發(fā)布時間：2018-07-24 13:58

【摘要】：我國高速公路近年來的交通安全形勢有所改善,但群死群傷事件仍時有發(fā)生,交通安全問題依然突出。為加強高速公路交通安全管理,可通過事故預(yù)測進行事故發(fā)生原因分析,從而預(yù)判事故發(fā)生規(guī)律并制定針對性措施,降低事故率及事故發(fā)生嚴(yán)重程度。因此本文基于事故數(shù)據(jù)統(tǒng)計分析及神經(jīng)網(wǎng)絡(luò)技術(shù)開展高速公路事故預(yù)測研究�；谑鹿蕯�(shù)據(jù)的統(tǒng)計分布特性及神經(jīng)網(wǎng)絡(luò)技術(shù),本文對高速公路事故預(yù)測展開研究,給出了各條高速公路的統(tǒng)計分布特性并基于此提出了基于負(fù)二項回歸分析的變量選擇方法,分別構(gòu)建了山嶺重丘區(qū)、平原微丘區(qū)高速公路神經(jīng)網(wǎng)絡(luò)事故預(yù)測模型,提出了基于敏感性分析的網(wǎng)絡(luò)模型驗證方法,最終通過模型的應(yīng)用驗證了模型的可靠性與可移植性。由于高速公路地形條件主要分為平原微丘區(qū)和山嶺重丘區(qū)兩類,且這兩類地形條件下的高速公路設(shè)計標(biāo)準(zhǔn)存在差異,其事故影響因素也有所不同,因此本文考慮了高速公路地形條件,分別對山嶺重丘區(qū)及平原微丘區(qū)事故預(yù)測模型的構(gòu)建進行研究。首先,選擇了遼寧省及廣東省的9條高速公路作為本文的研究對象,并對其事故數(shù)據(jù)及其關(guān)聯(lián)數(shù)據(jù)進行處理與組織,根據(jù)公路幾何線形按同質(zhì)法將高速公路劃分成滿足研究需求的事故預(yù)測單元,據(jù)此構(gòu)建包含事故數(shù)據(jù)及其關(guān)聯(lián)數(shù)據(jù)的山嶺重丘區(qū)、平原微丘區(qū)高速公路交通事故基礎(chǔ)數(shù)據(jù)系統(tǒng)。其次,分別對各條高速公路進行事故數(shù)據(jù)統(tǒng)計分布特性研究,研究結(jié)果表明基于幾何線形劃分的高速公路事故預(yù)測單元事故數(shù)主要服從負(fù)二項分布。據(jù)此,選擇根據(jù)負(fù)二項分布進行事故影響因素的分析及變量選擇工作。分別分析山嶺重丘區(qū)及平原微丘區(qū)高速公路各影響因素與預(yù)測單元事故數(shù)之間的統(tǒng)計關(guān)系,確定理想線形標(biāo)準(zhǔn),根據(jù)理想線形標(biāo)準(zhǔn)提出預(yù)測單元指標(biāo)空值項的合理賦值方法,從而使其滿足變量選擇算法要求,最后基于負(fù)二項回歸分別完成了山嶺重丘區(qū)、平原微丘區(qū)預(yù)測模型自變量的選擇。然后,根據(jù)所研究問題特性,采用Elman神經(jīng)網(wǎng)絡(luò)標(biāo)定山嶺重丘區(qū)及平原微丘區(qū)高速公路神經(jīng)網(wǎng)絡(luò)事故預(yù)測模型,分別進行模型的訓(xùn)練與測試,由測試結(jié)果可知,這兩類地形條件下預(yù)測模型網(wǎng)絡(luò)的泛化能力均較強。通過已標(biāo)定完成的事故預(yù)測模型分析各輸入變量的靈敏度,從而確定各變量與預(yù)測單元事故數(shù)的內(nèi)在規(guī)律,從交通安全機理角度驗證了這兩類模型均具有正確性與有效性。最終,分別對山嶺重丘區(qū)、平原微丘區(qū)事故預(yù)測模型進行應(yīng)用分析,應(yīng)用平均相對誤差分別為8.705%和6.651%。應(yīng)用結(jié)果表明這兩類地形條件下的事故預(yù)測模均型具有一定的有效性和較大的可移植性。
[Abstract]:The traffic safety situation of expressway in China has improved in recent years, but the mass death and injury incidents still occur from time to time, and the traffic safety problems are still prominent. In order to strengthen the management of expressway traffic safety, the cause analysis of accidents can be carried out through accident prediction, so as to predict the occurrence rules of accidents and formulate targeted measures to reduce the accident rate and the severity of accidents. Therefore, this paper based on statistical analysis of accident data and neural network technology to carry out highway accident prediction research. Based on the statistical distribution characteristics of accident data and neural network technology, this paper studies the prediction of expressway accidents, presents the statistical distribution characteristics of each expressway, and puts forward a variable selection method based on negative binomial regression analysis. The neural network accident prediction model of expressway in mountain and hill area and plain micro-hill area is constructed, and the method of network model verification based on sensitivity analysis is put forward. Finally, the reliability and portability of the model are verified by the application of the model. Because the topographic conditions of expressway are mainly divided into two types: plain micro-hill area and mountain heavy hill area, and the design standards of expressway under these two kinds of terrain conditions are different, the influencing factors of the accidents are also different. Therefore, considering the topographic condition of expressway, this paper studies the construction of accident prediction model in mountainous area and plain area. First of all, 9 highways in Liaoning Province and Guangdong Province are selected as the research object of this paper, and the accident data and their associated data are processed and organized. According to the homogeneity method of highway geometry, the expressway is divided into accident prediction units to meet the needs of research. Based on this, the basic data system of expressway traffic accidents in mountain heavy hill area and plain micro-hill area is constructed, which includes accident data and its correlation data. Secondly, the statistical distribution characteristics of each expressway accident data are studied respectively. The results show that the number of accidents in the expressway accident prediction unit based on geometric line partition mainly depends on the negative binomial distribution. According to this, the analysis of the influencing factors and the selection of variables are carried out according to the negative binomial distribution. The statistical relationship between the influence factors of expressway and the number of accidents of prediction unit in mountain heavy hill area and plain micro-hill area is analyzed, and the ideal linear standard is determined. According to the ideal line shape standard, the reasonable assignment method of empty value term of prediction unit index is put forward. Finally, based on the negative binomial regression, the selection of independent variables in the prediction model of mountain heavy hill region and plain micro-hill area is completed. Then, according to the characteristics of the studied problem, the neural network accident prediction model of expressway in mountain heavy hill area and plain micro-hill area is calibrated by using Elman neural network, and the model is trained and tested respectively. The generalization ability of the predictive model network is strong under these two kinds of terrain conditions. The sensitivity of each input variable is analyzed by the calibrated accident prediction model, and the inherent law of each variable and the number of accidents in the prediction unit is determined. The correctness and validity of the two models are verified from the view of traffic safety mechanism. Finally, the accident prediction models of mountain heavy hill area and plain micro-hill area are analyzed, and the average relative error is 8.705% and 6.651respectively. The application results show that the average pattern of accident prediction under these two kinds of terrain conditions is effective and transplantable to some extent.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：U491.3

