CN110672792B - Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy - Google Patents

Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy Download PDF

Info

Publication number
CN110672792B
CN110672792B CN201910951691.6A CN201910951691A CN110672792B CN 110672792 B CN110672792 B CN 110672792B CN 201910951691 A CN201910951691 A CN 201910951691A CN 110672792 B CN110672792 B CN 110672792B
Authority
CN
China
Prior art keywords
reaction tank
model
reaction
jth
leaching process
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910951691.6A
Other languages
Chinese (zh)
Other versions
CN110672792A (en
Inventor
孙备
李维剑
龙双
李勇刚
朱红求
阳春华
桂卫华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Central South University
Original Assignee
Central South University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Central South University filed Critical Central South University
Priority to CN201910951691.6A priority Critical patent/CN110672792B/en
Publication of CN110672792A publication Critical patent/CN110672792A/en
Application granted granted Critical
Publication of CN110672792B publication Critical patent/CN110672792B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Chemical & Material Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Biophysics (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Manufacture And Refinement Of Metals (AREA)

Abstract

The invention provides a method and a system for soft measurement of a pH value in a neutral leaching process of zinc hydrometallurgy, and relates to the field of pH value measurement. The method comprises the following steps: acquiring reaction tank data; acquiring a chemical reaction balance model, a reaction dynamics total model and a neutral leaching process data driving model under each working condition based on the reaction tank data; and integrating the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model. The invention can accurately measure the pH value.

