Multi-dimensional Particle Swarm Optimization

Inertial Navigation Systems (INS) consist of accelerometers, gyroscopes and a microprocessor provide inertial digital data from which position and orientation is obtained by integrating the specific forces and rotation rates. In addition to the accelerometers and gyroscopes, magnetometers can be used to derive the absolute user heading based on Earth's magnetic field. Unfortunately, the measurements of the magnetic field obtained with low cost sensors are corrupted by several errors including manufacturing defects and external electromagnetic fields. Consequently, proper calibration of the magnetometer is required to achieve high accuracy heading measurements. In this paper, a Particle Swarm Optimization (PSO) based calibration algorithm is presented to estimate the values of the bias and scale factor of low cost magnetometer. The main advantage of this technique is the use of the artificial intelligence which does not need any error modeling or awareness of the nonlinearity. The estimated bias and scale factor errors from the proposed algorithm improve the heading accuracy and the results are also statistically significant. Also, it can help in the development of the Pedestrian Navigation Devices (PNDs) when combined with the INS and GPS/Wi-Fi especially in the indoor environments.

Iranian Journal of Electrical and …, 2011

Using robot manipulators for high accuracy applications require precise value of the kinematics parameters. Since measurement of kinematics parameters are usually associated with errors and accurate measurement of them is an expensive task, automatic calibration of robot link parameters makes the task of kinematics parameters determination much easier. In this paper a simple and easy to use algorithm is introduced for correction and calibration of robot kinematics parameters. Actually at several end-effecter positions, the joint variables are measured simultaneously. This information is then used in five different algorithms; least square (LS), particle swarm optimization (PSO) , Genetic algorithms (GA), quadratic particle swarm optimization (QPSO) and simulated annealing particle swarm optimization (Sa_PSO) for automatic calibration and correction of the kinematics parameters. This process was also tested experimentally via a three degree of freedom manipulator which is actually used as a coordinate measuring machine (CMM). The experimental Results prove that the intelligent algorithms are useful for both parameter identification and calibration of link parameters.

Sadhana, 2014

The optimization of architecture and weights of feed forward neural networks is a complex task of great importance in problems of supervised learning. In this work we analyze the use of the Particle Swarm Optimization algorithm for the optimization of neural network architectures and weights aiming better generalization performances through the creation of a compromise between low architectural complexity and low training errors. For evaluating these algorithms we apply them to benchmark classification problems of the medical field. The results showed that a PSO-PSO based approach represents a valid alternative to optimize weights and architectures of MLP neural networks.

Procedia CIRP, 2015

Coordinates Measuring Arms (CMA) are increasingly used to control industrial parts and are often an alternative to CMM controls that require conditions of laboratory measurement and involve significant costs. However, the control of uncertainties is often not guaranteed because the measurement process is complex and there is no standard for setting a framework qualification process of the measurement process. The proposed study, in this paper, is a first approach to model the measurement uncertainties of a CMA with contact sensor. The problem is complex because there are many sources of uncertainty, largely due to variability in the handling carried out by the operator. A model, based on Denavit-Hartenberg description, has been developed taking into account the measurement conditions (i.e.: the influence not only of the temperature, of the encoder error, of the deformation of different parts of the arm, of the noise of external vibrations, but also of the calibration parameters). The Monte Carlo method is used to estimate the obtained uncertainties. This method allows to take into account of the covariance when factors cannot be considered independent. The resulting model was validated for the measurement of the location of different points of the working space of a CMA Sigma 2025 (ROMER ®), then for the measurement of an industrial part in comparison with a measurement carried using a CMM.

