Machine Monitor Research Articles

Fault detection and remote monitoring of robotic manipulator using Internet of Things (IoT)

Remote monitoring of industrial machines is important in order to have high productivitycontinuous process control. New emerging technologies such as Internet of Things (IoT), arefacilitating the process of automation and remote controlling in multiple ways. In this researchwork, a robotic manipulator based on PUMA robot structure and an intelligent remotemaintenance system is developed aimed to ensure the continual accurate operation of a roboticmanipulator. Entire manipulator is designed from different types of motors like DC motors,stepper motors and servo motors along with their motor drivers. Various types of sensors likeTachometer, DHT11 Temperature and Humidity sensor, Capacitance meter and EMFDetector are also designed and interfaced with the manipulator for identification of differentfaults. Android App and Wi-Fi module are used for the remote-controlled automationpurposes. The authors were succeeded in detecting various faults in the robotic manipulatorand notifying the operator in real-time.

An efficient industry 4.0 architecture for energy conservation using an automatic machine monitor and control in the foundry

In this article, a machine monitor and control architecture (MMCA) satisfying the industry 4.0 standard is proposed for energy conservation by optimizing the core moulding machine in industrial automation. Since the foundry environment is a fine dust area and is maintained at very high temperatures (around 140°C), the manual operation of machines is more complex and demanding. Moreover, the monitoring and controlling of machines need highly reliable eco-friendly systems. With real-time data logging, the proposed MMCA prototype system has been installed to monitor and control the overall process in a single core shooter machine (CSM). The parameters controlled using MMCA in foundry machinery include pressure, temperature and power consumption. The complete system can be controlled using an intranet or Internet connection without any human intervention in the machinery environment, which operates at a very high temperature. After explaining the architecture and its features, the experimental results are presented on a real-time implementation of the framework to validate the optimal energy management by the proposed MMCA. The experiments were performed on a CSM, which is automated for practical industrial applications. Its real-time implementation ensures that MMCA-based monitoring and controlling is more effective and advantageous than the programmable logic controller-based machine monitoring.

Drive Integrated Start-Up and Online ITSC Fault Monitoring Through Spatial Inductance Profiling

Fault diagnosis and condition monitoring of electric machines using readily available drive sensors are highly critical in safety-critical applications. This article presents an accurate method to detect stator interturn short-circuit (ITSC) fault using the spatial inductance profile, which can be implemented both at start-up (standstill) or in real time. For this purpose, ac motor drive spatially scans the motor at each start-up in milliseconds by injecting high-frequency signals to obtain spatial inductance profile, analyze the fault status, and locate faulty phase. Using the start-up inductance profiling as reference, online detection version is implanted successfully, which is essential for real-time condition monitoring. This approach is highly sensitive ITSC faults, agnostic to temperature variations, and takes inverter nonlinearities into account caused by dead time and voltage drop across the power devices. To demonstrate the efficacy and practicability of the proposed algorithm, it is experimentally verified on two PMSMs, interior permanent magnet synchronous motor (IPMSM) and an induction motor, all rewounded to mimic ITSC faults. It is shown that the algorithm can detect ITSC faults very accurately in the order of milliseconds even if the number of shorted turns is very low.

SEGA: Secured Edge Gateway Microservices Architecture for IIoT-Based Machine Monitoring

In this article, we propose SEGA, a secured edge gateway microservices architecture for industrial Internet of things-based monitoring of machines in industries. SEGA allows the secured collection, transmission, and temporary storage of data within the edge network. A k-nearest neighbors-based analytics module hosted on the edge gateway processes time-sensitive machine monitoring data on the gateway itself and identifies machines’ operational status. The system predicts the machine state and displays the monitored parameters such as current consumed, power factor, power consumption, and vibrational state of machinery. SEGA also enables secured offloading of data and advanced analytical functions from the edge gateway to the cloud. SEGA's deployment results show negligible changes in the edge gateway's performance due to the inclusion of various security and encryption mechanisms. However, the resource-constrained edge sensor nodes show an increase in wireless packet transmission latencies between them and the gateway by approximately 84.12 ms.

A Review of Multisensor Data Fusion Solutions in Smart Manufacturing: Systems and Trends.

Manufacturing companies increasingly become “smarter” as a result of the Industry 4.0 revolution. Multiple sensors are used for industrial monitoring of machines and workers in order to detect events and consequently improve the manufacturing processes, lower the respective costs, and increase safety. Multisensor systems produce big amounts of heterogeneous data. Data fusion techniques address the issue of multimodality by combining data from different sources and improving the results of monitoring systems. The current paper presents a detailed review of state-of-the-art data fusion solutions, on data storage and indexing from various types of sensors, feature engineering, and multimodal data integration. The review aims to serve as a guide for the early stages of an analytic pipeline of manufacturing prognosis. The reviewed literature showed that in fusion and in preprocessing, the methods chosen to be applied in this sector are beyond the state-of-the-art. Existing weaknesses and gaps that lead to future research goals were also identified.

