CN117111558A - Real-time control method of combined grinding system integrating process mechanism and data model - Google Patents
Real-time control method of combined grinding system integrating process mechanism and data model Download PDFInfo
- Publication number
- CN117111558A CN117111558A CN202311109759.9A CN202311109759A CN117111558A CN 117111558 A CN117111558 A CN 117111558A CN 202311109759 A CN202311109759 A CN 202311109759A CN 117111558 A CN117111558 A CN 117111558A
- Authority
- CN
- China
- Prior art keywords
- data
- constraint
- grinding system
- combined grinding
- abnormal
- 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
- 238000000227 grinding Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000008569 process Effects 0.000 title claims abstract description 28
- 230000007246 mechanism Effects 0.000 title claims abstract description 18
- 238000013499 data model Methods 0.000 title claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims abstract description 35
- 230000006870 function Effects 0.000 claims abstract description 27
- 238000004519 manufacturing process Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims abstract description 3
- 238000010801 machine learning Methods 0.000 claims abstract description 3
- 238000003062 neural network model Methods 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims abstract description 3
- 238000011160 research Methods 0.000 claims abstract 2
- 238000005457 optimization Methods 0.000 claims description 24
- 239000004568 cement Substances 0.000 claims description 21
- 239000000463 material Substances 0.000 claims description 15
- 125000004122 cyclic group Chemical group 0.000 claims description 13
- 239000000843 powder Substances 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000004615 ingredient Substances 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 235000019738 Limestone Nutrition 0.000 claims description 2
- 230000008859 change Effects 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims description 2
- 238000002939 conjugate gradient method Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 239000010881 fly ash Substances 0.000 claims description 2
- 238000011478 gradient descent method Methods 0.000 claims description 2
- 239000010440 gypsum Substances 0.000 claims description 2
- 229910052602 gypsum Inorganic materials 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 claims description 2
- 239000006028 limestone Substances 0.000 claims description 2
- 239000011707 mineral Substances 0.000 claims description 2
- 239000002893 slag Substances 0.000 claims description 2
- 239000010421 standard material Substances 0.000 claims description 2
- 238000005303 weighing Methods 0.000 claims description 2
- 230000000903 blocking effect Effects 0.000 claims 1
- 230000001360 synchronised effect Effects 0.000 claims 1
- 230000010485 coping Effects 0.000 abstract description 3
- 239000002994 raw material Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000001354 calcination Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036571 hydration Effects 0.000 description 1
- 238000006703 hydration reaction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000001404 mediated effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Disintegrating Or Milling (AREA)
Abstract
A real-time control method of a combined grinding system integrating a process mechanism and a data model comprises the steps of obtaining a set value of a controlled variable in a current control loop of the combined grinding system, definitely optimizing decision variables of a control problem in real time, constructing an objective function and constraint conditions of the combined grinding system, downloading data to be analyzed, performing smooth processing, removing abnormal values, distinguishing a stable production data set and non-stable production data, expanding the process mechanism, performing data modeling through machine learning algorithm or neural network model training and evaluation of the regression class, expanding abnormal working condition research, generating an abnormal working condition coping knowledge base, sending an abnormal working condition identification result to a lower control system in real time, synchronizing coping measures to the control system, realizing closed loop processing of abnormal working conditions, optimizing and solving the objective function and constraint conditions, and butting the optimized result with the control system.
Description
Technical Field
The invention belongs to the technical field of cement production combined grinding, and particularly relates to a process mechanism and a data model technology.
Background
The cement production mainly comprises the working procedures of raw material preparation, clinker calcination, cement grinding and the like, wherein the cement grinding is a process of overcoming cohesive force among raw material solid molecules, cracking the raw material solid molecules and forming a certain grain composition through mechanical external force acting.
