On-board Algorithm Research Articles

Utilizing IoMT-Based Smart Gloves for Continuous Vital Sign Monitoring to Safeguard Athlete Health and Optimize Training Protocols.

This paper presents the development of a vital sign monitoring system designed specifically for professional athletes, with a focus on runners. The system aims to enhance athletic performance and mitigate health risks associated with intense training regimens. It comprises a wearable glove that monitors key physiological parameters such as heart rate, blood oxygen saturation (SpO2), body temperature, and gyroscope data used to calculate linear speed, among other relevant metrics. Additionally, environmental variables, including ambient temperature, are tracked. To ensure accuracy, the system incorporates an onboard filtering algorithm to minimize false positives, allowing for timely intervention during instances of physiological abnormalities. The study demonstrates the system's potential to optimize performance and protect athlete well-being by facilitating real-time adjustments to training intensity and duration. The experimental results show that the system adheres to the classical "220-age" formula for calculating maximum heart rate, responds promptly to predefined thresholds, and outperforms a moving average filter in noise reduction, with the Gaussian filter delivering superior performance.

Clutch Torque Optimization for Heavy-Duty Vehicles Starting Based on Intelligent Identification of Driver’s Starting Intention, Vehicle Mass, and Road Grade

<div>For heavy-duty vehicles equipped with automated mechanical transmission (AMT), the control of automatic clutch torque is crucial during the start-up process. However, the difficulty of controlling clutch torque is exacerbated by differences in driver’s starting intentions, changes in vehicle mass, and road gradient. Therefore, this article proposes the clutch starting torque optimization strategy based on intelligent recognition of driver’s starting intention, vehicle mass, and road gradient. First, an intelligent recognition strategy is proposed based on the combination of data-driven and onboard transmission control unit (TCU) algorithms, which improves the accuracy of recognizing the driver’s intention to start as well as the vehicle mass and road gradient. Based on the vehicle’s historical state data information, the predictive model is trained offline using a long–short-term memory (LSTM) network to obtain predicted parameter identification results, which are then used to calibrate the computed values of the onboard TCU algorithm. Second, the clutch torque optimization strategy is designed based on the driver’s starting intention, while considering the effects of road gradient and vehicle mass on the clutch starting resistance torque. The weight coefficients of the objective performance function are adjusted according to the driver’s starting intention, and the Pontryagin’s minimum principle (PMP) is used to solve the clutch target torque. Finally, offline data training and real-vehicle testing are performed. The results show that the optimization strategy can effectively reduce the friction work and the degree of impact during the starting process, minimize the clutch slipping time, and improve the smoothness of vehicle starting and driving comfort.</div>

ICESat‐2 Onboard Flight Receiver Algorithms: On‐Orbit Parameter Updates the Impact on Science Driven Observations

AbstractThe ICESat‐2 (Ice, Cloud and Land Elevation Satellite‐2) photon‐counting laser altimeter technology required the design and development of very sophisticated onboard algorithms to collect, store and downlink the observations. These algorithms utilize both software and hardware solutions for meeting data volume requirements and optimizing the science achievable via ICESat‐2 measurements. Careful planning and dedicated development were accomplished during the pre‐launch phase of the mission in preparation for the 2018 launch. Once on‐orbit all of the systems and subsystems were evaluated for performance, including the receiver algorithms, to ensure compliance with mission standards and satisfy the mission science objectives. As the mission has progressed and the instrument performance and data volumes were better understood, there have been several opportunities to enhance ICESat‐2's contributions to Earth observation science initiated by NASA and the ICESat‐2 science community. We highlight multiple updates to the flight receiver algorithms, the onboard software for signal processing, that have extended ICESat‐2's data capabilities and allowed for advanced science applications beyond the original mission objectives.

