Search

Geological disaster rescue presents features such as multi-stage, multi-sector, multi-subject, and multi-target. However, due to the shortage of professional rescue technicians, it is necessary to consider the matching, fairness, and efficiency of rescue tasks and rescue subjects. This study takes "disaster scenario-rescue task-rescue subject-demand prediction-subject deployment" as the main line in major geological disasters such as landslides and mudslides. By collecting data on 87 rescue operations in China from 2004 to 2019, we screened 18 representative cases of rescue operations and sorted out different types of rescue force function positioning, divisions of responsibility, and collaboration modes, summarizing them into five major rescue tasks and five major rescue subjects. A rescue subject demand prediction model was developed based on different scenarios according to the influence of rescue tasks on the demand of rescue subjects. Considering the urgency of the rescue tasks, a rescue subject deployment model based on different tasks and the NSGA-II algorithm can be built up. We tested the Zhejiang Yongjia weir breach rescue operation case (2019) in China for empirical analysis to verify the effectiveness and practicality of the model and algorithm.

Throughout the digitization of the petrochemical industry, the Beidou technology-based disaster monitoring, evaluation, and early warning network system has supported emergency decision making for oil and gas accidents. Many problems arise throughout the emergency decision-making process during oil–gas accidents, such as the limited time for decision making, high complexity, and inadequate emergency plans. Targeting these issues, we propose the construction of a case library using a Bayesian network. This way, when a new accident occurs, its similarity and deviation indexes could be matched against those of historical cases registered in the database. As such, the candidate cases are adjusted using a case combination and pruning method, yielding the final qualified case model. A case verification of the “11.22” Sinopec Oil pipeline leak and explosion in Qingdao reveals that the proposed method only requires an oil and gas accident database to be built in advance, eliminating the need for sampling data to make decisions, and reducing the search space. Using the proposed case-based reasoning, historical data and experience regarding oil and gas emergency decisions can be activated and reused, which would greatly improve the modeling efficiency of the Bayesian network.

Measures programming is an important way for improving the effect of measures of oil fields. Based on the theory of fuzzy chance-constrained goal programming, a fuzzy chance-constrained goal programming model is put forward for measures programming of Oilfield, which uses the increasing production and cost as objectives. The process of its hybrid intelligent algorithm including fuzzy simulation, genetic algorithm and neural network is provided, and the sensitivity analysis on uncertain factors to determine the influence on the optimal result can also be carried on. Finally, an example is given to illustrate the validity of the model and approach.

Enterprise performance evaluation is an important means of enterprise management, which can diagnose the whole development status of enterprise. Data envelopment analysis (DEA) is one of the most frequently used evaluation methods and support vector machine (SVM) is a novel method of data mining, which can be used for prediction and regression. Based on DEA and SVM, the paper proposes a method for evaluating and predicting enterprise performance. First, DEA method is used to evaluate DEA efficiency of all the oil refining enterprises performance. Then the input/output data and results of some decision making units (DMUs) are selected as the learning examples to train the SVM network and the others are used as the test examples to test the network. If the SVM network is testified well, a synthetic evaluation formula can be given to predict the DEA efficiency of a new DMU. A real example testifies the efficiency, practicability and intellectual ability of this method.

Measures programming is an important way for improving the effect of measures of oil fields, which can extend the stable production age limit of oil fields, reduce the mining difficulty and improve oil-producing speed and final recovery ratio. Based on the theory of stochastic chance-constrained goal programming, a stochastic chance-constrained goal programming model is put forward for measures programming of oil fields, which considers the per increasing production and per increasing cost of measures as stochastic variables, uses the increasing production and increasing cost as objectives and the total work load and work load of each measure as constraints. At the same time, the process of its hybrid intelligent algorithm including stochastic simulation, genetic algorithm and neural network is also provided. Finally, the real example, i .e. measures programming of DX Oilfield testifies the efficiency, practicability and intellectual ability of the model and its solution algorithm, which provides a new decision basis for the incremental measures program of oil fields.