An E/H Control Design for a Hydraulic Variable Displacement Axial Piston Motor

2011 ◽  
Author(s):  
Hongliu Du
Keyword(s):  
Adaptive Learning ◽  
Lower Cost ◽  
Learning Algorithm ◽  
Control Design ◽  
Test Results ◽  
Satisfactory Performance ◽  
Control Scheme ◽  
Variable Displacement ◽  
System Uncertainties ◽  
Axial Piston

A simple and novel speed control scheme for variable displacement motors has been developed under the consideration of some system uncertainties. Theoretical analysis and experimental test results have shown that the proposed control strategy is capable of driving the swashplate to track its desired trajectory with robust stability and satisfactory performance. An adaptive learning algorithm enables the controls to automatically adjust for uncertainties in the control bias current. Compared with its hydro-mechanical counterpart, the provided E/H control results in a hydraulic variable displacement motor with lower cost and better performance.

Transfer Enabling Device for the Physically Handicapped

2003 ◽  
Author(s):  
Robert C. Elliott ◽  
Matthew Brew ◽  
David Higgs ◽  
Christopher Petrocelli ◽  
Derek Ruby ◽  
...  
Keyword(s):  
Psychological Factors ◽  
Lower Cost ◽  
Low Cost ◽  
Test Results ◽  
Satisfactory Performance ◽  
Physically Handicapped

The need for transferring a disabled individual from a wheelchair to another location and vice versa cannot be underemphasized, given the numerous day-to-day activities that may require relocation of the person and the psychological factors involved. While there are some devices currently available on the market that aid in transferring the handicapped individuals from one location to another, few are available for transferring them from a wheelchair to an automobile. Vehicular lifts, which is general require modification of the vehicle, and automobiles custom modified to accommodate wheelchairs are some examples of devices that facilitate transfer of individuals. However, these devices are in general suitable for one vehicle only and relatively expensive. This paper present the design of a device that will allow an individual to transfer himself/herself easily and safely from a wheelchair to automobile or another location and vice versa, with minimal assistance and at a relatively lower cost. Presented are the design and test results from a prototype. The results demonstrate that the intended specifications are satisfied and that this relatively low-cost design is likely to deliver a satisfactory performance and provide individuals in wheelchairs with more freedom to travel. Because of the easy usbility, less dependence on assistants, and ability for a larger range of vehicles to be used, the design may also provide feeling of independence.

Synchronization Motion of Four Supports Hydraulic Platform with Unbalanced Loading and Uncertainties

2010 ◽  
Vol 44-47 ◽  
pp. 935-940
Author(s):  
Xuan Ling ◽  
Xu Dong Wang
Keyword(s):  
Adaptive Learning ◽  
Learning Algorithm ◽  
High Mobility ◽  
Neural Controller ◽  
Hybrid Controller ◽  
The Neural Network ◽  
Series Of Experiments ◽  
System Uncertainties ◽  
Fast Dynamic ◽  
Synchronization Performance

Radar leveling system is the key equipment for improving radar high mobility and survival capability. In this paper, an integrated hybrid controller, comprising of a sets of fuzzy cylinder controllers and one synchronous neural controller, is proposed for a antenna trailer of radar with four points supporting, which is driven by one hydraulic oil supply, to achieve synchronization motion under he various conditions of system uncertainties and disturbances. A new control strategy for better synchronization performance is proposed and a self-adaptive learning algorithm to adjust the weights of the neural network, is also derived. To verify the effectiveness and potential of the proposed controller, a series of experiments were made. Experimental results have demonstrated its high accuracy synchronization performance and fast dynamic response as well as stability of the leveling servo system. The hybrid controller can drive the radar truck leveling platform accurately, quickly and stably.

scholarly journals Multi-AUVs Cooperative Target Search Based on Autonomous Cooperative Search Learning Algorithm

