CN104155956A - Wireless temperature remote monitoring system based on Wi-Fi - Google Patents
Wireless temperature remote monitoring system based on Wi-Fi Download PDFInfo
- Publication number
- CN104155956A CN104155956A CN201410407120.3A CN201410407120A CN104155956A CN 104155956 A CN104155956 A CN 104155956A CN 201410407120 A CN201410407120 A CN 201410407120A CN 104155956 A CN104155956 A CN 104155956A
- Authority
- CN
- China
- Prior art keywords
- neural network
- unit
- resistance wire
- control
- thermopair
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to a wireless monitoring system based on improved BP neural network PID controller. According to the work flow of the system, an industrial personal computer accesses an MMF module through a wireless network which comprises a Wi-Fi module, and monitors the work state of a resistance furnace temperature device in real time; and the MMF module adjusts and controls output according to an improved BP neural network PID control algorithm, so that temperature change quickly reaches a steady state on the premise of small overshoot. The system provided by the invention is composed of a hardware system and software implanted into the MMF module. The hardware system is composed of a management unit, a wireless transmission unit and a control unit. According to the invention, a Wi-Fi network is used as a transmission medium; the system has the advantages of simple stationing and short network-laying construction period; and the destructed network can be easily recovered.
Description
Technical field
The present invention relates to a kind of wireless temperature long distance control system based on Wi-Fi, belong to temperature course automatic control technology field.
Background technology
In recent years, the industrialization that China drives with informationization is just flourish, and temperature has become a kind of important parameter in industrial object control, particularly, in the industry such as metallurgy, chemical industry, machinery, is widely used various heating furnaces, heat-treatment furnace, reacting furnace etc.Because kind and the principle of stove are different, the heating means that therefore adopt and fuel are also different, as coal gas, rock gas, oil electricity etc.For the temperature under the different conditions of production and technological requirement, control, the type of heating adopting, the fuel of selecting, control program is also different.Along with the development of industrial technology, traditional control mode can not meet high precision, high-speed control requirement.In current temperature course supervisory system, great majority all adopt cable network.Wired network system has poor mobility, dumb, expansibility is poor, networking and the shortcoming such as maintenance is not convenient.Along with the development of wireless communication technology, the stability of wireless network and real-time have had very large improvement, are enough to Guarantee control system and safely and steadily run.
Temperature course is non-linear a, Large Time Delay Process.Adopt traditional PI D-algorithm to control temperature course, steady-state response characteristic is better, but is difficult to obtain satisfied dynamic response characteristic.Pid algorithm based on BP neural network can on-line tuning parameter, improve the dynamic property of system, but BP neural network exists the slow defect of speed of convergence, may decline into local smallest point in convergence process, and the optimum that cannot complete parameter is adjusted.
Summary of the invention
The wireless temperature long distance control system that the object of this invention is to provide the temperature course controller of a kind of employing based on Speed Controlling Based on Improving BP Neural Network pid algorithm.
In order to achieve the above object, technical scheme of the present invention has been to provide a kind of wireless temperature long distance control system based on Wi-Fi, it is characterized in that, comprises industrial computer, wireless transmission unit and a plurality of control module; Wireless transmission unit comprises admin site, receiving node, control website, relay reception node and relay; Each control module connects one and controls website, relay reception node and relay are common forms one group for extending the repeater of Internet Transmission distance, between all control websites and repeater, set up radio communication, between relay and admin site, by receiving node, realize radio communication, admin site is connected with industrial computer;
