本研究引用台灣石化企業自辦工程的實際完工案例做為研究分析之資料庫，但經初步整理仍有近 25% 比例的案件有展期紀錄，雖低其他學者研究 40% 之結論，但顯見目前的工期預估方式仍有所不足，能掌握的工期影響因子尚不足以反映真實狀況。故擬以實際完工資料庫為案例，仿估價方式以直接及間接屬性為因子，發展出可行工期預估經驗模式(Empirical Model)，供投資計劃階段審核設計單位提送之預估工期，以避免與實際所需的工期落差過大，造成後續設備採購、試車及運轉時程誤判，延誤新品上市時機甚而影響投資獲利。擬採用倒推演程序(Top-down approach)，重新依因子分類屬性面向架構研究主軸，以資料探勘方法之一的主成分分析法(PCA)重組案例中既有因子及衍生因子，以取得主成分(計分)因子(PCs)，再結合倒傳類神經網路(BPNN)建構PCA-BPNN組合預估模型。其結果經10組新案例驗證，其輸出預測的根均方誤差RMSE約在2.01~0.05，預估準確度可控制在12%，足可滿足實務作業需求；同時利用產出的因子權重的敏感度分析檢討，可作為加強管控依據，以增進施工效率達成專案目標。

This research collects completed construction projects of petrochemical industry in Taiwan as the database for analysis on construction project duration. With the initial compilation founding of nearly 25% of the projects have time extension records, though lower than the 40% found in other relative researches, the result shows that current scheduling factors cannot fully predict feasible construction project duration. The research employs projects from this database with valuation approach, by using direct and indirect factors to develop a predictable construction scheduling pattern, which can provide effective information for reviewing the feasible construction scheduling of new investments, and to help avoid project delays which may affect investment profits. A Top-down approach is used throughout the research for factor analysis; using Principle Component Analysis (PCA) method of data mining in restructuring factors and derived factors from the projects, in order to obtain Principal Components scores (PCs) which are then combined with Back Propagation Neural Network (BPNN) to produce a duration prediction mechanism, becoming a process of project period prediction called PCA-BPNN model. The results are then verified by 10 new projects, with outcomes showing root mean squared errors (RMSE) from 0.05 to 2.01, fulfilling demands in practice by predicting a feasible construction period and enhance project management.

Young, C. W. ,“An Empirical Equation for Predicting Penetration Depth into Soft Sediments”, OCEANS 81 Conference, pp.674 – 677(1981).
Calvel, P.; Barillot, C.; Lamothe, P.; Ecoffet, R.,” An empirical model for predicting proton induced upset”, Nuclear Science, IEEE Transactions, Vol.43, Issue 6, pp.2827 - 2832 (1996).
Axiotis, D.I.; Theologou, M.E.,” An empirical model for predicting building penetration loss at 2 GHz for high elevation angles”, Antennas and Wireless Propagation Letters, IEEE,Vol.2 ,Issue: 1,pp.234 – 237(2003).
Chen Pang; Xiaofen Ji.,” An Empirical Study on Predicting User Purchase Intention on the Creative Product: A Case of Apparel”, Electronic Commerce and Security, 2008 International Symposium Conference, pp.608–611..
Copper, J.; Baciu, A.; Price, D.,” Predicting Wind Farm Electricity Output: A Neural Network Empirical Modeling Approach”, Power and Energy Engineering 2009 Conference, Asia-Pacific, pp.1-5.
Cai Jihua; Eng. Fac.; Liu Hao; Gu Su.,” Empirical Correlation to Predict Viscosity Breaking Ratio of Guar-Based Biodegradable Drilling Fluid”, Information Engineering and Computer Science (ICIECS), pp. 1-4 (2010).
Jiacheng Zhao; Xiaobing Feng; Huimin Cui; Youliang Yan, ” An empirical model for predicting cross-core performance interference on multicore processors”, Parallel Architectures and Compilation Techniques (PACT), 2013 22nd International Conference, pp. 201 - 212.
