CN103869703A - Wireless monitoring system based on PID controller of internal secretion single-neuron - Google Patents

Wireless monitoring system based on PID controller of internal secretion single-neuron Download PDF

Info

Publication number
CN103869703A
CN103869703A CN201410120885.9A CN201410120885A CN103869703A CN 103869703 A CN103869703 A CN 103869703A CN 201410120885 A CN201410120885 A CN 201410120885A CN 103869703 A CN103869703 A CN 103869703A
Authority
CN
China
Prior art keywords
amp
control
delta
single neuron
unit
Prior art date
Application number
CN201410120885.9A
Other languages
Chinese (zh)
Inventor
周武能
孔超波
胡飞
刘娣
Original Assignee
东华大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 东华大学 filed Critical 东华大学
Priority to CN201410120885.9A priority Critical patent/CN103869703A/en
Publication of CN103869703A publication Critical patent/CN103869703A/en

Links

Abstract

The invention relates to a wireless monitoring system based on a PID controller of the internal secretion single-neuron. The operation process of the system comprises the steps that an industrial personal computer has access to an MMF module through a wireless network composed of Wi-Fi modules and the working condition of a controlled object is monitored in real time; output is adjusted and controlled by the MMF module according to the PIC control algorithm of the internal secretion single-neuron and the controlled object rapidly reaches the stable state on the premise of small overshooting. The wireless monitoring system is composed of a hardware system and a software portion implanted to the MMF module, wherein the hardware system is composed of a managing unit, a wireless transmission unit and a control unit. The managing unit is the industrial personal computer. The wireless transmission unit is used for being connected with the managing unit and the control unit and is composed of the Wi-Fi modules. The control unit is composed of a monitoring server, an analog-digital converter, a digital-analog converter, an active low-pass filter and the controlled object. The software portion is composed of a software filter and the PID control algorithm based on the internal secretion single-neuron.

Description

A kind of wireless supervisory control system based on endocrine single neuron PID controller

Technical field

The present invention relates to a kind of wireless supervisory control system based on endocrine single neuron PID controller, belong to wireless automatic control technology field.

Background technology

Current automatic control system great majority all adopt cable network to control.But cable network has poor mobility, dumb, expansibility is poor, networking and the shortcoming such as maintenance is not convenient.Along with the fast development of wireless communication technology, wireless communication and control system combines becomes the new trend of network control system development.Beyond doubt one of the most representative radio network technique nearly ten years of Wi-Fi.Wi-Fi adopts 802.11b standard, and high bandwidth is 11Mb/s, and at signal, in weak or noisy situation, bandwidth adjustable is 5.5Mb/s, 2Mb/s and 1Mb/s, and the automatic adjustment of bandwidth has ensured stability and the reliability of network effectively.

Since 20 century 70 biological intelligence control theory development, the control system based on neural network, immunity develops rapidly and reaches its maturity.But the biological intelligence control theory research based on neuroendocrine system is also fewer.The regulation and control of neuroendocrine system to various hormone in vivo, have the advantages such as good adaptivity and stability.The development on traditional control theory is produced actively impact by the Intelligent Control Theory of research based on neuroendocrine system, and contribute to improve the control quality of complex object.The neuron Proportional coefficient K of traditional single neuron PID controller is not supported online adjustment.K value is excessive, and overshoot quantitative change is large, system is unstable.K value is too small, the rapidity variation of system.

Summary of the invention

The wireless Wi-Fi sensing network supervisory system that the object of this invention is to provide a kind of Hierarchical network topological structure, realizes real time monitoring and the control of industry spot.

