CN115755608B - Energy consumption optimization decision method for high-pressure roller mill - Google Patents
Energy consumption optimization decision method for high-pressure roller mill Download PDFInfo
- Publication number
- CN115755608B CN115755608B CN202211445935.1A CN202211445935A CN115755608B CN 115755608 B CN115755608 B CN 115755608B CN 202211445935 A CN202211445935 A CN 202211445935A CN 115755608 B CN115755608 B CN 115755608B
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- roller
- case library
- roller mill
- 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
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005457 optimization Methods 0.000 title claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000003064 k means clustering Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 239000000463 material Substances 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 230000006798 recombination Effects 0.000 claims description 2
- 238000005215 recombination Methods 0.000 claims description 2
- 230000003068 static effect Effects 0.000 claims description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 abstract description 3
- 239000011707 mineral Substances 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Landscapes
- Crushing And Grinding (AREA)
Abstract
The invention relates to the field of mineral processing industry control parameter decision-making, in particular to an energy consumption optimization decision-making method of a high-pressure roller mill. Comprising the following steps: s1, acquiring required data characteristics by a sensor on site, and storing real-time data into a database; s2: preprocessing the acquired data, removing the data acquired in the non-working time and the data with the roller deviation not meeting the requirements, adding two characteristics (processing amount and energy consumption), and filtering; s3, clustering by adopting a K-means clustering method and taking the processing capacity as a standard, and selecting the data with the lowest energy consumption in each category to be placed in a case library; s4: the data at the current moment is preprocessed in the same way as S2, and the closest data in the case library is found out by taking the similarity as a standard and is used as output, wherein the calculation of the similarity adopts the maximum correlation coefficient to determine the weighted Euclidean distance of the weight. The invention combines historical experience, simultaneously considers the processing capacity and the energy consumption, intelligently selects the optimal parameters, and can continuously learn and update the data in the case library.
Description
Technical Field
The invention relates to the field of mineral processing industry control parameter decision-making, in particular to an energy consumption optimization decision-making method of a high-pressure roller mill.
Background
The high-pressure roller mill is widely applied to different fields of metallurgy, chemical industry, cement and the like, and plays a main role in the mineral separation process. The operation process of the high-pressure roller mill is still based on the traditional control theory at present, and the problems of large result error, unstable working condition and the like exist for parameter setting depending on manual experience. Meanwhile, the setting of parameters is mostly aimed at high yield, and the cost problem and the environmental problem caused by high energy consumption are ignored.
Therefore, the energy consumption is required to be reduced as a target, the set value of the parameter is intelligently selected, the energy consumption is reduced while the production value is ensured, the cost of enterprises can be reduced, and the environmental protection and carbon neutralization can be realized as much as possible.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides an energy consumption optimization decision method of a high-pressure roller mill, which reduces the energy consumption of the high-pressure roller mill under the condition of ensuring the treatment capacity. Therefore, a case library is established by adopting a K-means clustering method, and the optimal parameters are searched according to the weighted similarity based on the maximum correlation coefficient and are input into a control system, so that the final purpose is achieved.
In order to achieve the above purpose, the invention adopts the following technical scheme that the method comprises the following steps:
and step 1, acquiring required data characteristics (by an on-site sensor), and storing real-time data into a database through communication between the PLC and an upper computer.
Step 2: preprocessing the acquired data, removing the data acquired in the non-working time and the data with the roller deviation not meeting the requirements, adding two characteristics of processing capacity and energy consumption, reconstructing the data characteristics, and finally filtering the data.
And step 3, clustering by adopting a K-means clustering method and taking the processing capacity as a standard, and selecting the data with the lowest energy consumption in each category to be placed in a case library.
And 4, preprocessing the data at the current moment in the same way as the data at the step 2, and finding out the closest data in the case library by taking the similarity as a standard to be output, wherein the calculation of the similarity adopts a maximum correlation coefficient (MIC) to determine the weighted Euclidean distance of the weight.
