This chapter provides an introduction to intelligent machining. The various computational techniq... more This chapter provides an introduction to intelligent machining. The various computational techniques to achieve the goal of intelligent machining are described. First, a description of neural networks and fuzzy set theory is presented. These are soft computing techniques. Afterwards the application of the finite element method to the machining processes is briefly mentioned. Finally, the optimization of machining processes is described.
The assembly sequence optimization problem is challenging as number of sequences rises staggering... more The assembly sequence optimization problem is challenging as number of sequences rises staggeringly with part count making it combinatorially explosive, tedious and time consuming to solve. A Computer-Aided Process Planning (CAPP) system for robotic assembly by a discrete cuckoo search algorithm has been proposed by us to generate feasible and optimal sequences considering minimization of orientation changes, tool/gripper changes, assembly stability and base component location. A case study and comparison results with an established soft computing approach are presented to show its effectiveness. It is further integrated with an upstream assembly product database to extract information on assembly directions, contact details, assembly precedence constraints and tool/grippers. Further the assembly sequence output from CAPP system is integrated with a robot task planner developed using Knowledge Based System capable of automatically generating executable robot level program for performing the assembly. Keywords: assembly sequence optimization, robot task planning, cuckoo search algorithm, knowledge based system.
In this paper, we have proposed and implemented a methodology for assembly sequence optimization ... more In this paper, we have proposed and implemented a methodology for assembly sequence optimization by using a nature-inspired meta-heuristic algorithm, known as hybrid cuckoo-search genetic algorithm (CSGA) algorithm. The cost criteria for optimization in the present formulation take into consideration the total assembly time and the number of reorientations during the assembly process. To demonstrate the application of the CSGA algorithm, an example assembly containing 19 parts has been presented and the results have been compared with those of another meta-heuristic algorithm, Genetic Algorithm (GA). From the results, it has been observed that for the given problem, the CSGA algorithm not only produces optimal assembly sequences with costs comparable to that of GA, but the convergence of CSGA algorithm has been found to be faster than the GA algorithm.
Robotics offers a flexible automation technology for turning assembly systems into efficient and ... more Robotics offers a flexible automation technology for turning assembly systems into efficient and flexible manufacturing systems. The traditional method of manually generating the task level plan for robotic assembly is very tedious and time consuming. It will be beneficial if the task level planning can be automated. The current paper presents our ongoing research work on developing a knowledge based system to automate the generation of task level plan for robotic assembly. The implementation of the above task level plan has been shown by using a vision assisted robotic assembly system involving a Yaskawa Motoman industrial robot manipulator.
— Micro EDM gained popularity in the field of micro manufacturing due to various advantages likef... more — Micro EDM gained popularity in the field of micro manufacturing due to various advantages likeforce free machining, stringent control over the feature geometry and economical compared to other manufacturing methods. For making the patterns for micro casting and fabrication of 2D/3D micro features on the desired materials, micro EDM can be used instead of lithographic techniques or any other micro fabrication methods. In this paper, the scope of micro EDM for fabrication of micro pillars for collecting and sorting the biological cells, micro channels with micro pillar-structured walls for blood separation devices, injection mold Inserts for fluidic channel are discussed. This paper also presents the evolution of micro EDM in the field of manufacturing arrayed micro-features on metal surfaces, making composite three dimensional microelectrodes and micro-cavities, micro structuring with laminated micro-electrodes on metallic glass, and fabricating hydrophobic and anti-icing surfaces. Preliminary experiments are done to investigate the dimensional accuracy of micro EDM.
— This paper proposes a control method of an underactuated tendon-driven robot hand. The robot ha... more — This paper proposes a control method of an underactuated tendon-driven robot hand. The robot hand consists of a palm and three identical fingers actuated remotely by a tendon and pulley mechanism. One finger has two joints, while the other two fingers have three joints each and the motors are mounted in the palm. All the tendon wires run over the joint pulleys and some routing points inside the finger. The actuation mechanism is underactuated as the number of motors is fewer than the degrees of freedom of the hand. The objective of our work is to design a joint space controller. Joint space controller includes joint position control and joint torque control. Proportional Derivative (PD) feedback control law is used for position control and impedance control law is used for force control. One challenge with the position controller is to ensure positive tension in the tendons at all times. Tension force feedback along with position feedback in impedance controller loop are used to keep positive tension in the tendons. All the control laws are simulated with the three-fingered robot hand model. This work also compares the simulated performance of position controller and impedance controller.
