Method for treating acidic wastewater by high-density slurry method and control system

Abstract

The invention relates to the technical field of mine acid wastewater treatment, in particular to a method for treating acid wastewater through a high-density slurry method and a control system. The method specifically comprises the following steps: executing the following operations through a control device: receiving a real-time pH value fed back by a pH meter in a reaction device and liquid level data of a liquid level meter; the real-time pH value and the liquid level data are input into a preset reflux ratio calculation model, and the reflux ratio calculation model calculates the lime adding amount, the flocculating agent adding amount and the sludge reflux flow through a simulated annealing algorithm; and controlling the operation parameters of the delivery pump, the reflux pump and the stirring device according to the calculation result, and maintaining the pH value in the reaction device within a set interval. The pH value and liquid level data are monitored in real time, the lime adding amount, the flocculating agent adding amount and the sludge backflow flow are dynamically optimized in combination with the simulated annealing algorithm, and the pH value in the reaction device is maintained; the heavy metal concentration reaches the standard; the effluent quality is ensured to meet the standard; and normal operation of treatment facilities is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of mine acid wastewater treatment, and in particular, to a method and a control system for treating acid wastewater by the high-density sludge process. Background Art

[0002] Acid wastewater refers to acid mine wastewater generated by the oxidation of reducing sulfide minerals under the action of air, water and bacteria during mine exploitation, ore transportation, ore dressing, waste rock discharge and tailings storage, as well as acid waste liquid generated during the process of mineral leaching using chemical reagents such as sulfuric acid and hydrochloric acid. If acid wastewater is directly discharged, it will cause serious pollution to water bodies and even damage the ecological environment.

[0003] In the prior art, when treating sewage, the total phosphorus (TP) and total nitrogen (TN) concentrations are controlled by adjusting the reflux ratio of the CASS tank. However, this method has the following defects:

[0004] Lack of pH control: In the treatment of acid wastewater, the dynamic balance between the lime dosage and the pH value directly affects the heavy metal precipitation efficiency (for example, when pH < 5, Cu 2+ is difficult to form hydroxide precipitation). This technology does not monitor the pH value, resulting in inaccurate lime dosage, prone to insufficient neutralization (pH too low) or reagent waste (pH too high).

[0005] Insufficient multi-parameter coupling optimization: Parameters such as the sludge reflux ratio, chemical dosage, and stirring speed need to be adjusted synergistically. However, the prior art uses fixed rules (such as preset reflux ratios R = 20%, 50%, etc.), which cannot cope with water quality fluctuations, resulting in unstable system operation.

[0006] In view of the acid wastewater treatment scenario, there is an urgent need for a method that can monitor the pH value in real time, dynamically optimize the lime / flocculant dosage and the sludge reflux ratio, so as to solve the problems of low control accuracy and serious resource waste in the prior art. Summary of the Invention

[0007] The purpose of the present invention is to provide a method and a control system for treating acid wastewater by the high-density sludge process, which can solve the problems of low control accuracy and serious resource waste in the prior art.

[0008] In a first aspect, the present invention provides a method for treating acid wastewater by the high-density sludge process, which is performed by a control device as follows:

[0009] Receiving the real-time pH value feedback by a pH meter and the liquid level data of a liquid level meter in a reaction device;

[0010] Inputting the real-time pH value and the liquid level data into a preset reflux ratio calculation model, and the reflux ratio calculation model calculates the lime dosage, the flocculant dosage and the sludge reflux flow rate through a simulated annealing algorithm;

[0011] Control the operating parameters of the delivery pump, reflux pump and stirring device according to the calculation results to maintain the pH value in the reaction device within the set range.

[0012] In an alternative embodiment, the execution of the simulated annealing algorithm includes the following steps:

[0013] Step a: Initialize the temperature parameter T max , the lowest temperature T min , the temperature reduction coefficient δ and the maximum number of iterations ξ;

[0014] Step b: Randomly generate M groups of feasible solutions including the lime dosage, flocculant dosage, and sludge reflux flow rate;

[0015] Step c: Calculate the fitness value f = cx of each group of solutions through the deep neural network model, where x is the treatment effect score and c is the dynamic weight coefficient;

[0016] Step d: Accept the inferior solution with probability , update the temperature T = T × δ, and the number of iterations ξ = ξ × δ;

[0017] Step e: Terminate the calculation when T < T min and output the optimal parameter combination.

[0018] In an alternative embodiment, the probability in step d is calculated as:

[0019] f″ = f′ - f

[0020] where f′ is the fitness value of the new solution and f is the fitness value of the current solution.