Fault-tolerant control for satellite autonomous rendezvous with quality characteristics and actuator uncertainties

An autonomous fault detection and fault-tolerant control solution combining Model Predictive Control (MPC) and Label Distributed Learning (LDL) is developed for the position tracking and attitude synchronization problems in autonomous satellite rendezvous and docking. The proposed algorithm can deal with center of mass (CM) variations and time-varying mass characteristics due to satellite fuel consumption, actuator saturation and fault, and external disturbances. Firstly, a six-degree-of-freedom (6-DOF) satellite translation-rotation coupling model was established to express the relative motion between the satellite and the target, taking the above factors into account. Subsequently, an on-board autonomous closed-loop fault-tolerant control algorithm using MPC is proposed, in which an LDL-based fault detection mechanism is embedded. The scheme specifies that propulsion faults are estimated by calculating the difference between the MPC's prediction of the satellite's future state and the measured change in the actual state. And the mapping matrix between the commanded force/torque and the actual force of the propulsion system is updated in real time to achieve autonomous fault detection and compensation on board the satellite. Among them, the LDL-based fault detection scheme is trained offline. It requires only simple matrix operations for on-orbit use, which is low-cost and suitable for resource-limited space environments. The additional creation of a time-varying disturbance observer allows the estimation and compensation of unmodelled errors and external disturbances. The stability of the proposed fault-tolerant control algorithm is rigorously demonstrated using Lyapunov analysis. Finally, numerical simulations show that the proposed method can successfully achieve autonomous satellite docking under different combinations of thruster faults.

Аналіз точності самоналаштування динамічної моделі газотурбінного двигуна

One of the most promising directions in the development of aircraft engines is related to the introduction of adaptive automatic control systems (ACS). The defining element of these systems are dynamic mathematical models of engines capable of self-adjustment based on engine operating parameters measured in flight. A number of leading researchers have developed a concept of using such models called STORM (Self-Tuned On-board Real-time Model). However, in the corresponding works, clearly insufficient attention is paid to solving the problem of checking the sufficiency of the information used to ensure the necessary accuracy of the models. This check must be performed a priori (to predict the composition of engine operating modes, and the volume of registered information), as well as posteriori. The subject of this study is the process of forming dynamic mathematical models (MM) of gas turbine engines using real data for the subsequent use of these models to solve problems related to the control and diagnostics of on-board systems. The goal of this study is to determine the dependence of estimation errors of dynamic parameters of mathematical models on influencing factors. Tasks considered in the work: forming the structure of a mathematical model, dividing the identification process into stages according to the structure of the model (estimating the parameters that determine the static and dynamic properties of the object), forming the least-square functional for the assessment task, determining the errors in estimating dynamic coefficients, analyzing influencing factors, and determining dependencies between factors and errors. For this purpose, the methods of the theory of air-jet engines, the theory of linear dynamic systems, and statistical evaluation are used. The following results were obtained: a mathematical model of a turboshaft engine with a reciprocating gas generator was formed, and ratios were obtained that allow determining the errors in estimating the time constant of a reciprocating engine or gas generator. Scientific and practical innovation: for the first time, a ratio was obtained that determines the errors in estimating the time constant based on the specified values of the measurement errors, the intensity of the jump-like change in fuel consumption, and the frequency and duration of observation. These relations are presented in dimensionless coordinates, which makes them universal and able to be applied to any single-stroke turbojet engine or single-stroke gas generator during a priori or a posteriori analysis of results, as well as planning experiments and debugging on-board self-tuning algorithms of models.

The Data Compression Method and FPGA Implementation in the Mars Rover Subsurface-Penetrating Radar on the Tianwen-1 Mission

Since Mars is far away from Earth, the propagation delay between Mars and Earth is very large. To ensure the effective use of the link transmission bandwidth, China’s first Mars exploration mission has put forward a demand for data compression for all scientific payloads. The on-board mature algorithms for data compression are mainly focused on optical images and microwave imaging radar applications. No articles have been published on data compression methods that are applied to subsurface-penetrating radar. Based on the background of this application, this paper proposes a logarithmic lossy compression algorithm which can meet the mission requirements for high compression ratios of 4:1 and 2.5:1. Its compression error is less than that of the block adaptive quantization (BAQ) algorithm. The algorithm is not only easy to implement on field-programmable gate array (FPGA) platforms, but also offers simple ground decompression and fast imaging. The experimental results show that high compression ratios of 4:1 and 2.5:1 can be realized, even if the data in and between traces do not have a strong correlation. And its relative error is less than 2%, which is a new type of high-efficiency data compression method that can be implemented on-board to meet with the demand of subsurface penetrating radar.