Assembly sequence planning deals with finding the sequence of operations to assemble the componen... more Assembly sequence planning deals with finding the sequence of operations to assemble the components and sub-assemblies into the final product. With advent of Artificial Intelligence, several soft-computing based evolutionary optimisation algorithms had been used by researchers to solve the problem of finding the best feasible assembly sequence. In the proposed paper, an Ant Colony Optimisation (ACO) algorithm based approach has been used for assembly sequence optimisation based on minimizing the number of direction changes, while conforming to the precedence constraints between components. Because of the graph-based nature of ACO, it is relatively less computationally expensive than many of the other soft computing based approaches reported in the literature, and moreover it is also well suited to the nature of the problem on hand. However, the ACO algorithm has a lot of parameters such as rate of pheromone evaporation, pheromone decay parameter, number of iterations, etc. each of which needs to be varied in order to obtain the best convergence rate of the algorithm, Furthermore, the combination of the parameters also needs to be optimised. In the present paper, a binary coded Genetic Algorithm (GA) has been proposed to optimise the parameters of the ACO algorithm. Some of the reasons for choosing GA include the fact that the number of parameters in GA is less than ACO and thus it takes less time and efforts to optimise the GA than ACO. Moreover the modeling of the solutions (i.e. chromosomes) in the form of binary strings is easier. The optimized ACO parameters have been used for solving a problem of assembly sequence optimization for a sixteen component assembly to demonstrate the effectiveness of our proposed meta-optimization procedure.
In the present work, a cuckoo search (CS)-based approach has been developed for scheduling optimi... more In the present work, a cuckoo search (CS)-based approach has been developed for scheduling optimization of a flexible manufacturing system by minimizing the penalty cost due to delay in manufacturing and maximizing the machine utilization time. To demonstrate the application of cuckoo search (CS)-based scheme to find the optimum job, the proposed scheme has been applied with slight modification in its Levy flight operator because of the discrete nature of the solution on a standard FMS scheduling problem containing 43 jobs and 16 machines taken from literature. The CS scheme has been implemented using Matlab, and results have been compared with other soft computing-based optimization approaches like genetic algorithm (GA) and particle swarm optimization found in the literature. The results shown by CS-based approach have been found to outperform the results of existing heuristic algorithms such as GA for the given problem.
One of the important decisions in assembly process planning is determination of assembly sequence... more One of the important decisions in assembly process planning is determination of assembly sequence. Choice of the optimum sequence is made difficult due to various reasons. There are various precedence constraints and optimization criteria. Moreover, a product may be possible to assemble in many alternative ways following different sequences, thus making assembly sequence optimization a multi-modal optimization problem with multiple optimum solutions. It is necessary to generate as many unique optimum solutions as possible in order to allow the process planner to take a decision. Moreover, with increase in part count, the number of feasible sequences rises staggeringly, thereby making assembly sequence optimization laborious and time consuming. Most conventional mathematical algorithms are known to perform poorly when used to obtain multiple optimum solutions. On the other hand, soft computing based evolutionary optimization algorithms are good candidates for multi-modal optimization. Another challenge is to develop an algorithm that can automatically maintain diversity in the optimum solutions found over the generations (i.e. optimum solutions having the same fitness but unique). Keeping the above in mind, in the present paper, an intelligent assembly sequence optimization methodology based on application of flower pollination algorithm (FPA) has been developed to automatically generate multiple unique optimal assembly sequences, subject to various precedence constraints, based on minimisation of number of orientation changes and tool changes. Since in the present paper, FPA has been applied for the first time to a discrete optimization problem like assembly sequence optimization, the main challenge before us in applying FPA was the continuous nature of the original FPA. Therefore, modifications have been made by us in the rules for local and global pollination of FPA to make it suited for solving the given discrete optimization problem. In order to evaluate the performance of FPA, the results have been compared with two other well-known soft computing techniques namely, Genetic Algorithm (GA) and Ant Colony Optimization (ACO) and also with a recently published soft computing based algorithm, Improved Harmony Search (IHS). It was found that the novelty of the proposed FPA lies in its capability to find multiple unique optimum solutions in one single simulation run and capability to automatically maintain diversity in the optimum solutions found over the generations. On the other hand, in case of GA, ACO and IHS, it is not possible to maintain the diversity in multiple optimum solutions as the complete population finally converges to a few unique optimum solutions. Therefore, it can be concluded that FPA performs better in solving the given multi-modal optimization problem of assembly sequence optimization.
