CN118047359A - Control method and system for iron phosphate preparation equipment - Google Patents
Control method and system for iron phosphate preparation equipment Download PDFInfo
- Publication number
- CN118047359A CN118047359A CN202410097346.1A CN202410097346A CN118047359A CN 118047359 A CN118047359 A CN 118047359A CN 202410097346 A CN202410097346 A CN 202410097346A CN 118047359 A CN118047359 A CN 118047359A
- Authority
- CN
- China
- Prior art keywords
- sample
- target
- attribute
- feature
- label
- 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.)
- Pending
Links
- WBJZTOZJJYAKHQ-UHFFFAOYSA-K iron(3+) phosphate Chemical compound [Fe+3].[O-]P([O-])([O-])=O WBJZTOZJJYAKHQ-UHFFFAOYSA-K 0.000 title claims abstract description 64
- 238000002360 preparation method Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 42
- 229910000398 iron phosphate Inorganic materials 0.000 title claims abstract description 31
- 239000005955 Ferric phosphate Substances 0.000 claims abstract description 33
- 229940032958 ferric phosphate Drugs 0.000 claims abstract description 33
- 229910000399 iron(III) phosphate Inorganic materials 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000004519 manufacturing process Methods 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000010219 correlation analysis Methods 0.000 claims abstract description 8
- 210000005036 nerve Anatomy 0.000 claims abstract description 4
- 238000003646 Spearman's rank correlation coefficient Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 11
- 239000012043 crude product Substances 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000000921 elemental analysis Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000003556 assay Methods 0.000 claims 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 4
- 239000000047 product Substances 0.000 description 3
- NBIIXXVUZAFLBC-UHFFFAOYSA-N Phosphoric acid Chemical compound OP(O)(O)=O NBIIXXVUZAFLBC-UHFFFAOYSA-N 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- ACVYVLVWPXVTIT-UHFFFAOYSA-M phosphinate Chemical compound [O-][PH2]=O ACVYVLVWPXVTIT-UHFFFAOYSA-M 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 229910021578 Iron(III) chloride Inorganic materials 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 229910000147 aluminium phosphate Inorganic materials 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000003317 industrial substance Substances 0.000 description 1
- RBTARNINKXHZNM-UHFFFAOYSA-K iron trichloride Chemical compound Cl[Fe](Cl)Cl RBTARNINKXHZNM-UHFFFAOYSA-K 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Landscapes
- General Factory Administration (AREA)
Abstract
The invention provides a control method and a control system for preparation equipment of ferric phosphate, which belong to the technical field of production equipment control and specifically comprise the following steps: collecting an iron phosphate sample and performing element analysis to obtain sample attributes; presetting a target attribute, and performing nerve learning on the sample attribute and the target attribute to obtain a target feature and a sample feature respectively; performing correlation analysis on the target characteristics and the sample characteristics to obtain target attributes to be modified; sending sample characteristics corresponding to sample attributes except for the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label; and collecting operation parameters of the iron phosphate preparation equipment, and performing supervised learning based on the first label and the second label to obtain optimized control parameters for controlling the iron phosphate preparation equipment. The method can avoid the influence of subjective factors on the optimal control of equipment, and improves the quality and purity of the preparation of the ferric phosphate and the safety in the preparation process.
Description
Technical Field
The invention relates to the technical field of production equipment control, in particular to a method and a system for controlling preparation equipment of ferric phosphate.
Background
The optimization scheme of the production equipment of some industrial chemical supplies at present mainly collects the parameter information of the equipment, carries out the problem existing in manual prejudgement through equipment parameters, carries out data acquisition of crude products, and then carries out construction and optimization of a model so as to carry out intelligent control on the preparation equipment.
However, in this method, subjective consciousness of a worker cannot be eliminated, when sample collection is primarily conducted, if the deviation of sample collection causes deviation of direction of parameter adjustment and optimization of the equipment, and in addition, when neural learning is also conducted, loss contribution of degraded samples to model optimization parameters of preparation equipment is not considered, on the preparation equipment of ferric phosphate, optimization of the preparation equipment is generally not complete enough, the error rate is high, mechanical failure of equipment is caused, toxic byproducts such as phosphoric acid or ferric chloride are even generated, and potential safety hazards exist.
