CN109287021B - Online learning-based intelligent monitoring method for microwave heating temperature field - Google Patents
Online learning-based intelligent monitoring method for microwave heating temperature field Download PDFInfo
- Publication number
- CN109287021B CN109287021B CN201811197619.0A CN201811197619A CN109287021B CN 109287021 B CN109287021 B CN 109287021B CN 201811197619 A CN201811197619 A CN 201811197619A CN 109287021 B CN109287021 B CN 109287021B
- Authority
- CN
- China
- Prior art keywords
- microwave
- control strategy
- heating
- heating mode
- temperature
- 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
- 238000010438 heat treatment Methods 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims description 22
- 238000012544 monitoring process Methods 0.000 title claims description 9
- 238000011217 control strategy Methods 0.000 claims abstract description 43
- 238000003062 neural network model Methods 0.000 claims abstract description 4
- 239000000463 material Substances 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 6
- 230000000295 complement effect Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 239000002131 composite material Substances 0.000 description 6
- 230000005672 electromagnetic field Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000010606 normalization Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000005684 electric field Effects 0.000 description 3
- 238000009529 body temperature measurement Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001720 carbohydrates Chemical class 0.000 description 1
- 235000014633 carbohydrates Nutrition 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003822 epoxy resin Substances 0.000 description 1
- 239000003925 fat Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 102000039446 nucleic acids Human genes 0.000 description 1
- 108020004707 nucleic acids Proteins 0.000 description 1
- 150000007523 nucleic acids Chemical class 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 229920000647 polyepoxide Polymers 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B6/00—Heating by electric, magnetic or electromagnetic fields
- H05B6/64—Heating using microwaves
- H05B6/66—Circuits
- H05B6/68—Circuits for monitoring or control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Electromagnetism (AREA)
- Constitution Of High-Frequency Heating (AREA)
Abstract
A dynamic association relation between a heating mode and a control strategy in a part microwave heating process is learned in real time by adopting a neural network model, the control strategy for compensating the current temperature distribution is predicted in real time according to the idea of complementation of the heating mode based on the model, the uneven temperature distribution is compensated accurately and intelligently, and the accurate control of the part temperature uniformity in the heating process is realized.
Description
Technical Field
The invention relates to a temperature field monitoring method, in particular to a microwave heating temperature field monitoring method, and specifically relates to an intelligent microwave heating temperature field monitoring method based on online learning.
Background
The microwave is an electromagnetic wave having a frequency of 300M to 300 GHz. Microwave heating is a heating mode in which the material absorbs microwave energy and converts the microwave energy into heat energy, so that the temperature of the whole material is raised simultaneously. Due to the high frequency property, the microwave electromagnetic field periodically changes at a remarkable speed of billions of times per second, and polar molecules (typically water molecules, proteins, nucleic acids, fats, carbohydrates, etc.) in the material do polar motion at the same speed under the action of the high frequency electromagnetic field, so that the molecules frequently collide to generate a large amount of friction heat, thereby causing the temperature of the material to rapidly rise in a short time. Based on the heating mechanism, the microwave heating has a series of advantages of high heating speed, small temperature gradient in the thickness direction of the part, selective heating, easy control and the like, so the microwave heating is widely applied to various fields of food processing, material treatment, chemical synthesis and the like.
However, the microwave heating technology has the problem of uneven temperature field of the same layer material of the part. The fundamental reason is that the electromagnetic field in the microwave cavity is distributed in a standing wave state. Near an antinode, the electric field or the magnetic field intensity is high, polar molecules in the part vibrate violently, the temperature rises rapidly, the temperature is high, and a local hot spot is formed; near the wave node, the electric field or the magnetic field intensity is close to zero, the polar molecules in the part vibrate slightly or even do not vibrate, the temperature rise is slow, the temperature is low, and a local cold spot is formed. The uneven distribution of temperature seriously threatens the hygienic safety of food processing and the molding quality of part treatment. The existing method adopts a material rotating tray, a microwave mode stirrer and the like to realize random relative motion between a microwave field and a heated object so as to improve the temperature uniformity. The material rotating tray makes the heated material pass through the areas with higher and lower electric field (or magnetic field) intensity in the microwave cavity in turn, and the temperature uniformity is improved by utilizing the random offset effect between the cold point and the hot point on the same layer material of the part in a period of time. The electromagnetic field mode stirrer is provided with a series of rotating metal sheets at a microwave feed port in the cavity, dynamically disperses incident electromagnetic waves to each region in the cavity, and improves the temperature uniformity of the same layer of material of the part by utilizing the random superposition effect of the dynamic electromagnetic field in a period of time. However, the means such as the material rotating tray and the electromagnetic field mode stirrer belong to a method for temperature distribution random compensation in principle, and the accurate control of the temperature distribution of the same layer of material of the part in the microwave heating process is difficult to realize essentially.