Robotic grasping and manipulation require controlling the gripper
movement through different poin... more Robotic grasping and manipulation require controlling the gripper movement through different points in its work volume, necessitating inverse kinematics computations to determine joint angles. In the present work, a novel methodology, based on a radial basis function neural network, has been proposed for the inverse kinematics solution and a genetic algorithm-based approach for optimising the neural network parameters. Instead of taking the entire work volume of the hand for neural network training, a subspace of points is created in close vicinity of the given destination point. The joint variables corresponding to a destination point are obtained using a random walk algorithm that uses the forward kinematics model of the hand. Then, the subspace of points and the corresponding joint variables obtained above are used to train the neural network. This approach can provide an approximate yet fairly quick and effective solution to the inverse kinematics problem of multi-finger robot hands.
In the present paper, an intelligent methodology has been used for assembly tool/gripper selectio... more In the present paper, an intelligent methodology has been used for assembly tool/gripper selection and determination of the optimal assembly sequence. Since it is well known that assembly sequence planning (ASP) is an NP-hard combinatorial optimization problem, in particular, with increase in number of components in the assembly, the computational complexity involved in searching for the optimal assembly sequence in such a large solution space also increases. Furthermore, assembly process planning, tool/gripper selection is also an important decision making task and becomes tedious and time consuming for an assembly with large number of components. Keeping the above in mind, in the present work, a knowledge based system has been developed for selection of assembly tools and grippers for performing the assembly, while a Genetic Algorithm (GA) based approach has been used to determine the feasible and optimal assembly sequences considering minimum number of tool changes and assembly direction changes.
Anatomy of human hand is very complex in nature. The structure of human hand consists of number o... more Anatomy of human hand is very complex in nature. The structure of human hand consists of number of joints, bones, muscles and tendons, which creates a wide range of movements. It is very difficult to design a robotic hand and incorporate all the features of a normal human hand. In this paper, the model of a three finger robotic hand has been proposed. To replace the muscles and tendons of real human hand, it is proposed to use tendon wire and place the actuator at the palm. The advantage of using tendon and placing actuator at remote location is that it actually reduces the size of the hand. Pulling the tendon wire produces flexor motion in the hand finger. Currently torsional spring is considered at the joint for the extension motion of the finger. The purpose of design of such a hand is to grasp different kinds of object shapes. The paper further presents a kinematics model of the three finger hand and a mapping function to map the joint space coordinates to tendon space coordinates. Finally the hand model is simulated to validate the kinematics equations.
Robotic grasping of an object requires positioning the fingers of the robotic hand around the obj... more Robotic grasping of an object requires positioning the fingers of the robotic hand around the object in such a manner that the forces applied by the fingers on the object can create a force as well as moment equilibrium[1] and keep the object stable within the grasp. Research on robotic grasping is relevant too [2]. Recognizing a grasp of an object by a robotic gripper requires a definition of the grasp. In this paper we have compared different definitions of robotic grasp proposedby different researchers and we have proposed our definition of grasp and an algorithmic approach to execute the definition. The results obtained show the promising prospect of the approach.
The paper describes an intelligent ant system-based algorithm for automatic generation of optimal... more The paper describes an intelligent ant system-based algorithm for automatic generation of optimal sequence of machining operations required to produce a part, based on minimising the number of tool changes and set-up changes subject to satisfying all precedence constraints during manufacturing. The MATLAB programme for the algorithm uses a list of machining operations, tool approach directions, and the precedence constraints between the operations as inputs. It generates only feasible sequences of operations and finds out an optimal sequence among them. The concept of specific selection of a starting node at the beginning of each ant cycle and introducing a precedence check in the transition rules reduces the computation time significantly. A comparative study shows that for a demonstration run, the proposed ant system-based approach performed faster than previously developed methodologies for ant colony optimisation as well as a genetic algorithm-based optimisation techniques.
