Monitoring Data Processing Research Articles

Carbon cycle: ESP and UAV data processing approaches for forest ecosystem monitoring examples

The review article provides a comprehensive overview of modern methods and approaches for processing large volumes of observational data in the context of monitoring forest ecosystems. The article shows examples of processing various data obtained using Earth remote sensing (ERS) and unmanned aerial vehicles (UAVs). Particular attention is paid to assessing the carbon cycle; the practice of using machine learning methods in processing monitoring data is also discussed in detail, as they play a key role in increasing the accuracy of the resulting estimates. The article also discusses modern geographic information systems designed for complex analysis of data from various natural complexes.

Noise reduction analysis of deformation data based on CEEMD-PE-SVD modeling

In the field of high slope deformation monitoring, the deformation data obtained are often characterized by high volatility, strong nonlinearity, and noise content, due to the influence of factors such as the surrounding environment, human operation, and the complexity of the project. To overcome these problems, this paper proposes deformation data based on the coupling of complementary ensemble empirical modal decomposition (CEEMD), permutation entropy (PE), and singular value decomposition (SVD). Firstly, CEEMD decomposition is performed on the deformation data. Secondly, a randomness test is performed on the obtained modal components, and if the entropy value of the component arrangement entropy is greater than 0.5, SVD decomposition will be used for noise reduction. Finally, the components that meet the conditions are reconstructed to realize the noise reduction of the deformation data. The results show that the algorithm model has an excellent noise elimination effect, which can reflect the internal detail information of deformation data and provide a well-established method for future research on the processing of deformation monitoring data.

Review of recent developments in AI-based data processing and prediction for braced excavation design

Abstract This paper presents a review of the recent advances in the application of artificial intelligence (AI) techniques for data processing and prediction in the design and construction of braced excavation systems. It introduces various AI algorithms employed in addressing complex data processing and deformation prediction challenges in braced excavation. A pivotal development has been in the area of soil parameter and in situ monitoring data processing, which facilitates more reliable site characterization for efficient design. This paper delves into wall system and deformation predictions, showcasing AI’s ability to integrate multi-source data for real-time prediction. It also addresses spatiotemporal prediction, enhancing prediction accuracy by accounting for uncertainties. The significance of groundwater is highlighted by introducing predictive models that consider groundwater drawdown. Additionally, it discusses stability prediction based on the factor of safety of braced excavation, enabling proactive safety management for the retaining wall system and the surrounding environment. Furthermore, the paper discusses the challenges and opportunities associated with the use of generative AI and large language models, providing an overview of their significance, applications, and future directions in braced excavation.

Laser Welding of dissimilar cell tabs: Extracting physics semantics from infrared (IR) emissions as process monitoring data

Laser Welding of dissimilar & non-ferrous alloys for joining powertrain components in e-vehicles has been well-established in the automotive industry. Despite the advantages that provides compared to other joining methods, the use of Laser welding cannot eliminate the likelihood of having defective and out-of-spec products. To this end, online quality assessment has been widely adopted for welding applications, but it is implemented based on model performance criteria. In this study, the authors are attempting to undertake an explainable featured engineering approach to extract physics semantics from infrared imaging data and link them to holes and insufficient penetration of Al-Cu joints.

Статистические характеристики данных температурного мониторинга грунтовых оснований фундаментов зданий города Салехарда за 2018–2023 годы как основа для автоматизации процесса первичной обработки данных

The Arctic today is a dynamically developing territory where the construction and operation of infrastructure are complicated by the presence of permafrost. Climatic changes and anthropogenic factors have a negative impact on their condition. In this regard, studies of the current and forecast state of permafrost in natural and anthropogenic conditions are relevant, which is necessary for the formation of plans for adaptation to climate change, design and engineering surveys work, and risk ma­nagement. Monitoring the temperature regime of soils at the base of the existing infrastructure seems to be the most obvious solution for monitoring the state of permafrost. The object of the study is the soil foundation of buildings erected on permafrost. The subject of the study is data obtained using an automated soil temperature control system for the foundations of capital construction facilities in Salekhard. For the purpose of identifying negative changes in the bearing capacity of permafrost at early stages, the task of determining a set of criteria based on the analysis of temperature monitoring data and their statistical characteristics is solved. In Salekhard wells were drilled at the base of 30 buildings to the depth of the foundation, where thermometric equipment was installed. The sensors measure the soil temperature every 3 hours and transmit it to the server for analysis. As a result, the possibility of using the amplitude of annual fluctuations in the temperature of the soil base and the capacity of the seasonal melt layer under the building to assess the effectiveness of the soil thermal stabilization system is shown. By analyzing the average and maximum temperature values in the bases of objects, it is possible to identify objects with weakened zones. A set of criteria is given for identifying objects with negative changes in the frozen base, and statistical characteristics can serve as a basis for automating the process of processing monitoring data. The information obtained on the parameters of permafrost under buildings will allow us to determine the current state of the soil foundations and predict the development of the situation in order to prevent the destruction of infrastructure.

