CN112987741A - Uncertain interference-oriented ship course intelligent control method - Google Patents
Uncertain interference-oriented ship course intelligent control method Download PDFInfo
- Publication number
- CN112987741A CN112987741A CN202110228467.1A CN202110228467A CN112987741A CN 112987741 A CN112987741 A CN 112987741A CN 202110228467 A CN202110228467 A CN 202110228467A CN 112987741 A CN112987741 A CN 112987741A
- Authority
- CN
- China
- Prior art keywords
- ship
- output
- fuzzy set
- heading
- course
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000007246 mechanism Effects 0.000 claims abstract description 7
- 239000003638 chemical reducing agent Substances 0.000 claims abstract description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 24
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
Abstract
The invention provides an uncertain interference-oriented intelligent control method for ship course, which comprises the following steps: designing an input fuzzy set of course deviation according to the influence factors of the target navigation environment of the ship navigation; designing a rule base in an inference machine according to an actual navigation mechanism; obtaining a matched output fuzzy set based on the input fuzzy set and the rule base; executing a type reducer operation to obtain output of matched upper and lower bounds; and executing output defuzzification operation so as to obtain matched control information. The invention determines an input fuzzy set according to the ship control characteristics, constructs an inference engine by using a language mechanism, thereby realizing two-type fuzzy control, takes the current state (namely course deviation) of the ship obtained by observation as input, outputs a matched course control instruction and acts on a control system, thereby achieving the purpose of effectively controlling the course of the ship.
Description
Technical Field
The invention belongs to the technical field of intelligent motion control (including path tracking, trajectory tracking and the like) of ships and particularly relates to an uncertain interference-oriented ship course intelligent control method.
Background
Currently, a new technological revolution and an industry revolution are accelerated worldwide by artificial intelligence, and in particular, people pay great attention to the proposal and development of an optimization method based on a natural paradigm. Course control is an important research topic in the field of ship control in order to ensure the safety, maneuverability and economy of ships sailing at sea. Common methods for control mainly include PID control, robust control, adaptive control, variable structure control, and back-stepping control.
However, it has been found through analysis that the methods of the prior art control have at least the following technical problems: as known from the existing relevant research and analysis, aiming at the ship motion control problem with strong nonlinearity and high coupling, the commonly adopted solving means is a nonlinear control method. Many nonlinear control methods are based on a state feedback method, but in practice, a ship course control system can only measure a course angle, a state observer is required to be introduced to obtain course angle rate information required by a controller when the state feedback control method is applied, and meanwhile, uncertain interference caused by measurement noise, time-varying multi-environment factor interference and the like inevitably exists in measurement information used for estimating states or interference by the observer, so that the design and implementation difficulty of the control system is increased. Obviously, a ship course control method with strong robustness aiming at uncertain interference control is needed to be designed.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent motion control method facing uncertainty interference, which carries out intelligent motion control based on type-2FLS (Fuzzy-Logic-System), comprehensively considers the characteristics of ship control characteristics and planning area environment interference, introduces the concept of uncertainty interval (FOU) to redundantly consider the influence of environment on control, and can enable a ship to better adapt to the current navigation environment to carry out accurate control.
In order to solve the technical problems, the invention adopts the following technical scheme:
an uncertain interference-oriented ship course intelligent control method comprises the following steps:
step S1, designing an input fuzzy set of course deviation according to the influence factors of the target navigation environment of the ship navigation;
step S2, designing a rule base in the inference engine according to the actual navigation mechanism;
step S3, obtaining a matched output fuzzy set based on the input fuzzy set and the rule base;
step S4, executing a type reducer operation to obtain output of matched upper and lower bounds according to the input fuzzy set and the corresponding output fuzzy set by utilizing KM type-reduction;
and step S5, executing output defuzzification operation on the output of the upper and lower boundaries obtained in the step S4, and thus obtaining the matched control information for controlling the heading of the ship.
Further, in the step S1, an input fuzzy set of the heading deviation is designed by using the two-type fuzzy set, and a gaussian function is used as the membership function, and the input fuzzy set region is defined by an upper member function and a lower member function, so as to limit the influence factor of the target navigation environment between the upper gaussian function and the lower gaussian function.
