SoC-based Software-Hardware codesign of intelligent diagnosis

This study develops and implements a SoC-based HW/SW (Hardware-Software) codesign for an intelligent diagnostic system. To improve the efficiency of the VLSI (Very Large Scale Integration) design process, the components of the intelligent diagnostic system are designed in the form of SIP (Silicon Intellectual Property) modules. The SIP modules, including the CPU module, the GPIO (General Purpose I/O) module and the NN (Neural Network) module, are then integrated to form the complete intelligent diagnostic system. In constructing the system, an embedded processor is employed to run software programs. In addition to integrating the hardware architecture, this study also develops application software, comprising a bootloader, a UARTcomm module and a main program for human-machine interface, to drive the embedded processor. The SoC-based HW/SW codesign method employed in this study increases the efficiency of the system design process and reduces the rebuild time. The results of the experimental trials verify the successful performance of the developed intelligent diagnostic system.