The modeling and simulation of Internet of Things (IoT) and Industrial IoT (IIoT) systems allow practitioners to obtain valuable insights into the system's behavior before their actual deployment in the field. Ear...
详细信息
Since there are lots of influencing factors in indoor temperature regulation process of air conditioning system in the large-public building, it is difficult to establish an accurate mathematical model and to implemen...
详细信息
Since there are lots of influencing factors in indoor temperature regulation process of air conditioning system in the large-public building, it is difficult to establish an accurate mathematical model and to implement model-based online control. This paper proposes an online modeling method for indoor temperature regulation characteristic according to building thermal process. A physical-data driven model, which takes the state-space equation solution representation form as the reference structure, is proposed, and the model parameters are identified based on the multiple linear regression analysis. Then, experimental and simulation studies in online and offline have been carried out to validate the proposed modeling method. The contribution of this study is to provide an online model, which can not only retain system physical property but also be updated online simply. The proposed model with building thermal process property will be benefit for terminal controller design for indoor temperature regulation in the air conditioning system.
Conventional batch process monitoring strategies implement phase partition using all the collected variables in high dimensions, which may result in high computation complexity and inaccurate division results. Besides...
详细信息
Conventional batch process monitoring strategies implement phase partition using all the collected variables in high dimensions, which may result in high computation complexity and inaccurate division results. Besides, due to the time-varying characteristics, the acceptable operation regions of many monitoring models are generally too wide and thus their detection sensitivity may be compromised. In this brief, a stationary subspace analysis (SSA)-based hierarchical monitoring model is developed to solve the aforementioned issues. The proposed method extracts the global stationary features from the historical processdata and establishes a global monitoring model for the time-invariant information throughout the whole batch process. Based on the remaining nonstationary global features, a phase partition method is developed to divide the process using dynamic information in low dimensions. According to the partition result, local monitoring models are constructed for each operation phase using equilibrium relationship and dynamic information. The operation status of the newly collected sample is codetermined by both the global and local models, and a physical interpretation is provided for better process understanding. The proposed method is illustrated using a simulated process and a real industrial process. The experimental results show that the proposed method can extract key features to accurately divide the batch process into different operation phases and effectively detect the incipient fault so that immediate and corrective actions can be taken.
This paper proposes an approach to formally verify XACML policies using the process algebra mCRL2. XACML (eXtensible Access control Markup Language) is an OASIS standard for access control systems that is much used in...
详细信息
ISBN:
(数字)9783031086793
ISBN:
(纸本)9783031086793;9783031086786
This paper proposes an approach to formally verify XACML policies using the process algebra mCRL2. XACML (eXtensible Access control Markup Language) is an OASIS standard for access control systems that is much used in health care due to its fine-grained, attribute-based policy definitions, useful in dynamic environments such as emergency wards. A notorious problem in XACML is the detection of conflicts, which arise especially when combining policies, such as when health institutions merge. Our formal translation of XACML policies into mCRL2, using our automated tool XACML2mCRL2, enables us to verify the above property, called consistency, as well as other policy properties such as completeness and obligation enforcement. Verifying policy properties statically allows us to resolve inconsistencies in advance, thus avoiding situations where an access request is denied in a critical situation (e.g., in an ambulance, when lives may be put in danger) just because of incomplete or inconsistent policies. The mCRL2 toolset is especially useful for modeling behaviors of interactive systems, where XACML would be only one part. Therefore, we verify an access control system together with the intended health care system that it is supposed to protect. For this, we exemplify how to verify safety and liveness properties of an assisted living and community care system.
Soft sensor has been playing an indispensable role in the process monitoring of key process variables. How to know if deployed soft sensor models are still performing well is a challenging but crucial topic for the in...
详细信息
ISBN:
(数字)9784907764784
ISBN:
(纸本)9784907764784
Soft sensor has been playing an indispensable role in the process monitoring of key process variables. How to know if deployed soft sensor models are still performing well is a challenging but crucial topic for the industry. If there exists change points in soft sensor predictions, it indicates abrupt and significant changes in the process conditions. The presence of change points may require us to rebuild the model to ensure that it does not drift. Root cause analysis plays an important role in process monitoring when a change point occurs. Fast and accurate change point attribution is essential for timely recovery of model performance. This work proposes a straightforward way to detect the change points and find the root causes of changes. Off-line change point detection is used to detect changes by formulating change point detection as a discrete optimization problem. Then, we work on understanding which feature or combination of features that are shifting soft sensor predictions. Shapley additive explanations (SHAP) is adopted to explain the predictions of soft sensor model. It connects optimal contribution distribution with local explanations using the classic Shapley values. Finally, the effectiveness of proposed algorithms is validated on a real industrial data.
The study is devoted to Tesla stock price forecasting using sentiment analysis, econometrics, statistical methods, and machine learning models. After implementing the process of preparing price and sentiment indicator...
详细信息
ISBN:
(数字)9798350350043
ISBN:
(纸本)9798350350050
The study is devoted to Tesla stock price forecasting using sentiment analysis, econometrics, statistical methods, and machine learning models. After implementing the process of preparing price and sentiment indicators, adequate models for forecasting stock prices were built. For the considered data set, the Multivariate Regression model performed best. Using sentiment indicators reduced the errors of the LSTM and k-NN models.