Precision Engineering, 2015

The stage error of coordinate measuring machines (CMM) can significantly influence the measurement results, and it places ultra-high requirement on the measurement and calibration tools. A calibration technique based on self-calibration algorithm is presented to calibrate the two-dimensional stage error of CMM, and it can be carried out with a grid plate of the accuracy no higher than test stage. With the proposed self-calibration algorithm based on least squares method, the measurements at various position combinations of rotation and translation are carried out to separate the stage error from measurement results. Both the accuracy and feasibility of the proposed calibration method have been demonstrated by computer simulation and experiments, and the measurement accuracy RMS better than 1 m is achieved. The proposed calibration method has a good anti-noise ability and provides a feasible way to lower the accuracy requirement on standard parts. It is of great practicality for high-accuracy calibration of the stage error of CMM and manufacturing machines in the order of submicron.

Materials Today: Proceedings, 2015

Selection and peer-review under responsibility of the conference committee members of the 4th International conference on Materials Processing and Characterization.

Sensors and Materials, 2020

We propose a new method for the analysis and design of a robotic system that minimizes the energy consumption of a six-axis robot arm by controlling the velocity and acceleration of each arm of the robot to achieve the specified trajectory of the robot determined from a lean manufacturing method. A dynamic model of the PUMA 560 robot has been simulated on MATLAB, while the Robotics Toolbox and particle swarm optimization (PSO) are utilized to search for optimal paths and the optimal velocity and acceleration of the robot arms. The optimal velocity and acceleration are described as those giving minimum overall energy consumption constrained by a specified cycle time of the entire robotic system. Typically, the picking and placing of materials are carried out by humans, causing a variation in production rate, whereas our system using a robot arm ensures a stable production rate. Moreover, the optimal results obtained from PSO are adopted to train an artificial neural network (ANN) to extend the design system from discrete optimal values to a continuous and near-optimal value. In other words, the ANN is used to obtain an approximate optimal value between those obtained from PSO to make the system applicable to a real-world system. As shown by the simulation results, this method reduces the energy consumption of 12.3% from the initial energy and reduces the time for optimization by 99.8% compared with that for the PSO technique.

2016 2nd IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), 2016

Over the years, numerous researchers have explored the relationship between surface electromyography (sEMG) signal with joint torque that would be useful to develop a suitable controller for rehabilitation robot. This research focuses on the transformation of sEMG signal by adopting a mathematical model to find the estimated joint torque of knee extension. Swarm techniques such as Particle Swarm Optimization (PSO) and Improved Particle Swarm Optimization (IPSO) were adapted to optimize the mathematical model for estimated joint torque. The correlation between the estimated joint torque and actual joint torque were determined by Coefficient of Determination (R 2) and fitness value of Sum Squared Error (SSE). The outcome of the research shows that both the PSO and IPSO have yielded promising results.

Journal of Manufacturing and Materials Processing, 2018

Monitoring of the relative deviation between commanded and actual tool tip position, which limits the volumetric performance of the machine tool, enables the use of contemporary methods of compensation to reduce tolerance mismatch and the uncertainties of on-machine measurements. The development of a primarily optical sensor setup capable of being integrated into the machine structure without limiting its operating range is presented. The use of a frequency-modulating interferometer and photosensitive arrays in combination with a Gaussian laser beam allows for fast and automated online measurements of the axes’ motion errors and thermal conditions with comparable accuracy, lower cost, and smaller dimensions as compared to state-of-the-art optical measuring instruments for offline machine tool calibration. The development is tested through simulation of the sensor setup based on raytracing and Monte-Carlo techniques.

2012

Particle Swarm Optimization is a comparatively recent heuristic technique, introduced by Kenedy and Eberthart in 1995. It is very similar to Genetic Algorithm and it is also a population based method. Many developments have been carried out to the standard Particle Swarm Optimization algorithm. Due to the less computational effort PSOs are very widely being used as an optimization tool. The GA is discrete in nature where as the PSO is inherently continuous. As many variations of the PSO are being popular the motto of this paper is to make analysis of the existing modified versions of standard Particle Swarm Optimization algorithm and to suggest a new variant of PSO. This paper is divided into two parts. The first part is doing analysis of the time variant inertia weight methods suggested by different researchers. In the second part a new method of updating the inertia weight has been proposed. It is also implemented using Mat Lab and proven as worthy than the existing weight updating methods