Performance Monitoring in Fuel Cell Systems

Fuel cell hybrid energy management and control system with improved accuracy and reliability by filtering sensor data and predicting fuel cell degradation. The system uses a Butterworth filter to remove noise and interference from sensor signals. This cleaned data is then fed into a support vector machine (SVM) to predict trends in fuel cell hybrid energy performance. This allows detecting if the fuel cell is degrading and taking action before major issues arise.

Source

Monitoring the health and performance of small air-cooled hydrogen fuel cells to predict faults and evaluate fuel cell operation. It uses a modified Kalman filter to accurately predict fuel cell monitoring data by considering the changing amplitudes of different types of monitoring data. The filter algorithm obtains a noise matrix from all monitoring data, determines a battery state representation value based on fluctuation differences, and updates the noise matrix for more precise predictions.

Source

Stack health monitoring for fuel cells using a multi-point amplitude phase difference detection method to improve accuracy and real-time monitoring compared to voltage-only monitoring. The method involves capturing analog signals from a fuel cell stack during normal operation, extracting differential signals between historical and current signals, and determining monitoring items based on signal changes. This allows targeted fault detection and stack health assessment using fewer items compared to full monitoring.

Source

Predicting the remaining useful life of fuel cells using dynamic health indicators that consider the complex interactions between operating conditions and factors affecting fuel cell degradation. This improves accuracy and reliability of fuel cell life prediction compared to static models. The dynamic health indicators capture the long-term dependence between operating conditions and fuel cell degradation, accounting for factors like environment and operating mode. This allows more realistic and accurate predictions of fuel cell life under dynamic operating conditions.

Source

Method for efficiently monitoring components of a fuel cell system in a vehicle like a commercial truck. The method involves comparing sensor data from the component to a reference variable to determine an event size that indicates component health. This allows targeted monitoring of costly fuel cell turbomachines. The control unit acquires sensor data, calculates a comparison variable based on that data, compares the sensor data to the comparison variable, and outputs an event size based on the comparison. This provides specific and effective monitoring of fuel cell system components like compressors and expanders.

Source

Fuel cell operation monitoring method and system to detect early warning signs of fuel cell failure or degradation in real-time during operation. The monitoring involves analyzing factors like fuel cell load, hydrogen pressure, oxygen supply, and cell balancing to identify operation risks. It calculates indices like load uniformity, hydrogen pressure risk, and oxygen supply deviation. If thresholds are exceeded, it generates warning signals indicating potential issues. This allows proactive mitigation of problems before they become critical.

Source

Obtaining and updating fuel cell engine polarization performance in real-time by measuring operating current and voltage during load current delivery and using that data to adjust the load current and update control parameters. This allows online determination of fuel cell performance curves without bench testing, which can change over time due to factors like temperature, load, and degradation. The method involves delivering load current, measuring operating current/voltage, plotting on a curve, and iteratively adjusting load current based on the measured data. This allows obtaining accurate, real-time fuel cell performance curves that can be used to optimize control parameters for the specific operating conditions.

Source

Fuel cell online health diagnosis and life prediction method, device, and system using machine learning to monitor fuel cell stack performance and predict stack degradation and failure. The method involves continuously learning stack data to predict future stack health based on time. It uses a neural network with nonlinear layers to learn intermediate features representing the stack's future performance. The network is periodically updated to correct prediction errors. Additionally, a fault diagnosis module combines predicted and real-time data to identify features predicting fault occurrence.

Source

A system and method for monitoring the cold start status of a fuel cell to improve cold start reliability. The system has a monitoring device that tracks key parameters during cold start, like stack temperature, stack pressure, and stack current, and uses them to determine the risk of ice formation. If the stack temperature is below a certain point and the stack overpressure is above a threshold, it indicates a high risk of icing. This information can be used to adjust the fuel cell operating parameters during cold start to mitigate ice formation and improve startup success.

