Using statistical models in industrial equipment (original) (raw)
Related papers
Development of a model for failure prediction on critical equipment in the petrochemical industry
Engineering Failure Analysis, 2015
In this study, a mathematical model was developed for failure prediction on critical equipment in petrochemical industry. The model utilized three principal measurements, namely: temperature, vibration and pressure, in developing a framework for determining expected failure periods for each component of the critical equipment. Validation of the model was done using data collected from Warri Refinery and Petrochemical Company, carbon black plant, Ekpan-Warri, Nigeria. Condition monitored data based on the three principal measurements were generated and used to determine expected failure periods for each component of the critical equipment (single-stage centrifugal compressor) in the plant. It was observed that for all the equipment under consideration, the life expectancy for blower casing is longest for all components, while that of gear and gear bearing is least. Hence, special attention should be focused on monitoring the condition of the gear and its bearing components. It was also observed from the plot trends that the deterioration rate of all components is affected by the equipment operating speed condition and functionality.
Reliability Analysis for Refinery Plants
The Journal of King Mongkut's University of Technology North Bangkok
One of the main problems in compiling Preventive Maintenance (PM) plans for large-scale industries consisting of many subunits in the production system is the criterion used in the selection of machines and equipment to be maintained. The criteria most used are the failure frequency of each machine and equipment and the maintenance cycle time specified in the manual, as preventive maintenance is considered to be mainly time-based. In some cases, Failure Mode and Effect Analysis (FMEA) technique is applied in the selection of machines and equipment by considering individual and independent machines in the subsystems. The overall mechanisms of the machines and equipment were not considered, which may affect the production capacity. Therefore, this research applies reliability engineering techniques to find the overall reliability of machines and equipment in the production system of oil refinery models and determine the machine in the subsystem that affects that overall reliability. This in turn causes optimal preventive maintenance planning for machines and equipment in order to achieve the maximum efficiency for the oil refinery process. This research begins by studying the procedures of oil refinery models, then creating a reliability block diagram of the subsystems to find the reliability of the machines and equipment within each subsystem. Afterwards, the overall reliability of the production system will be determined, which leads to arranging the reliability of machines and equipment in the subsystems in ascending order. This develops into the preventive maintenance planning process so that the refinery process achieves its maximum efficiency.
Prognosis of defects for machines working under large variation of speed and load conditions is a topic still under development. Wind turbines are recent examples of such kind of machines that need reliable diagnosis methods. Vibration analysis can be of very limited use when the speed variation is too high. An effective angular resampling method can be very valuable as the first step of vibration signal processing but it is important to know what are the appropriate variables to be monitored.
MatheMatiCal MODel OF reliabilitY anD eFFiCienCY OF PUMPinG Unit OF an Oil PUMPinG StatiOn
MATHEMATICAL MODEL OF RELIABILITY AND EFFICIENCY OF PUMPING UNIT OF OIL PUMPING STATION, 2017
в. с. костишин, д-р техн. наук, проф., і. і. яремак Івано-Франківський національний технічний універси-тет нафти і газу, м. Івано-Франківськ, Україна, e-mail: yaremak_iryna@ukr.net МатеМатична Модель надійності та еФективності роботи насосного агрегата наФтоПерекачУвальної станЦії Purpose. Developing a mathematical model for the efficiency and reliability of the pumping unit (PU) of the oil pumping station (OPS) on the basis of the per-unit system and the methodology of the system approach which contains the electric, hydraulic and mechanical subsystems and reflects the energy inputs and outputs of the centrifugal pump (CP) and synchronous motor (SM). Methodology. Mathematical models of PU of OPS are developed which are synthesized on the basis of a system approach taking into account the impact of their operating modes on reliability and efficiency parameters of the SM and CP. This allows determining the optimal operation modes of PU OPS and to develop measures for their implementation. Findings. Based on a systematic approach a model which is a unified system of subsystems with different physical nature was formed. The mathematical model of efficiency and reliability parameters of SM and CP was formalized as polynomials and values of their coefficients were calculated. It was clarified that the extreme values of efficiency and reliability are achieved for different flow rate values. That requires the use of multi-objective optimization studies. Originality. Based on the systematic approach, a mathematical model of PU of OPS was formalized which makes it possible to take into account the effect of changes of operating mode of PU on performance and reliability parameters of SM and CP. It is clarified that the extreme values of efficiency and reliability parameters of SM and CP are achieved for different flow rate values. Practical value. Mathematical models that allow estimating the impact of changes of flow rate of OPS on the performance and reliability parameters of SM and CP to select the best operating mode without expensive field experiments are developed. introduction. For now lowering of power consumption is a global development priority in energy policy in Ukraine and in the world. OPS pipelines which are equipped with PU are complex energy-intensive facilities , consisting usually of CP driven by SM. The present day world politic and economic situation has resulted in the fact that the PUs of OPS often operate in un-derloaded mode which caused a sharp decline in their efficiency and reliability parameters. That is why particularly important is solving the problem of implementation of optimal multipurpose control of PU aimed at improving those parameters, which in turn requires developing a complex mathematical model of OPS based on a systematic approach. That model should be able to show correctly the complex interdependent connections between OPS's subsystems of different physical nature. analysis of the recent research. The most efficient operating mode of CP is determined considering its efficiency value [1]. However, it was also proposed to take into account the reliability of SM behavior [2] for a
The 4th International Reliability Engineering Conference, IREC2016, 26-28 April 2016, Sahand University of Technology, Tabriz, Iran, 2016
1. The pumps have undeniable role in industrial activities thus it can be mentioned that all industries have to use it and operate as store system to save huge amount of energy for instance to pump water from lower reservoir to a higher one.[1] Even mostly due to high failure risks and its consequences, industries obliged to using reserved systems. The experiences show that around 60% of industrial equipment energy usage is from electro motors and more than 30% of total usage is for pumps. Studies in 60 & 70 decades in USA and Swedish universities show that Bathtub curved model cannot be true for most of complicated equipment and merely 8% to 23% of failure mode follows it depend on system age and yield. Thus it was discussed that more preventive measures only will increase the costs and has no effect in decreasing emergent failure statistics. In most equipment pump maintenance has done in fixed intervals that lead to increasing repair costs or increasing pump energy usage that caused financial loss and increasing the pump breaking probabilities. Though in this research we will study around types of pump probabilistic failures and from the existing methods we have choose effective method of condition monitoring (CM) included performances analysis and economic analysis for diagnoses , finding best or optimal time of industrial pumps overhauls or repair. The common foundation of predictive maintenance is disciplined monitoring of real mechanical conditions, efficiency and other index of machines or processing systems. Though required information gathered to be assured maximum distance between two failure mode and minimum number of it and also achieving unconditional cost of unplanned failures in production systems. So we've required sampling during 12 months for two pumps and results have analyzed in relations and optimal time for repairing has proved. For future researches we can use results for financial or performance aspect in greater scale. 2.
