matter is corrected by comparing the actual value and the predicted value of the electron efficiency.

[0057] S5: the circulation flow parameter of the sewage electrolysis device is adjusted to the optimal circulation flow parameter, and the sewage is subjected to electrolysis operation.

[0058] In this step, according to the circulation flow parameter corresponding to the maximum value of the electron efficiency in the error allowable range and other operating parameters under the circulation flow parameter condition, including one or more of the voltage, current, power consumption, influent flow, influent organic matter content, influent oxidation-reduction potential, effluent organic matter content, effluent oxidation-reduction potential parameter, the sewage electrolysis device is adjusted and the sewage is subjected to electrolysis operation.

[0059] The operation control principle of the sewage electrolysis device of the present application is described with reference to Figure 2, the sewage is sequentially discharged from the circulating pool and the electrolytic device, wherein the circulating pool and the discharge link are connected to the online monitoring equipment, the online monitoring equipment inputs the measured parameters into the error back propagation neural network model to predict the electronic efficiency of organic matter removal, and selects the circulating flow corresponding to the optimal predicted electronic efficiency as the set value to adjust the circulating flow to the set value for electrolysis. When obtaining the optimal electronic efficiency, the maximum predicted electronic efficiency is compared with the actual electronic efficiency under the corresponding circulating flow parameter, and when the error meets the set threshold, the maximum value is taken as the optimal electronic efficiency; otherwise, the value is discarded, the second maximum predicted electronic efficiency is selected, the actual electronic efficiency under the corresponding circulating flow value is calculated, and the above steps are repeated until the error meets the set threshold. Further, the optimal circulating flow value can be returned to the error back propagation neural network model as an input sample.

[0060] In an embodiment of the present application, the sewage electrolysis device operation control method comprises:

[0061] Step 110: obtaining the voltage, current, power consumption, inflow, inflow COD, inflow redox potential, circulating flow parameter, outflow COD, and outflow redox potential of the sewage electrolysis treatment.

[0062] Preferably, the sewage in this step is refractory organic wastewater, and the parameters can be obtained by sampling, online monitoring equipment, etc.

[0063] Step 120: inputting a plurality of sets of circulating flow set values corresponding to the parameters into the error back propagation neural network model to predict the electronic efficiency of electrolytic removal of organic matter according to different circulating flow set values, and adjusting and controlling the circulating flow according to the circulating flow set value corresponding to the highest predicted electronic efficiency of electrolytic removal of organic matter.

[0064] Step 130: calculating the actual value of the electronic efficiency parameter of electrolytic removal of organic matter using the current, inflow, inflow COD, and outflow COD under the current circulating flow to correct the accuracy of the predicted value of the electronic efficiency parameter of electrolytic removal of organic matter, and performing model self-optimization.

[0065] It should be noted that the input parameters can be partial or total.

[0066] By Figure 2 The disclosed method can realize automatic and fine control of the electrolytic circulating flow parameter, and improve the electrolytic efficiency.

[0067] In one embodiment, according to the current circulation flow value, 20 circulation flow set values are set around the value with a deviation of 1% to 10%, a total of 21 numbers including the current circulation flow value, and the predicted value of the electronic efficiency of electrolytic removal of organic matter corresponding to each value is output. The circulation flow set value with the highest predicted value of the electronic efficiency of electrolytic removal of organic matter is compared with the corresponding actual value in order from large to small, and the error is calculated. The circulation flow corresponding to the maximum electronic efficiency in the error range is taken as the circulation flow control value for feedback control. It should be noted that the selection of the deviation range and the number of circulation flow set values involved in the calculation and comparison can be adjusted.

[0068] In a preferred embodiment, the input of the error back propagation neural network prediction model is voltage, current, power consumption, influent flow, influent COD, influent oxidation-reduction potential, and circulation flow, and the output is the predicted value of the electronic efficiency of electrolytic removal of organic matter. The first layer of the hidden layer has 9 nodes, and the second layer has 9 nodes. The learning rate of the two layers is adaptively adjusted using the Adam algorithm. The model is operated in the mode of offline training using historical data and regular updating.

[0069] After the method is applied for a period of time, the electronic efficiency of electrolytic removal of organic matter can be stably controlled at more than 40%, and the average reaches more than 45%.

