CN-122018330-A - Bridge pier active collision avoidance system control method and system based on fuzzy neural network

CN122018330ACN 122018330 ACN122018330 ACN 122018330ACN-122018330-A

Abstract

The invention belongs to the technical field of intelligent control, and particularly relates to a control method and a control system of an active collision avoidance system of a pier based on a fuzzy neural network, wherein the method comprises the steps of obtaining identity attribute data and motion state data of an incoming ship in a target water area; the method comprises the steps of determining the design load and the drainage volume of a ship according to identity attribute data, calculating the equivalent impact kinetic energy of the ship by combining the speed to ground and the impact incident angle, constructing a fuzzy neural network, taking the equivalent impact kinetic energy and the distance between the ship and an anti-collision facility as input quantities, outputting the basic damping current for controlling the magneto-rheological damper, determining a temperature change compensation correction coefficient according to the difference value between the real-time temperature of a cylinder body and a calibration reference temperature, and generating the final self-adaptive control current by utilizing the temperature change compensation correction coefficient so as to drive the magneto-rheological damper. The invention can adapt to the collision of ships with different tonnages, and effectively inhibit the performance attenuation of the magneto-rheological damper caused by temperature rise.

Inventors

XU MINGCAI
SONG WENTONG

Assignees

武汉力拓桥科防撞设施有限公司

Dates

Publication Date: 20260512
Application Date: 20260410

Claims (10)

1. The bridge pier active collision avoidance system control method based on the fuzzy neural network is characterized by comprising the following steps of: Acquiring identity attribute data and motion state data of an incoming ship in a target water area, and performing smoothing treatment on the motion state data to eliminate clutter interference; Determining the design load and the drainage volume of the ship according to the identity attribute data, and calculating the equivalent impact kinetic energy of the ship by combining the ground speed and the impact incidence angle relative to the anti-collision surface in the motion state data; constructing a fuzzy neural network, taking the equivalent impact kinetic energy and the distance between the ship and an anti-collision facility as input quantities, and outputting and controlling the basic damping current of the magneto-rheological damper through the processes of fuzzification, rule reasoning and defuzzification; And acquiring the real-time temperature of the cylinder body of the magnetorheological damper, determining a temperature change compensation correction coefficient according to the difference value between the real-time temperature of the cylinder body and a calibration reference temperature, correcting the basic damping current by using the temperature change compensation correction coefficient, and superposing a feedback item based on the relative compression speed of the damper piston to generate a final self-adaptive control current to drive the magnetorheological damper.
2. The method for controlling an active collision avoidance system of a pier based on a fuzzy neural network according to claim 1, wherein the step of acquiring the identity attribute data and the movement state data of an incoming ship in a target water area comprises the steps of: Analyzing the unique identification code of the incoming ship through the automatic ship identification system, and acquiring the design load, the ship length, the ship width and the draft as identity attribute data; tracking an incoming ship by utilizing a millimeter wave radar and a laser radar, and acquiring the ground speed, the course angle and the incident angle relative to an anti-collision surface as motion state data; and processing the original data acquired by the millimeter wave radar and the laser radar by adopting a Kalman filtering algorithm.
3. The pier active collision avoidance system control method based on the fuzzy neural network of claim 1, wherein the equivalent impact kinetic energy satisfies the relationship: ; In the formula, For the equivalent impact kinetic energy, The load is designed for the ship and the ship is not subject to load, In order to attach the water coefficient, Is the density of the water body, For the volume of the water to be drained, Is the ground speed of the ship, For the impinging angle of incidence.
4. The pier active collision avoidance system control method based on the fuzzy neural network of claim 1, wherein the constructing the fuzzy neural network comprises: setting an input layer to receive the equivalent impact kinetic energy and the distance; setting a fuzzification layer, and converting the input quantity into membership of a corresponding fuzzy language variable by using a membership function; setting a rule reasoning layer, carrying out logic operation on the membership degree according to a preset fuzzy control rule base, and activating a corresponding control rule; And setting an output layer, and performing fuzzy calculation on the output result of the rule reasoning layer to obtain the basic damping current.
5. The control method of the pier active collision avoidance system based on the fuzzy neural network according to claim 4, wherein the fuzzy control rule base comprises establishing a nonlinear mapping relation among energy, distance and damping current, and outputting an increased basic damping current when the equivalent impact kinetic energy is large and the distance is small.
6. The pier active collision avoidance system control method based on the fuzzy neural network of claim 1, wherein the temperature change compensation correction coefficient satisfies the relationship: ; Wherein, the For the purpose of temperature change compensation and correction coefficient, For the real-time temperature of the damper cylinder, In order to calibrate the reference temperature, As a thermal viscosity decay factor, Is an exponential factor.
7. The pier active collision avoidance system control method based on the fuzzy neural network of claim 6, wherein the adaptive control current satisfies the relationship: ; In the formula, In order to finally adaptively control the current, As a basis for the damping current, For the relative compression speed of the damper piston, As a result of the velocity feedback coefficient, As a function of the amplitude limiting function, Is the upper limit value of current safety.
8. The control method for the pier active collision avoidance system based on the fuzzy neural network according to claim 7, wherein the limiting function is used for limiting the calculated current value between 0 and the current safety upper limit value, so as to prevent occurrence of reverse current or overload current.
9. The control method for the pier active collision avoidance system based on the fuzzy neural network according to claim 1, wherein the magnetorheological damper is internally filled with magnetorheological fluid, the viscosity of the magnetorheological fluid decreases with the increase of temperature, and the temperature change compensation correction coefficient is used for increasing current output when the temperature increases to compensate the viscosity loss.
10. The bridge pier active collision avoidance system based on the fuzzy neural network is characterized by comprising a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions realize the bridge pier active collision avoidance system control method based on the fuzzy neural network according to any one of claims 1-9 when executed by the processor.