Further, in the step S2, e is adopted as the heading error, and is expressed as: e-psi0Wherein ψ0For the expected heading, ψ is the actual heading, then the rule base designed is:
if e is positive, indicating that the heading is larger than the expected heading, and controlling the ship to steer to the right when the ship deflects to the left;
if e is negative, indicating that the heading is less than the expected heading, the ship deflects to the right and needs to be controlled to steer to the left,
wherein the heading is positive to the left and negative to the right.
Further, in step S3, the output corresponding to the ith rule obtained from the inference engine in step S2 is represented as:
further, in the present invention,output fuzzy sets
Determined by the following expression:
further, in the step S4, an upper limit and a lower limit are set for the output of each rule, and the output upper limit and the output lower limit corresponding to the ith rule are respectively expressed as:
upper limit of
Lower limit of
Further, in the step S5, the output defuzzification operation is implemented by averaging the upper limit and the lower limit of the output corresponding to each rule.
Compared with the prior art, the invention has the beneficial effects that:
the invention determines an input fuzzy set based on the consideration of ship manipulation characteristics (turning performance), constructs an inference engine suitable for a target navigation environment by using a language mechanism, thereby realizing the establishment of a suitable two-type fuzzy control process, takes the current state of a ship (namely, the course deviation between the actual course and the expected course) obtained by observation as input, takes the course obtained after the control process as output, and controls the instruction and acts on a control system by the course, thereby achieving the purpose of controlling the course or the speed of the ship.
Drawings
FIG. 1 is a flowchart of an intelligent ship course control method for uncertain disturbance in the embodiment of the invention.
FIG. 2 is a diagram of a two-interval blur set for blur area FOU in an embodiment of the present invention.
FIG. 3 is a FIS (Fuzzy-Interval-system) diagram of the input Fuzzy function set according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating the result of t-norm operation in the inference engine according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating the result of calculating the switch point in performing the type reduction process according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of output results of upper and lower bounds obtained by using a KM type reducer (type-reduction) in an embodiment of the present invention.
FIG. 7 is a block diagram of a ship heading control system according to an embodiment of the invention.
Detailed Description
The invention will be further described with reference to examples of embodiments shown in the drawings.
As shown in fig. 1, the embodiment discloses an intelligent control method for ship course facing uncertain disturbance, which is used for keeping control over the course of ship navigation so as to keep the course of a ship consistent with an expected course. The control method comprises the following steps:
and step S1, designing an input fuzzy set of course deviation according to the influence factors of the target navigation environment of the ship navigation.
In step S1, an input fuzzy set of the heading deviation is designed using the two-type fuzzy set, and a gaussian function is used as the membership function, and the input fuzzy set region is defined by an upper membership function and a lower membership function, thereby limiting the influence factors of the target navigation environment between the upper and lower gaussian functions.
Here, the handling capacity of the control method for uncertain disturbances is improved by using a two-type fuzzy system. The specific principle and process are as follows:
the Type-two Fuzzy System Type-2 FS (Fuzzy-System) is used as an extension of the Type-1 FS of the Type-one Fuzzy System, and different from the Type-one Fuzzy set, the membership degree of the Type-two Fuzzy set is characterized by the Fuzzy set, so that the processing capacity for the uncertainty in the System can be improved. Because the range of the membership degree in the original one-type fuzzy set is designed according to experience, different people have different understandings on different linguistic variables, the finally designed fuzzy system can be completely different, and the membership degree of the one-type fuzzy set is also set as the fuzzy set in the two-type fuzzy set, so that the uncertainty of different people on the design of the fuzzy system is contained to a great extent, the processing capability of the fuzzy system on the uncertainty and the nonlinearity is greatly enhanced, and the advantages of the two-type fuzzy system relative to the one-type fuzzy system are also reflected on the nonlinear system with high uncertainty.
