Time-varying Operating Conditions Research Articles

A framework for predicting the remaining useful life of machinery working under time-varying operational conditions

Remaining useful life (RUL) prediction can provide additional capabilities to condition-based maintenance (CBM) and predictive maintenance (PdM) for the reliability and service life of a system. Time-varying operational conditions, such as the altitude, Mach number, and throttle resolver angle of an aero-engine, could result in two main challenges for RUL predictions: varying degradation rates and abrupt jumps in the amplitude of sensor readings. Our study addresses these two challenges in the data pre-processing stage, through operational condition features and the multi-operational condition-based normalization method (MOC-based Normalization). In the framework of our model, first, two density-based clustering algorithms are integrated to be a new classifier for operational conditions clustering and identification in an unsupervised manner. Then, operational condition features consisting of operational condition labels and an operational condition factor are conducted. In the meantime, the proposed MOC-based Normalization recalibrates the upward or downward abrupt jumps of sensor readings at the operational conditions change-points. Sensor data features and operational condition features are combined in the last step of the data pre-processing stage. On this basis, the RUL representation model is trained with the combined features through a gated recurrent unit (GRU)-based network with only two layers in the hidden layer. Experiments on benchmark datasets have been conducted. The results show that the MOC-based Normalization efficiently mitigates the jumps on sensor readings, and the operational condition features improve the prognostic model. Approximately 10% RMSE improvements over the top-three state-of-the-art algorithms are achieved in the RUL prediction under time-varying operational conditions.

Stochastic hybrid system approach to task-orientated remaining useful life prediction under time-varying operating conditions

Mechanical components mainly work under time-varying operating conditions, causing considerable complexity and variability to degradation signals and making it difficult to estimate the remaining useful life (RUL). To handle this problem, this paper proposes a stochastic hybrid system approach to predict the RUL online under time-varying operating conditions by modelling the degradation signals and operating conditions of components. The discrete dynamic nature of operating conditions is described by a continuous-time Markov chain, and their influences on the degradation signals are quantified by degradation rates and signal jumps in a state-space model that is constructed based on nonlinear Wiener process considering the unit-to-unit variability. Considering that a component may have different failure time points under different operating conditions, a novel simulation method based on sequential Monte Carlo is proposed to simulate future operating profiles, predict multiple failure time points and avoid delayed alarms. Hence, the definition of the RUL of the component can be determined through task orientation according to different functional requirements of users, and the accuracy of RUL prediction results can be significantly improved with engineering application value. The effectiveness of the proposed approach is verified via a simulation study and an accelerated degradation test of machine tool spindles.

Experimental characterization of a small-scale solar Organic Rankine Cycle (ORC) based unit for domestic microcogeneration

The integration of a Micro-Organic Rankine Cycle (ORC) power unit with conventional solar flat plate collectors ensures the simultaneous fulfillment of electricity and domestic hot water (DHW) demands. Due to the variability of the solar source, despite the introduction of a thermal storage unit, the plant is subject to severe off design operating conditions. A small-scale ORC-based was designed, built and fully tested, to experimentally assess the performance and operating robustness of the plant in steady and dynamic off-design condition. The unit is fed by hot water from a 135 L reservoir. Dedicated electric heaters (12 kW each one) reproduce the thermal availability from 15 m2 of standard solar thermal collectors for domestic applications. The test bench underwent an extensive experimental assessment in both stationary conditions of the hot source and in presence of a variable thermal load at the evaporator. Due to the plant architecture and components, the control of the unit is based on the variation of the mass flow rate of the working fluid (R245fa) matching the thermal equilibrium at the evaporator in each operating condition of the system. The variation of the flow rate, in fact, must fit with thermal power available. The off-design steady state assessment allows the understanding of the wide operability of the plant (17–62 g/s), with power and efficiency varying between 150 and 500 W and 2.4–4%, respectively. The dynamic testing of the pilot unit points out the plant consistency and robustness to severe off-design operation, mostly due to the 1 kW scroll expander, very suitable for time-varying operating conditions. Both the option of a full discharge of the thermal energy of the reservoir and the option of a split discharge to the evaporator were investigated and provided a clear indication on the CHP feasibility when no addition of thermal energy takes place at the reservoir. It was observed that during a complete reservoir thermal discharge, the plant works for 3000–3300 s continuously, with a slow power decrease from 500 W to 100 W. Considering the thermal energy recharging time, the plant could be averagely operated up to 7 times during the day if a partial discharge was performed. Each plant activation lasts 900 s producing a power ranging from 500 W to 200 W. This operating strategy allows to cover up to 11.2% of the whole electric energy yearly required by an average European household.