The present paper is aimed at developing an intelligent Computer-Aided Process Planning methodolo... more The present paper is aimed at developing an intelligent Computer-Aided Process Planning methodology based on application of a KBS for automatic generation of process plans for machining. It takes, as input, information about the different machining features present in the part and automatically generates a detailed sequence of machining operations including the precedence constraints, the different machining setups in accordance with the given Tool Approach Directions, the list of operations to be performed within each setup, the locating and clamping faces needed for fixturing the component as well as the setup sequence. To accomplish the above, a set of knowledge based rules have been developed and implemented using an Expert System Shell. The application of the proposed approach has been demonstrated using an example part. By using the proposed approach, it is anticipated, that process planning can be accomplished automatically and quickly by investigating a very limited amount of time making it attractive for applications in industry.
Abstract The research work reported in this thesis is aimed at exploring possible applications of... more Abstract The research work reported in this thesis is aimed at exploring possible applications of different Artificial Intelligence (AI) techniques for automating two of the important decision making tasks in generative Computer-Aided Process Planning (CAPP) systems, namely the selection of machining operations and the set-up planning in the case of rotationally symmetrical parts.
This chapter provides an introduction to intelligent machining. The various computational techniq... more This chapter provides an introduction to intelligent machining. The various computational techniques to achieve the goal of intelligent machining are described. First, a description of neural networks and fuzzy set theory is presented. These are soft computing techniques. Afterwards the application of the finite element method to the machining processes is briefly mentioned. Finally, the optimization of machining processes is described.
The assembly sequence optimization problem is challenging as number of sequences rises staggering... more The assembly sequence optimization problem is challenging as number of sequences rises staggeringly with part count making it combinatorially explosive, tedious and time consuming to solve. A Computer-Aided Process Planning (CAPP) system for robotic assembly by a discrete cuckoo search algorithm has been proposed by us to generate feasible and optimal sequences considering minimization of orientation changes, tool/gripper changes, assembly stability and base component location. A case study and comparison results with an established soft computing approach are presented to show its effectiveness. It is further integrated with an upstream assembly product database to extract information on assembly directions, contact details, assembly precedence constraints and tool/grippers. Further the assembly sequence output from CAPP system is integrated with a robot task planner developed using Knowledge Based System capable of automatically generating executable robot level program for performing the assembly. Keywords: assembly sequence optimization, robot task planning, cuckoo search algorithm, knowledge based system.
In this paper, we have proposed and implemented a methodology for assembly sequence optimization ... more In this paper, we have proposed and implemented a methodology for assembly sequence optimization by using a nature-inspired meta-heuristic algorithm, known as hybrid cuckoo-search genetic algorithm (CSGA) algorithm. The cost criteria for optimization in the present formulation take into consideration the total assembly time and the number of reorientations during the assembly process. To demonstrate the application of the CSGA algorithm, an example assembly containing 19 parts has been presented and the results have been compared with those of another meta-heuristic algorithm, Genetic Algorithm (GA). From the results, it has been observed that for the given problem, the CSGA algorithm not only produces optimal assembly sequences with costs comparable to that of GA, but the convergence of CSGA algorithm has been found to be faster than the GA algorithm.
Robotics offers a flexible automation technology for turning assembly systems into efficient and ... more Robotics offers a flexible automation technology for turning assembly systems into efficient and flexible manufacturing systems. The traditional method of manually generating the task level plan for robotic assembly is very tedious and time consuming. It will be beneficial if the task level planning can be automated. The current paper presents our ongoing research work on developing a knowledge based system to automate the generation of task level plan for robotic assembly. The implementation of the above task level plan has been shown by using a vision assisted robotic assembly system involving a Yaskawa Motoman industrial robot manipulator.
— Micro EDM gained popularity in the field of micro manufacturing due to various advantages likef... more — Micro EDM gained popularity in the field of micro manufacturing due to various advantages likeforce free machining, stringent control over the feature geometry and economical compared to other manufacturing methods. For making the patterns for micro casting and fabrication of 2D/3D micro features on the desired materials, micro EDM can be used instead of lithographic techniques or any other micro fabrication methods. In this paper, the scope of micro EDM for fabrication of micro pillars for collecting and sorting the biological cells, micro channels with micro pillar-structured walls for blood separation devices, injection mold Inserts for fluidic channel are discussed. This paper also presents the evolution of micro EDM in the field of manufacturing arrayed micro-features on metal surfaces, making composite three dimensional microelectrodes and micro-cavities, micro structuring with laminated micro-electrodes on metallic glass, and fabricating hydrophobic and anti-icing surfaces. Preliminary experiments are done to investigate the dimensional accuracy of micro EDM.