In order to achieve the above object, technical scheme of the present invention has been to provide a kind of wireless supervisory control system based on endocrine single neuron PID controller, it is characterized in that, comprise industrial computer, industrial computer by wireless transmission unit via the multiple supervision Control Server of wireless network access unit, the instruction that each supervision Control Server unit provides according to industrial computer has large time delay to one, non-linear, time become controlled device provide control signal, each supervision Control Server unit also monitors that the state of corresponding controlled device the monitoring data by acquisition feed back to industrial computer simultaneously, the output of control signal is controlled in each supervision Control Server unit according to endocrine Research on algorithm of single neuron adaptive PID, make the express delivery under the prerequisite of less overshoot of corresponding controlled device reach steady state (SS), wherein:

Endocrine Research on algorithm of single neuron adaptive PID comprises hypothalamus regulon, Single neuron PID control unit and ultrashort feedback unit, the command signal being provided by control machine and the feedback signal of current controlled device form input error signal e (k) and input in the lump hypothalamus regulon, Single neuron PID control unit and ultrashort feedback unit, k is sampling instant, regulated the neuron Proportional coefficient K (k) of Single neuron PID control unit by hypothalamus regulon, K (k)=K (k-1)/α (k), the regulatory factor of α (k) for obtaining by hypothalamus regulon, a, B are the adjusting parameter of hypothalamus regulon, output f (Δ u (k), e (k)) by ultrashort feedback unit compensates the output of Single neuron PID control unit, f ( Δu ( k ) , e ( k ) ) = β ( | Δu | ( k ) m λ + | Δu ( k ) | m ) · Δu ( k ) | Δuk | · Δe ( k ) | Δe ( k ) | · Δe ( k ) | Δe ( k ) | , The adjusting parameter that β, λ, m are arithmetic number, Δu ( k ) = u ( k ) - u ( k - 1 ) = K ( k ) Σ i = 1 3 ω i ( k ) Σ i = 1 3 | ω i ( k ) | x i ( k ) , Wherein:

X 1(k) do for input error signal e (k) signal obtaining after scale operation;

ω 1(k)=ω 1(k-1)+η pe (k) u (k) [e (k)-Δ e (k)], Δ e (k)=e (k)-e (k-1), η pfor ratio learning rate;

X 2(k) do for input error signal e (k) signal obtaining after integral operation;

ω 2(k)=ω 2(k-1)+η 1e (k) u (k) [e (k)-Δ e (k)], η ifor integration learning rate;

X 3(k) be the signal obtaining after input error signal e (k) differentiates;

ω 3(k)=ω 3(k-1)+η de (k) u (k) [e (k)-Δ e (k)], η nfor differential learning rate;

After f (Δ u (k), e (k)) compensation, be output as control signal U (k), U ( k ) = U ( k - 1 ) + K ( k ) Σ i = 1 3 ω i ( k ) Σ i = 1 3 | ω i ( k ) | x i ( k ) - f ( ΔU ( k ) , e ( k ) ) , Control signal U (k) inputs to current controlled device on the one hand, feeds back on the other hand ultrashort feedback unit.

Preferably, described wireless transmission unit comprises admin site, receiving node, control website, relay reception node, relay, admin site is connected with described industrial computer, admin site and receiving node are set up radio communication, receiving node and relay are set up radio communication, relay reception node connects relay, and each described supervision Control Server unit connects one and controls website, and all control websites and relay reception node are set up radio communication.

Preferably, described supervision Control Server unit comprises monitoring server, analog to digital converter, digital to analog converter and for filtering out the active low-pass filter of industry spot undesired signal, digital to analog converter and active low-pass filter connect corresponding controlled device, digital to analog converter directly connects monitoring server, monitoring server connects active low-pass filter by analog to digital converter, monitoring server is on the one hand for receiving the data from analog to digital converter, produce described control signal U (k) via controlled device described in analog to digital converter and active low-pass filter control according to described endocrine Research on algorithm of single neuron adaptive PID on the other hand.

Preferably, carrying out first adopting moving average filter algorithm and limit filtration algorithm before described endocrine Research on algorithm of single neuron adaptive PID.

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 present invention combines Neuroendocrine regulation principle with Research on algorithm of single neuron adaptive PID.The Proportional coefficient K of hypothalamus regulon on-line tuning Single neuron PID control unit; Ultrashort feedback unit produces feedback compensation effect to controller self output signal, thereby has improved the control effect of system.