Hardware-in-the-Loop Simulation of an On-Board Energy-Driven Scheduling Algorithm for CubeSats

Hardware-in-the-Loop Simulation of an On-Board Energy-Driven Scheduling Algorithm for CubeSats

Clot Waveform Analysis: From Hypercoagulability to Hypocoagulability - A Review.

Prothrombin time (PT) and activated partial thromboplastin time (aPTT) are coagulative screening tests used for the diagnosis of several pathologic conditions, such as liver failure, coagulation factor deficiencies, anti-phospholipid antibodies (lupus anticoagulant), and factor VIII inhibitors. A new test was developed several years ago to detect the amount of thrombin generated during plasma clotting, using low tissue factor concentrations and fluorogenic substrates, and it has since been used successfully in conditions ranging from hypocoagulable to hypercoagulable states. However, the test is expensive and difficult to perform in nonspecialized laboratories, and efforts have thus been made to find an economic and easily implementable test suitable for routine use, even in nonspecialist laboratories. To evaluate clot waveform analysis (CWA) of PT and aPTT, aiming to show the dynamics of clot formation; that is, the "hidden" features of both tests. CWA can be implemented by using an automated coagulometer with dedicated software. The aim of this review was to evaluate whether CWA is able to detect both hypercoagulative and hypocoagulative states. Using MedLine, we searched and retrieved articles relating to CWA. We only considered articles published in English, but with no limits in terms of article type, publication year, or geography. CWA was shown to be a reliable test in patients with both hypercoagulable and hypocoagulable states. It represents a simple and inexpensive global test that can easily provide information on the behavior of the coagulation system. Both the first and second derivatives are computed by using dedicated software implemented with an on-board algorithm in a routine automated coagulometer.

Gamma-Ray Burst Detection with Poisson-FOCuS and Other Trigger Algorithms

We describe how a novel online change-point detection algorithm, called Poisson-FOCuS, can be used to optimally detect gamma-ray bursts within the computational constraints imposed by miniaturized satellites such as the upcoming HERMES-Pathfinder constellation. Poisson-FOCuS enables testing for gamma-ray burst onset at all intervals in a count time series, across all timescales and offsets, in real time and at a fraction of the computational cost of conventional strategies. We validate an implementation with automatic background assessment through exponential smoothing, using archival data from Fermi-GBM. Through simulations of lightcurves modeled after real short and long gamma-ray bursts, we demonstrate that the same implementation has higher detection power than algorithms designed to emulate the logic of Fermi-GBM and Compton-BATSE, reaching the performance of a brute-force benchmark with oracle information on the true background rate, when not hindered by automatic background assessment. Finally, using simulated data with different lengths and means, we show that Poisson-FOCuS can analyze data twice as fast as a similarly implemented benchmark emulator for the historic Fermi-GBM on-board trigger algorithms.

Electron Density Specification in the Inner Magnetosphere From the Narrow Band Receiver Onboard DSX

AbstractElectron density plays an important role in the study of wave propagation and is known to be associated with the index of refraction and radiation belt diffusion coefficients. The primary objective of our investigation is to explore the possibility of implementing an onboard signal processing algorithm to automatically obtain electron densities from the upper hybrid resonance traces of wave spectrograms for future missions. U‐Net, developed for biomedical image segmentation, has been adapted as our deep learning architecture with results being compared with those extracted from a more traditional semi‐automated method. As a product, electron densities and cyclotron frequencies for the entire DSX mission between 2019 and 2021 are acquired for further analysis and applications. Due to limited space measurements, a synthetic image generator based on data statistics and randomization is proposed as an initial step toward the development of a generative adversarial network in hopes of providing unlimited realistic data sources for advanced machine learning.

