IMPROVE THE KINETIC PERFORMANCE OF THE PUMP CONTROLLED CLAMPING UNIT IN PLASTIC INJECTION MOLDING MACHINE WITH ADAPTIVE CONTROL STRATEGY

The kinetic characteristics of the clamping unit of plastic injection molding machine that is controlled by close loop with newly developed double speed variable pump unit are investigated. Considering the wide variation of the cylinder equivalent mass caused by the transmission ratio of clamping unit and the severe instantaneous impact force acted on the cylinder during the mold closing and opening process, an adaptive control principle of parameter and structure is proposed to improve its kinetic performance. The adaptive correlation between the acceleration feedback gain and the variable mass is derived. The pressure differential feedback is introduced to improve the dynamic performance in the case of small inertia and heavy impact load. The adaptation of sum pressure to load is used to reduce the energy loss of the system. The research results are verified by the simulation and experiment, The investigation method and the conclusions are also suitable for the differential cylinder system controlled by the traditional servo pump unit.

Deep Learning Applied to Computational Mechanics:A Comprehensive Review,State of the Art,and the Classics

Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.

Energy saving design of the machining unit of hobbing machine tool with integrated optimization

The machining unit of hobbing machine tool accounts for a large portion of the energy consumption during the operating phase.The optimization design is a practical means of energy saving and can reduce energy consumption essentially.However,this issue has rarely been discussed in depth in previous research.A comprehensive function of energy consumption of the machining unit is built to address this problem.Surrogate models are established by using effective fitting methods.An integrated optimization model for reducing tool displacement and energy consumption is developed on the basis of the energy consumption function and surrogate models,and the parameters of the motor and structure are considered simultaneously.Results show that the energy consumption and tool displacement of the machining unit are reduced,indicating that energy saving is achieved and the machining accuracy is guaranteed.The influence of optimization variables on the objectives is analyzed to inform the design.