The double closed circuit combined cement grinding system adopts the modes of replacing grinding and grinding more and less grinding, the grinding efficiency is improved, the unit power consumption is reduced, and the problems of nonlinearity, large hysteresis, large inertia, multiple disturbance and the like still exist. For example: when the rotating speed of the powder concentrator is too high or the rotating speed of the tail grinding fan is too low, the granularity of cement is too fine, so that the early hydration rate of cement is too high or the crack resistance is poor; the cement yield is influenced by the grindability of materials, and large fluctuation exists; the ingredients are not scientific, so that the grinding production cost is high. The above problems have plagued the stable production and control of integrated cement grinding systems.
The combined grinding control relates to the control of chemical components of cement products, fineness and specific surface area of cement, steady flow bin weight, mill current, tube outlet mill bucket current, tube mill pressure difference and the like. In a specific control process, the effect of each control loop is influenced by material properties, operator habit and adjustment mode differences and working condition fluctuation. Although the cement factories at home and abroad implement automatic control, such as fuzzy control, PID control, even Advanced Process Control (APC) and other modes, the problems of unreasonable parameter setting, poor performance, poor working condition adaptation and processing capability, excessive dependence on manual experience and the like still exist.
In order to solve the problems, from the technical point of real-time optimization control, the optimization problem of combining mechanism and data is established by comprehensively considering influencing factors in various aspects of quality, cyclic load, unit power consumption, safety and process. The target set value of the controlled variable in the control loop is determined by solving the target function with the constraint condition, and special treatment is developed aiming at the abnormal working condition, so that the stability, the economy and the safety of the combined grinding system are realized.
Disclosure of Invention
In order to solve the technical problems that the setting of the controlled variable in the field is excessively dependent on manual experience, quality, yield, unit electricity consumption, safety and cost cannot be comprehensively considered, real-time online optimization is adopted, a mapping relation between an objective function and a set value of the controlled variable is established, the technical scheme of the set value of the controlled variable is obtained by solving the objective function, the on-site production operation data, a mechanism model and expert experience are fully mined, key indexes such as safety, high efficiency, quality, low consumption and high yield of production operation are fully developed, the transition of the set value of the controlled variable is avoided depending on the manual experience, working condition adaptability is enhanced, the optimizing result of the set value of the controlled variable is reasonable and reliable, the online operation rate of an APC (automatic control) system is improved, the labor intensity of an on-site engineer is reduced, the operation stability of the system is improved, the system operation failure rate is reduced, the fluctuation of the system is improved, the yield of a mill is improved, the screen surplus stability of cement is improved, the main current of the mill and the current of the mill is improved, and the technical effect of unit electricity consumption is reduced.
The method comprises the steps of off-line analysis and on-line operation, wherein the off-line analysis comprises the steps of constructing a working condition identification model and a process model, smoothing data processing, removing abnormal values of data and extracting steady-state data, and the on-line operation comprises the steps of on-line working condition identification, on-line selection and updating of the process model, optimizing and solving an objective function and outputting calculated values, and the specific implementation flow of the method is shown in figure 1. The detailed steps are as follows:
step one: and acquiring a set value of a controlled variable in a current control loop of the combined grinding system, and definitely optimizing a decision variable of a control problem in real time.
Step two: and constructing an objective function and constraint conditions of the combined grinding system, wherein the objective function comprises a cyclic load, a material fineness screen, a specific surface area, unit consumption and a batching cost, and the constraint conditions comprise a quality constraint, a cyclic load constraint, a decision variable constraint, a proportioning constraint, a process constraint and a grinding efficiency constraint.
Step three: and downloading data to be analyzed, smoothing, and eliminating abnormal values.
Step four: the stationary production dataset is distinguished from the non-stationary production dataset.
Step five: and (3) expanding a process mechanism, obtaining proportioning constraint and grinding efficiency of the batching cost and constraint condition of the objective function constructed in the step two, and carrying out data modeling through training and evaluation of a machine learning algorithm or a neural network model of the regression class to obtain material fineness and specific surface area, unit power consumption, cyclic load and unit consumption.