[0070] Further, the application also shows a structure of an electrode assembly of a sewage electrolysis device, which comprises: an electrode pair, the electrode pair is arranged in groups in the transverse direction, and multiple groups of electrode pairs are arranged in rows in the vertical direction;

[0071] The influent flows through the electrode pairs in sequence, the next group of electrode pairs has opposite arrangement directions of the anode and the cathode to the previous group of electrode pairs, the electrodes in the next row of electrode pairs have opposite polarities to the electrodes in the previous row of electrode pairs, and the next row of electrodes has an angle of 0-180 degrees with the previous row of electrodes. Further, the voltage value / current value / current density of the electrolytic oxidation device can be set according to the determined influent flow, chemical organic matter content value, oxidation-reduction potential value, target chemical organic matter content value after electrolytic oxidation, and effective electrode plate area of the electrolytic device.

[0072] Optionally, the electrode plate coating material is preferably boron-doped diamond, the coating thickness is preferably 2-10 microns, and the electrode plate substrate is preferably a silicon plate or a niobium plate, and the substrate thickness is preferably 0.5-2 millimeters.

[0073] Optionally, the electrode plate spacing is 0.1mm-5mm, when the electrode plate spacing is less than 2mm, an insulating support layer can be filled between the electrode plates, the support layer type is parallel linear, net-like, or parallel plate-like, and the net-like type is preferred; the support layer material is polytetrafluoroethylene, polyvinylidene fluoride, polysulfone, polysulfone modified material, etc., and the polysulfone material is preferred.

[0074] Optionally, each electrode can be double-sided coated when using multiple sets of electrode pairs in each row and reversing the polarity; the anode can be double-sided coated and the cathode can use electrodes of non-coated material when using multiple sets of electrode pairs in each row and not reversing the polarity; each electrode can be single-sided coated when using only one set of electrode pairs in each row and reversing the polarity; the anode can use single-sided coated electrodes and the cathode can use electrodes of non-coated material when using only one set of electrode pairs in each row and not reversing the polarity. Since coated plates are costly, the present application only coats as necessary to maximize the amount of water treated per unit area of plate and reduce the cost of plate investment.

[0075] Reversing the polarity means reversing the polarity of the electrodes, i.e. reversing the polarity of the anode and cathode. During electrolysis, the use of electrodes over a long period of time can form contaminants on the surface of the electrodes, affecting the efficiency of electrolysis and reducing the service life of the electrodes. Therefore, the polarity of the two electrodes can be reversed to prevent or reduce the formation of contaminants on the surface of the electrodes, which is beneficial to maintaining the electrolysis efficiency and service life of the electrodes.

[0076] Optionally, flow guide components can be installed between the electrodes along the direction of the flow channel.

[0077] The presence of a high concentration of salt in wastewater is beneficial to improving the mass transfer and reaction efficiency of electrolytic degradation of organic matter. However, in the electrolysis process, the degradation of organic matter and the generation of chlorine gas, residual chlorine and other side reactions are in competition with each other. The acidic conditions formed locally at the anode are conducive to the generation of chlorine gas. The chlorine evolution potential is significantly reduced under acidic conditions, and the generation of chlorine gas and residual chlorine can become the main reaction. Through the design of the present application, the acidic conditions formed locally at the anode are rapidly pushed to the cathode of the next pair of plates, and the angle between the two sets of plates destroys the stable laminar flow state, significantly improving the mass transfer efficiency and inhibiting the formation and accumulation of local acidic environments. Thus, the generation of chlorine gas and residual chlorine in the electrolysis reaction is inhibited, the competitiveness of the electrolytic degradation of organic matter reaction is improved, the power consumption for electrolytic degradation of organic matter is reduced, the residual chlorine content of the effluent is reduced, and the consumption of reagents for removing residual chlorine is reduced.

[0078] The present application will be further described below in conjunction with the embodiments.

[0079] Embodiment 1

[0080] Please refer to FIG. 3(a) and FIG. 3(b), which show a structure of an electrode assembly of an electrolytic device, which includes three rows of one set of electrode pairs from top to bottom;

[0081] The embodiment takes coking wastewater as the object of sewage treatment. The influent flows through the paired electrodes in turn. The next electrode pair is opposite to the previous electrode pair in the arrangement direction of the anode and the cathode and forms a 10-degree angle with the previous electrode pair. Each row has a set of electrode pairs, including a pair of electrodes. According to the measured values of the influent flow rate, the chemical oxygen demand, the oxidation-reduction potential, the target value of the chemical oxygen demand after electrolytic oxidation, and the effective electrode area of the electrolytic device, the voltage value and the current density of the electrolytic oxidation device are controlled. The voltage value is controlled to be 4.5V-5.5V, and the current density is controlled to be 30-120mA / cm 2 .