Taruna, S.; Comput. Sci.; Pandey, M. ,” An empirical analysis of classification techniques for predicting academic performance”, Advance Computing Conference (IACC), 2014 IEEE International Conference, pp.523 – 528.
Lin, Wei,” A feasible method to predict thin package actual warpage based on an FEM model integrated with empirical data”, Electronic Components and Technology 2015 Conference (ECTC),pp. 1985 – 1990.
統雄-統計 因素分析篇；http://tx.liberal.ntu.edu.tw/wu-tx/Jx/Methodology/Analy-TxStatisticsCanon-Factor.htm
Roohollah Noori,” Evaluation of PCA and Gamma test techniques on ANN operation for weekly solid waste prediction”, Journal of Environmental Management,Vol. 91,pp. 767–771 (2010).
Liming Xia; Chunxue Zhao., ” The application of PCA - Fuzzy probability analysis on risk evaluation of construction schedule of highway”, Logistics Systems and Intelligent Management, 2010 International Conference on, Vol. 2, pp. 1230-1233.
Honda, K. ; Nonoguchi, R.; Notsu, A.; Ichihashi, H.,” PCA-guided k-Means clustering with incomplete data”, IEEE 2011 International Conference, pp.1710-1713.
Yata, K., Aoshima, M.,” Effective PCA for high-dimension, low-sample-size data with noise reduction via geometric representations”, Journal of Multivariate Analysis, Vol.105, Issue 1, pp. 193-215 (2012).
Niu B. ,” Construction of low-carbon city evaluation system using PCA and AHP”, WIT Transactions on Information and Communication Technologies, Vol. 46, pp. 2629-2634 (2014).
Ehsan Amiriana; Juliana Y. Leunga; Stefan Zanonb; Peter Dzurman,” Integrated cluster analysis and artificial neural network modeling for steam-assisted gravity drainage performance prediction in heterogeneous reservoirs” ,Expert Systems with Applications, Vol. 42, Issue 2, pp. 723–740 (2015).
Hojjat Adeli, ”Neural networks in civil engineering: 1989~2000” Computer-Aided Civil and Infrastructure Engineering Vol.16, pp.126–142 (2001).
楊人霈，「類神經網路與調適性類神經模糊推論系統從事鋼筋混凝土梁最佳化設計之比較」，碩士論文，義守大學土木與生態工程學系，高雄(2011).
王又萱，「運用倒傳遞類神經網路於鑽孔表面粗糙度即時預測系統」，碩士論文，中原大學工業與系統工程研究所，桃園(2012).
桂宇賢，「倒傳遞及徑向基底函數類神經網路於流速剖面推估之應用」，碩士論文，中興大學土木工程學系所，台中(2013).
蘇裕翔，「結合類神經網路與遺傳演算法評估地震尖峰地表加速度之研究」，碩士論文，屏東科技大學土木工程系所，屏東(2013).
鍾翔宇，「整合類神經網路和田口方法建構不動產估價模式-以台中市房地產交易為例」，碩士論文，國立臺中科技大學資訊管理系碩士班，台中(2013).
林俊雄，「應用類神經網路預測新建RC建築物大宗用料之研究」，碩士論文，華梵大學工程與經營資訊學系碩士班，新北市(2014).
高偉格，「台灣校舍耐震評估與補強資料庫之資料探勘」，博士論文，國立臺灣科技大學營建工程系，台北(2014).
Shafabakhsh, G. H.,Ani, O.J., Talebsafa, M,” Artificial neural network modeling (ANN) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates”, Construction and Building Materials, Vol. 85,pp.136-143 (2015).
Nourani, V. ,Alami, M.T. ,Vousoughi, F.D.,” Wavelet-entropy data pre-processing approach for ANN-based groundwater level modeling”, Journal of Hydrology,Vol.524, pp. 255-269 (2015).
Kourgialas, N.N. ,Dokou, Z., Karatzas, G.P.,” Statistical analysis and ANN modeling for predicting hydrological extremes under climate change scenarios: The example of a small Mediterranean agro-watershed”, Journal of Environmental Management,Vol.154, , pp. 86-101 (2015).