Step six: and (3) researching abnormal working conditions, identifying that the weighing bin is full of overflow, the roller press is arched in the bin, the roller press does work poorly, the pulverizer is full of grinding, the pulverizer is empty of grinding, the belt scale is mediated, and the cyclone cylinder is blocked in the running process corresponding to the non-stationary production data distinguished in the fourth step, and generating an abnormal working condition corresponding knowledge base by combining the influence factors of each abnormal working condition.
Step seven: and D, sending the abnormal working condition identification result obtained in the step six to a lower control system in real time, synchronizing countermeasures to the control system, and realizing closed-loop processing of the abnormal working condition.
Step eight: and (5) optimizing and solving the objective function and constraint conditions obtained in the step five.
Step nine: and D, butting the optimization result obtained in the step eight with a control system.
Drawings
Fig. 1 is a flowchart, fig. 2 is analysis data of the stability of a 1# cement mill, fig. 3 is a trend of the screen residue prediction of a 1# cement mill to 45 μm, fig. 4 is a relation between an objective function and a current of a powder concentrator and a current of a pipe mill hopper, fig. 5 is a comparison of screen residue before and after the 1# cement mill to 45 μm is put into use, and fig. 6 is a comparison of main motor current of the cement mill and current of a lifting machine of the outlet mill before and after the 1# cement mill is put into use.
Detailed Description
The technical scheme of the present invention is specifically described below with reference to the accompanying drawings, based on the nine steps of the foregoing summary, according to an implementation flow, as shown in fig. 1.
Step one: the decision variable X comprises the current X of the pipe outlet grinding bucket 1 Main machine current X of tube mill 2 Constant flow bin weight X 3 Current X of powder selecting machine 4 Negative pressure X of grinding head 5 Current X of roller press 6 Proportioning of ingredients X 7 To X 12 Respectively corresponding to the proportion of clinker, gypsum, limestone, fly ash, slag and externally doped mineral powder.
Step two: let f 1 (X) to f 5 (X) objective functions corresponding to the cyclic load, the material fineness screen residue, the specific surface area, the unit consumption and the batching cost, omega 1 To omega 5 The optimization weights corresponding to the cyclic load, the material fineness residue, the specific surface area, the unit consumption and the batching cost are respectively set by a user according to the control requirement, F and S respectively represent the standard values of the material fineness residue and the specific surface area, are set by a factory according to the cement model production requirement, and F 2 (X) -F represents the approximation degree of the predicted material fineness screen residue and the factory production standard material fineness screen residue, F 3 (X) -S represents the degree of approach of the predicted specific surface area to the factory production standard specific surface area, p i The cost of the ith ingredient is expressed, phi represents the grinding efficiency, and the following formula relationship is obtained.
Step three: and downloading data to be analyzed, smoothing, and eliminating abnormal values.
Step four: the stationary production dataset is distinguished from the non-stationary production dataset as shown in fig. 2.
Step five: aiming at the characteristic of variable production working conditions of the combined grinding system, carrying out data modeling by using an online model pool, selecting a section of data creation model with consistent data distribution characteristics, selecting a corresponding model based on a working condition judgment result for analysis and prediction during online application, optimizing and updating the model pool, enabling the input of the data model to be a decision variable, namely, a controlled variable expected value to be solved, and outputting the expected value as 45um fineness screen residue, wherein the variation trend of the prediction result obtained by the 45um fineness screen residue through the data modeling is shown as a smooth curve in fig. 3, the actual value of the 45um fineness screen residue in the time period is shown as a step-shaped broken line in fig. 3, the prediction value is basically consistent with the variation trend of the actual value, calculating a decision coefficient of the prediction value to be about 0.7, and a correlation coefficient to be about 0.9, and obtaining a desired controlled variable set value by optimizing the approach degree of the prediction value and a factory production standard value through the decision variable reaction trend better based on the 45um fineness screen residue prediction value of the data model.