Disclosure of Invention
The invention aims to solve the problem of uneven temperature field of the same layer of material of a part in the existing microwave heating, provides an intelligent monitoring method for the microwave heating temperature field based on online learning, and breaks through the difficult problem of uneven microwave heating in principle.
The technical scheme of the invention is as follows:
an intelligent microwave heating temperature field monitoring method based on online learning is characterized in that: and learning the dynamic association relation between the heating mode and the control strategy in the part microwave heating process in real time by adopting a neural network model, predicting and compensating the control strategy of the current temperature distribution in real time according to the complementary idea of the heating mode on the basis of the model, and carrying out uniform microwave heating on the part.
The establishment of the heating mode control strategy prediction model of the part based on the neural network algorithm means that in the microwave heating process, a temperature sensor is adopted to monitor the temperature distribution of the same layer of material of the part in real time, and for any time k (k is more than or equal to p), the data pairs of the front p groups of heating modes HP and control strategies U which are closest to the current time in a heating mode-control strategy database are adopted:
{(HPk-1,Uk-1),(HPk-2,Uk-2),…,(HPk-p,Uk-p)}
carrying out supervision training on the prediction model;
when k < p, the front k-1 group of heating mode HP and control strategy U data pairs are used:
{(HP1,U1),(HP2,U2),…,(HPk-1,Uk-1)}
carrying out supervision training on the prediction model; a forgetting mechanism is adopted in the training process: in each training, the more distant data from the current moment contributes less to the updating of the model weight, so that the dynamic characteristics of the microwave heating system are more accurately learned;
after training is finished, the idea of complementing based on heating mode is quickly calculated for compensating the current temperature distribution Tk-1Target heating mode HP'kAnd inputting the predicted data into a prediction model which is trained, and rapidly predicting a target heating mode HP'kControl strategy U ofk；
In the control strategy UkOn the basis, the power controller adjusts the power of each microwave source in a working state in real time, and the parts are uniformly heated by microwaves according to a set temperature curve;
according to a control strategy UkAfter a time of Δ T, based on the current temperature profile TkFast calculation of control strategy UkLower actual heating pattern HPkAnd the latest heating mode-control strategy data pair (HP)k,Uk) Saving to a heating mode-control strategy database;
and repeating the process until the whole microwave heating process of the part is completed.
The heating mode of the part is an arbitrary control strategy UkRate of temperature rise at points of the same layer of material of the lower part
(c is a constant).
The control strategy of the heating mode is that the combined state U of a plurality of microwave sources is [ delta ]1,δ2,…,δl]Wherein, delta represents the switch state (value is 0 or 1) of the microwave source, and l representsThe numbers of the individual microwave sources on the oven are shown.
The complementary idea of the heating mode is that a larger microwave power or a heating rate is applied to the area of the same part with the lower material temperature, and a smaller microwave power or a heating rate is applied to the area of the same part with the higher material temperature.
The power controller calculates the total power in the microwave cavity in real time based on PID algorithm according to a set temperature curve, and controls a strategy UkThe power increments are evenly distributed to the currently operating microwave sources on a per se basis.
The invention has the beneficial effects that:
by learning the dynamic association relationship between the heating mode and the control strategy in the microwave heating process of the composite material on line, the accurate and intelligent compensation of the monitored uneven temperature distribution in the microwave heating process of any part is realized, the difficult problem of uneven microwave heating is broken through in principle, and the temperature uniformity of the heated object in the microwave heating process is obviously improved.
Drawings
FIG. 1 is a flow chart of intelligent monitoring of microwave heating temperature field based on online learning.
FIG. 2 is a time series diagram of model online learning and real-time prediction.
Detailed Description
The invention is further described below with reference to the figures and examples.
As shown in fig. 1-2.
