Zinc-containing waste neutral leaching process parameter control method

Abstract

The invention is applicable to the technical field of neutral leaching of zinc-containing waste, and particularly relates to a zinc-containing waste neutral leaching process parameter control method which comprises the following steps: acquiring real-time state parameters of raw materials in a reaction kettle; obtaining a pollution index according to the real-time state parameter; obtaining a first target parameter based on the pollution index and the real-time state parameter; based on the correlation between the real-time state parameters and the first target parameters, determining a first correlation feature of each parameter in the first target parameters; determining a second correlation feature of each parameter in the first target parameters based on the correlation among the first correlation feature, the real-time state parameter and the first target parameters; determining at least one parameter adjustment feature based on the first association feature and the second association feature; and adjusting the first target parameter according to the at least one parameter adjustment feature to obtain a second target parameter. Therefore, according to the method provided by the invention, the sulfuric acid mist and noise pollution can be effectively controlled while the high zinc leaching rate is ensured.

Description

Technical Field

[0001] This application belongs to the field of neutral leaching technology for zinc-containing waste, and particularly relates to a method for controlling process parameters in the neutral leaching of zinc-containing waste. Background Technology

[0002] Neutral leaching technology for zinc-containing waste typically uses sulfuric acid solution as the leaching agent. Under conditions of 70-75℃ and final pH of 5.0-5.2, by controlling the leaching time and liquid-solid ratio, zinc in zinc calcined sand is selectively dissolved into the solution. At the same time, impurities such as germanium and arsenic are removed by adsorption or co-precipitation using ferric hydroxide colloids.

[0003] In existing technologies, sulfuric acid mist mainly originates from the volatilization of sulfuric acid during the leaching process. Increasing the leaching temperature or stirring speed can accelerate zinc dissolution (increasing the leaching rate), but it also exacerbates sulfuric acid volatilization, leading to an increase in sulfuric acid mist concentration. Stirring speed is a key parameter affecting leaching efficiency, but high-speed stirring can increase equipment vibration and generate noise pollution. Therefore, in existing neutral leaching processes for zinc-containing waste, it is difficult to effectively control sulfuric acid mist and noise pollution while ensuring a high zinc leaching rate. Summary of the Invention

[0004] This application provides a method for controlling parameters in the neutral leaching process of zinc-containing waste, which can effectively control sulfuric acid mist and noise pollution while ensuring a high zinc leaching rate.

[0005] In a first aspect, embodiments of this application provide a method for controlling parameters in a neutral leaching process for zinc-containing waste, including: The real-time state parameters of the raw materials in the reactor are obtained; wherein, the real-time state parameters include temperature, liquid-to-solid ratio and vibration frequency; The pollution index is obtained based on the real-time status parameters; wherein, the pollution index includes sulfuric acid mist concentration and noise index; A first target parameter is obtained based on the pollution index and the real-time status parameters; wherein, the first target parameter includes stirring speed, filtration pressure and / or reaction time; Based on the correlation between the real-time status parameters and the first target parameters, a first correlation feature is determined for each parameter in the first target parameters; wherein, the first correlation feature is used to reflect the impact of adjusting one process parameter on another status parameter under the current operating conditions; Based on the correlation between the first correlation feature, the real-time state parameter, and the first target parameter, a second correlation feature is determined for each parameter in the first target parameter; wherein, the second correlation feature is used to reflect the influence of the first correlation feature on the current state; At least one parameter adjustment feature is determined based on the first association feature and the second association feature; wherein the parameter adjustment feature is used to reflect the direction and degree of adjustment of the first target parameter; The second target parameter is obtained by adjusting the feature according to at least one of the parameters.

[0006] The technical solutions described in this application embodiment have at least the following technical effects: The method for controlling parameters in the neutral leaching process of zinc-containing waste provided in this application involves: acquiring real-time state parameters of the raw materials in the reactor; obtaining a pollution index based on the real-time state parameters; obtaining a first target parameter based on the pollution index and the real-time state parameters; determining a first correlation feature for each parameter in the first target parameter based on the correlation between the real-time state parameters and the first target parameter; determining a second correlation feature for each parameter in the first target parameter based on the correlation between the first correlation feature, the real-time state parameters, and the first target parameter; determining at least one parameter adjustment feature based on the first and second correlation features; and adjusting the first target parameter according to the at least one parameter adjustment feature to obtain a second target parameter. Therefore, the method for controlling parameters in the neutral leaching process of zinc-containing waste provided in this application achieves comprehensive monitoring and real-time optimization of the reaction process by real-time monitoring of multiple state parameters in the reactor and comprehensively considering the correlation and influence between multiple parameters. This helps to reduce sulfuric acid mist concentration and noise level, reduce environmental impact, and achieve environmentally friendly production while improving reaction efficiency and product quality, and reducing energy and material consumption through precise control of process parameters.

[0007] In one possible implementation of the first aspect, obtaining the pollution index based on the real-time state parameters includes: Obtain raw material information; wherein, the raw material information includes zinc content, impurity types and contents, and particle size distribution; The current information sequence during the neutral leaching process is obtained based on the real-time status parameters; wherein, the current information sequence includes the sulfuric acid mist concentration and noise at each node of solution preparation, stirring leaching, endpoint detection and / or solid-liquid separation; The position weights are determined based on the current information sequence; wherein, the position weights refer to the weight coefficients of each node. The degree of attention is obtained based on the correlation between the raw material information and the current information sequence; wherein, the degree of attention is used to reflect the degree of influence of each attribute of the raw material on the pollution index of each node; The contamination index for the next node in the neutral leaching process is determined based on the location weight and the level of attention.

[0008] In one possible implementation of the first aspect, obtaining the attention level based on the correlation between the raw material information and the current information sequence includes: Based on the raw material information, determine the correlation between each attribute of the raw material and the current information sequence, and sort them to obtain an importance sequence; The attention level is obtained by assigning weights to each attribute of the raw material based on the importance sequence.