Step six: aiming at the characteristic of low occurrence frequency of abnormal working conditions, carrying out data modeling by using small sample learning, researching the occurrence condition of the abnormal working conditions from the data change trend, setting T to represent the abnormal working conditions to be identified, x to represent known measurement data, and D T Representing available supervision information dataset, D A Representing a T-independent auxiliary dataset, constructing a model p (y/x) =h (x, D) A ，D T ) Wherein p (y/x) represents the abnormal condition category y identified under the condition that the measurement data x is known, and an abnormal condition corresponding knowledge base is generated by combining the influence factors of each abnormal condition.
Step seven: and D, sending the abnormal working condition identification result obtained in the step six to a lower control system in real time, synchronizing countermeasures to the control system, and realizing closed-loop processing of the abnormal working condition.
Step eight: and calculating a corresponding decision variable value when the objective function is minimum through an optimization solving algorithm. The optimization method includes, but is not limited to, a random gradient descent method, a Newton method, a conjugate gradient method, a Lagrange multiplier method and a heuristic optimization algorithm, the convexity of an objective function is analyzed based on an imaging mode, as shown in fig. 4, the relation between the objective function and the current of a powder concentrator and the current of a tube mill is shown, a plurality of local optimal points are found to exist in the objective function meeting constraint conditions, the optimization problem is a multi-objective nonlinear optimization problem, and the heuristic optimization algorithm is selected to develop the optimization problem for calculation and solution.
Step nine: and (3) sending the optimization result obtained in the step (eight), namely the value of the decision variable X, to an APC system or other control systems of the combined grinding system by using an OPC communication protocol or a Kafka message or an http interface to be used as a controlled variable set value, so as to realize automatic optimization of the controlled variable set value.
According to the flow, the real-time optimization calculation of the controlled variable in the APC control loop or other control modes is realized, the transition dependence of the set value of the controlled variable on manual experience is avoided, and the running stability of the system is improved by 5%; when the set value of the controlled variable is optimally calculated, from the aspects of cyclic load, quality, unit consumption and batching cost, comprehensive optimization is realized, quality constraint, cyclic load constraint, decision variable constraint, proportioning constraint, process constraint and grinding efficiency constraint are fully considered, key indexes such as safety, high efficiency, quality, low consumption and high yield of production operation are considered, unit power consumption is reduced by 2%, and mill yield is improved by 3%; when the system processes a steady state, a real-time optimization result of a controlled variable set value is sent, when the system is in a non-steady state, an abnormal working condition type and a coping treatment scheme are sent, the online operation rate of the APC control system is improved to more than 98%, the labor intensity of field engineers is reduced, and meanwhile, the operation failure rate of the system is obviously reduced; when a process function is constructed, the process function is updated through an online model pool, so that the working condition adaptability is enhanced, the system operation stability is ensured, and the system operation fluctuation of the system before and after the system is put into service is statistically analyzed, so that the system fluctuation is reduced by 5%; when the process function and the objective function are constructed, the data and mechanism dual-drive mode is adopted for unfolding modeling analysis, the factory data value is fully exerted, meanwhile, the process mechanism is followed, and the reasonable and reliable optimization result of the controlled variable set value is ensured.
After the implementation of the specific embodiment, as shown in fig. 5, the stability of the 45um screen residue of the cement mill is obviously improved compared with that before the implementation; as shown in fig. 6, the stability of the main current and the extracting current of the grinding machine is also improved obviously.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof, but rather as being included within the spirit and scope of the present invention.
