Non-Linear Regression Models with Vibration Amplitude Optimization Algorithms in a Microturbine

Machinery condition monitoring and failure analysis is an engineering problem to pay attention to among all those being studied. Excessive vibration in a rotating system can damage the system and cannot be ignored. One option to prevent vibrations in a system is through preparation for them with a model. The accuracy of the model depends mainly on the type of model and the fitting that is attained. The non-linear model parameters can be complex to fit. Therefore, artificial intelligence is an option for performing this tuning. Within evolutionary computation, there are many optimization and tuning algorithms, the best known being genetic algorithms, but they contain many specific parameters. That is why algorithms such as the gray wolf optimizer (GWO) are alternatives for this tuning. There is a small number of mechanical applications in which the GWO algorithm has been implemented. Therefore, the GWO algorithm was used to fit non-linear regression models for vibration amplitude measurements in the radial direction in relation to the rotational frequency in a gas microturbine without considering temperature effects. RMSE and R2 were used as evaluation criteria. The results showed good agreement concerning the statistical analysis. The 2nd and 4th-order models, and the Gaussian and sinusoidal models, improved the fit. All models evaluated predicted the data with a high coefficient of determination (85–93%); the RMSE was between 0.19 and 0.22 for the worst proposed model. The proposed methodology can be used to optimize the estimated models with statistical tools.

A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing

For anomaly identification of predicted data in machinery condition monitoring, traditional threshold methods have problems during residual testing. It is difficult to make decisions when the residuals are close to the threshold and fluctuate. This paper proposes a Bayesian dynamic thresholding method that combines Bayesian inference with neural network signal prediction. The method makes full use of historical prior data to build an anomaly identification and warning model applicable under single variable or multidimensional variables. A long short-term memory signal prediction model is established, and then a Bayesian hypothesis testing-based anomaly identification strategy is presented to quantify the probability of anomaly occurrence and issue early warnings for anomalies beyond a certain probability. The model was applied to open data sets of a pumping station and actual operating data of a nuclear power turbine. The results indicate that the model successfully predicts the failure probability and failure time. The effectiveness of the proposed method is verified.

A low quiescent power wireless rotating machinery condition monitoring system

Vibration-based monitoring of rotating machinery is rapidly evolving within the aerospace industry with priority on detecting impending failures. The workhorse of such monitoring system remains a piezoelectric-based accelerometers which requires a wired-harnesses, connectors, significant power, and signal conditioning, etc. Raytheon Technologies Research Center (RTRC) along with Collins Aerospace and Sandia National Laboratory have jointly developed an Aluminum-Nitride Resonant Integrated Accelerometer Sensors (ARISE). This is a low power alternate for a conventional wired vibration-based monitoring system. This self-contained sensor system includes: (1) a low quiescent power sensing element with a wake-up module, (2) a wireless communication module, and (3) a coin-cell battery. Leveraging work performed under Defense Advanced Research Projects Agency (DARPA) N-Zero program. This wireless health monitoring system can operate in a quiescent low power mode (~10nW) for a period of several years without servicing. With an exceedance above a preset vibration level (at designate characteristic frequencies), the sensor wakes up and wirelessly sends a warning of a precursor-to-failure. The ARISE sensor and wake-up module package has been validated with a replicated vibration environment acquired from a selected rotating machinery subject to progressive damage at the Structural Dynamics Laboratory at RTRC. The failure precursor is successfully detected by the sensor which triggers the wake-up module. This research was developed with funding from the Defense Advanced Research Projects Agency (DARPA) Micro Technology Office (MTO), under Aluminum-Nitride Resonant Integrated Accelerometer Sensors (ARISE) program.

Wireless Noise Characteristics on Gearboxes Due to Speed Variations

Noise inspection is a predictive maintenance technique that is used to determine machine condition. The noise inspection can be done offline and online. Online noise inspection, which is far away from the object, is performed in the control center room. This monitoring system requires a complicated installation and long cables. The complexity of installation can be overcome by implementing a wireless noise inspection system. Wireless noise monitoring system for machinery condition monitoring still lacks information. Therefore, it is necessary to develop a wireless noise monitoring system. The result of wireless noise testing data on the machine is justified through the analysis of noise testing data of wired system. The research objective was to create a wireless noise measurement that is applied on a gearbox that is equipped with a data acquisition system that operates at a constant load and 5 variations of speed. Comparative analysis is used to justify the noise amplitude, time domain, and frequency domain of wireless and cabled measurements. The final test result indicates that the noise and wireless spectrum signals match the noise spectrum and signals using a cable. The highest amplitude lies at 12-13 of a fundamental frequency at a low frequency and at 30 of a fundamental frequency at a high frequency.