Совершенствование методов и средств геомеханического мониторинга на основе цифровых технологий

The article discusses methods and technical means of instrumental assessment and control of rockburst hazard and technogenic seismicity during underground mining of ore. It is shown that in conditions of rockburst manifestation and anthropogenic seismicity, complex geomechanical monitoring with the use of a number of complementary methods and technical means is of key importance. The principles of measuring and computing complex construction and organization of integrated monitoring are disclosed using the case of a system created at the geodynamic testing sites of the area of the Streltsovsky and Dalnegorsky ore fields. The features and technical characteristics of measuring as well as software tools included in the monitoring system are listed. Algorithms and software have been developed to filter man-made interference and isolate useful signals, improve the accuracy of location and determination of parameters of acoustically active zones, processing and presentation of monitoring data using modern digital technologies. The scientific and methodological approaches to the study of extremely stressed complex-structured geological environment and the prediction of the hazardous dynamic manifestations of rock pressure in them, including those based on the isolation and parametrization of geomechanical fields and foci of destruction formed in a rockburst hazardous rock mass, are described. The results of complex geomechanical monitoring at a number of rockburst hazardous mines in Russia are presented and the possibility of effective management of rock pressure in rockburst hazardous conditions is shown.

Геоинформационные технологии сопровождения процессов горного производства

The paper presents the tasks, methods and results of comprehensive research in geoinformatics and in development of raw material base of the mining and metallurgical complex that are conducted at the Institute of Mining of the Ural Branch of the Russian Academy of Sciences. The main objectives of the research include evaluation of methods of information and analytical support for the use of subsurface resources, means and methods of multi-tier processing of geodata, digital modeling of geo-objects and complex geomonitoring; substantiation of methods of complex geomonitoring that ensure the integrated development of subsurface resources of the Earth with a safe level of anthropogenic impact on the geo-environment; development of methods of information and analytical support for subsurface resources to solve the challenges of integrated development of mineral raw materials. As the result, criteria for assessing the protection of mining territories are justified; the intensity of the self-restoration process of areas disturbed by mining operations is estimated; a methodical approach to the accumulation and processing of geodynamic and geoinformation monitoring data from mining territories in mutual geospatial correlation is proposed; a systematization of factors, objects and types of risks in subsoil use that generate negative effect. This approach helps to justify the range of geodata required to assess the probability of a specific type of risk.

Software and Algorithmic Tools Development for Processing and Interpretation Electrotomography Monitoring Data

Year by year researchers use the method of electrotomography more extensively to solve a wide variety of tasks. For example, electrotomography can be applied in archaeological excavations, in the tasks of controlling mine tailings, in engineering surveys, to study fault structures, for monitoring studies in seismically active areas. It is necessary to perform sufficiently long-term observations to form approaches in solving the problem of predicting seismic events. This leads to the need to consider large arrays of initial data and interpret a significant amount of field data. In this regard, it is important to use and develop modern computer tools for processing and interpreting the results of regular observations. The purpose of this work is to modernize and develop the Direct-Inverse-Solver (DiInSo) software package for solving direct and inverse problems for processing, interpreting and analyzing electrotomography monitoring data.

