Diagnosis for Slight Bearing Fault in Induction Motor Based on Combination of Selective Features and Machine Learning

Induction motors are widely used in industry and are essential to industrial processes. The faults in motors lead to high repair costs and cause financial losses resulting from unexpected downtime. Early detection of faults in induction motors has become necessary and critical in reducing costs. Most motor faults are caused by bearing failure. Machine learning-based diagnostic methods are proposed in this study. These methods use effective features. First, load currents of healthy and faulty motors are measured while the rotating speed is changing continuously. Second, experiments revealed the relationship between the magnitude of the amplitude of specific signals and the rotating speed, and the rotating speed is treated as a new feature. Third, machine learning-based diagnoses are conducted. Finally, the effectiveness of machine learning-based diagnostic methods is verified using experimental data.

Intended Ignorance: The Collapse of the I-35 W Mississippi River Bridge on 1 August 2007

At 6:05 PM on 1 August 2007, the I-35 W Highway Bridge crossing the Mississippi River in Minneapolis, Minnesota, collapsed due to the failure of crucial parts of the bridge’s steel truss structure. Thirteen people died in the disaster, 145 were injured. A report of United States National Transportation Safety Board (NTSB) revealed that the Minnesota Department of Transport, over a long period of time, had ignored available information about the structurally deficient status of the bridge in anticipation of ‘budget busting’ repair costs. Which resulted in a preference for less expensive patch-up measures to improve the drivability of the bridge rather than a retrofit of the fracture-critical components of the steel truss whose failure triggered the disaster of 1 August 2007.

Pemanfaatan Metode Activity Based Costing Dalam Sistem Informasi Akuntansi Penentuan Biaya Pada Bengkel Muji Jaya

The Muji Jaya Workshop in determining the cost of body repair, it still uses a manual estimate model with paper media which will result in losses if the calculation of the cost of body repair that is informed to the customer is not enough so that the body repair costs received are not sufficient for the needs of raw material costs and labor costs in body work. The repair and preparation of financial statements will be disrupted and delayed for a long time if the note paper used is lost or damaged. This results in the owner not being able to make decisions quickly, precisely and accurately. From these various problems, Workshop Muji Jaya implements the use of the activity based costing method in the accounting information system for determining body repair costs in order to make it easier to determine the cost of body repairs to be more accurate and in presenting financial statements to be easier and more efficient because this method is guided by the assignment of costs to products. or services based on all required activities. Keywords: estimation, cost, activity based costing

Converter for starting motor-generator sets of autonomous locomotives

Objective: To confirm the possibility of using a starting converter to spin up the shaft of the motorgenerator set to a speed that ensures stable combustion of the air-fuel mixture in the motor cylinders (starting), as well as of using semiconductor converters based on modern IGBT modules for starting promising motor-generator sets of mainline and shunting locomotives. Methods: The properties, characteristics, and operating modes of starting converters were studied on test benches. Results: The downsides of the currently most commonly used starter-generator circuit for engine starting have been identified. A technical solution has been developed to replace the startergenerator circuit with an inverter starting system using a starting converter for starting the locomotive motor-generator. The device structure has been designed. The basic algorithms of the automatic control system of the starting converter have been implemented. Bench tests of a starting converter prototype have been carried out. Practical importance: The developed technical solution in terms of replacing the starter-generator circuit with an inverter starting system for starting the motorgenerator set of autonomous locomotives makes it possible to increase their reliability by removing the electromechanical drive and replacing a number of engine drive auxiliary camshaft mechanisms (group 69). The inverter starting system will reduce the maintenance and scheduled repair costs, decrease the labor input, and optimize the time-schedule of locomotives. The proposed algorithms for starting the motor-generator set enable increasing the battery life by limiting its starting current, as well as improving the fault tolerance of a locomotive due to the possibility of starting the motorgenerator set at a low battery voltage (lower limit of 45 V).

Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern failure prevention systems. Therefore, many machine learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. This work shows a framework that incorporates neuroevolution methods to boost the anomaly detection scores of new and already known models. The presented approach adapts evolution strategies for evolving an ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimize the architecture and hyperparameters such as the window size, the number of layers, and the layer depths. The proposed framework shows that it is possible to boost most anomaly detection deep learning models in a reasonable time and a fully automated mode. We ran tests on the SWAT and WADI datasets. To the best of our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.

System of Water Vehicle Power Plant Remote Condition Monitoring

Remote condition monitoring of water vehicles plays an important role in preventing potentially very expensive marine incidents and ensuring maximum efficiency of a ship's operation and reliability with minimum maintenance downtime and repair costs. Concept of the condition-based approach to maintenance is today's best practise, and it is becoming increasingly important to move from planned maintenance to condition-based maintenance, to reduce the increasingly high cost of maintaining a modern fleet. Onboard and remote monitoring is now an essential part of condition-based maintenance process to obtain the good quality data, correct analysis, and effective counteractive actions necessary for such an approach, and article presents the water vehicle power plant monitoring model developed by authors. Considered approach, coupled with preventive maintenance, saves shipowners time and money through early diagnosis of component failure or excess wear. Power plant of water vehicle comprises far more than just an engine with its auxiliary equipment but also other main propulsion blocks – in particular, thrusters. The result was the development of the Water Vehicle Condition Monitoring (WVCM) system, which enables to closely examine water vehicle equipment performance. A WVCM system comprises the following installed onboard: accelerometers, pressure and temperature transmitters, oil, fuel and exhaust monitoring units and a torque measurement system.

Application of the soft starter for the asynchronous motor of the belt conveyor

The purpose of the work is to justify the need for a smooth start of the conveyor belt. Based on the technological features of the transportation process, the direct start of the conveyor with a loaded undercarriage entails an increase in inertial forces, overload of the traction chains and the drive. Due to the increased starting torque, there is a danger of slipping, the occurrence of an oscillatory transient of the escaping branch of the tape, slipping between the tape and the drive drum. This leads to significant wear of the tape and breakdowns of other equipment, which requires high repair costs. With a smooth start of the conveyor, the acceleration lasts longer, but the movement of the concentrated masses of the belt is more consistent, less oscillatory, which indicates less dynamic forces in the belt. Also, with a smooth start, energy losses in the engine and its heating are reduced. The main results of the work - the transients in the currents of the stator and rotor, in the speed of rotation of the motor and in the speed of movement of the conveyor belt were obtained. The developed model allows us to investigate the dynamic operating modes of the engine and the mechanical part of the conveyor, to analyze the forces arising in the belt during direct and smooth start of the conveyor, to evaluate the slip of the belt and the magnitude of the traction factor. Conclusions - the results of this work should be the basis for controlling the tension in the belt and maintaining the traction factor of the conveyor belt in the start-brake operating modes. In addition, the results obtained can be used in the development of a belt speed control system depending on the amount of random freight traffic entering the conveyor.

Analytical Model and Numerical Analysis of Composite Wrap System Applied to Steel Pipeline

Composite overwraps are a cost-effective repair technology, appropriate for corrosion defects, dents, and gouges for both onshore and offshore steel pipelines. The main benefit of polymer-based sleeves is safe installation without taking the pipeline out of service. This paper presents a new calculation procedure proposed in the form of an algorithm for the sizing of composite repairs of corroded pipelines when the sleeve is applied at zero internal pressure. The main objective of the presented methodology is determination of the effective thickness of the composite repair without its overestimation or underestimation. The authors used a non-linear finite element method with constitutive models allowing analysis of the steel, putty, and composite structures. The validation of the results of numerical computations compared to the experimental ones showed an appropriate agreement. The numerical calculations were applied to compare the analytical results in relation to those obtained by the standards ASME PCC-2 or ISO/TS 24817. The comparison showed that the proposed solution confirmed its effectiveness in reducing the thickness of the sleeve significantly, thus, showing that the current industrial standards provide a considerably excessive composite wrap around the steel pipe corroded area, which leads to an unnecessary increase in the repair costs.