scholarly journals Operating Condition-Invariant Neural Network-based Prognostics Methods applied on Turbofan Aircraft Engines

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Gabriel Duarte Pasa ◽  
Ivo Paixão de Medeiros ◽  
Takashi Yoneyama
Keyword(s):  
Short Term Memory ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Aircraft Engines ◽  
Simple Task ◽  
Operating Condition ◽  
Prediction Horizon ◽  
Engineered Systems ◽  
Using Data ◽  
The Impact

Neural networks in their many flavors have been widely used in prognostics of engineered systems due to their versatility and increasing potential, especially with recent breakthroughs in Deep Learning and specialized architectures. Despite these advances, some problems can still significantly benefit from a solid exploratory analysis and simple task-specific data/target transformations. In this work, popular architectures including Feedforward, Convolutional and LSTM (Long Short-Term Memory) networks are evaluated in a case study of RUL (Remaining Useful Life) prediction for turbofan aircraft engines, using data from publicly available repositories. A robust set of over 20,000 model configurations are tested, evaluating the effects of several hyper-parameters and design choices. The latter includes a maximum prediction horizon, revealing a trade-off between prediction accuracy and timeliness which can have significant impact in real-world applications. An operating condition-specific standardization scheme is also evaluated, in order to minimize the impact of normal changes in operating regimes which obfuscate the fault degradation patterns. A comparison with existing works in literature shows some simple policies for operating condition-invariance have lead to results which outperform the current state-of-the-art methods for some of the data subsets with multiple operating conditions.

Prognostics and RUL Estimations of SAC305, SAC105 and SnAg Solders Under Temperature and Vibration Using Long Short-Term Memory (LSTM) Deep Learning

2021 ◽  
Author(s):  
Pradeep Lall ◽  
Tony Thomas ◽  
Ken Blecker
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Short Term ◽  
Term Memory ◽  
Rectangular Pattern ◽  
Useful Life ◽  
Long Short Term Memory

Abstract Prognostics and Remaining Useful Life (RUL) estimations of complex systems are essential to operational safety, increased efficiency, and help to schedule maintenance proactively. Modeling the remaining useful life of a system with many complexities is possible with the rapid development in the field of deep learning as a computational technique for failure prediction. Deep learning can adapt to multivariate parameters complex and nonlinear behavior, which is difficult using traditional time-series models for forecasting and prediction purposes. In this paper, a deep learning approach based on Long Short-Term Memory (LSTM) network is used to predict the remaining useful life of the PCB at different conditions of temperature and vibration. This technique can identify the different underlying patterns in the time series that can predict the RUL. This study involves feature vector identification and RUL estimations for SAC305, SAC105, and Tin Lead solder PCBs under different vibration levels and temperature conditions. The acceleration levels of vibration are fixed at 5g and 10g, while the temperature levels are 55°C and 100°C. The test board is a multilayer FR4 configuration with JEDEC standard dimensions consists of twelve packages arranged in a rectangular pattern. Strain signals are acquired from the backside of the PCB at symmetric locations to identify the failure of all the packages during vibration. The strain signals are resistance values that are acquired simultaneously during the experiment until the failure of most of the packages on the board. The feature vectors are identified from statistical analysis on the strain signals frequency and instantaneous frequency components. The principal component analysis is used as a data reduction technique to identify the different patterns produced from the four strain signals with failures of the packages during vibration. LSTM deep learning method is used to model the RUL of the packages at different individual operating conditions of vibration for all three solder materials involved in this study. A combined model for RUL prediction for a material that can take care of the changes in the operating conditions is also modeled for each material.

scholarly journals Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

2021 ◽  
Vol 7 ◽  
pp. e795
Author(s):  
Pooja Vinayak Kamat ◽  
Rekha Sugandhi ◽  
Satish Kumar
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Rotating Machinery ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Learning Models ◽  
Vibration Data ◽  
Degradation Data ◽  
Useful Life

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

Parametric Study on Ported Shroud Locations and Geometries for a Turbocharger Compressor

2019 ◽  
Author(s):  
Suheab Thamizullah ◽  
Abdul Nassar ◽  
Antonio Davis ◽  
Gaurav Giri ◽  
Leonid Moroz
Keyword(s):  
Centrifugal Compressor ◽  
Combustion Engine ◽  
Engine Performance ◽  
Operating Conditions ◽  
Entire Study ◽  
Operating Condition ◽  
Baseline Design ◽  
Operating Range ◽  
Ported Shroud ◽  
The Impact

