Abstract: A cutting fluid digital monitoring and management system and method are provided, applicable to a computer numerical control (CNC) machining device. The CNC machining device has a cutting fluid tank configured to accommodate a cutting fluid. The cutting fluid digital monitoring and management system includes: a detection tank, configured to extract a cutting fluid from the cutting fluid tank through a motor and an electrically controlled water valve; a concentration sensing module, a pH sensing module, a water hardness sensing module, and a temperature sensing module, respectively configured to obtain a concentration, a pH value, a hardness, and a temperature of the cutting fluid; a processing module, configured to generate a monitoring integration value, compare the monitoring integration value with a standard model, and generate an adjustment signal; and an adjustment module, configured to actively adjust a variable parameter of the cutting fluid according to the adjustment signal.

Abstract: A power supply health check system for checking a health state of an under-test power supply is provided. The under-test power supply supplies power to a main board which has a voltage signal during operation. The health check system includes a detecting module, a deep learning model, and a processing unit. The detecting module is electrically connected to the main board to detect the voltage signal and convert the voltage signal into a digital signal. The deep learning model is established by using frequency-domain voltage data of a plurality of healthy power. The processing unit is configured to: collect the digital signal and store the digital signal as under-test time-domain voltage data; convert the under-test time-domain voltage data into under-test frequency-domain voltage data; and calculate, based on the under-test frequency-domain voltage data and the deep learning model, a health indicator for determining the health state of the under-test power supply.

Abstract: A signal abnormality detection system and a method thereof are provided. The signal abnormality detection system includes a signal sensor and a computing device. The signal sensor generates a sample signal to be tested through sensing. The computing device is signal-connected to the signal sensor to receive the sample signal to be tested, perform a correction on the sample signal to be tested, and perform a time-frequency transform on a one-dimensional signal generated after the correction to generate a two-dimensional time-frequency signal. The computing device reconstructs the two-dimensional time-frequency signal by using an abnormality detection model to calculate a reconstructed difference value. The computing device performs comparison to determine whether the reconstructed difference value is greater than a detection threshold to determine whether the sample signal to be tested is an abnormal sample.

Abstract: An automated optical inspection method, an automated optical inspection system, and a storage medium are provided. The method includes the following. An original image including first images of a target object is captured by an optical lens. An edge detection is performed on the original image to obtain an edge image including second images having an edge pattern. At least one of maximum, minimum, and average values of a pixel value in the second images is calculated. The edge image is divided into image blocks according to a unit area, and characteristic values are calculated according to the at least one of the maximum, minimum, and average values corresponding to the second images included in the image blocks. An optimal regression model is obtained by training a regression model corresponding to a defect of the target object according to the characteristic values and a data of the target object.

Abstract: A solar cell wafer is provided. It is a silicon wafer, and a surface of the silicon wafer has a plurality of pores, wherein based on a total amount of 100% of the plurality of pores, 60% or more of the pores has a circularity greater than 0.5. Therefore, the reflectance of the solar cell wafer can be efficiently reduced.