Disclosure of Invention
The present invention is directed to solving at least one of the technical problems existing in the related art. Therefore, the invention provides a control method and a control system for preparation equipment of ferric phosphate.
The invention provides a control method of preparation equipment of ferric phosphate, which comprises the following steps:
s1: collecting and elemental analyzing iron phosphate samples of a production line to obtain sample attributes;
S2: presetting a target attribute, and performing nerve learning on the sample attribute and the target attribute to obtain a target feature and a sample feature respectively;
S3: calculating the spearman rank correlation coefficients of the target features and the sample features so as to perform correlation analysis of the target features and the sample features and obtain target attributes to be modified;
s4: sending sample characteristics corresponding to the sample attributes except the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label;
S5: collecting operation parameters of iron phosphate preparation equipment, and performing supervised learning on the operation parameters based on the first label and the second label to obtain optimized control parameters;
S6: inputting the optimized control parameters into the preparation equipment of the ferric phosphate to complete the control.
According to the control method of the preparation equipment of the ferric phosphate, the sample attributes in the step S1 are obtained through verification analysis by an elemental analysis method, and the sample attributes comprise sample purity, reaction yield and sample stability.
According to the control method of the preparation equipment of the ferric phosphate provided by the invention, the step S3 further comprises the following steps:
S31: respectively preprocessing the target characteristic and the sample characteristic to obtain a preprocessed target characteristic and a preprocessed sample characteristic;
s32: selecting the similar attributes in the pretreatment target features and the pretreatment sample features to perform one-to-one correspondence, and constructing a plurality of feature pairs;
S33: calculating and obtaining a spearman rank correlation coefficient of the target feature and the sample feature based on the plurality of feature pairs;
S34: and selecting the corresponding sample attribute of the feature pair with the minimum spearman rank correlation coefficient as the target attribute to be modified.
According to the control method for the preparation equipment of the ferric phosphate provided by the invention, the expression of the spearman rank correlation coefficient in the step S33 is as follows:
Wherein ρ SR is the spearman rank correlation coefficient of the target feature and the sample feature, i is the feature pair index value, N is the total number of feature pairs, x i is the i-th pre-processing target feature, and y i is the i-th pre-processing sample feature.
According to the control method of the preparation equipment of the ferric phosphate, in the step S4, training loss function when the first label is obtained is learned as follows:
wherein, In order to learn the training loss function when the first label is obtained, B is a sample feature index value corresponding to the sample attribute except the target attribute to be modified, B is a total number of sample features corresponding to the sample attribute except the target attribute to be modified, H (-) represents cross entropy, y b is the first label, p (-) represents conditional probability,/>For the b-th weak data enhancement example corresponding to the sample characteristics corresponding to the sample attributes except the target attribute to be modified,/>And b, a strong data enhancement example corresponding to the sample characteristic corresponding to the sample attribute except the target attribute to be modified.
According to the control method of the preparation equipment of the ferric phosphate, in the step S5, the supervisory learning of the optimized control parameters is obtained through a OvR-SVM support vector machine model.
According to the control method of the preparation equipment of the ferric phosphate provided by the invention, the step S6 further comprises the following steps:
And after the preparation equipment of the ferric phosphate is controlled by the optimized control parameters, continuously collecting the crude product of the ferric phosphate obtained by the preparation equipment of the ferric phosphate after the optimized control, and obtaining the attribute of the crude product until the attribute of the crude product meets the target attribute.
The present invention also provides a control system for a production apparatus of iron phosphate, for performing a control method for a production apparatus of iron phosphate as set forth in any one of the above, comprising:
Sample attribute analysis module: the method is used for collecting iron phosphate samples of the production line and performing elemental analysis to obtain sample attributes;
And the characteristic learning module is used for: the system comprises a sample attribute analysis module, a target feature analysis module and a target feature analysis module, wherein the sample attribute analysis module is used for obtaining sample attributes and preset target attributes;
the attribute analysis module to be modified: the spearman rank correlation coefficients are used for calculating the target features and the sample features so as to perform correlation analysis of the target features and the sample features and obtain target attributes to be modified;
The label obtaining module: the method comprises the steps of sending sample characteristics corresponding to sample attributes except for the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label;
And a control parameter optimization module: the method comprises the steps of collecting operation parameters of iron phosphate preparation equipment, and performing supervised learning on the operation parameters based on the first label and the second label to obtain optimized control parameters; and the optimizing control parameters are input into the preparation equipment of the ferric phosphate to complete control.