Further, in the step 2, for the sequence of data processing, firstly, data which are acquired in non-working time and have unsatisfactory roller deviation are removed, then, two data features of a throughput Q and an energy consumption P are added according to formulas (1.1) and (1.2), a roll gap value S is obtained according to formula (1.3), a driving side roll gap and a non-driving side roll gap in a database are replaced, after the recombination of the data features is completed, kalman filtering processing is performed on the data, and input data are obtained; wherein:
Q＝3600nDSρ (1.1)
where n is the rotational speed, D is the roll diameter, S is the roll gap, and ρ is the bulk density.
Wherein P is Liquid and its preparation method Is constant and is different according to different roller mill models; p (P) Compression roller Then according to the collected dynamic and static roller current I Dynamic movement 、I Fixing device Is a real-time change of (2);
S＝(SND+SD)/2 (1.3)
wherein SD is the driving side roll gap, SND is the non-driving side roll gap.
Further, in step 2, the data filtering adopts kalman filtering, and for two data features of the fixed roll material saving valve LS and the movable roll material saving valve LD, two noise parameters in the kalman filtering are: q=0.001, r=0.1, and the filter parameters for the remaining data features are q=0.001, r=1.
In step 3, the data used in the K-means clustering method needs to be two-dimensional or more, so that two data features of the processing capacity and the roll gap are selected for clustering, the processing capacity class smaller than the bottom line value is removed, and samples with the lowest energy consumption are selected from the remaining classes to be placed in a case library to form an initial case library needed in a subsequent algorithm.
Further, in step 4, for the calculation of the similarity SIM, the MIC values of different features with respect to the current of the moving and fixed rollers are calculated according to the formula (1.4) in combination with the maximum correlation coefficient and the euclidean distance, then the weight of each feature is determined according to the formula (1.5), and the calculation formula of the final SIM is (1.6); wherein:
wherein X and Y are the number of bins in the X and Y directions of the sample, respectively, and B is typically n according to experience 0.5～0.6 N isNumber of samples.
Wherein omega j MIC for the weight of the jth feature j MIC values for the j-th feature.
Wherein m is the feature quantity, x j As the j-th feature of the input, x kj Is the j-th feature of the k-th case.
Compared with the prior art, the invention has the beneficial effects.
The case library combines historical experience, can intelligently select optimal parameters, continuously learn and update data in the case library, and avoid errors caused by manual parameter adjustment. Meanwhile, the energy consumption and the treatment capacity are taken into consideration, and the aim of the invention is achieved.
Drawings
The invention is further described below with reference to the drawings and the detailed description. The scope of the present invention is not limited to the following description.
FIG. 1 is a general flow diagram of an optimized decision control system.
FIG. 2 is a decision data output flow chart.
Detailed Description
As shown in fig. 1-2, the present invention includes the steps of:
s1: the on-site sensor collects the needed data characteristics, and the real-time data is stored in the database through communication between the PLC and the upper computer and collected every two seconds. The collected related data comprise a movable roller current ID, a fixed roller current IS, a stock bin weight BW, a driving side roller gap SD, a non-driving side roller gap SND, a locking pressure FP, a fixed roller material saving valve LS and a movable roller material saving valve LD.
S2: in order to make the establishment of the next case library more accurate and comprehensive, the invention needs to process some acquired data. Firstly, removing data collected in non-working time, and ensuring that the data are live data of work;
firstly, according to the working principle of the high-pressure roller mill, the processing capacity Q and the total energy consumption P of the high-pressure roller mill are calculated as new characteristics:
Q＝3600nDSρ (1.1)。
where n is the rotational speed, D is the roll diameter, S is the roll gap, and ρ is the bulk density.
The total energy consumption mainly comprises a hydraulic system of the high-pressure roller mill and a pressure roller system, the power of the hydraulic system can be calculated by adopting the installed power, so that P in the formula (1.2) Liquid and its preparation method Is constant and varies according to the model of the roller mill. P (P) Compression roller The current of the movable roller changes in real time according to the collected current of the movable roller, so that P is mainly influenced by the current of the movable roller;
further, in order to ensure the grinding effect and prolong the service life of the high-pressure roller mill, the roller bias of the high-pressure roller mill needs to be in a certain range, so that the difference value between the driving side roller gap SD and the non-driving side roller gap SND is smaller than deltas, the unconditional data is deleted, the value of the roller gap is calculated according to the formula (1.3), and the value of the non-driving side stitching driving side roller gap is replaced.