Fault detection for chemical processes based on non-stationarity sensitive cointegration analysis

Due to the time-varying operation conditions, chemical processes are characterized by non-stationary characteristics, which makes it a great challenge for conventional process monitoring methods to capture the non-stationary variations In the non-stationary processes, the abnormality would cause the stationary variables to be non-stationary. In this article, a non-stationarity sensitive cointegration analysis monitoring method is proposed to explore potential non-stationary variations. First, the essential non-stationary variables are distinguished using Augmented Dickey–Fuller test to eliminate the influence of essential non-stationary under normal conditions. Then by further analyzing the faulty data, the variables which are sensitive to the non-stationary variations are selected. On this basis, cointegration analysis models are established for both the essential non-stationary variables and non-stationarity sensitive variables to explore long-term dynamic equilibrium relationship, respectively. With the selection of non-stationarity sensitive variables, the potential faulty information is emphasized in the process monitoring model, which makes the model capable to handle the non-stationary variations. Finally, the monitoring results are combined through Bayesian inference criterion. The proposed method is applied on the Tennessee Eastman process and a vinyl acetate monomer plant model, and the feasibility and performance are demonstrated.

A Robust Health Indicator for Rotating Machinery Under Time-Varying Operating Conditions

Bearing is an essential component whose failure leads to costly downtime in operation. Therefore, it is important to establish an accurate health indicator (HI), using which the remaining useful life can be reliably predicted. To date, most of the health assessment for bearing have been focused on the constant operating condition while in practice, it operates under various operating conditions (rotating speed and loading). Motivated by this, this paper proposes a method to extract robust HI which undergoes variable operating conditions. The idea is to cluster the operating conditions regimes, and develop HI based on the Mahalanobis distance using the optimal features subset in each regime. To validate the effectiveness, bearing run-to-fail experiment is performed under variable operating condition, and proposed HI is compared with the traditional statistical features. The remaining useful life is predicted by the data augmentation prognostics algorithm which was to overcome data deficiency problem.

Unsteady flow modelling of hydraulic and electrical RTC of PATs for hydropower generation and service pressure regulation in WDN

ABSTRACT The topic of this paper is the recovery of energy from urban waters, which can be performed in water distribution networks (WDNs) through hydraulically and electrically regulated pumps operating as turbines (PATs). The time-varying operating conditions make real time control (RTC) techniques necessary for adjusting both hydropower generation and service pressure regulation. An unsteady flow model allows simulating the skeletonized layout of a real WDN, and assessing the effectiveness of the RTC. Two control schemes, operating at small and large-time steps, respectively, are presented and compared. The numerical simulations prove the application of the prototype feasible in real WDNs, providing effective hydropower generation and service pressure regulation. While the hydropower produced by the two controllers is similar, the first prevails in terms of closeness of the controlled pressure-head at the critical node to the desired set-point, whereas the second performs better in terms of control cost.

