Use of the Correlation Coefficient for Rotating Machine Monitoring

The use of electronics and computer technology in production systems has greatly improved the quality of our industrial products. The productivity of these installations is a function of the maintenance quality applied to the equipment. Several methods are used to monitor the functioning of industrial installations. One of these methods is vibration analysis. The vibration signals from the rotating machines support several types of information related to the working state of the production tool. The processing of this information makes it possible to have decision tools for maintenance. In this work, we propose a method of anticipating the maintenance of rotating machines. The algorithm we propose starts with the removal of 512 point windows during the running time of the ball bearing. Each signal is decomposed by DWT: we obtain the approximation coefficients. These coefficients make it possible to determine the correlation coefficient between the so-called reference window and the other windows following the functioning of the ball bearing. The correlation coefficient is then the fundamental element of the decision. This algorithm has been applied to real vibration data and the results are encouraging.

Reliability and Availability Study of a Gas Turbine based on usual Approaches with a Failure Mode Analysis

The rotating machines like gas turbine types are highly valuable in the gas transportation industry. They are often strategic and have a major impact on the proper operation of gas transport and compression facilities. In this context, the aim of this work is to increase efficiency and production by developing an approach for this kind of installations using real data collected from the operation of the gas turbine. The objective is to provide a database relating to the reliability, availability, and maintenance of gas turbines while using standard reliability approaches. In addition, ensuring maximum availability of this type of rotating machine by preventing its failures and reducing emissions, and by minimizing start-up sequences, which reduces emissions when starting this machine. Also, the proper operation of these gas turbine installations with the reliability approaches developed in this work makes it possible to model the effects of failures in order to predict optimal operating performance and increase the life of their components. This, therefore, ensures a reliable and safe operation of the gas turbine in a compression station for economically profitable gas recovery.

Feature extraction and recognition of rotating machinery fault noise based on convolutional neural networks

Rotating machines are common equipment in industrial production, which may cause failure for a long time. Because of its convenient use and non-destructive to itself, acoustic detection method is suitable for fault diagnosis of rotating machinery. The convolution neural network model is used to identify several typical rotating machine faults. The repeatability experiments and different training sets show that the method has good universality. A visual fault identification system is built, and the effect of the system is verified by experiments.

Novel Carbon Fibre Composite Centrifugal Impeller Design, Numerical Analysis, Manufacturing and Experimental Evaluations

This paper presents an experimental investigation on using high strength-to-weight composite materials to reduce the mass of a centrifugal compressor impeller by 600%. By reducing the blades number from 17 to 7 and by doubling their thickness, the compression ratio and efficiency were maintained close to the reference metallic impeller. Using autoclave technology, seven composite blades were manufactured individually and assembled to form the impeller. After manufacturing, small deviations were found at the blade’s tip. As these deviations were found to be symmetrical, impeller balancing was successfully performed removing a total of 45 g of mass, followed by an experimental test on a dedicated test bench. Experimental testing identified the resonant frequencies of the composite centrifugal impeller at 13.43 Hz 805 rot/min and at 77 Hz with a 0.1 mm/s amplitude at 4400 rot/min, highlighting feasibility and the advantage of a composite compressor impeller design with application in centrifugal compressors and rotating machine assemblies and sub-assemblies. As there are numerous numerical investigations performed on the strength analysis and on the lay-up orientations mechanical behaviour for polymer composite materials with respect to the design of centrifugal impellers, no experimental evaluations in relevant working conditions have been performed to date. As the paper contains relevant experimental data on the subject, the outcome of the paper may aid the oil and gas or aviation industries.

Vibration Measurement of a Rotating Shaft using Electrostatic Sensor

Measuring Vibration parameter for rotating machinery is essential for monitoring and diagnosis system in industrial plants. This paper demonstrates another approach to vibration measurement for rotating machine using electrostatic sensor and signal processing techniques. A single electrostatic sensor is used to detect charges surrounding the moving shaft of the machine. The signal from the electrostatic sensor is processed in MATLAB using Autocorrelation, Fast-Fourier, and Root Mean Square. The implementation of this technical approach was conducted on a modified test rig using three different shafts. The three shafts represent three different vibration modes: normal, abnormal, and severe. Each shaft was experimented under low and high rotation speed to observe amplitude and frequency level. Although the results of the tests did not show a direct measure of vibration displacement, due to the complex nature of the induced charges by the surface pattern. However, the results showed an indicative level of vibration at different amplitudes for the three shafts.

Capacitive Sensor Accuracy Optimisation by the Frequency Range Appropriate Choice

Measuring rotating machine vibrations requires an electronic instrument called a vibration sensor. In this work, the vibration sensor with capacitive detection is chosen to measure the vibrations movement. In order to fulfill the objectives of reducing the measurement error and achieving high sensor accuracy, this sensor is modeled by the application of motion law. The results obtained by the developed model simulation showed that it was possible to extract a formula linked to relative frequency of the vibrating structure and to the capacitive sensor natural frequency, this makes it possible to reduce the measurement error and improve the capacitive sensor accuracy

HEURISTIC OPTIMIZATION OF THE FOUNDATION OF A DYNAMICALLY STRESSED ROTATING MACHINE USING THE LATE ACCEPTANCE HILL CLIMBING (LAHC) ALGORITHM

This paper proposal the optimization of a foundation for rotative machine under dynamic loads in transient and permanent working mode. The foundation depends on fix parameters and 37 variables. Functional constraints are defined for the foundation. A cost function depending on the variables is defined to be minimized to find the optimal. From all the possible solutions, only are selected the ones that validate the constrains and minimize the cost function. The search of the optimal solution is made with an algorithm of random search by “neighbouring of one point” called Last Acceptance Hill Climbing(LAHC). It is an algorithm of the type called “Adaptative Memory Programming” (AMP) that accepts worse solutions to get the local minimum and learns of the results of the search. The algorithm only depends on the length of the comparison vector and the stop criteria. 350 experiences were made with different length of the comparison vector. It was analysed the quality of the optimal solutions got it with each length of the vector. Quality of the set of solutions was compared fitting them to a 3 parameters Weibull distribution.