Degradation Data Research Articles

A remaining useful life prediction method of aluminum electrolytic capacitor with adaptive degradation model selection

The degradation process of aluminum electrolytic capacitors(AECs) usually exhibits characteristics such as non-linearity and multi-stage. These degradation features lead to the difficulty to accurately predict the remaining useful life(RUL) of the whole degradation process of AECs. To address this, by dividing the capacitor degradation process into two stages, a two-stage RUL prediction method for AECs considering multiple degradation models is proposed in this paper.In the offline parameter estimation phase, the initial degradation model parameters of two stages are estimated using two-step maximum likelihood estimation combined with particle swarm optimization(PSO) algorithm. In the dynamic parameter updating phase, a sequential Bayesian method is used to update the model parameters. To select the optimal degradation model, an evaluation method based on historical RUL similarity is proposed to calculate the fitness of each model. Finally, the effectiveness of the method is verified on NASA’s accelerated degradation data set and several widely used methods are used for comparison. The experimental results show that the proposed method has higher accuracy, which proves the superiority of the method.

Subjectivity of visual assessments in FOCUS kinetics and acceptability of first-order fits for regulatory modelling

The degradation half-life (DegT50) of a substance in soil plays an important role in the approval process of a plant protection product and is a sensitive input parameter for regulatory models. It is usually derived through least squares optimizations of mathematical models to measured degradation data according to EU FOCUS degradation kinetics guidance. A strong consensus on degradation parameters provides a solid foundation for parts of the environmental risk assessment. The DegT50 of a substance for regulatory modeling is preferably derived from a single first-order (SFO) model as this is currently the only kinetic model implemented in EU regulatory models of the environmental fate of pesticides. However, kinetic optimisation tools do not always provide a regulatory acceptable SFO fit even though a visual inspection of the data suggests it may be possible. It was therefore hypothesized that more acceptable SFO fits might be achieved by adapting the objective function that is minimized during the optimization.Eight objective functions with varying weightings were tested on 29 laboratory soil degradation datasets. A web-based app was developed to allow experts in environmental safety of plant protection products to visually assess the goodness of fits resulting from different objective functions. The visual assessments and a quantitative metric, newly introduced in the proposed update of the FOCUS guidance, show that the acceptability of SFO fits can be increased, but no single objective function exclusively improves all fits. The assessment reveals that expert judgment is very subjective. Participants tended to change their mind when judging the acceptance of a fit, assumingly caused by a learning curve or a period of calibration.It is concluded that different objective functions could be considered in the kinetic assessment as it can improve the acceptability of SFO fits and hence endpoints for regulatory modeling. This study reveals that various qualitative factors influence the visual judgment of experts when performing a kinetic modeling assessment. The proposed quantitative metric seems to be in alignment with the visual assessment of fits to derive modeling endpoints and a promising step toward less subjective kinetic modeling assessments.

A comprehensive framework for estimating the remaining useful life of Li-ion batteries under limited data conditions with no temporal identifier

The escalating applications of Lithium-ion (Li-ion) batteries in renewable energy and electric vehicles underscore the need for enhanced prognostics and health management systems to reduce the risk of sudden failures. Remaining useful life (RUL) determination is one of the most critical tasks in the field of battery prognostics nowadays. Even though statistical and machine learning (ML) methods have proven effective in research setups, many challenges prevent applying these prediction methods to real-life scenarios. These challenges include (1) scarcity of run-to-failure datasets with similar experimental conditions, (2) low data granularity when presented in capacity vs. discharge cycle pairs, and (3) lack of “temporal identifiers” in real-life scenarios. A temporal identifier is any label that provides knowledge about the current degradation state of a working battery. The research question developed for this study was, ‘Can the remaining useful life of a Li-ion battery having limited data without a temporal identifier be predicted?’ The specific aims were to estimate the temporal identifier of limited data and to predict the remaining useful life (RUL). An innovative framework incorporating reliability analysis and deep learning addresses these specific aims. Experimental data is used to test the framework's capabilities, limiting the training dataset to only three batteries and the testing dataset to a small sample (< 10 data points) of another battery. This new approach enabled the RUL prediction to achieve errors as low as ∼5 cycles and root mean square error of 6.24 cycles, outperforming other benchmark studies on Li-ion battery RUL prediction that use more battery degradation data without temporal identifier.

