績效預測模式普遍應用於鋪面設計、評估、維修及路網管理各個方面。AASHTO2002手冊應用力學經驗方法改進了許多問題，但受到績效預測精確度的影響非常明顯。本研究利用美國長程鋪面績效資料庫(http://www.datapave.com)來探討與驗證現有柔性鋪面績效預測模式，由研究結果發現預測模式與資料庫之現地調查值有明顯差異，其模式預測結果是非常需要改進。因此，本研究嘗試利用上述之資料庫對於柔性鋪面之車轍及疲勞裂縫預測模式做進一步的改善。 針對反應變數進行探討分析時發現，由常態分配對於隨機誤差與連續變異情形，可能不適用傳統統計迴歸方法來構建預測模式。因此，本研究於後續分析時採用廣義線性模式(GLM)與廣義相加模式(GAM)對於反應變數的分佈情形均不給予任何假設，而是採用以概似估計法的方式測試分配適用度,其中以柏松分配之適用性較良好。並配合Box-Cox power transformation轉換法、視覺圖的技術，以及李英豪教授建議的系統化之統計與工程分析方法應用於構建預測模式中。 本研究將構建完成之預測模式檢定其適合度及針對相關的參數進行敏感度分析，最後建構之模式其適用情形與過去模式相比，有的到良好的改善。對目前建立之模式於未來亦可作更進一步之改進，使其更為完善。 Performance predictive models have been used in various pavement design, evaluation, rehabilitation, and network management activities. The improved 2002 AASHTO guide adopted mechanistic empirical pavement design approach which considerably depends upon the accuracy of pavement performance predictions. The prediction accuracy of existing flexible pavement performance prediction models was first investigated using the Long-Term Pavement Performance database (http://www.datapave.com or LTPP DataPave Online) and the results showed that it is greatly in need for improvement. Thus, this study strives to develop improved rutting and fatigue cracking prediction models for flexible pavements using the aforementioned database. Exploratory data analysis (EDA) of the response variables indicated that the normality assumption with random errors and constant variance using conventional regression techniques might not be appropriate for prediction modeling. Therefore, without assuming the error distribution of the response variable, generalized linear model (GLM) and general additive model (GAM) along with quasi-likelihood estimation method were Poisson distribution were adopted in the subsequent analysis. Box-Cox power transformation technique, visual graphical techniques, as well as the systematic statistical and engineering approach proposed by Lee were frequently adopted during the prediction modeling process. The goodness of the model fit was further examined through the significant testing and various sensitivity analyses of pertinent explanatory parameters. The tentatively proposed predictive models appeared to reasonably agree with the pavement performance data although their further enhancements are possible and recommended.
