Machine Condition Research Articles

Теоретико-методичні засади підвищення ефективності використання парку машин в регіональних транспортних системах та підприємствах на основі лізингових відносин

This work examines the problem of technical and economic efficiency of purchasing new transport vehicles by motor vehicle enterprises of the region by purchase and with the help of leasing relations in order to increase their productivity and efficiency. It is shown that there is a need to create the theoretical and methodological foundations of the leasing of transport vehicles, as one of the ways to re-equip the system of vehicles in the regions of Ukraine and increase the efficiency of their use on the basis of leasing relations. It is substantiated that when developing the foundations, it is expedient to base the system on improving the technical condition of machines with the appropriate strategy of their maintenance and repair. A structural diagram of the system of transport vehicles of the region and motor transport enterprises, which have a modular structure of rolling stock, was built. The main tasks in the development of issues of new leasing relations are outlined. When determining the number of leasing objects, the matrix of the system of technical effects of operations was used, according to the strategy of maintenance and repair of transport vehicles. When creating the theoretical and methodological foundations of the technical and economic efficiency of leasing, the costs for the implementation of maintenance and repair operations of transport vehicles were considered. It is noted that when leasing, it is important to assess the technical condition of transport vehicles by diagnosing them. The work defines the conditions under which it is expedient to develop leasing relations and when motor vehicle enterprises simply buy new vehicles. The sequence of the assessment of the corresponding costs is shown.

MODERN TRENDS IN TECHNICAL CONDITION MONITORING SYSTEMS OF HYDRAULIC DRIVES IN AGRICULTURAL MACHINERY

Increasing technical complexity of hydraulic systems in modern agricultural machines causes a low level of their maintainability in the domestic agro-industrial complex. In order to avoid unforeseen financial costs associated with equipment downtime due to emergency failures of their hydraulic drives, there is a need to identify the prerequisites for their efficiency loss in advance by using effective methods and means of monitoring the technical condition of machines in operation. The aim of the article is to analyse the applicability of methods for monitoring the technical condition of hydraulic drives in agricultural machinery and to substantiate the prospects for their improvement, in accordance with the level of modern information technology development and the conditions of the material and technical base of the domestic agro-industrial complex. To achieve this goal, a structural, logical, and comparative analysis of materials from periodicals and electronic information sources on the relevant topics was conducted. The article considers the known methods for diagnosing hydraulic drives and trends in improving the means of monitoring the technical condition through information technology. The study showed that the methods of the non-destructive testing group are the most applicable in conditions of weak material and technical base. Among the existing methods aimed at improving the process of monitoring the technical condition of agricultural machinery are remote diagnostic systems that combine the diagnostic parameters reading and their remote processing on electronic computers. Currently, artificial neural networks are being actively developed, which are finding their way into the monitoring hydraulic drive technical condition and can significantly improve the overall level of the planned preventive maintenance system.

A 2-D Fiber Bragg Grating Acceleration Sensor Based on Circular Flexure Hinges Structure

This work proposes and experimentally validates a 2D low- and medium-frequency fiber Bragg grating (FBG) acceleration sensor. The investigation of the vibration sensor uses a symmetrical circular flexure hinge structure with similar sensitivity in both measuring directions. The two FBGs are arranged differently to avoid a temperature impact; the sensitivity is double that of only one FBG fiber. First, the operating theory and theoretical system of the FBG accelerometer were analyzed. Second, the theoretical research and optimization improved the FBG sensor’s design, resonance frequency, and sensitivity. Third, the viability of the optimization findings and the simulation was evaluated using ANSYS software. Finally, the product was created, and the sensor calibration was performed using the simulation results. The theoretical values and experimental findings largely concur. According to performance tests, the resonance frequencies in the x- and y-direction are 440 and 500 Hz, respectively, with a flat frequency range from 20 to 300 Hz. Furthermore, the sensor shows average sensitivities along the two spatial dimensions of 124 and 83 pm/G, respectively. The overall anti-interference between the two measuring directions is less than 6%. This sensor is useful in various applications, including vibration monitoring, machine condition monitoring, and robotics.

