Subjects: Dynamic and Electric Engineering >> Power Machinery Engineering submitted time 2023-10-24
Abstract： Aiming at the problem that the stepless capacity control system of reciprocating compressor has a high failure rate and great impact on the operation of the unit, and the existing risk assessment methods of the compressor operation are difficult to complete the real-time and quantitative risk assessment, a risk dynamic analysis method of the safety of stepless capacity control system was proposed, which integrated Bayes network and variable weight AHP. The Bayesian network model, which included fault type, fault mode and monitoring signal, was established to obtain the real-time probability of fault occurrence. Based on variable weight analytic hierarchy process (AHP), a semi-quantitative analysis model of fault hazard was established, and the influence index of fault mode was calculated. Further, the fault risk calculation formula of FMEA method was modified, the probability of fault occurrence was introduced, and the calculation method of historical fault and real-time operation risk was proposed. The results showed that the new method proposed in this paper could quantify the real-time and historical operating risks of computer units, and the normalized real-time operating risk threshold was setted as 0.5 to determine the need for maintenance. The research results can provide quantitative indexes for the establishment of inspection and maintenance plans for reciprocating compressors and gas volume regulation systems.
Peer Review Status:
Awaiting Review
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-05-10 Cooperative journals: 《计算机应用研究》
Abstract： The drawbacks of existing task recommendation in mobile crowd sensing were as follows: on the one hand, not fully considering the influence of spatial-temporal information on worker preference led to low accuracy of recommendation; On the other hand, ignoring the impact of task popularity on recommendation led to poor recommendation coverage. To solve these drawbacks, this paper proposed a novel task recommendation approach based on spatial-temporal information and task popularity analysis in mobile crowd sensing. Firstly, this approach made full use of the relevant information contained in the worker execution record (e. g. , the time and location of worker performing tasks) to accurately predict the preference of worker for performing tasks. Secondly, in order to reduce the impact of popular tasks on recommendation coverage, this paper analyzed task popularity based on worker reputation and task execution record, and designed appropriate task popularity penalty factor. Then, combining worker preference and task popularity penalty factor, this paper provided an appropriate task recommendation list for each worker. Finally, the experimental results show that compared with the existing baseline methods, the proposed method improves the recommendation accuracy by 3.5% and the recommendation coverage by 25%.
Hits
Hits
Downloads
Comment