S＝(SND+SD)/2 (1.3)。
Preferably, the new feature combination is subjected to kalman filtering to remove noise existing in the data, and the specific method is as follows:
and step 1, initializing parameters.
Step 2, calculating the current estimated value
Step 3: updating Kalman gain
Step 4: updating estimated covariance
And actual covariance +.>
Turning to step 2.
Step 5: and outputting an estimated value.
Preferably, the values of the final database are obtained.
The final decision is determined by the data in the case library, and in order to ensure the final result, the invention adopts a K-means clustering method to search the case with the lowest energy consumption under the condition of ensuring the processing capacity.
Firstly, selecting roll gaps and throughput in a database as a two-dimensional sample set, setting a category as k, and setting a corresponding category set as C= { C b B=1, 2,.. b (b＝1，2，...，k)。
Preferably, euclidean distance is taken as a criterion for similarity and distance determination.
Preferably, the final sign of the end of classification is to let the objective function
Minimum.
Preferably, after classification is completed, the throughput is less than Q min The samples (the bottom line of the processing amount) are discarded, the rest of the classification set is used for selecting the sample with the lowest energy consumption to be put into a case library, and the case library required by the next step is formed.
S4: the data at the current moment is preprocessed as the same as S2, enters a database, and data with the maximum similarity is searched for output.
First, MIC values of different characteristics with respect to the moving and fixed roller currents are calculated according to the definition formula (1.4):
wherein X and Y are the number of bins in the X and Y directions of the sample, respectively, and B is typically n according to experience 0.5～0.6 (n is the number of samples).
Preferably, different weights are given to different features according to MIC values of the different features with respect to the moving and fixed roller currents, as follows:
wherein omega j MIC for the weight of the jth feature j MIC values for the j-th feature.
Preferably, the similarity is calculated
Is a value of (2).
Preferably, cases with similarity greater than 85% are taken as output, and cases with similarity less than 85% are updated to the case base and output as input data.
Preferably, the weight of the stock bin, the roll gap and the locking pressure in the output data are used as inputs of a control system.
According to the invention, a new characteristic is established according to the working mechanism of the high-pressure roller mill, and the characteristic data is filtered after the unconditional data are removed. A K-means clustering method is adopted to establish a case base, and the rule of selecting the case base is that the required energy consumption is the lowest on the premise of ensuring the minimum processing capacity. After the case library is established, calculating the correlation between a moving fixed roller current and other characteristics, and using the correlation to calculate the weight of the subsequent similarity. And (3) for the data input into the case library, adopting the same processing mode as before, matching the data according to the similarity with the data in the case library, taking the data with the similarity reaching the standard as output, and updating the data which does not reach the standard into the case library.
Example 1 is as follows:
the first step: and (5) data acquisition and transmission.
The data of the high-pressure roller mill is measured by an on-site sensor, the high-pressure roller mill is communicated with an upper computer through a PLC, the real-time data is stored in a database, and the data is sampled every two seconds. The new material and the return material enter the bin through the belt, the displacement of the material saving valve controls the material quantity entering the high-pressure roller mill, and in the process, the collected related data comprise a movable roller current ID, a fixed roller current IS, a bin weight BW, a driving side roller gap SD, a non-driving side roller gap SND, a locking pressure FP, a fixed roller material saving valve LS and a movable roller material saving valve LD.
And a second step of: preprocessing of process data.