A novel feature extraction method based on weighted multi-scale fluctuation based dispersion entropy and its application to the condition monitoring of rotary machines

Features describing the state of industrial gearboxes and their extraction from the mixed noisy signal are always an issue of concern. Unfortunately, traditional feature extraction methods are not equally useful for both adaptive and non-adaptive decomposition techniques. In the present study, a novel feature extraction method named weighted multi-scale fluctuation-based dispersion entropy (wtMFDE) is proposed for the condition monitoring of planetary gearbox (PGB). It is equally useful for adaptive (ensemble empirical mode decomposition) and non-adaptive (flexible analytical wavelet transform) signal denoising techniques. Four state-of-the-art classifiers viz. support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN), and multilayer perceptron (MLP), which have extensive applications in machine condition monitoring, are used for the classification of the chipped sun gear, pitted planet gear as well as the combined effect for these faults. It is observed that the extracted features are highly sensitive and effective in a way that they can recognize faults with comparable accuracy with all the selected classifiers.

An overview of thermal modelling techniques for permanent magnet machines

Permanent magnet (PM) machines have gained increasing attention from the industry because of their potential merits over conventional electrical machines. High-temperature level in electrical machines is a major factor that can adversely impact the performance and health conditions of these machines. These effects need to be minimized to make them competitive with currently operational machines in the industry. It can be done by performing a thorough thermal analysis of the prototype during the design process and proper online thermal monitoring of the machine during the operation stage. Thermal modelling is a powerful tool for achieving such goals in both cases. This paper aims to review the state-of-the-art of thermal modelling techniques and provide a detailed comparison of them in PM machines. The fundamental concepts of heat transfer and sources of heat in PM machines are first discussed. Then, different thermal modelling techniques, including thermal subdomain models (TSMs), lumped parameter thermal networks (LPTNs), finite element models (FEMs), computational fluid dynamics (CFD), reduced order models (ROMs), and hybrid thermal models (HTMs) are introduced and compared. Finally, the utilization of these models in the thermal design, control, and monitoring of PM machines is studied.

Optical FBG-T Based Fault Detection Technique for EV Induction Machines

Electric vehicles (EV) represent a key technology to achieve a low-carbon transportation objective, whist induction motors are one of the promising topologies. The reliability of these machines is crucial to minimize the downtime, cost and unwanted human lives. Although several techniques are utilized in the condition monitoring and fault detection of electrical machines, there is still no single technique that provides an all-round solution to fault detection in these machines and thus hybrid techniques are used widely. This paper presents a novel non-invasive optical fiber technique in condition monitoring of induction machines and in the process detecting inter-turn short circuit faults. Owing to optical fiber’s immunity to magnetic flux, a composite FBG-T sensor formed by bonding a giant magnetostrictive transducer, Terfenol-D, onto a fiber Bragg grating is utilized to sense machines’ stray flux as a signature to determine the internal winding condition of the machines. A tri-axial auto datalogging flux meter was used to obtain the stray magnetic flux and test results obtained via LabView were analyzed in MatLab. Experimental and numerical results agree with each other and how that the FBG-T sensor accurately and reliably detected the short-circuit faults. Bragg shifts observed under short-circuit faults were in 100s of picometre range under various operating frequencies compared to the mid-10s of picometre obtained under healthy machine condition. These provide much promise for future EVs.

Machine Monitoring Protocols Based on Quality of Service (QoS) to Improve Performance of Real-Time Industrial Applications

A major factor in the optimization of real-time industrial applications is Quality of Service (QoS). There is also a quality-of-service parameter (QoS). Normally, dynamic networks require QoS settings for real-time applications. The industrial production environment is changing due to rapid advances in ICT. Industries have increased output due to improved manufacturing chain efficiency, flexibility, and security. Establishing a secure, reliable, and fast network in the sector is therefore critical. In industrial applications, data collection is an important factor to consider. Various routing methods exist for collecting data from industrial environments and sending it to processing. In this situation, the energy consumption of device nodes and data transmission delay are important factors to consider. This research proposes to construct an energy-efficient delay-aware WSN routing (EDR) protocol for defect detection. The clustering group optimal approach is used to identify which clusters should be selected. A modified task selection method is proposed to calculate the most efficient path between industrial areas and data centres (monitoring rooms). The node selection approach is used to find the network’s aggregate node. The Network Simulator (NS2) programmed is used to model the projected IEM-EDR system. The proposed Industrial Energy Monitoring-Energy-Efficient Delay-Aware Routing (IEM-EDR) system’s performance is compared to that of existing techniques in hop count, latency, energy consumption, throughput, and delivery rate.