Claims (7)
1. A real-time control method of a combined grinding system integrating a process mechanism and a data model is characterized by comprising the following steps:
step one: acquiring a set value of a controlled variable in a current control loop of the combined grinding system, and definitely optimizing a decision variable of a control problem in real time;
step two: constructing an objective function and constraint conditions of the combined grinding system, wherein the objective function comprises a cyclic load, a material fineness screen, a specific surface area, unit consumption and a batching cost, and the constraint conditions comprise a quality constraint, a cyclic load constraint, a decision variable constraint, a proportioning constraint, a process constraint and a grinding efficiency constraint;
step three: downloading data to be analyzed, smoothing, and eliminating abnormal values;
step four: distinguishing between a stationary production dataset and a non-stationary production dataset;
step five: expanding a process mechanism, obtaining proportioning constraint of the batching cost and constraint conditions of the objective function constructed in the second step, and carrying out data modeling through training and evaluation of a machine learning algorithm or a neural network model of regression class to obtain material fineness, specific surface area, unit power consumption, cyclic load and unit consumption;
step six: developing abnormal working condition researches, identifying that weighing bins in the fourth-step distinguished non-stationary production data correspond to overflow materials, roller press arch bins, roller press work difference, full grinding of a pulverizer, empty grinding of the pulverizer, mediation of a belt scale and cyclone blocking in the running process, and generating an abnormal working condition corresponding knowledge base by combining influence factors of each abnormal working condition;
step seven: the abnormal working condition identification result obtained in the step six is sent to a lower control system in real time, countermeasures are synchronized to the control system, and closed-loop processing of the abnormal working condition is achieved;
step eight: optimizing and solving the objective function and constraint conditions obtained in the step five;
step nine: and D, butting the optimization result obtained in the step eight with a control system.
2. The method for controlling the combined grinding system in real time by combining the process mechanism and the data model according to claim 1, wherein the first step further comprises: the decision variable X comprises the current X of the pipe outlet grinding bucket 1 Main machine current X of tube mill 2 Constant flow bin weight X 3 Current X of powder selecting machine 4 Negative pressure X of grinding head 5 Current X of roller press 6 Proportioning of ingredients X 7 To X 12 Respectively corresponding to the proportion of clinker, gypsum, limestone, fly ash, slag and externally doped mineral powder.
3. The method for controlling the combined grinding system in real time by combining the process mechanism and the data model according to claim 2, wherein the second step further comprises: let f 1 (X) to f 5 (X) objective functions corresponding to the cyclic load, the material fineness screen residue, the specific surface area, the unit consumption and the batching cost, omega 1 To omega 5 The optimization weights corresponding to the cyclic load, the material fineness residue, the specific surface area, the unit consumption and the batching cost are respectively set by a user according to the control requirement, F and S respectively represent the standard values of the material fineness residue and the specific surface area, are set by a factory according to the cement model production requirement, and F 2 (X) -F represents the approximation degree of the predicted material fineness screen residue and the factory production standard material fineness screen residue, F 3 (X) -S represents the degree of approach of the predicted specific surface area to the factory production standard specific surface area, p i Represents the cost of the ith ingredient, phi represents the grinding efficiency, and the formula is obtainedThe relationship represented.
4. The method for controlling the combined grinding system in real time by combining the process mechanism and the data model according to claim 1, wherein the fifth step further comprises: aiming at the characteristic of variable production working conditions of the combined grinding system, carrying out data modeling by using an online model pool, selecting a section of data creation model with consistent data distribution characteristics, selecting a corresponding model based on a working condition judgment result for analysis and prediction during online application, optimizing and updating the model pool, enabling the input of the data model to be a decision variable, namely, a controlled variable expected value to be solved, and obtaining an expected controlled variable set value through optimizing the approaching degree of the predicted value and a factory production standard value.
5. The method for controlling the combined grinding system in real time by combining the process mechanism and the data model according to claim 1, wherein the step six further comprises: aiming at the characteristic of low occurrence frequency of abnormal working conditions, carrying out data modeling by using small sample learning, researching the occurrence condition of the abnormal working conditions from the data change trend, setting T to represent the abnormal working conditions to be identified, x to represent known measurement data, and D T Representing available supervision information dataset, D A Representing a T-independent auxiliary dataset, constructing a model p (y/x) =h (x, D) A ，D T ) Wherein p (y/x) represents the abnormal condition category y identified under the condition that the measurement data x is known, and an abnormal condition corresponding knowledge base is generated by combining the influence factors of each abnormal condition.