[0021] In an alternative embodiment, the treatment effect score x is predicted by the deep neural network model, specifically including:

[0022] The input parameters are the lime dosage, flocculant dosage, sludge reflux flow rate, real-time pH value, and liquid level data;

[0023] The output parameters are the pH value deviation score, heavy metal ion concentration score, and suspended solid concentration score, and x is the weighted sum of the three.

[0024] In an alternative embodiment, the dynamic weight coefficient c is dynamically adjusted according to the real-time water quality target:

[0025] When the heavy metal ion concentration exceeds the threshold, increase the weight of the heavy metal ion concentration score;

[0026] When the suspended solid concentration exceeds the threshold, increase the weight of the suspended solid concentration score;

[0027] When the pH value exceeds the set range, increase the weight of the pH value deviation score.

[0028] In an alternative embodiment, the heavy metal ion concentration and suspended solid concentration of the effluent water quality are monitored in real time through a deep neural network model, and the monitoring results are fed back to the reflux ratio calculation model for iterative optimization.

[0029] In an alternative embodiment, the training data of the deep neural network model includes the pH value, liquid level data, chemical dosage parameters, and corresponding treatment effect scores collected during the historical wastewater treatment process.

[0030] In an alternative embodiment, the operating parameters for controlling the transfer pump include: adjusting the rotation speed of the reflux pump to match the sludge reflux ratio according to the calculation result of the sludge reflux flow rate.

[0031] In an alternative embodiment, the set range is a pH value of 5.8 - 9.2.

[0032] In a second aspect, the present invention provides a control system for treating acidic wastewater by the high-density mud method, adopting the method according to any one of the foregoing embodiments.

[0033] The beneficial effects of the embodiments of the present invention are as follows:

[0034] By monitoring the pH value and liquid level data in real time, and dynamically optimizing the lime dosage, flocculant dosage, and sludge reflux flow rate in combination with the simulated annealing algorithm, the following breakthroughs have been achieved:

[0035] 1) Accurately maintain the pH value in the reaction device within the set range to ensure the efficient progress of the wastewater neutralization reaction;

[0036] 2) Combine the deep neural network to predict the influence of different flocculant addition amounts on the heavy metal ion precipitation effect, and optimize the flocculant dosage through the simulated annealing algorithm to enhance the precipitation effect and ensure that the heavy metal concentration meets the standard;

[0037] 3) The model adjusts the flocculant dosage and precipitation time according to the suspended solid concentration monitored in real time to improve the suspended solid removal efficiency and ensure that the effluent water quality meets the standard;

[0038] 4) Quickly and accurately regulate the bottom mud reflux ratio and the input amount of lime, avoid waste caused by excessive lime usage and the influence on the sewage treatment effect due to insufficient lime usage, so that the pH value of the system is maintained within a stable range, maintain a relatively stable reflux ratio, and the sewage treatment effect does not change with the change of the influent water volume, thereby ensuring the stable operation of the system, better sewage treatment effect, low calcium ion content in the water, effectively delaying the scaling phenomenon of equipment and pipelines, and ensuring the normal operation of the treatment facilities. Description of the Drawings

[0039] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0040] Figure 1 It is the optimization flowchart of the simulated annealing algorithm in the method for treating acidic wastewater by the high-density sludge method provided by the embodiments of the present invention;

[0041] Figure 2 It is the dynamic weight adjustment logic block diagram in the method for treating acidic wastewater by the high-density sludge method provided by the embodiments of the present invention;

[0042] Figure 3 It is the schematic structural diagram of the usage system of the method for treating acidic wastewater by the high-density sludge method provided by the embodiments of the present invention. Detailed implementation manners

[0043] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations.

[0044] 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 present invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0045] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0046] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the inventive product is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the present invention. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0047] In addition, terms such as "horizontal", "vertical", "hanging" do not mean that the components are required to be absolutely horizontal or hanging, but can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined.

[0048] In the description of the present invention, it should also be noted that unless otherwise clearly specified and defined, the terms "set", "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0049] The following Figures 1 - 3 will be used to detail some embodiments of the present invention. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0050] In the first aspect, the present invention provides a method for treating acidic wastewater by the high-density mud method, and the control device performs the following operations:

[0051] Receiving the real-time pH value feedback by the pH meter and the liquid level data of the liquid level meter in the reaction device;

[0052] Inputting the real-time pH value and the liquid level data into a preset reflux ratio calculation model, and the reflux ratio calculation model calculates the lime dosage, the flocculant dosage and the sludge reflux flow rate through the simulated annealing algorithm;

[0053] Controlling the operating parameters of the delivery pump, the reflux pump and the stirring device according to the calculation results to maintain the pH value in the reaction device within a set range.