Type-1 FS introduces a degree of ambiguity in order to create a language partition of a clear domain. Nevertheless, the MF (member functions) used for this operation are clear in themselves, since they are fully defined, without considering any uncertainty of its parameters. Type-2 FS overcomes this limitation by defining a second degree of ambiguity. In this case, in the [0, 1] domain, the membership value itself of each input of FS is defined as FS. To better understand this new dimension, assume a process of defining the concept as Type-1 FS by polling a set of experts. After all responses have been collected, it will of course be noted that the endpoints of the membership functions will vary from person to person. The union of all embedded Type-1 FS will eventually end up in a fuzzy area (called FOU) bounded by the two on-MF member functions Upper Membership Function (UMF) and Lower Membership Function (LMF)). In addition, each membership function given by a person may be assigned a variable weight based on the confidence level associated with its opinion, thereby defining a second ambiguity. Thus, the Type-2 FS representation embeds an extra degree of freedom that can better handle uncertainties caused by noisy data and environmental changes.
Fig. 2(a) shows a FOU with two types of blur sets, which contains multiple embedded blur sets, and fig. 2(b) shows a vertical slice through the FOU, showing the variable secondary membership value for each embedded blur set.
Based on this, the two-type fuzzy set can be broadly expressed as:
where g (x) is one of the primary membership functions, x is the FS input value, and u is the primary membership.
In practical application, as shown in fig. 3, according to the gyrating experiment of the unmanned ship and the motion characteristics thereof, the area of the fuzzy set is set to be [ -5,5], a gaussian function is adopted as a membership function, and the influence of the environment is considered between an upper gaussian function and a lower gaussian function.
And step S2, designing a rule base in the inference engine according to the actual navigation mechanism.
In step S2, as a natural extension of the Type-1 FLS, the Type-2FLS also synthesizes Rule Base in a set of If-Then rules, thereby establishing a relationship between system inputs and outputs. The process of rule creation is the same regardless of the nature of the fuzzy set. Thus, the type 2FLS rule is expressed as follows:
wherein R isiRepresents the ith rule and F and G represent linguistic terms with interval type 2FS, x being the rule input, in the present invention the heading angle of the vessel, y being the output, in the present invention the steering and speed of the steering engine.
In addition, one major difference between type one and type two ambiguities is that the inference engine, in type one, gets a distinct value through the rule base, and in type two, gets a range, as follows:
the t-norm operation is generally used, and the result is shown in FIG. 4.
In course-keeping control of a ship, the disturbance is generallyInterference from wave flows in the environment, particularly east lake, is small, so that a simple rule is established. The method specifically comprises the following steps: using e as the heading error and expressed as: e-psi0Wherein ψ0Psi is the actual heading for the desired heading. The deviation e can be practically divided into three fuzzy sets: mf1U (negative large) mf2U (zero) mf3U (positive large), which is classified into five grades of-5, -2.5, 0, 2.5, and 5 according to the variation range of e.
In this case, the rule base of the corresponding design may be:
if e is positive, indicating that the heading is larger than the expected heading, and controlling the ship to steer to the right when the ship deflects to the left;
if e is negative, indicating that the heading is less than the expected heading, the ship deflects to the right and needs to be controlled to steer to the left,
wherein the heading is positive to the left and negative to the right.
And step S3, obtaining a matched output fuzzy set based on the input fuzzy set and the rule base.
In step S3, the output corresponding to the ith rule is obtained from the inference engine in step S2 as:
further, a fuzzy set is output
Determined by the following expression:
and step S4, executing a Type reducer operation to obtain matched upper and lower bounds output according to the input fuzzy set and the corresponding output fuzzy set by using the KM Type-reduction so as to solve the additional degree of freedom provided by the Type-2 FS.
In order to develop a practical application based on the Type-two fuzzy system Type-2 FS, it is necessary to obtain a clear value from a combination of member functions FS of all conversion points. To achieve this goal, the centroid of Type-2 FS must be obtained, which is expressed as an interval commonly referred to as a reduced set of types. The Karnik-Mendel (KM) algorithm can be viewed as an extension of the Type-1 defuzzification process, and is currently the most accurate TR method. Although iterative in nature, IT is the most complex stage in the Fuzzy inference process, requiring a large number of calculations even with the simpler IT2FS (Interval-Type 2-Fuzzy-System).
