Search for: All records

Condition assessment of machinery components such as gears is important to maintain their normal operations and thus can bring benefit to their life circle management. Data-driven approaches haven been a promising way for such gear condition monitoring and fault diagnosis. In practical situation, gears generally have a variety of fault types, some of which exhibit continuous severities of fault. Vibration data collected oftentimes are limited to reflect all possible fault types. Therefore, there is practical need to utilize the data with a few discrete fault severities in training and then infer fault severities for the general scenario. To achieve this, we develop a fuzzy neural network (FNN) model to classify the continuous severities of gear faults based on the experimental measurement. Principal component analysis (PCA) is integrated with the FNN model to capture the main features of the time-series vibration signals with dimensional reduction for the sake of computational efficiency. Systematic case studies are carried out to validate the effectiveness of proposed methodology. 

This research concerns the uncertainty analysis and quantification of the vibration system utilizing the frequency response function (FRF) representation with statistical metamodeling. Different from previous statistical metamodels that are built for individual frequency points, in this research we take advantage of the inherent correlation of FRF values at different frequency points and resort to the multiple response Gaussian process (MRGP) approach. To enable the analysis, vector fitting method is adopted to represent an FRF using a reduced set of parameters with high accuracy. Owing to the efficiency and accuracy of the statistical metamodel with a small set of parameters, Bayesian inference can then be incorporated to realize model updating and uncertainty identification as new measurement/evidence is acquired. The MRGP metamodel developed under this new framework can be used effectively for two-way uncertainty propagation analysis, i.e., FRF prediction and uncertainty identification. Case studies are conducted for illustration and verification. 

Fault pattern recognition in complex mechanical systems such as gearbox has always been a great challenge. The performance of a classic fault pattern recognition approach heavily depends on domain expertise and the classifier applied. This paper proposes a deep convolutional neural network-based transfer learning approach that not only entertains adaptive feature extractions, but also requires only a small set of training data. The proposed transfer learning architecture essentially consists of two sequentially connected pieces; first is of a pre-trained deep neural network that serves to extract features automatically, the second piece is a neural network aimed for classification which is to be trained using data collected from gearbox experiment. The proposed approach performs gear fault pattern recognition using raw accelerometer data. The achieved accuracy indicates that the proposed approach is not only sensitive and robust in performance, but also has the potential to be applied to other pattern recognition practices.