[0009] In one possible implementation of the first aspect, obtaining the first target parameter based on the pollution index and the real-time state parameter includes: The influence coefficients of the real-time state parameters were obtained through analysis; The first target parameter is obtained based on the influence coefficient and the pollution index.

[0010] In one possible implementation of the first aspect, determining the first correlation feature of each parameter in the first target parameter based on the correlation between the real-time state parameter and the first target parameter includes: Calculate the first correlation coefficient between the real-time state parameters and the first target parameters to obtain the correlation matrix; Based on the correlation matrix, the first association feature of each parameter in the first target parameter is obtained.

[0011] In one possible implementation of the first aspect, determining the second association feature of each parameter in the first target parameter based on the correlation between the first association feature, the real-time state parameter, and the first target parameter includes: Based on the first correlation feature, for every two target parameters in the first target parameters, a second correlation coefficient is calculated between the corresponding state influence vectors; wherein, the state influence vector is composed of the first correlation coefficients between the parameters in the first target parameters and each parameter of the real-time state parameters; The second correlation feature is obtained based on the second correlation coefficient.

[0012] In one possible implementation of the first aspect, determining at least one parameter adjustment feature based on the first association feature and the second association feature includes: The first associated feature and the second associated feature are respectively mapped to the first dimension and the second dimension of the parameter adjustment feature space to construct the parameter adjustment feature space. The fusion distance between the first associated feature and the second associated feature is calculated based on the adjusted feature space according to the parameters. At least one parameter adjustment feature is obtained based on the fusion distance clustering.

[0013] In one possible implementation of the first aspect, the method further includes: The decision is made based on the real-time status parameters whether to directly perform secondary operations on the raw materials in the reactor according to the first target parameters; wherein, the secondary operations include secondary stirring, pressure filtration and / or extending the reaction time.

[0014] In one possible implementation of the first aspect, the method further includes: If it is determined based on the real-time status parameters that the secondary operation on the raw materials in the reactor should not be performed directly based on the first target parameters, then the first target parameters are adjusted to obtain the second target parameters, and the secondary operation is performed based on the second target parameters.

[0015] In one possible implementation of the first aspect, adjusting the first target parameter according to at least one of the parameter adjustment features to obtain the second target parameter includes: Multiple candidate parameter vectors are constructed based on the adjustment features for each parameter; wherein, the candidate parameter vector refers to possible combinations of parameters constructed based on the parameter adjustment features; The corresponding effect prediction score is obtained based on each candidate parameter vector and the real-time state parameter. Based on the predicted effect scores, candidate parameter vectors that are greater than a preset effect threshold are selected, and the first target parameter is adjusted according to the candidate parameter vectors that are greater than the effect threshold to obtain the second target parameter.

[0016] Secondly, embodiments of this application provide a parameter control device for the neutral leaching process of zinc-containing waste, comprising: The acquisition module is used to acquire real-time state parameters of the raw materials in the reactor; wherein, the real-time state parameters include temperature, liquid-to-solid ratio and vibration frequency; The pollution index module is used to obtain the pollution index based on the real-time status parameters; wherein, the pollution index includes sulfuric acid mist concentration and noise index; The first target parameter module is used to obtain a first target parameter based on the pollution index and the real-time status parameter; wherein, the first target parameter includes stirring speed, filtration pressure and / or reaction time; The first correlation feature module is used to determine a first correlation feature for each parameter in the first target parameter based on the correlation between the real-time state parameter and the first target parameter; wherein, the first correlation feature is used to reflect the impact of adjusting one process parameter on another state parameter under the current operating condition; The second correlation feature module is used to determine a second correlation feature for each parameter in the first target parameter based on the correlation between the first correlation feature, the real-time state parameter, and the first target parameter; wherein the second correlation feature is used to reflect the influence of the first correlation feature on the current state; A parameter adjustment feature module is used to determine at least one parameter adjustment feature based on the first association feature and the second association feature; wherein the parameter adjustment feature is used to reflect the direction and degree of adjustment of the first target parameter; The second target parameter module is used to adjust the first target parameter according to at least one of the parameter adjustment features to obtain the second target parameter.

[0017] Thirdly, embodiments of this application provide a device for controlling parameters in a neutral leaching process of zinc-containing waste, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method as described in any one of the first aspects above.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the first aspects above.

[0019] Fifthly, embodiments of this application provide a computer program product that, when run on a neutral leaching process parameter control device for zinc-containing waste, causes the device to perform the method described in any one of the first aspects.

[0020] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic flowchart of a method for controlling parameters in the neutral leaching process of zinc-containing waste according to an embodiment of this application; Figure 2 This is a schematic diagram of the implementation process of steps S200 and S240 in the neutral leaching process parameter control method for zinc-containing waste provided in an embodiment of this application; Figure 3 This is a schematic diagram of the implementation process of steps S300, S400 and S500 in the method for controlling process parameters of neutral leaching of zinc-containing waste provided in an embodiment of this application. Figure 4 This is a schematic diagram of the implementation process of steps S600 and S700 in the method for controlling process parameters of neutral leaching of zinc-containing waste provided in an embodiment of this application; Figure 5 This is a schematic diagram showing the changes in temperature, sulfuric acid mist concentration, and noise index with leaching time in a method for controlling parameters of the neutral leaching process of zinc-containing waste provided in an embodiment of this application. Figure 6 This is a schematic diagram illustrating the prediction of parameter adjustment effects in a parameter control method for the neutral leaching process of zinc-containing waste provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of the neutral leaching process parameter control device for zinc-containing waste provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of the neutral leaching process parameter control device for zinc-containing waste provided in the embodiments of this application. Detailed Implementation

[0023] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0024] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0025] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0026] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0027] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0029] In related technologies, sulfuric acid mist mainly originates from the volatilization of sulfuric acid during the leaching process. Increasing the leaching temperature or stirring speed can accelerate zinc dissolution (increasing the leaching rate), but it also exacerbates sulfuric acid volatilization, leading to an increase in sulfuric acid mist concentration. Stirring speed is a key parameter affecting leaching efficiency, but high-speed stirring can increase equipment vibration and generate noise pollution. Therefore, in existing neutral leaching processes for zinc-containing waste, it is difficult to effectively control sulfuric acid mist and noise pollution while ensuring a high zinc leaching rate.