Sensors
Smart remaining useful life (RUL) prognosis methods for condition-based maintenance (CBM) of engineering equipment are getting high popularity nowadays. Current RUL prediction models in the literature are developed with an ideal database, i.e., a combination of a huge “run to failure” and “run to prior failure” data. However, in real-world, run to failure data for rotary machines is difficult to exist since periodic maintenance is continuously practiced to the running machines in industry, to save any production downtime. In such a situation, the maintenance staff only have run to prior failure data of an in operation machine for implementing CBM. In this study, a unique strategy for the RUL prediction of two identical and in-process slurry pumps, having only real-time run to prior failure data, is proposed. The obtained vibration signals from slurry pumps were utilized for generating degradation trends while a hybrid nonlinear autoregressive (NAR)-LSTM-BiLSTM model was developed fo...
Vibration analysis of rotating machines for an optimal preventive maintenance
Mining Science, 2016
Face to the development and competition to competitiveness, which drives the search for quality and above ail; cost reduction, maintenance has become one of the strategic functions in the company. One of the solutions incorporated in management systems is Conditional maintenance that has proved successful; Reduce downtime, optimize manufacturing, ensure safety and profitability of production. For this type of maintenance to be effective, precise and reliable measurements are required. Experience has shown that vibration analysis is the most widely used technique for reliable monitoring and diagnosis. The objective of this work is the study carried out at the Elma Labiod cement plant, which has adopted continuous monitoring in the hope of an optimal approach to conditional maintenance. We use the analysis of global velocity and acceleration levels, spectral analysis and envelope analysis to detect defects and anticipate degradations that can affect a mechanism and determine the proba...
Availability Analysis of Repairable Pumping System in Oil Refinery Gas Plant
2018
This paper presents a constructive technique that can be used in analysing the availability of service producing repairable systems. The main focus is to provide an alternative approach that can be applied by a wider range of maintenance practitioners, especially in situations where mathematical complexities of existing models impose significant practical application difficulty in assessment of system availability measures. The procedure used involve careful combination of simpler aspects of selected existing models and empirical methods to assess most of the availability variables of a repairable system. In particular, a case of a pumping system in a gas power plant in Nigeria which is addressed as G4 Company for confidentiality was undertaken. The information on the operation and maintenance of the system were used to identify the best life time distribution for modelling the system availability. The results reveals that important system availability parameters like the mean time ...
USE OF SURVIVAL MODELS IN A REFINERY Authors
2013
Statistical methods are nowadays increasingly useful in industrial engineering. From plant design reliability to equipment analysis, there is much to cover with statistical models in order to improve the efficiency of systems. At Sines refinery we found it useful to apply a Cox model to a particular critical equipment trying to find process variables that cause its vibration as well as to apply well known distributions to baseline hazard rate. Key-Words:
Data, 2018
Collecting the failure data and reliability analysis in an underground mining operation is challenging due to the harsh environment and high level of production pressure. Therefore, achieving an accurate, fast, and applicable analysis in a fleet of underground equipment is usually difficult and time consuming. This paper aims to discuss the main reliability analysis challenges in mining machinery by comparing three main approaches: two analytical methods (white-box and black-box modeling), and a simulation approach. For this purpose, the maintenance data from a fleet of face drilling rigs in a Swedish underground metal mine were extracted by the MAXIMO system over a period of two years and were applied for analysis. The investigations reveal that the performance of these approaches in ranking and the reliability of the studies of the machines is different. However, all mentioned methods provide similar outputs but, in general, the simulation estimates the reliability of the studied machines at a higher level. The simulation and white-box method sometimes provide exactly the same results, which are caused by their similar structure of analysis. On average, 9% of the data are missed in the white-box analysis due to a lack of sufficient data in some of the subsystems of the studies' rigs.