Description

Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy
Technical Field
The invention relates to the technical field of pH value measurement, in particular to a method and a system for soft measurement of a pH value in a neutral leaching process of zinc hydrometallurgy.
Background
In the production process of zinc hydrometallurgy, leaching is an important process for ensuring leaching rate and stability of subsequent processes, and a neutral leaching process is the most important sub-process in the leaching process. The neutral leaching process is a reaction control process in which a plurality of continuously stirred reaction kettles are used as reaction containers, and reaction substances such as zinc calcine, waste acid, acid leaching supernatant, mixed liquor and the like are added into the reaction containers to realize high-degree dissolution of the zinc calcine.
The neutral leaching process is very demanding with respect to the pH at the outlet of the last reactor, and therefore it is necessary to monitor the pH change in the tank at the production site. In the prior art, a pH detection device capable of automatically lifting is generally arranged at an outlet of a reaction tank, and the waste acid entering the first three tanks and the amount of roasted sand are adjusted by a pH value indicated value and a pH value measured by a pH test paper manually on site.
However, the inventor of the present application found that the neutral leaching production conditions are severe, the deviation of the detection value of the on-site pH meter is large, and meanwhile, the measurement accuracy is not high enough because the pH value is measured by using the pH test paper manually. Namely, the prior art has the defect of inaccurate pH value soft measurement.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a method and a system for soft measurement of the pH value in the neutral leaching process of zinc hydrometallurgy, and solves the technical problem of inaccurate pH value soft measurement in the prior art.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
the invention provides a method for soft measurement of pH value in neutral leaching process of zinc hydrometallurgy, which solves the technical problem, the method is executed by a computer and comprises the following steps:
obtaining reaction tank data, the reaction tank data comprising: fj#Flow rate of solution into the jth reaction tank, cj#M is the acidity of the solution entering the jth reaction tankj#The mass of zinc calcine entering the jth reaction tank per hour, the flow rate F of each solvent entering each reaction tankiThe acidity c of each solvent fed into each reaction tankiAnd the flow rate m of zinc calcine entering each reaction tanki；
Based on Fj#And cj#Obtaining H+(ii) cumulative amount of; based on mj#Obtaining the consumption of H +; based on the H+And said H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on the H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition;
based on Fi、ciAnd miObtaining a reaction kinetic model of each reaction tank; integrating the reaction kinetic models of all the reaction tanks to obtain a reaction kinetic total model; acquiring a reaction dynamics total model under each working condition based on a preset working condition;
based on Fj#And mj#Acquiring a neutral leaching process data driving model, and acquiring the neutral leaching process data driving model under each working condition based on a preset working condition;
integrating a chemical reaction balance model, a reaction dynamics total model and a neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model; the neutral leaching process integrated model is used for soft measurement of pH value.
Said H+The method of obtaining the accumulated amount of (a) includes:
Figure GDA0002568751930000031
Tj＝20(n-j+1)
wherein:
Tjthe accumulated time length of each reaction tank is used; j is 1, n, n is the number of reaction tanks;
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
Figure GDA0002568751930000032
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#With the acidity c of the solution entering the jth reaction tankj#Accumulating the products;
preferably, said H+The method for obtaining the consumption of (1) comprises:
Figure GDA0002568751930000033
wherein:
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of a substance that is a reactant;
Figure GDA0002568751930000034
for the jth reaction tank at TjThe mass m of zinc calcine entering the jth reaction tank per hour in the time periodj#Accumulation of (1);
said H+The concentration acquisition method comprises the following steps:
Figure GDA0002568751930000041
Figure GDA0002568751930000042
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#Accumulation of (1);
the chemical reaction equilibrium model is as follows:
Figure GDA0002568751930000043
wherein:
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of a substance that is a reactant;
the preset working conditions comprise: an extremely low acid condition, a normal condition, a high acid condition and an extremely high acid condition;
the specific dividing method of the preset working condition comprises the following steps:
obtaining the acid-material ratio S and presetting a demarcation point p1、p2、p3And p4；
Figure GDA0002568751930000051
When S < p1When the acid is in the working condition of extremely low acid; when p is1≤S＜p2When the working condition is low acid; when p is2≤S＜p3When the working condition is normal; when p is3≤S＜p4In time, the working condition is high acid; when p is4When the acid content is less than or equal to S, the working condition is extremely high acid;
the reaction kinetic model of each reaction tank is as follows:
pHj#＝-logcj#
Figure GDA0002568751930000052
wherein:
Figure GDA0002568751930000053
Figure GDA0002568751930000054
is the outlet flow of the jth reaction tank, V is the volume of the reaction tank,
Figure GDA0002568751930000055
r0is the particle radius of zinc calcine, αj#M is the proportion of the effective matrix surface area in the zinc calcine entering the j # reaction tankiFor the flow of zinc calcine into each reaction tank,
Figure GDA0002568751930000056
Figure GDA0002568751930000057
the surface area of the manganese ore pulp and the effective solid matrix in other solution of the j # reaction tank;
Figure GDA0002568751930000058
i is a solvent species;
t0is the initial time;
Figure GDA0002568751930000059
the acidity of the outlet solution of the jth reaction tank at the initial moment; fiThe flow rate of the ith solvent into the jth reaction tank is shown;
the method for acquiring the data-driven model of the neutral leaching process comprises the following steps:
with Fj#And mj#Taking the pH value as an output quantity, taking a radial basis function neural network as a basic structure, and constructing a data driving model of the neutral leaching process;
the method for acquiring the radial basis function neural network comprises the following steps:
performing data preprocessing on the input quantity based on a min-max normalization method to obtain sample data;
processing the sample data based on a K-means clustering method to obtain a radial basis function;
constructing a radial basis function neural network based on the radial basis functions;
the neutral leaching process integrated model is as follows:
Figure GDA0002568751930000061
wherein:
x represents input parameters of each model;
when j is 1, representing a chemical reaction equilibrium model, when j is 2, representing a reaction kinetic overall model, and when j is 3, representing a neutral leaching process data driving model;
gi(σji) A membership function for the ith condition belonging to the jth model;
σjiis a membership function parameter;
ω1、ω2and ω3Respectively representing the weights of a chemical reaction balance model, a reaction dynamics total model and a neutral leaching process data driving model;
ξ is the bias term.
The invention provides a system for soft measurement of pH value in neutral leaching process of zinc hydrometallurgy, which solves the technical problem, and comprises a computer, wherein the computer comprises:
at least one memory cell;
at least one processing unit;
wherein the at least one memory unit has stored therein at least one instruction that is loaded and executed by the at least one processing unit to perform the steps of:
obtaining reaction tank data, the reaction tank data comprising: fj#Flow rate of solution into the jth reaction tank, cj#M is the acidity of the solution entering the jth reaction tankj#The mass of zinc calcine entering the jth reaction tank per hour, the flow rate F of each solvent entering each reaction tankiThe acidity c of each solvent fed into each reaction tankiAnd zinc calcine entering each reaction tankFlow rate mi；
Based on Fj#And cj#Obtaining H+(ii) cumulative amount of; based on mj#Obtaining H+The amount of consumption of (c); based on the H+And said H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on the H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition;
based on Fi、ciAnd miObtaining a reaction kinetic model of each reaction tank; integrating the reaction kinetic models of all the reaction tanks to obtain a reaction kinetic total model; acquiring a reaction dynamics total model under each working condition based on a preset working condition;