Applied Bayesian structural health monitoring: Inclinometer data anomaly detection and forecasting

AbstractInclinometer probes are devices that can be used to measure deformations within earthwork slopes. This paper demonstrates a novel application of Bayesian techniques to real‐world inclinometer data, providing both anomaly detection and forecasting. Specifically, this paper details an analysis of data collected from across the entire UK rail network.Inclinometers are a standard tool of geotechnical site monitoring. Data from these instruments is often used in risk analysis and decision‐making. However, discerning anomalous data points and forecasting future behaviour from inclinometer data requires significant ‘engineering judgement’ (subjective appraisal). This is because the observational data is derived from complex physical phenomena and contains complex spatio‐temporal correlations. Additionally, the practical demands of data collected from remote sites over several years tends to introduce systematic errors. These issues make the interpretation of inclinometer data challenging.Practitioners have effectively two goals when processing monitoring data. The first is to identify any anomalous or dangerous movements, and the second is to predict potential future adverse scenarios by forecasting. In this paper we apply Uncertainty Quantification (UQ) techniques by implementing a Bayesian approach to anomaly detection and forecasting for inclinometer data. Subsequently, both costs and risks may be minimised by quantifying and evaluating the appropriate uncertainties. This framework may then act as an enabler for enhanced decision making and risk analysis.We show that inclinometer data can be described by a latent autocorrelated Markov process derived from measurements. This can be used as the transition model of a non‐linear Bayesian filter. This allows for the prediction of system states. This learnt latent model also allows for the detection of anomalies: observations that are far from their expected value may be considered to have ‘high surprisal’, that is they have a high information content relative to the model encoding represented by the learnt latent model.We successfully apply the forecasting and anomaly detection techniques to a large real‐world data set in a computationally efficient manner. Although this paper studies inclinometers in particular, the techniques are broadly applicable to all areas of engineering UQ and Structural Health Monitoring (SHM).

Combined a Pressure Sensor and Internet of Things in a Low-Cost Tide Gauge

Tides are important in many fields, such as port planning, nautical charting, and bathymetry surveys. However, the distribution of tide observation stations in Indonesia is still uneven, so simple tidal data collection still uses tide palms to observe the movement of sea levels. The manual tidal observation method has limitations because visually the ability of the observer to see the tide reading is different, so it is subjective. Therefore, the solution to this problem is a tidal instrument that is easy to make, provides real-time data, and produces accurate information, saving energy and time. However, using automatic tide gauge instruments is still not affordable in the Indonesian market. This study creates a low-cost pressure tide gauge by integrating a pressure sensor with an Arduino microcontroller. In addition, the data monitoring process uses the Internet of Things system. Data from the instrument measurements were uploaded to the Thingspeak website live, allowing observers to monitor in real time. Instrument’s data with noise and anomalies will go through a data filtering process with the moving average and moving median methods. Testing the instrument’s error rate compares the data generated by the instrument with tidal data from the Indonesian Geospatial Agency (BIG). Both tidal data went through calculating Root Mean Square Error, or RMSE. Based on the instrument error test results, the RMSE value for moving average data against BIG is 27.963 cm and moving median data against BIG is 27.787 cm.

Data Management and Application System of Geological Gisaster Monitoring Data

The geological disaster monitoring data management and application system adopts B/S technology structure, based on data pre-processing technology and comprehensive analysis technology such as statistic calculation of the monitoring data, displacement vector map and comprehensive analysis map of displacement and rainfall, etc., this paper expounds the management and application of geological disaster monitoring data, and solves the problems of the lack of data, the poor quality of data and the lack of analytical models in geological disaster monitoring work. The ability of comprehensive processing and scientific analysis of geological disaster monitoring data has been further improved.

Environmental pollution along the coast of Binh Thuan province, caused by the discharge of wastewater into the main river basins from the mainland

Socio-economic activities of Binh Thuan province are associated with rivers flowing through districts, towns, and cities in this province. Along with the strong socio-economic development, seven river basins have to receive a large amount of wastewater from industrial parks, livestock farms and urban areas as well, these are the main sources that lead to coastal water pollution. For the purpose of both economic growth and environmental protection in coastal areas, the study used survey methods to collect data on socio-economic activities and waste discharge activities from the mainland. In addition, the study also conducted statistical processing of monitoring data and predictive analytics for forecasting water quality. The results have shown that environmental pollution in the coastal area of Binh Thuan province originates from the discharge of wastewater from the mainland. Furthermore, this study contributed to proposing solutions being able to prevent and protect the coastal environment effectively.