Each control module comprises monitoring server, analog to digital converter, digital to analog converter, active low-pass filter and resistance furnace temperature device; Monitoring server is on the one hand for receiving the data of analog to digital converter, and on the other hand according to passing through digital to analog converter controlling resistance furnace temperature device based on Speed Controlling Based on Improving BP Neural Network pid control algorithm, monitoring server is also connected with control website; Analog to digital converter is by active low-pass filter contact resistance furnace temperature device; Resistance furnace temperature device comprises upper resistance wire and the lower resistance wire for heating, by upper thermopair and lower thermopair, detect respectively temperature Ji Xia resistance wire district, upper resistance wire district temperature, upper resistance wire and lower resistance wire are connected with digital to analog converter, and upper thermopair and lower thermopair are connected with active low-pass filter;
Make u
1, u
2be respectively the input voltage of resistance wire and lower resistance wire, y
1, y
2be respectively the temperature value that thermopair and lower thermopair detect, the system model of the resistance furnace temperature device of the k sometime through simplifying is:
The Speed Controlling Based on Improving BP Neural Network pid control algorithm that monitoring server (MMF) adopts comprises BP neural network unit, traditional PID control unit and controlled device unit, each resistance furnace temperature device is a controlled device unit, at k sometime after Speed Controlling Based on Improving BP Neural Network pid control algorithm input temp controlled quentity controlled variable r (k), obtain input e (k)=r (the k)-y (k) of BP neural network unit and traditional PID control unit, by BP neural network unit, regulated the Proportional coefficient K of conventional PID controllers
p, integration time constant K
iand derivative time constant K
d, self study by neural network, weighting coefficient adjusts, thereby makes its steady state (SS) corresponding to the PID controller parameter under certain optimum control rate, obtains desirable adaptivity and rapidity; The algorithm of BP neural network unit is according to the weighting coefficient of method of steepest descent roll-off network, gets performance scalar functions to be
press J the negative gradient direction search of weighting coefficient adjusted, adopt the method that increases momentum term to improve algorithm, have:
in formula, α is factor of momentum, η is learning rate, learning rate η is larger, pace of learning can be faster, but can cause oscillation effect when excessive, and factor of momentum α obtains excessive may causing, disperses, too small speed of convergence is too slow, in control procedure, according to the situation of change of energy function, constantly regulate the value of η and α to optimize speed of convergence, the output U (k) of traditional PID control unit is:
U(k)=U(k-1)+K
p[e(k)-e(k-1)]+K
Ie(k)+K
D[e(k)-2e(k-1)+e(k-2)]。
The present invention is owing to taking above technical scheme, and it has the following advantages:
1, the present invention adopts Wi-Fi network as transmission medium, layouts simple, and the duration of arranging net is short, the destroyed rear easy recovery of network.
2, the present invention adopts multilayer distributed network, can expand neatly or dwindle monitoring range, and convenient increase and decrease needs the quantity of the controlled device of monitoring, has improved monitoring efficiency simultaneously.
3, the software filtering that the present invention adopts, the compound digital filter algorithm that limit filtration is combined with recurrence average filtering carries out filtering to the random noise of industry spot and periodic noise effectively.
4, the present invention combines the training of BP neural network parameter with traditional PID control algorithm.Conventional PID controllers is directly carried out closed-loop control to controlled device, is obtaining optimized parameter K
p, K
i, K
dprocess in to output control effectively.BP neural network unit, according to the running status of system, on-line tuning parameter K
p, K
i, K
din continuous training process, reach the parameter tuning value of optimal control results, to reaching the optimization of certain performance index, self study by neural network, weighting coefficient adjusts, thereby makes its steady state (SS) corresponding to the PID controller parameter under certain optimum control rate.
Accompanying drawing explanation
Fig. 1 is supervisory system structural representation;
Fig. 2 is resistance furnace temperature structure drawing of device;
Fig. 3 is feedforward compensation device decoupling principle figure;
Fig. 4 is based on Speed Controlling Based on Improving BP Neural Network PID controller architecture figure;
Fig. 5 is temperature course tracking characteristics figure.
Embodiment
For the present invention is become apparent, hereby with preferred embodiment, and coordinate accompanying drawing to be described in detail below.
The present invention proposes a kind of wireless Wi-Fi sensing network supervisory system of Hierarchical network topological structure, realize real time monitoring and the control of industry spot, propose simultaneously a kind of for industrial temperature, control based on Speed Controlling Based on Improving BP Neural Network pid control algorithm, Optimal Control System dynamically and steady-state characteristic.