based on Fj#And mj#Acquiring a neutral leaching process data driving model, and acquiring the neutral leaching process data driving model under each working condition based on a preset working condition;
integrating a chemical reaction balance model, a reaction dynamics total model and a neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model; the neutral leaching process integrated model is used for soft measurement of pH value.
Preferably, said H+The method of obtaining the accumulated amount of (a) includes:
Figure GDA0002568751930000081
Tj＝20(n-j+1)
wherein:
Tjthe accumulated time length of each reaction tank is used; j is 1, n, n is the number of reaction tanks;
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
Figure GDA0002568751930000082
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#With the acidity c of the solution entering the jth reaction tankj#Accumulating the products;
said H+The method for obtaining the consumption of (1) comprises:
Figure GDA0002568751930000083
wherein:
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of a substance that is a reactant;
Figure GDA0002568751930000084
for the jth reaction tank at TjThe mass m of zinc calcine entering the jth reaction tank per hour in the time periodj#Accumulation of (1);
said H+The concentration acquisition method comprises the following steps:
Figure GDA0002568751930000091
Figure GDA0002568751930000092
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#Accumulation of (1);
preferably, the chemical reaction equilibrium model is:
Figure GDA0002568751930000093
wherein:
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of material that is a reactant.
(III) advantageous effects
The invention provides a method and a system for soft measurement of pH value in neutral leaching process of zinc hydrometallurgy. Compared with the prior art, the method has the following beneficial effects:
the invention obtains the data of the reaction tank; reaction tank data based acquisition H+Cumulative amount of (A) and H+The amount of consumption of (c); based on H+Cumulative amount of (A) and H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition; acquiring a reaction kinetic model of each reaction tank based on the reaction tank data; integrating the reaction kinetic models of all the reaction tanks to obtain a total reaction kinetic model under each working condition; acquiring a neutral leaching process data driving model under each working condition based on the reaction tank data; and integrating the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model. According to the invention, three pH value soft measurement models under different working conditions are respectively constructed according to related data in the reaction tank, and the three models are integrated to obtain a final neutral leaching process integrated model, so that the real-time measurement or prediction of the pH value can be effectively realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is an overall flow chart of a method for soft measurement of pH value in a neutral leaching process of zinc hydrometallurgy according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides the method and the system for soft measurement of the pH value in the neutral leaching process of zinc hydrometallurgy, solves the technical problem of inaccuracy in soft pH value measurement in the prior art, and improves the accuracy of soft pH value measurement.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
the embodiment of the invention obtains the data of the reaction tank; reaction tank data based acquisition H+Cumulative amount of (A) and H+The amount of consumption of (c); based on H+Cumulative amount of (A) and H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition; acquiring a reaction kinetic model of each reaction tank based on the reaction tank data; integrating the reaction kinetic models of all the reaction tanks to obtain a total reaction kinetic model under each working condition; acquiring a neutral leaching process data driving model under each working condition based on the reaction tank data; and integrating the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model. The embodiment of the invention respectively constructs three pH value soft measurement models under different working conditions according to the relevant data in the reaction tank, integrates the three models to obtain a final neutral leaching process integrated model,the pH value can be effectively measured or predicted in real time, and compared with the manual measurement mode in the prior art, the pH value measuring method has the advantages that the measurement precision is improved, the measurement cost is reduced, the field automation level is effectively improved, and the stability of the production process is ensured.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
The main reactions in the neutral leaching reaction tank that affect the pH change can be summarized as follows:
ZnO+2H+＝Zn2++H2O
2FeO+4H+＝2Fe2++2H2O
2Fe2++MnO2+4H+＝2Fe3++Mn2++2H2O
Fe2O3+6H+＝2Fe3++3H2O
it should be noted that the ratio of the latter two chemical reaction formulas generated in the reaction tank is small and can be ignored.
Thus, on average about 2mol of H are consumed for 1mol of solid matrix+That is, the above reactions can be summarized as:
AO+2H+＝A2++H2o reaction equation (1)
Wherein: AO represents a solid reactant.
The following is one embodiment of the present invention.
The embodiment of the invention provides a method for soft measurement of pH value in neutral leaching process of zinc hydrometallurgy, which is executed by a computer and comprises the following steps as shown in figure 1:
s1, acquiring reaction tank data, wherein the reaction tank data comprises: fj#Flow rate of solution into the jth reaction tank, cj#M is the acidity of the solution entering the jth reaction tankj#The mass of zinc calcine entering the jth reaction tank per hour, the flow rate F of each solvent entering each reaction tankiThe acidity c of each solvent fed into each reaction tankiAnd the flow rate m of zinc calcine entering each reaction tanki；
S2 based on Fj#And cj#Obtaining H+(ii) cumulative amount of; based on mj#Obtaining H+The amount of consumption of (c); based on the above H+And the above H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on the above H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition;
s3 based on Fi、ciAnd miObtaining a reaction kinetic model of each reaction tank; integrating the reaction kinetic models of all the reaction tanks to obtain a reaction kinetic total model; acquiring a reaction dynamics total model under each working condition based on a preset working condition;
s4 based on Fj#And mj#Acquiring a neutral leaching process data driving model, and acquiring the neutral leaching process data driving model under each working condition based on a preset working condition;
s5, integrating the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model; the neutral leaching process integrated model is used for soft measurement of pH value.
The embodiment of the invention obtains the data of the reaction tank; reaction tank data based acquisition H+Cumulative amount of (A) and H+The amount of consumption of (c); based on H+Cumulative amount of (A) and H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition; acquiring a reaction kinetic model of each reaction tank based on the reaction tank data; integrating the reaction kinetic models of all the reaction tanks to obtain a total reaction kinetic model under each working condition; acquiring a neutral leaching process data driving model under each working condition based on the reaction tank data; the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions are integratedAnd finally, obtaining the neutral leaching process integrated model. According to the embodiment of the invention, three pH value soft measurement models under different working conditions are respectively constructed according to relevant data in the reaction tank, and the three models are integrated to obtain a final neutral leaching process integrated model, so that the real-time measurement or prediction of the pH value can be effectively realized.
The following is a detailed analysis of each step.
In step S1, reaction tank data is acquired, the reaction tank data including: fj#Flow rate of solution into the jth reaction tank, cj#M is the acidity of the solution entering the jth reaction tankj#The mass of zinc calcine entering the jth reaction tank per hour, the flow rate F of each solvent entering each reaction tankiThe acidity c of each solvent fed into each reaction tankiAnd the flow rate m of zinc calcine entering each reaction tanki。
In step S2, based on Fj#And cj#Obtaining H+(ii) cumulative amount of; based on mj#Obtaining H+The amount of consumption of (c); based on the H+And said H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on the H+Obtaining a chemical reaction balance model according to the concentration; and acquiring a chemical reaction balance model under each working condition based on a preset working condition.
Specifically, the method comprises the following steps:
setting the soft measurement of the neutral leaching process as the outlet of the nth reaction tank and the data sampling interval of 1 min, and determining the past period H of the neutral leaching process+The cumulative amount (unit: mol) of (A) is:
Figure GDA0002568751930000141
wherein:
Tjthe accumulated time length of each reaction tank is used; j is 1, n, n is the number of reaction tanksAn amount;
Fj#the flow rate of the solution (unit: m) into the jth reaction tank3/h)；
cj#The acidity (unit: g/L) of the solution entering the jth reaction tank;
Figure GDA0002568751930000142
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#With the acidity c of the solution entering the jth reaction tankj#And accumulating the products.
Wherein T isjThe solving method of (2) is as follows:
Tj＝20(n-j+1)
each T can be obtained by sequentially solving from j to 1j。
The cumulative amount (unit: g) of zinc calcine entering the reaction tank in the past period is as follows:
Figure GDA0002568751930000151
wherein:
mj#the mass of zinc calcine entering the jth reaction tank per hour (unit: t/h) is shown.
The amount of the zinc calcine, i.e. AO accumulated (unit: mol), which is reacted off is as follows:
Figure GDA0002568751930000152
wherein:
theta is the solubility of zinc calcine, MAOThe amount of material that is the solid reactant.
The reacted H can be obtained from the chemical reaction equation (1) and the formula (4)+The amount (unit: mol) of:
Figure GDA0002568751930000153
combining the formula (2) to obtain the outlet H of the last reactor+The concentrations (unit: mol/L) were:
Figure GDA0002568751930000154
Figure GDA0002568751930000155
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#Accumulation of (1);
according to H+The relationship between concentration and pH value can be found as follows:
Figure GDA0002568751930000156
according to the above format, a chemical reaction equilibrium model can be obtained as:
Figure GDA0002568751930000161
wherein:
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of material that is a reactant.
The chemical reaction equilibrium model described above can be expressed as:
pH＝f(θ,MAO) Formula (7)
Wherein:
f is a functional relation shown by a model, (theta, M)AO) Are parameters in the model that need to be identified.
The specific acquisition method of the parameters comprises the following steps:
in the embodiment of the invention, the following working conditions are preset: very low acid, normal, high acid and very high acid conditions.
The specific division method of the preset working condition comprises the following steps:
obtaining the acid-material ratio S and presetting a demarcation point p1、p1、p3And p4；
Figure GDA0002568751930000162
When S < p1When the acid is in the working condition of extremely low acid; when p is1≤S＜p2When the working condition is low acid; when p is2≤S＜p3When the working condition is normal; when p is3≤S＜p4In time, the working condition is high acid; when p is4When the acid content is less than or equal to S, the working condition is extremely high acid. In particular, p1、p2、p3And p4Respectively 10%, 40%, 60% and 90%.
Based on the least square method, the unknown parameters in formula (7) are identified, i.e. the objective function is as follows:
Figure GDA0002568751930000171
wherein:
l is the number of the data sets,
Figure GDA0002568751930000172
actual pH measurements.
According to the steps, chemical reaction balance models under five different working conditions can be finally obtained.
In step S3, based on Fi、ciAnd miObtaining a reaction kinetic model of each reaction tank; integrating the reaction kinetic models of all the reaction tanks to obtain a reaction kinetic total model; and acquiring a reaction dynamics total model under each working condition based on a preset working condition.
Specifically, the embodiment of the present invention takes the first reaction tank in the neutral leaching process as an example, and illustrates the method for obtaining the reaction kinetic model.
The number of the solvents entering the No. 1 tank is n, and the flow rate of each solvent is Fi(m3H) acidity of ci(g/L), the flow rate of the calcine entering the No. 1 tank is m1(t/h). The reaction surface area of the No. 1 tank leaching process is A1#For hydrogen ions, the following material balance is present:
Figure GDA0002568751930000173
wherein the hydrogen ion reaction rate equation is as follows:
Figure GDA0002568751930000174
the formula by arrhenius is:
Figure GDA0002568751930000181
meanwhile, the solids entering the reactor mainly comprise zinc calcine and solid matters in other solutions, and the solid matters comprise:
Figure GDA0002568751930000182
wherein:
Figure GDA0002568751930000183
is the effective matrix surface area of the zinc calcine, rho is the zinc calcine density, r0Is the particle radius of zinc calcine, α1#Is the proportion of the effective matrix surface area in the zinc calcine entering the No. 1 cell.
The effective surface area of the solid matrix in the manganese ore pulp and other solution in the No. 1 tank is
Figure GDA0002568751930000184
Then
Figure GDA0002568751930000185
From the chemical reaction equilibrium model and equations (5) and (6) above, it can be seen that:
Figure GDA0002568751930000186
in the embodiment of the invention, let:
Figure GDA0002568751930000187
Figure GDA0002568751930000188
the parameters to be identified are as follows:
Figure GDA0002568751930000189
therefore, equation (9) can be:
Figure GDA00025687519300001810
solving the first-order linear non-homogeneous differential equation to obtain a reaction kinetic model of the No. 1 reaction tank:
Figure GDA0002568751930000191
the relationship between the pH value and the hydrogen ion concentration can be obtained as follows: pH value1#＝-logc1#。
According to the steps, a reaction kinetic model of each reaction tank can be obtained:
Figure GDA0002568751930000192
wherein:
Figure GDA0002568751930000193
Figure GDA0002568751930000194
is the outlet flow of the jth reaction tank, V is the volume of the reaction tank,
Figure GDA0002568751930000195
r0is the particle radius of zinc calcine, αj#M is the proportion of the effective matrix surface area in the zinc calcine entering the j # reaction tankiFor the flow of zinc calcine into each reaction tank,
Figure GDA0002568751930000196
Figure GDA0002568751930000197
the surface area of the manganese ore pulp and the effective solid matrix in other solution of the j # reaction tank;
Figure GDA0002568751930000198
i is a solvent species;
t0is the initial time;
Figure GDA0002568751930000199
the outlet solution acidity of the jth reaction tank at the initial moment.
FiThe flow rate of the ith solvent into the jth reaction tank is shown;
ciindicates the acidity of the i-th solvent entering the j-th reaction tank.
Integrating the models of all the reaction tanks to obtain a reaction kinetic general model:
pH＝f(θ,input)+ξ
wherein:
theta is a parameter to be identified, input is an input variable, and xi is a deviation correction term. The unknown parameters can be obtained by solving a least squares problem using off-line data. The specific method can be referred to formula (8).
And acquiring a reaction kinetics total model under five working conditions.
In step S4, based on Fj#And mj#Obtaining a neutral leaching process data driven model based on a presetThe working conditions obtain a neutral leaching process data driving model under each working condition.
In particular, with Fj#And mj#The neutral leaching process data driving model is constructed by taking the pH value as an output quantity and taking the radial basis function neural network as a basic structure.
The input quantities of the data model are:
Figure GDA0002568751930000201
the output is the pH value. Is provided with
Figure GDA0002568751930000202
Specifically, the radial basis function neural network is a static forward neural network, which is a prior art. The method for acquiring the radial basis function neural network comprises the following steps:
s401, preprocessing the input quantity based on a min-max normalization method to obtain sample data.
Before training, the numerical value needs to be normalized. By adopting a min-max normalization method, taking one of the input variables as an example, the formula is as follows:
Figure GDA0002568751930000203
wherein
Figure GDA0002568751930000204
A certain data representing the input data of the first dimension,
Figure GDA0002568751930000205
representing the maximum and minimum values in this dimension of data,
Figure GDA0002568751930000206
the normalized values are indicated.
Secondly, in order to obtain a more accurate radial basis function neural network approximation model, based on the working condition division method, training data are divided into five types, namely an extremely low acid working condition, a normal working condition, a high acid working condition and an extremely high acid working condition, so that the following training operation can be conveniently carried out.
S402, processing the sample data based on a K-means clustering method to obtain a radial basis function.
And clustering the sample data by adopting a K-means clustering algorithm, and judging the quality of a clustering result by utilizing the contour coefficient. Firstly, the number of initialized clusters is 2, and two sample points are selected randomly
