Thermal power plant pickling wastewater, urea wastewater and domestic sewage cooperative treatment control system and method based on neural network
Through the neural network collaborative treatment system, combined with Fenton reaction and A2/O process, the problems of pickling wastewater, urea wastewater and domestic sewage treatment in thermal power plants are solved, water resource reuse and cost reduction are achieved, and treatment efficiency and water quality are optimized.
Patent Information
- Application Number
- CN202411193712.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-03
AI Technical Summary
The water quality of pickling wastewater, urea wastewater and domestic sewage in thermal power plants is very different. The existing treatment methods are costly and difficult, making it difficult to achieve cost-effective and efficient coordinated treatment, which affects the boiler combustion efficiency and water resource reuse rate.
Using a collaborative processing system based on neural network, through Fenton reaction, A2/O reaction cell and coagulation clarification cell, combined with neural network algorithms to achieve Fe ion precipitation, nitrogen and nitrogen phosphorus removal and organic degradation, precisely controlling Fenton reagent dosing and Water inlet volume, optimize internal circulation and return sludge treatment.
It improves the water resource reuse rate, reduces the water cost of thermal power plants, realizes the stability of effluent water quality and optimization of treatment efficiency, and reduces the difficulty and cost of treatment.
Smart Images

Figure CN119059671A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of water treatment, and relates to a control system and method for coordinated treatment of acid washing wastewater, urea wastewater and domestic sewage from a thermal power plant based on a neural network. Background Art
[0002] Urea is a white crystal. It can be used as a denitrification agent to produce ammonia in three ways: direct urea injection, urea thermal decomposition and urea hydrolysis. Urea hydrolyzer can convert urea into NH3 and CO2 for SCR denitrification system. The main sources of urea wastewater are regular sewage discharge from urea hydrolyzer, equipment and pipeline flushing water, etc. It has water quality characteristics such as small flow, high ammonia nitrogen and COD. At present, most thermal power plants adopt treatment methods such as mixing with other wastewater, spraying on the coal yard, and diluting and discharging into the desulfurization system, which is easy to affect the combustion calorific value and work efficiency of the boiler, and the discharge of urea wastewater into the desulfurization system will increase the difficulty of subsequent treatment of desulfurization wastewater. Conventional high-concentration ammonia nitrogen wastewater can be treated by air stripping, but a new packed air stripping tower needs to be built, and there is still a recovered product.
[0003] Thermal power plants need to regularly use organic acids to clean boilers to improve boiler efficiency. The acid wash wastewater produced has the characteristics of short discharge cycle, large discharge volume, high concentration of pollutants and organic matter, etc. Due to the high cost and great difficulty of separate treatment, thermal power plants used to mix the acid wash wastewater with ash water and discharge it into ash plants or spray it in coal yards. However, under the current new environmental protection requirements, ash yards are gradually banned and coal yards are closed, and the acid wash wastewater cannot be disposed of.
[0004] Domestic sewage from thermal power plants generally adopts biological treatment technology, which has the functions of degrading organic matter, removing nitrogen and phosphorus. Under the new environmental protection situation such as liquid ammonia to urea and closed coal yard transformation, domestic sewage can be used to synergistically treat urea wastewater and boiler pickling wastewater. Since the water quality of urea wastewater, boiler pickling wastewater and domestic sewage is quite different, in order to improve the water resource reuse rate of thermal power plants and reduce the operating costs of thermal power plants, it is urgent to explore an economical and efficient method for synergistic treatment of thermal power plant wastewater, optimize the water replenishment ratio of the three types of wastewater according to the operating status of the domestic sewage treatment system, and ensure the effluent water quality. Summary of the invention
[0005] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a neural network-based control system and method for the coordinated treatment of acid washing wastewater, urea wastewater and domestic sewage in thermal power plants, which ensures the water quality of the effluent.
[0006] To achieve the above object, the present invention discloses a neural network-based control system for the coordinated treatment of acid wash wastewater, urea wastewater and domestic sewage in a thermal power plant, comprising an acid wash wastewater storage tank, a Fenton reaction tank, a regulating tank, a pre-sedimentation tank, an A 2 / O reaction tank, coagulation clarification tank and Fenton reagent storage tank;
[0007] The outlet of the pickling wastewater storage tank passes through the Fenton reactor, regulating tank, pre-sedimentation tank, A 2 The inlet of the / O reaction tank is connected to the coagulation and clarification tank, and the outlet of the Fenton reagent storage tank is connected to the inlet of the Fenton reaction tank. 2 The water outlet of the / O reaction tank is connected with the inlet of the anoxic tank through a reflux pipe, and an internal circulation controller is arranged on the reflux pipe. The aerobic tank is provided with an aeration device, and the sludge outlet at the bottom of the clarification tank is connected with the sludge inlet at the bottom of the anaerobic tank through a reflux sludge control pump.