[0054] In this embodiment, the intelligent and dynamic optimization control of the wastewater treatment process is realized through the control device. The specific operation steps are as follows:

[0055] First, the control device receives the real-time pH value feedback by the pH meter and the liquid level data of the liquid level meter in the reaction device. These data are key parameters in the wastewater treatment process, which can reflect the acidity and alkalinity in the reaction device and the height of the wastewater liquid level in real time. For example, in a certain mine acid wastewater treatment system, the real-time pH value in the reaction device may be 4.2, and the liquid level is 3.5 meters. These data are collected by high-precision sensors and transmitted to the control device in real time at a cycle of 1 minute. The control device performs preliminary processing on the received data to ensure the accuracy and integrity of the data, providing a reliable basis for subsequent dynamic optimization calculations.

[0056] Subsequently, the control device inputs the real-time pH value and liquid level data into a preset reflux ratio calculation model. This model is based on the simulated annealing algorithm and can dynamically calculate the optimal lime dosage, flocculant dosage, and sludge reflux flow rate. The simulated annealing algorithm avoids the system falling into a local optimal solution by simulating the random search mechanism in the physical annealing process, thus finding the global optimal solution. In this embodiment, assume the initial parameters are: lime dosage 1.0 kg / m 3 , flocculant dosage 0.3 g / L, and sludge reflux flow rate 20%. Through the optimization of the simulated annealing algorithm, the system dynamically adjusts these parameters according to the real-time pH value and liquid level data. For example, when it is detected that the pH value is lower than the set interval (5.8 - 9.2), the model will increase the lime dosage to increase the pH value; when the liquid level is too high, the model will adjust the sludge reflux flow rate to optimize the reaction effect. After multiple iterations of optimization, the final output optimal parameter combination may be: lime dosage 1.5 kg / m 3 , flocculant dosage 0.6 g / L, and sludge reflux flow rate 25%.

[0057] Finally, the control device controls the operating parameters of the delivery pump, reflux pump, and stirring device according to the calculation results to maintain the pH value in the reaction device within the set interval. The delivery pump adjusts the delivery speed according to the dosages of lime and flocculant to ensure accurate dosing of the agents; the reflux pump adjusts the rotation speed according to the sludge reflux flow rate to ensure the accuracy of the sludge reflux ratio; the stirring device dynamically adjusts the stirring speed according to the real-time data to ensure full mixing of the wastewater and the agents, improving the treatment efficiency. Through this dynamic control method, the system can respond to water quality changes in real time, ensure that the wastewater treatment process is always in the best state, effectively improve the wastewater treatment efficiency and quality, and at the same time reduce resource waste and equipment wear.

[0058] In an alternative embodiment, the execution of the simulated annealing algorithm includes the following steps:

[0059] Step a, initialize the temperature parameter T max , the lowest temperature T min , the cooling coefficient δ, and the maximum number of iterations ξ;

[0060] Step b: Randomly generate M sets of feasible solutions including the lime dosage, flocculant dosage, and sludge return flow rate;

[0061] Step c: Calculate the fitness value f = cx for each set of solutions through a deep neural network model, where x is the treatment effect score and c is the dynamic weight coefficient;

[0062] Step d: Accept inferior solutions with probability Update the temperature T = T × δ and the iteration count ξ = ξ × δ;

[0063] Step e: Terminate the calculation when T < T min and output the optimal parameter combination.

[0064] In this embodiment, the simulated annealing algorithm is the core technology for realizing the dynamic optimization of treating acidic wastewater by the high-density slurry method. This algorithm avoids the system falling into a local optimal solution by simulating the random search mechanism in the physical annealing process, thereby finding the global optimal solution. The following are the specific implementation steps and application descriptions of this algorithm:

[0065] Step a: Initialize parameters.

[0066] First, initialize the temperature parameter T max (initial temperature), the lowest temperature T min , the temperature reduction coefficient δ, and the maximum iteration count ξ. The selection of these parameters is crucial for the performance of the algorithm. The parameter selection is based on experience and a preliminary analysis of the system's dynamic characteristics to ensure that the algorithm can converge to the global optimal solution within a limited number of iterations.

[0067] Step b: Generate the initial feasible solution.

[0068] Randomly generate M sets of feasible solutions including the lime dosage, flocculant dosage, and sludge return flow rate. Each set of solutions represents a possible combination of operating parameters.

[0069] In this embodiment, assume M = 10, that is, randomly generate 10 sets of initial feasible solutions. The generation of these solutions is based on the system's historical operation data and the operator's experience to ensure that the initial solutions are within a reasonable range.

[0070] Step c: Calculate the fitness value.