Figure GDA0002568751930000211
As the initial cluster center. Respectively calculating Euclidean distances from each sample point to two clustering centers:
dj1(2)＝||zj-μ1(2)||2
the cluster center to which the sample point is short is classified as that cluster. And solving the outline coefficient of the sample for the clustering result to judge the reasonability of clustering. For a single sample zjThe contour coefficient calculation formula is as follows:
Figure GDA0002568751930000212
wherein: a (j) is the intra-cluster dissimilarity of the sample j, which is numerically the average of the distances from the sample j to all the points of the class where the sample j is located, and b (j) is the inter-cluster dissimilarity of the sample j, which is numerically equal to the minimum of the distances from the sample j to all the points of the class closest to the class where the sample j is located. And averaging the contour coefficients of all the sample points to obtain the total contour coefficient of the clustering result.
And then, setting the clustering number to be 3, and repeating the clustering operation and the contour coefficient calculation operation until the clustering number reaches the set maximum upper limit M. And comparing the total contour coefficients under all the clustering numbers, wherein the maximum contour coefficient means the optimal classification effect, and taking the classification number as the number of hidden layer nodes of the radial basis function neural network.
Selecting a Gaussian function as a radial basis function, namely:
Figure GDA0002568751930000213
wherein C isiIs the center of the ith hidden node, X is the input vector, σiIs the width of the ith hidden node. And taking the clustering center point of the clustering result as the center of the hidden node, and taking the minimum value of the distance between the clustering centers as the width of the hidden node.
And S403, constructing a radial basis function neural network based on the radial basis function.
Let the model input be a 2n × L matrix and the actual measurement be a 1 × L matrix vector, i.e.
Figure GDA0002568751930000221
Wherein: n is the number of reaction tanks, L is the amount of training sample data, X,
Figure GDA0002568751930000222
representing the measured values of the input and output, respectively. If the hidden layer has P nodes, then for the ith training sample
Figure GDA0002568751930000223
The output of the p-th node is:
Figure GDA0002568751930000224
the output matrix of the hidden layer node is
Figure GDA0002568751930000225
The weight matrix from hidden layer to output layer is
Figure GDA0002568751930000226
The radial basis function neural network output is Y ═ HW. By solving a least squares problem
Figure GDA0002568751930000227
Then complete radial base can be obtainedAnd (4) a functional neural network structure. Based on the results of the five working conditions and the corresponding parameters, the data driving model of the neutral leaching process under the five different working conditions can be obtained.
In step S5, integrating the chemical reaction balance model, the reaction kinetics total model, and the neutral leaching process data driving model under all the operating conditions to obtain a neutral leaching process integrated model; the neutral leaching process integrated model is used for soft measurement of pH value.
Specifically, let the three models obtained in the above step be f1(i)(X),f2(i)(X),f3(i)(X), wherein i is 5, and the number of the working conditions is shown. In the embodiment of the invention, the membership function is used for expressing the membership of a current state belonging to a certain working condition or a certain model, and the membership function parameter is trained through historical data to obtain a final integrated model as follows:
Figure GDA0002568751930000231
wherein: x represents input parameters of each model; when j is 1, representing a chemical reaction equilibrium model, when j is 2, representing a reaction kinetic overall model, and when j is 3, representing a neutral leaching process data driving model;
gi(σji) A membership function for the ith condition belonging to the jth model;
σjiis a membership function parameter;
ω1、ω2and ω3Respectively representing the weight of the chemical reaction equilibrium model, the total reaction kinetic model and the neutral leaching process data driving model, and ξ is a deviation term.
The above integration model is summarized as the regression form:
f(X)＝wTy + ξ formula (10)
Wherein:
wT＝(ω1g1(σ11),...,ω1g5(σ15),ω2g1(σ21),...,ω2g5(σ25),ω3g1(σ31),...ω3g5(σ35))
y＝(f1(1)(X),...,f1(5)(X),f2(1)(X),...,f2(5)(X),f3(1)(X),...,f3(5)(X))
selecting mean square error as cost function, and introducing L2Norm regularization, the objective function is as follows:
Figure GDA0002568751930000241
wherein: m is the number of samples;
Figure GDA0002568751930000242
is an actual measured value; λ is a regularization parameter; the parameter to be solved is { omega1,ω2,σ1,σ2...,σ5}。
Is provided with
Figure GDA0002568751930000243
B is a row vector of 1 × m, then for a regression equation of the form (10), there is:
Figure GDA0002568751930000244
wherein: a (λ) ═ B (B)TB+mλI)-1BTThus, it can be seen that:
Figure GDA0002568751930000245
and (3) solving the formulas (11) and (12) to obtain lambda, and then carrying the formula (10) to obtain the parameters of the integrated model, so that the integrated model in the neutral leaching process can be obtained.
The embodiment of the invention also provides a system for soft measurement of the pH value in the neutral leaching process of zinc hydrometallurgy, which comprises a computer, wherein the computer comprises:
at least one memory cell;
at least one processing unit;
wherein, at least one instruction is stored in the at least one storage unit, and the at least one instruction is loaded and executed by the at least one processing unit to realize the following steps:
s1, acquiring reaction tank data, wherein the reaction tank data comprises: fj#Flow rate of solution into the jth reaction tank, cj#M is the acidity of the solution entering the jth reaction tankj#The mass of zinc calcine entering the jth reaction tank per hour, the flow rate F of each solvent entering each reaction tankiThe acidity c of each solvent fed into each reaction tankiAnd the flow rate m of zinc calcine entering each reaction tanki；
S2 based on Fj#And cj#Obtaining H+(ii) cumulative amount of; based on mj#Obtaining H+The amount of consumption of (c); based on the above H+And the above H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on the above H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition;
s3 based on Fi、ciAnd miObtaining a reaction kinetic model of each reaction tank; integrating the reaction kinetic models of all the reaction tanks to obtain a reaction kinetic total model; acquiring a reaction dynamics total model under each working condition based on a preset working condition;
s4 based on Fj#And mj#Acquiring a neutral leaching process data driving model, and acquiring the neutral leaching process data driving model under each working condition based on a preset working condition;
s5, integrating the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model; the neutral leaching process integrated model is used for soft measurement of pH value.
It can be understood that the above-mentioned measurement system provided in the embodiment of the present invention corresponds to the above-mentioned measurement method, and for the explanation, examples, and beneficial effects of the relevant contents, reference may be made to the corresponding contents in the pH value soft measurement method based on the neutral leaching process of zinc hydrometallurgy, and details are not described here.
In summary, compared with the prior art, the method has the following beneficial effects:
the embodiment of the invention obtains the data of the reaction tank; reaction tank data based acquisition H+Cumulative amount of (A) and H+The amount of consumption of (c); based on H+Cumulative amount of (A) and H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition; acquiring a reaction kinetic model of each reaction tank based on the reaction tank data; integrating the reaction kinetic models of all the reaction tanks to obtain a total reaction kinetic model under each working condition; acquiring a neutral leaching process data driving model under each working condition based on the reaction tank data; and integrating the chemical reaction balance model, the reaction dynamics total model and the neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model. According to the embodiment of the invention, three pH value soft measurement models under different working conditions are respectively constructed according to relevant data in the reaction tank, and the three models are integrated to obtain a final neutral leaching process integrated model, so that the real-time measurement or prediction of the pH value can be effectively realized.
It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments. In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (1)