Source

Controlling operation of multiple fuel cell systems in a vehicle to extend the overall system's service life. It involves monitoring the health of each individual fuel cell system during operation and comparing it to the expected health based on historical use conditions. If the actual health deviates significantly, indicating unexpected degradation, the other fuel cell system is used more to compensate. This prevents excessive degradation of the weaker system and extends the overall system's service life since it's based on the weakest fuel cell.

Source

Predicting fuel cell performance degradation in vehicles using real-world driving data rather than lab tests. The method involves retrieving vehicle operating data over a time interval, cleaning the data, extracting the fuel cell operating data, fitting curves to predict performance decay as working time increases, and using the curves to predict future performance decay. This allows continuous, flexible, and low-cost fuel cell performance degradation analysis and prediction based on actual driving conditions.

Source

Remote monitoring system and method for fuel cells that allows monitoring fuel cell performance and detecting issues without on-site access. The system uses sensors to collect data like temperature, voltage, current, and level. A local server acquires the data at adjustable frequencies and durations. It sends the data to a remote server that compares against normal ranges. If values are abnormal, an early warning is issued. By adjusting sensor data collection durations based on rate of change, the system can optimize monitoring efficiency.

Source

Method for assessing the health and predicting the life of proton exchange membrane fuel cells (PEMFCs) to improve their durability. The method involves estimating the degradation trends and remaining useful life of PEMFCs using a model that allows independent evaluation of critical parameters like open circuit voltage, exchange current density, internal resistance, and limit diffusion current. The parameters are estimated from measured voltage and current density data using a noise reduction process. By separately assessing each parameter, the method avoids the limitations of fixed or constrained parameter values and inconsistent attenuation rates.

Source

Digital twin-based fuel cell engine monitoring method and system that provides real-time fuel cell engine monitoring using a digital twin model. The method involves acquiring real-time engine operating data and environmental conditions, and using a trained neural network model to predict fuel cell engine health and faults based on the current operating conditions. This allows monitoring of engine components in real-time rather than relying on historical data. The model predicts engine life, damage levels, and failure probabilities.

Source

Diagnosing and controlling the operating state of a fuel cell system using a detailed electrochemical and physical model of the fuel cell. The model allows continuous forecasting of the fuel cell's electrical power based on the measured current and operating media variables. This provides a real-time indication of cell health and allows optimized media management based on the diagnosed state.

Source

Monitoring fuel cell systems, especially high-temperature fuel cells, to reliably determine degradation. The monitoring involves using machine learning models to predict degradation based on inputs like operating parameters. The models are trained using historical data. The degradation model is separated from a higher-level model that predicts overall system performance. The remaining residue from separating the models is the reference model. It predicts the target parameter when degradation is removed. The models are iteratively improved through alternating steps where the degradation model predicts degradation and the reference model predicts the target parameter. The iterations continue until convergence. This allows reliable degradation monitoring without needing direct degradation measurements.

Source

Assessing the health of fuel cells and fuel cell stacks in a fuel cell system by distinguishing between bad channels and weak cells, accounting for fuel cell aging, and compensating for fuel cell system operation and measurement variability. It involves tracking stack voltage, identifying bad channels with voltage measurement differences, validating data, and assessing stack health based on cell weakness.

Source

Method for predicting the degradation and remaining life of proton exchange membrane fuel cells. The method involves using a combination of temporal convolutional networks (TCN) and random vector functional link (RVFL) neural networks to predict fuel cell degradation indicators. The TCN extracts features from the input data, and the RVFL makes the final predictions. An improved transit search algorithm is used to optimize the TCN-RVFL model. The predicted remaining life is combined with observed life to estimate total life.

Source

Method for proactively recognizing stress situations of a fuel cell to prevent failures. The method involves continuously monitoring operating parameters of the fuel cell during normal operation. It compares the current operating conditions with a database of known stress situations. If a match is found, it indicates an impending failure. This allows identifying and addressing potential issues before they escalate. The method provides real-time failure prevention rather than relying on test stand experiments.

Source

Fuel cell output control system that allows customizing the amount of power generated by a fuel cell stack based on user requirements. The system involves training a neural network using fuel cell monitoring data to derive optimal design information for the unit cells. The number and area of cells in the stack are then set based on this optimized design to achieve the desired output.