[0030] To address the aforementioned issues, this application provides a method for controlling process parameters in the neutral leaching of zinc-containing waste. This method involves: acquiring real-time state parameters of the raw materials in the reactor; obtaining a pollution index based on the real-time state parameters; obtaining a first target parameter based on the pollution index and the real-time state parameters; determining a first correlation feature for each parameter in the first target parameter based on the correlation between the real-time state parameters and the first target parameter; determining a second correlation feature for each parameter in the first target parameter based on the correlation between the first correlation feature, the real-time state parameters, and the first target parameter; determining at least one parameter adjustment feature based on the first and second correlation features; and adjusting the first target parameter according to the at least one parameter adjustment feature to obtain a second target parameter. Therefore, the method for controlling process parameters in the neutral leaching of zinc-containing waste provided by this application achieves comprehensive monitoring and real-time optimization of the reaction process by real-time monitoring of multiple state parameters within the reactor and comprehensively considering the correlation and influence between these parameters. This helps reduce sulfuric acid mist concentration and noise levels, minimizing environmental impact and achieving environmentally friendly production. Simultaneously, it improves reaction efficiency and product quality while reducing energy and material consumption through precise control of process parameters.

[0031] The method for controlling the parameters of the neutral leaching process of zinc-containing waste provided in this application embodiment can be applied to the device for controlling the parameters of the neutral leaching process of zinc-containing waste. In this case, the device for controlling the parameters of the neutral leaching process of zinc-containing waste is the subject of execution of the method for controlling the parameters of the neutral leaching process of zinc-containing waste provided in this application embodiment. This application embodiment does not impose any restrictions on the specific type of device for controlling the parameters of the neutral leaching process of zinc-containing waste.

[0032] For example, the parameter control equipment for the neutral leaching process of zinc-containing waste can be an industrial computer, a programmable logic controller, an embedded control system, a distributed control system, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a desktop computer, a laptop computer, a handheld computing device, etc., but is not limited to these.

[0033] To better understand the parameter control method for the neutral leaching process of zinc-containing waste provided in this application embodiment, the specific implementation process of the parameter control method for the neutral leaching process of zinc-containing waste provided in this application embodiment will be described by way of example below.

[0034] Figure 1 This illustration shows a schematic flowchart of a method for controlling parameters in a neutral leaching process of zinc-containing waste, provided in an embodiment of this application. The method includes: S100: Acquire real-time state parameters of the raw materials in the reactor. These real-time state parameters include temperature, liquid-to-solid ratio, and vibration frequency.

[0035] For example, key parameters of a reaction vessel can be acquired in real time using an industrial IoT sensor array. For instance, a PT100 platinum resistance sensor (accuracy ±0.1℃) can be used to obtain temperature (e.g., ...). Figure 5 As shown, the liquid-to-solid ratio is calculated by a Coriolis mass flow meter (measurement accuracy 0.2%) and an online density meter (resolution 0.001 g / cm³). The vibration frequency is obtained by a triaxial accelerometer (sampling frequency 1 kHz). The data is transmitted to the edge computing gateway in real time via the Modbus TCP protocol. After noise reduction by Kalman filtering, the data is updated to the neutral leaching process parameter control system of zinc-containing waste at a frequency of 1 Hz.

[0036] S200 is a pollution index derived from real-time status parameters. This pollution index includes sulfuric acid mist concentration and noise level.

[0037] For example, a sulfuric acid mist concentration model and a noise index model can be established. For instance, an empirical formula based on the gas-liquid balance principle can be used to obtain the sulfuric acid mist concentration model based on historical production data (including temperature, solid-liquid ratio, and sulfuric acid mist concentration). =0.5×T+0.3×(liquid / solid)+10, where T is the temperature (°C). When T=150°C and the liquid-to-solid ratio=3.33, the calculation yields: =0.5×150+0.3×3.33+10=85.0ppm; The noise index model uses the A-weighted sound pressure level algorithm, and the relationship between the vibration frequency f (Hz) and the noise level L (dB) is: L=20log 10 (f)+30, when f=48Hz, L=20log 10 (48)+30=53.6dB. The correlation between the dominant frequency and noise can be confirmed by analyzing the vibration signal spectrum through Fourier transform. The sulfuric acid mist concentration is verified by periodic comparison using an ion chromatograph (detection limit 0.1ppm).

[0038] For example, real-time state parameters can be input into a sulfuric acid mist concentration model and a noise index model to obtain a pollution index (such as...). Figure 5 (As shown).

[0039] S300, based on the pollution index and real-time status parameters, yields the first target parameters. These first target parameters include stirring speed, filtration pressure, and / or reaction time.

[0040] For example, the NSGA-II genetic algorithm can be used to optimize the stirring speed N (rpm), filtration pressure P (MPa), and reaction time t (h) to obtain the first target parameters. For instance, statistical methods (such as regression analysis, machine learning models, etc.) can be used to analyze historical operating data (including temperature, liquid-to-solid ratio, vibration frequency, stirring speed, filtration pressure, reaction time, sulfuric acid mist concentration, and noise level during historical operations) to establish a pollution index. The mathematical model relating L to the first objective parameters N, P, and t is then used to minimize the sulfuric acid mist concentration under real-time state parameters. Given the noise index L, the objective function is to maximize output (e.g., output Y = 0.8 × N × P × t), where 100 ≤ N ≤ 300, 0.3 ≤ P ≤ 0.8, and 1 ≤ t ≤ 5. Through multi-generational evolutionary calculations, the Pareto optimal solution is obtained: N = 220 rpm, P = 0.5 MPa, t = 3 h. =78ppm, L=51dB, yield Y=330kg.

[0041] S400, based on the correlation between real-time state parameters and the first target parameters, determines the first correlation feature of each parameter in the first target parameters. The first correlation feature reflects the impact of adjusting one process parameter on another state parameter under the current operating conditions.

