Operational Sensor Data Research Articles

Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon.

This study aims to enhance diagnostic capabilities for optimising the performance of the anaerobic sewage treatment lagoon at Melbourne Water's Western Treatment Plant (WTP) through a novel machine learning (ML)-based monitoring strategy. This strategy employs ML to make accurate probabilistic predictions of biogas performance by leveraging diverse real-life operational and inspection sensor and other measurement data for asset management, decision making, and structural health monitoring (SHM). The paper commences with data analysis and preprocessing of complex irregular datasets to facilitate efficient learning in an artificial neural network. Subsequently, a Bayesian mixture density neural network model incorporating an attention-based mechanism in bidirectional long short-term memory (BiLSTM) was developed. This probabilistic approach uses a distribution output layer based on the Gaussian mixture model and Monte Carlo (MC) dropout technique in estimating data and model uncertainties, respectively. Furthermore, systematic hyperparameter optimisation revealed that the optimised model achieved a negative log-likelihood (NLL) of 0.074, significantly outperforming other configurations. It achieved an accuracy approximately 9 times greater than the average model performance (NLL = 0.753) and 22 times greater than the worst performing model (NLL = 1.677). Key factors influencing the model's accuracy, such as the input window size and the number of hidden units in the BiLSTM layer, were identified, while the number of neurons in the fully connected layer was found to have no significant impact on accuracy. Moreover, model calibration using the expected calibration error was performed to correct the model's predictive uncertainty. The findings suggest that the inherent data significantly contribute to the overall uncertainty of the model, highlighting the need for more high-quality data to enhance learning. This study lays the groundwork for applying ML in transforming high-value assets into intelligent structures and has broader implications for ML in asset management, SHM applications, and renewable energy sectors.

Statistical Models for Condition Monitoring and State of Health Estimation of Lithium-Ion Batteries for Ships

Battery systems are increasingly being used for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion is growing. To ensure the safety of such ships, it is important to monitor the available energy that can be stored in the batteries, and classification societies typically require the state of health (SOH) to be verified by independent tests. This paper addresses statistical modelling of SOH for maritime lithium-ion batteries based on operational sensor data. Various methods for sensor-based, data-driven degradation monitoring will be presented, and advantages and challenges with the different approaches will be discussed. The different approaches include cumulative degradation models and snapshot models, models that need to be trained and models that need no prior training, and pure data-driven models and physics-informed models. Some of the methods only rely on measured data, such as current, voltage and temperature, whereas others rely on derived quantities such as state of charge (SOC). Models include simple statistical models and more complicated machine learning techniques. Insight from this exploration will be important in establishing a framework for data-driven diagnostics and prognostics of maritime battery systems within the scope of classification societies. Conflict of Interest Statement The authors declare no conflicts of interest.

Confronting algorithmic management using subject access requests: Insights using the case of food deliveries

AbstractGig work is defined by a (mostly) automated management, operating remotely through an app. Without human interaction, workers are left with only guesses about the functioning of the algorithms they are subjected to. To better position themselves in their competition for tasks, they try to influence the data profile that platform build about them. Made of performance indicators, personal information, and sensor data, these profiles are an essential part of algorithmic management. This paper will identify data profiles as core sites of the struggle in the gig economy. It will discuss the benefits and limitations of bringing data at the centre stage through a workers’ inquiry of food delivery platforms. The analysis will distinguish three actors in this inquiry and discuss their uses of data profiles: the couriers themselves, as they attempt to make sense of algorithmic management; the researcher, and how they can use personal data in order to reconstitute this field of struggle; and the trade unions, which can provide a way to collectivise data governance and gain better information in building their case in favour of gig workers’ rights.

