To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

Metal additive manufacturing (AM), also known as metal three-dimensional (3D) printing, produces 3D metal products by repeatedly adding and solidifying metal materials layer by layer. During the metal AM process, products experience repeated local melting and cooling using a laser or electron beam, resulting in product defects, such as warpage, cracks, and internal pores. Such defects adversely affect the final product. This paper proposes the in situ monitoring-based warpage prediction of metal AM products with experimental feature extraction. The temperature profile of the metal AM substrate during the process was experimentally collected. Time-domain features were extracted from the temperature profile, and their relationships to the warpage mechanism were investigated. The standard deviation showed a significant linear correlation with warpage. The findings from this study are expected to contribute to optimizing process parameters for metal AM warpage reduction.

Even though several deep learning-based methods have been applied in the field of acoustic source localization, the previous works have only been conducted using the two-dimensional representation of the beamforming maps, particularly with the planar array system. While the acoustic sources are more required to be localized in a spherical microphone array system considering that we live and hear in the 3D world, the conventional 2D equirectangular map of the spherical beamforming map is highly vulnerable to the distortion that occurs when the 3D map is projected to the 2D space. In this study, a 3D deep learning approach is proposed to fulfill accurate source localization via distortion-free 3D representation. A target function is first proposed to obtain 3D source distribution maps that can represent multiple sources' positional and strength information. While the proposed target map expands the source localization task into a point-wise prediction task, a PointNet-based deep neural network is developed to precisely estimate the multiple sources' positions and strength information. While the proposed model's localization performance is evaluated, it is shown that the proposed method can achieve improved localization results from both quantitative and qualitative perspectives.

Condition monitoring of permanent magnet synchronous motors (PMSMs) and detecting faults such as eccentricity and demagnetization are essential for ensuring system reliability. Motor current signal analysis is the most commonly used precursor for detecting faults in the PMSM drive system. However, the current signature responds sensitively to the load and temperature of the motor, thereby making it difficult to monitor faults in real- applications. Therefore, in this study, a condition monitoring methodology that detects motor faults, including their classification with standstill conditions, is proposed. The objective is to detect and classify faults of PMSMs by using programmable inverter without additional sensors and systems for detection. Both DC and AC were applied through the d-axis of a three-phase motor, and the change in incremental inductance was investigated to detect and classify faults. Simulation with finite element analysis and experiments were performed on PMSMs in healthy conditions as well as with eccentricity and demagnetization faults. Based on the results obtained from experiments, the proposed method was confirmed to detect and classify types of faults, including their severity.

A complex system is comprised of numerous entities containing physical components, devices and hardware, events or phenomena, and subsystems, there are intricate interactions among these entities. To reasonably identify the critical fault propagation paths, a system fault propagation model is essential based on the system failure mechanism and failure data. To establish an appropriate mathematical model for the complex system, these entities and their complicated relations must be represented objectively and reasonably based on the structure. Taking a command and control system as an example, this paper proposes a hierarchical fault propagation analysis method, analyzes and determines the edge betweenness ranking model and the importance degree of each sub-system.

Permanent magnet synchronous motors (PMSMs) are widely used in systems requiring high control precision, efficiency, and reliability. Predicting the remaining useful life (RUL) with health monitoring of PMSMs prevents catastrophic failure and ensures reliable operation of system. In this study, a model-based method for predicting the RUL of PMSMs using phase current and vibration signals is proposed. The proposed method includes feature selection and RUL prediction based on a particle filter with a degradation model. The Paris-Erdogan model describing micro fatigue crack propagation is used as the degradation model. An experimental set-up to conduct accelerated life test, capable of monitoring various signals was designed in this study. Phase current and vibration data obtained from an accelerated life test of the PMSMs were used to verify the proposed approach. Features extracted from the data were clustered based on monotonicity and correlation clustering, respectively. The results identify the effectiveness of using the current data in predicting the RUL of PMSMs.