Tarık Çakar

A study of neural network based inverse kinematics solution for a three-joint robot

Abstract A neural network based inverse kinematics solution of a robotic manipulator is presented in this paper. Inverse kinematics problem is generally more complex for robotic manipulators. Many traditional solutions such as geometric, iterative and algebraic are inadequate if the joint structure of the manipulator is more complex. In this study, a three-joint robotic manipulator simulation software, developed in our previous studies, is used. Firstly, we have generated many initial and final points in the work volume of the robotic manipulator by using cubic trajectory planning. Then, all of the angles according to the real-world coordinates (x, y, z) are recorded in a file named as training set of neural network. Lastly, we have used a designed neural network to solve the inverse kinematics problem. The designed neural network has given the correct angles according to the given (x, y, z) cartesian coordinates. The online working feature of neural network makes it very successful and popular in this solution.

Machine number, priority rule, and due date determination in flexible manufacturing systems using artificial neural networks

When there is a production system with excess capacity, i.e. more capacity than the demand for the foreseeable future, upper management might consider utilizing only a portion of the available capacity by decreasing the number of workers or halting production on some of the machines/production lines, etc. while preserving the flexibility of the production system to satisfy demand spikes. To achieve this flexibility, upper management might be willing to attain some pre-determined/desired performance values in a production system having identical parallel machines in each work center. In this study, we propose a framework that utilizes parallel neural networks to make decisions on the availability of resources, due date assignments for incoming orders, and dispatching rules for scheduling. This framework is applied to a flexible manufacturing system with work centers having parallel identical machines. The artificial neural networks were able to satisfactorily capture the underlying relationship between the design and control parameters of a manufacturing system and the resulting performance targets.

Parallel robot scheduling to minimize mean tardiness with precedence constraints using a genetic algorithm

Identical parallel robot scheduling problem for minimizing mean tardiness with precedence constraints is a very important scheduling problem. But, the solution of this problem becomes much difficult when there are a number of robots, jobs and precedence constraints. Genetic algorithm is an efficient tool in the solution of combinatorial optimization problems, as it is well known. In this study, a genetic algorithm is used to schedule jobs that have precedence constraints minimizing the mean tardiness on identical parallel robots. The solutions of problems, which have been taken in different scales, have been done using simulated annealing and genetic algorithm. In particular, genetic algorithm is found noteworthy successful in large-scale problems.

Parallel Robot Scheduling to Minimize Mean Tardiness with Unequal Release Date and Precedence Constraints Using a Hybrid Intelligent System

This paper considers the problem of scheduling a given number of jobs on a specified number of identical parallel robots with unequal release dates and precedence constraints in order to minimize mean tardiness. This problem is strongly NP-hard. The author proposes a hybrid intelligent solution system, which uses Genetic Algorithms and Simulated Annealing (GA+SA). A genetic algorithm, as is well known, is an efficient tool for the solution of combinatorial optimization problems. Solutions for problems of different scales are found using genetic algorithms, simulated annealing and a Hybrid Intelligent Solution System (HISS). Computational results of empirical experiments show that the Hybrid Intelligent Solution System (HISS) is successful with regards to solution quality and computational time.

Single machine scheduling with unequal release date using neuro-dominance rule

A neuro-dominance rule (NDR) for single machine total weighted tardiness problem with unequal release date is presented by the author. To obtain the NDR, backpropagation artificial neural network (BPANN) has been trained using 10,000 data and also tested using 10,000 another data. Inputs of the trained BPANN are starting date of the first job (t), processing times (pi and pj), due dates (di and dj), weights of the jobs (wi and wj) and ri and rj release dates of the jobs. Output of the BPANN is a decision of which job should precede. Training set and test set have been obtained using Adjusted Pairwise Interchange method. The proposed NDR provides a sufficient condition for local optimality. It has been proved that if any sequence violates the NDR then violating jobs are switched according to the total weighted tardiness criterion. The proposed NDR is compared to a number of competing heuristics (ATC, COVERT, EDD, SPT, LPT, WDD, WSPT, WPD, CR, FCFS) and meta heuristics (simulated annealing and genetic algorithms) for a set of randomly generated problems. The problem sizes have been taken as 50, 70, 100. NDR is applied 270,000 randomly generated problems. Computational results indicate that the NDR dominates the heuristics and meta heuristics in all runs. Therefore, the NDR can improve the upper and lower bounding schemes.

