An anomaly detection method for rotating machinery monitoring based on the most representative data

Abstract

With the development of concepts of industry 4.0, condition monitoring techniques are changing. Large amounts of generated data require diagnostic procedures to be automated, which drives the need for new and better methods of autonomous interpretations of vibration condition monitoring data. However, if new methods are to be operational, they need to be verified under real industrial conditions and compared with well-established expert-based diagnostic techniques. This article introduces the novel algorithm of data preprocessing for the nearest-neighbor-based anomaly detection. This approach is validated on real industrial machinery in a series of case studies. The population of over-hung centrifugal fans, employed in the same industrial process, were monitored continuously according to the proposed methodology for an extended time period. Piezoceramic accelerometers were used to register time-domain vibration data. The data were processed to extract several signal features to serve as inputs to the anomaly detection algorithm. The novel solution is compared to the well-established condition monitoring approach. Presented data include not only the intact state of machinery but also a machine breakdown case and serious deterioration of the machine condition. The influence of maintenance work is also presented in the article. Authors show the data-driven approach to condition monitoring, which can be used as one of many predictive maintenance techniques.

Predictive maintenance framework for assessing health state of centrifugal pumps

“…At the same time, temperature ( o C) can be a vital indication, as it is stated that before the total malfunction of a machine, its temperature rapidly rises. In their analysis, [23] considered statistical values of vibration measurements for anomaly and RUL prediction in CNC milling machines.…”

A review of machine learning methods applied to structural dynamics and vibroacoustic

“…one-class SVM [76,77]; distance-based, e.g. k-means and k-nn [78]; probabilistic-based, e.g. Gaussian mixture model (GMM) [79] and reconstruction-based, e.g.…”

Review of fault detection techniques for predictive maintenance

“…, 2021), rotating machinery (Torres-Contreras et al. , 2021; Lis et al. , 2021), conveyor motors (Kiangala and Wang, 2020), injection moulding machines (Rousopoulou et al.…”

“…In the manufacturing industry, many sensor devices are interconnected to collect operational data from machines on a continuous basis and feed it to backend computers for control and predictive analysis (Gopalakrishnan and Kumaran, 2022;Masero et al, 2018). These techniques can be used to monitor different parts of a manufacturing process (He et al, 2017), including belt drives (Pollak et al, 2021), bearings (Pichler et al, 2020;Lalik and Wa ˛torek, 2021), fleet (Ioanna et al, 2021), boiler feed pumps (Moleda et al, 2020), bi-directional JQME 29,2 control valve (Khadim et al, 2021), rotating machinery (Torres-Contreras et al, 2021;Lis et al, 2021), conveyor motors (Kiangala and Wang, 2020), injection moulding machines (Rousopoulou et al, 2020) and steel plate systems (Chong et al, 2021). In addition to all these, failures can happen in key components such as barrier machines in railroad crossings (Grzechca et al, 2021a) and heavy Earth moving machinery.…”

“…systems handle more than one product, but most algorithms are designed to work with a single product. In addition to that, in manufacturing, it is essential to detect multiple faults (Shaheen et al, 2021) and for a longer period of time (Lis et al, 2021).…”