[0008] The outlet of the Fenton reaction tank is connected to the inlet of the regulating tank via the effluent COD monitor and the pickling wastewater control pump in turn.
[0009] The A 2 / O reaction pool is divided into anaerobic pool, anoxic pool and aerobic pool along the water flow direction.
[0010] The first water quality analyzer is installed in the pickling wastewater storage tank, the second water quality analyzer is installed in the pre-sedimentation tank, the third water quality analyzer is installed in the anaerobic tank, the fourth water quality analyzer is installed in the anoxic tank, and the fifth water quality analyzer is installed in the aerobic tank. 2 A water quality monitoring meter is provided at the outlet of the / O reaction tank.
[0011] It also includes a first controller, which is connected to a first water quality analyzer, a Fenton reagent storage tank and an outlet water COD monitor.
[0012] It also includes a second controller, which is connected to the pickling wastewater control pump, the total water inlet control pump, the internal circulation control pump and the return sludge control pump.
[0013] The neural network-based coordinated treatment control method for pickling wastewater, urea wastewater and domestic sewage in a thermal power plant of the present invention comprises:
[0014] 1) Domestic sewage, urea wastewater and treated pickling wastewater are discharged into the regulating tank, and then the pH is neutralized and the C / N of the mixed solution is adjusted in the regulating tank. At the same time, the Fe ions in the pickling wastewater react to form Fe(OH)3 flocs. The wastewater output from the regulating tank enters the sedimentation tank for sedimentation, and then enters A 2 / O reaction pool;
[0015] 2) Wastewater in A 2 / O reaction tank for simultaneous nitrogen and phosphorus removal, while the sludge from the clarification tank is returned to A 2 In the anaerobic tank of the / O reaction tank, A 2 / O The wastewater containing nitrate in the aerobic tank of the reaction tank is returned to the anoxic tank for denitrification;
[0016] 3) A 2 The effluent from the / O reaction tank enters the coagulation and clarification tank, and the turbidity and COD are reduced by adding coagulants and coagulant aids. The effluent from the coagulation and clarification tank is discharged into the industrial wastewater regulating tank.
[0017] The pH and Fe of the water in the pickling wastewater storage tank detected by the first water quality analyzer 2+ The concentration and COD, the temperature of the water in the Fenton reaction tank, the reaction time and the effluent COD are used as inputs. The dosage of the Fenton reagent is obtained through the trained first model of the collaborative processing system. The dosage of the Fenton reagent in the Fenton reagent storage tank is controlled by the dosage controller according to the dosage of the Fenton reagent, so as to realize the accurate dosage of the Fenton reagent.
[0018] To adjust the pH of the water in the pool, the pH of the water in the anaerobic pool detected by the third water quality analyzer, and NO3 - -N concentration, COD and NH4 + -N concentration, NO3 in the water of the anoxic pool detected by the fourth water quality analyzer - -N concentration, COD, NH4 + -N concentration and NO3 in the aerobic pool water detected by the fifth water quality analyzer - -N concentration, NH4 + -N concentration and DO are taken as input quantities. Through the trained second model of the collaborative treatment system, the internal circulation volume Q1, the return sludge volume Q2, the pickling wastewater inflow volume and the total inflow volume are obtained to realize the feedforward control of the pickling wastewater inflow volume and the total inflow volume.
[0019] The COD and NH4 of the effluent from the aerobic pool were detected by the effluent quality monitoring table. + -N concentration is taken as input, and the pickling wastewater inflow and total inflow are obtained through the trained third model of the collaborative treatment system, so as to realize feedback control of the pickling wastewater inflow and total inflow.