[0071] Calculate the fitness value f = cx for each set of solutions through a deep neural network model, where x is the treatment effect score and c is the dynamic weight coefficient. The treatment effect score x comprehensively considers factors such as pH value deviation, heavy metal ion concentration, and suspended solid concentration, and is predicted through a deep neural network model. For example, when the heavy metal ion concentration exceeds the threshold, increase the weight of the heavy metal ion concentration score, thereby affecting the calculation of the fitness value. The higher the fitness value, the better the adaptability of the solution to the current water quality conditions.

[0072] Step d: Accept the inferior solution.

[0073] According to the Metropolis criterion, with probability accept the inferior solution, where f″ is the fitness difference f″ = f′ - f, f′ is the fitness value of the new solution, and f is the fitness value of the current solution. The probability of accepting the inferior solution gradually decreases as the temperature T decreases.

[0074] Step e: Termination condition and optimal solution output.

[0075] When the temperature T is lower than the lowest temperature T min the algorithm terminates the calculation and outputs the optimal parameter combination. In this embodiment, after multiple iterations, assume that the final temperature T drops below 1, and the algorithm stops running. At this time, the system outputs the optimal parameter combination, which is obtained through a dynamic optimization process and can achieve the best treatment effect under the current water quality conditions while ensuring the stability and economy of the system operation.

[0076] In an alternative embodiment, the treatment effect score x is predicted through a deep neural network model, specifically including:

[0077] The input parameters are the lime dosage, flocculant dosage, sludge return flow rate, real-time pH value, and liquid level data;

[0078] The output parameters are the pH value deviation score, heavy metal ion concentration score, and suspended solid concentration score, and x is the weighted sum of the three.

[0079] In this embodiment, the input parameters of the deep neural network model include: lime dosage (unit: kg / m 3 )), flocculant dosage (unit: g / L), sludge return flow rate (percentage), real-time pH value, liquid level data (unit: meter); the output parameters are: pH value deviation score, heavy metal ion concentration score, suspended solid concentration score. The treatment effect score x is the weighted sum of the above three scores, and the weights are dynamically adjusted according to the real-time water quality target.

[0080] The training data of the deep neural network model includes the pH value, liquid level data, chemical dosage parameters, and corresponding treatment effect scores collected during the historical wastewater treatment process. Through training with a large amount of historical data, the model can learn the relationship between different parameter combinations and treatment effects, so as to accurately predict the treatment effect score during actual operation.

[0081] In this embodiment, by learning historical data, the model can quickly predict the treatment effect score under the current working conditions based on the input lime dosage, flocculant dosage, sludge return flow rate, real-time pH value, and liquid level data. This score not only reflects the overall effect of the current parameter combination on wastewater treatment, but also provides an optimization goal for the simulated annealing algorithm, ensuring that the system can dynamically adjust operating parameters under complex working conditions to achieve efficient and stable wastewater treatment.

[0082] In an alternative embodiment, the dynamic weight coefficient c is dynamically adjusted according to the real-time water quality target:

[0083] When the heavy metal ion concentration exceeds the threshold, increase the weight of the heavy metal ion concentration score;

[0084] When the suspended solid concentration exceeds the threshold, increase the weight of the suspended solid concentration score;

[0085] When the pH value exceeds the set range, increase the weight of the pH value deviation score.

[0086] In this embodiment, by dynamically adjusting the weight coefficient c, the system can prioritize optimizing key indicators according to the real-time water quality target:

[0087] When the heavy metal ion concentration exceeds the standard, the system preferentially adjusts the flocculant dosage to improve the removal efficiency of heavy metal ions.

[0088] When the pH value exceeds the set range, the system preferentially adjusts the lime dosage to quickly restore the pH value to a reasonable range.

[0089] When the suspended solid concentration exceeds the standard, the system adjusts the flocculant dosage and sedimentation time to improve the removal efficiency of suspended solids.

[0090] This dynamic adjustment mechanism not only improves the adaptability and flexibility of the system, but also ensures that the wastewater treatment process is always in an optimal state under complex working conditions, thereby improving the treatment efficiency, reducing resource waste, and extending the service life of the equipment.

[0091] In an alternative embodiment, the heavy metal ion concentration and suspended solid concentration of the effluent water quality are monitored in real time through the deep neural network model, and the monitoring results are fed back to the reflux ratio calculation model for iterative optimization.

[0092] In this embodiment, the real-time monitoring function of the deep neural network model is combined with the dynamic optimization function of the reflux ratio calculation model to form a closed-loop control system. This system can dynamically adjust the operating parameters according to the real-time water quality data to ensure the efficiency and stability of the wastewater treatment process.

[0093] In practical applications, the prediction accuracy and response speed of the deep neural network model are crucial for the optimization effect of the wastewater treatment system. Through training with a large amount of historical data, the model can accurately predict the key indicators of the effluent water quality and provide reliable feedback information for the reflux ratio calculation model. This dynamic optimization method based on deep learning not only improves the wastewater treatment efficiency but also reduces resource waste and equipment wear, with significant economic and environmental benefits.