— This paper proposes a control method of an underactuated tendon-driven robot hand. The robot ha... more — This paper proposes a control method of an underactuated tendon-driven robot hand. The robot hand consists of a palm and three identical fingers actuated remotely by a tendon and pulley mechanism. One finger has two joints, while the other two fingers have three joints each and the motors are mounted in the palm. All the tendon wires run over the joint pulleys and some routing points inside the finger. The actuation mechanism is underactuated as the number of motors is fewer than the degrees of freedom of the hand. The objective of our work is to design a joint space controller. Joint space controller includes joint position control and joint torque control. Proportional Derivative (PD) feedback control law is used for position control and impedance control law is used for force control. One challenge with the position controller is to ensure positive tension in the tendons at all times. Tension force feedback along with position feedback in impedance controller loop are used to keep positive tension in the tendons. All the control laws are simulated with the three-fingered robot hand model. This work also compares the simulated performance of position controller and impedance controller.
Assembly sequence planning deals with finding the sequence of operations to assemble the componen... more Assembly sequence planning deals with finding the sequence of operations to assemble the components and sub-assemblies into the final product. With advent of Artificial Intelligence, several soft-computing based evolutionary optimisation algorithms had been used by researchers to solve the problem of finding the best feasible assembly sequence. In the proposed paper, an Ant Colony Optimisation (ACO) algorithm based approach has been used for assembly sequence optimisation based on minimizing the number of direction changes, while conforming to the precedence constraints between components. Because of the graph-based nature of ACO, it is relatively less computationally expensive than many of the other soft computing based approaches reported in the literature, and moreover it is also well suited to the nature of the problem on hand. However, the ACO algorithm has a lot of parameters such as rate of pheromone evaporation, pheromone decay parameter, number of iterations, etc. each of which needs to be varied in order to obtain the best convergence rate of the algorithm, Furthermore, the combination of the parameters also needs to be optimised. In the present paper, a binary coded Genetic Algorithm (GA) has been proposed to optimise the parameters of the ACO algorithm. Some of the reasons for choosing GA include the fact that the number of parameters in GA is less than ACO and thus it takes less time and efforts to optimise the GA than ACO. Moreover the modeling of the solutions (i.e. chromosomes) in the form of binary strings is easier. The optimized ACO parameters have been used for solving a problem of assembly sequence optimization for a sixteen component assembly to demonstrate the effectiveness of our proposed meta-optimization procedure.
In the present work, a cuckoo search (CS)-based approach has been developed for scheduling optimi... more In the present work, a cuckoo search (CS)-based approach has been developed for scheduling optimization of a flexible manufacturing system by minimizing the penalty cost due to delay in manufacturing and maximizing the machine utilization time. To demonstrate the application of cuckoo search (CS)-based scheme to find the optimum job, the proposed scheme has been applied with slight modification in its Levy flight operator because of the discrete nature of the solution on a standard FMS scheduling problem containing 43 jobs and 16 machines taken from literature. The CS scheme has been implemented using Matlab, and results have been compared with other soft computing-based optimization approaches like genetic algorithm (GA) and particle swarm optimization found in the literature. The results shown by CS-based approach have been found to outperform the results of existing heuristic algorithms such as GA for the given problem.