Abstract Turbochargers are commonly used in automotive engines to increase the internal combustion engine performance during off-design operating conditions. When used, the widest operating range for the turbocharger is desired, which is limited on the compressor side by the choke condition and the surge phenomenon. The ported shroud technology is used to extend the operable working range of the compressor, by permitting flow disturbances that block the blade passage to escape and stream back through the shroud cavity to the compressor inlet. The impact of this technology, on a speed-line, at near optimal operating condition, near choke operating condition and near surge operating condition is investigated. The ported shroud (PS) self-recirculating casing treatment is widely used to delay the onset of surge by enhancing the aerodynamic stability of the turbocharger compressor. While the ported shroud design delays surge, it usually comes with a small penalty in efficiency. This research involves designing a single-stage centrifugal compressor for the given specifications, considering the application of an automotive turbocharger. The ported shroud was then introduced in the centrifugal compressor. The performance characteristics were obtained, both at the design and at off-design conditions, both with and without the ported shroud. The performance was compared at various off-design operating speed lines. The entire study, from designing the compressor to optimizing the ported shroud configuration, was performed using the commercial AxSTREAM® software platform. Parametric studies were performed to study the effect of ported shroud axial location along the blade axial length on the operating range and performance. The baseline design, without the ported shroud (P0), and the final geometry with it for all PS inlet axial locations (P1 to P5) were analysed using a commercial CFD package and the results were compared with those from the streamline solver.

Data Driven Approach to Analyzing The Impact of Power Plant Cycling on Air Preheater Degradation and Remaining Useful Life

2021 ◽  
Author(s):  
Himanshu Sharma ◽  
Veronica Adetola ◽  
Laurentiu Marinovici ◽  
Herbert T. Schaef
Keyword(s):  
Power Plant ◽  
Operation Time ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Dew Point ◽  
Data Driven ◽  
Air Preheater ◽  
Operational Life ◽  
Useful Life ◽  
The Impact

Abstract Due to the increased penetration of renewable energy generation sources, and fluctuations of the oil and gas prices, modern coal burning power plants deal with increased variability in the demand for power generation. These varying demands result in their intermittent under-capacity operation (cycling). Periodical ramping down and back up to follow the daily power demands causes damages to the plant components reducing its operational life. In this paper we analyze the impact of cycling on a rotary Ljungstrom air preheater (APH) unit installed at a coal fire power plant in the US. An inefficient air preheater can significantly impact boiler performance. Due to the repeated boiler’s hot-cold start, the APH experiences fluctuating operating conditions that result in accelerated degradation mechanisms, such as dew-point corrosion, fouling/deposition plugging, and air heater leakage. The analysis in this paper utilizes field data related to APH basket replacement, and the number of cycles experienced by the boiler to model the life expectancy of the baskets. The data-driven model enables preventive maintenance strategies for the APH by predicting how long the APH baskets will last in a probabilistic sense. The analysis showed that an increase in cycling for a fixed operation time can reduce the APH basket remaining useful life by about 30%.

Optimal button arrangement of a percussion drill bit and its operating condition for improving drilling efficiency

2017 ◽  
Vol 232 (16) ◽  
pp. 2887-2898 ◽  
Author(s):  
Hoon Kang ◽  
Jin-Young Park ◽  
Jung-Woo Cho ◽  
Jin-Seok Jang ◽  
Kun-Woo Kim ◽  
...  
Keyword(s):  
Evaluation Method ◽  
Optimal Solution ◽  
Operating Conditions ◽  
Rock Surface ◽  
Drill Bit ◽  
Operating Condition ◽  
Drilling Performance ◽  
Impact Area ◽  
Specific Operating Condition ◽  
The Impact

This paper proposes an optimal button arrangement of a percussion drill bit and its operating condition to improve drilling efficiency. A new evaluation method is introduced for the button arrangement that utilizes the superimposed impact area, blank area, and drilling deviation moment as the quantitative indices to evaluate the impact of buttons on the rock surface. To determine the optimal button arrangement and its operating conditions, a progressive metamodel-based design optimization was conducted using the new evaluation indices as the analysis response, and then the optimal solution was determined through iteration. Consequently, all the button evaluation indices were reduced significantly and the impact areas were distributed uniformly under a specific operating condition. Additionally, the drilling performances of the optimal button arrangement were investigated according to the operating conditions to obtain the maximum drilling performance in terms of the drilling machine operation.

