Combine harvesters, as essential equipment in agricultural engineering, frequently experience structural faults due to their complex structure and harsh working conditions, which severely affect their reliability and operational efficiency, leading to significant downtime and reduced agricultural productivity during critical harvesting periods. Therefore, developing accurate and timely Fault Detection and Diagnosis (FDD) techniques is crucial for ensuring food security. This paper provides a systematic and critical review and analysis of the latest advancements in research on data-driven FDD methods for structural faults in combine harvesters. First, it outlines the typical structural sections of combine harvesters and their common structural fault types. Subsequently, it details the core steps of data-driven methods, including the acquisition of operational data from various sensors (e.g., vibration, acoustic, strain), signal preprocessing methods, signal processing and feature extraction techniques covering time-domain, frequency-domain, time–frequency domain combination, and modal analysis among others, and the use of machine learning and artificial intelligence models for fault pattern learning and diagnosis. Furthermore, it explores the required system and technical support for implementing such data-driven FDD methods, such as the applications of on-board diagnostic units, remote monitoring platforms, and simulation modeling. It provides an in-depth analysis of the key challenges currently encountered in this field, including difficulties in data acquisition, signal complexity, and insufficient model robustness, and consequently proposes future research directions, aiming to provide insights for the development of intelligent maintenance and efficient and reliable operation of combine harvesters and other complex agricultural machinery.

The structural reliability of agricultural machinery is critically dependent on bolted joints, with loosening being a significant and prevalent failure mode. Harsh operational environments (intense vibration, impact, corrosion) severely exacerbate loosening risks, compromising machinery performance and safety. Traditional periodic inspections are inadequate for preventing sudden failures induced by loosening, leading to impaired efficiency and safety hazards. This review comprehensively analyzes the unique challenges and opportunities in monitoring bolted joint reliability within agricultural machinery. It covers the following: (1) the status of bolted joint reliability issues (failure modes, impacts, maintenance inadequacies); (2) environmental challenges to joint integrity; (3) evaluation of conventional detection methods; (4) principles and classifications of modern detection technologies (e.g., vibration-based, acoustic, direct measurement, vision-based); and (5) their application status, limitations, and techno-economic hurdles in agriculture. This review identifies significant deficiencies in current technologies for agricultural machinery bolt loosening surveillance, underscoring the pressing need for specialized, dependable, and cost-effective online monitoring systems tailored for agriculture’s demanding conditions. Finally, forward-looking research directions are outlined to enhance the reliability and intelligence of structural monitoring for agricultural machinery.

Complex mechanical systems, such as agricultural combine harvesters, are subjected to dynamic excitations from multiple coupled sources, compromising structural integrity and operational reliability. Disentangling these vibrations to identify dominant sources and quantify their transmission paths remains a significant engineering challenge. This study proposes a robust diagnostic framework to address this issue. We employed a multi-condition vibration test with sequential source activation and an improved Operational Transfer Path Analysis (OTPA) method. Applied to a harvester chassis, the results revealed that vibration energy is predominantly concentrated in the 0–200 Hz frequency band. Path contribution analysis quantified that the “cutting header → conveyor trough → hydraulic cylinder → chassis frame” path is the most critical contributor to vertical vibration, with a vibration acceleration level of 117.6 dB. Further analysis identified the engine (29.3 Hz) as the primary source for vertical vibration, while lateral vibration was mainly attributed to a coupled resonance between the threshing cylinder (58 Hz) and the engine’s second-order harmonic. This study’s theoretical contribution lies in validating a powerful methodology for vibration source apportionment in complex systems. Practically, the findings provide direct, actionable insights for targeted structural optimization and vibration suppression.