A novel time-delay multivariable grey model and its application in predicting oil production

An accurate prediction of oil production can provide a scientific basis for planning the production of the Qinghai oilfield and help in rationally arranging resources. To address the time-delay of related factors in the oil production system and how this problem affects oil production, this paper classifies the different degrees of timedelay of related factors and establishes a time-delay multivariable grey model with multiple parameters. This model not only reflects the characteristics of a Logistic model with strong historical recurrence ability and high prediction accuracy in the short and medium terms but also compensates for the defects of existing grey models that do not consider the time-delay of related factors; this is a new idea for grey modelling. Moreover, the parameter estimation of the new model is obtained via the least squares technique, the time response of the new model is obtained via a mathematical method, and the modelling steps of the new model are also obtained. Finally, the new model is applied to the prediction of production of the Qinghai oilfield in China, the effectiveness of the model is analysed according to two different correlation sequences, and six types of the same modelling objects are tested. Results of two types of twelve experiments each show that the total mean absolute percentage error is less than 5%, the lowest is 1.2580%, and the highest is only 4.0087%. This shows that the new model has a good effect and results of six technical indicators show that the new model is better than the other five multivariable grey models.