Data-Driven Approaches to Diagnostics and State of Health Monitoring of Maritime Battery Systems

Battery systems are increasingly being used for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion and maneuvering is growing. In order to ensure the safety of such electric ships, it is important to monitor the available energy that can be stored in the batteries, and classification societies typically require that the state of health (SOH) can be verified by independent tests. However, this paper addresses data-driven approaches to state of health monitoring of maritime battery systems based on operational sensor data. Results from various approaches to sensor-based, data-driven degradation monitoring of maritime battery systems will be presented, and advantages and challenges with the different methods will be discussed. The different approaches include cumulative degradation models and snapshot models. Some of the models need to be trained, whereas others need no prior training. Moreover, some of the methods only rely on measured data, such as current, voltage and temperature, whereas others rely on derived quantities such as state of charge (SOC). Models include simple statistical models and more complicated machine learning techniques. Different datasets have been used in order to explore the various methods, including public datasets, data from laboratory tests and operational data from ships in actual operation. Lessons learned from this exploration will be important in establishing a framework for data-driven diagnostics and prognostics of maritime battery systems within the scope of classification societies.

Data-driven condition monitoring of two-stroke marine diesel engine piston rings with machine learning

ABSTRACT Maintaining the condition of a vessel and its equipment guarantees the scheduled completion of voyages and the safety of the crew. This paper presents condition monitoring techniques for early detection of faults related to piston rings in remote cylinders of two-stroke marine diesel engines. Operational sensor data from the main engine of a container ship are provided by a shipping company. A graphical approach complimented by correlation heatmaps and feature importance from gradient boosting trees are used for feature selection. Support Vector Machine, Random Forest and Extreme Gradient Boosting Trees are tested for residual generation from the nominal behavior. The residual time series gives a good indication of the degradation of the system and can be used for alarm raising under strict rules. It is proven that the proposed method could alert the engine crew of a change in the condition of the piston rings much earlier than existing methods.

Data‐driven snapshot methods leveraging data fusion to estimate state of health for maritime battery systems

AbstractThe number of fully electric or hybrid ships relying on battery power for propulsion and maneuvering is growing. In order to ensure the safety of these ships, it is important to monitor the capacity that can be stored in the batteries, and classification societies typically require that this can be verified by independent tests—annual capacity tests. However, this paper discusses data‐driven alternatives based on operational sensor data collected from the batteries. There are different strategies for such data‐driven state of health (SOH) estimation. Some approaches require full operational history of the batteries in order to predict SOH, and this may be impractical due to several reasons. Thus, methods that are able to give reliable estimation of SOH based on only snapshots of the data streams are more attractive from a practical point of view. In this paper, data‐driven snapshot methods are explored and applied to degradation data from battery cells cycled in different laboratory tests. Hence, data from different sources are fused together with the aim of achieving better predictions. The paper presents the battery data show how relevant features can be extracted from snapshots of the data and presents data‐driven models for SOH estimation. It is discussed how such methods could be utilized in a data‐driven classification regime for maritime battery systems. Results are encouraging, and yields reasonable degradation estimates for nearly 40% of the tested cells, although the fusion of data from different laboratory tests did not improve results significantly. Results are greatly improved if data from the actual cell is included in the training data, and indicates that better results can be achieved if more representative training data is available.

Improved RUL Predictions of Aero- Engines by Hyper-Parameter Optimization of LSTM Neural Network Models.

Abstract: In the industry domains such as transportation, power generation and heavy engineering industries utilize complex machinery, as their working principles are very complex and it is very difficult to predict their exact life and operational availability due to difficulties involved in their operations. PHM- Prognostics and health management is one such domain which supports in the management of this machinery also known as assets for continuous monitoring for their best utilization and maximum efficiency. For any machine, the current health of the system can be determined by operational and raw sensor data. This data can also be utilized for the prediction of remaining useful life (RUL) of the system provided a reliable prediction model is available. It is always be challenging to determine the remaining useful life of complex machines such as turbofan jet engines from the knowledge of the data available from operating conditions and sensor data. An HPT LSTM- advanced hyper parameter tuned LSTM- Long Short Term Memory neural network model is developed to accurately determine the remaining useful life of the turbojet fan engines. To test this predictive model, a NASA developed database CMAPSS- Commercial Modular Aero Propulsion System Simulation is used. The performance of this HPT LSTM is found to be much improved as compared to reference machine learning algorithms such as simple linear regression and Lagged Multi- Layer Perceptron Models