[0042] It is understandable that the first correlation feature is used to reflect the intensity of the direct influence of adjusting one parameter in the first target parameters on one parameter in the real-time state parameters under the current operating conditions.

[0043] For example, the correlation between each (state) parameter in the real-time state parameters and each (process) parameter in the first target parameters can be quantified using the Pearson correlation coefficient matrix to obtain the first correlation feature of each parameter in the first target parameters.

[0044] S500, based on the correlation between the first correlation feature, the real-time state parameter, and the first target parameter, determines the second correlation feature for each parameter in the first target parameter. The second correlation feature reflects the influence of the first correlation feature on the current state.

[0045] It is understandable that the second correlation feature is used to reflect the lag or cumulative effect of the first correlation feature on the current state.

[0046] For example, an LSTM neural network model can be constructed based on historical operational data to capture time-series dependencies and obtain the second associated feature for each parameter in the first objective parameter. The input layer contains T (temperature), R (liquid-to-solid ratio), and f (vibration frequency) data from the past hour, while the output layer predicts changes in C (sulfuric acid mist concentration) and L (noise index) for the next 10 minutes. The model is trained using the Adam optimizer with MSE as the loss function, a learning rate of 0.001, and 100 training epochs. The SHAP values ​​are used to interpret the prediction results of the LSTM neural network model. For example, the SHAP values ​​show that f contributes 35% to C, 28% to T, and 17% to R.

[0047] S600, at least one parameter adjustment feature is determined based on the first correlation feature and the second correlation feature. The parameter adjustment feature reflects the direction and degree of adjustment of the first target parameter.

[0048] It is understandable that the degree of influence of adjusting the first target parameter on the real-time state parameter is determined based on the first and second correlation features, the change in the pollution index is determined based on the degree of influence on the real-time state parameter, and the direction and degree of adjustment of the first target parameter are determined based on the change in the pollution index.

[0049] For example, an adjustment rule base can be established based on a first and second correlation feature, and at least one parameter adjustment feature can be determined according to the current pollution index obtained from real-time state parameters. For instance, when the sulfuric acid mist concentration C > 80 ppm, the stirring speed N is preferentially reduced (C decreases by 3.2 ppm for every 20 rpm reduction); when L > 55 dB, the filtration pressure P is preferentially increased (the noise index L decreases by 1.8 dB for every 0.1 MPa increase). A fuzzy logic controller is used to achieve dynamic adjustment. For example, the membership function of C is defined as follows: Normal (<70 ppm): adjustment range 0%; Warning (70-90 ppm): adjustment range -10% to -5%; Danger (>90 ppm): adjustment range -20%.

[0050] S700, adjust the first target parameter according to at least one parameter to obtain the second target parameter.

[0051] For example, the effect of parameter adjustment can be simulated in a digital twin system based on features adjusted according to at least one parameter. For instance, adjusting N (stirring speed) from 220 rpm to 200 rpm predicts that C (sulfuric acid mist concentration) will decrease from 78 ppm to 74 ppm, L (noise level) from 51 dB to 49 dB, and the yield will decrease from 330 kg to 315 kg (a reduction of 4.5%). A cost-benefit analysis (approximately 50 RMB per ppm reduction in pollution cost and 200 RMB / kg per kg of yield loss) confirms a positive net benefit for this adjustment scheme. After multiple iterative adjustments, a second target parameter is determined that both the pollution index and yield meet the process requirements, such as stirring speed N = 205 rpm, filtration pressure P = 0.52 MPa, and reaction time t = 3.1 h.

[0052] In one possible implementation, please refer to Figure 2 S200, the pollution index is obtained based on real-time status parameters, including: S210, Obtain raw material information. This information includes zinc content, types and amounts of impurities, and particle size distribution.

[0053] For example, X-ray fluorescence spectroscopy (XRF) or inductively coupled plasma mass spectrometry (ICP-MS) can be used to analyze the zinc content in the raw material. Atomic absorption spectroscopy (AAS) or ICP-MS is used to detect impurity elements (such as Fe, Cu, Pb, etc.). AAS quantifies impurities by absorbing light at a specific wavelength and is suitable for single-element detection; ICP-MS can simultaneously detect multiple elements and is suitable for complex impurity systems. Particle size distribution is measured using laser diffraction (such as a Malvern laser particle size analyzer) or sieving methods. Laser diffraction calculates particle size based on the angular distribution of scattered light, covering a range of 0.01-2000 μm; sieving methods classify particles using standard sieves and are suitable for rapid analysis of coarse particles (>45 μm).

[0054] S220, obtain the current information sequence in the neutral leaching process based on real-time status parameters. The current information sequence includes the sulfuric acid mist concentration and noise at each node of solution preparation, stirred leaching, endpoint detection, and / or solid-liquid separation.

[0055] For example, the neutral leaching process can be divided into four key stages: solution preparation: the mixing stage of sulfuric acid and raw materials; stirred leaching: the stirring reaction stage in the reactor; endpoint detection: the reaction endpoint stage determined by pH / potential; and solid-liquid separation: the pressure filtration or sedimentation separation stage. Electrochemical sensors (detection range 0-100ppm, resolution 0.1ppm) are installed at each stage to monitor the sulfuric acid mist concentration, and gas samples are collected in real time using a diffusion sampling head; sound level meters (compliant with IEC61672 standard, A-weighted) are installed near the stages to monitor noise.

[0056] S230, determine the position weights based on the current information sequence. Here, position weights refer to the weight coefficients of each node.

[0057] For example, sulfuric acid mist concentration and noise data can be normalized to [0,1], according to the information entropy formula E. j =−k ij lnp ij (k=1 / lnn) Calculate the entropy value of each node. The position weight is inversely proportional to the entropy value, i.e., w j =(1−E j ) / 1−E j ).

[0058] S240, the level of attention is obtained based on the correlation between raw material information and the current information sequence. The level of attention reflects the degree of influence of each attribute of the raw material on the contamination index of each node.