[0082] The anode plate 506 of the electrode plate is a silicon-based single-sided boron-doped diamond with a coating thickness of 2 microns and a silicon substrate thickness of 2 millimeters. The cathode plate is stainless steel, and the electrode plate spacing is 3mm. The electrode cannot be reversed.

[0083] The influent chemical oxygen demand and the effluent chemical oxygen demand of the electrolytic device are monitored by sampling and testing. The influent flow rate and the circulation flow rate are measured using an online flow meter, and the influent oxidation-reduction potential and the effluent oxidation-reduction potential are measured using an oxidation-reduction potential analyzer.

[0084] According to the current circulation flow rate value, 20 circulation flow rate set values are given, each of which is offset by 1% to 10% around the value. Add the current circulation flow rate value to get a total of 21 numbers. The predicted value of the electronic efficiency of electrolytic removal of organic matter corresponding to each value is output. According to the circulation flow rate set value with the highest predicted value of the electronic efficiency of electrolytic removal of organic matter, the actual value of the electronic efficiency corresponding to each value is compared from large to small, and the error is calculated. The circulation flow rate corresponding to the maximum value of the electronic efficiency within the error range is used as the circulation flow rate control value for feedback control.

[0085] The error backpropagation neural network prediction model includes at least two hidden layers and a P-ReLU activation function. The kaiming parameter initialization method is used. The input items of the model are voltage, current, power consumption, influent flow rate, influent chemical oxygen demand, influent oxidation-reduction potential, and circulation flow rate. The output item is the predicted value of the electronic efficiency of electrolytic removal of organic matter. The first layer of the hidden layer has 7 nodes, and the second layer has 4 nodes. The learning rate of both layers is set to α, and the default value is 0.1. The model can be trained offline using historical data and updated regularly.

[0086] The error backpropagation neural network prediction model is optimized using the above parameter values. The actual current I, the influent flow rate F, the influent chemical oxygen demand COD in , the effluent chemical oxygen demand COD out , and the electronic efficiency η parameter actual value of electrolytic removal of organic matter are calculated to correct the accuracy of the predicted value of the electronic efficiency parameter of electrolytic removal of organic matter.

[0087] The formula for calculating the actual value of the electron efficiency parameter of electrolytic removal of organic matter is:

[0088]

[0089] wherein N A is the Avogadro constant, and e is the electric quantity carried by the elementary charge.

[0090] The following table records the electron efficiency values of electrolytic removal of organic matter under different water inlet types and parameter conditions in this embodiment. It can be concluded that after the method is applied for 2 months, the electron efficiency of electrolytic removal of organic matter in coking wastewater can be stably controlled above 40%, and the power consumption for removing 1 kg of COD is 30-40 kwh / kgCOD.

[0091]

[0092] Example 2

[0093] Please refer to FIG. 4(a) and FIG. 4(b), which show another electrode assembly structure form of the electrolytic device, which includes three rows from top to bottom, each row including two groups of electrode pairs (one group in the first row and the second row from top to bottom, and another group in the third row and the fourth row), each group of electrode pairs containing one or more pairs of electrodes, which are set to five pairs of electrodes in this embodiment; further, among the five electrodes of each row, one single electrode (anode 506 plate or cathode 507 plate) can be included at the end, and two sensing plates are included, one end of which is an anode 506 and the other end of which is a cathode 507. In specific implementation, the remaining electrodes can be arranged according to the polarity of the first single electrode, for example, the first electrode in the first row of the first group is a single anode, and the second and third electrodes are set as sensing electrodes and are cathodes and anodes respectively, the fourth and fifth electrodes are set as sensing electrodes and are cathodes and anodes respectively, the first and second electrodes in the second row of the first group are set as sensing electrodes and are cathodes and anodes respectively, the third and fourth electrodes are set as sensing electrodes and are cathodes and anodes respectively, and the fifth electrode is a single electrode and is a cathode. The remaining rows are arranged according to the above arrangement principle, and details are shown in FIG. 3, which will not be described here.