According to the method and the system for controlling the preparation equipment of the ferric phosphate, the samples of the ferric phosphate are collected in real time and subjected to attribute analysis, then the first rank attribute which is needed to be optimized in the process of optimizing is obtained according to the correlation degree analysis of the sample attributes and the target attributes obtained by analysis, and then multi-label learning of parameters is carried out according to the attribute and other attributes except the attribute.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a control method of a preparation device of ferric phosphate provided by the embodiment of the invention;
Fig. 2 is a schematic structural diagram of a control system of a preparation device of iron phosphate according to an embodiment of the present invention.
Reference numerals:
100. A sample attribute analysis module; 200. a feature learning module; 300. the attribute analysis module is to be modified; 400. a tag obtaining module; 500. and a control parameter optimization module.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. The following examples are illustrative of the invention but are not intended to limit the scope of the invention.
In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the embodiments of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In describing embodiments of the present invention, it should be noted that, unless explicitly stated and limited otherwise, the terms "coupled," "coupled," and "connected" should be construed broadly, and may be either a fixed connection, a removable connection, or an integral connection, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium. The specific meaning of the above terms in embodiments of the present invention will be understood in detail by those of ordinary skill in the art.
In embodiments of the invention, unless expressly specified and limited otherwise, a first feature "up" or "down" on a second feature may be that the first and second features are in direct contact, or that the first and second features are in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the embodiments of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Embodiments of the present invention are described below with reference to fig. 1 to 2.
The invention provides a control method of preparation equipment of ferric phosphate, which comprises the following steps:
s1: collecting and elemental analyzing iron phosphate samples of a production line to obtain sample attributes;
Wherein, the sample attribute in the step S1 is obtained by performing verification analysis through an elemental analysis method, and the sample attribute comprises sample purity, reaction yield and sample stability.
Further, the sample number includes the purity of the sample, the purity is an important standard for measuring the quality of the product, the purity of the product is checked by performing the content of harmful impurities or the content of ferric phosphate by an elemental analysis method, the reaction yield is checked by comparing the effective elements before and after the production, the stability of the sample is also the same as the quality of the sample, and in addition, the energy consumption and the safety of the sample can also be used as the selection range of the sample attribute.
S2: presetting a target attribute, and performing nerve learning on the sample attribute and the target attribute to obtain a target feature and a sample feature respectively;
Further, the target attribute mentioned in step S2 is actually set to have the same properties as the purity, reaction yield and stability of the sample in step S1, and the step is mainly set to be an optimizing index of each attribute, for example, the purity rate of the sample needs to reach the purity rate value of purified ferric phosphate.
In the stage, after the target attribute and the sample attribute are subjected to neural learning, the obtained target characteristic and sample characteristic can simulate the nonlinear relation therein, and are favorable for subsequent characteristic processing, correlation analysis and the like.
S3: calculating the spearman rank correlation coefficients of the target features and the sample features so as to perform correlation analysis of the target features and the sample features and obtain target attributes to be modified;
In this stage, we select the spearman rank correlation coefficient to analyze the correlation corresponding to the same attribute data in the target feature set and the sample feature set, the spearman rank correlation coefficient can measure the correlation between variables, the correlation coefficient obtained by calculation has a value ranging from 0 to 1, and the closer the coefficient is to 0, the smaller the correlation between the two variables is shown.
Wherein, step S3 further comprises:
S31: respectively preprocessing the target characteristic and the sample characteristic to obtain a preprocessed target characteristic and a preprocessed sample characteristic;
s32: selecting the similar attributes in the pretreatment target features and the pretreatment sample features to perform one-to-one correspondence, and constructing a plurality of feature pairs;
S33: calculating and obtaining a spearman rank correlation coefficient of the target feature and the sample feature based on the plurality of feature pairs;
wherein, the expression of the spearman rank correlation coefficient in step S33 is:
Wherein ρ SR is the spearman rank correlation coefficient of the target feature and the sample feature, i is the feature pair index value, N is the total number of feature pairs, x i is the i-th pre-processing target feature, and y i is the i-th pre-processing sample feature.
