CN112327627A - Nonlinear switching system self-adaptive sliding mode control method based on composite learning - Google Patents
Nonlinear switching system self-adaptive sliding mode control method based on composite learning Download PDFInfo
- Publication number
- CN112327627A CN112327627A CN202011274007.4A CN202011274007A CN112327627A CN 112327627 A CN112327627 A CN 112327627A CN 202011274007 A CN202011274007 A CN 202011274007A CN 112327627 A CN112327627 A CN 112327627A
- Authority
- CN
- China
- Prior art keywords
- sliding mode
- substances
- content
- switching system
- neural network
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention relates to a nonlinear switching system self-adaptive sliding mode control method based on composite learning, which is used for solving the technical problem of poor practicability of the existing nonlinear switching system control method. Considering the existence of external interference and input nonlinearity of a nonlinear switching system, and obtaining an input dead zone model of the switching system; respectively estimating unknown nonlinear functions and complex interference of the system by using a neural network and a switching disturbance observer, constructing a prediction error representing the learning performance based on a parallel estimation model, and adjusting the neural network weight updating law and the disturbance observer by the prediction error; designing a self-adaptive sliding die cutting controller based on a dynamic inverse technology framework and a composite learning strategy; a sliding mode time-varying gain function is constructed by utilizing the prediction error, the amplitude of the sliding mode switching buffeting is reduced, and the performance of sliding mode control is improved; the invention combines the control characteristics of a nonlinear switching system and effectively improves the control performance by designing the self-adaptive sliding mode controller based on the composite learning.
Description
Technical Field
The invention relates to a nonlinear switching system control method, in particular to a nonlinear switching system self-adaptive sliding mode control method based on composite learning, and belongs to the field of flight control.
Background
In practical engineering, many control objects such as a variant aircraft, a variable frequency motor, a robot and the like can be described by using a nonlinear switching system, so that the nonlinear switching system control technology attracts wide attention and is researched and applied in many industries such as automobiles, electric power, chemical engineering and the like.
The nonlinear switching system has strong uncertainty and is easily influenced by external interference and an input dead zone, the existing control method mostly adopts intelligent systems such as a neural network or fuzzy logic to approximate the uncertainty, and a disturbance observer is adopted to estimate the external interference. The control methods only consider the approaching effect of the intelligent system, ignore the essence of the intelligent learning strategy, do not effectively evaluate the uncertain learning performance, and have no information interaction between the intelligent approaching system and the disturbance observer, so the robustness is poor, and the engineering realization is not facilitated. Therefore, the research of the advanced control method for improving the learning performance has great significance and urgent need for the control research of the nonlinear switching system.
Disclosure of Invention
Technical problem to be solved
In order to overcome the defect that the existing nonlinear switching system control method is poor in practicability, the invention provides a nonlinear switching system self-adaptive sliding mode control method based on composite learning. According to the method, uncertainty, external interference and input nonlinearity of a nonlinear switching system are considered, and an input dead zone model is obtained through model conversion. And simultaneously, a neural network and a disturbance observer are adopted to estimate the nonlinear function and the composite interference respectively, and the learning effect is evaluated by constructing a prediction error, so that the weight adaptive updating law of the neural network and the disturbance observer are adjusted. A self-adaptive sliding mode controller is designed based on a dynamic inverse technology frame and a composite learning strategy, and a time-varying sliding mode gain function improves the robustness of the controller and facilitates engineering realization.