Acoustic-Based Machine Condition Monitoring—Methods and Challenges

The traditional means of monitoring the health of industrial systems involves the use of vibration and performance monitoring techniques amongst others. In these approaches, contact-type sensors, such as accelerometer, proximity probe, pressure transducer and temperature transducer, are installed on the machine to monitor its operational health parameters. However, these methods fall short when additional sensors cannot be installed on the machine due to cost, space constraint or sensor reliability concerns. On the other hand, the use of acoustic-based monitoring technique provides an improved alternative, as acoustic sensors (e.g., microphones) can be implemented quickly and cheaply in various scenarios and do not require physical contact with the machine. The collected acoustic signals contain relevant operating health information about the machine; yet they can be sensitive to background noise and changes in machine operating condition. These challenges are being addressed from the industrial applicability perspective for acoustic-based machine condition monitoring. This paper presents the development in methodology for acoustic-based fault diagnostic techniques and highlights the challenges encountered when analyzing sound for machine condition monitoring.

Optimal Squared Wald Statistics-Based Methodology for On-Line Machine Condition Monitoring and Degradation Assessment

Optimal Squared Wald Statistics-Based Methodology for On-Line Machine Condition Monitoring and Degradation Assessment

Update on progress with NDT and CM apprenticeships

The author has previously reported on progress with NDT and CM apprenticeships1. This paper provides an update on progress since 2022. The UK has an ageing skills base and skills shortage particularly in the field of Non-Destructive Testing (NDT) and other Measurement related activities such as Machine Condition Monitoring (CM) and Structural Health Monitoring (SHM). These are vital skills (Often regulated) required across all Industry and Infrastructure. A portfolio of Apprenticeship Standards has been developed in the UK by the UK Institute for Apprenticeships and Technical Education (IfATE). BINDT has sponsored the development of three NDT Apprenticeship Standards. This paper gives an overview of the history, entry requirements, content, duration, funding and deliverables of these three apprenticeships plus an update on the results of Ofqual taking over quality assessment of the scheme.

Sparse Low-Rank Matrix Estimation With Nonconvex Enhancement for Fault Diagnosis of Rolling Bearings

The diagnosis of bearing early fault is significant and fundamental in the machine condition monitoring. The accurate and effective diagnosis is of great importance to avoid further serious accidents. However, existing sparse low-rank (SLR) methods for bearing fault diagnosis suffer from underestimation of amplitude and inaccurate approximation of singular values. Therefore, in this paper, a novel sparse low-rank matrix estimation method with nonconvex enhancement (SLRNE) is proposed, extracting the fault transients from observed noisy signal. Specifically, fault transients have both sparse and low-rank properties in time-frequency domain. Based on this, a SLR optimization model is proposed to simultaneously promote the above two properties via truncated nuclear norm (TNN) and generalized minimax concave (GMC) penalty function. The two nonconvex functions aim to promote low-rank property and sparsity respectively. Then, based on derived convexity conditions of the optimization problem, convex optimization algorithm, alternating direction method of multipliers (ADMM) and forward-and-backward splitting (FBS) algorithm, are applied to obtain global optimal solution. In the iterative algorithm, a weighting strategy is designed for the singular value threshold operator to enhance the effect of fault feature extraction. Simulated and experimental signals verify the effectiveness of SLRNE and contrast experiments verify its superiority.

基于模态试验的揉碎机振动特性分析

Aiming at the problems of large vibrations and noise of a working stalk rubbing machine, this paper took the 9R-60 rubbing machine as the research object and used the B&K modal test system and the vibration test system to analyse the modal and no-load conditions of the whole machine. Through analysing modal test data, it was concluded that the first five natural frequencies of the machine were 95.262 Hz, 144.386 Hz, 288.198 Hz, 313.719 Hz and 326.140 Hz. The results showed that spindle rotation had a more significant effect on the vibration than the feed chain rotation; the maximum vibration acceleration occurred at the small motor frame at a spindle speed of 1700 r·min-1 and a feed chain speed of 0.65 m·s-1, which was 135.539 m·s-2. The distribution of the amplitude statistical characteristics of the vibration signals follows the normal distribution and belongs to the stationary random process. The vibration was a self-excited vibration of the rotating machinery caused by the rotation of the main shaft and a forced vibration excited by the rotation of the same shaft. The research provides a direction for further research on the vibration characteristics of the rubbing machine under load conditions, and provides a theoretical basis for the subsequent vibration reduction design.

