Search results

The purpose of this paper is to predict the remaining useful life of a natural gas export compressor, in order to assist decision making of the next planned work order.

Extraction and aggregation of information from rapid developing condition‐monitoring systems has given rise to the Technical Condition Index (TCI) methodology. The trends of aggregated TCIs at compressor level and historical work orders were used as the basis for remaining useful life estimation.

The model is merging several condition‐related measurements and quantifying belief in aging versus belief in condition monitoring. This is important information in, for example, maintenance policy selection, and for the choice of a remaining useful life approach.

The model requires historical failure data and well documented condition‐related measurements. Investigation of the physics of failure at the component level also seems important for prognostic theory development.

The proposed methodology combines the TCI methodology, the survival analysis (PHM) methodology, and the general maximum‐likelihood theory to estimate and validate parameters and remaining useful life.

This article aims to show the application of scientometrics and patent bibliometrics in remaining useful life (RUL) analysis for evaluating the value of intangible assets.

Technology innovation management is strictly related to the RUL. The RUL concept is defined as the time remaining until the reliability drops below a defined minimal operating threshold. The RUL analysis of certain intangible assets (patents and know‐how licence agreements, industrial designs, trade marks, logos, customer base) is done through different methodologies and various different approaches. The key subject in all these methodologies is the life cycle of the technology. The analyst tries to approach the foresight of the life cycle of technology to establish its value in use. Different life measure systems are considered in RUL analysis depending on different typologies of technology life: statutory, contract, judicial, economic and functional. Data used in life cycle estimation may be used in RUL analysis. Typically, these data include scientific articles, registration documents (patent applications, trade marks and copyright applications), commercial contracts, judicial orders, financial statements and technology data.

The analysis of the life cycle allows the incorporation of qualitative considerations (legal, contractual, physical, technical know‐how, functional, economic) related to the conduct of future technologies. But technology development is conditioned by trends in scientific research and by the changes in the marketing dynamic, today and in the future. Qualitative methods provide a valuable information service that relates to the intangible assets over time. The “typical survivor curve” shows the released, remaining and probable life span of a certain technology by taking into account factors such as technological changes, marketing acceptance, and other exogenous and endogenous factors. Quantitative analysis of scientific production, applications for patents, industrial designs and trade marks, developed in scientometrics and bibliometrics, provide an unbiased guide to R&D and business trends.

The original purpose of the paper is to emphasise how the technology life cycle is influenced by changes in technology but also in scientific research evolution. Scientific research life analysis must examine the historical emergence or decay of a certain intellectual interest in the scientific community through the study of what is and what is not published in scientific journals.

The purpose of this paper is to check the actual life of lubricating oil.

Present work aims to find the remaining useful life of the lubricant based on study of periodic deterioration of oil. Chronological samples of oil were selected from the dumper of a local open cast mine. The deterioration in oil was studied using Fourier transform infrared (FTIR) spectroscopy.

The data obtained from FTIR spectroscopy was used in vector projection approach and analytical hierarchy process to evaluate the remaining useful life of the lubricating oil.

FTIR spectra were used to study the periodic deterioration of oil. IR radiation with all frequencies in the range was passed through the sample. Radiations at certain frequency, depending upon the molecular structure of compounds in the sample were absorbed and rest was transmitted by the sample. A spectrum representing molecular absorption or transmission was obtained. Transmission spectra have been used in the study. Comparing the percent value of transmission peak of different chronological sample with that of fresh oil was used to represent the periodic degradation in oil.

Failure of a critical reinforced concrete beam due to fatigue can have severe safety and production consequences, and preventative repair/replacement of such a beam is expensive. It would therefore be beneficial if repair/replacement can be done based on an accurately and conservatively predicted remaining useful life (RUL). The purpose of this paper is to develop such a model.

Condition-based maintenance is a maintenance approach that uses empirical/analytical models and a measurable condition to predict remaining useful life. The P-F curve (condition-life) is a useful tool that can aid in making these decisions. A model to create a P-F curve is developed using rebar fatigue test results (in the form of an S–N curve) and the Palmgren-Miner law of damage accumulation. A Monte Carlo simulation with statistical distributions is employed to provide confidence levels of RUL outputs.