The constant 6 in this formula is used to calculate the sum of squares of the differences, that is to say to make the adjustment of the weights.
S34: and selecting the corresponding sample attribute of the feature pair with the minimum spearman rank correlation coefficient as the target attribute to be modified.
In step S34, when ρ SR is close to 0, it is proved that the lower the correlation between the pretreatment target feature and the pretreatment sample feature is, the property corresponding to the set of feature values is proved to be most required to be promoted, so we select the property as the target property to be modified.
S4: sending sample characteristics corresponding to the sample attributes except the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label;
In this stage, we are inspired by noise learning, observe that the neural network learns from the noisy sample at a slower speed than from the clean sample, because the noisy sample usually has greater loss in the early training stage, select other target attributes except for the target attribute to be modified, the corresponding sample attribute, the corresponding sample feature, learn, so as to ensure that after the corresponding device parameter correction can be performed on the attribute with the largest difference reflected, the information of the other collected features can not be lost, and provide additional supervision in the subsequent step S5.
The training loss function when the first tag is obtained in the step S4 is:
wherein, In order to learn the training loss function when the first label is obtained, B is a sample feature index value corresponding to the sample attribute except the target attribute to be modified, B is a total number of sample features corresponding to the sample attribute except the target attribute to be modified, H (-) represents cross entropy, y b is the first label, p (-) represents conditional probability,/>For the b-th weak data enhancement example corresponding to the sample characteristics corresponding to the sample attributes except the target attribute to be modified,/>And b, a strong data enhancement example corresponding to the sample characteristic corresponding to the sample attribute except the target attribute to be modified.
In the above formula, we perform weak data enhancement and random strong data enhancement on the sample features corresponding to the sample attributes except the target attribute to be modified, so as to perform training similar to countermeasure learning, and the training is an expert model, which includes a full connection layer and an activation layer, and similarly, when learning the target attribute to be modified, the training architecture performs label acquisition by adopting the same training mode.
S5: collecting operation parameters of iron phosphate preparation equipment, and performing supervised learning on the operation parameters based on the first label and the second label to obtain optimized control parameters;
In step S5, a OvR-SVM support vector machine model is used to obtain supervised learning of the optimized control parameters.
In this stage, we can perform supervised learning by constructing multiple classifiers, one for each classifier, and besides the hierarchical structure, we can also convert the double-layer labels into nested structures, and perform model learning and result output through the multiple layers of labels.
S6: inputting the optimized control parameters into the preparation equipment of the ferric phosphate to complete the control.
After obtaining the control parameters of the optimized iron phosphate preparation equipment, we can convert the control parameters into stream data to control the preparation equipment.
Wherein, step S6 further comprises:
And after the preparation equipment of the ferric phosphate is controlled by the optimized control parameters, continuously collecting the crude product of the ferric phosphate obtained by the preparation equipment of the ferric phosphate after the optimized control, and obtaining the attribute of the crude product until the attribute of the crude product meets the target attribute.
After the control of the iron hypophosphite preparation equipment is closed, the next optimization can be performed according to the sample collected in real time, namely, the circulation can be continuously performed according to the collected sample, so that the iron hypophosphite preparation equipment is controlled and optimized in real time continuously.
The present invention also provides a control system for a production apparatus of iron phosphate, for performing a control method for a production apparatus of iron phosphate as set forth in any one of the above, comprising:
Sample attribute analysis module 100: the method is used for collecting iron phosphate samples of the production line and performing elemental analysis to obtain sample attributes;
Feature learning module 200: the neural learning module is used for performing neural learning on the sample attribute obtained by the sample attribute analysis module 100 and a preset target attribute to obtain a target feature and a sample feature respectively;
The attribute analysis module to be modified 300: the spearman rank correlation coefficients are used for calculating the target features and the sample features so as to perform correlation analysis of the target features and the sample features and obtain target attributes to be modified;
tag acquisition module 400: the method comprises the steps of sending sample characteristics corresponding to sample attributes except for the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label;
Control parameter optimization module 500: the method comprises the steps of collecting operation parameters of iron phosphate preparation equipment, and performing supervised learning on the operation parameters based on the first label and the second label to obtain optimized control parameters; and the optimizing control parameters are input into the preparation equipment of the ferric phosphate to complete control.