Analysis and Comparison of Clean vs Inlet Distortion Flow Physics at Design Operating Condition Using Proper Orthogonal Decomposition

2015 ◽  
Author(s):  
Ronald A. Spencer ◽  
Steven E. Gorrell ◽  
Matthew R. Jones ◽  
Earl P. N. Duque
Keyword(s):  
Proper Orthogonal Decomposition ◽  
Orthogonal Decomposition ◽  
Flow Distortion ◽  
Efficient Operation ◽  
Operating Condition ◽  
Shock Location ◽  
Stage Performance ◽  
Engineered Systems ◽  
Proper Orthogonal ◽  
The Impact

Assessing the impact of inlet flow distortion in turbomachinery is critical to the safe and efficient operation of many engineered systems. This paper introduces and validates the use of methods based on the Proper Orthogonal Decomposition (POD) to analyze clean and 1/rev static pressure distortion simulation results at design operating condition. The value of POD comes in its ability to efficiently extract both quantitative and qualitative information about dominant spatial flow structures as well as information about temporal fluctuations in flow properties. The analysis was used to quantify circumferential varying stage performance in terms of shock location and strength. Since the result of 1/rev total pressure distortion is circumferential varying stage performance, POD is a useful means to analyze and quantify such variation. Observation of the modes allowed qualitative identification of shockwaves as well as quantification of their location and range of motion. Modal coefficients revealed the location of the passage shock at a given angular location. Distortion amplification and attenuation between rotors was also identified.

scholarly journals A Data-Driven-Based Industrial Refrigeration Optimization Method Considering Demand Forecasting

Processes ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 617 ◽  
Author(s):  
Josep Cirera ◽  
Jesus A. Carino ◽  
Daniel Zurita ◽  
Juan A. Ortega
Keyword(s):  
Demand Forecasting ◽  
Optimization Method ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Data Driven ◽  
Refrigeration System ◽  
Operation Condition ◽  
Self Organizing Maps ◽  
Using Data ◽  
Industrial Refrigeration

One of the main concerns of industry is energy efficiency, in which the paradigm of Industry 4.0 opens new possibilities by facing optimization approaches using data-driven methodologies. In this regard, increasing the efficiency of industrial refrigeration systems is an important challenge, since this type of process consume a huge amount of electricity that can be reduced with an optimal compressor configuration. In this paper, a novel data-driven methodology is presented, which employs self-organizing maps (SOM) and multi-layer perceptron (MLP) to deal with the (PLR) issue of refrigeration systems. The proposed methodology takes into account the variables that influence the system performance to develop a discrete model of the operating conditions. The aforementioned model is used to find the best PLR of the compressors for each operating condition of the system. Furthermore, to overcome the limitations of the historical performance, various scenarios are artificially created to find near-optimal PLR setpoints in each operation condition. Finally, the proposed method employs a forecasting strategy to manage the compressor switching situations. Thus, undesirable starts and stops of the machine are avoided, preserving its remaining useful life and being more efficient. An experimental validation in a real industrial system is performed in order to validate the suitability and the performance of the methodology. The proposed methodology improves refrigeration system efficiency up to 8%, depending on the operating conditions. The results obtained validates the feasibility of applying data-driven techniques for the optimal control of refrigeration system compressors to increase its efficiency.

scholarly journals Remaining Useful Life Prediction of Bearings Using Ensemble Learning: The Impact of Diversity in Base Learners and Features

2020 ◽  
Vol 21 (2) ◽  
Author(s):  
Junchuan Shi ◽  
Tianyu Yu ◽  
Kai Goebel ◽  
Dazhong Wu
Keyword(s):  
Ensemble Learning ◽  
Health Management ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Learning Methods ◽  
Vibration Data ◽  
Model Based ◽  
Useful Life ◽  
The Impact