[0020] The present invention has the following beneficial effects:
[0021] The neural network-based control system and method for coordinated treatment of acid wash wastewater, urea wastewater and domestic sewage in thermal power plants of the present invention, in specific operation, mixes boiler acid wash wastewater treated by Fenton with urea wastewater and domestic sewage, which has the effect of neutralizing the pH of the mixed solution and reducing the concentration of metal ions such as Fe ions; the urea wastewater has a high ammonia nitrogen content, and the boiler acid wash wastewater can be used as a denitrification carbon source to improve the C / N of the mixed solution and promote A 2 / O process for nitrogen and phosphorus removal and organic matter degradation efficiency; through anaerobic tanks and anoxic tanks to further promote the degradation of macromolecular organic matter in the mixed liquid, improve A 2 / O process reaction efficiency, realize water resource reuse in thermal power plants, and reduce water costs in thermal power plants.
[0022] Furthermore, the present invention realizes the accurate addition of Fenton reagent through the neural network algorithm, realizes the accurate control of the pickling wastewater inflow, total water inflow, internal reflux and reflux sludge, and ensures the stable operation of the system. 2 The / O process achieves optimal efficiency in nitrogen removal, phosphorus removal and organic matter degradation. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:
[0024] Figure 1 It is a flow chart of the present invention;
[0025] Figure 2 It is the principle diagram of the present invention;
[0026] Figure 3 It is the control principle diagram of the present invention;
[0027] Figure 4 It is a structural diagram of the present invention.
[0028] Among them, 1 is the first water quality analyzer, 2 is the Fenton reagent storage tank, 3 is the pickling wastewater control pump, 4 is the second water quality analyzer, 5 is the total water inlet control pump, 6 is the third water quality analyzer, 7 is the fourth water quality analyzer, 8 is the fifth water quality analyzer, 9 is the internal circulation controller, 10 is the aeration device, 11 is the effluent water quality monitoring meter, 12 is the return sludge control pump, and 13 is the effluent COD monitoring instrument. DETAILED DESCRIPTION
[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0030] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.
[0031] Embodiment 1
[0032] refer to Figure 1 The neural network-based control system for coordinated treatment of acid wash wastewater, urea wastewater and domestic sewage in thermal power plants comprises an acid wash wastewater storage tank, a Fenton reaction tank, a regulating tank, a pre-sedimentation tank, an A 2 / O reaction tank, coagulation and clarification tank and Fenton reagent storage tank (2);
[0033] The outlet of the pickling wastewater storage tank passes through the Fenton reactor, regulating tank, pre-sedimentation tank, A 2 / O The reaction tank is connected to the inlet of the coagulation and clarification tank.
[0034] The outlet of the Fenton reagent storage tank 2 is connected to the inlet of the Fenton reaction tank, and the outlet of the Fenton reaction tank is connected to the inlet of the regulating tank via the effluent COD monitor 13 and the pickling wastewater control pump 3 in turn.
[0035] The A 2 The / O reaction tank is divided into an anaerobic tank, an anoxic tank and an aerobic tank along the water flow direction, wherein a third water quality analyzer 6 is arranged in the anaerobic tank, a fourth water quality analyzer 7 is arranged in the anoxic tank, a fifth water quality analyzer 8 is arranged in the aerobic tank, and a second water quality analyzer 4 is arranged in the pre-sedimentation tank.
[0036] A 2 The water outlet of the / O reaction tank is connected to the inlet of the anoxic tank through a reflux pipe, an internal circulation controller 9 is arranged on the reflux pipe, and an aeration device 10 is arranged in the aerobic tank.
[0037] The sludge outlet at the bottom of the anaerobic tank and the sludge outlet at the bottom of the clarification tank are connected to the sludge output device, and a return sludge control pump 12 is provided at the sludge outlet at the bottom of the anaerobic tank.
[0038] A 2 A water quality monitoring meter 11 is provided at the water outlet of the / O reaction tank.
[0039] The first controller is connected to the first water quality analyzer 1 , the Fenton reagent storage tank 2 and the effluent COD monitor 13 , and the second controller is connected to the pickling wastewater control pump 3 , the total water inlet control pump 5 , the internal circulation control pump and the return sludge control pump 12 .