According to the control method and system for the iron phosphate preparation equipment, provided by the invention, the attribute data of the sample can be obtained through real-time sample collection and element analysis, then the attribute data is compared with the target attribute to obtain the attribute to be optimized, the control parameter of the double-layer label preparation equipment is learned by the attribute to control the iron phosphate preparation equipment, the subjectivity of optimizing the target pre-judgment by human factors is avoided, and meanwhile, the parameters are selected by utilizing more monitoring information, so that the safety in the generation process of mechanical equipment and chemicals can be ensured, and the parameter control of the preparation equipment can be accurately optimized, so that the yield and the product quality are improved.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for controlling a production facility of iron phosphate, comprising:
s1: collecting and elemental analyzing iron phosphate samples of a production line to obtain sample attributes;
S2: presetting a target attribute, and performing nerve learning on the sample attribute and the target attribute to obtain a target feature and a sample feature respectively;
S3: calculating the spearman rank correlation coefficients of the target features and the sample features so as to perform correlation analysis of the target features and the sample features and obtain target attributes to be modified;
s4: sending sample characteristics corresponding to the sample attributes except the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label;
S5: collecting operation parameters of iron phosphate preparation equipment, and performing supervised learning on the operation parameters based on the first label and the second label to obtain optimized control parameters;
S6: inputting the optimized control parameters into the preparation equipment of the ferric phosphate to complete the control.
2. The method according to claim 1, wherein the sample properties in step S1 are obtained by performing an assay analysis by elemental analysis, and the sample properties include sample purity, reaction yield, and sample stability.
3. The method for controlling a production apparatus of iron phosphate according to claim 1, wherein step S3 further comprises:
S31: respectively preprocessing the target characteristic and the sample characteristic to obtain a preprocessed target characteristic and a preprocessed sample characteristic;
s32: selecting the similar attributes in the pretreatment target features and the pretreatment sample features to perform one-to-one correspondence, and constructing a plurality of feature pairs;
S33: calculating and obtaining a spearman rank correlation coefficient of the target feature and the sample feature based on the plurality of feature pairs;
S34: and selecting the corresponding sample attribute of the feature pair with the minimum spearman rank correlation coefficient as the target attribute to be modified.
4. A control method of a production apparatus of iron phosphate according to claim 3, wherein the expression of the spearman rank correlation coefficient in step S33 is:
Wherein ρ SR is the spearman rank correlation coefficient of the target feature and the sample feature, i is the feature pair index value, N is the total number of feature pairs, x i is the i-th pre-processing target feature, and y i is the i-th pre-processing sample feature.
5. The method according to claim 1, wherein the training loss function when learning to obtain the first label in step S4 is:
wherein, In order to learn the training loss function when the first label is obtained, B is a sample feature index value corresponding to the sample attribute except the target attribute to be modified, B is a total number of sample features corresponding to the sample attribute except the target attribute to be modified, H (-) represents cross entropy, y b is the first label, p (-) represents conditional probability,/>For the b-th weak data enhancement example corresponding to the sample characteristics corresponding to the sample attributes except the target attribute to be modified,/>And b, a strong data enhancement example corresponding to the sample characteristic corresponding to the sample attribute except the target attribute to be modified.
6. The method according to claim 1, wherein in step S5, supervised learning of the optimized control parameters is performed by using OvR-SVM support vector machine model.
7. The method for controlling a production apparatus of iron phosphate according to claim 1, wherein step S6 further comprises:
And after the preparation equipment of the ferric phosphate is controlled by the optimized control parameters, continuously collecting the crude product of the ferric phosphate obtained by the preparation equipment of the ferric phosphate after the optimized control, and obtaining the attribute of the crude product until the attribute of the crude product meets the target attribute.