Unsupervised health indicator construction by a new Gaussian-student’s t-distribution mixture model and its application

The equipment’s remaining useful life (RUL) must be accurately estimated to guarantee its reliable operation. As a crucial part of data-driven RUL prediction, the health indicator (HI) construction method employing the distribution discrepancies can represent the variation trend of health conditions. However, the existing Gaussian mixture model based HI construction method cannot accurately estimate the long-tail distribution characteristics in some degradation data. Moreover, it cannot comprehensively mine the distribution characteristics of degradation data by leveraging different types of distributions. A novel Gaussian-student’s t-distribution mixture model (GSMM) that simultaneously considers Gaussian distribution and student’s t-distribution is developed in this work to estimate the distributions of normal and degradation data. Next, the distribution contact ratio metric (DCRM) is applied to measure the discrepancies between the baseline distribution of normal data and the distributions of test data at different moments. The bearing HI can be constructed with the acquired DCRMs. Finally, the effectiveness and merit of the developed HI construction approach are validated by two bearing life-cycle datasets. The experimental results illustrate that the GSMM-based HI performs better than other classical and state-of-the-art HIs. Additionally, the constructed HI is more suitable for bearing RUL prediction.

Bayesian Approach for Estimating the Parameters of the Time-To-Failure Distribution and Its Percentiles Under Power Degradation Model

The degradation models are often applied on the degradation data for studying time-to-failure distribution. In this study, the Bayesian approach is applied on the power degradation model for estimating the parameters of the time-to-failure distribution and its percentiles. Two different distributions are assumed for the degradation parameter of the model. The degradation parameter is firstly assumed to follow the skew-normal distribution with three jointly independently distributed parameters such that the gamma prior is assumed for the shape parameter, while the scale and the location parameters are assumed uniform. The second distribution assumed for the degradation parameter is the log-logistic distribution with two jointly independent random parameters where the shape parameter is assumed gamma, while the scale parameter is assumed uniform. Based on the Gibbs sampling method carried out under the JAGS platform, the models considered are applied on the simulated data and the NASA turbofan Jet engine dataset and the results found are compared. In modeling the time-to-failure distribution, it is shown that based on the simulated data and real data, the Bayesian approach for the power degradation model with the skew-normal degradation parameter outperformed the Bayesian approach for the power degradation model with the log-logistic degradation parameter.

A Study on the Collection of Degradation Data and Anomaly Detection Based on Artificial Neural Network for the Application of Condition-Based Maintenance Plus (CBM+) in Single Board Computer

A Study on the Collection of Degradation Data and Anomaly Detection Based on Artificial Neural Network for the Application of Condition-Based Maintenance Plus (CBM+) in Single Board Computer

Kinetics and mechanism of thermal and thermo-oxidative degradation for high-density polyethylene modified by fullerene and its derivative

To investigate the effect of fullerene (C60) and its iron compound (C60-Fe) on the thermal and thermo-oxidative degradation mechanism of high-density polyethylene (HDPE), the Kissinger method, Flynn-Wall-Ozawa method and Coats-Redfern methods are used. The data of thermal and thermo-oxidative degradation are achieved through the thermogravimetric (TG) analysis, and the trapping free-radical ability and the dispersion of C60 or C60-Fe in matrix are characterized by the electron spin resonance (ESR) and transmission electron microscopy (TEM). C60 and C60-Fe improve effectively the thermal and thermo-oxidative stability of HDPE. In N2, C60 and C60-Fe do not change the degradation mechanism of HDPE, and the degradation rate is determined by the random generation and growth of free-radicals. In air, C60 changes the reaction order (n) of HDPE at the oxidation stage and the degradation mechanism at the random fracture. C60-Fe changes the thermo-oxidative mechanism of HDPE due to the formation of cross-linked network.