Predictive maintenance integrated production scheduling by applying deep generative prognostics models: approach, formulation and solution

To harness the full potential of predictive maintenance (PdM), PdM information has to be used to optimally plan production and maintenance actions. Hence, operation-specific modelling of degradation, i.e. predictions of the health condition under time-varying operational conditions, has to be realized. By utilizing operation-specific degradation information, maintenance and production can be planned with regard to each other and thus, predictive maintenance integrated production scheduling (PdM-IPS) is enabled. This publication proposes a novel PdM-IPS approach consisting of two interacting modules: an operation-specific Prognostics and Health Management (PHM) module and an integrated production scheduling and maintenance planning (IPSMP) module. Specifically, the mathematical problem of the IPSMP module based on an extended version of the maintenance integrated flexible job shop problem is formulated. A two-stage genetic algorithm to efficiently solve this problem is designed and subsequently applied to simulated condition monitoring, as well as real industrial data. Results indicate that the approach is able to find feasible high quality PdM integrated production schedules.

Field degradation modeling and prognostics under time-varying operating conditions: A Bayesian based filtering algorithm

In practice, degradation modeling and prognostics for a product working in field is of importance for condition-based maintenance, meanwhile a challenging work due to the uncertainty in degradation and the time-varying operating conditions. This study investigates a degradation modeling framework for field working product and its applications by incorporating multiple data sources to associate the operating condition and reduce the uncertainty. The Wiener process is adopted to model the degradation process with nonlinearity, unit-to-unit variation, and condition covariates, which is delineated by state space modeling. Meanwhile, the acceleration factor, which establishes the relationship between operating condition and degradation rate, is integrated to adapt the drift parameter. A recursive filtering algorithm based on Bayesian theorem is employed for online updating of drift. Finally, a simulation study and an application on degradation modeling of turbofan engine are given to demonstrate the feasibility and validity of the proposed model.

Time-Varying Spectral Kurtosis: Generalization of Spectral Kurtosis for Local Damage Detection in Rotating Machines under Time-Varying Operating Conditions.

Vibration-based local damage detection in rotating machines (i.e., rolling element bearings) is typically a problem of detecting low-energy cyclic impulsive modulations in the measured signal. This can be challenging as both the amplitude of a single damage-related impulse and the distance between impulses might be changing in time. From the signal processing point of view, this means time varying regarding the the signal-to-noise ratio, location of information in the frequency domain, and loss of periodicity (this remains cyclic but not periodic). One of the many attempted approaches to this problem is filtration using custom filters derived in a data-driven fashion. One of the methods to obtain such filters is a selector approach, where the value of a certain statistic is calculated for individual frequency bands of a signal that results in the magnitude response of a filter. In this approach, each chosen statistic will yield different results, and the obtained filter will be focused on different frequency bands focusing on different behaviors. One of the most popular and powerful selectors is spectral kurtosis as popularized by Antoni, which uses kurtosis as an operational statistic. Unfortunately, after closer inspection, it is easy to notice that, although selectors can significantly enhance the signal, they accumulate a great deal of noise and other background content of signals, which occupies the space (or rather time) in between the impulses. Another disadvantage is that such filters are time-invariant, because, in the principle of their construction, they are not adaptive, and even slight changes in the signal yield suboptimal results either by missing relevant data when the conditions in the signal change (i.e., informative impulses widen in bandwidth), or by accumulating unnecessary noise when the relevant information is not present (in between impulses or in frequency bands that impulses no longer occupy). To address this issue, I propose generalization of the selector approach using the example of spectral kurtosis. This assumes creating a time-varying selector that can be seen as a spatial filter in the time-frequency domain. The time-varying SK (TVSK) is estimated for segments of the signal, and, instead of a vector of SK-based filter coefficients, one obtains a TVSK-based matrix of coefficients that takes into account the time-varying properties of the signal. The obtained structure is then binarized and used as a filter. The presented method is tested using a simulated signal as well as two real-life signals measured on heavy-duty bearings in two different types of machine.

