{"title":"利用多元线性回归预测伊拉克石油项目绩效指标","authors":"Nadal Adnan Jasim, A. Ibrahim, W. A. Hatem","doi":"10.25130/tjes.30.2.10","DOIUrl":null,"url":null,"abstract":"Many oil and gas projects have been subjected to significant cost overruns and schedule delays, which is a major concern for the decision-makers in the oil industry. This paper aims to develop three mathematical models to estimate earned value indicators, the Schedule Performance Index (SPI), Cost Performance Index (CPI), and To-Complete Cost Performance Indicator (TCPI), to reduce the cost and time estimation error in Iraqi oil projects. The research methodology adopted artificial intelligence techniques using Multiple Linear Regression technology (MLR) to predict Earned Value (EV) Indexes to get standard local equations to measure the performance of Iraqi oil projects. The data is based on (83) monthly reports from 26 June 2015 to 25 August 2022 collected from the Karbala Refinery Project, selected as a case study. It is one of the Oil Projects Company (SCOP)- the Iraqi Ministry of Oil’s massive and modern projects, and it combines several projects into one project. The results showed numerous significant points, such as the average accuracy (AA%) for the CPI, SPI, and TCPI was 95.194%, 92.195%, and 83.706%, respectively, while the correlation coefficients (R) were 92.4%, 98.4%, and 93.7%. It was shown that there were relatively few differences between the theoretical and actual results. Therefore, the MLR technique was utilized in this paper to derive the prediction models for its more correct earned value predictions.","PeriodicalId":30589,"journal":{"name":"Tikrit Journal of Engineering Sciences","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Forecasting the Performance Measurement for Iraqi Oil Projects using Multiple Linear Regression\",\"authors\":\"Nadal Adnan Jasim, A. Ibrahim, W. A. Hatem\",\"doi\":\"10.25130/tjes.30.2.10\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Many oil and gas projects have been subjected to significant cost overruns and schedule delays, which is a major concern for the decision-makers in the oil industry. This paper aims to develop three mathematical models to estimate earned value indicators, the Schedule Performance Index (SPI), Cost Performance Index (CPI), and To-Complete Cost Performance Indicator (TCPI), to reduce the cost and time estimation error in Iraqi oil projects. The research methodology adopted artificial intelligence techniques using Multiple Linear Regression technology (MLR) to predict Earned Value (EV) Indexes to get standard local equations to measure the performance of Iraqi oil projects. The data is based on (83) monthly reports from 26 June 2015 to 25 August 2022 collected from the Karbala Refinery Project, selected as a case study. It is one of the Oil Projects Company (SCOP)- the Iraqi Ministry of Oil’s massive and modern projects, and it combines several projects into one project. The results showed numerous significant points, such as the average accuracy (AA%) for the CPI, SPI, and TCPI was 95.194%, 92.195%, and 83.706%, respectively, while the correlation coefficients (R) were 92.4%, 98.4%, and 93.7%. It was shown that there were relatively few differences between the theoretical and actual results. Therefore, the MLR technique was utilized in this paper to derive the prediction models for its more correct earned value predictions.\",\"PeriodicalId\":30589,\"journal\":{\"name\":\"Tikrit Journal of Engineering Sciences\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tikrit Journal of Engineering Sciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.25130/tjes.30.2.10\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Environmental Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tikrit Journal of Engineering Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.25130/tjes.30.2.10","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Environmental Science","Score":null,"Total":0}
Forecasting the Performance Measurement for Iraqi Oil Projects using Multiple Linear Regression
Many oil and gas projects have been subjected to significant cost overruns and schedule delays, which is a major concern for the decision-makers in the oil industry. This paper aims to develop three mathematical models to estimate earned value indicators, the Schedule Performance Index (SPI), Cost Performance Index (CPI), and To-Complete Cost Performance Indicator (TCPI), to reduce the cost and time estimation error in Iraqi oil projects. The research methodology adopted artificial intelligence techniques using Multiple Linear Regression technology (MLR) to predict Earned Value (EV) Indexes to get standard local equations to measure the performance of Iraqi oil projects. The data is based on (83) monthly reports from 26 June 2015 to 25 August 2022 collected from the Karbala Refinery Project, selected as a case study. It is one of the Oil Projects Company (SCOP)- the Iraqi Ministry of Oil’s massive and modern projects, and it combines several projects into one project. The results showed numerous significant points, such as the average accuracy (AA%) for the CPI, SPI, and TCPI was 95.194%, 92.195%, and 83.706%, respectively, while the correlation coefficients (R) were 92.4%, 98.4%, and 93.7%. It was shown that there were relatively few differences between the theoretical and actual results. Therefore, the MLR technique was utilized in this paper to derive the prediction models for its more correct earned value predictions.