Similar to the centroid defuzzification process, centroid TR begins by taking K samples from Type-2 FS. Since a FOU of type 2FS embeds multiple type 1FS, to perform TR, first two type 1FS must be obtained, whose centroids are closest to the upper and lower boundaries of the type 2FS centroid. For example, considering the FS of the G output, the process first starts with its upper and lower sampling limits to find the optimum value of the switching point [ L, R ], as shown in FIGS. 5(a) and 5 (b).
In step S4, an upper limit and a lower limit are set for the output of each rule, and the output upper limit and the output lower limit corresponding to the ith rule are respectively expressed as:
upper limit of
Lower limit of
As shown in fig. 6(a) and 6(b), the lower and upper bound outputs for each system rule, respectively, are arranged in ascending order.
And step S5, executing output defuzzification operation on the output of the upper and lower boundaries obtained in step S4, and thus obtaining the matched control information for controlling the heading of the ship.
In step S5, after applying one type of reduction method, the obtained interval fuzzy set has to be converted into clear numbers to make it fit into most FLS application scenarios. In practical application, the output defuzzification operation can be realized by averaging the upper limit and the lower limit of the output corresponding to each rule, that is, the fuzzy value can be obtained by calculating the average value of the left end point and the right end point of the interval:
the embodiment determines an input fuzzy set based on the consideration of ship manipulation characteristics (turning performance), and constructs an inference engine suitable for a target navigation environment by using a language mechanism, so that a suitable two-type fuzzy control process is established, the current state of a ship (namely, the course deviation between the actual course and the expected course) obtained by observation is used as input, the course obtained after the control process is used as output, and the course control instruction is acted on a control system, so that the purpose of controlling the course or the speed of the ship is achieved.
The method comprises the steps of firstly, utilizing known information (including target environment information of ship navigation and the like) to design a control process, specifically presenting environment variables or noise collected by a sensor in an interval, and then utilizing the control process to accurately control the environment variables or the noise.
The following explains the application of the intelligent control method to a control system of a ship. The verification is carried out by a simulation system of the ship course, so that a motion model of the ship course needs to be established, and external interference factor information is simulated according to the assumed target navigation environment.
As shown in FIG. 7, in the ship control system, the intelligent control method is integrated in the TYPE-2 controller, the reference course obtained by the reference model and the course error between the actual courses of the ships obtained after the disturbance of the wind flow and the wave are taken as the input of the TYPE-2 controller, the expected required course angle or the navigation speed is obtained by using the two-TYPE fuzzy controller, and then the expected required course angle or the navigation speed is converted into the angle and the rotating speed of the steering engine through the ship motion equation. Due to the qualitative consideration of the environment variables, the unmanned ship can better adapt to the current environment and automatically make accurate course control with better robustness.
As a specific implementation manner, the nonlinear mathematical model of the ship course motion is as follows:
wherein psi is the ship course angle generated by rudder action, T is the following time index, K is the rudder gain coefficient,
for non-linear characteristics determined by spiral or inverse spiral tests, n1 for a ship with stable heading>0, unstable vessel has n1<0 and delta are the control rudder angles,
let r be the course angular rate, have
Expressed as state space form:
the protective scope of the present invention is not limited to the above-described embodiments, and it is apparent that various modifications and variations can be made to the present invention by those skilled in the art without departing from the scope and spirit of the present invention. It is intended that the present invention cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents.
Claims (6)
1. An uncertain interference-oriented ship course intelligent control method is characterized by comprising the following steps:
step S1, designing an input fuzzy set of course deviation according to the influence factors of the target navigation environment of the ship navigation;
step S2, designing a rule base in the inference engine according to the actual navigation mechanism;
step S3, obtaining a matched output fuzzy set based on the input fuzzy set and the rule base;
step S4, executing a type reducer operation to obtain output of matched upper and lower bounds according to the input fuzzy set and the corresponding output fuzzy set by utilizing KM type-reduction;
and step S5, executing output defuzzification operation on the output of the upper and lower boundaries obtained in the step S4, and thus obtaining the matched control information for controlling the heading of the ship.