A novel semi-supervised learning approach for State of Health monitoring of maritime lithium-ion batteries

Lithium-ion batteries are a prominent technology for the electrification of the transport sector, which itself is a key measure towards the departure from fossil fuels. The “green shift” is taking place in the marine industry too, where the number of battery-powered vessels is fastly growing. In this case, monitoring the battery State of Health is essential more than ever to optimise battery use, promote safety, and ensure the coverage of ship power and energy demands. Classification societies typically require annual capacity tests for this purpose; however, the tests are disruptive, costly and time-consuming. As a consequence they are seldom, in addition to not being always fully reliable. We propose a novel alternative semi-supervised learning approach to estimate the State of Health of a lithium-ion battery system with no labelled data, starting from a minimal set of weakly labelled data from another similar system. The method is based on operational sensor data gathered from the battery, together with the battery State of Charge. Our results show that the procedure is valid, and the obtained estimates can be used to significantly progress in failure prevention, operational optimisation, and for planning batteries at the design stage.

A Data-Driven Snapshot Method for State of Health Modelling and Diagnostics of Maritime Battery Systems

Battery systems are increasingly being used for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion and manoeuvring is growing. In order to ensure the safety of such electric ships, it is of paramount importance to monitor the available energy that can be stored in the batteries, and classification societies typically require that the state of health of the batteries can be verified by independent tests - annual capacity tests. However, this paper discusses data-driven diagnostics for state of health modelling for maritime battery systems based on operational sensor data collected from the batteries as an alternative approach. There are different strategies for such data-driven diagnostics. Some approaches, referred to as cumulative damage models, require full operational history of the batteries in order to predict state of health, and this may be impractical due to several reason. Thus, snapshot methods that are able to give reliable estimation of state of health based on only snapshots of the data streams are attractive candidates for data-driven diagnostics of battery systems on board ships. In this paper, data-driven snapshot methods are explored and applied to a novel set of degradation data from battery cells cycled in laboratory tests. The paper presents the laboratory tests, the resulting battery data, shows how relevant features can be extracted from snapshots of the data and presents data-driven models for state of health prediction. It is discussed how such methods could be utilized in a data-driven classification regime for maritime battery systems. Results are encouraging, and yields reasonable degradation estimates for 40% of the tested cells. This is greatly improved if data from the actual cell is included in the training data, and indicates that better results can be achieved if more representative training data is available. Nevertheless, improved accuracy is required for such snapshot methods to be recommended for ships in actual operation.

An Efficient IIoT Gateway for Cloud–Edge Collaboration in Cloud Manufacturing

The cloud manufacturing system can provide consumers with on-demand manufacturing services, which significantly improve the utilization rate of distributed manufacturing resources and the response speed of personalized product needs. In the cloud manufacturing platform, the successful implementation of various industrial applications relies on the uploading and streaming of related field-level manufacturing data. For example, the realization of manufacturing service composition application should match the manufacturing tasks with distributed manufacturing resources according to their working state data and performance measurement data. Therefore, this paper proposes a data integration and analysis framework of a cloud manufacturing system based on cloud–edge collaboration and the Industrial Internet of Things (IIoT). A service-oriented information model is established to uniformly describe the related operational data and functional attributes of heterogeneous manufacturing resources. Secondly, a real-time transmission and integration method of high-volume operational field and sensor data based on message middleware is proposed to realize the remote monitoring of distributed manufacturing resources and efficient distribution of related data. Finally, a cloud–edge collaboration mechanism is put forward to train and update the parameters of various artificial intelligence models deployed at edge gateways. In the experiment, taking the computer numerical control (CNC) lathe as an example, the effectiveness of the proposed manufacturing resource access method is verified. Taking the fault diagnosis model of the CNC lathe as an example, the efficiency of the proposed cloud–edge collaboration mechanism for model updating is verified.

