The existing Fault Detection and Diagnosis (FDD) model of chillers requires considerable normal and fault data. The acquisition of these data is time-consuming and expensive, and the model is only suitable for special units, which makes it difficult to popularize FDD technology in the operation and management of chillers. At present, a 120-ton chiller has only a small amount of normal and fault data compared with the abundant data of a 200-ton model of the same series. This study investigates the FDD model of a 120-ton chiller and considers similar characteristics of the refrigeration cycle of the same series of chillers. A training set can be created using the 200-ton prior-knowledge data and 120-ton. However, this training set is imbalanced, and the common imbalanced processing Synthetic Minority Oversampling Technique (SMOTE) synthesis mechanism has an overlap problem. This study adopts two adaptive imbalance processing technologies called the Adaptive Synthetic Sampling Approach (ADASYN) and Borderline SMOTE (BSM) that can solve the imbalance problem and SMOTE oversampling overlap problem during knowledge transfer. A support vector machine FDD model with 100%–400% oversampling ratios is established. The best model is ADASYN under 100% oversampling ratio, with a diagnostic accuracy rate of 94.33%.
28 January 2023 in Journal of Analytical and Applied Pyrolysis
How to protect acquired images plays a significant role in power internet of things (PIoT). The semi-fragile watermark can be introduced into PIoT to authenticate the integrity of PIoT color images. A semi-fragile restorable watermarking technology based on weight-function on modulo operations is presented. First, the watermarking embedding is implemented at the end-device of PIoT. The 11-bit recovery watermark of each block in YUV components is generated by the significant coefficients. Using this weight-function on modulo operations, the recovery watermark is embedded by modulating 7 quantized coefficients. The steps of authentication and recovery requiring large computation resource are implemented in the cloud data center of PIoT. The tampered blocks are localized and restored by the interpolation and inpainting methods with the extracted recovery watermark. Experimental results on actual PIoT color images prove that higher invisibility can be achieved and this method detects tampered regions with a better performance.
21 April 2025 in Journal of Environmental Chemical Engineering
1. Achieving low-carbon production by reducing CO2 emissions has\ become a major focus for society under the national dual carbon goals (Qi et al. 2023; Tong, Hy, and Jb 2022). As a cornerstone of ...