An intriguing way to synthesize a TiO2–ZnO hybrid nanostructure for the pragmatic application as a photocatalyst

In an attempt to counter the problem of treating wastewater more efficiently, we report the study on photocatalytic properties of metal oxide nanostructures under different light sources. A novel sonication-assisted refluxing method was employed to synthesize a binary heterostructure consisting of TiO2 and ZnO. XRD and EDS analysis of synthesized materials confirm the presence of both TiO2 and ZnO. Also, the change in the intensity of XRD peaks and elemental composition are well observed with a change in molar concentration of Ti and Zn. HR-TEM micrographs show nanostructures having hybrid Janus and Core-shell type structures. The XPS spectra were probed to identify the surface chemical species associated with the prepared heterostructures. Raman spectra confirm the smaller ZnO particles attached over agglomerated TiO2 as a shell layer as depicted in TEM results. Optical studies exhibit the modification in the band structure of the materials due to the formation of the heterostructure. The synthesized hybrid catalyst shows impressive results in photocatalytic performance. The catalytic potency of the prepared heterostructures under UV light is reminiscent of Anatase while it gets convalescent with an increment of Zn content under visible light. The photocatalytic performance of synthesized materials under sunlight shows their potential to be utilized as commercial catalysts for direct application in wastewater treatment. The kinetic study of the degradation data reveals interesting facets of the catalysis. It suggests that the photo-corrosion of the catalyst inordinately changes the rate of photocatalytic reaction which ultimately affects the photocatalytic efficiency of the catalyst. The study also discusses the role of kinetic and validation parameters in the selection of the best-fitted kinetic model with realistic arguments.

Extraction, Purification, Structural Characterization, and Antitumor Effects of Water-Soluble Intracellular Polysaccharide (IPSW-1) from Phellinus igniarius Mycelia.

Phellinus igniarius is a commonly used Chinese medicine fungus, and its polysaccharide is a valuable bioactive with antioxidant, antiaging, antitumor activities, etc. However, their bioactivities are influenced by their structural and physicochemical properties. Hence, this research isolated and purified homogeneous water-soluble intracellular polysaccharide (IPSW-1) from P. igniarius mycelia. A coherent study of its structural characteristics, conformation, and antitumor mechanisms was evaluated. The results showed IPSW-1 has no triple helical conformation according to the Congo red test. Based on FT-IR, periodate oxidation, Smith degradation, methylation analysis, 1H and 13C NMR spectroscopy data, and IPSW-1 consisted of α-d-glucopyranose (Glcp). The backbone of IPSW-1 consisted primarily of repeating three (1 → 6)-linked α-d-Glcp and one (1 → 3,4)-linked α-d-Glcp, with one terminal α-d-Glcp as side chains of 3-O-connected to the main chain for every four residues. The IPSW-1 had an inhibitory influence on HepG2 cell proliferation and inhibited the migration and invasion ability by down-regulating the expression levels of MMP-7 and RhoA. Moreover, IPSW-1 could inhibit the lysis of autophagosomes to inhibit autophagy and regulate mitochondrial membrane potential and pro-apoptotic protein Bax, which causes the caspase cascade to promote apoptosis, thereby inhibiting the role of tumor cells. These findings show IPSW-1 holds potential as an innovative functional food.

Dynamic predictive maintenance strategy for multi‐component system based on LSTM and hierarchical clustering

AbstractIn recent years, there has been growing interest in employing predictive methods to forecast the remaining useful life of industrial equipment. However, the challenge lies in how to take advantage of the dynamic predictive information to facilitate the maintenance of decision‐making. This problem becomes particularly challenging for complex industrial systems consisting of multiple components with economic dependencies. This paper aims at providing an effective maintenance strategy for multi‐component systems based on predictive information, while considering economic dependencies among different system components. To this end, a dynamic predictive maintenance (PdM) strategy that minimizes the mean maintenance cost over a decision period is proposed, where both long‐term and short‐term policies are integrated into the decision‐making framework. Specifically, the long‐term policy is formulated using predictions derived from historical degradation data through a Long Short‐Term Memory (LSTM) model. Concurrently, real‐time monitoring data is employed to forecast imminent degradation in components, serving as a basis for determining the necessity of short‐term adjustments. This paper embeds the consideration of economic dependencies among components within the maintenance strategy design and employs hierarchical clustering to establish an effective and efficient maintenance grouping policy. The experimental results demonstrate that our proposed strategy significantly outperforms conventional approaches, including block‐based and age‐based maintenance, resulting in substantial cost savings. The proposed strategy is also compared with a similar version without grouping, and the results verify the added value of the optimal maintenance grouping policy in cost reduction. Moreover, a comprehensive analysis of the proposed method is provided, including the impact of different inspection costs and inspection intervals on maintenance decision‐making, which can provide insightful guidance to various PdM scenarios in practice.