New Reprocessing towards Life-Time Quality-Consistent Suomi NPP OMPS Nadir Sensor Data Records (SDR): Calibration Improvements and Impact Assessments on Long-Term Quality Stability of OMPS SDR Data Sets

The Nadir Mapper (NM) and Nadir Profiler (NP) within the Ozone Mapping and Profiler Suites (OMPS) are ultraviolet spectrometers to measure Earth radiance and Solar irradiance spectra from 300–380 nm and 250–310 nm, respectively. The OMPS NM and NP instruments flying on the Suomi-NPP (SNPP) satellite have provided over ten years of operational Sensor Data Records (SDRs) data sets to support a variety of OMPS Environmental Data Record (EDR) applications. However, the discrepancies of quality remain in the operational OMPS SDR data prior to 28 June 2021 due to changes in calibration algorithms associated with the calibration coefficient look-up tables (LUTs) during this period. In this study, we present results for the newly (v2) reprocessed SNPP OMPS NM and NP SDR data prior to 30 June 2021, which uses consistent calibration tables with improved accuracy. Compared with a previous (v1) reprocessing, this new reprocessing includes the improvements associated with the following updated tables or error correction: an updated stray light correction table for the NM, an off-nadir geolocation error correction for the NM, an artificial offset error correction in the NM dark processing code, and biweekly solar wavelength LUTs for the NP. This study further analyzes the impact of each improvement on the quality of the OMPS SDR data by taking advantage of the existing OMPS SDR calibration/validation studies. Finally, this study compares the v2 reprocessed OMPS data sets with the operational and the v1 reprocessed data sets. The results demonstrate that the new reprocessing significantly improves the accuracy and consistency of the life-time SNPP OMPS NM and NP SDR data sets. It also advances the uniformity of the data over the dichroic range from 300 to 310 nm between the NM and NP. The normalized radiance differences at the same wavelength between the NM and NP observations are reduced from 0.001 order (v1 reprocessing) or 0.01 order (operational processing) to 0.001 order or smaller. The v2 reprocessed data are archived in the NOAA CLASS data center with the same format as the operational data.

Land use/land cover classification using machine learning models

<p>An ensemble model has been proposed in this work by combining the extreme gradient boosting classification (XGBoost) model with support vector machine (SVM) for land use and land cover classification (LULCC). We have used the multispectral Landsat-8 operational land imager sensor (OLI) data with six spectral bands in the electromagnetic spectrum (EM). The area of study is the administrative boundary of the twin cities of Odisha. Data collected in 2020 is classified into seven land use classes/labels: river, canal, pond, forest, urban, agricultural land, and sand. Comparative assessments of the results of ten machine learning models are accomplished by computing the overall accuracy, kappa coefficient, producer accuracy and user accuracy. An ensemble classifier model makes the classification more precise than the other state-of-the-art machine learning classifiers.</p>

Data-Driven Diagnostics and Prognostics for Modelling the State of Health of Maritime Battery Systems – a Review

Battery systems are becoming an increasingly attractive alternative for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion and maneuvering is growing. In order to ensure the safety of such electric ships, it is of paramount importance to monitor the available energy that can be stored in the batteries, and classification societies typically require that the state of health of the batteries can be verified by independent tests – annual capacity tests. However, this paper discusses data-driven diagnostics for state of health modelling for maritime battery systems based on operational sensor data collected from the batteries as an alternative approach. Thus, this paper presents a comprehensive review of different data-driven approaches to state of health modelling, and aims at giving an overview of current state of the art. Furthermore, the various methods for data-driven diagnostics are categorized in a few overall approaches with quite different properties and requirements with respect to data for training and from the operational phase. More than 300 papers have been reviewed, most of which are referred to in this paper. Moreover, some reflections and discussions on what types of approaches can be suitable for modelling and independent verification of state of health for maritime battery systems are presented.