In the embodiment, a chopped carbon fiber mat/epoxy resin composite material flat plate part (with the length of 300mm, the width of 300mm and the thickness of 2mm) is used as a heating object, and an octagonal high-performance industrial microwave oven with 16 microwave sources is used as heating equipment. A30-channel optical fiber fluorescence temperature measurement system is adopted to monitor the temperature distribution of the surface of the composite material, and the surface of the composite material is equally divided into 10 (length direction m) × 6 (width direction n) temperature measurement areas. Different microwave source combinations are adopted as a control strategy of the heating mode of the composite material part. The different microwave source combinations mainly include information such as different microwave source numbers or different microwave source distribution positions, and can be described as the following formula:
U＝[δ1,δ2,…,δl]
wherein, U is the control strategy of the heating mode of the composite material part, delta is the on-off state (value is 0 or 1, and 0, open is 1) of a certain microwave source in the microwave cavity, and l is the number (value is less than or equal to 16) of a certain specific microwave source in the microwave cavity. The temperature rise rate distribution of the same layer of material of the part after normalization processing in a period of time is defined as a heating mode:
wherein
In the above formula, c represents a normalization constant (value 10); t ishRepresenting the temperature distribution of the same layer material of the part at the moment h; t ish-1The temperature distribution of the same layer of material of the part at the h-1 moment; delta t is the heating time; pij rThe temperature rise rate of a material at a position with the length direction i and the width direction j on the part after normalization in heating time is represented;
the temperature value of the material at the position of which the length direction is i and the width direction is j on the part at the moment h is represented;
the average temperature of the same layer of the material of the part measured by the temperature sensor at the moment h is represented;
represents the maximum temperature rise of all temperature measuring points of the same layer of the part in the heating time.
Before heating, initializing weight parameters of a prediction model, and setting a temperature process curve. Defining a loss function:
wherein, deltaiFor control strategy historical tag data, delta, generated during microwave heating of a parti' is a control strategy that the model predicts from the input heating pattern. At any time k in the heating process, the prediction model adopts p (p is 50) groups of heating modes HP and control strategy U data pairs which are closest to the current time in the heating mode-control strategy database { (HP)k-1,Uk-1),(HPk-2,Uk-2),…,(HPk-p,Uk-p) And (6) carrying out supervision training. Meanwhile, a forgetting mechanism is adopted, so that the data farther away from the current moment contributes less to the updating of the model weight: dividing 50 groups of data for training into 5 groups according to the time sequence of data generation, wherein each group of 10 data is updated with a weight after each group of data is input into a neural network, and the following formula of each training to the weight according to the thought of gradient descent is as follows:
wherein eta is a constant and lambda is a forgetting coefficient, and the smaller the value is, the more obvious the forgetting mechanism is. n represents the number of groups, n-0 represents the newly generated 10 groups of data, and n-4 represents the 10 groups of data farthest from the current time. If the total data pair generated currently is less than 50 groups, the model is supervised and trained by adopting all data generated currently, at the moment, a forgetting mechanism is not adopted, and the weight is updated based on the thought of gradient descent:
in this way, the change of the dynamic characteristics of the microwave heating system is concerned in real time.
The prediction model is continuously trained in the heating process, and meanwhile, the corresponding control strategy is predicted based on the input heating mode. At the k moment after the heating begins, according to the current material surface temperature distribution
Based on the idea of pattern compensation, the target heating pattern is obtained by the following formula
Wherein:
taking the target heating mode as the input of the prediction model to obtain a group of control strategies:
U(k)＝[δ1,δ2,…,δ16],δ i0 or 1
Wherein the number of the magnetrons in the working state is m, m is less than or equal to 16, the power controller obtains the total power P required by the microwave heating system based on a PID algorithm according to the average temperature of the 30 temperature points monitored in real time and the program control temperature difference information on the target process curve at the corresponding momentmThus, the operating power of the microwave heating system is:
P＝U×Pm÷m＝[δ1,δ2,…,δ16]×Pm÷m
the group of control strategies are applied to a microwave heating system for heating for delta t seconds, the temperature distribution T (k) of the same layer of heated material is obtained through a temperature sensor, so that the temperature rise rate distribution in the period of time is calculated, normalization processing is also carried out, and the actual temperature rise rate distribution, namely a heating mode, is obtained:
wherein:
meanwhile, the above-described heating mode control strategy data pair (HP)k,Uk) The tag data is stored as a set in a heating mode-control policy database.
The above process is repeated until the heating is completed.
The invention adopts a neural network model to learn the dynamic association relation between the heating mode and the control strategy in the part microwave heating process in real time, and predicts and compensates the control strategy of the current temperature distribution in real time based on the idea of the complementation of the heating mode by the model, so as to accurately and intelligently compensate the uneven temperature distribution and realize the accurate control of the part temperature uniformity in the heating process.
