To prevent possible accidents,the study of data-driven analytics to predict hidden dangers in cloud service-based intelligent industrial production management has been the subject of increasing interest recently.A mac...To prevent possible accidents,the study of data-driven analytics to predict hidden dangers in cloud service-based intelligent industrial production management has been the subject of increasing interest recently.A machine learning algorithm that uses timeliness managing extreme learning machine is utilized in this article to achieve the above prediction.Compared with traditional learning algorithms,extreme learning machine(ELM) exhibits high performance because of its unique feature of a high generalization capability at a fast learning speed.Timeliness managing ELM is proposed by incorporating timeliness management scheme into ELM.When using the timeliness managing ELM scheme to predict hidden dangers,newly incremental data could be added prior to the historical data to maximize the contribution of the newly incremental training data,because the incremental data may be able to contribute reasonable weights to represent the current production situation according to practical analysis of accidents in some industrial productions.Experimental results from a coal mine show that the use of timeliness managing ELM can improve the prediction accuracy of hidden dangers with better stability compared with other similar machine learning methods.展开更多
In multi-phase flows, the phases can flow and arranged in different spatial configurations in the pipe, which called flow patterns. This type of flow is found in the oil, chemical and nuclear industries. For example, ...In multi-phase flows, the phases can flow and arranged in different spatial configurations in the pipe, which called flow patterns. This type of flow is found in the oil, chemical and nuclear industries. For example, in the production and transport of oil and gas, the identification of the flow patterns are essential for answering those questions which are related to the economic return of the field, such as, measuring the volumetric flow, determining the pressure drop along the flow lines, production management and supervision. In offshore production, these factors are very important. This paper presents a new method for measuring the void fraction in horizontal pipelines, taking the air as gas in water-air two-phase flow. Through acoustic analysis of the frequency response of the pipe, the method gets the parameters to changes in runoff regime, in an experimental arrangement constructed on a small scale. The main advantages are the non-intrusive characteristic and easy to implement. The paper is composed of a qualitative experimental evaluation and transducers （microphone） which are used to analyze variations in the response accompanying variations in void and flow pattern changes. Changes are imposed and controlled by a two-phase flow experimental simulation rig, including a measurement cell constituted of an external casing that can isolate the measurement from the environmental background noise fitted with acoustic pressure transducers radially arranged, and the impact of a monitored excitation mechanism. The signals which captured by the microphones are processed and analyzed by checking their frequency contents changes according to the amount of air in the mixture.展开更多
基金partially supported by the National Key Technologies R&D Program of China under Grant No.2015BAK38B01the National Natural Science Foundation of China under Grant Nos.61174103 and 61272357the Fundamental Research Funds for the Central Universities under Grant No.06500025
文摘To prevent possible accidents,the study of data-driven analytics to predict hidden dangers in cloud service-based intelligent industrial production management has been the subject of increasing interest recently.A machine learning algorithm that uses timeliness managing extreme learning machine is utilized in this article to achieve the above prediction.Compared with traditional learning algorithms,extreme learning machine(ELM) exhibits high performance because of its unique feature of a high generalization capability at a fast learning speed.Timeliness managing ELM is proposed by incorporating timeliness management scheme into ELM.When using the timeliness managing ELM scheme to predict hidden dangers,newly incremental data could be added prior to the historical data to maximize the contribution of the newly incremental training data,because the incremental data may be able to contribute reasonable weights to represent the current production situation according to practical analysis of accidents in some industrial productions.Experimental results from a coal mine show that the use of timeliness managing ELM can improve the prediction accuracy of hidden dangers with better stability compared with other similar machine learning methods.
文摘In multi-phase flows, the phases can flow and arranged in different spatial configurations in the pipe, which called flow patterns. This type of flow is found in the oil, chemical and nuclear industries. For example, in the production and transport of oil and gas, the identification of the flow patterns are essential for answering those questions which are related to the economic return of the field, such as, measuring the volumetric flow, determining the pressure drop along the flow lines, production management and supervision. In offshore production, these factors are very important. This paper presents a new method for measuring the void fraction in horizontal pipelines, taking the air as gas in water-air two-phase flow. Through acoustic analysis of the frequency response of the pipe, the method gets the parameters to changes in runoff regime, in an experimental arrangement constructed on a small scale. The main advantages are the non-intrusive characteristic and easy to implement. The paper is composed of a qualitative experimental evaluation and transducers （microphone） which are used to analyze variations in the response accompanying variations in void and flow pattern changes. Changes are imposed and controlled by a two-phase flow experimental simulation rig, including a measurement cell constituted of an external casing that can isolate the measurement from the environmental background noise fitted with acoustic pressure transducers radially arranged, and the impact of a monitored excitation mechanism. The signals which captured by the microphones are processed and analyzed by checking their frequency contents changes according to the amount of air in the mixture.