Data-driven state of health modelling—A review of state of the art and reflections on applications for maritime battery systems

Battery systems are becoming an increasingly attractive alternative for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion and manoeuvring is growing. In order to ensure the safety of such electric ships, it is of paramount importance to monitor the available energy that can be stored in the batteries, and classification societies typically require that the state of health of the batteries can be verified by independent tests — annual capacity tests. However, this paper discusses data-driven state of health modelling for maritime battery systems based on operational sensor data collected from the batteries as an alternative approach. Thus, this paper presents a comprehensive review of different data-driven approaches to state of health modelling, and aims at giving an overview of current state of the art. More than 300 papers have been reviewed, most of which are referred to in this paper. Moreover, some reflections and discussions on what types of approaches can be suitable for modelling and independent verification of state of health for maritime battery systems are presented.

Developing a near real-time road surface anomaly detection approach for road surface monitoring

Road surface hazards affect the driving safety and comfort of road users. Recently, smartphones and mobile devices equipped with motion sensors such as accelerometers and gyroscope sensors have attracted researchers’ attention for the development of low-cost approaches for road surface monitoring. However, processing smartphone sensors to monitor road surface conditions is technically challenging due to dissimilar sensor properties, different smartphone placement, and also different vehicle mechanical properties. This study aimed to develop a hybrid method using threshold based and Machine Learning approaches for near real-time detection and classification of road surface anomalies using smartphone sensor data with higher-level accuracy. The proposed algorithm has self-adapting and self-updating capabilities to adapt itself to any type of smartphone and the dynamic behaviors of various vehicles and road surface conditions. A prototype is developed using MATLAB and ArcGIS to perform sensor data analysis, geocoding, geo-visualizing, and data querying for performance evaluation.

Identification of Bridge Key Performance Indicators Using Survival Analysis for Future Network-Wide Structural Health Monitoring.

Machine learning and statistical approaches have transformed the management of infrastructure systems such as water, energy and modern transport networks. Artificial Intelligence-based solutions allow asset owners to predict future performance and optimize maintenance routines through the use of historic performance and real-time sensor data. The industrial adoption of such methods has been limited in the management of bridges within aging transport networks. Predictive maintenance at bridge network level is particularly complex due to the considerable level of heterogeneity encompassed across various bridge types and functions. This paper reviews some of the main approaches in bridge predictive maintenance modeling and outlines the challenges in their adaptation to the future network-wide management of bridges. Survival analysis techniques have been successfully applied to predict outcomes from a homogenous data set, such as bridge deck condition. This paper considers the complexities of European road networks in terms of bridge type, function and age to present a novel application of survival analysis based on sparse data obtained from visual inspections. This research is focused on analyzing existing inspection information to establish data foundations, which will pave the way for big data utilization, and inform on key performance indicators for future network-wide structural health monitoring.

NOAA-20 VIIRS Reflective Solar Band Postlaunch Calibration Updates Two Years In-Orbit

The National Oceanic and Atmospheric Administration (NOAA)-20 Visible Infrared Imaging Radiometer Suite (VIIRS) was launched on November 18, 2017, and it has been operational for more than two years and follows the first Joint Polar Satellite System (JPSS) series of the Suomi National Polar-orbiting Partnership (S-NPP) mission. VIIRS has 14 reflective solar bands (RSBs) covering a spectral range of 0.41– $2.3~\mu \text{m}$ . The primary source of RSB calibration is the solar diffuser (SD), and the time-dependent SD degradation is monitored by the SD stability monitor (SDSM). The initial instability of the SD degradation (H-factor) was resolved by updating SDSM sun screen transmittance function combining yaw maneuver data and on-orbit SDSM data sets. After the H-factor improvements, the VIIRS RSB calibration coefficients (F-factors) are updated and applied to the operational Sensor Data Record (SDR) product generation. To validate the SD F-factors, the lunar F-factors are calculated by using a lunar irradiance model and comparing the trend differences between them. Over the two years of operation, decreasing trends have been calculated with the SD F-factors, whereas constant lunar F-factors were observed in bands M1–M4. With these discrepancies, the operational F-factors remained unchanged since April 2018 because the deep convective cloud (DCC) and cross-calibration comparison results did not show any further degradations in these bands. All the possible radiometric calibration sources, such as SD and lunar F-factors, DCC trends, and cross-calibration results, are monitored, compared, and applied by the NOAA VIIRS SDR science team for the best quality of the VIIRS SDR product.