1. A method for soft measurement of pH value in neutral leaching process of zinc hydrometallurgy is characterized in that the method for soft measurement of pH value is executed by a computer and comprises the following steps:
obtaining reaction tank data, the reaction tank data comprising: fj#For the solution entering the jth reaction tankFlow rate, cj#M is the acidity of the solution entering the jth reaction tankj#The mass of zinc calcine entering the jth reaction tank per hour, the flow rate F of each solvent entering each reaction tankiThe acidity c of each solvent fed into each reaction tankiAnd the flow rate mi of the zinc calcine entering each reaction tank;
based on Fj#And cj#Obtaining H+(ii) cumulative amount of; based on mj#Obtaining H+The amount of consumption of (c); based on the H+And said H+Obtaining the consumption of the last reaction tank outlet H+Concentration; based on the H+Obtaining a chemical reaction balance model according to the concentration; acquiring a chemical reaction balance model under each working condition based on a preset working condition;
based on Fi、ciAnd mi obtaining a reaction kinetic model of each reaction tank; integrating the reaction kinetic models of all the reaction tanks to obtain a reaction kinetic total model; acquiring a reaction dynamics total model under each working condition based on a preset working condition;
based on Fj#And mj#Acquiring a neutral leaching process data driving model, and acquiring the neutral leaching process data driving model under each working condition based on a preset working condition;
integrating a chemical reaction balance model, a reaction dynamics total model and a neutral leaching process data driving model under all working conditions to obtain a neutral leaching process integrated model; the neutral leaching process integrated model is used for soft measurement of pH value;
said H+The method of obtaining the accumulated amount of (a) includes:
Figure FDA0002568751920000011
Tj＝20(n-j+1)
wherein:
Tjthe accumulated time length of each reaction tank is used; j is 1, n, n is the number of reaction tanks;
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
Figure FDA0002568751920000021
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#With the acidity c of the solution entering the jth reaction tankj#Accumulating the products;
said H+The method for obtaining the consumption of (1) comprises:
Figure FDA0002568751920000022
wherein:
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of a substance that is a reactant;
Figure FDA0002568751920000023
for the jth reaction tank at TjThe mass m of zinc calcine entering the jth reaction tank per hour in the time periodj#Accumulation of (1);
said H+The concentration acquisition method comprises the following steps:
Figure FDA0002568751920000024
Figure FDA0002568751920000031
for the jth reaction tank at TjSolution flow F into the jth reaction tank in the time periodj#Accumulation of (1);
the chemical reaction equilibrium model is as follows:
Figure FDA0002568751920000032
wherein:
Fj#the solution flow rate entering the jth reaction tank;
cj#the acidity of the solution entering the jth reaction tank;
mj#the mass of zinc calcine entering the jth reaction tank per hour;
theta is the solubility of zinc calcine, MAOThe amount of a substance that is a reactant;
the preset working conditions comprise: an extremely low acid condition, a normal condition, a high acid condition and an extremely high acid condition;
the specific dividing method of the preset working condition comprises the following steps:
obtaining the acid-material ratio S and presetting a demarcation point p1、p2、p3And p4；
Figure FDA0002568751920000033
When S < p1When the acid is in the working condition of extremely low acid; when p is1≤S＜p2When the working condition is low acid; when p is2≤S＜p3When the working condition is normal; when p is3≤S＜p4In time, the working condition is high acid; when p is4When the acid content is less than or equal to S, the working condition is extremely high acid;
the reaction kinetic model of each reaction tank is as follows:
pHj#＝-logcj#
Figure FDA0002568751920000041
wherein:
Figure FDA0002568751920000042
Figure FDA0002568751920000043
the outlet flow of the jth reaction tank, V is the body of the reaction tankThe volume of the mixture is accumulated,
Figure FDA0002568751920000044
r0is the particle radius of zinc calcine, αj#M is the proportion of the effective matrix surface area in the zinc calcine entering the j # reaction tankiFor the flow of zinc calcine into each reaction tank,
Figure FDA0002568751920000045
Figure FDA0002568751920000046
the surface area of the manganese ore pulp and the effective solid matrix in other solution of the j # reaction tank;
Figure FDA0002568751920000047
i is a solvent species;
t0is the initial time;
Figure FDA0002568751920000048
the acidity of the outlet solution of the jth reaction tank at the initial moment; fiThe flow rate of the ith solvent into the jth reaction tank is shown;
the method for acquiring the data-driven model of the neutral leaching process comprises the following steps:
with Fj#And mj#Taking the pH value as an output quantity, taking a radial basis function neural network as a basic structure, and constructing a data driving model of the neutral leaching process;
the method for acquiring the radial basis function neural network comprises the following steps:
performing data preprocessing on the input quantity based on a min-max normalization method to obtain sample data;
processing the sample data based on a K-means clustering method to obtain a radial basis function;
constructing a radial basis function neural network based on the radial basis functions;
the neutral leaching process integrated model is as follows:
Figure FDA0002568751920000051
wherein:
x represents input parameters of each model;
when j is 1, representing a chemical reaction equilibrium model, when j is 2, representing a reaction kinetic overall model, and when j is 3, representing a neutral leaching process data driving model;
gi(σji) A membership function for the ith condition belonging to the jth model;
σjiis a membership function parameter;
ω1、ω2and ω3Respectively representing the weights of a chemical reaction balance model, a reaction dynamics total model and a neutral leaching process data driving model;
ξ is the bias term.
CN201910951691.6A 2019-10-09 2019-10-09 Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy Active CN110672792B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910951691.6A CN110672792B (en) 2019-10-09 2019-10-09 Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910951691.6A CN110672792B (en) 2019-10-09 2019-10-09 Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy

Publications (2)

Publication Number Publication Date
CN110672792A CN110672792A (en) 2020-01-10
CN110672792B true CN110672792B (en) 2020-08-28

Family

ID=69081040

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910951691.6A Active CN110672792B (en) 2019-10-09 2019-10-09 Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy

Country Status (1)

Country Link
CN (1) CN110672792B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1367388A (en) * 2002-03-05 2002-09-04 江南大学 On-line soft measurement method of pH value and H2 SO3 concentration in acrylonitrile polymerization system
KR20130118682A (en) * 2012-04-20 2013-10-30 경북대학교 산학협력단 Optimized coagulant feeding devices based on the prediction of phosphorus concentrations
CN104700153A (en) * 2014-12-05 2015-06-10 江南大学 PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization
CN104777270A (en) * 2015-03-26 2015-07-15 浙江理工大学 Hydrogenation air cooler system pH value soft measurement method
CN104965971A (en) * 2015-05-24 2015-10-07 北京工业大学 Ammonia nitrogen concentration soft-measuring method based on fuzzy neural network
CN105700579A (en) * 2016-01-26 2016-06-22 国网山东省电力公司青岛供电公司 A PH value prediction method and apparatus for a desulphurization solution in a desulphurization system
CN106745739A (en) * 2016-12-22 2017-05-31 北京工业大学 A kind of method that SBR short distance nitrations are realized based on Neural Network model predictive pH changes
CN106959360A (en) * 2017-03-18 2017-07-18 江西理工大学 The rare-earth mining area farmland water pH value flexible measurement method developed using backward difference
CN107728664A (en) * 2017-05-25 2018-02-23 中南大学 A kind of metallurgical process multiple reactor cascades pH value optimal control method
CN107830891A (en) * 2017-10-26 2018-03-23 仲恺农业工程学院 Aquaculture water quality pH value many reference amounts data acquisition device and data processing method
CN109002862A (en) * 2018-08-22 2018-12-14 齐鲁工业大学 A kind of flexible measurement method neural network based and system towards copper ore floatation machine
EP3298151A4 (en) * 2015-05-19 2019-04-10 The University of Chicago Methods and composition for determining ph
CN110208453A (en) * 2019-05-22 2019-09-06 沈阳博宇科技有限责任公司 The flexible measurement method of caustic sodium concentration in a kind of sodium aluminate solution