2. The intelligent ship course control method facing uncertain disturbance as recited in claim 1,
in the step S1, an input fuzzy set of the heading deviation is designed by using the two-type fuzzy set, and a gaussian function is used as the membership function, and the input fuzzy set region is defined by an upper member function and a lower member function, so that the influence factor of the target navigation environment is limited between the upper gaussian function and the lower gaussian function.
3. The intelligent ship course control method facing uncertain disturbance as recited in claim 1,
in step S2, e is used as the heading error, and is expressed as: e-psi0Wherein ψ0For the expected heading, ψ is the actual heading, then the rule base designed is:
if e is positive, indicating that the heading is larger than the expected heading, and controlling the ship to steer to the right when the ship deflects to the left;
if e is negative, indicating that the heading is less than the expected heading, the ship deflects to the right and needs to be controlled to steer to the left,
wherein the heading is positive to the left and negative to the right.
4. The intelligent ship course control method facing uncertain disturbance as recited in claim 3,
in step S3, the output corresponding to the ith rule obtained from the inference engine in step S2 is represented as:
further, a fuzzy set is output
Determined by the following expression:
5. the intelligent ship course control method facing uncertain disturbance as recited in claim 4,
in step S4, an upper limit and a lower limit are set for the output of each rule, and the output upper limit and the output lower limit corresponding to the ith rule are respectively expressed as:
upper limit of
Lower limit of
6. The intelligent ship course control method facing uncertain disturbance as recited in claim 5,
in step S5, the output defuzzification operation is performed by averaging the upper and lower limits of the output corresponding to each rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228467.1A CN112987741A (en) | 2021-02-24 | 2021-02-24 | Uncertain interference-oriented ship course intelligent control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228467.1A CN112987741A (en) | 2021-02-24 | 2021-02-24 | Uncertain interference-oriented ship course intelligent control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112987741A true CN112987741A (en) | 2021-06-18 |
Family
ID=76351809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110228467.1A Pending CN112987741A (en) | 2021-02-24 | 2021-02-24 | Uncertain interference-oriented ship course intelligent control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112987741A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114115256A (en) * | 2021-11-17 | 2022-03-01 | 武汉理工大学 | Ship course control method based on cloud model |
| CN114879668A (en) * | 2022-04-25 | 2022-08-09 | 广东逸动科技有限公司 | Control method for electric ship, and computer-readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105467833A (en) * | 2015-12-07 | 2016-04-06 | 南京航空航天大学 | A non-linear self-adaptive flight control method |
| CN107070336A (en) * | 2017-02-24 | 2017-08-18 | 沈阳工业大学 | The two patterns paste fractional order System with Sliding Mode Controller and method of permanent magnet linear synchronous motor |
| CN108510060A (en) * | 2018-03-12 | 2018-09-07 | 华南理工大学 | A kind of two type Fuzzy Cognitive Map model of section based on fuzzy neural network |
| CN109102066A (en) * | 2018-07-12 | 2018-12-28 | 山东师范大学 | Online time series data prediction technique, system and storage medium based on fuzzy reasoning |
| CN110083061A (en) * | 2019-04-12 | 2019-08-02 | 国网宁夏电力有限公司电力科学研究院 | A kind of Control of Wheeled Mobile Robots method |
| CN112124537A (en) * | 2020-09-23 | 2020-12-25 | 哈尔滨工程大学 | Intelligent control method for underwater robot for autonomous absorption and fishing of benthos |
-
2021
- 2021-02-24 CN CN202110228467.1A patent/CN112987741A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105467833A (en) * | 2015-12-07 | 2016-04-06 | 南京航空航天大学 | A non-linear self-adaptive flight control method |
| CN107070336A (en) * | 2017-02-24 | 2017-08-18 | 沈阳工业大学 | The two patterns paste fractional order System with Sliding Mode Controller and method of permanent magnet linear synchronous motor |