Description

Bridge pier active collision avoidance system control method and system based on fuzzy neural network Technical Field The invention relates to the technical field of intelligent control. More particularly, the invention relates to a pier active collision avoidance system control method and system based on a fuzzy neural network. Background The bridge pier anti-collision facility is an important barrier for guaranteeing the safety of bridge structures, the development process of the bridge pier anti-collision facility is subjected to the evolution from a rigid anti-collision device to a flexible anti-collision device, most of the existing bridge pier anti-collision facilities belong to passive structures, the rigidity and damping characteristics of the bridge pier anti-collision facility are fixed after factory manufacturing is completed, and the protection effect is difficult to consider when the bridge pier anti-collision facility is impacted by ships with different tonnages. In the prior art, the pier anti-collision facility with fixed rigidity and damping characteristics faces the contradiction that the pier anti-collision facility is difficult to consider for ships with different tonnages, if the pier anti-collision device is designed to be too hard, the small-tonnage ship is damaged or even directly damaged due to the excessive counter force when the small-tonnage ship collides, and if the pier anti-collision device is designed to be too soft, the pier anti-collision facility is easy to break down when the large-tonnage ship collides, and the pier is directly damaged. In addition, the pier anti-collision facility with the passive structure often generates a huge counter-force peak value at the moment of high-speed collision of the ship, and the instantaneous impact force has great damage to pier pile foundations and hull structures. At present, a magnetorheological damper is theoretically proposed to be used, but in the actual impact process, huge mechanical energy can be quickly converted into heat energy, the temperature of the magnetorheological damper is rapidly increased, and the physical characteristics of magnetorheological fluid in the magnetorheological damper determine that the viscosity of the magnetorheological fluid can be greatly reduced along with the temperature increase, so that the output force of the magnetorheological damper is attenuated, and the control of the magnetorheological damper is invalid. Disclosure of Invention The invention provides a bridge pier active anti-collision system control method and system based on a fuzzy neural network, which are used for solving the problems of fixed rigidity, poor adaptability, thermal attenuation effect and the like of the existing bridge pier anti-collision facilities and the magneto-rheological damper, can be used for self-adapting to the collision of ships with different tonnages, effectively inhibiting the performance attenuation of the magneto-rheological damper caused by temperature rise, and improving the reliability and the protection effect of the system. In a first aspect, the invention provides a bridge pier active anti-collision system control method based on a fuzzy neural network, which comprises the steps of obtaining identity attribute data and motion state data of an incoming ship in a target water area, carrying out smooth processing on the motion state data to eliminate clutter interference, determining a design load and a drainage volume of the ship according to the identity attribute data, combining a ground navigation speed and an impact incidence angle relative to an anti-collision surface in the motion state data, calculating equivalent impact kinetic energy of the ship, constructing the fuzzy neural network, taking the equivalent impact kinetic energy and a distance between the ship and an anti-collision facility as input quantities, outputting a basic damping current for controlling the magneto-rheological damper through fuzzification, rule reasoning and defuzzification processes, acquiring a real-time temperature of a cylinder body of the magneto-rheological damper, determining a temperature change compensation correction coefficient according to a difference value between the real-time temperature of the cylinder body and a calibration reference temperature, correcting the basic damping current by utilizing the temperature change compensation correction coefficient, and superposing a feedback item based on a relative compression speed of the damper piston to generate a final self-adaptive control current to drive the magneto-rheological damper. By adopting the technical scheme, the system can output nonlinear basic damping current by using the fuzzy neural network according to the actual impact kinetic energy and the actual impact distance of the ship, and solves the problem of performance attenuation of the magnetorheological damper during impact heating by using the temperature change compensation correction