Characteristics of Vegetation and Soil of Degraded Grasslands and Their Relationships in Xizang

To investigate the characteristics of grassland degradation on a regional scale in Xizang, data on grassland degradation from the second grassland survey of Xizang and 12 vegetation and soil indicators from the National Tibetan Plateau Data Center were collected. Using ArcMap, 10 000 random sample points were selected on raster data （excluding non-grassland, desertification, and salinization data, leaving 7 949 valid sample points）. The multi-value extraction to-point method was applied to extract degradation and indicator data for each sample point. The characteristics of degraded grassland vegetation and soil and their relationships were analyzed in Xizang. Moreover, random forest modeling was conducted to predict the trend of grassland ecosystem changes. The results indicated that： ① The grasslands in Xizang were primarily composed of alpine steppe and alpine meadow types, accounting for 45.83% and 41.15% of the valid sample points, respectively. ② With the intensification of grassland degradation, the number of steppe-type species among the 17 grassland types gradually decreased, and the proportion of steppe dominated by species such as Stipa purpurea and Carex moorcroftii decreased, whereas the proportion of miscellaneous grasses and Dasiphora fruticosa increased. ③ As the degree of degradation increased, vegetation indicators generally showed a declining trend, with soil total nitrogen, total phosphorus, total potassium, and organic carbon decreasing, whereas soil pH and bulk density increased, and soil moisture content was not significant. ④ A positive correlation exists between soil moisture content, total nitrogen, total phosphorus, total potassium, organic carbon, vegetation cover, net primary productivity of vegetation, normalized difference vegetation index, aboveground biomass, and habitat quality. However, there was a negative correlation between pH and soil bulk density, and the correlation coefficients among various indicators decreased with the intensification of degradation. ⑤ The random forest simulation results showed that during the degradation process, the contribution rates of soil bulk density and habitat quality both exceeded 12%, with the model prediction accuracy reaching 78%. The study revealed that grassland degradation in Xizang was closely related to soil bulk density and habitat quality, indicating that higher soil bulk density or lower habitat quality may correspond to more severe grassland degradation. This provides a scientific basis for future grassland conservation and management.

Reliability test for degradation data based on ranked set sampling

AbstractIn this article, we consider test for the two null hypotheses for and , two widely useful tests in reliability, based on ranked set sampling (RSS). We derive the likelihood ratio test as well as the associated exact and asymptotic results. Considering a fixed significance level and power of the test, we show that the proposed test statistic outperforms the existing test. In small sample cases, the proposed test leads to a much narrower confidence interval for the reliability function . Then, the test statistics obtained from simple random sampling and RSS schemes are compared through which, the efficiency of using RSS is demonstrated. For illustration, we apply the proposed test to a degradation data from the reliability literature. Upon using RSS, the cost of measurement gets reduced and efficiency gets improved, suggesting the importance and use of RSS data in reliability experiments and their design.

Modeling Particle Versus SEI Cracking in Lithium-Ion Battery Degradation: Why Calendar and Cycle Aging Cannot Simply be Added

Degradation models are important tools for understanding and mitigating lithium-ion battery aging, yet a universal model that can predict degradation under all operating conditions remains elusive. One challenge is the coupled influence of calendar and cycle aging phases on degradation mechanisms, such as solid electrolyte interphase (SEI) formation. In this work, we identify and systematically compare three different SEI interaction theories found in the literature, and apply them to experimental degradation data from a commercial lithium-ion cell. In a step-by-step process, and after careful data selection, we show that SEI delamination without any cracking of the active particles, and SEI microcracking, where cycling only affects SEI growth during the cycle itself, are both unlikely candidates. Instead, the results indicate that upon cycling, both the SEI and the active particle crack, and we provide a simple, 4-parameter equation that can predict the particle crack rate. Contrary to the widely-accepted Paris’ law, the particle crack rate decreases with increasing cycles, potentially due to changing intercalation dynamics resulting from the increasing surface-to-volume ratio of the active particles. The proposed model predicts SEI formation accurately at different storage conditions, while simply adding the degradation from pure calendar and cycle aging underestimates the total degradation.