[0094] In an alternative embodiment, the training data of the deep neural network model includes the pH value, liquid level data, chemical dosage parameters, and corresponding treatment effect scores collected during the historical wastewater treatment process.

[0095] In this embodiment, these data are collected in real time through sensors and the control system and stored in the database, providing rich samples for model training.

[0096] Specifically, in this embodiment, the training method of the deep neural network model is as follows:

[0097] The collected historical data first needs to be cleaned to remove outliers and missing values; next, the pH value and liquid level data are normalized to a range between 0 and 1 so that the model can learn better; the treatment effect score is used as the target variable, and other parameters are used as input features.

[0098] Construct a deep neural network model and select an appropriate network structure.

[0099] The historical data is divided into a training set, a validation set, and a test set with proportions of 70%, 15%, and 15% respectively. The training set data is used to train the model, and the model performance is evaluated on the validation set every 100 epochs, and the model with the best performance on the validation set is saved. The performance of the final model is evaluated using the test set data to ensure that the model has good generalization ability.

[0100] In an alternative embodiment, the operating parameters for controlling the transfer pump include: adjusting the rotation speed of the reflux pump to match the sludge reflux ratio according to the calculation result of the sludge reflux flow rate.

[0101] In this embodiment, in the method for treating acidic wastewater by the high-density sludge process, controlling the operating parameters of the transfer pump is one of the key links to ensure the efficient operation of the system. In particular, according to the calculation result of the sludge return flow rate, dynamically adjusting the rotational speed of the return pump to match the sludge return ratio can significantly improve the stability and treatment effect of the system.

[0102] In an alternative embodiment, the set range is a pH value of 5.8 - 9.2.

[0103] In this embodiment, in the method for treating acidic wastewater by the high-density sludge process, maintaining the pH value in the reaction device within the set range is the key to ensuring the wastewater treatment effect. The set pH value range in the present invention is 5.8 - 9.2, and this range can ensure the effective precipitation of heavy metal ions in the wastewater, while avoiding resource waste and the decline of treatment effect caused by excessive lime dosing.

[0104] As can be seen from the above, this embodiment provides a method for treating acidic wastewater by the high-density sludge process, which specifically includes the following steps:

[0105] Step 1: The lime in the lime storage tank 1 is sent into the mixing tank 3, and at the same time, the return sludge in the sedimentator 7 is sent to the mixing tank 3. The stirring shaft 101 drives the stirring blades 102 to mix the return sludge and lime, and then the mixed liquid is sent into the first reactor 4;

[0106] Step 2: Wastewater is added into the first reactor 4 from the wastewater inlet pipe 43. The stirring shaft 101 drives the stirring rod 103 to stir the wastewater and the mixed liquid evenly. At the same time, compressed air is sent into the first reactor 4 from the air inlet pipe 111 through the aeration nozzles 110 at the upper end of the aeration pipe 109. The mixed liquid sequentially passes through the second reactor 5, the flocculation tank 6, and the sedimentator 7. The sedimentation time of the mixed liquid in the sedimentator 7 is 20 - 120 min. The sedimented bottom sludge is discharged to the sludge main pipe through the bottom central pipe, and the discharged sludge is metered and collected through the external discharge valve and enters the subsequent filter press. Part of the sludge is refluxed to the lime / sludge mixing tank through the reflux pipeline 72. The reflux sludge returns to the mixing tank 3 through the reflux pipeline 72 under the action of the return pump 106;

[0107] Step 3: The pH meter 9 and the liquid level meter 10 monitor the pH value and the liquid level in real time, and send them to the data processing module 83 through the data transmission module 82. The data processing module 83 calculates the treatment result according to the reflux ratio calculation model, and then feeds back the treatment result to the control module 81. The control module 81 issues instructions to the motor 100, the transfer pump 104, the water pump 105, and the return pump 106 to adjust the lime dosing amount, the flocculant dosing amount, the water pump flow rate, and the sludge return flow rate, so as to control the reflux ratio.

[0108] A reflux ratio calculation model is preset in the data processing module 83. The reflux ratio calculation model calculates the lime dosage, flocculant dosage, water pump flow rate, and sludge reflux flow rate through the simulated annealing algorithm, so as to control the reflux ratio.

[0109] The calculation steps of the reflux ratio calculation model include:

[0110] Step a: Preset the initial temperature T max , the lowest temperature T min , the temperature reduction coefficient δ, and the maximum number of iterations ξ, and let the current temperature T = T max ; The initial temperature T max , the lowest temperature T min , the temperature reduction coefficient δ, and the maximum number of iterations ξ are all preset by those skilled in the art according to the actual situation.

