After analyzing the influencing factors of flexible workpiece path(FWP) process deformation, this article proposes the basic conception of process deformation intelligent forecasting and compensation, start from the process modeling method of Takagi-Sugeno fuzzy neural network, to modify the classic FNN model and construct the multiple input/output TS-FNN model for FWP process control; with LMS law and steepest descent method, antecedent network membership function parameter adjustment and descent network parameter study method of TS-FNN model is deduced; finally to carry on comprehensive simulation on TS-FNN model, the result shows the constructed model is better than BP neural network and RBF neural network for an order of magnitude on predication accuracy; in the quilting process of flexible objects, compensated by TS-FNN, the path processing obtains good approaching effect, testing result indicates that the position error scope of quilting is from 0.078 to 0.162(mm), the accuracy is higher than excellence grade of quilting which refers to national standard FZ/T81005-2006.

On the basis of analysis of research on embedded soft hardware collaborative design method, image processing SOPC collaborative design principle is elaborated, relation between complicated algorithm time and soft hardware implementation and the implementation method to accelerate algorithm by multi-processor and multi-core is studied, thus the logical relationship between equipment IP core on the chip with Fast Simplex Link(FSL) bus and bus bridge, connecting conditions and application flow is organized. Finally, design SOPC, for which, multi-core and multi-processor collaborative work with the core of PowerPC 405 processor by taking flexible workpiece path (FWP) image as an example. The test manifests that the computation speed of SOPC designed in this passage is higher 10 times than that of common single-core SOPC in terms of image processing computing, effectively solving the problem of slow speed for computing image preprocessing by software in the embedded system.