Abstract Prognostics and health management (PHM) of bearings is crucial for reducing the risk of failure and the cost of maintenance for rotating machinery. Model-based prognostic methods develop closed-form mathematical models based on underlying physics. However, the physics of complex bearing failures under varying operating conditions is not well understood yet. To complement model-based prognostics, data-driven methods have been increasingly used to predict the remaining useful life (RUL) of bearings. As opposed to other machine learning methods, ensemble learning methods can achieve higher prediction accuracy by combining multiple learning algorithms of different types. The rationale behind ensemble learning is that higher performance can be achieved by combining base learners that overestimate and underestimate the RUL of bearings. However, building an effective ensemble remains a challenge. To address this issue, the impact of diversity in base learners and extracted features in different degradation stages on the performance of ensemble learning is investigated. The degradation process of bearings is classified into three stages, including normal wear, smooth wear, and severe wear, based on the root-mean-square (RMS) of vibration signals. To evaluate the impact of diversity on prediction performance, vibration data collected from rolling element bearings was used to train predictive models. Experimental results have shown that the performance of the proposed ensemble learning method is significantly improved by selecting diverse features and base learners in different degradation stages.

scholarly journals Optimization Modeling and Empirical Research on Gasoline Octane Loss Based on Data Analysis

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Ji Guo ◽  
Yujia Lou ◽  
Wanyi Wang ◽  
Xianhua Wu
Keyword(s):  
Data Analysis ◽  
Catalytic Cracking ◽  
Economic Cost ◽  
Petroleum Products ◽  
Operating Conditions ◽  
Atmospheric Environment ◽  
Optimal Operating ◽  
Operating Variables ◽  
Using Data ◽  
The Impact

Gasoline is one of the most consumed light petroleum products in transportation and other industries. This paper proposes a method for optimizing gasoline octane loss using data analysis technology aimed at optimizing the production process and minimizing the loss of gasoline octane. Firstly, the data are screened and the high-dimensional data are reduced to construct the neural network prediction model optimized by genetic algorithm. After utilizing the model for prediction, the optimal operating condition is achieved. Secondly, ensuring that the gasoline emission meets the standard, the octane loss is reduced by adjusting the operating variables. Thirdly, actual data are collected and calculated to obtain the main operating variables and their optimal operating conditions of a petrochemical company affecting the catalytic cracking gasoline S-Zorb unit, thus providing companies using S-Zorb units with reference data for optimizing gasoline catalytic cracking processes. Fourthly, the superiority of the proposed method was verified by comparing it with the other methods. This paper intends to contribute to better modeling the progress of gasoline catalytic cracking by adequately considering the impact of multiple factors, improving the quality of refined oil products of chemical enterprises, saving the economic cost of chemical enterprises, and protecting the atmospheric environment.

Combustion and Exhaust Emission Characteristics of a Passenger Car Diesel Engine Fueled With Biodiesel 30% Derived From Soybean

2010 ◽  
Author(s):  
Myung Yoon Kim ◽  
WooHeum Cho ◽  
Eun-Hyun Lee ◽  
Jerok Chun
Keyword(s):  
Diesel Engine ◽  
Diesel Fuel ◽  
Operating Conditions ◽  
Engine Management System ◽  
Exhaust Gas ◽  
Operating Condition ◽  
Part Load ◽  
Full Load ◽  
The Impact ◽  
Engine Power

The impact of soybean methyl ester (SME) on the injection mass curve, exhaust emissions, engine performance, and exhaust gas temperatures of a common-rail direct injection diesel engine have been investigated. In this study, 30% SME blended diesel fuel (BD30) has been used as a fuel in the engine and results of the investigation were compared to those obtained using petroleum diesel fuel. The results of the investigation show that the change in injection mass curve when using BD30 instead of diesel was insignificant. A combustion analysis shows BD30 has a shorter ignition delay at part-load operating condition where heavy exhaust gas recirculation (EGR) rate is used. This difference in behavior is due to the oxygen contents and lower stoichiometric air-fuel ratio of BD30, which leads to higher O2 concentration in the exhaust gas. At part-load operating conditions, BD30 results showed 53% reduction in smoke at the expense of 18% increase in NOx emission. The full load engine power for BD30 was decreased by 2.1∼3.8% using EMS (engine management system) configurations without torque adjustment to compensated reduction in calorific value of BD30. When the engine power was so adjusted that BD30 produced the same power as diesel fuel, a lower exhaust gas temperature was observed at full load operating condition. Considering that the LHV (lower heating value) of BD30 is 2.6% lower than that of diesel fuel, there may be no factors that cause deterioration of thermal efficiency on using BD30 under all operating conditions.

Sign in / Sign up

Export Citation Format

Share Document