Source

Fault detection and alarm method for fuel cell systems using neural networks and time series analysis. It involves monitoring target parameters and stack currents in real-time, feeding them into a pre-trained neural network to predict stack current, calculating a state index based on predicted vs actual currents, and raising an alarm if the index exceeds a threshold. The threshold is determined by analyzing sample data during normal operation. The method provides real-time fault detection to quickly alert staff and mitigate issues before they cause significant damage or system failures.

Source

Determining the state of a fuel cell engine to monitor and improve the durability of fuel cells. The method involves comprehensively monitoring the health of each subsystem in the fuel cell engine, determining an initial reference state, and calculating deviations using Mahalanobis distance. If any subsystem exceeds a warning threshold, it indicates deterioration and the engine is controlled to stop running to prevent further damage. This enables proactive maintenance of specific subsystems before complete failure.

Source

Sensor and method for monitoring gas quality of a fuel reformer in a fuel cell system or power generation system. The sensor is a miniature fuel cell that estimates hydrogen content of fuel by measuring voltage. Placing sensors at the reformer inlet and outlet, and maintaining constant temperature, allows measuring voltage difference to assess reformer efficiency.

Source

Accurate analysis of fuel cell decay to improve the accuracy of fuel cell lifetime prediction for hydrogen fuel cell vehicles. The method involves analyzing operating data from fuel cells under different load conditions to determine the factors that contribute most to voltage decay. By using a stacking fusion model to process the operating data, it can determine the relative importance of factors like temperature, current density, and concentration changes in affecting voltage decay. This allows targeting specific factors that cause voltage decay instead of just analyzing voltage decay trends.

Source

System and method to accurately determine the performance of a fuel cell stack in a vehicle to improve driving stability by receiving current and voltage data from the stack in real time, analyzing the drop in performance, and determining whether to replace the stack based on an ensemble average SOH. This involves calculating an average SOH for each current interval within a range, determining an overall average SOH, and checking if it falls below a threshold to diagnose stack faults.

Source

Monitoring a fuel cell system, such as a solid oxide fuel cell system, using machine learning to estimate fuel parameters like hydrogen concentration from operating parameters like cell voltage and current. This allows predicting fuel quality without invasive sensing. The method involves recording operating parameters, storing them with measured fuel parameters, and using a machine learning algorithm like Gaussian processes to estimate fuel parameters from future operating data.

Source

Fuel cell sensor optimization screening method that reduces the number of sensors needed for performance prediction and fault diagnosis in fuel cell systems. The method involves using simulation and machine learning to identify the most sensitive sensors for fuel cell monitoring. It calculates sensor sensitivity based on fuel cell model output changes due to failure modes. This allows filtering out insensitive sensors for online diagnosis since high-dimensional sensor data is impractical in embedded systems. The method uses a fuel cell simulation model to calculate sensor sensitivity, a machine learning algorithm, and a fuel cell failure mode impact analysis.

Source

Monitoring a fuel cell system, like a solid oxide fuel cell system, using machine learning to estimate fuel cell parameters without direct measurement. The method involves training a model by recording fuel cell operating parameters and corresponding fuel cell fuel parameters at different loads, settings, and ages. This data is used to learn the relationship between the operating parameters and fuel parameters. During regular operation, the learned model can be used to estimate the fuel parameters without direct measurement.

Source

Monitoring a fuel cell system, particularly a solid oxide fuel cell system, by creating enthalpy balances for multiple subassemblies to determine fuel parameters. The fuel cell system is divided into subassemblies like fuel lines, reformers, and fuel cells. Enthalpy balances are created for at least two subassemblies, using which current fuel parameters are determined. This provides more detailed fuel consumption and efficiency monitoring compared to just tracking overall system fuel usage.

Source

Fuel cell full life cycle monitoring and evaluation system for optimizing performance and durability of fuel cells. The system has components like a fuel cell stack, voltage acquisition module, fuzzy logic controller, output display, hydrogen and oxygen flow meters, temperature sensor, and neural network controller. The stack voltage is monitored and analyzed using fuzzy logic to evaluate performance and identify issues. It also measures hydrogen and oxygen flow rates, temperature, and pressure to assess stack degradation. Neural networks are used to predict stack lifetime based on these parameters.