One of the important decisions in assembly process planning is determination of assembly sequence... more One of the important decisions in assembly process planning is determination of assembly sequence. Choice of the optimum sequence is made difficult due to various reasons. There are various precedence constraints and optimization criteria. Moreover, a product may be possible to assemble in many alternative ways following different sequences, thus making assembly sequence optimization a multi-modal optimization problem with multiple optimum solutions. It is necessary to generate as many unique optimum solutions as possible in order to allow the process planner to take a decision. Moreover, with increase in part count, the number of feasible sequences rises staggeringly, thereby making assembly sequence optimization laborious and time consuming. Most conventional mathematical algorithms are known to perform poorly when used to obtain multiple optimum solutions. On the other hand, soft computing based evolutionary optimization algorithms are good candidates for multi-modal optimization. Another challenge is to develop an algorithm that can automatically maintain diversity in the optimum solutions found over the generations (i.e. optimum solutions having the same fitness but unique). Keeping the above in mind, in the present paper, an intelligent assembly sequence optimization methodology based on application of flower pollination algorithm (FPA) has been developed to automatically generate multiple unique optimal assembly sequences, subject to various precedence constraints, based on minimisation of number of orientation changes and tool changes. Since in the present paper, FPA has been applied for the first time to a discrete optimization problem like assembly sequence optimization, the main challenge before us in applying FPA was the continuous nature of the original FPA. Therefore, modifications have been made by us in the rules for local and global pollination of FPA to make it suited for solving the given discrete optimization problem. In order to evaluate the performance of FPA, the results have been compared with two other well-known soft computing techniques namely, Genetic Algorithm (GA) and Ant Colony Optimization (ACO) and also with a recently published soft computing based algorithm, Improved Harmony Search (IHS). It was found that the novelty of the proposed FPA lies in its capability to find multiple unique optimum solutions in one single simulation run and capability to automatically maintain diversity in the optimum solutions found over the generations. On the other hand, in case of GA, ACO and IHS, it is not possible to maintain the diversity in multiple optimum solutions as the complete population finally converges to a few unique optimum solutions. Therefore, it can be concluded that FPA performs better in solving the given multi-modal optimization problem of assembly sequence optimization.
Robotic grasping and manipulation require controlling the gripper
movement through different poin... more Robotic grasping and manipulation require controlling the gripper movement through different points in its work volume, necessitating inverse kinematics computations to determine joint angles. In the present work, a novel methodology, based on a radial basis function neural network, has been proposed for the inverse kinematics solution and a genetic algorithm-based approach for optimising the neural network parameters. Instead of taking the entire work volume of the hand for neural network training, a subspace of points is created in close vicinity of the given destination point. The joint variables corresponding to a destination point are obtained using a random walk algorithm that uses the forward kinematics model of the hand. Then, the subspace of points and the corresponding joint variables obtained above are used to train the neural network. This approach can provide an approximate yet fairly quick and effective solution to the inverse kinematics problem of multi-finger robot hands.
In the present paper, an intelligent methodology has been used for assembly tool/gripper selectio... more In the present paper, an intelligent methodology has been used for assembly tool/gripper selection and determination of the optimal assembly sequence. Since it is well known that assembly sequence planning (ASP) is an NP-hard combinatorial optimization problem, in particular, with increase in number of components in the assembly, the computational complexity involved in searching for the optimal assembly sequence in such a large solution space also increases. Furthermore, assembly process planning, tool/gripper selection is also an important decision making task and becomes tedious and time consuming for an assembly with large number of components. Keeping the above in mind, in the present work, a knowledge based system has been developed for selection of assembly tools and grippers for performing the assembly, while a Genetic Algorithm (GA) based approach has been used to determine the feasible and optimal assembly sequences considering minimum number of tool changes and assembly direction changes.
Anatomy of human hand is very complex in nature. The structure of human hand consists of number o... more Anatomy of human hand is very complex in nature. The structure of human hand consists of number of joints, bones, muscles and tendons, which creates a wide range of movements. It is very difficult to design a robotic hand and incorporate all the features of a normal human hand. In this paper, the model of a three finger robotic hand has been proposed. To replace the muscles and tendons of real human hand, it is proposed to use tendon wire and place the actuator at the palm. The advantage of using tendon and placing actuator at remote location is that it actually reduces the size of the hand. Pulling the tendon wire produces flexor motion in the hand finger. Currently torsional spring is considered at the joint for the extension motion of the finger. The purpose of design of such a hand is to grasp different kinds of object shapes. The paper further presents a kinematics model of the three finger hand and a mapping function to map the joint space coordinates to tendon space coordinates. Finally the hand model is simulated to validate the kinematics equations.
Robotic grasping of an object requires positioning the fingers of the robotic hand around the obj... more Robotic grasping of an object requires positioning the fingers of the robotic hand around the object in such a manner that the forces applied by the fingers on the object can create a force as well as moment equilibrium[1] and keep the object stable within the grasp. Research on robotic grasping is relevant too [2]. Recognizing a grasp of an object by a robotic gripper requires a definition of the grasp. In this paper we have compared different definitions of robotic grasp proposedby different researchers and we have proposed our definition of grasp and an algorithmic approach to execute the definition. The results obtained show the promising prospect of the approach.