A new neuro-dominance rule for single machine tardiness problem

We present a neuro-dominance rule for single machine total weighted tardiness problem. To obtain the neuro-dominance rule (NDR), backpropagation artificial neural network (BPANN) has been trained using 5000 data and also tested using 5000 another data. The proposed neuro-dominance rule provides a sufficient condition for local optimality. It has been proved that if any sequence violates the neuro-dominance rule then violating jobs are switched according to the total weighted tardiness criterion. The proposed neuro-dominance rule is compared to a number of competing heuristics and meta heuristics for a set of randomly generated problems. Our computational results indicate that the neuro-dominance rule dominates the heuristics and meta heuristics in all runs. Therefore, the neuro-dominance rule can improve the upper and lower bounding schemes.

A neuro-genetic-simulated annealing approach to the inverse kinematics solution of robots: a simulation based study

AbstractIn this study, a hybrid intelligent solution system including neural networks, genetic algorithms and simulated annealing has been proposed for the inverse kinematics solution of robotic manipulators. The main purpose of the proposed system is to decrease the end effector error of a neural network based inverse kinematics solution. In the designed hybrid intelligent system, simulated annealing algorithm has been used as a genetic operator to decrease the process time of the genetic algorithm to find the optimum solution. Obtained best solution from the neural network has been included in the initial solution of genetic algorithm with randomly produced solutions. The end effector error has been reduced micrometer levels after the implementation of the hybrid intelligent solution system.

A new neuro-dominance rule for single-machine tardiness problem with double due date

Abstract In this study, the single-machine total weighted tardiness scheduling problem with double due date has been addressed. The neuro-dominance rule (NDR-D) is proposed to decrease the total weighted tardiness (TWT) for the double due date. To obtain NDR-D, a back-propagation artificial neural network was trained using 12,000 data items and tested using another 15,000 items. The adjusted pairwise interchange method was used to prepare training and test data of the neural network. It was proved that if there is any sequence violating the proposed NDR-D then, according to the TWT criterion, these violating jobs are switched. The proposed NDR was compared with a number of generated heuristics. However, all of the used heuristics were generated for double due date based on using the original heuristic (ATC, COVERT, SPT, LPT, EDD, WDD, WSPT and WPD). These generated competing heuristics were called ATC1, ATC2, ATC3, COV1, COV2, COV3, COV4, EDD1, EDD2, EDD3, WDD1, WDD2, WDD3, WSPT1, WSPT2, WSPT3, WPD1, WPD2, WPD3 and WPD4. The arrangements among the heuristics were made according to the double due date. The proposed NDR-D was applied to the generated heuristics and metaheuristics, simulated annealing and genetic algorithms, for a set of randomly generated problems. Problem sizes were chosen as 50, 70 and 100. In this study, 202,500 problems were randomly generated and used to demonstrate the performance of NDR-D. From the computational results, it can be clearly seen that the NDR-D dominates the generated heuristics and metaheuristics in all runs. Additionally, it is possible to see which heuristics are the best for the double due date single-machine TWT problems.

Solving single machine total weighted tardiness problem with unequal release date using neurohybrid particle swarm optimization approach

A particle swarm optimization algorithm (PSO) has been used to solve the single machine total weighted tardiness problem (SMTWT) with unequal release date. To find the best solutions three different solution approaches have been used. To prepare subhybrid solution system, genetic algorithms (GA) and simulated annealing (SA) have been used. In the subhybrid system (GA and SA), GA obtains a solution in any stage, that solution is taken by SA and used as an initial solution. When SA finds better solution than this solution, it stops working and gives this solution to GA again. After GA finishes working the obtained solution is given to PSO. PSO searches for better solution than this solution. Later it again sends the obtained solution to GA. Three different solution systems worked together. Neurohybrid system uses PSO as the main optimizer and SA and GA have been used as local search tools. For each stage, local optimizers are used to perform exploitation to the best particle. In addition to local search tools, neurodominance rule (NDR) has been used to improve performance of last solution of hybrid-PSO system. NDR checked sequential jobs according to total weighted tardiness factor. All system is named as neurohybrid-PSO solution system.

A new neuro-dominance rule for single machine tardiness problem with unequal release dates

We present a neuro-dominance rule for single machine total weighted tardiness problem with unequal release dates. To obtain the neuro-dominance rule (NDR), backpropagation artificial neural network (BPANN) has been trained using 10000 data and also tested using 10000 another data. The proposed neuro-dominance rule provides a sufficient condition for local optimality. It has been proved that if any sequence violates the neuro-dominance rule then violating jobs are switched according to the total weighted tardiness criterion. The proposed neuro-dominance rule is compared to a number of competing heuristics and meta heuristics for a set of randomly generated problems. Our computational results indicate that the neuro-dominance rule dominates the heuristics and meta heuristics in all runs. Therefore, the neuro-dominance rule can improve the upper and lower bounding schemes.