A Bayesian Kalman filter algorithm for quantifying estimation uncertainty of track irregularity on bridges with randomness in system parameters

Vehicle on-board monitoring methods use responses of running vehicles to identify track irregularity in real time. But the parameters of both the bridges and the vehicles in such processes may have a non-negligible degree of uncertainty or randomness that will inevitably lead to uncertainty in the track irregularity identification. Quantifying such uncertainty is a great challenge as the vehicle-bridge system (VBS) to be treated with is time-dependent and random. This paper proposes an on-board track irregularity identification algorithm that realizes an inverse random dynamic analysis of the VBS to quantify estimation uncertainty by using a Bayesian Kalman filter technology. The proposed algorithm utilizes sigma point sets to simulate the random parameters and the noises, and is therefore capable of implementing high-fidelity probability density propagation in the nonlinear state transfer and observation functions describing the VBS. The proposed algorithm is validated by numerical examples with various running states and parameter uncertainty levels.

An On-Board Imaging Processing Algorithm for Stripmap Mode of Azimuth Multichannel Spaceborne SAR

In the traditional processing methods of azimuth multi-channel spaceborne synthetic aperture radar (SAR), the azimuth spectrum reconstruction and subsequent azimuth focusing are always via full-aperture processing. However, if the multi-channel full-aperture echo data are stored on the satellite, and then the full-aperture algorithms are used for the on-board imaging processing, the huge amount of echo data will require more on-board storage resources and computing resources, and the imaging processing time will become longer. To solve above problems, a novel on-board imaging processing algorithm via the idea that the data acquisition and the on-board imaging processing of the sub-aperture data are carried out simultaneously is proposed in this paper. In the algorithm, the azimuth spectrum ambiguity is eliminated by the sub-aperture azimuth spectrum reconstruction. Then, the range cell migration correction (RCMC) and the range compression for the unambiguous sub-aperture signals are accomplished by the chirp scaling algorithm (CSA). After that, the low-resolution subaperture images are got via the sub-aperture focusing. By coherently combining all sub-aperture images, the final result with high-resolution of all echo data can be obtained. At last, the simulation for the point targets is given to verify the effectiveness of the proposed algorithm.

Gaia data processing

Aims. Our goal is to describe two potential options for the Source Environment Analysis pipeline (SEAPipe) for the Gaia mission. This pipeline will enable the discovery of sources that are new to Gaia, in the sense that they were not found by the on-board detection algorithm. These additional sources (secondaries) are discoverable in the vicinity of those Gaia sources (primaries) that were found by the on-board detection. Methods. The main algorithmic steps required are described: the two dimensional image reconstruction of one dimensional transit data; the analysis of these images to find the additional sources present, and the determination of the mean positions; proper motions, parallaxes, and brightness of these sources. Additionally, the Monte Carlo simulations used to characterise the performance of the pipelines are described. Results. The performance of the two options for SEAPipe, the vanilla and image-subtraction versions, are compared. Their selection functions were computed in terms of the magnitude of the secondary sources and their angular separations from their corresponding primary source. The completeness and purity of the resultant catalogue of secondary sources as found by each of the pipelines, given the expected magnitude distribution of the primary sources and the magnitude and angular separation distributions of the secondary sources, is also presented. The image-subtraction pipeline is shown to outperform the vanilla pipeline.