Bw-ICEEMDAN/NExT-ERA method of data processing for dynamic monitoring of a super high-rise TV tower based on GNSS-RTK technique

Bw-ICEEMDAN/NExT-ERA method of data processing for dynamic monitoring of a super high-rise TV tower based on GNSS-RTK technique

Scalable in situ non-destructive evaluation of additively manufactured components using process monitoring, sensor fusion, and machine learning

Laser Powder Bed Fusion (L-PBF) Additive Manufacturing (AM) is among the metal 3D printing technologies most broadly adopted by the manufacturing industry. However, the current industry qualification paradigm for critical-application L-PBF parts relies heavily on expensive non-destructive inspection techniques, which significantly limits the use-cases of L-PBF. In situ monitoring of the process promises a less expensive alternative to ex situ testing, but existing sensor technologies and data analysis techniques struggle to detect sub-surface flaws (e.g., porosity and cracking) on production-scale L-PBF printers. In this work, an in situ NDE (INDE) system was engineered to detect subsurface flaws detected in X-Ray Computed Tomography (XCT) directly from process monitoring data. A multilayer, multimodal data input allowed the INDE system to detect numerous subsurface flaws in the size range of 200–1000 µm using a novel human-in-the-loop annotation procedure. Furthermore, a framework was established for generating probability-of-detection (POD) and probability-of-false-alarm (PFA) curves compliant with NDE standards by systematically comparing instances of detected subsurface flaws to post-build XCT data. We also introduce for the first time in the AM in situ sensing literature the a90/95 – the flaw size corresponding to a 90% detection rate on the lower 95% confidence interval of the POD curve. The INDE system successfully demonstrated POD capabilities commensurate with traditional NDE methods. Traditional ML performance metrics were also shown to be inadequate for assessing the ability of the INDE system’s flaw detection performance. It is the belief of the authors that future studies should adopt the POD and PFA approach outlined here to provide better insight into the utility of process monitoring for AM.

Pavement dynamic monitoring data processing based on wavelet decomposition and reconfiguration methods

Pavement dynamic monitoring data processing based on wavelet decomposition and reconfiguration methods

An Unsupervised Machine Learning Approach for Monitoring Data Fusion and Health Indicator Construction.

The prediction of system degradation is very important as it serves as an important basis for the formulation of condition-based maintenance strategies. An effective health indicator (HI) plays a key role in the prediction of system degradation as it enables vital information for critical tasks ranging from fault diagnosis to remaining useful life prediction. To address this issue, a method for monitoring data fusion and health indicator construction based on an autoencoder (AE) and a long short-term memory (LSTM) network is proposed in this study to improve the predictability and effectiveness of health indicators. Firstly, an unsupervised method and overall framework for HI construction is built based on a deep autoencoder and an LSTM neural network. The neural network is trained fully based on the normal operating monitoring data and then the construction error of the AE model is adopted as the health indicator of the system. Secondly, we propose related machine learning techniques for monitoring data processing to overcome the issue of data fusion, such as mutual information for sensor selection and t-distributed stochastic neighbor embedding (T-SNE) for operating condition identification. Thirdly, in order to verify the performance of the proposed method, experiments are conducted based on the CMAPSS dataset and results are compared with algorithms of principal component analysis (PCA) and a vanilla autoencoder model. Result shows that the LSTM-AE model outperforms the PCA and Vanilla-AE model in the metrics of monotonicity, trendability, prognosability, and fitness. Fourthly, in order to analyze the impact of the time step of the LSMT-AE model on HI construction, we construct and analyze the system HI curve under different time steps of 5, 10, 15, 20, and 25 cycles. Finally, the results demonstrate that the proposed method for HI construction can effectively characterize the health state of a system, which is helpful for the development of further failure prognostics and converting the scheduled maintenance into condition-based maintenance.

A novel approach to intelligent monitoring of gas composition and light mode of greenhouse crop growing zone on the basis of fuzzy modelling and human-in-the-loop techniques

Gas composition and light mode of industrial greenhouses are some of the most determining factors in the process of growing vegetable crops in greenhouse conditions. The intelligentisation of information technologies for monitoring and control based on artificial intelligence methods can increase the efficiency of agrotechnical procedures for greenhouse cultivation. One of the efficient approaches in today's world practice is the development and implementation of trustworthy hybrid decision-support systems based on the techniques of Fuzzy logic and Human-in-the-Loop. The research object is non-stationary processes of complex intelligent transformation of measurement data on the concentration of carbon dioxide and effective energy illumination in the growing zone of industrial greenhouses. The scientific novelty and practical value of the obtained research results consist in creating a computer model for aggregation and intelligent processing of agricultural monitoring data for greenhouses. The developed computer model is fully transformed into peripheral-level software of Internet of Things systems for agricultural purposes. This makes it possible to implement the for-computing architecture of monitoring systems in greenhouses. The obtained research results make it possible to optimise the resources used in growing crops in greenhouse conditions through the implementation of hardware and software intelligent monitoring tools that are adaptive to the types and periods of crop vegetation. The scientific and applied effect of the research is creating the novel approach of development and practical use of intelligent technologies for agrotechnical monitoring by substantiating the methodological provisions for synthesis of structural and algorithmic organisation of the corresponding software and hardware solutions.

