Diagnosis of automation devices based on engineering and historical data

Fisher information matrix based time-series segmentation of process data

The diagnosis of abnormal plant operation can be greatly facilitated if periods of similar plant performance can be located in the historical database. A novel methodology is proposed for this pattern matching problem. The new approach provides a preliminary screening of large amounts of historical data in order to generate a candidate pool of similar periods of operation. This much smaller number of records can then be further evaluated by someone familiar with the process. Similarity factors are used to characterize the degree of similarity between the current abnormal operation and historical data. A new distance similarity factor is proposed that complements the standard PCA similarity factor. The two similarity factors provide the basis for an unsupervised pattern matching technique. The proposed pattern matching methodology has been evaluated in a detailed case study for a controlled CSTR (14 measured variables, more than 474,000 data points for each measured variable, and 19 operating modes/faults). The proposed methodology was able to locate over 90% of the previous occurrences of "abnormal situations".

Industrial processes generally have various operation modes, and fault detection for such processes is important. This paper proposes a method that integrates a variational Bayesian Gaussian mixture model with canonical correlation analysis (VBGMM-CCA) for efficient multimode process monitoring. The proposed VBGMM-CCA method maximizes the advantage of VBGMM in automatic mode identification and the superiority of CCA in local fault detection. First, VBGMM is applied to unlabeled historical process data to determine the number of operation modes and cluster the data in each mode. Second, local CCA models that explore input and output relationships are established. Fault detection residuals are generated in each local CCA model, and monitoring statistics are derived. Finally, a Bayesian inference probability index that integrates monitoring results from all local models is developed to increase the monitoring robustness. The effectiveness of the proposed monitoring scheme is verified through experimental studies on a numerical example and the multiphase batch-fed penicillin fermentation process. Note to Practitioners —Process monitoring is important in guaranteeing process safety and improving product quality. Large amounts of unlabeled process data with multiple operation modes generally exist in industrial processes. Labeling these data is difficult or costly. Hence, this paper presents a VBGMM-CCA method for monitoring multimode processes. The key advantage of the proposed method is that it automatically identifies the number of operation modes in historical data and clusters the data. Then, local CCA monitors are established to model the process input and output relationships. During online monitoring, the running-on operation mode is identified through a density function, and the process status is evaluated by the corresponding CCA monitor. A probabilistic monitoring index is also developed to increase the robustness of the monitoring. In comparison with the results of conventional methods, the monitoring results of the proposed approach are more reliable and informative because the process status and the type of the detected fault are presented.

Todays many devices generate data everywhere and anytime. Data grow massively and becomes complex thing that needs to be handled. Unstructured data is one type of big data that is difficult to process and consists of unstable attributes. In traffic management, CCTVs are installed to monitor the specific location in the highway. CCTV generates unstructured data in image and video format. These data are difficult to process due to the complexity of the data. This research proposes to implement big data analytics to process real-time unstructured data from CCTV into knowledge displayed in web dashboard. We implement the YOLO framework with YoloV4 Architecture and COCO dataset for traffic flow counting and detecting illegal parking which is categorized as abnormal situation. Unstructured data from CCTV then transformed into semi-structured format in JSON. Data also can be visualized in real time to facilitate local authority to understand the highway situation. Historical data are stored in the NoSQL database to deep more knowledge such as vehicle traffic pattern. The proposed system requires the ROI drawing line as trigger to count the passing vehicles. These experiments are conducted from open CCTV for traffic online in Bali Tower Public Streaming. The prototype result is able to detect the object with 10 fps.

Monte Carlo simulation is a probabilistic simulation where the solution of problem is given based on random process. The random process involves a probabilitydistribution from data variable collected based on historical data. The used model is probabilistic Economic Order Quantity Model (EOQ). This model then assumed use Monte Carlo simulation, so that obtained the total of optimal supply cost in the future. Based on data processing, the result of probabilistic EOQ is $486128,19. After simulation using Monte Carlo simulation where the demand data follows normal distribution and it is obtained the total of supply cost is $46116,05 in 23 months later. Whereas the demand data uses Weibull distribution is obtained the total of supply stock is $482301,76. So that, Monte Carlo simulation can calculate the total of optimal supply in the future based on historical demand data.

Well testing is one of the vital process as part of reservoir performance monitoring. As field matures with increase in number of well stock, testing becomes tedious job in terms of resources (MPFM and test separators) and this affect the production quota delivery. In addition, the test data validation and approval follow a business process that needs up to 10 days before to accept or reject the well tests. The volume of well tests conducted were almost 10,000 and out of them around 10 To 15 % of tests were rejected statistically per year. The objective of the paper is to develop a methodology to reduce well test rejections and timely raising the flag for operator intervention to recommence the well test. This case study was applied in a mature field, which is producing for 40 years that has good volume of historical well test data is available. This paper discusses the development of a data driven Well test data analyzer and Optimizer supported by artificial intelligence (AI) for wells being tested using MPFM in two staged approach. The motivating idea is to ingest historical, real-time data, well model performance curve and prescribe the quality of the well test data to provide flag to operator on real time. The ML prediction results helps testing operations and can reduce the test acceptance turnaround timing drastically from 10 days to hours. In Second layer, an unsupervised model with historical data is helping to identify the parameters that affecting for rejection of the well test example duration of testing, choke size, GOR etc. The outcome from the modeling will be incorporated in updating the well test procedure and testing Philosophy. This approach is being under evaluation stage in one of the asset in ADNOC Onshore. The results are expected to be reducing the well test rejection by at least 5 % that further optimize the resources required and improve the back allocation process. Furthermore, real time flagging of the test Quality will help in reduction of validation cycle from 10 days hours to improve the well testing cycle process. This methodology improves integrated reservoir management compliance of well testing requirements in asset where resources are limited. This methodology is envisioned to be integrated with full field digital oil field Implementation. This is a novel approach to apply machine learning and artificial intelligence application to well testing. It maximizes the utilization of real-time data for creating advisory system that improve test data quality monitoring and timely decision-making to reduce the well test rejection.

Predictive maintenance is a strategy aimed at anticipating asset deterioration by forecasting future condition, enabling proactive maintenance scheduling. Advanced analytics and machine learning allow for the identification of patterns in historical data, leading to more accurate forecasts and better-informed maintenance planning. In civil engineering, this approach is particularly relevant for managing complex assets such as bridge structures. This article presents a study on 24 517 bridges in Spain’s national highway network, managed by the Directorate-General for Highways under the Ministry of Transport and Sustainable Mobility. The objective was to model the evolution of the condition index (CI) over time. Historical inspection data were combined with traffic volumes, climate variables and geotechnical characteristics. Due to the absence of key variables such as the year of construction and maintenance history, the deterioration rate between inspections was modelled first and subsequently used to forecast future CI values. An iterative process was used to develop a predictive model with gradient boosting algorithms. The model improved the error metric by 40% compared to a naïve baseline and provided a continuous estimate of structural condition. This data-driven approach supports more efficient bridge management by optimising maintenance planning and identifying anomalies in inspection data.

Part 1 Time series analysis and population reconstruction: inverse projection and demographic fluctuations generalized inverse projection benchmarks for a new inverse population projection programme - England, Sweden and a standard demographic transition the trend method applied to English data other paths to the past - from vital series to population patterns short-run population dynamics among the rich and poor in European countries, rural Jutland and urban Rouen. Part 2 New challenges for record linking and family reconstitution: the construction of individual life histories - application to the study of geographical mobility in the Valserine valley in the 19th and 20th centuries incomplete histories in family reconstitution - a sensitivity test of alternative strategies with historical Croatian data family reconstitution and population reconstruction - two approaches to the fertility transition in France, 1740-1911 family reconstitution as event-history analysis. Part 3 Event-history analysis with historical data: techniques of event-history analysis an attempt to analyze individual migration histories from data on place of usual residence at the time of certain vital events - France during the 19th century some applications of recent developments in event-history analysis for historical demography combined time-series and life-event analysis - the impact of economic fluctuations and air temperature on adult mortality by sex and occupation in a Swedish mining parish, 1757-1850. Part 4 Simulating historical processes: simulation of change to validate demographic analysis estimating numbers of kin in historical England using demographic microsimulation my brother's keeper - modelling kinship links in early urbanization. Part 5 New sources, new techniques: coarse and refined methods for studying the fertility transition in historical populations the last emperors - an introduction to the demography of the Qing (1644-1911) imperial lineage historical demography from the census - applications of the American census microdata files excess mortality in youth.

