近十幾年來，全球航空運輸量不斷地成長，若飛航安全管理系統沒有重大的改進以應付日後龐大的交通流量，意外發生也很有可能會隨之增加。飛安事件的發生在統計機率的分析上是屬於稀有的事件，但是飛機失事對社會確會帶來極大的衝擊。 在航空運輸作業中如何管理風險與安全中是一個非常實際的問題，因此，在飛安風險管理上，必須作持續的改進，才能防避空難意外的發生。統計顯示接近70％以上的民航失事之導因為駕駛疏失(McFadden, 1993)，傳統的研究多著重在風險的概念性敘述和透過已發生的失事進行調查找出與人為疏失有關聯的因素。但較少研究是針對未來各種人為因素風險加以分析其長中短期趨勢，故航空公司和飛安監督單位難以研擬相關之防治措施。因此，本研究將建構一人為因素風險分析模式，期能預早發覺危機的發生，提供飛安監督單位或航空公司，作為決策與因應的參考，以提升飛安品質。 本研究利用比例危險模型（Proportional Hazards Model）與延伸型危險迴歸模型（Extended Hazard Regression Model）建構風險趨勢分析動態模型，從而建立各家航空公司針對各類事件的風險函數，並在考慮航空公司平日作業之飛安相關績效指標來評估與比較不同人為因素飛安事件在未來的風險值，若發覺某類人為因素事件可能發生風險機率過高狀況時，則可進行必要的措施或調整相關查核計劃來降低此類事件的發生風險，以達到風險管理的目的。 Risk and safety have always been of the first important issue in civil aviation, especially when the air transportation traffic volume grows rapidly and continuously. Although being a rare event in an absolute sense, aircraft accidents can have severe implications. A practical problem in air transport is how to manage risk and safety. In contrast to traditional reactive approach of casual analysis for finding linkage between human factors and history accidents, innovative proactive approach appears to be more essential for aviation risk management. Moreover, since the airlines’ operation performances actually reflect their safety ‘profile’ and overall safety quality, the relationship between human factors and safety performances should be considered while assessing the aviation risk. The objective of this research is to develop an analytic method that uses both accident and safety data to quantify the aviation risk which are caused by human error. Assessment of the risk of aircraft accidents may be carried out in different ways, from highly intuitive to very formal and analytical. The probability of an air accident is very low making it a difficult and complex task to proper explain, locate, and manage overall aviation safety. In this study we present a new methodology for assessment risk and safety in civil aviation. A specified proportional hazard model is investigated and demonstrated its applicability in aviation risk assessment. Our approach takes into account the more complex relationships among relevant aviation risk factors. The dependence of the aviation risk on airlines operational performance is also measured. Using the models presented, risk has been assessed as the probability of the occurrence of a specific type of human errors related aviation accident. So the potential human errors related risk is identified and monitored timely. The results can provide well references to the civil aviation communities to manage the aviation-safety risk, thus corrective action can be taken to reduce the happenings of aviation accidents.