2020 ◽  
Vol 8 (11) ◽  
pp. 843
Author(s):  
Yuan Liu ◽  
Min Wang ◽  
Zhou Su ◽  
Jun Luo ◽  
Shaorong Xie ◽  
...  
Keyword(s):  
Adaptive Learning ◽  
Autonomous Underwater Vehicle ◽  
Learning Algorithm ◽  
Test Results ◽  
Reward Function ◽  
Collaborative Search ◽  
New Type ◽  
System Robustness ◽  
Mine Countermeasures ◽  
Tailored Design

As a new type of marine unmanned intelligent equipment, autonomous underwater vehicle (AUV) has been widely used in the field of ocean observation, maritime rescue, mine countermeasures, intelligence reconnaissance, etc. Especially in the underwater search mission, the technical advantages of AUV are particularly obvious. However, limited operational capability and sophisticated mission environments are also difficulties faced by AUV. To make better use of AUV in the search mission, we establish the DMACSS (distributed multi-AUVs collaborative search system) and propose the ACSLA (autonomous collaborative search learning algorithm) integrated into the DMACSS. Compared with the previous system, DMACSS adopts a distributed control structure to improve the system robustness and combines an information fusion mechanism and a time stamp mechanism, making each AUV in the system able to exchange and fuse information during the mission. ACSLA is an adaptive learning algorithm trained by the RL (Reinforcement learning) method with a tailored design of state information, reward function, and training framework, which can give the system optimal search path in real-time according to the environment. We test DMACSS and ACSLA in the simulation test. The test results demonstrate that the DMACSS runs stably, the search accuracy and efficiency of ACSLA outperform other search methods, thus better realizing the cooperation between AUVs, making the DMACSS find the target more accurately and faster.

An Adaptive Pressure Servo-Control Design for Variable Displacement Pumps

2000 ◽  
Author(s):  
Hongliu Du ◽  
Noah D. Manring
Keyword(s):  
Adaptive Learning ◽  
Control Design ◽  
Time History ◽  
Order System ◽  
Loop Control ◽  
Control Approach ◽  
Displacement Pump ◽  
Variable Displacement ◽  
Discharge Pressure ◽  
Variable Displacement Pumps

Abstract In this paper, a new pressure control scheme for a variable displacement pump is proposed under the consideration of various system uncertainties. The control design reported in this paper provides an effective approach for controlling the discharge pressure of variable displacement pumps to asymptotically track the desired pressure time history. With the provided nonlinear control design, the output pressure error dynamics are presented in a first order system with which the system performance is restricted by the limitations on control actuation, unmodeled dynamics, and parametric uncertainties. The discharge pressure overshoot is eliminated for the compensated closed-loop control system. On-line adaptive learning is introduced to compensate for the uncertainty in the pressure carry-over angle, which induces the most significant torque on the swashplate in a variable displacement pump. Experimental results are provided to validate the effectiveness of the proposed control approach.

SMART IDENTIFICATION OF POWER QUALITY EVENTS USING NEW STOCKWELL TRANSFORM AND MACHINE LEARNING ALGORITHM

2019 ◽  
Vol XVI (4) ◽  
pp. 95-113
Author(s):  
Muhammad Tariq ◽  
Tahir Mehmood
Keyword(s):  
Machine Learning ◽  
Power Quality ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Noisy Environments ◽  
Satisfactory Performance ◽  
Feature Values ◽  
Learning Machine ◽  
Stockwell Transform ◽  
Electrical Utilities

Accurate detection, classification and mitigation of power quality (PQ) distortive events are of utmost importance for electrical utilities and corporations. An integrated mechanism is proposed in this paper for the identification of PQ distortive events. The proposed features are extracted from the waveforms of the distortive events using modified form of Stockwell’s transform. The categories of the distortive events were determined based on these feature values by applying extreme learning machine as an intelligent classifier. The proposed methodology was tested under the influence of both the noisy and noiseless environments on a database of seven thousand five hundred simulated waveforms of distortive events which classify fifteen types of PQ events such as impulses, interruptions, sags and swells, notches, oscillatory transients, harmonics, and flickering as single stage events with their possible integrations. The results of the analysis indicated satisfactory performance of the proposed method in terms of accuracy in classifying the events in addition to its reduced sensitivity under various noisy environments.