Monte Carlo simulation-based traffic speed forecasting using historical big data

Healthcare information systems typically collect, store and manage various kinds of data such as illness details, clinical history, essential body parameters, health insurance plans, and other related data towards enabling data processing and analytics to arrive at better decision making with all the clarity and alacrity. To reduce the mortality rate due to heart diseases, it is essential to predict the presence of disease in its budding stage itself. Manual extraction of the useful knowledge from historical data is practically tedious and time-consuming. Machine learning (ML) algorithms are being used to detect and predict something useful out of both historical and current data. Despite the applicability of machine learning algorithms for prediction, the accuracy of prediction is significantly influenced by features used for prediction. Moreover, to meet the needs of evolving data sizes, suitable technologies for data storage also become essential. Based on these two aspects, a comparative analysis has been performed for feature selection using four filter methods, namely, correlation measure, information gain, gain ratio and relief. Further, a scalable architecture using Hadoop framework has been proposed to enable the machine learning algorithms to handle larger datasets while performing prediction task. The impact of the proposed architecture on the performance of machine learning algorithm has been evaluated with benchmark dataset and found to have improved scalability and accuracy.

An error analysis method based on historical orbital data is introduced, the periodic characteristics of the orbit prediction error are presented, and the error fitting is done by bringing in the Poisson series.

Based on the concepts laid out in an earlier article (Jaeckle and MacGregor, 1998), this paper defines the problem of moving the production of a particular product grade from a plant A to another plant B when both plants have already produced a similar range of grades. Since the two plants may differ in size, configurations, and so on, the process conditions required to produce any given product grade may be very different in the two plants. How historical process data on both plants may be utilized to assist in this problem is investigated. A multivariate latent variable method is proposed that uses data from both plants to predict process conditions for plant B for a grade previously produced only in plant A. The approach is illustrated by a simulation example.

The natural development of the region of North-West Bohemia has been affected by human activity in many ways. In the brown-coal basin, the open-pit mines and the heavy/chemical industry have completely changed the shape of the georelief, including hydrographic networks, land-use and settlement. The neighboring Ore Mountains are victims of settlement extinction caused by the political situation after the Second World War and huge water dam constructions. In this paper different methods for preserving the changes that have been occurred in this region. The methods include historical data processing, modelling, reconstructions, analysis and visualizations. Historical data preprocessing is a very important part of the project as it influences the overall quality of all the results. Different methods for old maps, georeferencing, and aerial imagery processing and digital terrain models derivation were tested and used throughout the project. Data supporting the research were obtained directly in the field using the KAP (Kite Aerial Photography) and UAV (Unmanned Aerial Vehicle) technology. The task concerning modelling and reconstruction is based on data derived from defined time-line of processed data—here we covered the period from 1720 up to nowadays. The results of this part of the project are high quality digital terrain models derived for different time periods, hydrological network reconstructions, land-use development, and extinct settlement 3D reconstructions. Analysis and visualization was performed within the GIS environment. All the processed data are published using the ArcGIS for Server technology offering data visualizations and basic analysis to the public within the Internet. The information system resulting from this project will offer a comprehensive source of processed historical data for other scientific usages and for preserving the cultural heritage of this region for further generations.

All applications in current trends need to use Machine Learning and Big Data in this huge data world.Machine learning is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so.Machine learning use historical data as input to predict new output values.Small Scale and even large developers cannot maintain Machine Learning Algorithms and other big data processing techniques all by themselves.To harvest, process and analyze the data we need a data processing engine.Our project is to provide them with a machine learning engine which runs on.a specified port on their servers which collects the data sets in real time.This which can be queried using a simple Query Language and analyze the database on the query.The purpose of our project is to create a Data Processing Engine for Big Data Analytics. Machine learning and Big Data plays a major role in the current huge data world. Our project is to maintain a dedicated machine learning and data processing engine, so that even small developers without the knowledge of machine learning and big data analysis can produce expected results based on Machine Learning to make their application smooth. All applications in current trends need to use Machine Learning and Big Data in this huge data world. Machine learning is a subset of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning uses historical data as input to predict new output values. Small Scale and even large developers cannot maintain Machine Learning Algorithms and other big data processing techniques all by themselves. To harvest, process and analyze the data we need a data processing engine. This project is to provide them a data processing engine which runs on a specified port on their servers which collects the data sets in real time. This can be queried using a simple Query Language and analyze the data and produce respected results using ML based on the query

Digital construction and information management have become the development trend of the construction industry. The integration of BIM technology and big data concepts has broad application prospects in engineering digital information management. The application of BIM technology has not only promoted the flow of construction information in the entire life cycle of the project, improved the level of project management informationization, but also brought higher practical value and social benefits. Based on the large amount of historical engineering data accumulated by the BIM digital platform, the value of engineering data information management is analyzed. This paper proposes a value mining method for engineering digital information management based on BIM massive data, which provides a reference for mining the potential value of engineering information, and provides a path basis for the realization of engineering data twinning and digital management. It is expected to provide theoretical and practical guidance for future engineering project decision-making through value mining.KeywordsBuilding information modelingValue miningRealization path