Hidden Markov models for pipeline damage detection using piezoelectric transducers

Oil and gas pipeline leakages lead to not only enormous economic loss but also environmental disasters. How to detect the pipeline damages including leakages and cracks has attracted much research attention. One of the promising leakage detection method is to use lead zirconate titanate (PZT) transducers to detect the negative pressure wave when leakage occurs. PZT transducers can generate and detect guided stress waves for crack detection also. However, the negative pressure waves or guided stress waves may not be easily detected with environmental interference, e.g., the oil and gas pipelines in offshore environment. In this paper, a Gaussian mixture model based hidden Markov model (GMM-HMM) method is proposed to detect the pipeline leakage and crack depth in changing environment and time-varying operational conditions. Leakages in different sections or crack depths are considered as different states in hidden Markov models (HMM). Laboratory experiments show that the GMM-HMM method can recognize the crack depth and leakage of pipeline such as whether there is a leakage, where the leakage is.

The anomalous and smoothed anomalous envelope spectra for rotating machine fault diagnosis

The order-frequency spectral coherence and its integrated spectra (e.g. improved envelope spectrum, squared envelope spectrum) are some of the most powerful methods for performing fault diagnosis under time-varying operating conditions. However, it may require much work to interrogate the order-frequency spectral coherence for symptoms of damage. Hence, in this work we propose a methodology that combines the order-frequency spectral coherence with historical data that were acquired from a healthy machine to obtain an anomalous envelope spectrum, which is further processed for fault diagnosis. This anomalous envelope spectrum is further processed with a smoothing operation to not only perform automatic fault detection, but it is also possible to identify the damaged component if the kinematics of the gearbox are known. The proposed method is investigated on one numerical gearbox dataset and three experimental datasets, where its potential for performing automatic fault detection under time-varying operating conditions is highlighted.

An informative frequency band identification framework for gearbox fault diagnosis under time-varying operating conditions

The application of informative frequency band identification methods makes it possible to enhance weak damage components in the vibration signals acquired from rotating machines. Some rotating machines (e.g. wind turbines) operate inherently under time-varying operating conditions, however, very few frequency band identification methods have been developed with varying operating conditions in mind. Therefore, in this work, a systematic framework for obtaining consistent feature planes under time-varying operating conditions is proposed. This framework utilises the angle-frequency instantaneous power spectrum and the order-frequency cyclic modulation spectrum to construct feature planes. The kurtogram, the sparsogram, the infogram, the ICS2gram and the log-cycligram are obtained on numerical and experimental datasets acquired under time-varying operating conditions using this framework. In addition to this, we also implement the Informative Frequency Band Identification method using targeted cyclic orders, abbreviated to IFBIαgram, in this framework and compare the performance of this method against the other frequency band identification methods. Ultimately, we found that the feature used in the construction of the IFBIαgram is very well-suited for gear and bearing fault diagnosis under time-varying operating conditions.

Enhancing gearbox vibration signals under time-varying operating conditions by combining a whitening procedure and a synchronous processing method

Condition monitoring is very important to avoid unexpected breakdowns of expensive rotating machines found in the power generation and mining industries. The fault information in vibration signals is often buried in low energy frequency bands. In addition to this, time-varying operating conditions and the presence of impulsive components result in the signal to have time-varying spectral content, which impedes the condition inference process. The instantaneous power spectrum is a powerful method that for bearing and gear damage detection under time-varying operating conditions. In this work, we propose a new method of using the instantaneous power spectrum for improved fault diagnosis under time-varying conditions by enhancing the fault information in the vibration signals. It is shown on experimental datasets that the proposed method enhances the fault information in the signal, whereafter it can be used to obtain reliable condition indicators under time-varying operating conditions.