An example of how the model can successfully be used in practice is shown in this paper, and a sensitivity study is performed leading to conclusions being drawn with regard to damage tolerant design considerations.

If a critical reinforced concrete beam fails due to fatigue can have serious consequences. This paper develops a model to help base repair/replacement decisions based on accurately and conservatively predicted RUL. Financial and safety benefits would be gained if this model would be used in practice.

Reverse supply chain (RSC) is an extension of the traditional supply chain (TSC) motivated by environmental requirements and economic incentives. TSC management deals with planning, executing, monitoring, and controlling a collection of organizations, activities, resources, people, technology, and information as the materials and products move from manufacturers to the consumers. Except for a short warranty period, TSC excludes most of the responsibilities toward the product beyond the point of sale. However, because of growing environmental awareness and regulations (e.g. product stewardship statute), TSC alone is no longer an adequate industrial practice. New regulations and public awareness have forced manufacturers to take responsibilities of products when they reach their end of lives. This has necessitated the creation of an infrastructure, known as RSC, which includes collection, transportation, and management of end-of-life products (EOLPs). The advantages of implementing RSC include the reduction in the use of virgin resources, the decrease in the materials sent to landfills and the cost savings stemming from the reuse of EOLPs, disassembled components, and recycled materials. TSC and RSC together represent a closed loop of materials flow. The whole system of organizations, activities, resources, people, technology, and information flowing in this closed loop is known as the closed-loop supply chain (CLSC).

In RSC, the management of EOLPs includes cleaning, disassembly, sorting, inspecting, and recovery or disposal. The recovery could take several forms depending on the condition of EOLPs, namely, product recovery (refurbishing, remanufacturing, repairing), component recovery (cannibalization), and material recovery (recycling). However, neither the quality nor the quantity of returning EOLPs is predictable. This unpredictable nature of RSC is what makes its management challenging and necessitates innovative management science solutions to control it.

In this chapter, we address the order-driven component and product recovery (ODCPR) problem for sensor-embedded products (SEPs) in an RSC. SEPs contain sensors and radio-frequency identification tags implanted in them at the time of their production to monitor their critical components throughout their lives. By facilitating data collection during product usage, these embedded sensors enable one to predict product/component failures and estimate the remaining life of components as the products reach their end of lives. In an ODCPR system, EOLPs are either cannibalized or refurbished. Refurbishment activities are carried out to meet the demand for products and may require reusable components. The purpose of cannibalization is to recover a limited number of reusable components for customers and internal use. Internal component demand stems from the component requirements in the refurbishment operation. It is assumed that the customers have specific remaining-life requirements on components and products. Therefore, the problem is to find the optimal subset and sequence of the EOLPs to cannibalize and refurbish so that (1) the remaining-life-based demands are satisfied while making sure that the necessary reusable components are extracted before attempting to refurbish an EOLP and (2) the total system cost is minimized. We show that the problem could be formulated as an integer nonlinear program. We then develop a hybrid genetic algorithm to solve the problem that is shown to provide excellent results. A numerical example is presented to illustrate the methodology.

Opportunistic maintenance gives the maintenance crew an opportunity to replace or repair those items, which are found to be defective or needs replacement in the immediate future, during the maintenance of a sub‐system or a module. This paper tries to address the questions of how to decide whether a particular item needs opportunistic maintenance, and if so how cost effective the opportunistic maintenance is in comparison to a later grounding. These questions play an important role, especially in case of complex systems containing expensive items with hard lives and condition monitoring maintenance strategies. A systematic analysis of selection of components that require opportunistic maintenance is carried out, after which genetic algorithms are used to decide whether opportunistic maintenance is cost effective or not. A hypothetical example is used to describe the methodology for genetic algorithms.

The purpose of this paper is to present a weakly supervised learning method to perform health evaluation and predict the remaining useful life (RUL) of rolling bearings.

Based on the principle that bearing health degrades with the increase of service time, a weak label qualitative pairing comparison dataset for bearing health is extracted from the original time series monitoring data of bearing. A bearing health indicator (HI) quantitative evaluation model is obtained by training the delicately designed neural network structure with bearing qualitative comparison data between different health statuses. The remaining useful life is then predicted using the bearing health evaluation model and the degradation tolerance threshold. To validate the feasibility, efficiency and superiority of the proposed method, comparison experiments are designed and carried out on a widely used bearing dataset.