Brief description of the drawings

Fig. 1 is supervisory system structural representation;

Fig. 2 is endocrine single neuron PID controller structural drawing;

Fig. 3 is single neuron PID controller structural drawing;

Fig. 4 is liquid level control design sketch;

Fig. 5 is temperature control effect figure.

Embodiment

For the present invention is become apparent, hereby with preferred embodiment, and coordinate accompanying drawing to be described in detail below.

The invention discloses 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, system of the present invention has adopted a kind of based on neuroendocrine Research on algorithm of single neuron adaptive PID, the dynamic and steady-state characteristic of Optimal Control System.

As described in Figure 1, a kind of wireless supervisory control system based on endocrine single neuron PID controller provided by the invention, comprises industrial computer, and industrial computer is stable performance, the technical grade PC that processing speed is fast.Industrial computer by wireless transmission unit via the multiple supervision Control Server of wireless network access unit, the instruction that each supervision Control Server unit provides according to industrial computer has large time delay to one, non-linear, time become controlled device provide control signal, each supervision Control Server unit also monitors that the state of corresponding controlled device the monitoring data by acquisition feed back to industrial computer simultaneously, the output of control signal is controlled in each supervision Control Server unit according to endocrine Research on algorithm of single neuron adaptive PID, make the express delivery under the prerequisite of less overshoot of corresponding controlled device reach steady state (SS).

Wireless transmission unit comprises admin site MST, receiving node AP, controls website CST, relay reception node R AP, relay RST, and admin site MST is connected with industrial computer, and the connected mode of admin site MST and industrial computer is wired connection.Admin site MST and receiving node AP set up radio communication, receiving node AP and relay RST set up radio communication, relay reception node R AP connects relay RST, each supervision Control Server unit connects one and controls website CST, and all control website CST and relay reception node R AP set up radio communication.

Monitor that Control Server unit comprises monitoring server MMF, analog to digital converter ADI, digital to analog converter DAI and for filtering out the active low-pass filter LPF of industry spot undesired signal.The mode of industrial computer access monitoring server MMF is for inputting the access of corresponding IP address by webpage.Digital to analog converter DAI and active low-pass filter LPF connect corresponding controlled device, digital to analog converter DAI directly connects monitoring server MMF, monitoring server MMF connects active low-pass filter LPF by analog to digital converter ADI, monitoring server MMF is on the one hand for receiving the data from analog to digital converter ADI, produce control signal U (k) according to described endocrine Research on algorithm of single neuron adaptive PID on the other hand, k is sampling instant warp, controls described controlled device by analog to digital converter ADI and active low-pass filter LPF.In the present embodiment, monitoring server MMF, analog to digital converter ADI and digital to analog converter DAI are integrated in a device, and are directly connected by wired mode with active low-pass filter LPF.

Endocrine Research on algorithm of single neuron adaptive PID comprises hypothalamus regulon, Single neuron PID control unit and ultrashort feedback unit, its structure as shown in Figure 2, hypothalamus regulon is mainly used to regulate the neuron Proportional coefficient K of Single neuron PID control unit, thereby improves adaptivity and the rapidity of system.Ultrashort feedback unit directly acts on controlled device, for compensating the output of Single neuron PID control unit, thus the stability of Hoisting System.

The algorithm of hypothalamus regulon adopts neuro-endocrinology hormone to regulate rule.Regulate algorithm to regulate the neuron Proportional coefficient K (k) of Single neuron PID control unit according to the variation of error originated from input e (k).Regulatory factor α (k) adopts the universal law of hormone secretion:

α ( k ) = | e ( k ) | A + | e ( k ) | + B , Wherein, A, B are for regulating parameter.

Have: K (k)=K (k-1)/α (k).