On Making Factories Smarter through Actionable Predictions based on Time-Series Data

The emergence of the Industrial Internet of Things paves the way for enhancing the real-time monitoring capabilities of contemporary factories. This can be materialised through sensors collecting data which can be further analysed. This paradigm enables the detection of indicators concerning systems’ degradation and facilitates corrective actions to be performed ahead of time. In this paper, we propose a damage prediction framework exploiting data that are coming from the core IT system in a steel industry use case. The novelty of our approach lies in the exploitation of Deep Learning techniques over streaming operational sensor data. To evaluate the framework, real-life data are collected and analysed based on daily operational activities enriched with the Remaining Useful Life (RUL). The Remaining Useful Life is automatically computed. We also periodically align the damage attribute, which is recorded in the planned activities and is performed by the maintenance engineers. We demonstrate the framework’s potential by conducting a quantitative and qualitative analysis to timely identify rare events based on historical data and predict dynamic behavioural changes in the manufacturing settings.

Improved Lunar Intrusion Detection Algorithm for the CrIS Sensor Data Record

As one of the calibration reference targets used to calibrate the cross-track infrared sounder (CrIS) earth scene (ES) measurements, the stable deep space (DS) reference spectrum in the 30-scan DS calibration moving window is very important for the accuracy of the calibrated ES radiances. The DS view changes when the lunar radiation intrudes into the observation field of view (FOV). In the original CrIS lunar intrusion (LI) detection algorithm implemented in the operational ground processing system, the contaminated DS spectra were not effectively removed from the DS moving window due to large threshold values and the assumption that the first DS spectrum in the moving window was not contaminated. As a result, inaccurate, degraded, or invalid ES radiances were produced in the operational CrIS sensor data record (SDR) during LI events. In this article, an improved LI detection algorithm is developed and implemented into the operational system. First, the new algorithm efficiently finds a contamination-free DS spectrum in the DS 30-scan calibration moving window to use as the reference spectrum. Second, based on the phase characteristics of the complex raw DS spectra during LI events, the LI band-dependent thresholds were derived to effectively reject the contaminated DS spectra and to make the valid DS window size consistent among the three CrIS bands. The new LI algorithm implemented in the operational system shows a successful detection and removal of all the lunar-contaminated DS spectra in the DS moving window, resulting in an improved calibration of ES radiances during LI events.

Prediction of odor complaints at a large composite reservoir in a highly urbanized area: A machine learning approach.

Odorous compound emissions and odor complaints from the public are rising concerns for agricultural, industrial, and water resource recovery facilities (WRRFs) near urban areas. Many facilities are deploying sensors that measure malodorous compounds and other factors related to odor creation and dispersion. Focusing on the Metropolitan Water Reclamation District of Greater Chicago's (MWRDGCs) Thornton Composite Reservoir (7.9 billion gallon capacity), we used meteorological, operational, and H2S sensor data to train a 3-day advance-warning predictor of local odor complaints, so as to implement targeted odor prevention measures. Using a machine learning approach, we bypassed difficulties in modeling both physical dispersion and human perception of odors. Utilizing random forest algorithms with varied settings and input attributes, we find that a small network of H2S sensors, meteorological data, and operational data are able to predict odor complaints three days in advance with greater than 60% accuracy and less than 25% false-positive rates, exceeding MWRDGC's standards required for full-scale deployment. PRACTITIONER POINTS: A random forest algorithm trained on H2 S, weather, and operations data successfully predicted odor complaints surrounding a large composite reservoir. Thirty-two data attribute combinations were tested. It was found that H2 S sensor data alone are insufficient for predicting odor complaints. The best predictor was a Random Forest Classifier trained on weather, operational, and H2 S readings from the reservoir corner locations. This study demonstrates odor complaint prediction capability utilizing a limited set of data sources and open-source machine learning techniques. Given a small network of H2 S sensors and organized data management, WRRFs and similar facilities can conduct advance-warning odor complaint prediction.