The paper describes an intelligent ant system-based algorithm for automatic generation of optimal... more The paper describes an intelligent ant system-based algorithm for automatic generation of optimal sequence of machining operations required to produce a part, based on minimising the number of tool changes and set-up changes subject to satisfying all precedence constraints during manufacturing. The MATLAB programme for the algorithm uses a list of machining operations, tool approach directions, and the precedence constraints between the operations as inputs. It generates only feasible sequences of operations and finds out an optimal sequence among them. The concept of specific selection of a starting node at the beginning of each ant cycle and introducing a precedence check in the transition rules reduces the computation time significantly. A comparative study shows that for a demonstration run, the proposed ant system-based approach performed faster than previously developed methodologies for ant colony optimisation as well as a genetic algorithm-based optimisation techniques.
The present paper is aimed at developing an intelligent Computer-Aided Process Planning methodolo... more The present paper is aimed at developing an intelligent Computer-Aided Process Planning methodology based on application of a KBS for automatic generation of process plans for machining. It takes, as input, information about the different machining features present in the part and automatically generates a detailed sequence of machining operations including the precedence constraints, the different machining setups in accordance with the given Tool Approach Directions, the list of operations to be performed within each setup, the locating and clamping faces needed for fixturing the component as well as the setup sequence. To accomplish the above, a set of knowledge based rules have been developed and implemented using an Expert System Shell. The application of the proposed approach has been demonstrated using an example part. By using the proposed approach, it is anticipated, that process planning can be accomplished automatically and quickly by investigating a very limited amount of time making it attractive for applications in industry.
Abstract The research work reported in this thesis is aimed at exploring possible applications of... more Abstract The research work reported in this thesis is aimed at exploring possible applications of different Artificial Intelligence (AI) techniques for automating two of the important decision making tasks in generative Computer-Aided Process Planning (CAPP) systems, namely the selection of machining operations and the set-up planning in the case of rotationally symmetrical parts.
Design of membership grades for a fuzzy set based inference system is an important issue. Conside... more Design of membership grades for a fuzzy set based inference system is an important issue. Considering that the knowledge of an expert is available for the initial estimates of a fuzzy parameter, a methodology is proposed for fine tuning these estimates to enhance the performance of a fuzzy set based system. The proposed methodology combines the best of an expert's knowledge and available experimental data to predict the membership grades of fuzzy parameters. Criteria considered for the optimal membership grades are the accuracy of solution and minimum violation of expert's opinion. The proposed methodology is applied in the estimation of burr height in drilling holes. It is observed that the fine tuned values of membership grades for fuzzy input parameters give better matching of predicted and observed burr height than the initial membership grades provided by expert. Fine tuning of the initial expert's estimates enhances the performance of the burr height prediction. The methodology is suitable 1 Journal of Manufacturing Technology Research, 2012, vol 4(1/2)
Uploads
Books by Deb Sankha
Papers by Deb Sankha
movement through different points in its work volume, necessitating inverse
kinematics computations to determine joint angles. In the present work, a novel
methodology, based on a radial basis function neural network, has been
proposed for the inverse kinematics solution and a genetic algorithm-based
approach for optimising the neural network parameters. Instead of taking the
entire work volume of the hand for neural network training, a subspace of
points is created in close vicinity of the given destination point. The joint
variables corresponding to a destination point are obtained using a random
walk algorithm that uses the forward kinematics model of the hand. Then, the
subspace of points and the corresponding joint variables obtained above are
used to train the neural network. This approach can provide an approximate
yet fairly quick and effective solution to the inverse kinematics problem of
multi-finger robot hands.
movement through different points in its work volume, necessitating inverse
kinematics computations to determine joint angles. In the present work, a novel
methodology, based on a radial basis function neural network, has been
proposed for the inverse kinematics solution and a genetic algorithm-based
approach for optimising the neural network parameters. Instead of taking the
entire work volume of the hand for neural network training, a subspace of
points is created in close vicinity of the given destination point. The joint
variables corresponding to a destination point are obtained using a random
walk algorithm that uses the forward kinematics model of the hand. Then, the
subspace of points and the corresponding joint variables obtained above are
used to train the neural network. This approach can provide an approximate
yet fairly quick and effective solution to the inverse kinematics problem of
multi-finger robot hands.