[0059] For example, the degree of attention can be obtained by analyzing the correlation between raw material information and the current information sequence through grey relational analysis. For instance, by normalizing the raw material information (zinc content, Fe content, Cu content, particle size D50) and the current information sequence (sulfuric acid mist concentration, noise), the degree of attention can be determined using the formula ξi(k)=[min i min k |x0(k)−x i (k)∣+ρmax i max k |x0(k)−x i (k)∣] / [∣x0(k)−x i (k)∣+ρmax i max k |x0(k)−x i (k)∣](ρ=0.5)Calculate the correlation coefficient between raw material attributes and pollution index, normalize the correlation coefficient to [0,1], and obtain the attention of each raw material attribute to the pollution index of each node.

[0060] S250 determines the contamination index at the next node in the neutral leaching process based on location weights and attention levels.

[0061] For example, the pollution index can be obtained by weighted summation of the pollution indices (sulfuric acid mist concentration, noise) of all currently visited nodes, where the weights are the product of location weight and attention level. The pollution index of the next node is then predicted using the ARIMA model (Autoregressive Integral Moving Average). Through steps S210 to S250, a complete closed loop is formed from raw material detection to pollution prediction, supporting real-time adjustment of process parameters. Identifying key pollution factors through attention analysis helps reduce unnecessary treatment investments and optimize costs.

[0062] Optionally, please refer to Figure 2 S240, attention is determined based on the correlation between raw material information and the current information sequence, including: S241, determine the correlation between each attribute of the raw material and the current information sequence based on the raw material information, and sort them to obtain the importance sequence.

[0063] For example, correlation analysis and principal component analysis can be used to quantify the association between each attribute of the raw materials and the current information sequence. For instance, the correlation coefficient between each raw material attribute and the current information sequence can be calculated, or principal component analysis can be used to extract the main raw material attributes affecting the current information sequence. Based on the analysis results of the association relationships, the attributes of the raw materials are ranked. The ranking can be based on the absolute value of the correlation, the significance level, or the contribution to the current information sequence. The ranking result is the importance sequence.

[0064] S242 assigns weights to each attribute of the raw material based on the importance sequence to obtain attention.

[0065] For example, weights can be assigned to each attribute of a raw material based on its importance sequence, using methods such as linear or non-linear weight allocation, and the level of attention can be determined based on the weight of each attribute. For instance, in a linear weight allocation method, each attribute can be assigned a linearly decreasing weight based on its ranking in the importance sequence.

[0066] Through steps S241 to S242 above, the correlation between raw material attributes and the current information sequence is quantitatively analyzed, providing an objective and scientific basis for decision-making and improving the accuracy and reliability of decisions. The system can update the current information sequence in real time based on factors such as market changes and adjustments to production conditions, dynamically adjusting the weight and attention given to raw material attributes to make decisions more aligned with reality. By comprehensively considering multiple attributes of raw materials and their importance, resources can be allocated more rationally, improving resource utilization efficiency and reducing production costs.

[0067] In one possible implementation, please refer to Figure 3 S300, based on the pollution index and real-time state parameters, obtains the first target parameters, including: S310, the influence coefficients of the real-time state parameters are obtained through analysis.

[0068] It is understandable that the analysis yields the influence coefficients of real-time state parameters on stirring speed, filtration pressure, and reaction time.

[0069] For example, regression models (such as linear regression, random forest regression, support vector regression, etc.) can be established for each (process) parameter based on historical operating data, with real-time state parameters as input and (process) parameters as output, to obtain the influence coefficients of real-time state parameters on stirring speed, filtration pressure and reaction time.

[0070] S320, the first target parameter is obtained based on the impact coefficient and pollution index.

[0071] For example, the adjustment direction and degree of the first target parameter can be determined based on the adjustment rule base, the current pollution index, and the impact coefficient. For instance, in the adjustment rule base: if... If the standard is exceeded, reduce the stirring speed (adjustment direction: decrease; adjustment degree: influence coefficient × amount exceeding the standard). (The pollution index also includes PM2.5) If PM2.5 exceeds the standard (>35μg / m³), increase the vibration frequency (adjustment direction: increase; adjustment degree: influence coefficient × amount exceeding the standard).

[0072] Through steps S310 to S320, the quantitative analysis of the impact of real-time state parameters on the pollution index provides a scientific basis for environmental protection decision-making and improves the accuracy and reliability of decisions. Real-time updates of the impact coefficients facilitate rapid response to environmental changes, timely parameter adjustments to optimize the pollution index, and enhanced system dynamic response capabilities. By clarifying the degree of influence of each parameter on the pollution index, environmental protection resources can be allocated more rationally, such as strengthening air purification in key areas and optimizing industrial emission control, thereby improving resource utilization efficiency, contributing to the continuous improvement of environmental quality, promoting coordinated economic, social, and environmental development, and providing strong support for sustainable development.

[0073] In one possible implementation, please refer to Figure 3 S400, based on the correlation between real-time state parameters and the first target parameters, determines the first correlation feature of each parameter in the first target parameters, including: S410, calculate the first correlation coefficient between the real-time state parameters and the first target parameters to obtain the correlation matrix.

[0074] For example, for each pair of real-time state parameters x i and the first target parameter y j Appropriate correlation coefficient calculation methods are employed, such as Pearson correlation coefficient and Spearman rank correlation coefficient. The correlation coefficients between all m×n pairs of parameters are calculated sequentially, resulting in an m×n correlation matrix R, where R... ij =r ij , representing the real-time state parameter x i With the first target parameter y jThe degree of correlation between them ranges from [−1, 1], and the closer the absolute value is to 1, the stronger the correlation.

[0075] S420, based on the correlation matrix, obtain the first association feature of each parameter in the first target parameter.

[0076] For example, for each first target parameter y j Extract the correlation coefficients of all real-time state parameters related to y from the correlation matrix R (reflecting the influence of different real-time state parameters on y). j The degree and direction of influence). They can be sorted according to the absolute value of the correlation coefficient (the larger the absolute value, the greater the influence of the real-time state parameter on y). j The more significant the impact, the stronger the correlation coefficient. The sign of the correlation coefficient indicates the direction of the impact; a positive correlation indicates that as the real-time state parameter y increases, the influence is stronger. j It also tends to increase, while a negative correlation tends to increase (the opposite is true for negative correlations). For each first objective parameter y j Real-time state parameters with an absolute value of correlation coefficient greater than a preset threshold are selected as their first correlation features.