[0094] In this embodiment, sintering acid-making wastewater is taken as the treatment object, and the influent sequentially flows through the paired sensing electrodes. The anode and cathode arrangement directions of the next group of electrode pairs and the previous group of electrode pairs are opposite, the anode and cathode arrangement directions of the next row of electrode pairs and the previous row of electrode pairs are also opposite, and the next row and the previous row of electrodes form an angle of 6 degrees. There are five pairs of electrodes in each group. According to the measured values of the flow rate, the chemical oxygen demand, the oxidation-reduction potential, the chemical oxygen demand target value after electrolytic oxidation, and the effective plate area of the electrolytic device, the voltage value and the current density of the electrolytic oxidation device are controlled; the voltage value is controlled at 4.2V-5.2V, and the current density is controlled at 30-100mA / cm 2 .

[0095] The electrode plate anode and cathode are both niobium-based double-sided boron-doped diamond with a coating thickness of 8 microns and a niobium substrate thickness of 1 millimeter, and the electrode plate spacing is 2 mm, and the electrode plate can be operated in reverse.

[0096] The influent chemical oxygen demand and effluent chemical oxygen demand of the electrolysis device are monitored online, the influent flow and circulation flow are measured by an online flow meter, and the influent oxidation-reduction potential and effluent oxidation-reduction potential are measured by a redox potential analyzer.

[0097] According to the current circulation flow value, 20 circulation flow set values are given around the value with a deviation of 1% to 10%, and 21 numbers are added to the current circulation flow value, and the predicted value of the electronic efficiency of electrolytic removal of organic matter corresponding to each value is output, and the circulation flow set value with the highest predicted value of the electronic efficiency of electrolytic removal of organic matter is compared with the corresponding actual value from large to small and the error is calculated, and the circulation flow corresponding to the maximum value of the electronic efficiency in the error range is taken as the circulation flow control value for feedback control.

[0098] The error back propagation neural network prediction model includes at least two hidden layers and a P-ReLU activation function, uses the kaiming parameter initialization method, the model input items are voltage, current, power consumption, influent flow, influent chemical oxygen demand, influent oxidation-reduction potential, and circulation flow, and the output item is the predicted value of the electronic efficiency of electrolytic removal of organic matter, the first layer of the hidden layer has 9 nodes, the second layer has 9 nodes, and the learning rate of the two layers is adaptively adjusted using the Adam algorithm. Run in the way of using historical data offline training and regularly updating the model.

[0099] Of course, this application only shows a way of using an error back propagation neural network prediction model, which is only a data analysis tool for completing the control method of this application, and existing data analysis software such as SPSSPRO can also be used to directly set input and output parameters, the number of nodes in each layer, learning rate, etc.

[0100] The error back propagation neural network prediction model is optimized using the parameter values, and the actual current I, influent flow F, influent chemical oxygen demand COD in , effluent chemical oxygen demand COD out The electronic efficiency η parameter actual value of electrolytic removal of organic matter is calculated, and the accuracy of the predicted value of the electronic efficiency parameter of electrolytic removal of organic matter is corrected.

[0101] After the method is applied for 3 months, the electronic efficiency of electrolytic removal of organic matter of sintering acid wastewater can be stably controlled at more than 42%.

[0102] Of course, the above structure is only a preferred embodiment of the present application, and the electrode pairs can be arranged in one row, or arranged in multiple rows up and down; arranged in one group or multiple groups in the lateral direction; and each group of electrode pairs can be one pair or multiple pairs of electrodes.

[0103] The present application also provides a sewage electrolysis device 5, comprising:

[0104] The parameter acquisition module 501 is configured to acquire a circulation flow parameter value and acquire one or more of the following parameter values: a corresponding voltage, a current, an electricity consumption, an inflow flow rate, an inflow organic matter content, an inflow oxidation-reduction potential, an outflow organic matter content, and an outflow oxidation-reduction potential.

[0105] The prediction module 502 is configured to store a preset neural network model and predict an electronic efficiency of electrolytic removal of organic matter, and output an electronic efficiency prediction value.

[0106] The calculation module 503 is configured to acquire a maximum value in the electronic efficiency prediction value; and calculate an actual value of the electronic efficiency of electrolytic removal of organic matter under a circulation flow condition of the maximum value in the electronic efficiency prediction value, and an error between the electronic efficiency prediction value and the actual value of the electronic efficiency under the condition.

[0107] The judgment module 504 is configured to judge whether the error meets a preset condition.