Smart Energy Management System: Design of a Monitoring and Peak Load Forecasting System for an Experimental Open-Pit Mine

Digitization in the mining industry and machine learning applications have improved the production by showing insights in different components. Energy consumption is one of the key components to improve the industry’s performance in a smart way that requires a very low investment. This study represents a new hardware, software, and data processing infrastructure for open-pit mines to overcome the energy 4.0 transition and digital transformation. The main goal of this infrastructure is adding an artificial intelligence layer to energy use in an experimental open-pit mine and giving insights on energy consumption and electrical grid quality. The achievement of these goals will ease the decision-making stage for maintenance and energy managers according to ISO 50001 standards. In order to minimize the energy consumption, which impact directly the profit and the efficiency of the industry, a design of a monitoring and peak load forecasting system was proposed and tested on the experimental open-pit mine of Benguerir. The main challenges of the application were the monitoring of typical loads machines per stage, feeding the supervisors by real time energy data on the same process SCADA view, parallel integrating hardware solutions to the same process control system, proposing a fast forest quantile regression algorithm to predict the energy demand response based on the data of different historical scenarios, finding correlations between the KPIs of energy consumption, mine production process and giving global insights on the electrical grid quality.

Locally optimized chirplet spectrogram for condition monitoring of induction machines in transient regime

The locally optimized chirplet spectrogram (LOCS) is a novel method proposed in this work for generating a high-resolution and cost-effective spectrogram of the induction machine (IM) current, suitable for the identification of fault-related harmonics in transient conditions. Its distinctive novelty is that it optimizes automatically the parameters of the analysing window used for building the current spectrogram, at each point of the time–frequency plane, with the computational cost of a conventional, non-optimized spectrogram. It is based on the definition of a large dictionary of different chirplet windows, which are combined into a single, complex time window. A single short time Fourier transform with this new window generates in parallel the spectrograms of all the dictionary windows, and the LOCS chooses among them the locally optimized values in an automatic way. The proposed technique is applied to the diagnosis of two commercial induction motors with bar breakages and mixed eccentricity faults.

Short Circuit and Broken Rotor Faults Severity Discrimination in Induction Machines Using Non-invasive Optical Fiber Technology

Multiple techniques continue to be simultaneously utilized in the condition monitoring and fault detection of electric machines, as there is still no single technique that provides an all-round solution to fault finding in these machines. Having various machine fault-detection techniques is useful in allowing the ability to combine two or more in a manner that will provide a more comprehensive application-dependent condition-monitoring solution; especially, given the increasing role these machines are expected to play in man’s transition to a more sustainable environment, where many more electric machines will be required. This paper presents a novel non-invasive optical fiber using a stray flux technique for the condition monitoring and fault detection of induction machines. A giant magnetostrictive transducer, made of terfenol-D, was bonded onto a fiber Bragg grating, to form a composite FBG-T sensor, which utilizes the machines’ stray flux to determine the internal condition of the machine. Three machine conditions were investigated: healthy, broken rotor, and short circuit inter-turn fault. A tri-axial auto-data-logging flux meter was used to obtain stray magnetic flux measurements, and the numerical results obtained with LabView were analyzed in MATLAB. The optimal positioning and sensitivity of the FBG-T sensor were found to be transverse and 19.3810 pm/μT, respectively. The experimental results showed that the FBG-T sensor accurately distinguished each of the three machine conditions using a different order of magnitude of Bragg wavelength shifts, with the most severe fault reaching wavelength shifts of hundreds of picometres (pm) compared to the healthy and broken rotor conditions, which were in the low-to-mid-hundred and high-hundred picometre (pm) range, respectively. A fast Fourier transform (FFT) analysis, performed on the measured stray flux, revealed that the spectral content of the stray flux affected the magnetostrictive behavior of the magnetic dipoles of the terfenol-D transducer, which translated into strain on the fiber gratings.

Process monitoring of machining

This keynote paper mainly focuses on advancements of machining technology and systems for enhanced performance, increased system integration and augmented machine intelligence, critically hinging on new sensors, sensor systems and sensing methodologies being robust, reconfigurable and intelligent, while providing direct adoption and plug-and-play use in industrial practice. One chief novelty is given by the key enabling technologies of Industry 4.0 where integration of sensing systems in manufacturing plants is a cornerstone for transforming conventional manufacturing concepts into digital manufacturing paradigms. Application examples to industrial processes, future challenges and coming trends in machining monitoring are shown.

