Multivariate time-series (MTS) collected from multiple sensors on industrial pumps often exhibit concept drift and noise contamination due to variable working conditions and complex environments. To ...detect anomalies in such MTS, we propose a novel model called spectral residual with self-attention variational autoencoder (SR-SAVAE). Specifically, the spectral residual operation is used to mitigate concept drift, while the variational inference combined with a total variation regularization is used to address the issue of noise contamination. Experimental results on three public datasets indicate that the SR-SAVAE model achieves good anomaly detection results for general MTS. More importantly, compared to other state-of-the-art models on a private dataset about pumps, the results illustrate the superiority of the SR-SAVAE model in anomaly detection for MTS with concept drift and noise contamination. Finally, ablation studies on the SR-SAVAE model detail the efficacy of each component.
The paper discusses customers’ purchasing behavior in the industrial pumps market. Considering the increase in the global competition among suppliers, they must design and employ customer-oriented ...strategies to compete successfully in the market. The empirical analysis is based on the survey data from a sample of 133 industrial pump buyers. The importance of each of the supply factors that are important for a successful sales process is analyzed. The results show that the brand of industrial pumps has a statistically greater influence on smaller customers than on larger customers. The study contributes to the existing literature on purchase decision-making and industrial branding. A broader potential application of the results is discussed, and possible research directions in this area are presented at the end, given the limitations of this study.
Comparative LCA of industrial objects Lewandowska, Anna; Foltynowicz, Zenon
The international journal of life cycle assessment,
01/2004, Volume:
9, Issue:
3
Journal Article
This paper investigates how to increase the efficiency of a photovoltaic/energy storage generation unit supplying dynamic loads by regulating and managing both the photovoltaic generator and the ...storage battery charge-discharge modes. The proposed photovoltaic/energy storage unit is proposed to supply an induction motor driven industrial pump with controlled speed and/or a DC motor driven water pump. An optimal proportional-integral-derivative control based on an Artificial Bee Colony Optimization algorithm is used to regulate the photovoltaic generator in case of normal operation or in case of maximum power point tracking (MPPT) and to also control the battery storage charge discharge modes. A vector control based on the proposed optimal control is used to regulate the induction motor rotor speed at its low reference values needed by the industrial pump. First, a total model of the entire system is obtained. The controller performance with the proposed system is studied with both a DC motor and/or induction motor loads. Simulation results show that the proposed photovoltaic/storage generator is able to supply the suggested dynamic loads under different conditions and with good performance. Also, it is noticed that operating the photovoltaic base on maximum power point tracking condition will give about 43% extra generation power than the normal operation case.
Industrial pumps operating with variable speed provides numerous benefits including valve elimination, wide range of flow rate, single stage higher head and energy saving. The realization of variable ...speed pump operation is carried out using an induction motor, power electronic switches, current sensors and controller without speed feedback is known as sensorless variable speed control. This paper implements a field-oriented control based sensorless scheme on 150 kW induction motor drive system, which is integrated to centrifugal pump load in Matlab/Simulink environment. The centrifugal pump is modelled mathematically in the same environment for obtaining the identical torque speed characteristics.
Legionnaires' disease is an acute pneumonia caused by inhalation or aspiration of aerosols contaminated with Legionella bacteria. The majority (>90%) of Legionnaires' disease cases are caused by the ...species Legionella pneumophila, and about 85% more specifically by L. pneumophila serogroup 1 that can be detected by a fast and easy to perform urinary antigen test. Previously reported sources of infection include cooling towers, plumbing systems of hospitals, and whirlpool spas, but for the majority of cases of Legionnaires' disease the source of infection remains unknown.
A 52-year-old Caucasian man was admitted to a Dutch hospital with pneumonia, where a culture of the available bronchial lavage was found positive for L. pneumophila serogroup 3, confirming the diagnosis of Legionnaires' disease. An environmental investigation identified a manually operated pressure test pump at the metal processing company where he worked as the source of infection: the water sample from the pump contained 9·8×103 colony forming units/L L. pneumophila, and sequence-based typing showed the same sequence type (ST93) for both the clinical and environmental strains.
This case shows that Legionnaires' disease can be acquired by exposure to relatively rare sources that are not considered in regular control and prevention measures.
PDF