An embedding layer-based quantum long short-term memory model with transfer learning for proton exchange membrane fuel stack remaining useful life prediction

The battery management system (BMS) plays a critical role in electric vehicles (EVs), with the prediction of remaining useful life (RUL) being of utmost importance. This functionality enables real-time monitoring and enhances driver assistance through intelligent driving mechanisms. To improve the precision of stack voltage degradation and RUL prognostication for proton exchange membrane fuel cell (PEMFC) aging, especially with limited real-time training data, we propose a novel approach using a layer-enhanced quantum long short-term memory model with transfer learning. The proposed model is trained offline using historical stack voltage degradation data from a source stack, which is then fine-tuned and transferred to a target stack. Comparative evaluations demonstrate the model's robustness, with consistently low root mean square errors in stack voltage predictions, even with increased training data. The proposed model significantly improves RUL prediction accuracy, achieving a maximum relative accuracy enhancement of 1.33 % when initiating predictions at 712 h. These results affirm the effectiveness of our approach in enhancing the accuracy of PEMFC aging prognosis, thereby offering valuable insights for practical integration within the BMS framework for EVs.

A new multivariate gamma process model for degradation analysis

AbstractIn reliability engineering, it is frequently encountered that multiple performance characteristics (PCs) deteriorate simultaneously. The associated degradation processes are usually dependent and exhibit some heterogeneity from unit to unit, which makes the multivariate degradation modeling and reliability evaluation more challenging. To this end, we propose a new multivariate gamma process model. This model introduces a multivariate random vector, whose joint distribution is constructed by marginal gamma distributions and a copula function, to describe the unit‐to‐unit variability and the dependence among PCs. Meanwhile, it does not require all PCs to be inspected at the same time points in contrast to the traditional copula‐based degradation models. In addition, two reliability evaluation methods are developed. Model parameters are estimated by the stochastic expectation maximization algorithm, and a three‐step procedure is provided to initialize this algorithm. Subsequently, numerical simulations are implemented to verify the proposed methods. Finally, two examples are provided for illustration, and it is shown that the proposed model and methods scale well to the degradation data with different numbers of PCs. What is more, comparisons with several benchmark models are performed, and the superiority of the proposed model is well demonstrated.

Remaining Useful Life prediction based on physics-informed data augmentation

Current approaches for monitoring machine health (SOH) and effective prognostics depend on the extensive use of complete degradation data trajectories, implying the reliance on data generation techniques that involve functional degradation of the real system until the failure state is reached. These commonly adopted approaches that depend on labeled target data remain operationally and economically nonviable for most industries and safety critical systems. This paper presents novel approaches that alleviate the existing dependence of most prognostics procedures on Remaining Useful Life (RUL) labeled data for training. To this end, firstly, a hybrid data augmentation procedure is proposed that enables the integration of system knowledge available a priori as well as physics of failure, within the training data. Secondly, an unsupervised Health Index (HI) extraction approach is developed, followed by a long-term prediction of this same HI, that leads to an efficient prediction of RUL without labeled data. Finally, a reliability-based assessment is performed to validate the proposed approach. This comprehensive approach (i.e. integrating all the various stages involved in achieving a RUL prediction based on unlabeled data) is tested on a real industrial aircraft system demonstrating the effectiveness of the proposed approach in real industrial context.

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability

AbstractThis research explores the reliability of deep learning, specifically Long Short‐Term Memory (LSTM) networks, for estimating the Hurst parameter in fractional stochastic processes. The study focuses on three types of processes: fractional Brownian motion (fBm), fractional Ornstein–Uhlenbeck (fOU) process, and linear fractional stable motions (lfsm). The work involves a fast generation of extensive datasets for fBm and fOU to train the LSTM network on a large volume of data in a feasible time. The study analyses the accuracy of the LSTM network's Hurst parameter estimation regarding various performance measures like root mean squared error (RMSE), mean absolute error (MAE), mean relative error (MRE), and quantiles of the absolute and relative errors. It finds that LSTM outperforms the traditional statistical methods in the case of fBm and fOU processes; however, it has limited accuracy on lfsm processes. The research also delves into the implications of training length and valuation sequence length on the LSTM's performance. The methodology is applied to estimating the Hurst parameter in li‐ion battery degradation data and obtaining confidence bounds for the estimation. The study concludes that while deep learning methods show promise in parameter estimation of fractional processes, their effectiveness is contingent on the process type and the quality of training data.

