Diagnostics and Prognostics of Energy Conversion Processes via Knowledge-Based Systems

This paper presents a critical and analytical description of an ongoing research program aimed at the implementation of an expert system capable of monitoring, through an Intelligent Health Control procedure, the instantaneous performance of a cogeneration plant. The expert system is implemented in the CLIPS environment and is denominated PROMISA as the acronym for Prognostic Module for Intelligent System Analysis. It generates, in real time and in a form directly useful to the plant manager, information on the existence and severity of faults, forecasts on the future time history of both detected and likely faults, and suggestions on how to control the problem. The expert procedure, working where and if necessary with the support of a process simulator, derives from the available real-time data a list of selected performance indicators for each plant component. For a set of faults, pre-defined with the help of the plant operator (Domain Expert), proper rules are defined in order to establish whether the component is working correctly; in several instances, since one single failure (symptom) can originate from more than one fault (cause), complex sets of rules expressing the combination of multiple indices have been introduced in the knowledge base as well. Creeping faults are detected by analyzing the trend of the variation of an indicator over a pre-assigned interval of time. Whenever the value of this ‘‘discrete time derivative’’ becomes ‘‘high’’ with respect to a specified limit value, a ‘‘latent creeping fault’’ condition is prognosticated. The expert system architecture is based on an object-oriented paradigm. The knowledge base (facts and rules) is clustered—the chunks of knowledge pertain to individual components. A graphic user interface (GUI) allows the user to interrogate PROMISA about its rules, procedures, classes and objects, and about its inference path. The paper also presents the results of some simulation tests.

Download Full-text

An expert system for real-time well field management

Water Science & Technology Water Supply ◽

10.2166/ws.2012.021 ◽

2012 ◽

Vol 12 (5) ◽

pp. 699-706 ◽

Cited By ~ 2

Author(s):

B. S. Marti ◽

G. Bauser ◽

F. Stauffer ◽

U. Kuhlmann ◽

H.-P. Kaiser ◽

...

Keyword(s):

Drinking Water ◽

Expert System ◽

Knowledge Base ◽

Real Time ◽

Urban Areas ◽

Industrial Sites ◽

Water Wells ◽

Well Field ◽

Field Management ◽

Historical Management

Well field management in urban areas faces challenges such as pollution from old waste deposits and former industrial sites, pollution from chemical accidents along transport lines or in industry, or diffuse pollution from leaking sewers. One possibility to protect the drinking water of a well field is the maintenance of a hydraulic barrier between the potentially polluted and the clean water. An example is the Hardhof well field in Zurich, Switzerland. This paper presents the methodology for a simple and fast expert system (ES), applies it to the Hardhof well field, and compares its performance to the historical management method of the Hardhof well field. Although the ES is quite simplistic it considerably improves the water quality in the drinking water wells. The ES knowledge base is crucial for successful management application. Therefore, a periodic update of the knowledge base is suggested for the real-time application of the ES.

Download Full-text

Using Downhole Real-Time Data To Estimate Zonal Production in a Commingled-Multiple-Zones Intelligent System

10.2118/102743-ms ◽

2006 ◽

Cited By ~ 4

Author(s):

Kai Sun ◽

Michael R. Konopczynski ◽

Arashi A. Ajayi

Keyword(s):

Real Time ◽

Intelligent System ◽

Time Data ◽

Real Time Data

Download Full-text

Development of a System for Monitoring Tool Wear Using Artificial Intelligence Techniques

10.1115/imece2001/dsc-24507 ◽

2001 ◽

Author(s):

Rui. G. Silva ◽

Steven J. Wilcox ◽

Robert L. Reuben

Keyword(s):

Neural Networks ◽

Expert System ◽

Tool Wear ◽

Knowledge Base ◽

Tool Life ◽

Intelligent System ◽

Process Data ◽

Line System ◽

Life Model ◽

The Neural Networks

Abstract The main objective of the work reported here was to develop an intelligent condition monitoring system able to detect when a cutting tool was worn out. To accomplish this objective the use of a hybrid intelligent system, based on an expert system and two neural networks was investigated. The neural networks were employed to process data from sensors and the classifications made by the neural networks were combined with information from the knowledge base to obtain an estimate of the wear state of the tool by the expert system. The novelty of this work is mainly associated with the configuration of the developed system. The combination of sensor-based information and inference rules, results in an on-line system that can learn from experience and update the knowledge base pertaining to information associated with different cutting conditions. The neural networks resolved the problem of interpreting the complex sensor inputs while the expert system, by keeping track of previous success, estimated which of the two neural networks was more reliable. Mis-classifications were filtered out through the use of a rough but approximate estimator, Taylor’s tool life model. The system’s modular structure would make it easy to update as required for different machines and/or processes. The use of Taylor’s tool life model, although weak as a tool life estimator, proved to be crucial in achieving higher performance levels. The application of the Self Organizing Map to tool wear monitoring proved to be slightly more reliable then the Adaptive Resonance Theory neural network although overall the system made reliable, accurate estimates of the tool wear.

Download Full-text

Aerocraft Real-Time Measured Data Processing Method Based on Combined Filtering

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.716-717.983 ◽

2014 ◽

Vol 716-717 ◽

pp. 983-986

Author(s):

Yan Li ◽

Hua Jun Liu ◽

Guang Lang Bian ◽

Miao Hui Liu

Keyword(s):

Data Processing ◽

Real Time ◽

Measured Data ◽

Control Procedure ◽

Time Data ◽

The Real ◽

Data Processing Method ◽

Real Time Data ◽

Processing Accuracy ◽

Real Time Data Processing

To solve the problems that resulted from using a certain filtering method alone to process the real-time data measured on aerocraft, a new method combined filter and Savitzky-Golay smoothing filter is proposed to process the real-time measuring data, which could classify and segment the measured data of aerocraft trajectory according to its priority and time domain. It could provide useful principle and control procedure of combined filters on different conditions to improve the filter efficiency, and the combined filtering results meet the needs of aerocraft real-time data processing accuracy in different measured sections.

Download Full-text

Internet of Things (IoT) for digital concrete quality control (DCQC): A conceptual framework

The proceedings of the 13th international conference "Modern Building Materials, Structures and Techniques" (MBMST 2019) ◽

10.3846/mbmst.2019.100 ◽

2019 ◽

Author(s):

Arka Ghosh ◽

M. Reza Hosseini ◽

Riyadh Al-Ameri ◽

Gintaris Kaklauskas ◽

Bahareh Nikmehr

Keyword(s):

Quality Control ◽

Internet Of Things ◽

Conceptual Framework ◽

Real Time ◽

Progress Monitoring ◽

Predictive Analytics ◽

Time Data ◽

Ongoing Research ◽

Concrete Members ◽

Concrete Quality

Concreting is generally a manual, labour intensive and time-consuming process, putting additional burden on constrained resources. Current practices of concreting are wasteful, non-sustainable and end products usually lack proper quality conformance. This paper, as the first outcome of an ongoing research project, proposes concrete as an area ripe for being disrupted by new technological developments and the wave of automation. It puts forward arguments to show that The Internet of Things (IoT), as an emerging concept, has the potential to revolutionize concreting operations, resulting in substantial time savings, confidence in its durability and enhanced quality conformance. A conceptual framework for a digital concrete quality control (DCQC) drawing upon IoT is outlined; DCQC facilitates automated lifecycle monitoring of concrete, controlled by real-time monitoring of parameters like surface humidity, temperature variance, moisture content, vibration level, and crack occurrence and propagation of concrete members through embedded sensors. Drawing upon an analytical approach, discussions provide evidence for the advantages of adopting DCQC. The proposed system is of particular appeal for practitioners, as a workable solution for reducing water, energy consumption and required man-hours for concreting procedures, as well as, providing an interface for access to real-time data, site progress monitoring, benchmarking, and predictive analytics purposes.

Download Full-text

Expert System Diagnosis of Television Damage with Depth First Search Method Using Vb.Net Programming Language

Tech-E ◽

10.31253/te.v1i2.24 ◽

2018 ◽

Vol 1 (2) ◽

pp. 50

Author(s):

Dicky Surya Dwi Putra

Keyword(s):

Artificial Intelligence ◽

Expert System ◽

Expert Systems ◽

Knowledge Base ◽

Programming Language ◽

System Analysis ◽

Search Method ◽

Depth First Search ◽

Analysis Process ◽

System Diagnosis

The expert system is part of an artificial intelligence consisting of the knowledge and experience of an expert who is included in the knowledge base. The expert system can help someone who is still lay in solving the problem. Television is a medium of communication that receives broadcasts of moving pictures and sounds. One example of an expert system created is an expert system to diagnose television damage using the Depth First Search method using the VB.NET programming language. With the application of expert systems in diagnosing television damage, expected in the analysis process becomes faster. Expert system analysis on the damage of television can be known directly to assist in knowing what damage experienced by television and what steps to improve television. In this case, the author has consulted with an expert in the field of television damage to build a knowledge base

Download Full-text

On-Line Power System Analysis Based on Hybrid Network Model

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.484-485.665 ◽

2014 ◽

Vol 484-485 ◽

pp. 665-670

Author(s):

Qin Xiao

Keyword(s):

Power System ◽

Electric Power ◽

Real Time ◽

Network Model ◽

System Analysis ◽

Hybrid Network ◽

Time Data ◽

System Operation ◽

Power System Operation ◽

Power System Analysis

Online power system analysis to electric mode-based on information that will offer a decided in real time the quality of the studies and efficiency of the power system operation precision closely associated with the power system model. Accurate and quick decision based on real-time data analysis needs battle plan deregulation of the power system in all over the world. In addition a significant expansion of electric power system in India in recent times, especially in the 2003 introduction of electricity bill, introduction of open access, electric power market, the appearance of communication through power with complex power system operation and control. Electric power network analysis in real-time data is expected to further improve the critical role of power network operation to repair the proposed law after transmission loss of tariff and share. All this forced the power system real time is accurate, but conditions analysis based on different principles. In order to meet the requirements of all, from the monitoring, commercial, reliability and stability of the Angle, attempt to have been forced to take hybrid network model in natural real-time supervisory control and data acquisition (SCADA) systems work so far a single network model of the integrated. This paper presents a network model for the theory foundation and the same is in the southern area rapidly adapt to load center (SRLDC) Bangalore and utilization of energy management system in India (EMS) real-time systems and tools. It is proved to be how to planning can online network system modeling and analysis of relatively simple in complex operational requirements. The experimental results show that the online power management strategy to adapt to can be a key tool control engineers hand in complex power system operation situations.

Download Full-text

The Galicia HF Experience: Analysis of the Results of the SeaSonde HF Radar Experience in Galicia

Volume 4: Ocean Engineering; Offshore Renewable Energy ◽

10.1115/omae2008-57831 ◽

2008 ◽

Author(s):

Pedro Agostinho ◽

Javier Garcia ◽

Chad Whelan ◽

Andre´s Alonso-Martirena

Keyword(s):

Real Time ◽

System Analysis ◽

Positive Impact ◽

Hf Radar ◽

Particle Model ◽

Special Focus ◽

Sources Of Information ◽

Time Data ◽

Fully Integrated ◽

Drifting Buoy

Two long-range CODAROS SeaSonde HF radar stations were installed and operated for three months (Nov 2005 to Feb 2006) in the Galician coast, the main area affected by the Prestige disaster. During this period, all the produced data were freely distributed in real time via Internet. The dissemination system was fully integrated with the Puertos del Estado web products, which are providing real time data of several oceanographic and atmospheric parameters, such as sea level and waves. One of the buoys of the Puertos del Estado deep-water network, equipped with a current meter, is moored in the area covered by the Radar system. Analysis of the three months of data shows good correlation between both sources of information (RMS of 5.11 cm/s for u component and 6.67 cm/s for ν) [1]. Additionally, a lagrangian buoy was released in the area, in order to analyze the benefit of employing HF radar currents for the tracking of drifting objects. The validation exercise with the drifting buoy was carried out inside the ESEOO project; the analysis was lead by University of Cantabria and Imedea balear, as part of their modeling tasks inside ESEOO, and the drifting buoy was released by SASEMAR, the Spanish Coastguard, as part of an ESEOO exercise [2]. A particle model was employed with and without the use of HF radar currents. Results of the experiment clearly show a positive impact of the use of measured current. When using HF data, the search and rescue areas are reduced, in average, in 49%. In this work, results from this experience will be analyzed in detail, making special focus in the scientific aspects of the comparison with the moored and drifting buoys.

Download Full-text