6. The method for controlling the combined grinding system in real time by combining the process mechanism and the data model according to claim 1, wherein the step eight further comprises: and calculating a corresponding decision variable value when the objective function is minimum through an optimization solving algorithm, wherein the decision variable value comprises a random gradient descent method, a Newton method, a conjugate gradient method, a Lagrangian multiplier method and a heuristic optimization algorithm, and analyzing the convexity and convexity of the objective function based on an imaging mode.
7. The method for controlling the combined grinding system in real time by combining the process mechanism and the data model according to claim 1, wherein the step nine further comprises: and (3) sending the optimization result obtained in the step (eight), namely the value of the decision variable, to an APC system or other control systems of the combined grinding system by using an OPC communication protocol or a Kafka message or an http interface to be used as a controlled variable set value, so as to realize automatic optimization of the controlled variable set value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311109759.9A CN117111558A (en) | 2023-08-31 | 2023-08-31 | Real-time control method of combined grinding system integrating process mechanism and data model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311109759.9A CN117111558A (en) | 2023-08-31 | 2023-08-31 | Real-time control method of combined grinding system integrating process mechanism and data model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117111558A true CN117111558A (en) | 2023-11-24 |
Family
ID=88807334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311109759.9A Pending CN117111558A (en) | 2023-08-31 | 2023-08-31 | Real-time control method of combined grinding system integrating process mechanism and data model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117111558A (en) |
-
2023
- 2023-08-31 CN CN202311109759.9A patent/CN117111558A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111701698B (en) | Cement mill system and automatic optimization control system and method thereof | |
| WO2022037500A1 (en) | Material distribution control system and method based on material layer thickness prediction | |
| CN104965532B (en) | Cement raw material ingredient control system and method | |
| CN103030313A (en) | Cement production and optimization system | |
| CN114265885B (en) | A method and system for automatically controlling moisture content of sintering return powder | |
| CN109033511B (en) | A kind of quality coal in cement kiln systems heat consumption analysis method of combined data driving and data mining | |
| CN111047104A (en) | Energy consumption optimization method of grinding system | |
| CN111443597B (en) | Apparatus and method for controlling particle size of vertical mill ore powder | |
| CN111701697A (en) | Cement raw material grinding system and automatic optimization control method thereof | |
| Ma et al. | A novel self-learning fuzzy predictive control method for the cement mill: Simulation and experimental validation | |
| CN102156405B (en) | Sintered ore chemical component prediction and intelligent control system under small sample poor information | |
| Prasath et al. | Soft constrained based MPC for robust control of a cement grinding circuit | |
| CN117111558A (en) | Real-time control method of combined grinding system integrating process mechanism and data model | |
| CN104776045B (en) | A kind of suction adjustment control method | |
| CN107417145B (en) | Method, device and system for controlling temperature of cement clinker sintering decomposing furnace | |
| CN112452520A (en) | Slag vertical mill intelligent method | |
| Itävuo et al. | Size reduction control in cone crushers | |
| Martin et al. | Next generation controllers for kiln/cooler and mill applications based on model predictive control and neural networks | |
| CN104898563B (en) | A kind of ball mill control method | |
| CN113769880A (en) | Cement production raw material mill system control index optimization method based on industrial big data | |
| Kazarinov et al. | Interactive mill control | |
| Eremenko et al. | Neural network based identification of ore processing units to develop model predictive control system | |
| Sahasrabudhe et al. | Control and optimization in cement plants | |
| EP1769292A2 (en) | Process-related systems and methods | |
| CN202351625U (en) | Sintered ore chemical component prediction and intelligent control system under small sample and poor information conditions |
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 |