Coasting advice based on the analytical solutions of the train motion model

Supervision, data analysis and communication algorithms monitor trains, exploiting most of their available computational power. On-board eco-driving algorithms such as Driver Advisory Systems (DAS) are no exception, as the computational power available limits their complexity and features. This was the case of Roltijd, the in-house developed DAS based on coasting advice of NS, the main Dutch passenger railway undertaking. This platform calculated the coasting curves at every second by integrating the equations of motion numerically, assuming that the track is flat. However, generating more complex driving advice required replacing this coasting curve calculation by a more computationally-efficient algorithm. In this article we propose a new coasting advice algorithm based on the analytical solutions of the train motion model, assuming that gradients and speed limits are piecewise constant functions of the train location. We analyse the qualitative properties of these solutions using bifurcation theory, showing that bifurcations arise depending on the value of the gradient and the applied tractive effort. We validate the proposed algorithm, finding that our algorithm is accurate and can be 15 times faster than the previous method. This allowed NS to implement our algorithm on their trains, contributing daily to the sustainable mobility of 1.3 million passengers.

B-236 Portable 2 Hour Sample-to-Answer Multi-pathogen Phenotypic Antibiotic Susceptibility Test (AST)

Abstract Background Antimicrobial Resistance is a rapidly growing issue worldwide, arising from the overuse and misuse of antibiotics. The strongest tool the medical community has available to combat AMR is rapid, correct application of antibiotics to identified bacterial infections. Clinics and physician offices seek on-site rapid solutions to speed the pathway to timely and appropriate antibiotic therapies. GeneCapture is prototyping a rapid, sample-to-answer product to provide antibiotic susceptibility results directly from infected urine or wound samples. The test provides a susceptible vs non-susceptible call in under two hours and can be applied to samples with single or mixed pathogens. With support from the Defense Health Agency, a portable table-top instrument and disposable cartridge are being engineered to run this test at the point of care, allowing same-day prescriptions. The process is currently operational on the lab bench. Methods Fluorescent labeling of bacterial species, followed by optical counting, determines population growth with/without a suite of antibiotics. An on-board algorithm instantly converts raw cell numbers into a differential call of Susceptible or Non-susceptible for each bug/drug pair. A disposable cartridge with on-board antibiotics has been designed and is being finalized for fabrication. The optical counting is operating in a desktop device. Results Testing to date includes 124 strains from 7 of the most common Urinary Tract Infection and wound pathogens against a panel of six antibiotics. A total of 541 antibiotic/bacterial strain pairs in single or multiple pathogen antibiotic susceptibility testing (AST), are producing an initial 88.7% agreement to gold standard culture results. These results are all generated in two hours or less of assay time and represent a strong preliminary data set. Conclusion This 2-hour portable, novel, phenotypic AST profiling will produce informed and effective treatment options for medics, clinics and physician offices long before existing AST methods could return results.

Uncertainties in Onboard Algorithms for Autonomous Vehicles: Challenges, Mitigation, and Perspectives

Autonomous driving is considered one of the revolutionary technologies shaping humanity’s future mobility and quality of life. However, safety remains a critical hurdle in the way of commercialization and widespread deployment of autonomous vehicles on public roads. Safety concerns require the autonomous driving system to handle uncertainties from multiple sources that are either preexisting, e.g., the stochastic behavior of traffic participants or scenario occlusion, or introduced as a result of processing, e.g., the application of neural networks. Thus, it is crucial to analyze the sources of uncertainties and quantify the risks associated with them, including the propagated risks that accumulate in the decision-making system. In this context, this paper provides an overview of uncertainty challenges and state-of-the-art techniques for mitigating these challenges. We argue that the uncertainties mainly originate from two aspects: 1) the external traffic environment, and 2) the internal autonomous driving system. Specifically, this paper first analyzes the safety challenges caused by the uncertainties and summarizes their sources. In addition, the corresponding techniques that mitigate and quantify the risk of uncertainties are presented. Finally, research perspectives are highlighted to facilitate future studies for guaranteeing the safety of autonomous vehicles.