8. A production apparatus control system of iron phosphate for performing a production apparatus control method of iron phosphate according to any one of claims 1 to 7, comprising:
Sample attribute analysis module: the method is used for collecting iron phosphate samples of the production line and performing elemental analysis to obtain sample attributes;
And the characteristic learning module is used for: the system comprises a sample attribute analysis module, a target feature analysis module and a target feature analysis module, wherein the sample attribute analysis module is used for obtaining sample attributes and preset target attributes;
the attribute analysis module to be modified: the spearman rank correlation coefficients are used for calculating the target features and the sample features so as to perform correlation analysis of the target features and the sample features and obtain target attributes to be modified;
The label obtaining module: the method comprises the steps of sending sample characteristics corresponding to sample attributes except for the target attribute to be modified into a neural network for learning to obtain a first label, and sending the target attribute to be modified into the neural network for learning to obtain a second label;
And a control parameter optimization module: the method comprises the steps of collecting operation parameters of iron phosphate preparation equipment, and performing supervised learning on the operation parameters based on the first label and the second label to obtain optimized control parameters; and the optimizing control parameters are input into the preparation equipment of the ferric phosphate to complete control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410097346.1A CN118047359A (en) | 2024-01-24 | 2024-01-24 | Control method and system for iron phosphate preparation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410097346.1A CN118047359A (en) | 2024-01-24 | 2024-01-24 | Control method and system for iron phosphate preparation equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118047359A true CN118047359A (en) | 2024-05-17 |
Family
ID=91049696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410097346.1A Pending CN118047359A (en) | 2024-01-24 | 2024-01-24 | Control method and system for iron phosphate preparation equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118047359A (en) |
-
2024
- 2024-01-24 CN CN202410097346.1A patent/CN118047359A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109459993B (en) | Online adaptive fault monitoring and diagnosing method for process industrial process | |
| CN111949700A (en) | Intelligent safety guarantee real-time optimization method and system for petrochemical device | |
| WO2021036546A1 (en) | Near-infrared quantitative analysis model construction method based on biased estimation | |
| Chang et al. | A theoretical survey on Mahalanobis-Taguchi system | |
| CN112085252B (en) | Anti-fact prediction method for set type decision effect | |
| CN110322014A (en) | A kind of finished cement specific surface area prediction technique based on BP neural network | |
| Dong et al. | Quality monitoring and root cause diagnosis for industrial processes based on Lasso-SAE-CCA | |
| CN117312816B (en) | Special steel smelting effect evaluation method and system | |
| CN116224947B (en) | Deep learning industrial control system capable of actively integrating domain rule knowledge | |
| Yuan et al. | Abnormal condition identification modeling method based on Bayesian network parameters transfer learning for the electro-fused magnesia smelting process | |
| CN111222798B (en) | Complex industrial process key index soft measurement method | |
| CN114004331A (en) | Fault analysis method based on key indexes and deep learning | |
| CN115096627A (en) | Method and system for fault diagnosis and operation and maintenance in manufacturing process of hydraulic forming intelligent equipment | |
| CN116092014A (en) | Intelligent inspection control method and system based on Internet of things equipment | |
| CN117272196A (en) | Industrial time sequence data anomaly detection method based on time-space diagram attention network | |
| CN114444811A (en) | Aluminum electrolysis mixing data superheat degree prediction method based on attention mechanism | |
| CN116825253B (en) | Method for establishing hot rolled strip steel mechanical property prediction model based on feature selection | |
| CN118047359A (en) | Control method and system for iron phosphate preparation equipment | |
| CN116662925A (en) | Industrial process soft measurement method based on weighted sparse neural network | |
| CN116109039A (en) | Data-driven anomaly detection and early warning system | |
| CN115186584A (en) | Width learning semi-supervised soft measurement modeling method integrating attention mechanism and adaptive composition | |
| CN108614536A (en) | A kind of complex network construction method of cigarette primary processing technology key factor | |
| Prabowo et al. | Improving Internet of Things Platform with Anomaly Detection for Environmental Sensor Data | |
| Yan et al. | Nonlinear quality-relevant process monitoring based on maximizing correlation neural network | |
| CN117870034B (en) | Control method, device and system for environmental parameters of clean room |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |