In order to reduce unnecessary stops and expensive downtime originating from clutch failure of construction equipment machines; adequate real time sensor data measured on the machine in combination with feature extraction and classification methods may be utilized. This paper presents a framework with feature extraction methods and an anomaly detection module combined with Case-Based Reasoning (CBR) for on-board clutch slippage detection and diagnosis in heavy duty equipment. The feature extraction methods used are Moving Average Square Value Filtering (MASVF) and a measure of the fourth order statistical properties of the signals implemented as continuous queries over data streams. The anomaly detection module has two components, the Gaussian Mixture Model (GMM) and the Logistics Regression classifier. CBR is a learning approach that classifies faults by creating a new solution for a new fault case from the solution of the previous fault cases. Through use of a data stream management system and continuous queries (CQs), the anomaly detection module continuously waits for a clutch slippage event detected by the feature extraction methods, the query returns a set of features, which activates the anomaly detection module. The first component of the anomaly detection module trains a GMM to extracted features while the second component uses a Logistic Regression classifier for classifying normal and anomalous data. When an anomaly is detected, the Case-Based diagnosis module is activated for fault severity estimation. © 2018, Prognostics and Health Management Society. All rights reserved.

A stream validation system called SVALI is developed in order to continuously validate correct behavior of industrial equipment. A functional data model allows the user to define meta-data, analyses, and queries about the monitored equipment in terms of types and functions. Two different approaches to validate that sensor readings in a data stream indicate correct equipment behavior are supported: with the model-and-validate approach anomalies are detected based on a physical model, while with learn-and-validate anomalies are detected by comparing streaming data with a model of normal behavior learnt during a training period. Both models are expressed on a high level using the functional data model and query language. The experiments show that parallel stream processing enables SVALI to scale very well with respect to system throughput and response time. The paper is based on a real world application for wheel loader slippage detection at Volvo Construction Equipment implemented in SVALI. © 2016 The Author(s)

Quantifying and Monitoring of drilling performance are becoming exceedingly important in the case of Down the Hole drilling. Various economic, environmental and safety constraints are driving the drilling process to become more efficient. To make a robust system that would enable the performance/condition monitoring of the drilling, we must understand how different properties like different line pressure etc. respond to various drilling conditions and what information can they provide regarding the Drilling Performance. A comparison of different properties like spectral properties, of the vibration signals and Pressure signals under known conditions would enable better understanding of the drilling system and the physics behind the process. A comparison is made between the Spectral properties of the vibrational signals obtained from remote locations on the drill rig and pressure signals that provide the feed and holdback forces to the drill string and a correlation between their characteristics and patterns under good and bad drilling conditions have been made. A simplified model of the system is simulated and results are compared with the patterns obtained from analyzing the Vibration signals.

This paper describes a remote implementation of Galileos inclined plane experiment, focused on secondary school students. A remotely controlled inclined plane has been designed and implemented in the VISIR lab at Blekinge Institute of Technology (BTH), Sweden. In this demo session, it will be demonstrated how to perform measurements remotely in the remotely controlled Inclined Plane Laboratory. A web camera is used to show the experiment. Data concerning the distance a cube has slided down the inclined plane are collected. These data are stored in a file and can subsequently be analyzed by the students. The friction acting on the cube sliding down the inclined plane and its acceleration may for instance be investigated.

In Atlas Copco a wide range of machines is produced from surface drill rigs, exploration drill rigs, underground drill rigs both for mining and construction to underground loader and haulers for mines. Recently new rock excavation methods have developed in cooperation with large mining companies. The machines are produced in low volume and often customized although having a modular approach. Time for validation is limited due to machines available for test are planned for customer delivery. It is on regular basis needed to validate and investigate vibrational behavior of installations as power packs and drivelines to get loads for simulation, identify resonances, operational deflection shapes, and vibration and stress levels for life length estimations under operational conditions. The time for a 40-180 Channel measurement is now down the range of 1-3 days. To reduce the time it takes to perform measurement a systematic approach has been taken that includes mainly three areas. First the Bookkeeping of all information and data needed for the analysis and reporting is input before or during the measurement. Systematic Approach of how to setup sensors, handle cable and equipment, planning and measurement. This includes practical examples of how to. Finally it is very important to take steps to assure Quality early in the measurement and also avoiding disturbances in the sensor path. There will be practical examples of important disturbances to look out for and quality check to perform. It should also be noted that the measurements is regular measured in mines or start up halls under rpm sweeps or/and operating conditions of the machines.

In Atlas Copco a wide range of machines is produced from surface drill rigs, exploration drill rigs, underground drill rigs both for mining and construction to underground loader and haulers for mines. Recently new rock excavation methods have developed in cooperation with large mining companies. The machines are produced in low volume and often customized although having a modular approach. Time for validation is limited due to machines available for test are planned for customer delivery. It is on regular basis needed to validate and investigate vibrational behavior of installations as power packs and drivelines to get loads for simulation, identify resonances, operational deflection shapes, and vibration and stress levels for life length estimations under operational conditions. The time for a 40-180 Channel measurement is now down the range of 13 days. To reduce the time it takes to perform measurement a systematic approach has been taken that includes mainly three areas. First the Bookkeeping of all information and data needed for the analysis and reporting is input before or during the measurement. Systematic Approach of how to setup sensors, handle cable and equipment, planning and measurement. This includes practical examples of how to. Finally it is very important to take steps to assure Quality early in the measurement and also avoiding disturbances in the sensor path. There will be practical examples of important disturbances to look out for and quality check to perform. It should also be noted that the measurements is regular measured in mines or start up halls under rpm sweeps or/and operating conditions of the machines.

With increasing complexity in the heavy duty construction equipment, early fault detection of certain components in the machine becomes more and more challenging due to too many fault codes generated when a failure occurs. The axle is one such component. The axle transfers driving torque from the transmission to the wheels and axle failure may result in costly downtime of construction equipment. To reduce service cost and to improve uptime, adequate condition monitoring based on sensor data from the axle is considered by for instance measuring vibrations on the axle. Further, the analysis of the data collected has been has been carried out using adequate signal processing methods. The results indicate that the vibration properties of the axle are relevant for early fault detection of the axle. Thus, the health of the axle may be continuously monitored on-board using the vibration information and if the axle health starts to degrade a service and/or repair may be scheduled well in advance of a potential axle failure and in that way the downtime of a machine may be reduced and costly replacements and repairs avoided.

Improving uptime is paramount in the heavy duty construction equipment business. Failure of critical components in the heavy duty machine may lead to unnecessary stops and expensive downtime. The torque converter, a complex component of the driveline, transmits and multiplies torque from the engine to the gearbox, and its failure may not only lead to the machine standing still but may also lead to damage of other parts of the automatic transmission. For adequate condition monitoring of the torque converter, different sensor data are measured on a construction equipment machine during controlled driving sessions. Vibration has been measured on the torque converter. An initial investigation of the vibration measured on the torque converter has been carried out to identify its vibration properties in order to enable its health monitoring to prevent failure. Initial signal analysis of the data have been carried out using Order Power Spectrum and Order Modulation Spectrum methods. The results indicate that the torque converter vibration properties contain information relevant for early fault detection.

In In this demo session, it will be shown how to perform Active Noise Control (ANC) and various important Acoustic experiments remotely on the remotely controlled ANC laboratory developed by Blekinge Institute of Technology, Sweden. An important consideration in ANC is the active control’s performance dependence on the spatial position of the reference and error sensors, etc. This will be highlighted particularly. This feature is recently implemented using stepper motors which can be controlled via the Internet. It will be demonstrated how to write and upload active noise control algorithms e.g. Filtered-X Least Mean Square (FXLMS) to a digital signal processors (DSP) board. For the acoustic experiments various interesting acoustic properties such as waveforms, speed of sound, mode shapes and sound pressure spectra may be measured. A short guide about the measurements and PowerPoint presentation will be provided during the demo to facilitate for the users. The Lab setup and the equipment will be shown to the user using Skype and a web camera.

Heavy duty construction equipment is generally equipped with automatic transmission enabling to change gear ratio automatically. The clutches in an automatic transmission transfer torque from the engine to the gearbox and clutch failures may result in costly downtime of construction equipment. To prevent costly downtime of construction equipment, condition monitoring in combination with condition based maintenance may be utilized. Different sensor data are collected on a machine that enables condition monitoring. Vibration have been measured on an automatic transmission in a construction equipment machine during controlled driving sessions, with and without clutch slippage, on a test track. An initial investigation of the vibration measured on the automatic transmission have been carried out with the purpose to find out if the vibration may contain reliable information related to clutch slippage considered to be abnormal. Initial signal analysis of the data have been carried out using Spectrogram and Spectral Kurtosis methods. The results indicate that information related to abnormal clutch slippage may be extracted from vibration measured on an automatic transmission in a construction equipment machine.