1. And (5) establishing a database.
The invention aims to reduce the energy consumption of a high-pressure roller mill, and the actual consumed power of the high-pressure roller mill mainly comprises two parts, namely a hydraulic system and a pressure roller system, wherein the definition of the hydraulic system and the pressure roller system is as follows:
meanwhile, to ensure the processing capacity of the high-pressure roller mill, the calculation formula is as follows:
Q＝3600nDSρ。
where n is the rotational speed, D is the roll diameter, S is the roll gap, and ρ is the bulk density.
The data acquisition is carried out in real time, but the machine is not always in a working state, so the data in a non-working period is firstly removed, and then the energy consumption and the processing amount at each moment are calculated according to a formula.
To ensure stable working conditions, the roll deflection should be less than Δs, i.e., the difference between the drive side gap SD and the non-drive side gap SND should be less than Δs, data that do not meet this condition should also be culled, and the value of the gap S calculated according to equation (1.3). Finally, the database IS characterized by a moving roll current ID, a fixed roll current IS, a stock bin weight BW, a roll gap S, a locking pressure FP, a fixed roll material saving valve position LS, a moving roll material saving valve position LD, a throughput Q and a total power P.
2. And (5) preprocessing data.
The data of the production process has certain noise in the acquisition process, which affects the accuracy of the subsequent algorithm, so that the data needs to be subjected to Kalman filtering. For the fixed and movable roll pitch valve positions LS, LD, the parameter q=0.001, r=0.1 in kalman filtering, the remaining data feature q=0.001, r=1.
And a third step of: and establishing a case library based on K-means clustering.
The control process of the high-pressure roller mill needs to ensure the processing amount of the grinding, so the removal is smaller than Q min Is a data of (a) a data of (b). K-means clustering is carried out on the processing quantity Q of the residual data, K categories are divided, sorting is carried out according to the value of the total power P, and the data with the lowest energy consumption is put into a case library to obtain a case library containing K cases.
1. Selecting a sample set from a database
G＝{g 1 ,g 2 ,...,g N }
＝{(Q 1 ,S 1 ),(Q 2 ,S 2 ),...,(Q N ,S N )}。
Randomly selecting k initial cluster centers, and marking as:
2. the distance between each sample and the center of the k initial clusters is calculated, and in the method, the Euclidean distance is adopted for distance calculation, and the formula is as follows:
wherein, N is the number of samples, k is the number of categories, and after traversing all samples, sample data conforming to the following formula is classified into corresponding category clusters:
d_m＝min[d(g a ,f b )]。
3. updating the center of each class cluster according to the following steps, comparing the center with the center of the last iteration class cluster, and judging whether the center changes or not:
where b is the b-th class, l is the number of iterations, and n is the number of samples allocated to the b-th class.
4. Calculating the value of the objective function J:
judging
If not, go to 2, if yes, go to 5./>
5. And outputting the final classification after the iteration is ended.
6. Centralizing the classifications, the throughput is less than Q min And (3) comparing the energy consumption P corresponding to the samples in the residual classification, and selecting a group of data with the minimum energy consumption to be placed in a final case library.
Fourth step: decision optimization based on case reasoning.
Based on case reasoning, according to the data at the current moment, searching the case with the highest Similarity (SIM) in the case library, outputting the value of the corresponding case, optimizing the value at the next moment, and controlling the operation of the high-pressure roller mill by a control system. In the invention, the similarity calculation adopts a weighted Euclidean distance of a weight determined by MIC, and the specific steps are as follows:
1. MIC values are calculated according to the formula (1.4), weights of each feature are determined according to the formula (1.5), and the calculation results are shown in the following table: table 1. Weights corresponding to different features.
2. The value of SIM is calculated according to the following equation.
Wherein m is the feature quantity, x j As the j-th feature of the input, x kj Is the j-th feature of the k-th case.
3. Taking the case characteristic with the largest SIM value calculated in the step 2 as output, marking as y, inputting three characteristics of a roll gap S, a locking pressure FP and a bin weight BW into a control system, and controlling the operation of the high-pressure roller mill. If the maximum value is less than 85%, the piece of data is updated into the case library, and the case is taken as output.