[0111] Step b: Preset M sets of adjustment parameters, where M is an integer greater than 1. The adjustment parameters include lime dosage, flocculant dosage, water pump flow rate, and sludge reflux flow rate; randomly set a feasible solution, and the feasible solution is the adjustment parameter, and the range of the feasible solution is M sets of adjustment parameters; among them, M sets of adjustment parameters are collected by those skilled in the art according to the technical parameters of the mixing device, the reaction device, the flocculation device, and the precipitation device, and the range corresponding to each parameter in the adjustment parameters is collected, and a value is randomly selected from each range for combination to obtain M sets of adjustment parameters.

[0112] Step c: Determine the fitness function;

[0113] The expression of the fitness function is: f = cx;

[0114] In the formula, f is the fitness, and cx is the treatment effect;

[0115] The method for obtaining the treatment effect is: taking the adjustment parameters, pH value, and liquid level corresponding to the feasible solution χ as analysis data; inputting the analysis data into the trained effect prediction model to predict the corresponding treatment effect; the matching prediction model is a deep neural network model, and the deep neural network model is a prior art and will not be elaborated here; the treatment effect corresponding to the analysis data is collected by those skilled in the art during the historical acid wastewater treatment process, and n sets of analysis data are collected, where n is an integer greater than 1. According to the actual treatment situation, the treatment effect corresponding to each set of analysis data is analyzed in turn, and the corresponding treatment effect is set for the n sets of analysis data in turn.

[0116] Step d: Calculate the fitness f corresponding to the feasible solution χ; taking the feasible solution χ as the current point, perform random perturbation in the neighborhood of the current point to obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′.

[0117] Step e: Calculate the fitness difference f″, and the expression of the fitness difference is f″ = f′ - f; if the fitness difference f″ > 0, then let χ = χ′, that is, assign the value of the new feasible solution to the feasible solution; if the fitness difference f″ ≤ 0, then calculate the probability p′, and let χ = χ′ according to the probability p′; the expression of the probability p′ is: where e is the natural constant.

[0118] Step f: Loop steps d to e until the number of loops reaches the maximum number of iterations, and then the loop ends; let the current temperature T = T × δ, that is, cool down the current temperature in step a and assign the cooled value to the current temperature; let the maximum number of iterations ξ = ξ × δ, that is, assign the reduced value of the maximum number of iterations to the maximum number of iterations; if the reduced maximum number of iterations is not an integer, then round up the reduced maximum number of iterations to make it an integer.

[0119] Step g: Loop steps d to f until the current temperature T < T min at this time, the loop ends, and the adjustment parameter corresponding to the feasible solution is obtained.

[0120] It should be understood that through the reflux ratio calculation model, key adjustment parameters such as the lime dosage, flocculant dosage, water pump flow rate, and sludge reflux flow rate can be effectively adjusted, so as to achieve precise control of the reflux ratio; by setting appropriate temperature and iteration parameters and combining with the deep neural network model to predict the treatment effect, the best adjustment parameters can be found in multiple iterations, improving the wastewater treatment effect and system operation efficiency; the introduction of the simulated annealing algorithm not only ensures the ability of global search and avoids falling into local optimal solutions, but also effectively balances the randomness and convergence of the search by dynamically adjusting the temperature and the number of iterations, and finally obtains the optimal feasible solution.

[0121] In the second aspect, the present invention provides a control system for treating acidic wastewater by the high-density sludge method, adopting the method described in any one of the foregoing embodiments.

[0122] This embodiment provides a system for treating acidic wastewater by the high-density sludge method, including a lime storage tank 1, a flocculant storage tank 2, a mixing tank 3, a first reactor 4, a second reactor 5, a flocculation tank 6, a sedimentation tank 7, and a control device 8.

[0123] As Figure 3 shown, in an optional embodiment, the lime storage tank 1 is arranged behind the mixing tank 3, the first reactor 4, the second reactor 5, the flocculation tank 6, and the sedimentation tank 7 are all arranged on the right side of the mixing tank 3, and the flocculant storage tank 2 is arranged behind the flocculation tank 6.

[0124] In an alternative embodiment, a detachable top cover 11 of the lime storage tank 1 is installed at the top of the lime storage tank 1, and a lime feeding port 12 is provided on the top cover 11 of the lime storage tank; a detachable top cover 21 of the flocculant storage tank is installed at the top of the flocculant storage tank 2, and a flocculant feeding port 22 is provided on the top cover 21 of the flocculant storage tank; a mixing tank seal cover 31 is installed at the top of the mixing tank 3, and a flocculation tank seal cover 61 is installed at the top of the flocculation tank 6; a first reactor top cover 41 is installed at the top of the first reactor 4, a second reactor top cover 51 is installed at the top of the second reactor 5, and a detachable sedimentation tank top cover 71 is installed at the top of the sedimentation tank 7.