The algorithm of Single neuron PID control unit have the parameter of adjustment few, be easy to the features such as field adjustable, can improve significantly the dynamic quality of nonlinear time-varying object, time-varying characteristics that can the procedure of adaptation, Guarantee control system moves in the best condition, specific algorithm can list of references: sun is handsome, Ren Jinxia. a kind of improved single neuron PID controller [J]. and automated manufacturing, 2010,32 (11): 119-121, its structure as shown in Figure 3.The renewal of weights is adopted to improved Hebb learning rules, and the learning algorithm after specification arranges is:

X 1(k) do for input error signal e (k) signal obtaining after scale operation;

ω 1(k)=ω 1(k-1)+η pe (k) u (k) [e (k)-Δ e (k)], Δ e (k)=e (k)-e (k-1), η pfor ratio learning rate;

X 2(k) do for input error signal e (k) signal obtaining after integral operation;

ω 2(k)=ω 2(k-1)+η le (k) u (k) [e (k)-Δ e (k)], η ifor integration learning rate;

X 3(k) be the signal obtaining after input error signal e (k) differentiates;

ω 3(k)=ω 3(k-1)+η de (k) u (k) [e (k)-Δ e (k)], η dfor differential learning rate;

u ( k ) = u ( k - 1 ) + K ( k ) Σ i = 1 3 ω i ( k ) Σ i = 1 3 | ω i ( k ) | x i ( k ) .

The algorithm of ultrashort feedback unit is according to neuro-endocrinology hormone regulation mechanism, and the rate of change using the output signal of controller self within the sampling period, as feedback signal, adopts the design of rising Hill function principle.It examines output f (Δ u (k), e (k)):

f ( Δu ( k ) , e ( k ) ) = β ( | Δu | ( k ) m λ + | Δu ( k ) | m ) · Δu ( k ) | Δuk | · Δe ( k ) | Δe ( k ) | · Δe ( k ) | Δe ( k ) | , The adjusting parameter that β, λ, m are arithmetic number, Δ u (k)=u (k)-u (k-1).

After f (Δ u (k), e (k)) compensation, be output as control signal U (k), U ( k ) = U ( k - 1 ) + K ( k ) Σ i = 1 3 ω i ( k ) Σ i = 1 3 | ω i ( k ) | x i ( k ) - f ( ΔU ( k ) , e ( k ) ) .

Below choose three rank liquid level objects and a pure temperature hysteresis object of second order, carry out emulation.For the ease of compared with control effect, described single neuron PID controller is got to identical value with parameter total in described endocrine single neuron PID controller.In order to verify the stable control ability of described endocrine single neuron PID controller, in the time of 300s, 750s and 900s, change respectively technique set-point.In addition, in order to verify the antijamming capability of described endocrine single neuron PID controller, controlled device is added the shock response of moment in the time of 500s.

Liquid level target transfer function is:

G ( s ) = 3 s 3 + 4 s 2 + 3 s + 1

For liquid level object, the control parameter value of emulation experiment is as follows: η p, η i, η dbe respectively 0.2,4,0.4; K (0) is 0.07; ω 1(0), ω 2(0), ω 3(0) be respectively 0.2,0.2,0.03; β, λ, m is respectively 2,0.8, and 2; A is that 0.4, B is 0.2.Sampling period is elected 2s as.In order to check the adaptive faculty of the described wireless supervisory control system based on endocrine single neuron PID controller, the parameter that changes controlled device in the time of 1100s is:

G ( s ) = 4 s 3 + 6 s 2 + 3 s + 1

When 1300s, recover its raw parameter value, control effect as shown in Figure 4.In Fig. 4, SN-PID refers to described single neuron PID, and ESN-PID refers to described endocrine single neuron PID.As can be seen from Figure 4, with respect to traditional single neuron PID controller, ESN-PIDC can reach faster target level value under the prerequisite that does not produce overshoot; After adding momentary pulse response, can tend to be steady more fast; Changing after object parameters, there is good robustness.