[0077] Through steps S410 to S420, by clarifying the correlation between real-time state parameters and the first target parameter and extracting the first correlation feature, it is possible to more accurately understand which factors have the greatest impact on the target parameter, thereby formulating more targeted control strategies and improving the accuracy and effectiveness of decision-making. Limited resources can be concentrated on monitoring and controlling key factors, avoiding resource waste and improving resource utilization efficiency. Real-time analysis of the dynamic relationships between parameters enables the system to better adapt to changes in environmental conditions. When environmental conditions change, the understanding of correlations and control strategies can be adjusted promptly to maintain the efficient operation of the system.

[0078] In one possible implementation, please refer to Figure 3 S500, based on the correlation between the first correlation feature, the real-time state parameter, and the first target parameter, determine the second correlation feature for each parameter in the first target parameter, including: S510, based on the first correlation feature, for every two target parameters in the first target parameters, calculate the second correlation coefficient between the corresponding state influence vectors. The state influence vector is composed of the first correlation coefficients between the parameters in the first target parameters and the parameters of the real-time state parameters.

[0079] For example, a state influence vector can be constructed for each target parameter based on a first correlation feature. This state influence vector consists of the first correlation coefficients between the target parameter and all real-time state parameters. For every two state influence vectors of target parameters, the similarity is quantified using the Pearson correlation coefficient to obtain a second correlation coefficient.

[0080] S520, the second correlation feature is obtained based on the second correlation coefficient.

[0081] For example, the second correlation feature can be obtained by determining the cooperative / competitive relationship between every two target parameters in the first target parameter based on the strength and direction of the second correlation coefficient. For instance, when the state influence vectors of two target parameters are positively correlated (e.g., r=0.9), it indicates that their influence trends on the real-time state parameters are consistent, and they can be jointly adjusted to amplify the effect; competitive feature: when they are negatively correlated (e.g., r=-0.996), simultaneous adjustment in the same direction should be avoided.

[0082] Through steps S510 to S520, multi-parameter collaborative optimization can be achieved using the second correlation feature. After identifying key correlation paths, resources can be concentrated on controlling high-impact parameters. The second correlation coefficient can quantify the chain reaction of parameter adjustments, which is beneficial for improving risk prediction capabilities.

[0083] In one possible implementation, please refer to Figure 4 S600, determining at least one parameter adjustment feature based on the first association feature and the second association feature, including: S610, the first associated feature and the second associated feature are mapped to the first dimension and the second dimension of the parameter-adjusted feature space, respectively, to construct the parameter-adjusted feature space.

[0084] For example, the first correlation feature (the correlation coefficient matrix between a single parameter and real-time parameters) and the second correlation feature (the correlation coefficient matrix of the state influence vectors between parameters) can be mapped to a two-dimensional feature space: First dimension (X-axis): the quantized value of the first correlation feature. For example, the mean of the absolute values ​​of the correlation coefficients between each parameter in the first target parameter and all real-time parameters can be taken. Second dimension (Y-axis): the quantized value of the second correlation feature. For example, the absolute value of the maximum correlation coefficient between each parameter in the first target parameter and the state influence vectors of other parameters can be taken. This calculation is repeated for all parameters in the first target parameter to obtain their coordinates in the feature space, thus obtaining the parameter-adjusted feature space.

[0085] S620 calculates the fusion distance between the first and second associated features based on parameter-adjusted feature space.

[0086] For example, the fusion distance between the first associated feature and the second associated feature can be calculated using a weighted Manhattan distance based on parameter adjustments to the feature space.

[0087] S630, at least one parameter adjustment feature is obtained based on fusion distance clustering.

[0088] For example, DBSCAN density clustering can be used based on the fusion distance. Dense regions can be automatically identified as feature clusters based on the neighborhood radius (e.g., ε=0.2, set based on the distance matrix distribution). The parameter adjustment path can be determined based on the feature clusters (e.g., some parameters are adjusted synchronously in the same direction, and some parameters are adjusted synchronously in the opposite direction). The degree of influence of adjusting the first target parameter on the real-time state parameter can be determined based on the first correlation feature and the second correlation feature. The change in the pollution index can be determined based on the degree of influence on the real-time state parameter. The direction and range of the adjustment of the first target parameter can be determined based on the change in the pollution index and the current pollution index, thus obtaining at least one parameter adjustment feature.

[0089] Through steps S610 to S630 above, the clustering results reveal key adjustment paths. The fusion distance quantifies the cascading effects of parameter adjustments. For example, in cluster 1, the stirring speed N and filtration pressure P need to be adjusted synchronously to improve the effect.

[0090] In one possible implementation, please refer to Figure 3 The methods also include: S800 determines whether to perform secondary operations on the raw materials in the reactor based on real-time status parameters and the first target parameters. These secondary operations include secondary stirring, pressure filtration, and / or extending the reaction time.

[0091] For example, an LSTM model can be trained based on historical operating data (including output) to predict the target parameter range under the current operating conditions. For instance, if the LSTM model predicts that the output at the current reaction stage is less than a preset threshold, a secondary operation condition is triggered. Operations are matched from a preset rule base based on the degree of deviation between the real-time state parameters and the target parameter range. For example, if the temperature is too low and the output is insufficient, secondary stirring (enhancing mass transfer) + extending the reaction time (10 minutes); if the pressure is too high and the reaction rate is slow, pressure filtration (removing impurities) + reducing the stirring speed (avoiding excessive shear).

[0092] By automatically switching the judgment rules for different reaction stages through the above steps S800, it is beneficial to reduce invalid operations and avoid safety accidents caused by operations.

