Abstract: A virtual metrology method using a convolutional neural network (CNN) is provided. In this method, a dynamic time warping (DTW) algorithm is used to delete unsimilar sets of process data, and adjust the sets of process data to be of the same length, thereby enabling the CNN to be used for virtual metrology. A virtual metrology model of the embodiments of the present invention includes several CNN models and a conjecture model, in which plural inputs of the CNN model are sets of time sequence data of respective parameters, and plural outputs of the CNN models are inputs to the conjecture model.

Abstract: A secure power-saving hard disk storage system and method having a plurality of storage units and a control unit connected to an external controller. The system detects and checks information of installation of each storage unit and control unit, driving program and format stored at the control end while executing installation. During storage selection, the storage unit selected to execute data access is conducted with a power source via an electronic switch of the control unit to activate data transmission connection. The activated storage unit then executes data access according to store or read command input from the control end. When the storage unit is no longer in use, the power source is switched to improve synchronous conduction, power consumption, high noise and greenhouse effect of high temperature generated thereby.