Technical scheme
A nonlinear switching system self-adaptive sliding mode control method based on composite learning is characterized by comprising the following steps:
step 1: single-input single-output non-linear energy control standard type switching system
Wherein the content of the first and second substances,is a system state vector; u. ofσ(t)E R is system input, y e R is system output; the function σ (t) [ [0, ∞) → M ═ 1,2, …, M } is the switching signal, and σ (t) → k indicates that the kth subsystem is active;is aboutIs determined by the unknown smoothing function of (a),is aboutAn unknown non-zero smoothing function of (a); dσ(t)(t) is external unknown interference;
step 2: describing system input nonlinearity as
can be further described as (2)
Wherein
Signal ukThere are the following relationships
the system (1) can be further written as
Wherein the content of the first and second substances,andis the optimal weight vector of the neural network,andis a vector of basis functions of the neural network, epsilonf,kAnd εG,kIs a neural network residual and existsAndandis a normal number;
Wherein the content of the first and second substances,andis the optimal weight vector estimation value of the neural network;
definition of Δ uk=uv,k-uc,kThen xnCan be written as
and 4, step 4: aiming at a nonlinear switching system (1), designing an adaptive sliding mode controller based on a composite learning strategy;
the slip form surface is designed as
s=[ΛT 1]E (11)
Wherein Λ ═ τn-1,(n-1)τn-2,…,(n-1)τ]T,τ>0;
The derivative of the slip form surface s is
the design controller is
Wherein
Wherein the content of the first and second substances,is Dk(t) estimated value, βkIs a positive design parameter, mkIs a sliding mode gain function;
construction prediction error znNNIs composed of
Wherein the content of the first and second substances,can be obtained by a parallel estimation model
designing a sliding mode gain function of
mk=-γz,kλkznNN (19)
Wherein, γz,kIs a positive design parameter;
design neural network weight update law as
Wherein, γf,k,γG,k,δf,kAnd deltaG,kIs a positive design parameter;
design a switching disturbance observer as
Wherein ξnIs an intermediate variable, LkIs a positive design parameter;
and 4, step 4: according to the control amount u obtained in step 3 (13)c,kReturning to the system model (1), the system output y is subjected to tracking control.
Advantageous effects
The invention provides a nonlinear switching system self-adaptive sliding mode control method based on composite learning. According to the method, uncertainty, external interference and input nonlinearity of a nonlinear switching system are considered, and an input dead zone model is obtained through model conversion. And simultaneously, a neural network and a disturbance observer are adopted to estimate the nonlinear function and the composite interference respectively, and the learning effect is evaluated by constructing a prediction error, so that the weight adaptive updating law of the neural network and the disturbance observer are adjusted. A self-adaptive sliding mode controller is designed based on a dynamic inverse technology frame and a composite learning strategy, and a time-varying sliding mode gain function improves the robustness of the controller and facilitates engineering realization. The beneficial effects are as follows:
(1) a prediction error is constructed based on a parallel estimation model, a neural network weight updating law is designed based on the error, the uncertainty learning precision is improved, and engineering application is facilitated;
(2) a nonlinear switching disturbance observer is designed, and effective estimation compensation is carried out on the adverse effects caused by external time-varying interference and an input unknown dead zone;
(3) based on the prediction error, an improved time-varying gain sliding mode is adopted for controller design, and buffeting during control switching is reduced;
(4) and introducing the sliding mode surface signal into the design of a neural network and a disturbance observer, and realizing effective estimation on an unknown nonlinear function and external time-varying interference through the interactive cooperation of the neural network and the disturbance observer.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will now be further described with reference to the following examples and drawings:
referring to fig. 1, the adaptive sliding mode control method of the nonlinear switching system based on the composite learning comprises the following specific steps:
step 1: consider morphing aircraft wing rock model
Wherein phi is,Androll angle, roll angle rate and roll angle acceleration, respectively, u is the control input;
the various coefficients in the model are defined as
Wherein, a1To a5Is a variable related to angle of attack, c1And c2Is a constant determined by the sweep angle;
defining a state quantity x (t) ═ x1,x2]T∈R2Wherein x is1=φ,The sweep-back angle is used as a switching signal, and the morphing aircraft wing rock model can be converted into a 2-order single-input single-output nonlinear switching system
Wherein the content of the first and second substances,is a system state vector; u. ofσ(t)E R is system input, y e R is system output; the function σ (t) e {1,2} is the switching signal;is an unknown non-linear function; d1(t)=0.1cos(t2),d2(t) ═ 0.1sin (t) is the introduced external interference;
step 2: describing system input nonlinearity as
can be further described as (2)
Wherein
Signal ukThere are the following relationships
the system (1) can be further written as
Wherein the content of the first and second substances,is the optimal weight vector of the neural network,is a vector of basis functions of the neural network, epsilonf,kIs a neural network residual and existsIs a normal number;
Wherein the content of the first and second substances,andis the optimal weight vector estimation value of the neural network;
definition of Δ uk=uv,k-uc,kThen x2Can be written as
Wherein the content of the first and second substances,and 4, step 4: aiming at a nonlinear switching system (1), designing an adaptive sliding mode controller based on a composite learning strategy;
the slip form surface is designed as
s=[ΛT 1]E (10)
Wherein Λ τ > 0;
the derivative of the slip form surface s is
the design controller is
Wherein
Wherein the content of the first and second substances,is Dk(t) estimated value, βkIs a positive design parameter, mkIs a sliding mode gain function;
construction prediction error z2NNIs composed of
Wherein the content of the first and second substances,can be obtained by a parallel estimation model
designing a sliding mode gain function of
mk=-γz,kλkz2NN (18)
Wherein, γz,kIs a positive design parameter;
design neural network weight update law as
Wherein, γf,kAnd deltaf,kIs a positive design parameter;
design a switching disturbance observer as
Wherein ξ2Is an intermediate variable, LkIs a positive design parameter;
and 4, step 4: according to the control amount u obtained in step 3 (12)c,kAnd returning to the wing rock-roll model (1) of the morphing aircraft, and performing tracking control on the roll angle phi.