[0040] Embodiment 2
[0041] The neural network-based coordinated treatment control method for pickling wastewater, urea wastewater and domestic sewage in a thermal power plant of the present invention comprises the following steps:
[0042] 1) Domestic sewage, urea wastewater, and treated pickling wastewater are discharged into the regulating tank, and then the pH is neutralized and the C / N of the mixed solution is adjusted in the regulating tank. At the same time, the Fe ions in the pickling wastewater react to form Fe(OH)3 flocs. The wastewater output from the regulating tank enters the sedimentation tank for sedimentation, and then enters A 2 / O reaction pool;
[0043] 2) Wastewater in A 2 / O reaction pool for simultaneous nitrogen and phosphorus removal. At the same time, the sludge in the clarification pool is returned to the anaerobic pool, and the wastewater containing nitrate in the aerobic pool is returned to the anoxic pool for denitrification.
[0044] 3) A 2 The effluent from the / O reaction tank enters the coagulation and clarification tank, and the turbidity and COD are reduced by adding coagulants and coagulant aids. The effluent from the coagulation and clarification tank is discharged into the industrial wastewater regulating tank and finally enters the circulating water system for reuse.
[0045] In step 1), the flow rate of urea wastewater is small. After mixing with domestic sewage, the pH and ammonia nitrogen concentration in the mixed solution are increased. By mixing boiler pickling wastewater as a denitrification carbon source with urea wastewater and domestic sewage, the C / N of the mixed solution is adjusted on the basis of neutralizing the pH of the mixed solution and reducing the concentration of metal ions such as Fe ions, so as to increase A 2 / O reaction pool nitrogen and phosphorus removal and organic matter degradation rate.
[0046] In addition, the present invention adopts a neural network algorithm to improve the reaction efficiency of the collaborative treatment system, realize the precise addition of Fenton reagent, and realize the precise control of the pickling wastewater inflow, total water inflow, internal reflow volume and reflow sludge volume.
[0047] The specific process is:
[0048] 21) Establishing a first model of the collaborative processing system based on the GA-BP neural network; establishing a second model of the collaborative processing system based on the PSO-LSTM; establishing a third model of the collaborative processing system based on the PSO-LSTM, and training the first model of the collaborative processing system, the second model of the collaborative processing system, and the third model of the collaborative processing system to obtain the trained first model of the collaborative processing system, the second model of the collaborative processing system, and the third model of the collaborative processing system.
[0049] 22) The pH and Fe of the water in the pickling wastewater storage tank detected by the first water quality analyzer 1 2+ The concentration and COD, the thermometer reaction time of the water in the Fenton reaction tank and the outlet COD are used as input quantities. The Fenton reagent dosage is obtained through the trained first model of the collaborative processing system. The Fenton reagent dosage of the Fenton reagent storage tank 2 is controlled by the dosage controller according to the Fenton reagent dosage to achieve accurate dosage of the Fenton reagent.
[0050] 23) To adjust the pH of the water in the pool, the pH of the water in the anaerobic pool detected by the third water quality analyzer 6, and the NO3 - -N concentration, COD and NH4 + -N concentration, NO3 in the water of the anoxic pool detected by the fourth water quality analyzer 7 - -N concentration, COD, NH4 + -N concentration and NO3 in the aerobic pool water detected by the fifth water quality analyzer 8 - -N concentration, NH4 + -N concentration and DO are taken as inputs. Through the trained second model of the collaborative treatment system, the internal circulation volume Q1, the return sludge volume Q2, the pickling wastewater inflow volume and the total inflow volume are obtained to realize the feedforward control of the pickling wastewater inflow volume and the total inflow volume to improve A 2 / O process nitrogen and phosphorus removal and organic matter degradation efficiency.
[0051] 24) COD and NH4 of the effluent from the aerobic pool detected by the effluent quality monitoring table 11 + -N concentration is taken as input, and the pickling wastewater inflow and total inflow are obtained through the trained third model of the collaborative treatment system, so as to realize feedback control of the pickling wastewater inflow and total inflow.
[0052] In addition, the mean square error (MSE), mean absolute error (MAE) and R 2 _score performs model evaluation, specifically:
[0053]
[0054]
[0055]
[0056] In step 21), historical data is preprocessed using a clustering analysis algorithm and then normalized. A data set is then constructed using the normalized historical data. The data set is then divided into a training set and a test set. The first model of the collaborative processing system, the second model of the collaborative processing system, and the third model of the collaborative processing system are trained and tested based on the training set and the test set.
[0057] In addition, it should be noted that during the training process of the first model of the collaborative processing system, the GA genetic algorithm is used to continuously adjust and optimize the weights and thresholds of the BP neural network, so that the error between the predicted value and the actual value of the BP neural network is minimized.
