In order to reduce the uncertainty of the genetic algorithm (GA) in optimizing the near-infrared spectral calibration model and avoid the loss of spectral information of the unselected variables, a strategy of fusing consensus models is proposed to measure the soluble solids content (SSC) in peaches. A total of 266 peach samples were collected at four arrivals, and their interactance spectra were scanned by an integrated analyzer prototype, and then an internal index of SSC was destructively measured by the standard refractometry method. The near-infrared spectra were pre-processed with mean centering and were selected successively with a genetic algorithm (GA) to construct the consensus model, which was integrated with two member models with optimized weightings. One was the conventional partial least square (PLS) optimized with GA selected variables (PLS_GA), and the other one was the derived PLS developed with residual variables after GA selections (PLS_RV). The performance of PLS_RV models showed some useful spectral information related to peaches’ SSC and someone performed close to the full-spectral-based PLS model. Among these 10 runs, consensus models obtained a lower root mean squared errors of prediction (RMSEP), with an average of 1.106% and standard deviation (SD) of 0.0068, and performed better than that of the optimized PLS_GA models, which achieved a RMSEP of average 1.116% with SD of 0.0097. It can be concluded that the application of fusion strategy can reduce the fluctuation uncertainty of a model optimized by genetic algorithm, fulfill the utilization of the spectral information amount, and realize the rapid detection of the internal quality of the peach.

Total soluble solids (TSSs) serve as a crucial maturity indicator and quality determinant in apricots, influencing harvest timing and postharvest management decisions. This study develops an advanced framework integrating adaptive boosting (Adaboost) ensemble learning with high-frequency spectral variables selected by uninformative variable elimination (UVE) for the rapid non-destructive detection of fruit quality. Near-infrared (NIR) spectra (1000~2500 nm) were acquired and then preprocessed through robust principal component analysis (ROBPCA) for outlier detection combined with z-score normalization for spectral pretreatment. Subsequent data processes included three steps: (1) 100 continuous runs of UVE identified characteristic wavelengths, which were classified into three levels—high-frequency (≥90 times), medium-frequency (30–90 times), and low-frequency (≤30 times) subsets; (2) the development of the base optimal partial least squares regression (PLSR) models for each wavelength subset; and (3) the execution of adaptive weight optimization through the Adaboost ensemble algorithm. The experimental findings revealed the following: (1) The model established based on high-frequency wavelengths outperformed both full-spectrum model and full-characteristic wavelength model. (2) The optimized UVE-PLS-Adaboost model achieved the peak performance (R = 0.889, RMSEP = 1.267, MAE = 0.994). This research shows that the UVE-Adaboost fusion method enhances model prediction accuracy and generalization ability through multi-dimensional feature optimization and model weight allocation. The proposed framework enables the rapid, non-destructive detection of apricot TSSs and provides a reference for the quality evaluation of other fruits in agricultural applications.

Accurate assessment of the aging state of transformer oil-barrier insulation is crucial for ensuring the safe and reliable operation of power systems. This study presents the development of indoor accelerated thermal aging experiments to simulate the degradation of oil-immersed barrier insulation within transformers. A series of samples reflecting various aging states was obtained and categorized into six distinct groups. Raman spectroscopy analytical technology was employed to characterize the information indicative of different aging states of the oil-immersed barrier insulation. The raw Raman spectra were processed using asymmetric reweighted penalty least squares to correct baseline shifts, Savitzky–Golay (S-G) smoothing to eliminate fluctuation noise, and principal component analysis (PCA) to reduce data dimensionality by extracting principal components. A support vector machine (SVM) classifier was developed to discriminate between the Raman spectra and category labels. The SVM parameters were optimized using grid search, particle swarm optimization (PSO), and genetic algorithm (GA), yielding the optimal parameters (C and gamma). Notably, the grid search method demonstrated high efficiency in identifying the best combination of SVM parameters (c and g). Comparative analyses with varying numbers of principal components in SVM classifiers revealed that incorporating an optimal subset of PCA features achieved the highest classification accuracy of 94.44% for external validation samples, with only eight samples being misclassified into adjacent categories. This study offers technical support and a theoretical foundation for the effective assessment of the aging state of oil-barrier type insulation in transformers, contributing to the advancement of condition monitoring and maintenance strategies in power systems.