The above is only a specific application example of the present invention, and the protection scope of the present invention is not limited in any way. All technical solutions formed by equivalent transformation or equivalent replacement fall within the protection scope of the present invention.
The parts not involved in the present invention are the same as or can be implemented using the prior art.
Claims (6)
1. An intelligent microwave heating temperature field monitoring method based on online learning is characterized in that: the method adopts a neural network model to learn the dynamic association relationship between a heating mode and a control strategy in the microwave heating process of the part in real time, and predicts the control strategy for compensating the current temperature distribution in real time according to the complementary idea of the heating mode based on the model, namely:
establishing a heating mode control strategy prediction model of the part based on a neural network algorithm; in the microwave heating process, a temperature sensor is adopted to monitor the temperature distribution of the same layer material of the part in real time, and for any time k (k is more than or equal to p), the data pairs of the front p groups of heating modes HP and control strategies U which are closest to the current time in a heating mode-control strategy database are adopted:
{(HPk-1,Uk-1),(HPk-2,Uk-2),…,(HPk-p,Uk-p)}
carrying out supervision training on the prediction model;
after training is finished, the idea of complementing based on heating mode is quickly calculated for compensating the current temperature distribution Tk-1Target heating mode HP'kAnd inputting the predicted data into a prediction model which is trained, and rapidly predicting a target heating mode HP'kControl strategy U ofk；
In the control strategy UkOn the basis, the power controller adjusts the power of each microwave source in a working state in real time, and the parts are uniformly heated by microwaves according to a set temperature curve;
according to a control strategy UkAfter a time of Δ T, based on the current temperature profile TkFast calculation of control strategy UkLower actual heating pattern HPkAnd the latest heating mode-control strategy data pair (HP)k,Uk) Saving to a heating mode-control strategy database;
and repeating the process until the whole microwave heating process of the part is completed.
2. The method of claim 1, wherein: when k < p, the front k-1 group of heating mode HP and control strategy U data pairs are used:
{(HP1,U1),(HP2,U2),…,(HPk-1,Uk-1)}
and carrying out supervision training on the prediction model.
3. The method of claim 1, wherein: the heating mode of the part is an arbitrary control strategy UkRate of temperature rise at points of the same layer of material of the lower part
c is a constant.
4. The method of claim 1, wherein: the control strategy of the heating mode is that the combined state U of a plurality of microwave sources is [ delta ]1,δ2,…,δl]Wherein, delta represents the on-off state of the microwave source, the on value is 1, and the off value is 0), and l represents the number of each microwave source on the microwave oven.
5. The method of claim 1, wherein: the complementary idea of the heating mode is that a larger microwave power or a heating rate is applied to the area of the same part with the lower material temperature, and a smaller microwave power or a heating rate is applied to the area of the same part with the higher material temperature.
6. The method of claim 1, wherein: the power controller calculates the total power in the microwave cavity in real time based on PID algorithm according to a set temperature curve, and controls a strategy UkThe power increments are evenly distributed to the currently operating microwave sources on a per se basis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811197619.0A CN109287021B (en) | 2018-10-15 | 2018-10-15 | Online learning-based intelligent monitoring method for microwave heating temperature field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811197619.0A CN109287021B (en) | 2018-10-15 | 2018-10-15 | Online learning-based intelligent monitoring method for microwave heating temperature field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109287021A CN109287021A (en) | 2019-01-29 |
| CN109287021B true CN109287021B (en) | 2021-01-12 |
Family
ID=65176486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811197619.0A Active CN109287021B (en) | 2018-10-15 | 2018-10-15 | Online learning-based intelligent monitoring method for microwave heating temperature field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109287021B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110213844B (en) * | 2019-06-28 | 2021-04-13 | 厦门艾美森新材料科技股份有限公司 | Air cushion machine and automatic compensation method for heating power of heating wire of air cushion machine |