DeepFogSim: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms

The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early exits, executed atop virtualized multi-tier Fog platforms, makes feasible the real-time and energy-efficient execution of analytics required by future Internet applications. However, until now, toolkits for the evaluation of energy-vs.-delay performance of the inference phase of CDNNs executed on such platforms, have not been available. Motivated by these considerations, in this contribution, we present DeepFogSim. It is a MATLAB-supported software toolbox aiming at testing the performance of virtualized technological platforms for the real-time distributed execution of the inference phase of CDNNs with early exits under IoT realms. The main peculiar features of the proposed DeepFogSim toolbox are that: (i) it allows the joint dynamic energy-aware optimization of the Fog-hosted computing-networking resources under hard constraints on the tolerated inference delays; (ii) it allows the repeatable and customizable simulation of the resulting energy-delay performance of the overall Fog execution platform; (iii) it allows the dynamic tracking of the performed resource allocation under time-varying operating conditions and/or failure events; and (iv) it is equipped with a user-friendly Graphic User Interface (GUI) that supports a number of graphic formats for data rendering. Some numerical results give evidence for about the actual capabilities of the proposed DeepFogSim toolbox.

Dual Attention-Based Temporal Convolutional Network for Fault Prognosis Under Time-Varying Operating Conditions

Fault prognosis under time-varying operating conditions is critical to predictive maintenance of complex industrial machines. However, prognostic methods proposed in the literature toward varying operating conditions typically focus on limited discrete states with clear boundaries, which are not always encountered in practical scenarios. This article aims to propose a more general method that can handle complex operating conditions with more nonlinearity and dynamics. In this work, a novel deep model named dual attention-based temporal convolutional network (DATCN), is developed to integrate multisensor data with time-varying operating settings for health assessment of industrial machines. An efficient deep temporal convolutional network is introduced to extract degradation features for sequence modeling. A novel dual attention model is developed to adaptively capture the temporal dynamics of sensor data and operating data, further enhancing the feature representations and highlighting the degradation information under time-varying operating settings. Besides, domain adaptation layer with multikernel maximum mean discrepancies (MK-MMD) is embedded to mitigate the domain-shift issue caused by varying operating conditions. The experimental results on the popular turbofan engine data set and a real-world Ion mill etching process validate the effectiveness of the proposed method and show its superiority in yielding significant improvements of prognostic accuracy relative to existing state-of-the-art methods.

Design, optimization, and testing of a high-speed centrifugal pump for motorsport application

Centrifugal pumps are designed to have their BEP (Best Efficiency Point) for a given flow rate, hydraulic head, and speed. In the design phase, those parameters are combined into a dimensionless specific speed used to define geometry of the pump. In this paper, a downsized centrifugal pump has been designed to have high efficiency at very high speeds (10000 – 15000 RPM), as requested by the cooling circuit of an engine for motorsport and racing applications. The pump design point was 13 L/min and 3.0 bar at 12000 RPM, while the impeller external diameter is 34 mm. A mathematical model has been realized to optimize the pump in the early design phase through an iterative process, based on a 0D procedure which generates the optimal geometry of both impeller and volute. Hence, the model estimates main losses and, thus, hydraulic, volumetric, and organic efficiency. Once the geometry is generated, the performance of the pump has been verified on the design working point through a detailed CFD analysis. Physical phenomena that occur when the pump is running have been simulated, to represent as closely as possible vein fluid detachments, cavitation, and backflow at clearances between impeller and pump casing. At last, a prototype of the pump has been built and experimentally characterized in a dynamic test bench able to reproduce the characteristic curves (hydraulic head and efficiency) at very high revolution speeds as well as the performances in real time-varying operational conditions.

A decomposition heuristic algorithm for dynamic reconfiguration after contingency situations in distribution systems considering island operations

This paper presents a decision-making model for the dynamic reconfiguration of distribution networks after contingency situations based on formulations of the self-healing problem with islanding. This paper develops a three-stage algorithm. The first stage applies a greedy reconfiguration heuristic, which calculates the criteria values for each viable network configuration in each hour. To address the variety of criteria, the analytic hierarchy process method is applied to define the weights. The second stage addresses the problem statically to reduce the number of configurations and, therefore, the combinations of step 3. In the third stage, the problem is approached dynamically, generating the optimal sequence of topologies for the analyzed period, while considering the time-varying operational conditions of the system. The proposed heuristic significantly reduces the complexity of the problem while minimizing the following criteria: energy not supplied, losses, number of interrupted consumers and switch operations. The physical constraints of the power grid considered in the proposed model are the line limits, protective equipment settings, voltage limits, distributed generators (DG) limits and network radiality. The proposed model is analyzed in different scenarios in the IEEE 123-bus system, modified with the insertion of DGs. The proposed method is compared with a conventional benchmark model.

Fault diagnosis for rolling bearings under unknown time-varying speed conditions with sparse representation

In practice, bearings often run at a time-varying speed, which induces non-stationary vibration signals. How to extract the fault characteristic frequency (FCF) effectively under unknown variable speed conditions is a challenging work. This paper proposes a sparse time frequency method for fault diagnosis with no speed information demanded. Firstly, the Hilbert Transform is used to demodulate the vibration signal. Then the iterated soft-thresholding algorithm is applied to solve the l1 norm regularized linear least squares cost function. The sparsity of the FCF is expounded in detail, and how to choose the basis to map the vibration signal into the sparse space is also detailed. With the appropriate basis, the solution is exactly the optimized sparse TFR, which can enhance both time and frequency resolutions greatly, and meanwhile denoise the signal effectively. This method does not produce the confusing components when the bearing is in the healthy condition, while indicates the FCF when the bearing is defective. To show the robustness of the effectiveness, the proposed method is verified with simulated and experimental signals under various time-varying operating conditions. All the signals are also processed with the STFT, Fourier-based Synchrosqueezing Transform and ridge extraction method for comparison.

A Holistic Probabilistic Framework for Monitoring Nonstationary Dynamic Industrial Processes

Multivariate statistical process monitoring (MSPM) methods provide sensitive indicators of process conditions by harnessing the value of massive process data. Large-scale industrial processes are subject to wide-range time-varying operating conditions such that some variables inevitably exhibit nonstationary behavior, which poses significant challenges for the design of MSPM schemes. In this brief, a novel nonstationary probabilistic slow feature analysis algorithm is developed to comprehensively describe both nonstationary and stationary variations that underlie process measurements during routine operations. For efficient parameter estimation, the expectation-maximization algorithm is employed. By modeling nonstationarity and stationarity as the random walk and stable autoregressive processes, interpretable monitoring statistics are constructed to detect abnormality in nonstationary dynamics, stationary dynamics, and stationary steady conditions. This forms a holistic and pragmatic monitoring framework for industrial processes, which is beneficial for reducing false alarms and providing meaningful operational information for industrial practitioners. The efficacy of the proposed monitoring framework is validated via two case studies.

Combining an optimisation-based frequency band identification method with historical data for novelty detection under time-varying operating conditions

Incipient damage detection is important for critical rotating machines such as gearboxes found in the power generation, mining and aeronautical industries. However, the fault information frequently manifests in weak frequency bands in the vibration signals and the fault diagnosis process is impeded by time-varying operating conditions. Frequency band identification methods can be used to enhance the weak fault information in the vibration signal, however, this process is impeded by impulsive components unrelated to the component-of-interest and time-varying operating conditions. Hence, in this work, an optimisation-based frequency band identification method is developed to address these shortcomings. This method comprises of two steps; in the first step, a coarse informative frequency band procedure is used, whereafter a derivative-free optimisation algorithm is utilised to find the optimal frequency band for fault diagnosis. Since many rotating machines operate for long periods of time in a healthy condition, much healthy historical data are usually available when continuous monitoring is performed. Hence, this historical data are used with the proposed frequency band identification approach for automatic fault detection. The method is investigated on two experimental datasets acquired under time-varying operating conditions and compared to other existing approaches for fault diagnosis. The results indicate that the method is very capable of enhancing the fault information and can be used for automatic fault detection under time-varying operating conditions.