Temperature object transport function is:

G ( s ) = e - 10 s ( 12 s + 1 ) ( 15 + 1 )

For temperature object, the control parameter value of emulation experiment is as follows: η p, η I, η dbe respectively 0.4,4,0.4; K (0) is 0.4; ω 1(0), ω 2(0), ω 3(0) be respectively 0.2,0.2,0.03; β, λ, m is respectively 1.5,1, and 2; A is that 0.3, B is 0.3.Sampling period is elected 5s as.In order to check the adaptive faculty of ESN-PIDC, the parameter that changes controlled device in the time of 1100s is:

G ( s ) = 1.5 e - 10 s ( 14 s + 1 ) ( 15 s + 1 )

When 1300s, recover its raw parameter value, control effect as shown in Figure 5.In Fig. 5, SN-PID refers to described single neuron PID, and ESN-PID refers to described endocrine single neuron PID.As can be seen from Figure 5, with respect to traditional single neuron PID controller, ESN-PIDC can reach faster target temperature value under the prerequisite that does not produce overshoot; After adding momentary pulse response, can tend to be steady more fast; Changing after object parameters, there is good robustness.

Claims (4)

1. the wireless supervisory control system based on endocrine single neuron PID controller, it is characterized in that, comprise industrial computer, industrial computer by wireless transmission unit via the multiple supervision Control Server of wireless network access unit, the instruction that each supervision Control Server unit provides according to industrial computer has large time delay to one, non-linear, time become controlled device provide control signal, each supervision Control Server unit also monitors that the state of corresponding controlled device the monitoring data by acquisition feed back to industrial computer simultaneously, the output of control signal is controlled in each supervision Control Server unit according to endocrine Research on algorithm of single neuron adaptive PID, make the express delivery under the prerequisite of less overshoot of corresponding controlled device reach steady state (SS), wherein:
Endocrine Research on algorithm of single neuron adaptive PID comprises hypothalamus regulon, Single neuron PID control unit and ultrashort feedback unit, the command signal being provided by control machine and the feedback signal of current controlled device form input error signal e (k) and input in the lump hypothalamus regulon, Single neuron PID control unit and ultrashort feedback unit, k is sampling instant, regulated the neuron Proportional coefficient K (k) of Single neuron PID control unit by hypothalamus regulon, K (k)=K (k-1)/α (k), the regulatory factor of α (k) for obtaining by hypothalamus regulon, a, B are the adjusting parameter of hypothalamus regulon, output f (Δ u (k), e (k)) by ultrashort feedback unit compensates the output of Single neuron PID control unit, f ( Δu ( k ) , e ( k ) ) = β ( | Δu | ( k ) m λ + | Δu ( k ) | m ) · Δu ( k ) | Δuk | · Δe ( k ) | Δe ( k ) | · Δe ( k ) | Δe ( k ) | , The adjusting parameter that β, λ, m are arithmetic number, Δu ( k ) = u ( k ) - u ( k - 1 ) = K ( k ) Σ i = 1 3 ω i ( k ) Σ i = 1 3 | ω i ( k ) | x i ( k ) , Wherein:
X 1(k) do for input error signal e (k) signal obtaining after scale operation;
ω 1(k)=ω 1(k-1)+η pe (k) u (k) [e (k)-Δ e (k)], Δ e (k)=e (k)-e (k-1), η pfor ratio learning rate;
X 2(k) do for input error signal e (k) signal obtaining after integral operation;
ω 2(k)=ω 2(k-1)+η ie (k) u (k) [e (k)-Δ e (k)], η ifor integration learning rate;
X 3(k) be the signal obtaining after input error signal e (k) differentiates;
ω 3(k)=ω 3(k-1)+η de (k) u (k) [e (k)-Δ e (k)], η dfor differential learning rate;
After f (Δ u (k), e (k)) compensation, be output as control signal U (k), U ( k ) = U ( k - 1 ) + K ( k ) Σ i = 1 3 ω i ( k ) Σ i = 1 3 | ω i ( k ) | x i ( k ) - f ( ΔU ( k ) , e ( k ) ) , Control signal U (k) inputs to current controlled device on the one hand, feeds back on the other hand ultrashort feedback unit.
2. a kind of wireless supervisory control system based on endocrine single neuron PID controller as claimed in claim 1, it is characterized in that, described wireless transmission unit comprises admin site (MST), receiving node (AP), control website (CST), relay reception node (RAP), relay (RST), admin site (MST) is connected with described industrial computer, admin site (MST) is set up radio communication with receiving node (AP), receiving node (AP) is set up radio communication with relay (RST), relay reception node (RAP) connects relay (RST), each described supervision Control Server unit connects one and controls website (CST), all control websites (CST) are set up radio communication with relay reception node (RAP).
3. a kind of wireless supervisory control system based on endocrine single neuron PID controller as claimed in claim 1, it is characterized in that, described supervision Control Server unit comprises monitoring server (MMF), analog to digital converter (ADI), digital to analog converter (DAI) and for filtering out the active low-pass filter (LPF) of industry spot undesired signal, digital to analog converter (DAI) and active low-pass filter (LPF) connect corresponding controlled device, digital to analog converter (DAI) directly connects monitoring server (MMF), monitoring server (MMF) connects active low-pass filter (LPF) by analog to digital converter (ADI), monitoring server (MMF) is on the one hand for receiving the data from analog to digital converter (ADI), produce described control signal U (k) according to described endocrine Research on algorithm of single neuron adaptive PID on the other hand and control described controlled device via analog to digital converter (ADI) and active low-pass filter (LPF).
4. a kind of wireless supervisory control system based on endocrine single neuron PID controller as claimed in claim 1, is characterized in that, carrying out first adopting moving average filter algorithm and limit filtration algorithm before described endocrine Research on algorithm of single neuron adaptive PID.
CN201410120885.9A 2014-03-28 2014-03-28 Wireless monitoring system based on PID controller of internal secretion single-neuron CN103869703A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410120885.9A CN103869703A (en) 2014-03-28 2014-03-28 Wireless monitoring system based on PID controller of internal secretion single-neuron