The structure of a kind of wireless temperature long distance control system based on Wi-Fi provided by the invention as shown in Figure 1, comprises industrial computer, wireless transmission unit and a plurality of control module; Wireless transmission unit comprises admin site MST, receiving node AP, controls website CST, relay reception node R AP and relay RST; Each control module connects one and controls website CST, relay reception node R AP and relay RST are common forms one group for extending the repeater of Internet Transmission distance, between all control website CST and repeater, set up radio communication, between relay RST and admin site MST, by receiving node AP, realize radio communication, admin site MST is connected with industrial computer;
Each control module comprises monitoring server MMF, analog to digital converter ADI, digital to analog converter DAI, active low-pass filter LPF and resistance furnace temperature device; Monitoring server MMF is on the one hand for receiving the data of analog to digital converter ADI, on the other hand according to passing through digital to analog converter DAI controlling resistance furnace temperature device based on Speed Controlling Based on Improving BP Neural Network pid control algorithm, make temperature under the prerequisite of less overshoot, reach fast predefined temperature objectives value, monitoring server MMF is also connected with control website CST; Analog to digital converter ADI is by active low-pass filter LPF contact resistance furnace temperature device; Resistance furnace temperature device comprises upper resistance wire 1 and the lower resistance wire 2 for heating, by upper thermopair 3 and lower thermopair 4, detect respectively resistance wire district temperature Ji Xia resistance wire district temperature, upper resistance wire 1 and lower resistance wire 2 are connected with digital to analog converter DAI, and 4 of upper thermopair 3 and lower thermopairs are connected with active low-pass filter LPF.
Industrial computer is stable performance, the technical grade PC that processing speed is fast.The connected mode of itself and described MST is wired connection.The mode of the MMF that described industrial computer access is described is accessed for inputting corresponding IP address by webpage.Information transmission mode between all MST, AP in wireless transmission unit, CST, RAP, RST is wireless transmission.ADI in control module, DAI and MMF are integrated in a device, and directly by wired mode, are connected with LPF.
Make u
1, u
2be respectively the input voltage of resistance wire 1 and lower resistance wire 2, y
1, y
2be respectively the temperature value that thermopair 3 and lower thermopair 4 detect.Due to aspects such as the heat flow of resistance furnace inside and technique, structures, cause top y
1-u
1with bottom y
2-u
2between there is stronger coupling.This heating process is the multivariable system withstrong coupling with time lag of 2 * 2, and under a certain operating mode, the k constantly model of the resistance furnace temperature device through simplifying is:
In conjunction with Fig. 2, the impact on other loop regulated variables during for the disturbance of elimination set-point, must carry out decoupling zero control to system, by the Feed-forward Compensation Decoupling method principle of Fig. 3, is not difficult to obtain:
And then the mathematical model that solves respectively decoupling compensator is:
After having adopted the compensation of feedforward compensation battle array, the transfer matrix of system has become diagonal matrix, and at this moment system becomes the system of two single-input single-outputs.
Based on Speed Controlling Based on Improving BP Neural Network PID controller, comprise BP neural network unit, traditional PID control unit, controlled device unit.As shown in Figure 4, BP neural network unit is mainly used to regulate three parameter K of conventional PID controllers to its structure
p, K
i, K
d, cross self study, the weighting coefficient adjustment of neural network, thereby make its steady state (SS) corresponding to the PID controller parameter under certain optimum control rate, obtain desirable adaptivity and rapidity.The direct controlled device in traditional PID control unit is carried out closed-loop control, to output dreamboat value.
The algorithm of described BP neural network unit is according to the weighting coefficient of method of steepest descent roll-off network, gets performance scalar functions to be
r (k) is the controlled quentity controlled variable of input, by J, the negative gradient direction search of weighting coefficient is adjusted, and has:
weighting coefficient for output layer.But when error curved surface corresponding to system capacity function is narrow long type, this algorithm jumps at two walls of paddy, causes the vibration of network, has affected the speed of convergence of network, therefore adopt the method that increases momentum term to improve algorithm, have:
In formula, α is factor of momentum, generally gets the number close to 1, utilizes additional momentum item can play the acute variation of smooth gradient direction, increases the stability of algorithm.In calculating, learning rate η is larger, and pace of learning can be faster, but can cause oscillation effect when excessive, generally gets η=0.2-0.5. and factor of momentum α obtains excessive may causing disperses, and too small speed of convergence is too slow.In control procedure, according to the situation of change of energy function, constantly regulate the value of η and α, can optimize speed of convergence.
Adopt the controller formula of increment type PID to be:
The input and output of BP neural network unit are:
In formula, the nodes that r is output layer,
for the output of hidden layer, s=1,2,3,
G (.) is transfer function.Due to three setting parameters of PID in output be all on the occasion of, so get here
tanh represents hyperbolic tangent function, general as the case may be for the output function of neural network.