RANCANG BANGUN SISTEM MONITORING PENJUALAN BARANG DI TOKO MAINAN LOVELLA TOYS

Companies that master technology and information will be able to master and become leaders in their field of business. By utilizing information technology, companies can run business processes more quickly and can process data more accurately. Lovella Toys Toy Store is a company engaged in selling toys for hobbies. Recording of sales that still uses Manual Notes for proof of transactions every day, and then at the end of the sale will be input into a Microsoft Excel file. It can make the data inaccurate because can be an input error that causes the transaction not input correctly in the Sales Data Format. A web-based computerized system is needed so that every piece of information provides added value to the process of quality management, decision-making, and problem-solving along with a competitive advantage that is useful for sales activities. This study uses qualitative research methods using field research approaches and library research in its data collection methods. The results are in the form of a web-based monitoring data processing system prototype which is expected to minimize and even solve current problems.

Statistical methods for handling nondetected results in food chemical monitoring data to improve food risk assessments.

Chemical risk assessment is important for risk management, and estimates of chemical exposure must be as accurate as possible. Chemical concentrations in food below the limit of detection are known as nondetects and result in left-censored data. During statistical analysis, the method used for handling values below the limit of detection is important. Many risk assessors employ widely used substitution methods to treat left-censored data, as recommended by international organizations. The National Institute of Food and Drug Safety Evaluation of South Korea also recommends these methods, which are currently used for chemical exposure assessments. However, these methods have statistical limitations, and international organizations recommend more advanced alternative statistical approaches. In this study, we assessed the validity of currently used statistical methods for handling nondetects. To identify the most suitable statistical method for handling nondetection, we created virtual data and conducted simulation studies. Based on both simulation and case studies, the Maximum Likelihood Estimation (MLE) and Robust Regression on Order Statistics (ROS) methods were found to be the best options. The statistical values obtained from these methods were similar to those obtained from the commonly used 1/2 Limit of Detection (LOD) substitution method for nondetection treatment. In three case studies, we compared the various methods based on the root mean squared error. The data for all case studies were from the same source, to avoid heterogeneity. Across various sample sizes and nondetection rates, the mean and 95th percentile values for all treatment methods were similar. However, "lognormal maximum likelihood estimation" method was not suitable for estimating the mean. Risk assessors should consider statistical processing of monitoring data to reduce uncertainty. Currently used substitution methods are effective and easy to apply to large datasets with nondetection rates <80%. However, advanced statistical methods are required in some circumstances, and national guidelines are needed regarding their use in risk assessments.

A criterial model for assessing the quality of the digital educational environment using cloud services

Globalization of all spheres of activity of educational systems determines the need to create simple and accessible tools for monitoring and evaluating the quality of objects and resources. In particular, due to the need to intensify the processes of digital transformation of education, it is important to assess the quality of digital educational environments (DEE). The aim of the work is to substantiate the approach and describe the procedure for monitoring of DEE of educational institutions based on the available cloud services, providing convenient collection, accumulation, and processing of statistical and monitoring indicators.The projective criterial model of the system of assessment and monitoring of the quality of DEE, which is based on the results of self-assessment of the educational organization and external expert evaluation, was adopted. The main feature of the model is the participation of organizations and external experts in the process of designing criterion rubrics, conducting and analyzing the results of monitoring. Yandex Forms service is used for self-assessment of DEE and expert evaluation of the educational organization website which allows converting of the collected data into spreadsheets. By combining the data and their statistical processing it is possible to obtain indicators for different slices and ratings, to conduct a summary clustering of the DEE of the studied organizations by three levels: low, average, and high.The proposed model was implemented in the assessment of DEE practices of supplementary education for children. To determine the quantitative and qualitative indicators of the DLE and the official sites of additional education organizations we created questionnaires in Yandex Forms filled in by the representatives of the studied organizations. Pilot testing showed that the collection, processing, and delivery of monitoring data to users was technologically simple and easy.The projective criterial model for assessing the quality of the DEE of supplementary education organizations can be used for many other studies related to criterion-based assessment activities.