Source

Fuel cell test system data processing method that uses cloud, edge and terminal fusion to improve the accuracy and objectivity of fuel cell system state data collection. The method involves a fuel cell test system with sensors, an edge server, local database, cloud server and client. The sensors collect fuel cell operating data. The edge server processes and stores the data locally. The cloud server analyzes the data from multiple sources and provides insights. Users can access the data via the client terminals. This allows real-time monitoring, comparison and analysis of fuel cell performance. The method leverages cloud, edge and terminal computing power and storage to enhance fuel cell test system data collection and analysis.

Source

Fuel cell failure prediction method and system using hybrid data-model driven approach to extend fuel cell life and reduce costs by predicting remaining service time. The method involves collecting fuel cell stack aging data, preprocessing it to remove noise, training a data-driven model, updating a model-driven state, and using both models for hybrid prediction of future degradation trends. The trends are then used to calculate the remaining service life based on threshold limits.

Source

A method and system for accurately determining the actual value of a controlled variable in a fuel cell's reactant regulation system. The method involves measuring the actual value using a sensor and compensating for errors between the measured value and the theoretical value using a controller. This reduces the measurement error to improve the accuracy of the controlled variable in dynamic fuel cell operation. The system includes a sensor to measure the actual value, a controller to compensate for errors, and a fuel cell reactant control unit that uses the compensated value for regulation.

Source

Method for detecting critical situations in fuel cells to identify potential damage and failure conditions during operation. The method involves monitoring fuel cell operating parameters and comparing them against a database of critical conditions. If a parameter exceeds a critical threshold, it indicates a potential critical situation. This allows real-time identification of potential fuel cell issues during operation, rather than relying on post-test analysis.

Source

Optimizing the life cycle of a fuel cell integrated system by tracking and analyzing conversion characteristics of the anode, cathode, and electrolyte during operation. By monitoring parameters like fuel medium, electron emission, ion generation, and electrolyte conductivity, the method evaluates the fuel cell's life cycle. This provides data support for accurate assessment and prolongation of fuel cell durability.

Source

A method for monitoring and diagnosing fuel cell systems that can detect and recover from abnormal operating conditions. The method involves using a digital algorithm to monitor the fuel cell system's behavior during normal and abnormal operating states. When anomalies are detected, the algorithm puts the system into a diagnostic or compensation state to identify and recover from the issue. The algorithm also retrieves data from other fuel cell systems to differentiate between normal and abnormal conditions.

Source

Determining the health and aging of a proton exchange membrane (PEM) fuel cell stack over its operating life to optimize performance and longevity. The method involves continuously monitoring stack parameters like voltage, current, and power while it's operating at a load. These values are compared against reference values to determine deviations. Based on the deviations, a status indicator is assigned using an assignment logic. This indicator can be displayed to the user as an indicator of stack health.

Source

Monitoring electrochemical cell units like fuel cells or electrolyzers to detect damage early and prevent failure. The monitoring involves continuously recording cell parameters like voltage and comparing them to stored patterns for each cell stack. If a current pattern matches a stored pattern, it indicates normal operation. If not, it indicates a critical state. This allows detecting cell degradation or stack imbalances before they cause damage.

Source

Monitoring electrochemical cell units like fuel cells to detect and diagnose cell damage earlier and more accurately than current methods. The monitoring involves operating the cell stack with changed parameters during a temporary period, like higher oxidant flow, to stress the cells. Cell parameters like voltage are measured before, during, and after this period. By comparing changes, the method can identify cells with impaired performance or damage that may not be apparent during normal operation. This allows proactive maintenance before full failure.

Source

A method and system for diagnosing fuel cell failures using historical data analysis. The method involves extracting and analyzing data signals like temperature, humidity, voltage, and current from fuel cells over time. By processing and classifying this historical data, it allows determining failure types and estimating failure probabilities for different issues in fuel cell systems.