An adversarial-based domain generalization method for the health evaluation of axial piston pumps

Abstract The axial piston pump is the power component in hydraulic systems and evaluating its health status is of great importance to the safe operation of hydraulic systems. Discharge pressure signals are common monitoring signals for axial piston pumps, but it is difficult to obtain satisfactory health evaluation results by directly using raw discharge pressure signals since the degradation information lies in some specific frequency bands. Furthermore, the axial piston pump often operates under different operating conditions and most existing deep learning models have low diagnostic accuracies due to the problems of insufficient degradation data and different data distribution. This paper proposes an adversarial-based domain generalization (DG) method by integrating time-frequency analysis and data augmentation, to accurately predict the health status of axial piston pumps under unknown working conditions. First, discharge pressure signals under various operating conditions are decomposed by using the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and effective intrinsic mode functions (IMFs) are selected to train multiple convolutional neural network (CNN) models. Second, a novel data augmentation method based on the modified discrete cosine transform-composite spectrum (DCS) algorithm is introduced to fuse the IMFs from different domains and generate pseudo data sets. Finally, the adversarial training is adopted between the real data and the pseudo data to capture domain-generalized features. The discharge pressure signal of an actual axial piston pump at different health levels were collected on a test bench to verify the effectiveness of the proposed method. Results indicate that the proposed method has a higher prediction accuracy than the comparative methods.

Development of a new test design to investigate the degradation of pesticides in soil under sunlight conditions

Pesticides applied to soil surface are subject to photodegradation if the parent molecule is sensitive to UV-light absorption. Photodegradation studies are therefore mandatory for the registration of plant protection products to provide data on the degradation rate and on the nature of photoproducts formed. In general, sunlight is simulated in these studies with xenon lamps, e.g., a Suntest® device. Surface application on very thin soil layers followed by direct irradiation is common practice, but the control of the boundary conditions, i.e. soil temperature and moisture, to maintain the structure and viability of the soil is challenging. A homogeneous and stable soil microclimate is crucial to compare the degradation data of the test item from the irradiated soil samples to the dark controls as well as to the results from the aerobic soil metabolism study. After trying different scale-up test systems with the UV-sensitive herbicide imazamox as comparative test item, a new soil photolysis test system was developed which is manageable in the laboratory and enables a more favorable management of the boundary conditions, especially with regard to the soil moisture and temperature. For this, the solar simulator SolarConstant® 1200, equipped with metal halide lamps Radium HRI-TS 1000W/D/S/PRO, was installed by Atlas Ametek (Germany) in a temperature controllable walk-in incubation chamber with aluminum racks and reflectors to minimize diffuse light and to maintain a homogenous temperature of 22(± 1)°C within the irradiated soil. Borosilicate glass vessels with an inner diameter of 10 cm and a maximum height of 9 cm, covered by quartz glass, were used for the incubation of the applied soil under light. Contrary to the imazamox degradation half-lives obtained with the Suntest® test system, where an unusual slower degradation was observed under light compared to the dark controls, the results from the new SolarConstant® study design showed the expected faster degradation under light. Hence, it can be concluded that the experimental boundary conditions of the new test system are more suitable to maintain the viablity of the irradiated soil. Since no adjustments of the soil water content were needed, compared to daily water adjustments for thin soil layers incubated under a Suntest®, drying–wetting cycles are eliminated and microbial-induced soil processes are maintained.

Optimal condition‐based parameter learning and mission abort decisions

AbstractUnexpected failures of safety‐critical systems during mission execution are not desirable in that they often result in severe safety hazards and significant financial losses. Prompt mission abort based on real‐time degradation data is an effective means to prevent such failures and enhance system safety. In this study, we focus on safety‐critical systems that experience cumulative shock degradation and fails when the degradation exceeds a failure threshold. Real‐time degradation measurements are obtained via sensor monitoring, which are stochastically related to the hidden degradation parameters that vary across components. We formulate the optimal mission risk control problem as a sequential abort decision‐making problem that integrates adaptive parameter learning, following which a dynamic Bayesian learning approach is exploited to sequentially infer the uncertain degradation parameters by utilizing real‐time sensor data. The problem is constituted as a finite horizon Markov decision process to minimize the expected costs associated with inspections, mission failures and system failures. We derive a series of structural properties of the value function and demonstrate the existence of optimal abort thresholds. In particular, we establish that the optimal policy follows a state‐dependent control limit policy. Additionally, we study the existence and monotonicity of control limits associated with both the number of inspections and degradation severities. We demonstrate the performance of the proposed risk management policy through comparative experiments that show substantial superiorities over risk‐induced loss control.