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410120885.9A CN103869703A (en) 2014-03-28 2014-03-28 Wireless monitoring system based on PID controller of internal secretion single-neuron

Publications (1)

Publication Number Publication Date
CN103869703A true CN103869703A (en) 2014-06-18

Family

ID=50908352

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410120885.9A CN103869703A (en) 2014-03-28 2014-03-28 Wireless monitoring system based on PID controller of internal secretion single-neuron

Country Status (1)

Country Link
CN (1) CN103869703A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104155956A (en) * 2014-08-19 2014-11-19 东华大学 Wireless temperature remote monitoring system based on Wi-Fi
CN104199477A (en) * 2014-08-27 2014-12-10 东华大学 Remote industrial pH process monitoring system based on WI-FI
CN104331085A (en) * 2014-11-03 2015-02-04 东华大学 Unmanned aerial vehicle control method based on PID (Proportion Integration Differentiation) neural network
CN104503226A (en) * 2014-11-06 2015-04-08 东华大学 Wireless Wi-Fi remote monitoring system based on multi-sensor information fusion in fermentation chamber environment
CN104571079A (en) * 2014-11-25 2015-04-29 东华大学 Wireless long-distance fault diagnosis system based on multiple-sensor information fusion
CN105067140A (en) * 2015-08-04 2015-11-18 东华大学 Wireless network based motor temperature monitoring system
CN106899034A (en) * 2017-03-10 2017-06-27 国网江苏省电力公司常州供电公司 Grid-connected distribution network voltage falls compensating control method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5805602A (en) * 1995-09-25 1998-09-08 Bell Atlantic Network Services, Inc. Network monitoring system for cell delay variation
CN101467113A (en) * 2006-04-12 2009-06-24 霍尼韦尔国际公司 System and method for monitoring valve status and performance in a process control system
CN102830681A (en) * 2012-06-21 2012-12-19 上海擎云物联网有限公司 Remote electric energy consumption data monitoring method and matching device thereof
GB2494416A (en) * 2011-09-07 2013-03-13 Rolls Royce Plc Asset Condition Monitoring Using Internal Signals Of The Controller
CN203232326U (en) * 2013-02-21 2013-10-09 东华大学 WIFI-based wireless distributed liquid level control system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5805602A (en) * 1995-09-25 1998-09-08 Bell Atlantic Network Services, Inc. Network monitoring system for cell delay variation
CN101467113A (en) * 2006-04-12 2009-06-24 霍尼韦尔国际公司 System and method for monitoring valve status and performance in a process control system
GB2494416A (en) * 2011-09-07 2013-03-13 Rolls Royce Plc Asset Condition Monitoring Using Internal Signals Of The Controller
CN102830681A (en) * 2012-06-21 2012-12-19 上海擎云物联网有限公司 Remote electric energy consumption data monitoring method and matching device thereof
CN203232326U (en) * 2013-02-21 2013-10-09 东华大学 WIFI-based wireless distributed liquid level control system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
罗兵 等: "《智能控制技术》", 31 March 2011, 清华大学出版社 *
郭崇滨 等: "基于神经内分泌的并联机器人智能控制系统", 《机电工程》 *
阳帅 等: "一种改进的单神经元PID控制器", 《制造业自动化》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104155956A (en) * 2014-08-19 2014-11-19 东华大学 Wireless temperature remote monitoring system based on Wi-Fi
CN104199477A (en) * 2014-08-27 2014-12-10 东华大学 Remote industrial pH process monitoring system based on WI-FI
CN104331085A (en) * 2014-11-03 2015-02-04 东华大学 Unmanned aerial vehicle control method based on PID (Proportion Integration Differentiation) neural network
CN104503226A (en) * 2014-11-06 2015-04-08 东华大学 Wireless Wi-Fi remote monitoring system based on multi-sensor information fusion in fermentation chamber environment
CN104571079A (en) * 2014-11-25 2015-04-29 东华大学 Wireless long-distance fault diagnosis system based on multiple-sensor information fusion
CN105067140A (en) * 2015-08-04 2015-11-18 东华大学 Wireless network based motor temperature monitoring system
CN106899034A (en) * 2017-03-10 2017-06-27 国网江苏省电力公司常州供电公司 Grid-connected distribution network voltage falls compensating control method

