The traditional means of monitoring the health of industrial systems involves the use of vibration and performance monitoring techniques amongst others. In these approaches, contact-type sensors, such as accelerometer, proximity probe, pressure transducer and temperature transducer, are installed on the machine to monitor its operational health parameters. However, these methods fall short when additional sensors cannot be installed on the machine due to cost, space constraint or sensor reliability concerns. On the other hand, the use of acoustic-based monitoring technique provides an improved alternative, as acoustic sensors (e.g., microphones) can be implemented quickly and cheaply in various scenarios and do not require physical contact with the machine. The collected acoustic signals contain relevant operating health information about the machine; yet they can be sensitive to background noise and changes in machine operating condition. These challenges are being addressed from the industrial applicability perspective for acoustic-based machine condition monitoring. This paper presents the development in methodology for acoustic-based fault diagnostic techniques and highlights the challenges encountered when analyzing sound for machine condition monitoring.

Fault diagnosis of rolling bearing is of great importance to ensure high reliability and safety in the industrial machinery system. Entropy measures are useful non-linear indicators for time series complexity analysis and have been widely applied in bearing fault diagnosis in the past decade. In this paper, an improved entropy measure is proposed, named Adaptive Multiscale Weighted Permutation Entropy (AMWPE). Then, a new rolling bearing fault diagnosis method is developed based on the AMWPE and multi-class SVM. For comparison, an experimental bearing dataset is analyzed using the AMWPE and conventional entropy measures, and then multi-class SVM is adopted for fault type classification. Further, the robustness of different entropy measures against noise is studied by analyzing noisy signals with various Signal-to-Noise Ratios (SNRs). The experimental results have demonstrated the effectiveness of the proposed method in bearing fault diagnosis under different fault types, severity degrees, and SNR levels.

Intelligent equipment and flexible production lines are at the cores of smart manufacturing. Meanwhile, Internet of Things and Artificial Intelligence have provided new solutions for the intelligent equipment management and maintenance in mixed model assembly (MMA). This article focuses on knowledge-driven techniques, and it proposes a knowledge sharing-enabled multirobot collaboration (KS-enabled MRC) strategy for preventive maintenance of robots in MMA. First, a formal semantic environment for MMA is constructed by way of ontology-enabled semantic modeling. Then,task-related action primitives and ontology-based robot skill bases are established according to robot capability and task environment. Finally, the Wu-Palmer similarity metric and first-order logic are leveraged to match and reason new tasks according to the semantic rules, and a knowledge sharing and update mechanism are developed for this application. Experimental results demonstrate that the proposed KS-enabled MRC can reduce unscheduled downtime and assist in achieving a load balance for robots in MMA. The studied MRC can potentially avoid severe equipment degradation, thus acting as a preventive maintenance paradigm of complex equipment. Furthermore, it is applicable across different platforms and exhibits high deployment efficiency without intense programming requirements.

Distributed strain sensing is a powerful tool for in situ structural health monitoring for a wide range of critical engineering infrastructures. Strain information from a single sensing device can be captured from multiple locations simultaneously, offering a reduction in hardware, wiring, installation costs, and signal analysis complexity. Fiber optic distributed strain sensors have been the widely adopted approach in this field, but their use is limited to lower strain applications due to the fragile nature of silica fiber. Coaxial cable sensors offer a robust structure that can be adapted into a distributed strain sensor. They can withstand greater strain events and offer greater resilience in harsh environments. This paper presents the developments in methodology for coaxial cable distributed strain sensors. It explores the two main approaches of coaxial cable distributed strain sensing such as time domain reflectometry and frequency domain reflectometry with applications. Furthermore, this paper highlights further areas of research challenges in this field, such as the deconvolution of strain and temperature effects from coaxial cable distributed strain sensor measurements, mitigating the effect of dielectric permittivity on the accuracy of strain measurements, addressing manufacturing challenges with the partial reflectors for a robust coaxial cable sensor, and the adoption of data-driven analysis techniques for interrogating the interferogram to eliminate concomitant measurement effects with respect to temperature, dielectric permittivity, and signal-to-noise ratio, amongst others

The aim of this paper is to introduce the bases of an intelligent fault diagnostic platform, which assists in detecting mechanical failures of Industrial Gas Turbines (IGTs). This comprises an integration of an expert system and its complementary signal processing techniques. The essential characteristic here is not to exclude humans (experts) from the diagnostic process, but rather to transfer their knowledge and experience to a computerized platform. The automated process executed by the computerized platform is to ensure the scalability and consistency in fault diagnosis; while the humans are required to corroborate the transparency and liability of the outcomes. In this paper, a Knowledge Transfer Platform (KTP) is proposed for fault diagnosis of industrial systems. It is then designed and tested for combustion fault diagnosis using field data of IGTs. The preliminary results have revealed the feasibility and efficacy of the proposed scheme, which has the potential to be further extended to a large industrial scale and to different engineering diagnostic applications.

The effect of compressor fouling on the performance of a gas turbine has been the subject of several papers; however, the goal of this paper is to address a more fundamental question of the effect of fouling, which is the onset of unstable operation of the compressor. Compressor fouling experiments have been carried out on a test rig refitted with TJ100 small jet engine with centrifugal compressor. Fouling on the compressor blade was simulated with texturized paint with average roughness value of 6 μm. Compressor characteristic was measured for both the clean (baseline) and fouled compressor blades at several rotational speeds by throttling the engine with variable exhaust nozzle. A Greitzer-type compression system model has been applied based on the geometric and performance parameters of the TJ100 small jet engine test rig. Frequency of plenum pressure fluctuation, the mean disturbance flow coefficient, and pressure-rise coefficient at the onset of plenum flow field disturbance predicted by the model was compared with the measurement for both the baseline and fouled engine. Model prediction of the flow field parameters at inception of unstable operation in the compressor showed good agreement with the experimental data. The results proved that used simple Greitzer model is suitable for prediction of the engine compressor unstable behavior and prediction of the mild surge inception point for both the clean and the fouled compressor.