[0125] In a preferred embodiment, in order to make the materials in each device mix more evenly, motors 100 are provided on both the mixing tank seal cover 31 and the flocculation tank seal cover 61. The motors 100 are connected to the stirring shaft 101 through couplings, and stirring blades 102 are provided at the ends of the stirring shaft 101. Motors 100 are also provided on both the first reactor top cover 41 and the second reactor top cover 51. The motors 100 are connected to the stirring shaft 101 through couplings, and equally spaced stirring rods 103 are installed on the stirring shaft 101.

[0126] pH meters 9 and liquid level gauges 10 are installed on the inner side walls of the mixing tank 3, the first reactor 4, the second reactor 5, and the flocculation tank 6. It can be understood that the positions of the pH meters 9 and the liquid level gauges 10 can be set according to the actual situation and are not limited to those shown in the drawings of this application.

[0127] As Figure 3 shown, exemplarily, the connection manner between the containers can be:

[0128] The lower part of the side of the lime storage tank 1 communicates with the top of the mixing tank 3 through a first pipeline 13. The lower part of the side of the mixing tank 3 communicates with the top of the first reactor 4 through a second pipeline 32. The lower part of the side of the first reactor 4 communicates with the top of the second reactor 5 through a third pipeline 42. The lower part of the side of the second reactor 5 communicates with the top of the flocculation tank 6 through a fourth pipeline 52. The lower part of the side of the flocculation tank 6 communicates with the top of the sedimentation tank 7 through a fifth pipeline 62. The lower part of the side of the sedimentation tank 7 communicates with the top of the mixing tank 3 through a reflux pipeline 72. The lower part of the side of the flocculant storage tank 2 communicates with the top of the flocculation tank 6 through a sixth pipeline 23.

[0129] In order to ensure the power of the material flow and the accuracy of metering and control, in a preferred embodiment, delivery pumps 104 are provided on both the first pipeline 13 and the sixth pipeline 23, water pumps 105 are provided on the second pipeline 32, the third pipeline 42, the fourth pipeline 52, and the fifth pipeline 62, and a reflux pump 106 and a flow meter 107 are provided on the reflux pipeline 72.

[0130] To facilitate the input of wastewater into the reaction device, in an alternative embodiment, a wastewater inlet pipe 43 is provided at the upper part of the side of the first reactor 4, and a flow valve 108 is provided on the wastewater inlet pipe 43.

[0131] To facilitate the discharge of the treated water, in an alternative embodiment, an overflow port 73 is provided at the upper part of the side of the sedimentation tank 7.

[0132] To improve the reaction efficiency and reaction uniformity, in a preferred embodiment, air diffuser pipes 109 are provided at the inner bottom of both the first reactor 4 and the second reactor 5, and aeration nozzles 110 are evenly distributed on the air diffuser pipes 109; the air diffuser pipes 109 are communicated with a gas source through an air inlet pipe 111.

[0133] To ensure fast and accurate control, in a preferred embodiment, the control device 8 includes a control module, a data transmission module, and a data processing module. The data transmission module is used to transmit data, and its data input terminals are electrically connected to the pH meter 9, the liquid level meter 10, the flow meter 107, and the flow valve 108 respectively, and its data output terminal is electrically connected to the data processing module; the data processing module calculates and processes the data from the data transmission module, outputs the result to the control module, and the control module issues instructions based on the result output by the data processing module to control the motor 100, the delivery pump 104, the water pump 105, and the reflux pump 106, and adjusts the dosages of lime and flocculant, the material stirring speed, and the conveying speed.

[0134] It should be noted that the control device 8 is also provided with facilities such as an operation panel for manually inputting relevant parameters or other data to the data transmission module, so as to enable manual adjustment of relevant control actions.

[0135] The beneficial effects of the embodiments of the present invention are as follows:

[0136] By real-time monitoring of the pH value and liquid level data, and dynamically optimizing the lime dosage, flocculant dosage, and sludge reflux flow rate in combination with the simulated annealing algorithm, the following breakthroughs have been achieved:

[0137] 1) By real-time monitoring of the pH value of the wastewater, the model calculates the required lime addition amount based on the simulated annealing algorithm, adjusts the lime dosage and stirring speed, and keeps the pH value within the set range (5.8 - 9.2) to ensure the efficient progress of the wastewater neutralization reaction;

[0138] 2) Combining the deep neural network to predict the influence of different flocculant dosages on the heavy metal ion precipitation effect, and optimizing the flocculant dosage through the simulated annealing algorithm to enhance the precipitation effect and ensure that the heavy metal concentration meets the standard;

[0139] 3) The model adjusts the flocculant dosage and sedimentation time according to the real-time monitored suspended solid concentration, improves the suspended solid removal efficiency, and ensures that the effluent quality meets the standard.