4. The case library is updated continuously, and the prediction precision is improved.
It should be understood that the foregoing detailed description of the present invention is provided for illustration only and is not limited to the technical solutions described in the embodiments of the present invention, and those skilled in the art should understand that the present invention may be modified or substituted for the same technical effects; as long as the use requirement is met, the invention is within the protection scope of the invention.
Claims (3)
1. The energy consumption optimization decision method of the high-pressure roller mill is characterized by comprising the following steps of: the method comprises the following steps:
step 1, acquiring required data characteristics, and storing real-time data into a database through communication between a PLC and an upper computer; the collected data comprise a movable roller current ID, a fixed roller current IS, a bin weight BW, a driving side roller gap SD, a non-driving side roller gap SND, a locking pressure FP, a fixed roller material saving valve LS and a movable roller material saving valve LD;
step 2: preprocessing the acquired data, removing the data acquired in non-working time and the data with the roller deviation not meeting the requirements, adding two characteristics of processing capacity and energy consumption, reconstructing the data characteristics, and finally filtering the data;
step 3, clustering by adopting a K-means clustering method and taking the processing capacity as a standard, and selecting the data with the lowest energy consumption in each category to be placed in a case library;
step 4, preprocessing the data at the current moment in the same way as the step 2, and finding out the closest data in the case library by taking the similarity as a standard to be output, wherein the calculation of the similarity adopts the maximum correlation coefficient to determine the weighted Euclidean distance of the weight;
taking the case characteristic with the maximum calculated similarity SIM value as output, marking as y, inputting three characteristics of a roll gap S, locking pressure FP and bin weight BW into a control system, controlling the operation of a high-pressure roller mill, and updating the data into the case library if the maximum value of the similarity SIM is less than 85%;
in the step 3, the data used in the K-means clustering method is required to be two-dimensional or more, so that two data features of the processing capacity and the roll gap are selected to be clustered, the processing capacity class smaller than the bottom line value is removed, and a sample with the lowest energy consumption is selected from the rest classes to be placed in a case library, so that an initial case library containing K cases required in a subsequent algorithm is formed;
in step 4, calculating MIC values of different characteristics about the current of the movable and fixed rollers according to a formula (1.4) by combining the maximum correlation coefficient and the Euclidean distance, determining the weight of each characteristic according to a formula (1.5), and finally determining the calculation formula of the SIM as (1.6); wherein:
wherein X and Y are the number of bins in the X and Y directions of the sample, respectively, and B is typically n according to experience 0.5～0.6 N is the number of samples;
wherein omega j MIC for the weight of the jth feature j MIC values for the j-th feature;
wherein m is the feature quantity, x j As the j-th feature of the input, x kj Is the j-th feature of the k-th case.
2. The energy consumption optimization decision method of a high-pressure roller mill according to claim 1, wherein: in the step 2, for the sequence of data processing, firstly, data which are acquired in non-working time and have unsatisfactory roller deflection are removed, then two data characteristics of the throughput Q and the energy consumption P are added according to formulas (1.1) and (1.2), then a roll gap value S is obtained according to formula (1.3), a driving side roll gap and a non-driving side roll gap in a database are replaced, after the recombination of the data characteristics is completed, kalman filtering processing is carried out on the data, and input data are obtained; wherein:
Q＝3600nDSρ (1.1)
wherein n is the rotation speed, D is the roller diameter, S is the roller gap, and ρ is the bulk density;
wherein P is Liquid and its preparation method Is constant according to different roller mill model numbersIs different from the other; p (P) Compression roller Then according to the collected dynamic and static roller current I Dynamic movement 、I Fixing device Is a real-time change of (2);
S＝(SND+SD)/2 (1.3)
wherein SD is the driving side roll gap, SND is the non-driving side roll gap.