The invention is not described in detail and is part of the common general knowledge of a person skilled in the art.
Claims (1)
1. A nonlinear switching system self-adaptive sliding mode control method based on composite learning is characterized by comprising the following steps:
step 1: single-input single-output non-linear energy control standard type switching system
Wherein the content of the first and second substances,is a system state vector; u. ofσ(t)E R is system input, y e R is system output; the function σ (t) [ [0, ∞) → M ═ 1,2, …, M } is the switching signal, and σ (t) → k indicates that the kth subsystem is active;is aboutIs determined by the unknown smoothing function of (a),is aboutAn unknown non-zero smoothing function of (a); dσ(t)(t) is external unknown interference;
step 2: describing system input nonlinearity as
can be further described as (2)
Wherein
Signal ukThere are the following relationships
the system (1) can be further written as
Wherein the content of the first and second substances,andis a neural networkThe optimal weight vector is a vector of weights,andis a vector of basis functions of the neural network, epsilonf,kAnd εG,kIs a neural network residual and existsAnd andis a normal number;
Wherein the content of the first and second substances,andis the optimal weight vector estimation value of the neural network;
definition of Δ uk=uv,k-uc,kThen xnCan be written as
and 4, step 4: aiming at a nonlinear switching system (1), designing an adaptive sliding mode controller based on a composite learning strategy;
the slip form surface is designed as
s=[ΛT 1]E (11)
Wherein Λ ═ τn-1,(n-1)τn-2,…,(n-1)τ]T,τ>0;
The derivative of the slip form surface s is
the design controller is
Wherein
Wherein the content of the first and second substances,is Dk(t) estimated value, βkIs a positive design parameter, mkIs a sliding mode gain function;
construction prediction error znNNIs composed of
Wherein the content of the first and second substances,can be obtained by a parallel estimation model
designing a sliding mode gain function of
mk=-γz,kλkznNN (19)
Wherein, γz,kIs a positive design parameter;
design neural network weight update law as
Wherein, γf,k,γG,k,δf,kAnd deltaG,kIs a positive design parameter;
design a switching disturbance observer as
Wherein ξnIs an intermediate variable, LkIs a positive design parameter;
and 4, step 4: according to the control amount u obtained in step 3 (13)c,kReturning to the system model (1), the system output y is subjected to tracking control.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011274007.4A CN112327627B (en) | 2020-11-14 | 2020-11-14 | Nonlinear switching system self-adaptive sliding mode control method based on composite learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011274007.4A CN112327627B (en) | 2020-11-14 | 2020-11-14 | Nonlinear switching system self-adaptive sliding mode control method based on composite learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112327627A true CN112327627A (en) | 2021-02-05 |
CN112327627B CN112327627B (en) | 2022-06-21 |
Family
ID=74319146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011274007.4A Active CN112327627B (en) | 2020-11-14 | 2020-11-14 | Nonlinear switching system self-adaptive sliding mode control method based on composite learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112327627B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112947089A (en) * | 2021-03-18 | 2021-06-11 | 西安电子科技大学 | Self-adaptive neural network tracking control method with preset tracking precision |
CN113031449A (en) * | 2021-03-29 | 2021-06-25 | 西北工业大学 | Pneumatic unknown-oriented intelligent backstepping switching control method for wide-area flight |
CN113093539A (en) * | 2021-03-29 | 2021-07-09 | 西北工业大学 | Wide-area flight robust self-adaptive switching control method based on multi-mode division |