scholarly journals Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1127
Author(s):  
Ji Hyung Nam ◽  
Dong Jun Oh ◽  
Sumin Lee ◽  
Hyun Joo Song ◽  
Yun Jeong Lim
Keyword(s):  
Deep Learning ◽  
Small Bowel ◽  
Scoring System ◽  
Operating Characteristic ◽  
Clinical Evidence ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
External Validation ◽  
Test Results ◽  
Deep Learning Algorithm

Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.

Energy-saving design of variable-displacement bi-directional pump-controlled electrohydraulic system

2020 ◽  
pp. 095965182097389
Author(s):  
Samir Kumar Hati ◽  
Nimai Pada Mandal ◽  
Dipankar Sanyal
Keyword(s):  
Energy Saving ◽  
Absolute Error ◽  
Fast Response ◽  
Maximum Energy ◽  
Radial Clearance ◽  
Simulation Based Design ◽  
Simulation Based ◽  
Displacement Pump ◽  
Variable Displacement ◽  
Axial Piston

Losses in control valves drag down the average overall efficiency of electrohydraulic systems to only about 22% from nearly 75% for standard pump-motor sets. For achieving higher energy efficiency in slower systems, direct pump control replacing fast-response valve control is being put in place through variable-speed motors. Despite the promise of a quicker response, displacement control of pumps has seen slower progress for exhibiting undesired oscillation with respect to the demand in some situations. Hence, a mechatronic simulation-based design is taken up here for a variable-displacement pump–controlled system directly feeding a double-acting single-rod cylinder. The most significant innovation centers on designing an axial-piston pump with an electrohydraulic compensator for bi-directional swashing. An accumulator is conceived to handle the flow difference in the two sides across the load piston. A solenoid-driven sequence valve with P control is proposed for charging the accumulator along with setting its initial gas pressure by a feedforward design. Simple proportional–integral–derivative control of the compensator valve is considered in this exploratory study. Appropriate setting of the gains and critical sizing of the compensator has been obtained through a detailed parametric study aiming low integral absolute error. A notable finding of the simulation is the achievement of the concurrent minimum integral absolute error of 3.8 mm s and the maximum energy saving of 516 kJ with respect to a fixed-displacement pump. This is predicted for the combination of the circumferential port width of 2 mm for the compensator valve and the radial clearance of 40 µm between each compensator cylinder and the paired piston.

Adaptive Learning Algorithm for Cerebellar Model Articulation Controller: Neural Network Based Hybrid-Type Controller—Part I

2000 ◽  
Author(s):  
Magdy Mohamed Abdelhameed ◽  
Sabri Cetinkunt
Keyword(s):  
Neural Network ◽  
Control System ◽  
Adaptive Learning ◽  
Learning Algorithm ◽  
Cerebellar Model Articulation Controller ◽  
Neural Network Learning ◽  
Network Learning ◽  
Hybrid Type ◽  
Cmac Neural Network ◽  
Learning Technique

Abstract Cerebellar model articulation controller (CMAC) is a useful neural network learning technique. It was developed two decades ago but yet lacks an adequate learning algorithm, especially when it is used in a hybrid- type controller. This work is intended to introduce a simulation study for examining the performance of a hybrid-type control system based on the conventional learning algorithm of CMAC neural network. This study showed that the control system is unstable. Then a new adaptive learning algorithm of a CMAC based hybrid- type controller is proposed. The main features of the proposed learning algorithm, as well as the effects of the newly introduced parameters of this algorithm have been studied extensively via simulation case studies. The simulation results showed that the proposed learning algorithm is a robust in stabilizing the control system. Also, this proposed learning algorithm preserved all the known advantages of the CMAC neural network. Part II of this work is dedicated to validate the effectiveness of the proposed CMAC learning algorithm experimentally.

Sign in / Sign up

Export Citation Format

Share Document