P24 Point of care rapid urinary tract infection phenotypic antibiotic susceptibility test

Abstract Background Urinary tract infections (UTIs) are one of the most common infections in the world today. In the last few years, the occurrence of antimicrobial resistant pathogens causing UTIs has rapidly increased. One in three UTIs are trimethoprim/sulfamethoxazole (Bactrim) resistant, and one in five are resistant to other common antibiotic choices. This growing resistance is mainly due to overuse or misuse of antibiotics. The strongest tool the medical community has available to combat antimicrobial resistance (AMR) is rapid, correct application of antibiotics to an identified bacterial infection. Clinics and physician offices seek on-site rapid solutions to speed the pathway to timely and appropriate antibiotic therapies. GeneCapture is developing products that perform rapid UTI pathogen identification and antimicrobial susceptibility tests (ASTs) directly from infected urine samples. The AST provides a susceptible versus non-susceptible call in under 2 h and can be applied to samples with single or mixed pathogens. A portable tabletop instrument and disposable cartridge are being engineered to run this test at the point of care, allowing same-day prescriptions. The process is currently operational on the lab bench. Methods Fluorescent labelling of bacterial species, followed by optical counting, determines population growth with/without a suite of antibiotics. An on-board algorithm instantly converts raw cell numbers into a differential call of susceptible or non-susceptible for each bug/drug pair. A disposable cartridge with on-board antibiotics has been designed and is being finalized for fabrication. The optical counting is operating in a desktop device. Results Testing to date includes 124 strains from 7 of the most common UTI and wound pathogens against a panel of six antibiotics. A total of 541 antibiotic/bacterial strain pairs in single or multiple pathogen antibiotic susceptibility testing produce an initial 88.7% agreement to gold standard culture results. These results are all generated in 2 h or less of assay time and represent a strong preliminary dataset. Conclusions This 2 h portable, novel, phenotypic AST profiling will produce informed and effective treatment options for medics, clinics and physician offices long before existing AST methods could return results.

0280 Unlocking the Potential of Consumer Wearables for Predicting Sleep in Children: A Device-Agnostic Machine Learning Approach

Abstract Introduction Consumer wearables use accelerometry and heart rate to predict sleep, the same data signals used by research-grade devices to classify sleep/wake patterns. However, metrics predicted by consumer wearables are based on black box algorithms limiting their use in research. The objective of this study was to develop algorithms for predicting sleep in children based on the raw accelerometry and heart rate data from a popular consumer wearable device, therefore bypassing the onboard black box algorithms. Methods 38 children (M=8.5 years, SD=2.4, 42% black, 61% male) underwent overnight laboratory-based polysomnography (PSG) while wearing an Apple Watch Series 7. Heart rate and accelerometry data were collected via the Apple Watch application program interface. Features extracted included (1) age, (2) heart rate, (3) y-axis offset angle, (4) y-axis angle relative to x-axis (y-angle), (5) x-axis fast Fourier transformation (FFT) 4Hz, (6) x-axis FFT 9Hz, (7) vector magnitude (VM) FFT 9Hz, (8) VM FFT 14Hz, (9) mean power dispersion (MPD), (10) bandpass filter followed by Euclidean norm/vector magnitude (BFEN), (11) dominant signal power at 0.6–2.5Hz (PMAXBAND), and (12) activity counts. Four machine learning models: logistic regression (LR), K-nearest neighbor (KNN), random forest (RF), and neural network (NN) predicted sleep or wake. Model performance was evaluated by F1 score, precision, sensitivity, and specificity. Feature importance was evaluated using the RF model. Results LR achieved the best performance according to F1 score (RF: 85.04, LR: 86.50, KNN: 82.52, NN: 85.13). LR also had the highest precision (RF:88.33, LR:88.94, KNN: 86.77, NN:87.95), and nearly the highest sensitivity (RF:84.52, LR:86.11, KNN:84.73, NN:86.55) and specificity (RF:75.72, LR:75.00, KNN:54.01, NN:60.57). BFEN was the most important feature, followed by MPD, age, PMAXBAND, VM FFT 14Hz, x-axis FFT 9Hz, heart rate, y-axis offset angle, y-angle, activity count, VM FFT 9Hz, x-axis FFT 4Hz. Conclusion Raw accelerometry data combined with heart rate data from the Apple Watch Series 7 was able to detect sleep and wake in children. Leveraging the raw accelerometry data is a viable alternative to relying on black-box algorithms for sleep classification in consumer wearable devices. Support (if any)