[0058] The steps of LSTM algorithm are:
[0059] 31) Forget Gate f t The calculation formula is:
[0060] f t =σ(W f ·[h t-1 ,x t ]+b f )
[0061] Among them, σ is the sigmoid activation function, W f is the forget gate weight matrix, [h t-1 ,x i ] is the connection between the hidden state of the previous moment and the current input, b f is the forget gate bias term.
[0062] 32) Input gate i t The calculation formula is:
[0063] i t =σ(W i ·[h t-1 ,x t ]+b i )
[0064]
[0065] Among them, C t is a new candidate memory cell, W i and W c is the weight matrix of the input gate and the candidate memory unit, b i and b c is the bias term between the input gate and the candidate memory unit.
[0066] 33) The current state of the memory unit C t The calculation formula is:
[0067]
[0068] Among them, C t-1 is the memory unit state at the previous moment.
[0069] 34) Output gate o t The calculation formula is:
[0070] o t =σ(W o ·[h t-1 ,x t ]+b o )
[0071] h t =o t tanh(C t )
[0072] Among them, h t is the hidden state at the current moment, W o and b o is the weight matrix and bias term of the output gate.
[0073] In order to avoid the LSTM algorithm from falling into local optimization and improve the algorithm accuracy and running speed, the PSO algorithm is used to update the initial weights and thresholds of the LSTM algorithm. The standard form of the PSO algorithm is:
[0074] v i =w×v i +c1×rand()×(pbest i -x i )+c2×rand()×(gbest i -x i )
[0075] x i =x i +v i
[0076] Where i = 1, 2, ..., N, N is the total number of particles in the group, v i is the particle velocity, w is the inertia factor, C1 and C2 are learning factors, pbest and gbest are the best historical position and global best position of a single particle respectively, x i is the current position of the particle.
[0077] Embodiment 3
[0078] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the neural network-based thermal power plant acid pickling wastewater, urea wastewater and domestic sewage coordinated treatment control method are implemented. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, the network interface, and the memory are interconnected through an internal bus, which may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.
[0079] Embodiment 4
[0080] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the neural network-based thermal power plant acid pickling wastewater, urea wastewater and domestic sewage coordinated treatment control method are implemented. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include a read-only memory (ROM), a hard disk, a flash memory, an optical disk, a magnetic disk, etc.
[0081] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0082] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0085] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.
[0086] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
[0087] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A neural network-based collaborative treatment control system for acid wash wastewater, urea wastewater and domestic sewage in thermal power plants, characterized in that: Including pickling wastewater storage tank, Fenton reactor, regulating tank, pre-sedimentation tank, A 2 / O reaction tank, coagulation and clarification tank and Fenton reagent storage tank (2); The outlet of the pickling wastewater storage tank passes through the Fenton reactor, regulating tank, pre-sedimentation tank, A 2 The inlet of the / O reaction tank is connected to the coagulation and clarification tank, the outlet of the Fenton reagent storage tank (2) is connected to the inlet of the Fenton reaction tank, and the A 2 The water outlet of the / O reaction tank is connected to the inlet of the anoxic tank through a return pipe, and the return pipe is provided with an internal circulation controller (9). The aerobic tank is provided with an air aeration device (10). The sludge outlet at the bottom of the clarifier tank is connected to the sludge inlet at the bottom of the anaerobic tank through a return sludge control pump (12).
2. The neural network-based coordinated treatment control system for pickling wastewater, urea wastewater and domestic sewage from thermal power plants according to claim 1 is characterized in that: The outlet of the Fenton reactor is connected to the inlet of the regulating tank via the effluent COD monitor (13) and the pickling wastewater control pump (3).
3. The neural network-based coordinated treatment control system for pickling wastewater, urea wastewater and domestic sewage from thermal power plants according to claim 2, characterized in that: The A 2 The / O reaction tank is divided into anaerobic tank, anoxic tank and aerobic tank along the direction of water flow.
4. The neural network-based coordinated treatment control system for pickling wastewater, urea wastewater and domestic sewage from thermal power plants according to claim 3 is characterized in that: A first water quality analyzer (1) is provided in the pickling wastewater storage tank, a second water quality analyzer (4) is provided in the pre-sedimentation tank, a third water quality analyzer (6) is provided in the anaerobic tank, a fourth water quality analyzer (7) is provided in the anoxic tank, and a fifth water quality analyzer (8) is provided in the aerobic tank. 2 A water quality monitoring meter (11) is provided at the water outlet of the / O reaction tank.
