درباره بسترهای نرم افزاری نگهداری پیشگویانه برای سیستم های تولید
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|21868||2012||6 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 4238 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
- تولید محتوا با مقالات ISI برای سایت یا وبلاگ شما
- تولید محتوا با مقالات ISI برای کتاب شما
- تولید محتوا با مقالات ISI برای نشریه یا رسانه شما
پیشنهاد می کنیم کیفیت محتوای سایت خود را با استفاده از منابع علمی، افزایش دهید.
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Procedia CIRP, Volume 3, 2012, Pages 221–226
Maintenance and support may account for as much as 60 to 75% of the total lifecycle cost of a manufacturing system. This paper presents a review on the predictive maintenance approaches, methods and tools in manufacturing systems and proposes an integrated predictive maintenance platform. This platform consists of three pillars, namely data acquisition and analysis, knowledge management, and a sustainability maintenance dashboard. The first pillar is responsible for data extraction and processing, the second one focuses on the maintenance knowledge modeling and representation and the third pillar provides advisory capabilities on maintenance planning with special emphasis given to environmental and energy performance indicators.
During the last years, cost and time have been the basic drivers of manufacturing systems, whilst ensuring that reliability, safety and integrity are not compromised .Manufacturing systems maintenance is becoming increasingly important, since in many industrial plants, the maintenance costs often exceed 30% of the operating costs and in the context of manufacturing systems lifecycle,maintenance and support, account for as much as 60 to 75%of the total lifecycle costs . The present systems do not provide a systematic and structured way of modeling and integrating early failures in the associated maintenance activities. Although advanced systems or subsystems are built, with real-time monitoring capabilities, the data when collected are not organized and analyzed and in the end, correct predictive maintenance actions cannot be enforced. The visualization of the operation data that could lead to a better analysis for preventive maintenance is rather simplistic with the use of 2D images and typical charts, lacking in a user friendly interface that facilitates the engineer’s understanding.
نتیجه گیری انگلیسی
Multi-sensory intelligent systems capable of numerous parameters monitoring will be implemented under the proposed platform The increased quality of retrieved data is guaranteed by the sensory systems of advanced accuracy and the noise removal, achieved by the following symbolic dynamic filtering approaches(SDF). The SDF outperforms the existing methods used in data analysis for noise removal. So far, the SDF has been utilized only in the fault diagnostics of aircraft engines . The ARIMA models are capable of modeling non stationary processes, since they also include the “integration” part while at the same time,accommodate random shocks, in contrast to simple regression approaches . Reliability and maintenance considerations take place during the early design steps by utilizing past failure knowledge, stored in the knowledge repository in the form of failure templates,described by the ontology. The design of equipment,processes and systems, taking into account maintenance and reliability parameters is covered by the proposed approach. Reasoning mechanisms, IF-Then Rules, and similarity measurements, provide a systematic and automatic way for the detection, identification and isolation of failure without requiring skilled personnel.Parameters deviations are connected with the fault types,their cause and a possible solution. All the aforementioned relationships are modeled with the knowledge mechanisms, i.e, ontology, inference rules and in terms of time and cost, they are efficiently and automatically retrieved. Scheduled based maintenance is by condition a based maintenance by utilizing prognostics tools, specifically remaining useful life.Thus, only necessary maintenance activities take place at the time defined by the condition of the equipment. The maintenance planning engine takes into consideration the following indicative criteria i) environmental impact(scrap, CO2 emissions etc), ii) energy costs, iii) energy efficiency, iv) energy efficiency, v) remaining useful life, vi) operating costs, vii) maintenance time (repair time, setup time. The augmented reality technology will allow a user friendly presentation of the results of maintenance activities that are described by high complexity. Specific interfaces will facilitate the overview of the key performance indicators that are critical for the maintenance activities.The proposedplatform will utilize smart phones and mobile devices ingeneral, in order to for them to be used in the shop floor by the maintenance engineers that would allow them to have an overview of the maintenance analysis results in a timely and cost efficient way.