[0108] The adjustment module 505 is configured to change the circulation flow parameter when the error does not meet the preset condition; and adjust the circulation flow parameter to an optimal circulation flow parameter when the error meets the preset condition, and perform an electrolysis operation on the sewage.

[0109] The present application also provides an electronic device, such as Figure 6 As shown in the figure, the electronic device 600 includes a memory 610 and a processor 620.

[0110] The processor 620 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0111] The memory 610 can include various types of storage units, such as a system memory, a read-only memory (ROM), and a permanent storage device. Among them, the ROM can store static data or instructions required by the processor 620 or other modules of the computer. The permanent storage device can be a read-write storage device. The permanent storage device can be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a mass storage device (such as a magnetic or optical disk, a flash memory) as a permanent storage device. In some other embodiments, the permanent storage device can be a removable storage device (such as a floppy disk, an optical drive). The system memory can be a read-write storage device or a volatile read-write storage device, such as a dynamic random access memory. The system memory can store some or all of the instructions and data required by the processor during runtime. In addition, the memory 610 can include a combination of any computer readable storage media, including various types of semiconductor storage chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks and / or optical disks. In some embodiments, the memory 610 can include a read and / or write removable storage device, such as a compact disc (CD), a read-only digital versatile disc (such as DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a min SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer readable storage medium does not include a carrier wave and an instantaneous electronic signal transmitted by wireless or wired transmission.

[0112] The memory 610 stores executable code, which, when processed by the processor 620, can cause the processor 620 to perform part or all of the above-mentioned methods.

[0113] The solutions of the present application have been described in detail above with reference to the accompanying drawings. In the above-described embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments. It should also be appreciated by those skilled in the art that the actions and modules involved in the specification are not necessarily required by the present application. In addition, it can be understood that the steps in the method embodiments of the present application can be adjusted, combined and reduced in sequence according to actual needs, and the modules in the device embodiments of the present application can be combined, divided and reduced according to actual needs.

[0114] In addition, the method according to the present application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing part or all of the steps in the above-mentioned methods of the present application.

[0115] Alternatively, the application can also be implemented as a non-transitory machine readable storage medium (or computer readable storage medium, or machine readable storage medium) on which executable code (or computer program, or computer instruction code) is stored, and when the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor is caused to perform part or all of the steps of the above method according to the application.

[0116] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the present disclosure can be implemented as electronic hardware, computer software, or combinations of both.

[0117] The flow diagrams and block diagrams in the drawings are representative of the architecture, functionality, and operation of possible implementations of systems and methods according to the present disclosure. In this regard, each block in the flow diagrams and block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may be executed in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0118] It should be understood that, for brevity and clarity of the present application, and for the purpose of helping to understand one or more of the various application aspects, in the above description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description of a figure. However, this method of disclosure should not be interpreted as reflecting a necessity that the application requires more features than are explicitly recited in each claim. Rather, inventive aspects lie in fewer than all features of a single disclosed embodiment. Thus, the claims following, refraining from the specific description of the embodiments, expressly incorporate the entire disclosure of the application as a part of the claims. Thus, the claims following, the specific description of the embodiments, expressly incorporate the entire disclosure of the application as a part of the claims.

[0119] Those skilled in the art will appreciate that the modules in the apparatuses in the embodiments can be adapted and placed in one or more apparatuses other than that of the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and furthermore can be split into multiple sub-modules or sub-units or sub-components. Any combination of all the features disclosed in the present specification (including the accompanying claims, abstract and drawings), and any method or process of any combination of the features disclosed in the present specification (including the accompanying claims, abstract and drawings) can be adopted unless expressly stated otherwise. Each feature disclosed in the present specification (including the accompanying claims, abstract and drawings) can be replaced by alternative features providing the same, equivalent or similar function unless expressly stated otherwise.

[0120] Furthermore, those skilled in the art will appreciate that the features of the different embodiments described herein can be combined in any combination, which is meant to be within the scope of the application and forms different embodiments. For example, in the following claims, any of the embodiments can be used in any combination.