An Unsupervised Noisy Sample Detection Method for Deep Learning-Based Health Status Prediction

Due to rough environment or data-acquisition equipment failure, the machine monitoring data may be contaminated with noise, which may lead to the generation of noisy samples. For the widely used deep learning-based prediction model, some noisy samples (with low-intensity noise) may improve model generalization while some noisy samples (with high-intensity noise) may hamper the prediction models. To detect the noisy samples that hamper the prediction models, an unsupervised noisy sample detection method is proposed, thereby promoting the accuracy of the deep learning-based prediction model. First, the transforming model with an attention mechanism is built to transform the multivariate input sequences of samples to attention weight vectors, which are related to the prediction task. Then, a clustering method without hyperparameters is proposed to cluster these attention weight vectors and the hierarchy of clusters is created. Afterward, the noisy samples that hamper the prediction models are detected and removed based on the clustering thresholds, and a prediction model with higher prediction accuracy can thus be obtained. The effectiveness of the proposed method is verified using a simulated turbofan engine degradation dataset and a real milling machine monitoring dataset. The results show that the prediction errors for the two datasets have been reduced by 13.44% and 12.97% on average after removing the noisy samples detected by the proposed method. The comparison results show that the proposed method outperforms other methods in terms of improving the prediction accuracy.

Smart Data Collection System for Brownfield CNC Milling Machines: A New Benchmark Dataset for Data-Driven Machine Monitoring

Manufacturing processes have undergone tremendous technological progress in recent decades. To meet the agile philosophy in industry, data-driven algorithms need to handle growing complexity, particularly in Computer Numerical Control machining. To enhance the scalability of machine learning in real-world applications, this paper presents a benchmark dataset for process monitoring of brownfield milling machines based on acceleration data. The data is collected from a real-world production plant using a smart data collection system over a two-years period. In this work, the edge-to-cloud setup is presented followed by an extensive description of the different normal and abnormal processes. An analysis of the dataset highlights the challenges of machine learning in industry caused by the environmental and industrial factors. The new dataset is published with this paper and available at: https://github.com/boschresearch/CNC_Machining.

On the Behaviour of an Ac Induction Motor as Sensor for Condition Monitoring of Driven Rotary Machines

On the Behaviour of an Ac Induction Motor as Sensor for Condition Monitoring of Driven Rotary Machines

Optimisation of energy consumption in cloud video surveillance centre based on monitoring and placement of virtual machines

Optimisation of energy consumption in cloud video surveillance centre based on monitoring and placement of virtual machines

An analysis of machine learning algorithms in rotating machines maintenance

The industrial maintenance activities represent an increase in production costs, mainly caused by unnecessary production stops. Recent technologies approaches are handling the continuous monitoring of industrial machines, storing sensors data, and also maintenance history. More data analysis is necessary specifically for rotating machines presenting methodologies to reduce the maintenance. In order to handle this problem, a comparative analysis of machine learning methods is presented. The strategy aims to predict failures and then indicates the maintenance necessity before a break occurs. Thus, it is applied and analyzed the specific machine learning algorithms, Gradient Boosting and Random Forest, using a dataset of rotation machines. The results show that both methods have an excellent performance (metrics accuracy, precision, and recall), with slightly better results in Gradient Boosting (hit rate of 99.93%) indicating the prominent application of these algorithms in this industrial scenario.

Optimisation of energy consumption in cloud video surveillance centre based on monitoring and placement of virtual machines

Cloud computing is one of the most popular computational models, which requires plenty of physical devices where services are provided based on user demand. A majority of data centres need plenty of energy consumption which has become a challenge in recent years. Regarding cloud video surveillance - as a contemporary research field of cloud computing and big data, the service, due to the high demand for monitoring remote places, continually consumes surplus energy to process the high-volume data. This study considers the importance of energy consumption in cloud video surveillance, and it has been tried to increase the efficiency of servers concerning energy usage. The proposed method employs virtual machine placement in two steps, including monitoring and placement, to reduce energy consumption and increase the efficiency of servers. Implementation results in Cloudsim showed that it reduces energy consumption and increases resource efficiency.

Motor Current Based Misalignment Diagnosis on Linear Axes with Short- Time Fourier Transform (STFT)

Machines and their components wear down over the course of time. A cause for increased wear can be misalignment issues that stay undetected and cause follow-up damages. Therefore, online monitoring of machines in the industry is of great importance. In this study, the axial misalignment occurring in different dimensions is determined. For this, a time frequency-based Short Time Fourier Transform (STFT) signal processing algorithm is used. The aim of the study is to diagnose faults without using sensors and external data collection systems, but rather by capturing motor current data from the servo motor of the machine.