Counteracting contingencies in fast rendezvous with ISS

The existing rendezvous profiles of Russian crew vehicles in some flight phases are not adapted to contingencies which can be caused by an autonomous rendezvous system failure. If it occurs, the crew can complete the rendezvous in manual mode only at a range of less than a kilometer. However, at a long range the manual rendezvous mode is complicated because the on-board algorithm of the motion control system generates free trajectories that do not provide the crew with a convenient manual control. As a rule, in this case re-rendezvous is required with shifting the docking to the next day. In the case of fast rendezvous profiles (which allow to get to the ISS in 3 h) re-docking should be scheduled only in two days because of the crew adaptation to the weightlessness. In order to allow the crew to complete the rendezvous in manual mode without delaying the docking, it is required to create a more simple procedure for calculating and performing transfer burns. From the Gemini, Apollo and ATV spaceflight heritage, the technique for approaching the target from a coelliptical orbit has been known, that provides a uniform motion and convenient control of the crew vehicle in manual mode. The paper proposes the fast rendezvous profile with the insertion of the crew vehicle into an intermediate orbit coelliptical with the target orbit. In this approach, in case of automatic rendezvous failure, the crew, having a complete understanding of the relative motion, is able to perform the transfer to the target in manual mode without increasing the duration of the flight till the docking. The paper presents the results of testing this approach on a simulator, which in the long term will allow to reduce the rendezvous duration of Russian vehicles to a single orbit.

Prescriptive Lifetime Management for PEM fuel cell systems in transportation applications, Part II: On-board operando feature extraction, condition assessment and lifetime prediction

The 2030 and 2050 targets for lifetime requirements of proton exchange membrane (PEM) fuel cell (FC) systems in heavy-duty vehicle (HDV) applications are set to 25,000h and 30,000h, respectively. The need to reduce PEM fuel cell system (FCS) costs is expected to be accompanied by greater uncertainty in lifetime. This will require robust and reliable approaches and algorithms for feature extraction, condition assessment and lifetime prediction to obtain the Remaining Useful Life (RUL) and to prevent premature failure, downtime and lower system availability leading to higher total cost of ownership (TCO).Current approaches to feature extraction and component-based condition assessment typically focus on in/ex situ measurement methods performed on test benches, rather than operando measurement methods that can be performed on-board commercial vehicles. Methods developed on test benches are often difficult or even impossible to transfer to commercial vehicle applications. As a result, the lifetime prediction in commercial vehicle applications often focuses on data-driven approaches to predict voltage or power decay. Since these data-driven approaches do not contain sufficient information about the component-based State of Health (SoH), a component-based lifetime prediction and subsequent optimization of operating strategy to control RUL and meet the lifetime requirements is significantly limited.Prescriptive Lifetime Management is a technique that involves developing and implementing on-board strategies and algorithms for feature extraction, condition assessment and lifetime prediction to mitigate degradation, extend the RUL and reduce the overall TCO, e.g., of the PEM fuel cell system through global optimization-based post-prognostic decision-making. With this in mind, this paper presents approaches for on-board operando feature extraction and condition assessment of the PEM integrity and the electrochemical surface area (ECSA). The calibration of macroscopic degradation models allows for lifetime prediction and RUL control to meet the lifetime requirements of PEM fuel cells. The results show that the operating parameters have a high effect on PEM fuel cell degradation. The complexity of degradation prevents the generation of reliable degradation lookup tables. Therefore, the direct implementation of calibratable macroscopic degradation models in the Prescriptive Lifetime Management framework is recommended.