【參考文獻】

相關(guān)期刊論文 前10條

1 孟祥海;覃薇;鄧曉慶;;基于神經(jīng)網(wǎng)絡(luò)的山嶺重丘區(qū)高速公路事故預(yù)測模型[J];公路交通科技;2016年03期

2 黃合來;許鵬鵬;馬明;ABDEL-ATY M;;道路交通安全規(guī)劃理論研究前沿[J];中國公路學(xué)報;2014年09期

3 孟祥海;侯芹忠;史永義;;基于線形指標(biāo)的山嶺重丘區(qū)高速公路事故預(yù)測模型[J];公路交通科技;2014年08期

4 姚磊;;基于RST的事故黑點成因?qū)嵗治鯷J];交通運輸工程與信息學(xué)報;2014年01期

5 王雪松;宋洋;黃合來;張丹云;;基于分層負(fù)二項模型的城郊公路安全影響因素研究[J];中國公路學(xué)報;2014年01期

6 胡啟洲;高寧波;葉茂;;基于支持向量機的道路交通事故數(shù)據(jù)統(tǒng)計模型研究[J];中國安全科學(xué)學(xué)報;2013年06期

7 孟祥海;張曉明;鄭來;;基于線形與交通狀態(tài)的山區(qū)高速公路追尾事故預(yù)測[J];中國公路學(xué)報;2012年04期

8 張鐵軍;唐t$t$;康云霞;;基于負(fù)二項預(yù)測模型的山區(qū)雙車道公路穿村鎮(zhèn)路段的安全特性[J];公路交通科技;2012年06期

9 馬壯林;邵春福;胡大偉;馬社強;;高速公路交通事故起數(shù)時空分析模型[J];交通運輸工程學(xué)報;2012年02期

10 趙金寶;鄧衛(wèi);王建;;基于貝葉斯網(wǎng)絡(luò)的城市道路交通事故分析[J];東南大學(xué)學(xué)報(自然科學(xué)版);2011年06期

相關(guān)博士學(xué)位論文 前1條

1 趙玲;基于馬爾可夫鏈的道路交通事故預(yù)測研究及應(yīng)用[D];長安大學(xué);2013年

相關(guān)碩士學(xué)位論文 前2條

1 張宏璐;高速公路交通事故起數(shù)預(yù)測方法研究[D];長安大學(xué);2015年

2 劉海珠;道路交通事故嚴(yán)重程度影響因素分析及預(yù)測模型建立[D];吉林大學(xué);2014年

，

本文編號：2141596