We present a new neural velocity force control scheme for a 6 DOF industrial manipulator ensuring tracking of end effector positions along unconstrained directions and tracking of contact force along the constrained direction to significantly expand the range of manipulator applications. Neural velocity force control is actually feasible even in the case of an extreme stiff environment, which is a quite common situation in industrial applications. A cascaded velocity controller (CVC) ensures the precise approach with a tender impact to the unknown surface. The neural controller is of inverse dynamics type with a force feedforward action and performs an adaptive computation of the inverse manipulator model. Simulation results for a 6 DOF industrial manipulator are reported and show the convenience of the approach for demanding tasks like dismantling or surface tracking inclusive establishing contact to rigid objects with precisely bounded impact forces1.

We developed a novel approach for surface tracking and force/position control based on neural networks. A new concept of neural trajectory optimization NTO will be presented as a part of the neural force/position control NFC and as a very capable and versatile tool for the generation of natural manipulator movements (fast, flexible and smooth). The NTO concept is based on DRBF neural networks, an extension of the RBF type network, to be proposed in this paper. Experimental results of the realtime implementation of NTO and simulation results of its combination with the neural force/position control NFC will be presented. As a testbed we use a 6 DOF industrial manipulator executing demanding tasks such as surface tracking with defined normal force.1

In order to apply intelligent robot control to complex force/position tasks, we developed a novel concept for force/position control based on neural networks (NN). A neural dynamic net (NDN) contains a neural computed torque controller, which delivers a precise mapping of the inverse model of the real manipulator. Specifically, the mapping considers different types of nonlinear properties, which are essential for this type of control, but are hard to model analytically. Furthermore the inverse kinematics is represented by a neural kinematics network (NKN), which includes strategies for avoidance of singularities, self-collisions, and conflicts with workspace constraints. This neural control approach has been tested in simulations and will be applied to a 6 DOF industrial manipulator to various demanding tasks including screw removal and surface tracking with constant normal force.

We present a novel control concept that solves a wide range of surface tracking tasks for manipulators with defined contact to (moving) rigid objects. The position based neural force control (NFC-P) consists of a hybrid force/position controller that accurately generates contact forces to objects with arbitrary flexibility and uncertain distance or shape. NFC-P performs force control by modifying the desired joint angle changes in force direction. These are fed into a computed torque controller, where the inverse dynamics of the manipulator is represented by neural networks. NFC-P includes a neural trajectory generating tool for smooth and kinematical valid contact trajectories with the possibility to adapt the trajectories to the unknown shape of the surface online. The kinematical mappings guarantee singularity robustness (SR) in the entire workspace. Results from real-time experiments are presented using a 6-DOF industrial manipulator as testbed

We present a novel type of friction estimation applied to the field of sensorless force/position control. As part of a position based neural force control (NFC-P) the estimation friction and external force allows a force/position control without using a force sensor. NFC-P consists of a hybrid force/position controller that accurately generates contact forces to objects with arbitrary flexibility and uncertain distance or shape. NFC-P performs force control by modifying the desired joint angle changes in force direction before they are fed into a computed torque controller. The inverse dynamics of the manipulator is modeled in a computed torque controller. Kinematic mappings guarantee singularity robustness in the entire workspace. Results from real time experiments are presented with a 6-DOF industrial manipulator as a testbed.

We present a new method of neural friction compensation in manipulator control, especially during dynamic tasks with defined contact to external environment. Such manipulator movements involve internal joint friction and external friction between tool and environment. The suggested method compensates friction caused disturbances by means of neural networks. Based on a minimal friction model Lyapunov stability theory is used to gain a stable learning rule for Radial-Basis-Function (RBF) neural networks. This novel compensation method is of particular importance in force/position control for slow movements, in which static friction and stick-slip friction are the foremost effects of disturbance. We implemented this method in a real time control of an 6 DOF industrial manipulator (Siemens manutec r2). Results from experiments are presented. Using additional RBF networks to adapt to different kinds of effects (e.g. mass coupling gravitation, load mass), this algorithm can easily be extended to unknown manipulators.

We present a new design of hybrid force/position control NVFC capable of friction-compensation, which is a mandatory requirement in industrial applications for precise tracking of hard surfaces with desired contact force. The control architecture consists of an outer-loop velocity controller and an inner-loop adaptive hybrid force/position controller, which compensates the friction of the manipulators joints, significantly improving the force tracking performance during slow movements. The cascaded velocity controller ensures the precise approach during neural force/position control with a reduced bounce into the unknown surface, which is a demanding requirement for tasks like deburring or chamfering. The resulting performance of the force control system is illustrated in simulations, and is consistent with velocity/force control experiments on a 6-DOF industrial manipulator controlled with a PC-based real-time control system

We developed a novel concept of hybrid force/position control based on neural networks (NFC) to significantly expand the range of manipulator applications. NFC includes neural approaches for complex robotic mappings such as inverse dynamics and kinematics. The neural dynamics network, as an essential component of the computed torque controller, performs a fast and adaptive computation of the inverse manipulator model. The kinematic mappings are represented by a neural kinematics network (NKN). The features of NKN provide singularity robustness and the handling of constraints in joint space and Cartesian space. To guarantee a tender impact while establishing contact between manipulator and surface, a cascaded velocity controller is added to the NFC approach. Simulations for a 6-DOF industrial manipulator have proved that the NFC concept is capable to manage various demanding tasks such as screw removal and surface tracking with high accuracy

Summary The ASTEC CPA module was validated by performing simulations of transients in systems of different scales: the Phebus containment, the KAEVER vessel, the Battelle Model Containment, the LACE facility and the VVER-1000 NPP containment. The physical parameters of interest are those that describe thermal-hydraulic and aerosol phenomena. The results of the simulations in the first four facilities were compared with experimental results, whereas the calculated results of the simulated accident in the VVER-1000 containment were compared to results, obtained with the MELCOR code. In the present work, the main results from the performed validations are described and illustrated with some comparisons of calculated variables with reference data. A. INTRODUCTION Activities on the validation of the ASTEC V1.2 CPA (Containment Part of ASTEC) module concern the modeling of thermal-hydraulic as well as aerosol and fission product phenomena. For this purpose, simulations are being carried out of transients in containment systems of different scales. The module is being validated by comparing simulation results with experimental data, as well as with results obtained with other established severe accident codes that were validated more extensively. Although this last option cannot be considered as a genuine validation, a concordance of simulation results still supports the validity of the tested physical models. In the present work, recent validation activities of the CPA module are presented. Transients in experimental and real systems of different scale were simulated. The Phebus containment vessel and the KAEVER vessel may be considered as small-scale experimental containment facilities, whereas the LACE facility and the Battelle Model Containment may be considered as large-scale facilities. Experimental data obtained in facilities are suitable for validation of the modeling of containment thermal-hydraulics and aerosol phenomena. To validate the CPA module in a real-scale system, a hypothetical accident scenario in a VVER- 1000 NPP containment was simulated, and the results were compared to simulation results obtained with the severe accident MELCOR code. The comparison of results provides a general overview of the current abilities and deficiencies of the ASTEC CPA module.