3. The energy consumption optimization decision method of a high-pressure roller mill according to claim 1, wherein: in the step 2, the data filtering adopts Kalman filtering, and for two data characteristics of the fixed roll material saving valve LS and the movable roll material saving valve LD, two noise parameters in the Kalman filtering are as follows: q=0.001, r=0.1, and the filter parameters for the remaining data features are q=0.001, r=1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211445935.1A CN115755608B (en) | 2022-11-18 | 2022-11-18 | Energy consumption optimization decision method for high-pressure roller mill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211445935.1A CN115755608B (en) | 2022-11-18 | 2022-11-18 | Energy consumption optimization decision method for high-pressure roller mill |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115755608A CN115755608A (en) | 2023-03-07 |
| CN115755608B true CN115755608B (en) | 2023-05-30 |
Family
ID=85373267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211445935.1A Active CN115755608B (en) | 2022-11-18 | 2022-11-18 | Energy consumption optimization decision method for high-pressure roller mill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115755608B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7177863B2 (en) * | 2002-04-26 | 2007-02-13 | International Business Machines Corporation | System and method for determining internal parameters of a data clustering program |
| CN105241239B (en) * | 2015-09-10 | 2017-07-21 | 广西大学 | A kind of baked brick tunnel kiln roasting process intelligent optimized control method and device |
| CN109443766A (en) * | 2018-09-10 | 2019-03-08 | 中国人民解放军火箭军工程大学 | A kind of heavy-duty vehicle gearbox gear Safety Analysis Method |
| CN113239482B (en) * | 2021-04-23 | 2022-02-08 | 北京科技大学 | Dynamic prediction method and device for converter post-blowing carbon content |
| CN115291519B (en) * | 2022-08-16 | 2024-04-12 | 中南大学 | Intelligent optimization control method for ore grinding process |
-
2022
- 2022-11-18 CN CN202211445935.1A patent/CN115755608B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115755608A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108469180B (en) | Method for establishing sintering end point prediction system based on big data and machine learning | |
| CN109472057B (en) | Product processing quality prediction device and method based on cross-process implicit parameter memory | |
| CN108469797B (en) | Neural network and evolutionary computation based ore grinding process modeling method | |
| CN113177358B (en) | Soft measurement method for cement quality based on fuzzy fine-grained feature extraction | |
| CN115351601B (en) | Tool wear monitoring method based on transfer learning | |
| CN112749840B (en) | Method for acquiring energy efficiency characteristic index reference value of thermal power generating unit | |
| CN1307415C (en) | Soft investigating method for overflow grain index of ore grinding system based on case inference | |
| CN111126255A (en) | Numerical control machine tool cutter wear value prediction method based on deep learning regression algorithm | |
| CN111881860B (en) | Modeling method of hob abrasion in-situ recognition model and hob abrasion in-situ recognition method | |
| CN116611743B (en) | Building engineering construction quality evaluation method based on big data | |
| CN115755608B (en) | Energy consumption optimization decision method for high-pressure roller mill | |
| CN111730412A (en) | Ant colony optimization algorithm-based micro milling cutter wear state monitoring method of support vector machine | |
| CN116244625A (en) | Overflow type mill load indirect forecasting method based on multi-feature fusion neural network | |
| CN111958321A (en) | Numerical control machine tool cutter wear degree identification method based on deep neural network | |
| CN115169453A (en) | Hot continuous rolling width prediction method based on density clustering and depth residual error network | |
| CN117196881B (en) | Intelligent cultivation information management system based on big data | |
| CN117034601A (en) | Soft measurement modeling method for overflow granularity in multi-station ore dressing process | |
| CN112946072A (en) | Abrasive belt wear state monitoring method based on machine learning | |
| CN113537579A (en) | Cement production quality prediction method integrating CSA and H-ELM | |
| CN117563756A (en) | Control method, device, equipment and storage medium of cement vertical mill system | |
| CN115017671B (en) | Industrial process soft measurement modeling method and system based on online cluster analysis of data flow | |
| CN114580268A (en) | Machine tool machining energy efficiency modeling system and method based on support vector regression and t test | |
| CN113579849A (en) | Digital twinning control method and system for weak rigidity drilling | |
| CN113297542A (en) | Method and device for predicting fresh ball proportion of pelletizer | |
| CN113313181A (en) | Cutter wear prediction method under different working conditions based on incremental learning |
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 |