The method achieves the transformation of bearing health from qualitative comparison to quantitative evaluation via a learning algorithm, which is promising in industrial equipment health evaluation and prediction.

The method achieves the transformation of bearing health from qualitative comparison to quantitative evaluation via a learning algorithm, which is promising in industrial equipment health evaluation and prediction.

With the promotion of lithium-ion battery, it is more and more important to ensure the safety usage of the battery. The purpose of this paper is to analyze the battery operation data and estimate the remaining life of the battery, and provide effective information to the user to avoid the risk of battery accidents.

The particle filter (PF) algorithm is taken as the core, and the double-exponential model is used as the state equation and the artificial neural network is used as the observation equation. After the importance resampling process, the battery degradation curve is obtained after getting the posterior parameter, and then the system could estimate remaining useful life (RUL).

Experiments were carried out by using the public data set. The results show that the Bayesian-based posterior estimation model has a good predictive effect and fits the degradation curve of the battery well, and the prediction accuracy will increase gradually as the cycle increases.

This paper combines the advantages of the data-driven method and PF algorithm. The proposed method has good prediction accuracy and has an uncertain expression on the RUL of the battery. Besides, the method proposed is relatively easy to implement in the battery management system, which has high practical value and can effectively avoid battery using risk for driver safety.

Rolling element bearings (REBs) are commonly used in rotating machinery such as pumps, motors, fans and other machineries. The REBs deteriorate over life cycle time. To know the amount of deteriorate at any time, this paper aims to present a prognostics approach based on integrating optimize health indicator (OHI) and machine learning algorithm.

Proposed optimum prediction model would be used to evaluate the remaining useful life (RUL) of REBs. Initially, signal raw data are preprocessing through mother wavelet transform; after that, the primary fault features are extracted. Further, these features process to elevate the clarity of features using the random forest algorithm. Based on variable importance of features, the best representation of fault features is selected. Optimize the selected feature by adjusting weight vector using optimization techniques such as genetic algorithm (GA), sequential quadratic optimization (SQO) and multiobjective optimization (MOO). New OHIs are determined and apply to train the network. Finally, optimum predictive models are developed by integrating OHI and artificial neural network (ANN), K-mean clustering (KMC) (i.e. OHI–GA–ANN, OHI–SQO–ANN, OHI–MOO–ANN, OHI–GA–KMC, OHI–SQO–KMC and OHI–MOO–KMC).

Optimum prediction models performance are recorded and compared with the actual value. Finally, based on error term values best optimum prediction model is proposed for evaluation of RUL of REBs.

Proposed OHI–GA–KMC model is compared in terms of error values with previously published work. RUL predicted by OHI–GA–KMC model is smaller, giving the advantage of this method.

With the rapid development and stable operated application of lithium-ion batteries used in uninterruptible power supply (UPS), the prediction of remaining useful life (RUL) for lithium-ion battery played an important role. More and more researchers paid more attentions on the reliability and safety for lithium-ion batteries based on prediction of RUL. The purpose of this paper is to predict the life of lithium-ion battery based on auto regression and particle filter method.

In this paper, a simple and effective RUL prediction method based on the combination method of auto-regression (AR) time-series model and particle filter (PF) was proposed for lithium-ion battery. The proposed method deformed the double-exponential empirical degradation model and reduced the number of parameters for such model to improve the efficiency of training. By using the PF algorithm to track the process of lithium-ion battery capacity decline and modified observations of the state space equations, the proposed PF + AR model fully considered the declined process of batteries to meet more accurate prediction of RUL.

Experiments on CALCE dataset have fully compared the conventional PF algorithm and the AR + PF algorithm both on original exponential empirical degradation model and the deformed double-exponential one. Experimental results have shown that the proposed PF + AR method improved the prediction accuracy, decreases the error rate and reduces the uncertainty ranges of RUL, which was more suitable for the deformed double-exponential empirical degradation model.

In the running of UPS device based on lithium-ion battery, the proposed AR + PF combination algorithm will quickly, accurately and robustly predict the RUL of lithium-ion batteries, which had a strong application value in the stable operation of laboratory and other application scenarios.