Mesut Remzia,Theodore Anagnostoub,” An artificial neural network to predict the outcome of repeat prostate biopsies”, Urology, Vol. 62,Issue 3,September, pp. 456–460 (2003).
Lu, WZ; Wang,” Potential assessment of a neural network model with PCA/RBF approach for forecasting pollutant trends in Mong Kok urban air, Hong Kong”, Environmental Research,Vol. 96,Issue 1, pp. 79–87 (2004).
Buciński,A.,Baczek,T.,Krysiński,J.,Szoszkiewicz, R.,Załuski, J. ,”Clinical data analysis using artificial neural networks (ANN) and principal component analysis (PCA) of patients with breast cancer after mastectomy”, Reports of Practical Oncology & Radiotherapy,Vol.12, Issue 1,pp. 9–17 (2007).
Omid, M.,Mahmoudi, A.,Omid, M.H.,” Development of pistachio sorting system using principal component analysis (PCA) assisted artificial neural network (ANN) of impact acoustics”, Expert Systems with Applications,Vol. 37, pp. 7205-7212 (2010).
Yande Liu,Xudong Sun,Aiguo Ouyang,” Nondestructive measurement of soluble solid content of navel orange fruit by visible–NIR spectrometric technique with PLSR and PCA-BPNN”, LWT - Food Science and Technology,Vol. 43, Issue 4, pp. 602–607 (2010).
Noori, R.,Karbassi, A.R.,Moghaddamnia, A.,Han, D.,Zokaei-Ashtiani, M.H., Farokhnia, A.,” Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction ”, Journal of Hydrology,Vol.401, Issue 3-4, pp. 177-189 (2011).
曾智鴻，「類神經網路模式用於推估邊坡破壞面積之研究」，碩士論文，屏東科技大學土木工程系所，屏東(2013).
Hong Zhanga, Fei Yanga, Yang Lia, Heng Li., ”Predicting profitability of listed construction companies based on principal component analysis and support vector machine—Evidence from China”, Automation in Construction, Vol.53,pp. 22–28 (2015).
簡崑棋，「結合模糊類神經網路與快速混雜基因演算法於專案工期之預測」，碩士論文，成功大學土木工程學系碩博士班，台南(2003).
F. Khosrowshahi and A. P. Kakat“Estimation of project total cost and duration for housing projects in the U.K.” Building and Enviroment, Vol. 31, No. 4, pp. 373-383 (1996).
馬龍堯，「自來水輸水管抽換工程之研究-- 明挖與現場固化內襯工法之進度比較」，碩士論文，國立台灣大學土木工程學研究所，台北(2002).
劉萬正，「以DELPHI法探討合理工期之研究 以大型鐵路工程為例」，碩士論文，國立交通大學土木工程學系所，新竹(2002).
林清吉，「卵礫石層長隧道施工進度與生產力分析」，碩士論文，逢甲大學土木工程學系，台中(2005).
Vahida Žujo and Diana Car- r-Pušić,”Modeling of risk factor influence on construction time overrun by applying multivariant regression analysis”, CIB Joint International Symposium -Construction Facing Worldwide Challenges, pp. 148-157 (2009).
R.NooriA.R.KarbassiA.MoghaddamniaD.HanM.H.Zokaei-AshtianiA.FarokhniaM. GhafariGousheh, “Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction”, Journal of Hydrology, Vol. 401, No. 3-4, pp. 177-189 (2011).
Long Le-Hoai,Young Dai Lee,and Anh Tuan Nguyen ‘Estimating time performance for building construction project in Vietnam”,Jounal of Civil Engineering Vol.17(1), pp.1-8 (2013).
F. J. Bromilow,”Contract time performance: expectations and reality”Building Forum Vol.1, pp.70 (1969).
陳世晃，「Principal Component Analysis」研究數據分析-6教學講義投影片資料，逢甲大學運輸科技與管理學系教授。
陳順宇著呂金河譯，「第六章 主成份分析(Principal Component Analysis)多變量分析」網路教學講義資料，國立成功大學統計系教授兼系主任。.