| CN108510060A (en) * | 2018-03-12 | 2018-09-07 | 华南理工大学 | A kind of two type Fuzzy Cognitive Map model of section based on fuzzy neural network |
| CN109102066A (en) * | 2018-07-12 | 2018-12-28 | 山东师范大学 | Online time series data prediction technique, system and storage medium based on fuzzy reasoning |
| CN110083061A (en) * | 2019-04-12 | 2019-08-02 | 国网宁夏电力有限公司电力科学研究院 | A kind of Control of Wheeled Mobile Robots method |
| CN112124537A (en) * | 2020-09-23 | 2020-12-25 | 哈尔滨工程大学 | Intelligent control method for underwater robot for autonomous absorption and fishing of benthos |
Non-Patent Citations (2)
| Title |
|---|
| 贺辉: "基于自适应区间二型模糊聚类的 遥感土地覆盖自动分类", 《地球物理学报》, pages 1983 - 1992 * |
| 郑高: "二型模糊系统辨识方法研究", 《公安海警学院学报》, pages 1 - 3 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114115256A (en) * | 2021-11-17 | 2022-03-01 | 武汉理工大学 | Ship course control method based on cloud model |
| CN114879668A (en) * | 2022-04-25 | 2022-08-09 | 广东逸动科技有限公司 | Control method for electric ship, and computer-readable storage medium |
| CN114879668B (en) * | 2022-04-25 | 2024-01-26 | 广东逸动科技有限公司 | Control method for electric ship, electric ship and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Woo et al. | Deep reinforcement learning-based controller for path following of an unmanned surface vehicle | |
| Qin et al. | Adaptive trajectory tracking algorithm of unmanned surface vessel based on anti-windup compensator with full-state constraints | |
| Junmin et al. | Mechanism of dynamic automatic collision avoidance and the optimal route in multi-ship encounter situations | |
| CN108983774B (en) | Single-jet-pump-propelled unmanned surface vehicle self-adaptive course control method based on fuzzy state observer | |
| CN112987741A (en) | Uncertain interference-oriented ship course intelligent control method | |
| CN111897225B (en) | Fuzzy self-adaptive output feedback control method and system for intelligent ship autopilot system | |
| Zhang et al. | Neural network control of underactuated surface vehicles with prescribed trajectory tracking performance | |
| He et al. | Nonparametric modeling of ship maneuvering motion based on self-designed fully connected neural network | |
| CN111290387B (en) | Fuzzy self-adaptive output feedback designated performance control method and system for intelligent ship autopilot system | |
| Deng et al. | Event-triggered composite adaptive fuzzy control of sailboat with heeling constraint | |
| CN111880546A (en) | Virtual guide ship automatic berthing control method based on self-adaptive dynamic programming algorithm | |
| Londhe et al. | Robust proportional derivative (PD)-like fuzzy control designs for diving and steering planes control of an autonomous underwater vehicle | |
| CN113110511A (en) | Intelligent ship course control method based on generalized fuzzy hyperbolic model | |
| CN110377034A (en) | A kind of waterborne vessel track following Global robust sliding-mode control based on dragonfly algorithm optimization | |
| Løver et al. | Explainable AI methods on a deep reinforcement learning agent for automatic docking | |
| Zhang et al. | Improved LVS guidance and path-following control for unmanned sailboat robot with the minimum triggered setting | |
| Kanazawa et al. | A multiple-output hybrid ship trajectory predictor with consideration for future command assumption | |
| Zhao et al. | An improved nonlinear innovation-based parameter identification algorithm for ship models | |
| Kula | Model-based controller for ship track-keeping using Neural Network | |
| Amendola et al. | Navigation in restricted channels under environmental conditions: Fast-time simulation by asynchronous deep reinforcement learning | |
| CN115755603A (en) | Intelligent ash box identification method for ship motion model parameters and ship motion control method | |
| Vianna et al. | Neural Network Based Model Predictive Control for an Autonomous Vehicle | |
| Ngongi et al. | Design of generalised predictive controller for dynamic positioning system of surface ships | |
| Deryabin et al. | A vessel’s dead reckoning position estimation by using of neural networks | |
| Wang et al. | Model-free adaptive control for unmanned surface vessels: a literature review |
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 |