Source

A method for evaluating the health state of a fuel cell in real time during operation, using sensor data, rather than fixed criteria. The method involves determining working current intervals and conditions to analyze, screening sensor data for compliance, and calculating a health factor based on compliant data. This allows quantitative evaluation of fuel cell health during specific operating conditions, which can inform adaptive control strategies to improve efficiency and longevity.

Source

Method for monitoring and replacing fuel cells within a fuel cell stack to extend stack life and enable cell-level maintenance. The method involves measuring operating conditions of individual cells, determining cell health, and selectively replacing faulty cells without disassembling the stack. The cells have mating matrix of protrusions and sockets on endplates that allow easy detachment and attachment. This enables swapping cells without disrupting the stack. The monitoring system detects cell faults and sends alerts.

Source

Reducing the amount of data transmitted from a fuel cell system to an external data collection terminal while still providing sufficient error diagnostic data. The fuel cell system has a control unit that selectively transmits sensor data to the collection terminal based on error conditions. When no errors occur, it transmits at a minimum required period. But when an error occurs, it sends error-related data at a shorter cycle. This balances supplying enough data to identify error causes with minimizing normal operation data transmission. The system also stores error data before/after an error and sends that along with subsequent errors to avoid redundant transmission.

Source

Method for predicting fuel cell consistency and fault diagnosis that can accurately predict fuel cell performance and diagnose faults without requiring extensive experimental testing. The method involves using a fuel cell performance prediction model to simulate steady-state, dynamic, and consistency characteristics of the cell. It compares the model output to expected values and adjusts operating parameters until the cell meets performance requirements. This provides a systematic approach to optimize fuel cell operation and diagnose faults using simulation rather than extensive experiments.

Source

Predictive fuel cell management for integrated hydrogen-electric systems like aircraft. It optimizes the number of fuel cells online at any given time to avoid wasting energy or damaging cells. The system uses a controller to monitor aircraft flight conditions and predict the power requirements for each phase of flight. Based on this data, it activates or deactivates fuel cells to match the power needs without overloading the fuel cell stack.

Source

Multi-sequence fuel cell output control method and system that adaptively adjusts the output stability of a fuel cell based on its operating sequence. The method involves calculating the involvement of different parameters on stable output for each sequence, then obtaining duty cycle and frequency functions to control the output. This allows the fuel cell to compensate for unstable output due to environment effects by adaptively adjusting the duty cycle and frequency based on the current sequence.

Source

Predicting fuel cell system performance degradation in a multimodal fusion approach that provides better accuracy compared to prior methods. The method involves using adaptive data decomposition to separate the fuel cell performance time series into multiple modal components with different time scales. This allows capturing both short-term random fluctuations and long-term decay. By analyzing and modeling each modal component separately, it provides more accurate predictions compared to treating the entire time series as a whole.

Source

A method and system for predicting fuel cell failures based on historical data. The method involves extracting operating state data from the fuel cell, identifying abnormal data, generating input and output signals from the state sequence, classifying the signals into fault types, and forecasting failures based on the classified signals. By analyzing historical data to predict future failures, it allows identifying and isolating failures before they occur.

Source

Preventing missing components in fuel cell system monitoring by adding control logic to the fuel cell controller that checks if all monitoring components are properly powered and connected. If any monitoring component has a power issue or missing signal input, the fuel cell controller disconnects the demand signal data and prevents itself from outputting commands. This ensures the fuel cell system cannot operate until all monitoring components are present and functional. The controller checks the power-on signals of explicit monitoring components, determines if hidden monitoring components provide signals, and disconnects if any are missing. This prevents fuel cell operation without complete monitoring coverage.

Source

Distributed fault management system for fuel cell systems that leverages AI and machine learning to improve fault resolution and sharing between multiple fuel cell systems. The system uses AI to analyze fault conditions detected in one fuel cell and generates resolution commands. These commands are sent to other fuel cell systems with similar faults to automatically apply the learned resolution. This allows faster, adaptive fault resolution and prevents recurrence across multiple systems.

Source