In turning, tool wear and cutting vibration are inevitable, which have great influence on surface quality. Analyzing the influence mechanism of tool wear and cutting vibration on surface quality is important to achieve the accurate prediction of surface roughness before machining and improve machining quality. In this paper, a turning vibration experiment is conducted to reveal that the diameter of shafts is an important factor affecting the vibration amplitude and frequency. In addition, based on machining parameters, tool wear and workpiece diameter, this empirical model, the response surface method and a support vector machine are used to model and predict surface roughness. The fitting accuracy, prediction accuracy and generalization performance of the proposed methods are compared in detail. The results show that the response surface modeling method has the highest fitting accuracy, but the exponential empirical modeling method has the highest prediction accuracy and best generalization performance. Additionally, the prediction results indicate that the surface roughness increases with the increase in tool wear and decreases with the increase in workpiece diameter.

High-fidelity acquisition of canopy phenotypic data is critical for the advancement of orchard Artificial Intelligence (AI). Yet, an improper Light Detection and Ranging (LiDAR) installation height (IH) frequently induces data occlusion and substantial measurement errors. To address this limitation, this study developed an information collection vehicle (ICV) integrated with a 16-channel three-dimensional (3D) LiDAR to determine the optimal LiDAR IH. Three representative LiDAR IHs (1.4 m, 2.0 m, and 2.6 m) were evaluated on spindle-shaped cherry trees under both forward and reverse driving strategies. Subsequently, a novel 12-zone refined evaluation framework was introduced to quantify localized errors that are conventionally obscured by traditional whole-canopy metrics. Results demonstrated a profound nonlinear relationship between IH and measurement accuracy. Specifically, the 2.0 m IH (approximating the canopy’s geometric center) emerged as the optimal setup, maintaining relative errors (REs) below 5% with minimal dispersion. Conversely, the 2.6 m IH caused lower-canopy volume REs to surge beyond 16% owing to restricted downward viewing angles. Additionally, reverse driving at higher IHs exacerbated mechanical vibrations via the “lever arm effect”, thereby significantly degrading point cloud registration accuracy. Ultimately, these findings underscore the critical necessity of aligning sensors with the canopy geometric center, supplying essential theoretical guidelines for the hardware design of future orchard robots.