| CN114621778B (en) * | 2020-12-11 | 2023-09-01 | 中国石油化工股份有限公司 | Memory, biomass microwave pyrolysis process temperature control method, device and equipment |
| CN114679806B (en) * | 2022-04-01 | 2024-04-12 | 昆明理工大学 | Self-switching control method and system for improving microwave heating uniformity |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05113220A (en) * | 1991-10-21 | 1993-05-07 | Matsushita Electric Ind Co Ltd | Cooking equipment |
| GB2293027A (en) * | 1994-09-07 | 1996-03-13 | Sharp Kk | Apparatus for and method of controlling a microwave oven |
| CN103561497A (en) * | 2013-11-18 | 2014-02-05 | 四川大学 | Distributed type microwave heating and drying control device and method |
| CN105142408A (en) * | 2012-12-04 | 2015-12-09 | 英戈·施托克格南特韦斯伯格 | Heat treatment monitoring system |
| CN106037448A (en) * | 2016-07-29 | 2016-10-26 | 广东美的厨房电器制造有限公司 | Cooking control method and equipment and cooking device |
| CN107071953A (en) * | 2017-04-10 | 2017-08-18 | 南京航空航天大学 | Based on the complementary microwave heating temperature uniformity Active Control Method of heating mode |
-
2018
- 2018-10-15 CN CN201811197619.0A patent/CN109287021B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05113220A (en) * | 1991-10-21 | 1993-05-07 | Matsushita Electric Ind Co Ltd | Cooking equipment |
| GB2293027A (en) * | 1994-09-07 | 1996-03-13 | Sharp Kk | Apparatus for and method of controlling a microwave oven |
| CN105142408A (en) * | 2012-12-04 | 2015-12-09 | 英戈·施托克格南特韦斯伯格 | Heat treatment monitoring system |
| CN103561497A (en) * | 2013-11-18 | 2014-02-05 | 四川大学 | Distributed type microwave heating and drying control device and method |
| CN106037448A (en) * | 2016-07-29 | 2016-10-26 | 广东美的厨房电器制造有限公司 | Cooking control method and equipment and cooking device |
| CN107071953A (en) * | 2017-04-10 | 2017-08-18 | 南京航空航天大学 | Based on the complementary microwave heating temperature uniformity Active Control Method of heating mode |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109287021A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108563121B (en) | Intelligent microwave heating temperature field monitoring method based on historical data | |
| CN109287021B (en) | Online learning-based intelligent monitoring method for microwave heating temperature field | |
| Hosen et al. | Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation | |
| CN104460319B (en) | Multiple batches of Batch reaction processes two dimension multi-model predicts iterative learning control method | |
| CN104375475B (en) | The optimal control method of Batch reaction processes in batch reactor | |
| Liao et al. | Integrated hybrid-PSO and fuzzy-NN decoupling control for temperature of reheating furnace | |
| CN101962708B (en) | Temperature uniformity control system for multi-temperature zone of large plate vacuum annealing furnace and control method thereof | |
| CN108566696B (en) | Method for improving microwave heating temperature uniformity | |
| CN103941584A (en) | Temperature control method based on fuzzy self-adaptive controller | |
| CN107071953A (en) | Based on the complementary microwave heating temperature uniformity Active Control Method of heating mode | |
| CN109814636A (en) | The advanced control method of crosslinked cable production temperature based on predictive PI algorithm | |
| Cheng et al. | Double-layered model predictive optimization control strategy for temperature uniformity of microwave heating process | |
| CN109688652B (en) | Method for accurately controlling temperature of microwave high-temperature reactor based on double-layer structure model predictive control | |
| Ma et al. | Using deep reinforcement learning for zero defect smart forging | |
| Pradeep et al. | A finite horizon Markov decision process based reinforcement learning control of a rapid thermal processing system | |
| CN108366446B (en) | Microwave heating temperature field control method based on time-varying electromagnetic field | |
| Apriaskar et al. | Microwave heating control system using genetic algorithm-based PID controller | |
| CN115221944A (en) | Method for controlling heat treatment of large casting based on CNN neural network model | |
| Prist et al. | Temperature control of an innovative aluminium-steel molds induction preheat process placed on automated laser guided vehicles | |
| Wang et al. | Application of soft sensor in welding seam tracking prediction based on LSSVM and PSO with compression factor | |
| Veligorskyi et al. | Variable structure controller for plastic injection moulding system | |
| Yang et al. | Adaptive temperature tracking control of microwave heating high titanium slag based on ε-ADP | |
| Hu et al. | Differential Evolution Algorithm Based Self-adaptive Control Strategy for Fed-batch Cultivation of Yeast. | |
| CN112248387B (en) | Rubber injection molding machine | |
| CN117192996A (en) | Microwave metallurgy process multi-intelligent model predictive control method based on priority negotiation |
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 |