CN113268023A (en) * | 2021-05-13 | 2021-08-17 | 哈尔滨工程大学青岛船舶科技有限公司 | Sliding mode prediction congestion control system suitable for satellite spatial information transmission network |
CN113377013A (en) * | 2021-06-10 | 2021-09-10 | 江南大学 | Continuous interference trigger control method for saturated nonlinear system |
CN113608438A (en) * | 2021-07-22 | 2021-11-05 | 浙江中烟工业有限责任公司 | Fan system and control method thereof |
CN114114925A (en) * | 2021-11-29 | 2022-03-01 | 江南大学 | Cooperative self-adaptive sliding mode constraint control method and system based on data driving |
CN114371623A (en) * | 2022-01-10 | 2022-04-19 | 南京工业大学 | Fractional order global sliding mode control method for structural thermal test neural network observer |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105867134A (en) * | 2016-04-27 | 2016-08-17 | 南京航空航天大学 | Control method for continuous switching movement of double-framework airplane skin detection robot |
CN107450323A (en) * | 2017-09-05 | 2017-12-08 | 西北工业大学 | Hypersonic aircraft reentry stage neutral net Hybrid Learning control method |
CN108828957A (en) * | 2018-08-20 | 2018-11-16 | 西北工业大学 | Aircraft overall situation finite time neural network control method based on handover mechanism |
CN109062234A (en) * | 2018-08-20 | 2018-12-21 | 西北工业大学 | A kind of non-minimum phase aircraft Hybrid Learning sliding-mode control |
CN110376887A (en) * | 2019-07-11 | 2019-10-25 | 西北工业大学 | Aircraft discrete sliding mode intelligent control method based on time-varying sliding formwork gain |
-
2020
- 2020-11-14 CN CN202011274007.4A patent/CN112327627B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105867134A (en) * | 2016-04-27 | 2016-08-17 | 南京航空航天大学 | Control method for continuous switching movement of double-framework airplane skin detection robot |
CN107450323A (en) * | 2017-09-05 | 2017-12-08 | 西北工业大学 | Hypersonic aircraft reentry stage neutral net Hybrid Learning control method |
CN108828957A (en) * | 2018-08-20 | 2018-11-16 | 西北工业大学 | Aircraft overall situation finite time neural network control method based on handover mechanism |
CN109062234A (en) * | 2018-08-20 | 2018-12-21 | 西北工业大学 | A kind of non-minimum phase aircraft Hybrid Learning sliding-mode control |
CN110376887A (en) * | 2019-07-11 | 2019-10-25 | 西北工业大学 | Aircraft discrete sliding mode intelligent control method based on time-varying sliding formwork gain |
Non-Patent Citations (2)
Title |
---|
YIXIN CHENG 等: "HOSM observer based robust adaptive hypersonic flight control using composite learning", 《NEUROCOMPUTING》 * |
王素珍 等: "一类切换非线性系统的自适应反步滑模控制", 《济南大学学报(自然科学版)》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112947089A (en) * | 2021-03-18 | 2021-06-11 | 西安电子科技大学 | Self-adaptive neural network tracking control method with preset tracking precision |
CN113031449B (en) * | 2021-03-29 | 2022-08-09 | 西北工业大学 | Pneumatic unknown-oriented intelligent backstepping switching control method for wide-area flight |
CN113031449A (en) * | 2021-03-29 | 2021-06-25 | 西北工业大学 | Pneumatic unknown-oriented intelligent backstepping switching control method for wide-area flight |
CN113093539A (en) * | 2021-03-29 | 2021-07-09 | 西北工业大学 | Wide-area flight robust self-adaptive switching control method based on multi-mode division |
CN113093539B (en) * | 2021-03-29 | 2022-08-09 | 西北工业大学 | Wide-area flight robust self-adaptive switching control method based on multi-mode division |
CN113268023A (en) * | 2021-05-13 | 2021-08-17 | 哈尔滨工程大学青岛船舶科技有限公司 | Sliding mode prediction congestion control system suitable for satellite spatial information transmission network |
CN113268023B (en) * | 2021-05-13 | 2022-07-22 | 哈尔滨工程大学青岛船舶科技有限公司 | Sliding mode prediction congestion control system suitable for satellite spatial information transmission network |
CN113377013A (en) * | 2021-06-10 | 2021-09-10 | 江南大学 | Continuous interference trigger control method for saturated nonlinear system |
CN113377013B (en) * | 2021-06-10 | 2022-10-18 | 江南大学 | Continuous interference trigger control method for saturated nonlinear system |
