Early-life cycle-life prediction for lithium-ion batteries—estimating end-of-life from initial cycles—is valuable for rapid cell screening and battery health management. We investigate whether an explicit correlation-structure descriptor can complement physics-informed ΔQ-based indicators and generic early-cycle statistical features on the Severson 124-cell benchmark. We develop a lightweight hybrid framework that combines ΔQ-based health indicators, data-driven statistical features, and Laplacian Eigenmaps embeddings derived from a Pearson-correlation feature graph, with XGBoost used as the predictor. Across five feature configurations (ΔQ Only, ΔQ + Statistics, Hybrid Append, VIF + Laplacian, and Integrated Laplacian), we evaluate pointwise regression accuracy using RMSE and R² together with PHM-style error-band measures RA@0.2, PH@0.1, and α-λ(0.15), computed on implied RUL trajectories induced by the early-life cycle-life estimate. On the Primary test domain, all four non-baseline configurations improved over ΔQ Only; Integrated Laplacian achieved the strongest RMSE/R² pair (97.00 cycles, 0.8215), while Hybrid Append remained competitive (102.28 cycles, 0.8016) and improved RA@0.2 and PH@0.1 relative to ΔQ + Statistics. On the shifted Secondary domain, ΔQ Only gave the most favorable RMSE/R² pair (267.82 cycles, 0.2275), whereas Hybrid Append and VIF + Laplacian improved selected error-band metrics. In an additional comparison against PCA, Random Projection, and Truncated SVD conducted at a matched 79-feature scale, with all transforms estimated from the training cells only, the graph-derived embedding remained competitive, but its margin over simpler reductions varied across splits. Taken together, these results support Hybrid Append as the main appended-structure configuration in this study, while indicating that the benefit of the correlation-structure descriptor is more visible in selected PHM-style error-band metrics than in uniformly improved pointwise accuracy.

Nondestructive testing (NDT) methods such as visual inspection and ultrasonic testing are widely applied in manufacturing quality control, but they remain limited in their ability to detect defect characteristics. Visual inspection depends strongly on operator experience, while ultrasonic testing requires physical contact and stable coupling conditions that are difficult to maintain in production lines. These constraints become more pronounced when defect-related information is scarce or when background noise interferes with signal acquisition in manufacturing processes. This study presents a non-contact acoustic method for diagnosing defects in scroll compressors during the manufacturing process. The diagnostic approach leverages Mel-frequency cepstral coefficients (MFCC), and short-time Fourier transform (STFT) parameters to capture the rotational frequency and harmonic characteristics of the scroll compressor. These parameters enable the extraction of defect-related features even in the presence of background noise. A convolutional neural network (CNN) model was constructed using MFCCs and spectrograms as image inputs. The proposed method was validated using acoustic data collected from compressors operated at a fixed rotational speed under real manufacturing process. The method identified normal operation and three defect types. These results demonstrate the applicability of this method in noise-prone manufacturing environments and suggest its potential for improving product quality, manufacturing reliability and productivity.