Claims

1. A method for operating control of a wastewater electrolysis device, characterized by, The method comprises the following steps: S1: setting the circulation flow rate parameters of multiple groups of sewage electrolytic devices, and obtaining corresponding voltage, current, power consumption, influent flow rate, influent organic matter content, influent oxidation-reduction potential, effluent organic matter content, and effluent oxidation-reduction potential parameters; S2: inputting the parameters in step S1 into an error back propagation neural network model to predict the electron efficiency of electrolytic removal of organic matter, outputting an electron efficiency prediction value, and obtaining a maximum value in the electron efficiency prediction value; S3: calculating the actual value of the electron efficiency of electrolytic removal of organic matter under the circulation flow rate condition corresponding to the maximum value of the electron efficiency prediction value, and the error between the electron efficiency prediction value and the actual value of the electron efficiency under the condition, wherein the influent organic matter content is influent chemical oxygen demand, and the effluent organic matter content is effluent chemical oxygen demand, The calculation formula of the actual value of the electron efficiency is: ， wherein N A is the Avogadro constant, e is the electric charge carried by a elementary charge, I is the electric current, F is the influent flow rate, COD in is the influent chemical oxygen demand, COD out is the effluent chemical oxygen demand; S4: when the error meets a preset condition, stopping iteration, taking the circulation flow rate value under the condition of the maximum value in the electron efficiency prediction value as the optimal circulation flow rate parameter, otherwise, discarding the maximum value, selecting the maximum value in the remaining electron efficiency prediction values, returning to step S3, and iterating; S5: adjusting the circulation flow rate parameter of the sewage electrolytic device to the optimal circulation flow rate parameter, and performing electrolysis on sewage.

2. The method of claim 1, wherein the method is characterized by: In step S1, the circulation flow rate parameters of multiple groups of sewage electrolytic devices are set, including setting a basic circulation flow rate value, and selecting multiple values uniformly distributed before and after the basic circulation flow rate value as circulation flow rate setting values, wherein the basic circulation flow rate value and the circulation flow rate setting values together constitute the circulation flow rate parameters of the multiple groups of sewage electrolytic devices.

3. The method of claim 1, wherein the method is characterized by: In step S1, the influent organic matter content and the effluent organic matter content are obtained by sampling and testing, the influent flow rate is obtained by measuring with an online flow meter, and the influent oxidation-reduction potential and the effluent oxidation-reduction potential are obtained by measuring with an oxidation-reduction potential analyzer; and the voltage, current, and power consumption are obtained by measuring with a power meter.

4. The method of claim 1, wherein the method is characterized by: The error back propagation neural network model comprises two hidden layers and a P-ReLU activation function.

5. The method of claim 4, wherein the method is characterized by: The learning rate of the two hidden layers is adaptively adjusted using an Adam algorithm.

6. A sewage electrolysis device, characterized by, It comprises: a parameter acquisition module, configured to acquire circulation flow rate parameter values, and to acquire corresponding voltage, current, power consumption, influent flow rate, influent organic matter content, influent oxidation-reduction potential, effluent organic matter content, and effluent oxidation-reduction potential parameter values; a prediction module, configured to store an error back propagation neural network model, to receive the parameters acquired by the parameter acquisition module, and to input the parameters into the error back propagation neural network model to predict the electron efficiency of electrolytic removal of organic matter, and to output an electron efficiency prediction value; a calculation module, configured to obtain a maximum value in the electron efficiency prediction value, and to calculate the actual value of the electron efficiency of electrolytic removal of organic matter under the circulation flow rate condition corresponding to the maximum value of the electron efficiency prediction value, and the error between the electron efficiency prediction value and the actual value of the electron efficiency under the condition, wherein the influent organic matter content is influent chemical oxygen demand, and the effluent organic matter content is effluent chemical oxygen demand, The formula for calculating the actual value of electronic efficiency η is: , wherein N A is the Avogadro constant, e is the electric charge carried by a elementary charge, I is the electric current, F is the influent flow rate, COD in is the influent chemical oxygen demand, COD out is the effluent chemical oxygen demand; a judgment module, configured to judge whether the error meets a preset condition. The adjusting module is configured to stop iteration when the error meets a preset condition, take a circulation flow value under a maximum value in the electronic efficiency prediction value as an optimal circulation flow parameter, otherwise, discard the maximum value, select a maximum value in remaining electronic efficiency prediction values, input a calculation module and a judging module to continue iteration until an optimal circulation flow parameter is obtained, and adjust a circulation flow parameter of the sewage electrolysis device to the optimal circulation flow parameter to perform electrolysis work on sewage.

7. An electronic device, comprising: Comprise: a processor; and a memory having stored thereon executable code that, when executed by the processor, causes the processor to perform the method of any one of claims 1-5.

8. A non-transitory machine-readable storage medium having stored thereon executable code that, when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-5.

Images