CN113608438A (en) * | 2021-07-22 | 2021-11-05 | 浙江中烟工业有限责任公司 | Fan system and control method thereof |
CN113608438B (en) * | 2021-07-22 | 2024-02-20 | 浙江中烟工业有限责任公司 | Fan system and control method thereof |
CN114114925A (en) * | 2021-11-29 | 2022-03-01 | 江南大学 | Cooperative self-adaptive sliding mode constraint control method and system based on data driving |
CN114114925B (en) * | 2021-11-29 | 2023-09-08 | 江南大学 | Data-driven collaborative self-adaptive sliding mode constraint control method and system |
CN114371623A (en) * | 2022-01-10 | 2022-04-19 | 南京工业大学 | Fractional order global sliding mode control method for structural thermal test neural network observer |
Also Published As
Publication number | Publication date |
---|---|
CN112327627B (en) | 2022-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112327627B (en) | Nonlinear switching system self-adaptive sliding mode control method based on composite learning | |
CN112379595B (en) | Complex interference learning control method for nonlinear strict feedback switching system | |
Sui et al. | Finite-time adaptive quantized control of stochastic nonlinear systems with input quantization: A broad learning system based identification method | |
CN113341726B (en) | Iterative learning control method for multi-quality-point vehicle queue driving system | |
CN102411305B (en) | Design method of comprehensive disturbance rejection control system for single-rotor wing helicopter/turboshaft engine | |
CN108828949A (en) | A kind of optimally in distributed mode collaboration fault tolerant control method based on adaptive Dynamic Programming | |
CN103399487A (en) | Nonlinear MIMO (multiple input multiple output) system-based decoupling control method and device | |
CN116339155B (en) | High-speed motor train unit data driving integral sliding mode control method, system and equipment | |
Guo et al. | Finite-time deterministic learning command filtered control for hypersonic flight vehicle | |
CN113805561A (en) | Spacecraft intelligent fault diagnosis method based on deep migration learning | |
CN113093538A (en) | Non-zero and game neural-optimal control method of modular robot system | |
CN113848887A (en) | Under-actuated unmanned ship trajectory tracking control method based on MLP method | |
CN106647241B (en) | Novel nonlinear PID controller | |
CN111459031A (en) | Learning-oriented disturbance observer design method | |
Zhang et al. | Decentralized adaptive output feedback dynamic surface control for stochastic nonstrict‐feedback interconnected nonlinear systems with actuator failures and input quantization via command filter | |
Yang et al. | Predictor-based neural dynamic surface control for strict-feedback nonlinear systems with unknown control gains | |
Mu et al. | Single-parameter-learning-based robust adaptive control of dynamic positioning ships considering thruster system dynamics in the input saturation state | |
CN108762065B (en) | Rigid aerospace vehicle finite time self-adaptive fault-tolerant control method based on enhanced exponential approach law and fast terminal sliding mode surface | |
CN109194244B (en) | Control method and system for electric servo system | |
Kang et al. | Adaptive neural practical fixed‐time command filtered control for multi‐input and multi‐output nonlinear systems with dead zones input and unknown control direction | |
CN104749952A (en) | Self-adaptive dynamic surface controller structure and design method thereof | |
Cheng-Du et al. | Ship dynamic positioning system based on backstepping control | |
CN114330910A (en) | Electric vehicle charging load prediction method | |
CN114637318A (en) | Sliding mode control method for hypersonic aircraft | |
CN111342477B (en) | Four-order electric power system chaotic control method for bidirectionally optimizing BP neural network sliding mode variable structure |
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 |