By the controller formula of formula increment type PID and the input and output of formula network, obtained:
Can obtain the weighting coefficient calculating formula of BP neural network NN output layer:
In like manner obtain the computing formula of hidden layer weighting coefficient:
In formula, g ' (.)=g (x) [1-g (x)],
for
as calculating
an intermediate parameters,
for the output of hidden layer, sgn is sign function, uses here
approximate replacement
Comprehensive described BP neural network unit, traditional PID control unit, controlled device unit.The described output signal based on Speed Controlling Based on Improving BP Neural Network PID controller of order is U (k):
U(k)=U(k-1)+K
p[e(k)-e(k-1)]+K
Ie(k)+K
D[e(k)-2e(k-1)+e(k-2)]。
For the tracking characteristics of verification system to target setting temperature value, initial time set temperature value is 30 ℃, and when 1000s, target setting temperature value is 70 ℃, and when 2000s, set temperature value is 50 ℃.The tracking characteristics of BP-PID algorithm as shown in Figure 5, can be found out based on BP Neural Network PID and can make system respond fast, reaches goal-setting value, and non-overshoot, and dynamic property and steady-state behaviour are all good.
Claims (1)
1. the wireless temperature long distance control system based on Wi-Fi, is characterized in that, comprises industrial computer, wireless transmission unit and a plurality of control module; Wireless transmission unit comprises admin site (MST), receiving node (AP), controls website (CST), relay reception node (RAP) and relay (RST); Each control module connects one and controls website (CST), relay reception node (RAP) and relay (RST) form one group jointly for extending the repeater of Internet Transmission distance, between all control websites (CST) and repeater, set up radio communication, between relay (RST) and admin site (MST), by receiving node (AP), realize radio communication, admin site (MST) is connected with industrial computer;
Each control module comprises monitoring server (MMF), analog to digital converter (ADI), digital to analog converter (DAI), active low-pass filter (LPF) and resistance furnace temperature device; Monitoring server (MMF) is used for receiving the data of analog to digital converter (ADI) on the one hand, according to passing through digital to analog converter (DAI) controlling resistance furnace temperature device based on Speed Controlling Based on Improving BP Neural Network pid control algorithm, monitoring server (MMF) is also connected with control website (CST) on the other hand; Analog to digital converter (ADI) is by active low-pass filter (LPF) contact resistance furnace temperature device; Resistance furnace temperature device comprises upper resistance wire (1) and the lower resistance wire (2) for heating, by upper thermopair (3) and lower thermopair (4), detect respectively resistance wire district temperature Ji Xia resistance wire district temperature, upper resistance wire (1) and lower resistance wire (2) are connected with digital to analog converter (DAI), and upper thermopair (3) and lower thermopair (4) are connected with active low-pass filter (LPF);
Make u
1, u
2be respectively the input voltage of resistance wire (1) and lower resistance wire (2), y
1, y
2be respectively the temperature value that thermopair (3) and lower thermopair (4) detect, the system model of the resistance furnace temperature device of the k sometime through simplifying is:
The Speed Controlling Based on Improving BP Neural Network pid control algorithm that monitoring server (MMF) adopts comprises BP neural network unit, traditional PID control unit and controlled device unit, each resistance furnace temperature device is a controlled device unit, at k sometime after Speed Controlling Based on Improving BP Neural Network pid control algorithm input temp controlled quentity controlled variable r (k), obtain input e (k)=r (the k)-y (k) of BP neural network unit and traditional PID control unit, by BP neural network unit, regulated the Proportional coefficient K of conventional PID controllers
p, integration time constant K
iand derivative time constant K
d, self study by neural network, weighting coefficient adjusts, thereby makes its steady state (SS) corresponding to the PID controller parameter under certain optimum control rate, obtains desirable adaptivity and rapidity; The algorithm of BP neural network unit is according to the weighting coefficient of method of steepest descent roll-off network, gets performance scalar functions to be