5. The neural network-based coordinated treatment control system for pickling wastewater, urea wastewater and domestic sewage from thermal power plants according to claim 4 is characterized in that: It also includes a first controller connected to the first water quality analyzer (1), the Fenton reagent storage tank (2) and the effluent COD monitor (13).
6. The neural network-based coordinated treatment control system for pickling wastewater, urea wastewater and domestic sewage from thermal power plants according to claim 4 is characterized in that: It also includes a second controller, which is connected to the pickling wastewater control pump (3), the total water inlet control pump (5), the internal circulation control pump and the return sludge control pump (12).
7. A neural network-based collaborative treatment control method for acid washing wastewater, urea wastewater and domestic sewage in thermal power plants, characterized in that: The neural network-based coordinated treatment control system for pickling wastewater, urea wastewater and domestic sewage from a thermal power plant according to claim 4 comprises: 1) The domestic sewage, urea wastewater and treated pickling wastewater are discharged into the regulating tank, and then the pH is neutralized and the C / N ratio of the mixed solution is adjusted in the regulating tank. At the same time, the Fe ions in the pickling wastewater react to form Fe(OH)3 flocs. The wastewater output from the regulating tank enters the sedimentation tank for sedimentation, and then enters the A 2 / O reaction pool; 2) Wastewater in A 2 / O reaction tank for simultaneous denitrification and phosphorus removal, while the sludge from the clarifier tank is returned to A 2 In the anaerobic tank of the / O reaction tank, A 2 / The wastewater containing nitrate in the aerobic tank of the O reaction tank is returned to the anoxic tank for denitrification; 3)A 2 The effluent from the / O reaction tank enters the coagulation and clarification tank, where the turbidity and COD are reduced by adding coagulants and coagulant aids. The effluent from the coagulation and clarification tank is discharged into the industrial wastewater regulating tank.
8. The neural network-based coordinated treatment control method for pickling wastewater, urea wastewater and domestic sewage in thermal power plants according to claim 1, characterized in that: The pH and Fe of the water in the pickling wastewater storage tank detected by the first water quality analyzer (1) 2+ The concentration and COD, the temperature of the water in the Fenton reaction tank, the reaction time and the effluent COD are input, and the Fenton reagent dosage is obtained through the trained first model of the collaborative processing system. The Fenton reagent dosage of the Fenton reagent storage tank (2) is controlled by the dosage controller according to the Fenton reagent dosage, thereby realizing the accurate dosage of the Fenton reagent.
9. The neural network-based coordinated treatment control method for pickling wastewater, urea wastewater and domestic sewage in thermal power plants according to claim 1, characterized in that: The pH of the water in the regulating pool, the pH of the water in the anaerobic pool detected by the third water quality analyzer (6), and the NO3 - -N concentration, COD and NH4 + -N concentration, NO3 in the water of the anoxic pool detected by the fourth water quality analyzer (7) - -N concentration, COD, NH4 + -N concentration and NO3 in the aerobic pool water detected by the fifth water quality analyzer (8) - -N concentration, NH4 + -N concentration and DO are input quantities. Through the trained second model of the collaborative treatment system, the internal circulation volume Q1, the return sludge volume Q2, the pickling wastewater inflow volume and the total inflow volume are obtained to realize the feedforward control of the pickling wastewater inflow volume and the total inflow volume.
10. The neural network-based coordinated treatment control method for pickling wastewater, urea wastewater and domestic sewage in thermal power plants according to claim 1, characterized in that: The COD and NH4 of the effluent from the aerobic pool were detected by the effluent quality monitoring table (11). + -N concentration is used as input, and the pickling wastewater inflow and total inflow are obtained through the trained third model of the collaborative treatment system, thereby realizing feedback control of the pickling wastewater inflow and total inflow.
Citation Information
Patent Citations
Method and device for synchronously treating steel pickling waste water and coking waste water
CN101259978A
Thermal power plant wastewater treatment and recycling system and method
CN106830559A
Treating method for standardized discharging of coking wastewater
CN109607985A
Wastewater advanced oxidation treatment intelligent dosing system and method based on fuzzy BP neural network
CN110981021A
Industrial park sewage intelligent management and control platform and control method thereof
CN111470740A