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008058804A1 (en) * 2008-11-24 2010-06-02 Mettler-Toledo Ag Method for monitoring a potentiometric measuring probe

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1367388A (en) * 2002-03-05 2002-09-04 江南大学 On-line soft measurement method of pH value and H2 SO3 concentration in acrylonitrile polymerization system
KR20130118682A (en) * 2012-04-20 2013-10-30 경북대학교 산학협력단 Optimized coagulant feeding devices based on the prediction of phosphorus concentrations
CN104700153A (en) * 2014-12-05 2015-06-10 江南大学 PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization
CN104777270A (en) * 2015-03-26 2015-07-15 浙江理工大学 Hydrogenation air cooler system pH value soft measurement method
EP3298151A4 (en) * 2015-05-19 2019-04-10 The University of Chicago Methods and composition for determining ph
CN104965971A (en) * 2015-05-24 2015-10-07 北京工业大学 Ammonia nitrogen concentration soft-measuring method based on fuzzy neural network
CN105700579A (en) * 2016-01-26 2016-06-22 国网山东省电力公司青岛供电公司 A PH value prediction method and apparatus for a desulphurization solution in a desulphurization system
CN106745739A (en) * 2016-12-22 2017-05-31 北京工业大学 A kind of method that SBR short distance nitrations are realized based on Neural Network model predictive pH changes
CN106959360A (en) * 2017-03-18 2017-07-18 江西理工大学 The rare-earth mining area farmland water pH value flexible measurement method developed using backward difference
CN107728664A (en) * 2017-05-25 2018-02-23 中南大学 A kind of metallurgical process multiple reactor cascades pH value optimal control method
CN107830891A (en) * 2017-10-26 2018-03-23 仲恺农业工程学院 Aquaculture water quality pH value many reference amounts data acquisition device and data processing method
CN109002862A (en) * 2018-08-22 2018-12-14 齐鲁工业大学 A kind of flexible measurement method neural network based and system towards copper ore floatation machine
CN110208453A (en) * 2019-05-22 2019-09-06 沈阳博宇科技有限责任公司 The flexible measurement method of caustic sodium concentration in a kind of sodium aluminate solution

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
Prediction model of slurry pH based on mechanism and error compensation for mineral flotation process;Xiaoli Wang et al.;《Chinese Journal of Chemical Engineering》;20180831;第26卷(第8期);第1766-1772页 *
Soft sensor and expert control for blending and digestion process in alumina metallurgical industry;YongGang Li et al.;《Journal of Process Control》;20130831;第23卷(第7期);第1012-1021页 *
基于机器视觉的矿物浮选pH软测量方法;阳春华 等;《计算机工程与应用》;20110131;第47卷(第1期);第228-230、248页 *
有色冶金净化过程建模与优化控制问题探讨;孙备 等;《自动化学报》;20170630;第43卷(第6期);第880-892页 *
湿法炼锌浸出过程中pH的控制;何献忠;《西安科技大学学报》;20090731;第29卷(第4期);第487-499页 *
状态估计软测量技术在湿法冶金控制中的应用;朱晓青;《自动化与仪表》;20130630(第6期);第6-9页 *

Also Published As

Publication number Publication date
CN110672792A (en) 2020-01-10

Similar Documents

Publication Publication Date Title
CN109492265B (en) Wastewater effluent index prediction method based on dynamic nonlinear PLS soft measurement method
CN101482750B (en) Cobalt oxalate granularity prediction method in hydrometallurgical synthesis process
Yue et al. Multivariate nonparametric control chart with variable sampling interval
CN109603617B (en) Mixed homogenate system and application thereof
CN1126515A (en) Process of measuring chemical and physical parameters for characterisation and classification of aqueous suspensions
CN110390132B (en) Nonferrous metallurgy unit procedure digitalization and modeling method based on process state space
CN104655607B (en) A kind of flotation froth layer antimony sulfide ore article position detecting method
CN111693667A (en) Water quality detection system and method based on gated recursive array
CN114417740B (en) Deep sea breeding situation sensing method
CN110672792B (en) Soft measurement method and system for pH value in neutral leaching process of zinc hydrometallurgy
Tuan et al. A smart diagnostic tool based on deep kernel learning for on-site determination of phosphate, calcium, and magnesium concentration in a hydroponic system
CN101995891A (en) Method for online analysis of water content of solid master batch recovery system in aromatic acid production
CN110826794A (en) Power plant coal consumption reference value rolling prediction method and device based on PSO (particle swarm optimization) SVM (support vector machine)
CN112750507B (en) Method for simultaneously detecting nitrate and nitrite contents in water based on hybrid machine learning model
CN100370453C (en) Rare-earth cascade extraction separation component content soft measuring method
CN116953184A (en) Construction method of residual chlorine online detection model and residual chlorine concentration online detection method
CN114355846A (en) Fault diagnosis method for papermaking sewage treatment process based on SBR simulation model
CN114487284A (en) Method and system for measuring concentration of heavy metal in air
Ben‐Yaakov et al. An automatic method for on‐line estimation of the photosynthetic rate in open algal ponds
CN113065242A (en) KPLSR model-based soft measurement method for total nitrogen concentration of effluent from sewage treatment
Majcen et al. Linear and non-linear multivariate analysis in the quality control of industrial titanium dioxide white pigment
CN109726474B (en) Online-correction multi-scale forecasting system for propylene polymerization production process
CN109858699B (en) Water quality quantitative simulation method and device, electronic equipment and storage medium
CN112899496A (en) Method and system for estimating concentration of copper ions at inlet of zinc hydrometallurgy purification cobalt removal process
CN116523388B (en) Data-driven quality modeling method based on industrial Internet platform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant