Browsing by Author "Ma, Lin"

Now showing 1 - 8 of 8

A Machine Learning Approach for Solar Power Technology Review and Patent Evolution Analysis
(2019-04-01)
Trappey, Amy J. C.
;
Chen, Paul P. J.
;
Trappey, Charles, V
;
Ma, Lin
;
管理科學系
Solar power systems and their related technologies have developed into a globally utilized green energy source. Given the relatively high installation costs, low conversion rates and battery capacity issues, solar energy is still not a widely applied energy source when compared to traditional energy sources. Despite the challenges, there are many innovative studies of new materials and new methods for improving solar energy transformation efficiency to improve the competitiveness of solar energy in the marketplace. This research searches for promising solar power technologies by text mining 2280 global patents and 5610 literature papers of the past decade (January 2008 to June 2018). First, a solar power knowledge ontology schema (or a key term relationship map) is constructed from the comprehensive literature and patent review. Non-supervised machine learning techniques for clustering patents and literature combined with the Latent Dirichlet Allocation (LDA) topic modeling algorithm identify sub-technology clusters and their main topics. A word-embedding algorithm is applied to identify the patent documents of the specified technologies. Cross-validation of the results is used to model the technology progress with a patent evolution map. Initial analysis show that many patents focus on solar hydropower storage systems, transferring light generated power to waterpower gravity systems. Batteries are also used but have several limitations. The objectives of this research are to review solar technology development progress and describe the innovation path that has evolved for the solar power domain. By adopting unsupervised learning approaches for literature and patent mining, this research develops a novel technology e-discovery methodology and presents the detailed reviews and analyses of the solar power technology using the proposed e-discovery workflow. The insights of global solar technology development, based on both comprehensive literature and patent reviews and cross-analyses, helps energy companies select advanced technologies related to their key technical R&D strengths and business interests. The structured solar-related technology mining can be extended to the analysis of other forms of renewable energy development.
An Intelligent Transformer Maintenance System with Real-time Life Assessment Condition Monitoring
(2013-12-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Sun, Yong
;
Ma, Lin
;
Chen, Leo Kuan Ju
Transformers are critical assets that require continuous monitoring in the generation of electrical power. The management of engineering assets requires real-time diagnosis and preventive maintenance in order to avoid unexpected and catastrophic equipment shut-downs. In addition, the health status and remaining life of the transformer are critical knowledge for proper maintenance and management. This research focuses on oil-immersed transformers as a case study to help managers compile real-time monitoring and sampling data for information systems. The deterioration of the transformation's insulating paper was measured to derive the transformer's remaining life and to project the optimal replacement time. The proposed prediction method uses the Group Method of Data Handling (GMDH) to estimate the remaining life of any given transformer in use. This algorithm uses the dissolved gas-in-oil and furfural formation as the input variables to form the transformer life assessment model. Finally, the derived model is compared to models proposed by the International Electrotechnical Commission (IEC). The results show improved performance over the currently used IEC models.
Data driven modeling for power transformer lifespan evaluation
(2014-03-01)
Trappey, Charles V.
;
Trappey, Amy J. C.
;
Ma, Lin
;
Tsao, Wan-Ting
;
管理科學系
Large sized power transformers are important parts of the power supply chain. These very critical networks of engineering assets are an essential base of a nation's energy resource infrastructure. This research identifies the key factors influencing transformer normal operating conditions and predicts the asset management lifespan. Engineering asset research has developed few lifespan forecasting methods combining real-time monitoring solutions for transformer maintenance and replacement. Utilizing the rich data source from a remote terminal unit (RTU) system for sensor-data driven analysis, this research develops an innovative real-time lifespan forecasting approach applying logistic regression based on the Weibull distribution. The methodology and the implementation prototype are verified using a data series from 161 kV transformers to evaluate the efficiency and accuracy for energy sector applications. The asset stakeholders and suppliers significantly benefit from the real-time power transformer lifespan evaluation for maintenance and replacement decision support.
Incorporating Data Warehouse Technology into Asset Information Management Systems for Large Assets
(2016)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Ma, Lin
;
Chang, Acer C. C.
;
管理科學系
Large sized engineering assets such as power transformers are critical parts of the power supply networks. Therefore, focusing on early fault diagnosis to maintain large transformers in good condition is an important operational task to the power companies. In order to manage and fully utilize the big data generated from the large number of transformers, this paper incorporates data warehouse technology to a fault diagnosis system for the entire transformer fleet. The research includes two major parts. First, a data warehouse (DW) is designed for the large assets information management. Then, the DW-based intelligent fault diagnosis system is developed and implemented. The DW stores the complete transformers\' data and then different data cubes are defined according to various applications. The fault diagnosis system for power transformers consists of the condition monitoring module, failure diagnosis module, and intelligent decision supports module. The research methodology and prototype system are verified with real data from a series of 161 kV transformers in operations.
Integrating Real-Time Monitoring and Asset Health Prediction for Power Transformer Intelligent Maintenance and Decision Support
(2015-01-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Ma, Lin
;
Chang, Jimmy C. M.
;
管理科學系
Large sized transformers are an important part of global power systems and industrial infrastructures. An unexpected failure of a power transformer can cause severe production damage and significant loss throughput the power grid. In order to prevent power facilities from malfunctions and breakdowns, the development of real-time monitoring and health prediction tools are of great interests to both researchers and practitioners. An advanced monitoring tool performs real-time monitoring of key parameters to detect signals of potential failure through data mining techniques and prediction models. Asset managers use the result to develop a suitable maintenance and repair strategy for failure prevention. Principal component analysis (PCA) and back-propagation artificial neural network (BP-ANN) are the algorithms adopted in the research. This chapter utilizes industrial power transformers\' historical data from Taiwan and Australia to train and test the failure prediction models and to verify the proposed methodology. First, PCA detects the conditions of transformers by identifying the state of dissolved gasses. Then, the BP-ANN health prediction model is trained using the key factor values. The integrated engineering asset management database includes nine gases in oil as input factors (N-2, O-2, CO2, CO, H-2, CH4, C2H4, C2H6, and C2H2). After applying the principal components algorithm, the research identifies five factors from the Taiwan operational transformer data and six factors from the Australia data. The integrated PCA and BP-ANN fault diagnosis system yields effective and accurate predictions when tested using Taiwan and Australia data. The accuracy rates are much higher (i.e., 92 and 96 % respectively) when compared to previous result of 69 and 75 %. This research is benchmarked against the DGA heuristic approaches including IEEE\'s Doernenburg and Rogers and IEC\'s Duval Triangle for the experimental fault diagnoses.
Intelligent engineering asset management system for power transformer maintenance decision supports under various operating conditions
(2015-06-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Ma, Lin
;
Chang, Jimmy C. M.
;
管理科學系
Large sized transformers are an important part of global power systems and industrial infrastructures. An unexpected failure of a power transformer can cause severe production damage and significant loss throughput the power grid. In order to prevent power facilities from malfunctions and breakdowns, the development of real-time monitoring and fault prediction tools are of great interests to both researches and practitioners. This research develops an intelligent engineering asset nianagement system for power transformer maintenance. The system performs real-time monitoring of key parameters and uses data mining and fault prediction models to detect transformers\' potential failure under various operating conditions. Principal component analysis (PCA) and a back-propagation artificial neural network (BP-ANN) are the algorithms adopted for the prediction model. Historical industrial power transformer data from Taiwan and Australia are used to train and test the failure prediction models and to verify the proposed general methodology as comparative case studies. The PCA algorithm reduces the number of the primary dissolved gasses as the key factor values for BP-ANN prediction modeling inputs. The system yields effective predictions when verified using various operating condition data from Australia and Taiwan power companies. The accuracy rates are much higher when compared to the fault prediction results without using PCA. The intelligent system combining PCA and BP-ANN algorithms, developed in this research, can be adopted by asset managers in different regions to develop suitable maintenance and repair strategies for transformer failure preventions., (C) 2015 Published by Elsevier Ltd.
RE-ENGINEERING TRANSFORMER MAINTENANCE PROCESSES TO IMPROVE CUSTOMIZED SERVICE DELIVERY
(2011-09-01)
Trappey, Amy J. C.
;
Sun, Yong
;
Trappey, Charles V.
;
Ma, Lin
;
管理科學系
The outage of a transformer in a power generation system will generally result in a shutdown of the entire system. Consequentially, large amounts of revenue are lost to the plant owner with a substantial negative impact on the civil community and industrial customers. This paper analyzes the current maintenance practices (i.e., an as-is process model) of a transformer manufacturing company, which provides maintenance services to power generation plants and reports the major weaknesses in current business practices. The maintenance weaknesses include isolated processes and paper based information communication. These inefficient processes result in service delays, cost increases, and inappropriate responses to customers' specific requests and complaints. To improve the efficiency and flexibility of the entire transformer maintenance service system, an e-integration approach is implemented with three key tasks. First, the current business processes are re-engineered to provide an improved (to-be) business model. Then, we replace paper based documentation methods with an electronic filing system for efficient and cost-effective information exchange. Afterward, the improved process model is implemented as an Internet based system to enhance the interactions among the transformer manufacturer, end-users, and service contractors for customized maintenance services. The case study demonstrates that implementing the e-integration approach increases the efficiency and effectiveness of the customized maintenance services.
Sales Service Improvement for an Industrial Transformer Manufacturer
(2010-01-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Lin, Yi-Liang
;
Kuo, Yi-Kai
;
Chang, Yu-Sheng
This paper defines and integrates after-sales service processes for an industrial manufacturer of power transformers. High priced and highly customized electricity transformers are sold to power generating companies that hold high service expectations througout the product life cycle. The e-integration of business processes for prior sales, ongoing sales, and after sales services are critically important for the transformer manufactuer to overcome well know problems with traditional paper based systems. This research analyses the business processes for transformer sales services and then integrates the best practices into a sales service platform. The study studies the current practices (as-is models) of customer services offered by the company. After identifying problems such as service delays, cost inefficiencies, and inappropriate responses to customers requests and complaints, the improved (to-be) process models are built, analyzed, and structured using the enterprise systems tool INCOME4. The Internet based system incorporating the to-be service processes is implemented to improve customer response as well as enhance the efficiency and effectiveness of after sales services.