Intelligent manufacturing system of impeller for computer numerical control(CNC) programming based on KBE

To solve the problem of advanced digital manufacturing technology in the practical application, a knowledge engineering technology was introduced into the computer numerical control(CNC) programming. The knowledge acquisition, knowledge representation and reasoning used in CNC programming were researched. The CNC programming system functional architecture of impeller parts based on knowledge based engineering(KBE) was constructed. The structural model of the general knowledge-based system(KBS) was also constructed. The KBS of CNC programming system was established through synthesizing database technology and knowledge base theory. And in the context of corporate needs, based on the knowledge-driven manufacturing platform(i.e. UG CAD/CAM), VC++6.0 and UG/Open, the KBS and UG CAD/CAM were integrated seamlessly and the intelligent CNC programming KBE system for the impeller parts was developed by integrating KBE and UG CAD/CAM system. A method to establish standard process templates was proposed, so as to develop the intelligent CNC programming system in which CNC machining process and process parameters were standardized by using this KBE system. For the impeller parts processing, the method applied in the development of the prototype system is proven to be viable, feasible and practical.

VTensor:Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework

Tensors are a popular programming interface for developing artificial intelligence(AI)algorithms.Layout refers to the order of placing tensor data in the memory and will affect performance by affecting data locality;therefore the deep neural network library has a convention on the layout.Since AI applications can use arbitrary layouts,and existing AI systems do not provide programming abstractions to shield the layout conventions of libraries,operator developers need to write a lot of layout-related code,which reduces the efficiency of integrating new libraries or developing new operators.Furthermore,the developer assigns the layout conversion operation to the internal operator to deal with the uncertainty of the input layout,thus losing the opportunity for layout optimization.Based on the idea of polymorphism,we propose a layout-agnostic virtual tensor programming interface,namely the VTensor framework,which enables developers to write new operators without caring about the underlying physical layout of tensors.In addition,the VTensor framework performs global layout inference at runtime to transparently resolve the required layout of virtual tensors,and runtime layout-oriented optimizations to globally minimize the number of layout transformation operations.Experimental results demonstrate that with VTensor,developers can avoid writing layout-dependent code.Compared with TensorFlow,for the 16 operations used in 12 popular networks,VTensor can reduce the lines of code(LOC)of writing a new operation by 47.82%on average,and improve the overall performance by 18.65%on average.