press J the negative gradient direction search of weighting coefficient adjusted, adopt the method that increases momentum term to improve algorithm, have:
in formula, α is factor of momentum, η is learning rate, learning rate η is larger, pace of learning can be faster, but can cause oscillation effect when excessive, and factor of momentum α obtains excessive may causing, disperses, too small speed of convergence is too slow, in control procedure, according to the situation of change of energy function, constantly regulate the value of η and α to optimize speed of convergence, the output U (k) of traditional PID control unit is:
U(k)=U(k-1)+K
p[e(k)-e(k-1)]+K
Ie(k)+K
D[e(k)-2e(k-1)+e(k-2)]。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410407120.3A CN104155956A (en) | 2014-08-19 | 2014-08-19 | Wireless temperature remote monitoring system based on Wi-Fi |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410407120.3A CN104155956A (en) | 2014-08-19 | 2014-08-19 | Wireless temperature remote monitoring system based on Wi-Fi |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104155956A true CN104155956A (en) | 2014-11-19 |
Family
ID=51881480
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410407120.3A Pending CN104155956A (en) | 2014-08-19 | 2014-08-19 | Wireless temperature remote monitoring system based on Wi-Fi |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104155956A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104571079A (en) * | 2014-11-25 | 2015-04-29 | 东华大学 | Wireless long-distance fault diagnosis system based on multiple-sensor information fusion |
CN104616416A (en) * | 2015-01-14 | 2015-05-13 | 东华大学 | Multi-sensor information fusion-based wireless fire alarm system |
CN104914765A (en) * | 2015-06-05 | 2015-09-16 | 广东中鹏热能科技有限公司 | Handheld mobile device for ceramic tile kiln parameter debugging and control method thereof |
CN105067140A (en) * | 2015-08-04 | 2015-11-18 | 东华大学 | Wireless network based motor temperature monitoring system |
CN105807811A (en) * | 2016-03-14 | 2016-07-27 | 东华大学 | Remote greenhouse temperature control system based on WI-FI |
CN106292785A (en) * | 2015-05-18 | 2017-01-04 | 广东兴发铝业有限公司 | Aluminum-bar heating furnace ignition temperature automaton based on neutral net |
CN106325155A (en) * | 2016-08-25 | 2017-01-11 | 陕西网铸互联网信息技术有限公司 | Electric furnace remote monitoring system having autonomous learning function and electric furnace remote monitoring method thereof |
CN110032132A (en) * | 2017-12-26 | 2019-07-19 | 阿自倍尔株式会社 | Monitoring system, monitoring method and epigyny device |
CN115032891A (en) * | 2022-08-11 | 2022-09-09 | 科大智能物联技术股份有限公司 | Polycrystalline silicon reduction furnace control method based on time series prediction |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1152316A2 (en) * | 2000-05-03 | 2001-11-07 | Computer Process Controls, Inc. | Wireless method and apparatus for monitoring and controlling food temperature |
CN101141339A (en) * | 2007-02-09 | 2008-03-12 | 江苏怡丰通信设备有限公司 | Embedded SoC chip based wireless network industry monitoring management system |
CN201413471Y (en) * | 2009-05-27 | 2010-02-24 | 广东省力拓民爆器材厂 | Automatic control system of production line of expanded ammonium nitrate explosive |
CN201984323U (en) * | 2010-12-17 | 2011-09-21 | 于明 | Wireless remote multi-stage independent thermal power plant desulfurization process monitoring and management system |
CN103869703A (en) * | 2014-03-28 | 2014-06-18 | 东华大学 | Wireless monitoring system based on PID controller of internal secretion single-neuron |
-
2014
- 2014-08-19 CN CN201410407120.3A patent/CN104155956A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1152316A2 (en) * | 2000-05-03 | 2001-11-07 | Computer Process Controls, Inc. | Wireless method and apparatus for monitoring and controlling food temperature |
CN101141339A (en) * | 2007-02-09 | 2008-03-12 | 江苏怡丰通信设备有限公司 | Embedded SoC chip based wireless network industry monitoring management system |
CN201413471Y (en) * | 2009-05-27 | 2010-02-24 | 广东省力拓民爆器材厂 | Automatic control system of production line of expanded ammonium nitrate explosive |
CN201984323U (en) * | 2010-12-17 | 2011-09-21 | 于明 | Wireless remote multi-stage independent thermal power plant desulfurization process monitoring and management system |
CN103869703A (en) * | 2014-03-28 | 2014-06-18 | 东华大学 | Wireless monitoring system based on PID controller of internal secretion single-neuron |
Non-Patent Citations (1)
Title |
---|
涂川川: "基于BP神经网络PID控制的温室环境控制系统的仿真研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104571079A (en) * | 2014-11-25 | 2015-04-29 | 东华大学 | Wireless long-distance fault diagnosis system based on multiple-sensor information fusion |