Informatization and intelligence are the development trends of the future highway asphalt pavement construction quality processcontrol. This paper starts with the principle of asphalt pavement management and control ...
详细信息
The fluid structure of gas-water two-phase flow is complex and diverse, and the flow status changes with time. Monitoring the evolution process of flow status in time and accurately is of practical significance for th...
详细信息
ISBN:
(纸本)9781665483605
The fluid structure of gas-water two-phase flow is complex and diverse, and the flow status changes with time. Monitoring the evolution process of flow status in time and accurately is of practical significance for the stable operation of industrial process. With the development of multi-sensor technology, a variety of sensors designed based on different sensitivity principles can obtain comprehensive information of flow process. However, due to the uncertain factors such as the change of environment and the randomness of fluid flow, there are both nonstationary and stationary signals. In this paper, Augmented Dickey-Fuller (ADF) test is used to distinguish the nonstationary signals and the stationary signals from the multi-sensor measurement data of gas-water two-phase flow in horizontal pipe. The long-term equilibrium relationship of nonstationary signals is processed by cointegration analysis (CA) method. It solves the problem that the fluctuation of nonstationary signals masks the change trend of flow status characteristics. The nonstationary signal monitoring index is established based on the obtained cointegration sequence. Principal component analysis (PCA) method is used to process the stationary signals, which obtains the principal characteristics and residuals of flow status to establish the stationary signal monitoring indexes. Considering the non-stationarity and stationarity of gas-water two-phase flow process signals, the three monitoring indexes are integrated through Bayesian inference to realize flow status monitoring. The CA-PCA monitoring strategy is applied to the gas-water two-phase flow data to verify the feasibility and effectiveness.
The proceedings contain 108 papers. The special focus in this conference is on Computer Science Online. The topics include: Methodology for Solving the Problem of Classification of Professional Orientation Using Encep...
ISBN:
(纸本)9783031705175
The proceedings contain 108 papers. The special focus in this conference is on Computer Science Online. The topics include: Methodology for Solving the Problem of Classification of Professional Orientation Using Encephalogram data;Investigation of the Influence of External Conditions on the process of Automated Landing of an UAV on a Seismic Sensor Using Technical Vision;methodology for a Business Intelligence Platform by Using Oracle 19C database Engine and its Limitations;control of the State of Agrocenosis and Soil Environment According to Remote Sensing data;design of a Web Platform for Smoke and Flood Monitoring in a data Center Based on the Internet of Things (IoT);enhancing Quality of Experience in Omnidirectional Video: Strategies Overview;optimizing 360° Video Delivery: Advancements and Strategic Approaches;identification and Interpretation of Significant Factors Influencing Client Defaults in Microfinance Institutions Using Machine Learning Methods;a Study About Complexity of Social Network;Limitations and Benefits of the ChatGPT for Python Programmers and Its Tools for Evaluation;Security Testing in IEEE 802.11 Wireless Networks;technology Transfer in the Field of Additive Medical Technologies Based on Patent Informatics Research;personnel Privacy and Organisational data: The Awareness and Policy Enforcement for Smartphone Security Among the Malaysian Armed Forces Personnel;Forensic analysis of Cyber Attacks Using the Cyber Kill Chain Model to Enhance Antivirus Protection in an IT Solutions Company;integral Assessment of Cryptocurrency Quality;proposed Model for the Detection of Diabetic Retinopathy Using Convolutional Neural Networks;proposed Ransomware Detection Model Based on Machine Learning;unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning Decisions;Analyzing Nonlinear Behavior Sequences Through ASM.
Objectives/Scope: Subsurface scales include scale deposits present at downhole, in or near perforations, in fractures, on fracture proppants/frac faces, in porous media near frac face. As fractures and frac faces prov...
详细信息
Objectives/Scope: Subsurface scales include scale deposits present at downhole, in or near perforations, in fractures, on fracture proppants/frac faces, in porous media near frac face. As fractures and frac faces provide key pathways for hydrocarbon production in shale & tight formation, assessing and controlling subsurface scale formation has become a critical task for operators in the shale sector. This paper presents a field case study on subsurface scale diagnosis/control and produced water source allocation for a shale asset development in the Delaware Basin. Methods/Procedures/process: Subsurface scales at shale horizontal producers are difficult to collect or visually observe and thus poses challenges to diagnose and mitigate. In this study, integrated analysis of time-lapse produced water chemistry/production surveillance data, frac water data, well history/intervention jobs/field observations, petrophysics/geological data, and analog well data were conducted to understand produced water sources and diagnose subsurface scale formation for two underperforming wells. Scale modeling/risk assessment was conducted to assess the composition of subsurface scale and provided an important basis for scale formation root cause analysis and proactive scale control for upcoming development wells. Results/Observations/Conclusions: Through collaborative efforts across different disciplines, this data-driven field case study has demonstrated that scale formation at the subsurface is a primary root cause for the dramatic production underperformance of an impacted well (Well A). Integrated analysis suggested presence of high Ba water from non-targeted formation and Barite scale formation at the subsurface due to the commingling of high SO4 water and high Ba water sources during the frac/shut in stages for this well. The Chevon conceptual model on subsurface scale management (SPE-200668) was applied and updated in explaining the findings and the well production performance. A
暂无评论