The tomography technique is an effective way to quantitatively evaluate damage from reconstruction imaging in structure health monitoring (SHM). The reconstruction algorithm for the probabilistic inspection of damage (RAPID) algorithm based on the signal difference coefficient (SDC) feature is a promising approach due to its superior performance. This paper focuses on the influence of different patterns of PZT (Lead Zirconate Titanate) sensor array configurations, i.e., the circular, square, and parallel array, on reconstruction image qualities for evaluating hole and crack damage. Variable shape parameters are applied to account for the unequal damage distances of different actuator-sensor pairs. Considering the directionality scattering fields of cracks, the angular scattering pattern of the SDC values are studied by simulation. The SDC variations for different groups of sensing paths at the same actuator are applied to predict the crack orientation. An improved RAPID algorithm is proposed by defining an additional SDC value of 1 in the path along the predicted crack orientation, which is determined by the point of the actuator causing the minimal SDC variation and the center point of the initial reconstruction image of the crack. The results show that the improved RAPID algorithm is effective for the evaluation of crack damage. Reconstruction image qualities with three PZT sensor array configurations for both holes and cracks are compared. The research is significant for selecting the PZT sensor array configuration in SHM.

The helicopter tail drive shaft is vulnerable to failure from projectile impacts during low-altitude flight. Stress wave-based inversion of impact parameters and quantitative damage assessment remain insufficiently explored. To address small-sample and nonlinear challenges, a framework based on stress wave characteristics and physics-guided hierarchical Gaussian process regression is proposed. Four key features, namely first-arrival wave trough amplitude, frequency standard deviation, ratio of low-frequency to high-frequency root mean square, and wavelet energy entropy, are extracted from transient signals to construct a hierarchical progressive architecture for damage mode discrimination, parameter inversion, and quantitative assessment. Perforation is identified using a wavelet energy entropy-based adaptive threshold. Incidence angle inversion is achieved by an adaptive composite kernel and Bayesian physical prior correction. Damage degree is assessed through residual learning guided by a physical prior surface mean function. Results show an incidence angle inversion root mean square error (RMSE) of 3.02°, with entry and exit hole equivalent failure area RMSEs of 13.32 mm² and 12.98 mm², respectively. The 95% prediction interval maintained reliable coverage across the validation samples. This framework provides a new method with both physical interpretability and uncertainty quantification for the assessment of impact damage in thin-walled tube structures.