CN104616416A (en) * | 2015-01-14 | 2015-05-13 | 东华大学 | Multi-sensor information fusion-based wireless fire alarm system |
CN106292785A (en) * | 2015-05-18 | 2017-01-04 | 广东兴发铝业有限公司 | Aluminum-bar heating furnace ignition temperature automaton based on neutral net |
CN104914765B (en) * | 2015-06-05 | 2018-10-16 | 广东中鹏热能科技有限公司 | A kind of handheld mobile device and its control method of ceramic tile kiln parameter testing |
CN104914765A (en) * | 2015-06-05 | 2015-09-16 | 广东中鹏热能科技有限公司 | Handheld mobile device for ceramic tile kiln parameter debugging and control method thereof |
CN105067140A (en) * | 2015-08-04 | 2015-11-18 | 东华大学 | Wireless network based motor temperature monitoring system |
CN105807811A (en) * | 2016-03-14 | 2016-07-27 | 东华大学 | Remote greenhouse temperature control system based on WI-FI |
CN106325155A (en) * | 2016-08-25 | 2017-01-11 | 陕西网铸互联网信息技术有限公司 | Electric furnace remote monitoring system having autonomous learning function and electric furnace remote monitoring method thereof |
CN106325155B (en) * | 2016-08-25 | 2018-11-23 | 陕西网铸互联网信息技术有限公司 | Electric furnace long-distance monitoring method with autonomous learning function |
CN110032132A (en) * | 2017-12-26 | 2019-07-19 | 阿自倍尔株式会社 | Monitoring system, monitoring method and epigyny device |
CN110032132B (en) * | 2017-12-26 | 2021-09-07 | 阿自倍尔株式会社 | Monitoring system, monitoring method, and host device |
CN115032891A (en) * | 2022-08-11 | 2022-09-09 | 科大智能物联技术股份有限公司 | Polycrystalline silicon reduction furnace control method based on time series prediction |
CN115032891B (en) * | 2022-08-11 | 2022-11-08 | 科大智能物联技术股份有限公司 | Polycrystalline silicon reduction furnace control method based on time series prediction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104155956A (en) | Wireless temperature remote monitoring system based on Wi-Fi | |
CN107726358B (en) | Boiler Combustion Optimization System based on CFD numerical simulations and intelligent modeling and method | |
Kong et al. | Nonlinear multivariable hierarchical model predictive control for boiler-turbine system | |
CN105538325B (en) | A kind of hydraulic pressure quadruped robot list leg joint decoupling control method | |
CN103869703A (en) | Wireless monitoring system based on PID controller of internal secretion single-neuron | |
CN109212974A (en) | The robust fuzzy of Interval time-varying delay system predicts fault tolerant control method | |
CN104154635A (en) | Variable air volume room temperature control method based on fuzzy PID and prediction control algorithm | |
CN107160398B (en) | The safe and reliable control method of Rigid Robot Manipulator is limited based on the total state for determining study | |
Dahiya et al. | Design of sampled data and event-triggered load frequency controller for isolated hybrid power system | |
CN108490790A (en) | A kind of overheating steam temperature active disturbance rejection cascade control method based on multiple-objection optimization | |
CN103064292A (en) | Biological fermentation adaptive control system and control method based on neural network inverse | |
CN105467833A (en) | A non-linear self-adaptive flight control method | |
CN105807811A (en) | Remote greenhouse temperature control system based on WI-FI | |
CN107193210A (en) | A kind of adaptive learning default capabilities control method of nonlinear system | |
CN108167802A (en) | The multi-model intelligence optimizing forecast Control Algorithm of boiler load under underload | |
Zhang et al. | Synchronization of networked harmonic oscillators with communication delays under local instantaneous interaction | |
CN108333933A (en) | A kind of single order pure delay system closed-loop identification method | |
CN110673482B (en) | Power station coal-fired boiler intelligent control method and system based on neural network prediction | |
CN108762086B (en) | Secondary reheat steam temperature control device and control system based on model predictive control | |
CN104460317A (en) | Control method for self-adaptive prediction functions in single-input and single-output chemical industry production process | |
Hamdan et al. | Analysis and challenges in wireless networked control system: A survey | |
Yan et al. | Iterative learning control in large scale HVAC system | |
Cheng et al. | An optimized nonlinear generalized predictive control for steam temperature in an ultra supercritical unit | |
CN108281972A (en) | AGC methods based on forecasting type PID controller | |
Song et al. | Projective synchronization for two nonidentical time-delayed fractional-order T–S fuzzy neural networks based on mixed H∞/passive adaptive sliding mode control |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20141119 |