[0093] In one possible implementation, please refer to Figure 3 The methods also include: S900, if it is determined from the real-time status parameters that the raw materials in the reactor should not be directly operated on according to the first target parameters, then the first target parameters are adjusted to obtain the second target parameters, and the secondary operation is performed according to the second target parameters.

[0094] For example, when the LSTM model predicts that the yield at the current reaction stage is not less than a preset threshold, or when the rule engine determines that directly adjusting the first target parameter cannot meet the process requirements, the first target parameter is adjusted to obtain a second target parameter. Then, a secondary operation is performed based on the second target parameter.

[0095] Through the above steps S900, real-time data and historical experience are integrated to form a closed loop of "perception-decision-execution". Through dynamic target adjustment and compensation operations, the product quality is stabilized, which is conducive to improving process robustness and optimizing resource utilization.

[0096] In one possible implementation, please refer to Figure 4 S700, adjusting the first target parameter based on at least one parameter to obtain the second target parameter, including: S710 constructs multiple candidate parameter vectors based on the adjusted features for each parameter. Here, a candidate parameter vector refers to a possible combination of parameters constructed based on the adjusted features.

[0097] For example, based on parameter adjustment characteristics (such as needing to increase stirring speed by 20 rpm or decrease filtration pressure by 0.1 MPa), the adjustment direction (positive / negative) and magnitude (percentage / absolute value) of each parameter can be extracted. Within the parameter adjustment range, a grid search method is used to generate all possible combinations at a fixed step size to obtain multiple candidate parameter vectors. Alternatively, Latin hypercube sampling can be used to randomly generate multiple non-repeating candidate parameter vectors within the parameter space.

[0098] S720 obtains the corresponding effect prediction score based on each candidate parameter vector and real-time state parameter.

[0099] For example, a gradient boosting tree (GBT) model can be trained based on historical data. Real-time state parameters are concatenated with candidate vectors to form complete input features. The trained GBT model then yields the predicted performance score. Figure 6 As shown.

[0100] S730: Based on the predicted scores of each effect, candidate parameter vectors that are greater than the preset effect threshold are selected, and the first target parameter is adjusted according to the candidate parameter vectors that are greater than the effect threshold to obtain the second target parameter.

[0101] For example, an effect threshold can be set based on process requirements, and the candidate parameter vector filtered based on the prediction scores of each effect can be used as the second target parameter. For instance, the stirring speed N=170rpm, filtration pressure P=0.4MPa, and reaction time t=4h of the candidate parameter vector will replace the original first target parameter (150rpm, 0.5MPa, 3h). After the second target parameter is executed, indicators such as pollution index and yield are monitored in real time. If the expected results are not achieved, a secondary adjustment is triggered.

[0102] Through steps S710 to S730, the optimal parameter combination can be accurately located via candidate vector generation and effect prediction. The dynamic integration of real-time state parameters and candidate vectors enables the method to adapt to changes in operating conditions such as raw material fluctuations and equipment aging. High-value parameter combinations are selected based on effect prediction scores, avoiding ineffective adjustments.

[0103] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0104] Corresponding to the method for controlling parameters in the neutral leaching process of zinc-containing waste described in the above embodiments, this application also provides a device for controlling parameters in the neutral leaching process of zinc-containing waste. Each module of this device can realize each step of the method for controlling parameters in the neutral leaching process of zinc-containing waste. Figure 7 The diagram shows a structural block diagram of a parameter control device for the neutral leaching process of zinc-containing waste provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0105] Reference Figure 7 The device includes: The acquisition module is used to acquire real-time state parameters of the raw materials in the reactor; wherein, the real-time state parameters include temperature, liquid-to-solid ratio and vibration frequency; The pollution index module is used to obtain the pollution index based on the real-time status parameters; wherein, the pollution index includes sulfuric acid mist concentration and noise index; The first target parameter module is used to obtain a first target parameter based on the pollution index and the real-time status parameter; wherein, the first target parameter includes stirring speed, filtration pressure and / or reaction time; The first correlation feature module is used to determine a first correlation feature for each parameter in the first target parameter based on the correlation between the real-time state parameter and the first target parameter; wherein, the first correlation feature is used to reflect the impact of adjusting one process parameter on another state parameter under the current operating condition; The second correlation feature module is used to determine a second correlation feature for each parameter in the first target parameter based on the correlation between the first correlation feature, the real-time state parameter, and the first target parameter; wherein the second correlation feature is used to reflect the influence of the first correlation feature on the current state; A parameter adjustment feature module is used to determine at least one parameter adjustment feature based on the first association feature and the second association feature; wherein the parameter adjustment feature is used to reflect the direction and degree of adjustment of the first target parameter; The second target parameter module is used to adjust the first target parameter according to at least one of the parameter adjustment features to obtain the second target parameter.

[0106] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0107] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0108] This application also provides a device for controlling parameters in the neutral leaching process of zinc-containing waste. Figure 8 This is a schematic diagram of a parameter control device for the neutral leaching process of zinc-containing waste provided in an embodiment of this application. Figure 8 As shown, the parameter control device 8 for the neutral leaching process of zinc-containing waste in this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the image), at least one memory 81 ( Figure 8 (Only one is shown in the image) and a computer program 82 stored in the at least one memory 81 and executable on the at least one processor 80. When the processor 80 executes the computer program 82, it causes the zinc-containing waste neutral leaching process parameter control device 8 to implement the steps in any of the above-described zinc-containing waste neutral leaching process parameter control method embodiments, or causes the zinc-containing waste neutral leaching process parameter control device 8 to implement the functions of each module / unit in the above-described device embodiments.

[0109] Exemplarily, the computer program 82 may be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 82 in the zinc-containing waste neutral leaching process parameter control device 8.