Similar Documents

Publication Publication Date Title
CN103455843B (en) A kind of feedback-type artificial neural network training method and computing system
Yu et al. Distributed control gains design for consensus in multi-agent systems with second-order nonlinear dynamics
Mao et al. Fault-tolerant control for a class of nonlinear sampled-data systems via a Euler approximate observer
Shaker et al. Active sensor fault tolerant output feedback tracking control for wind turbine systems via T–S model
CN101772641B (en) A wind turbine, a method for compensating for disparities in a wind turbine rotor blade pitch system and use of a method
Liang et al. Short-term wind power combined forecasting based on error forecast correction
Ding et al. Network-based leader-following consensus for distributed multi-agent systems
CN103853046B (en) A kind of Adaptive-learning control method of piezoelectric ceramic actuator
Sambariya et al. Robust tuning of power system stabilizer for small signal stability enhancement using metaheuristic bat algorithm
Yang et al. Multirate control in internet-based control systems
CN101761917B (en) Boiler overheating steam temperature fuzzy control method
CN102621889B (en) Composite control method for piezoelectric ceramic positioning
Yu et al. Fault-tolerant control with linear quadratic and model predictive control techniques against actuator faults in a quadrotor UAV
CN102629104A (en) Calcination predictive control system and method for rotary cement kiln
Meng et al. Event detection and control co-design of sampled-data systems
Ruß et al. Data mining with neural networks for wheat yield prediction
CN103810497A (en) Memristor based image identification system and method
Liu et al. H∞ control for network-based systems with time-varying delay and packet disordering
CN105904461B (en) A kind of adaptive remote operating control method of neutral net based on RBF
CN101710245B (en) PID control based self-focusing lens ion exchange temperature control method and device
CN105805822B (en) Heating energy-saving control method based on neural network prediction and system
Jiao et al. Distributed L2-gain output-feedback control of homogeneous and heterogeneous systems
CN102868336B (en) Three-motor synchronous control system based on fuzzy second-order active disturbance rejection controller
CN104089270B (en) A kind of generating set boiler load control and optimize Adjustment Tests method
CN104950948A (en) Intelligent cowshed temperature control system

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20140618

C02 Deemed withdrawal of patent application after publication (patent law 2001)