[0140] 4) In terms of sludge reflux control, the model monitors the composition of neutralized sludge in real time, optimizes the sludge reflux ratio, reduces lime consumption, and improves the wastewater treatment effect at the same time. It quickly and accurately regulates the bottom sludge reflux ratio and the input amount of lime, avoiding waste caused by excessive lime usage and ensuring that the sewage treatment effect is not affected by too little lime usage. As a result, the pH value of the system is maintained within a stable range, and a relatively stable reflux ratio is maintained. The sewage treatment effect does not change with the change of the influent water volume, ensuring the stable operation of the system, achieving a better sewage treatment effect, having a low calcium ion content in the water, effectively delaying the scaling phenomenon of equipment and pipelines, and ensuring the normal operation of treatment facilities;

[0141] 5) In terms of automatic valve control, the model calculates the appropriate influent water flow rate and adjusts the opening degree of the influent valve to ensure a stable wastewater flow rate; by monitoring the effluent water quality in real time, it adjusts the opening degree of the effluent valve to maintain stable water quality and meet the flow rate requirements.

[0142] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various changes and modifications can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for treating acidic wastewater by a high-density slurry method, characterized in that: The following operations are performed via the control unit: Receive the real-time pH value fed back by the pH meter in the reaction device and the liquid level data of the liquid level meter; Inputting the real-time pH value and the liquid level data into a preset reflux ratio calculation model, the reflux ratio calculation model calculates the lime dosage, the flocculant dosage and the sludge reflux flow rate through a simulated annealing algorithm; The operating parameters of the delivery pump, reflux pump and stirring device are controlled according to the calculation results to maintain the pH value in the reaction device within the set range.

2. The method for treating acidic wastewater by high-density slurry method according to claim 1, characterized in that: The execution of the simulated annealing algorithm comprises the following steps: Step a: Initialize temperature parameter T max , minimum temperature T min Cooling coefficient δ and maximum number of iterations ξ; Step b, randomly generating M groups of feasible solutions including lime dosage, flocculant dosage, and sludge return flow rate; Step c, calculating the fitness value f=cx of each set of solutions through the deep neural network model, where x is the processing effect score and c is the dynamic weight coefficient; Step d: By probability Accept the degraded solution, update the temperature T = T × δ, and the number of iterations ξ = ξ × δ; Step e: When T <T min The calculation is terminated when , and the optimal parameter combination is output.

3. The method for treating acidic wastewater by high-density slurry method according to claim 2, characterized in that: The probability described in step d The fitness difference f″ is calculated as: f″=f′-f Where f′ is the fitness value of the new solution, and f is the fitness value of the current solution.

4. The method for treating acidic wastewater by high-density slurry method according to claim 2, characterized in that: The treatment effect score x is predicted by a deep neural network model, specifically including: The input parameters are lime dosage, flocculant dosage, sludge return flow, real-time pH value and liquid level data; The output parameters are pH value deviation score, heavy metal ion concentration score and suspended solids concentration score, and x is the weighted sum of the three.

5. The method for treating acidic wastewater by high-density slurry method according to claim 2, characterized in that: The dynamic weight coefficient c is dynamically adjusted according to the real-time water quality target: When the heavy metal ion concentration exceeds the threshold, the heavy metal ion concentration score weight is increased; When the suspended matter concentration exceeds the threshold, the suspended matter concentration score weight is increased; When the pH value exceeds the set range, the pH deviation score weight is increased.

6. The method for treating acidic wastewater by high-density slurry method according to claim 2, characterized in that: The heavy metal ion concentration and suspended solids concentration of the effluent water quality are monitored in real time through a deep neural network model, and the monitoring results are fed back to the reflux ratio calculation model for iterative optimization.

7. The method for treating acidic wastewater by high-density slurry method according to claim 2, characterized in that: The training data of the deep neural network model includes pH values, liquid level data, dosage parameters and corresponding treatment effect scores collected during historical wastewater treatment.

8. The method for treating acidic wastewater by high-density slurry method according to claim 1, characterized in that: The operating parameters of the control delivery pump include: adjusting the rotation speed of the return pump to match the sludge return ratio according to the calculation result of the sludge return flow rate.

9. The method for treating acidic wastewater by high-density slurry method according to claim 1, characterized in that: The setting interval is pH 5.8-9.

2.

10. A control system for treating acidic wastewater using a high-density slurry method, characterized in that: The method according to any one of claims 1 to 9 is adopted.

Images