[0110] The neutral leaching process parameter control device 8 for zinc-containing waste can be a computing device such as an industrial computer, programmable logic controller, embedded control system, distributed control system, desktop computer, laptop, handheld computer, and cloud server. This device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of the parameter control device 8 for the neutral leaching process of zinc-containing waste and does not constitute a limitation on the parameter control device 8 for the neutral leaching process of zinc-containing waste. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0111] The processor 80 can be a Central Processing Unit (CPU), or it can 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 gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0112] In some embodiments, the memory 81 may be an internal storage unit of the zinc-containing waste neutral leaching process parameter control device 8, such as a hard disk or memory of the zinc-containing waste neutral leaching process parameter control device 8. In other embodiments, the memory 81 may be an external storage device of the zinc-containing waste neutral leaching process parameter control device 8, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the zinc-containing waste neutral leaching process parameter control device 8. Further, the memory 81 may include both internal storage units and external storage devices of the zinc-containing waste neutral leaching process parameter control device 8. The memory 81 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 81 can also be used to temporarily store data that has been output or will be output.

[0113] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0114] This application provides a computer program product that, when run on a neutral leaching process parameter control device for zinc-containing waste, enables the device to implement the steps described in any of the above method embodiments.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a parameter control device for the neutral leaching process of zinc-containing waste, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0116] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0118] In the embodiments provided in this application, it should be understood that the disclosed equipment and method for controlling parameters in the neutral leaching process of zinc-containing waste can be implemented in other ways. For example, the embodiments of the equipment for controlling parameters in the neutral leaching process of zinc-containing waste described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for controlling parameters in a neutral leaching process of zinc-containing waste, characterized in that, include: The real-time state parameters of the raw materials in the reactor are obtained; wherein, the real-time state parameters include temperature, liquid-to-solid ratio and vibration frequency; The pollution index is obtained based on the real-time status parameters; wherein, the pollution index includes sulfuric acid mist concentration and noise index; A first target parameter is obtained based on the pollution index and the real-time status parameters; wherein, the first target parameter includes stirring speed, filtration pressure and / or reaction time; Based on the correlation between the real-time status parameters and the first target parameters, a first correlation feature is determined for each parameter in the first target parameters; wherein, the first correlation feature is used to reflect the impact of adjusting one process parameter on another status parameter under the current operating conditions; Based on the correlation between the first correlation feature, the real-time state parameter, and the first target parameter, a second correlation feature is determined for each parameter in the first target parameter; wherein, the second correlation feature is used to reflect the influence of the first correlation feature on the current state; At least one parameter adjustment feature is determined based on the first association feature and the second association feature; wherein the parameter adjustment feature is used to reflect the direction and degree of adjustment of the first target parameter; The second target parameter is obtained by adjusting the feature according to at least one of the parameters.

2. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The process of obtaining the pollution index based on the real-time status parameters includes: Obtain raw material information; wherein, the raw material information includes zinc content, impurity types and contents, and particle size distribution; The current information sequence during the neutral leaching process is obtained based on the real-time status parameters; wherein, the current information sequence includes the sulfuric acid mist concentration and noise at each node of solution preparation, stirring leaching, endpoint detection and / or solid-liquid separation; The position weights are determined based on the current information sequence; wherein, the position weights refer to the weight coefficients of each node. The degree of attention is obtained based on the correlation between the raw material information and the current information sequence; wherein, the degree of attention is used to reflect the degree of influence of each attribute of the raw material on the pollution index of each node; The contamination index for the next node in the neutral leaching process is determined based on the location weight and the level of attention.

3. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 2, characterized in that, The step of obtaining attention based on the correlation between the raw material information and the current information sequence includes: Based on the raw material information, determine the correlation between each attribute of the raw material and the current information sequence, and sort them to obtain an importance sequence; The attention level is obtained by assigning weights to each attribute of the raw material based on the importance sequence.

4. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The process of obtaining the first target parameter based on the pollution index and the real-time status parameters includes: The influence coefficients of the real-time state parameters were obtained through analysis; The first target parameter is obtained based on the influence coefficient and the pollution index.

5. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The step of determining the first correlation feature of each parameter in the first target parameter based on the correlation between the real-time state parameter and the first target parameter includes: Calculate the first correlation coefficient between the real-time state parameters and the first target parameters to obtain the correlation matrix; Based on the correlation matrix, the first association feature of each parameter in the first target parameter is obtained.

6. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The step of determining a second association feature for each parameter in the first target parameter based on the correlation between the first association feature, the real-time state parameter, and the first target parameter includes: Based on the first correlation feature, for every two target parameters in the first target parameters, a second correlation coefficient is calculated between the corresponding state influence vectors; wherein, the state influence vector is composed of the first correlation coefficients between the parameters in the first target parameters and each parameter of the real-time state parameters; The second correlation feature is obtained based on the second correlation coefficient.

7. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The step of determining at least one parameter adjustment feature based on the first association feature and the second association feature includes: The first associated feature and the second associated feature are respectively mapped to the first dimension and the second dimension of the parameter adjustment feature space to construct the parameter adjustment feature space. The fusion distance between the first associated feature and the second associated feature is calculated based on the adjusted feature space according to the parameters. At least one parameter adjustment feature is obtained based on the fusion distance clustering.

8. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The method further includes: The decision is made based on the real-time status parameters whether to directly perform secondary operations on the raw materials in the reactor according to the first target parameters; wherein, the secondary operations include secondary stirring, pressure filtration and / or extending the reaction time.

9. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 8, characterized in that, The method further includes: If it is determined based on the real-time status parameters that the secondary operation on the raw materials in the reactor should not be performed directly based on the first target parameters, then the first target parameters are adjusted to obtain the second target parameters, and the secondary operation is performed based on the second target parameters.

10. The method for controlling parameters in the neutral leaching process of zinc-containing waste as described in claim 1, characterized in that, The step of adjusting the first target parameter based on at least one of the parameters to obtain the second target parameter includes: Multiple candidate parameter vectors are constructed based on the adjustment features for each parameter; wherein, the candidate parameter vector refers to possible combinations of parameters constructed based on the parameter adjustment features; The corresponding effect prediction score is obtained based on each candidate parameter vector and the real-time state parameter. Based on the predicted effect scores, candidate parameter vectors that are greater than a preset effect threshold are selected, and the first target parameter is adjusted according to the candidate parameter vectors that are greater than the effect threshold to obtain the second target parameter.

Images