Decision Support System for Industry Machine Maintenance Using Weight Product (WP) Method

Machine maintenance management is one of the important aspects in every industry. Implementation of machine maintenance management requires the management of various types of data such as machine age, machine condition and so on. Data management with the help of a decision support system will help improve the effectiveness and efficiency of machine maintenance management. In making the right and correct decisions, it is necessary to have decision support. Without machine maintenance management, it can harm the industry because the machine maintenance schedule cannot be determined optimally, and the costs incurred by repair, maintenance and production cessation activities cannot be determined directly. Therefore, the industry needs a decision support system that is able to improve the efficiency of its machine maintenance management. This research focuses on the design and development of a machine maintenance decision support system application using the weighted product (WP) method. Weighted product (WP) method is one of the multi criteria decision making methods used to determine the final decision by using several criteria. This method can provide a reliable methodology that helps to organize the most optimized result in the presence of many different opportunities, parameters, and constraints. Research method used in this study is the Web Engineering Method. This system is developed by using PHP programming language and MySQL as a database. This system is expected to increase the effectiveness and efficiency of machine maintenance management.

Approximation of blades of radial machines with multiparameter family of smooth surfaces

Purpose. Development of a mathematical model for creating the spatial forms of blade devices of rotating radial dynamic blade machines. Methodology. An approach to the development of a mathematical model of blade profiling of radial dynamic blade machines, as parts of power plants, air-jet engines and fuel component supply systems of rocket engines, has been suggested. The approach is based on a physical model of the working body flow over helical surfaces. Findings. A system of equations for describing the blade of a radial dynamic blade machine of any purpose as a family of smooth surfaces has been obtained. A multi-parameter correction of the shape of the smooth surface of the blade, accounting for the change in geometric data, based on input and output parameters of the blade, has been developed. Based on a review of modern technology samples, possible configurations of the spatial shape of the blade of the radial and radial-axial type, geometric factors affecting the surface of the blade being created are taken into account. The possibility of obtaining a multi-level blade apparatus by changing the conditions of the geometric parameters at the entrance is shown. Originality. As part of the developed approach, in relation to the conditions for ensuring the calculated geometric parameters and the working process conditions of the blade machine, blade machines operating on compressible and non-compressible working bodies are considered. In particular, the possibility is shown of ensuring the construction of the spatial surface of the blade of the impellers of radial blade machines with a wide range of angles of the blades at the entrance and exit using smooth surfaces. Practical value. The use of a developed mathematical method allows you to perform the profile of rotating vane devices for radial vane dynamic machines of various purposes, such as centrifugal pumps and compressors, centrifugal radial turbines, as well as diagonal type vane machines. The practical significance of the obtained results is determined by the use of dynamic radial vane machines in aviation and rocket technology, aggregates of the mining industry, and technological devices of chemical industry enterprises.

Pitch and yaw angular speed measurement using Kalman data fusion

Pitch and yaw angular speed measurements are vitally important parameters for monitoring the condition of precision machines. In this letter, we propose a dynamic pitch and yaw angular speed measurement system based on line scan vision. The characteristic line scan image can be considered a discrete time sequence, and each column of pixels represents a different time. A double light-spot centroid and double Gaussian fitting algorithm are developed to obtain the centroid coordinates. Kalman data fusion is employed to enhance the accuracy of the obtained measurement results. The experimental results prove that the proposed method is effective and highly accuracy.

Modified multi-scale symbolic dynamic entropy and fuzzy broad learning-based fast fault diagnosis of railway point machines

Abstract Railway point machine (RPM) condition monitoring has attracted engineers’ attention for safe train operation and accident prevention. To realize the fast and accurate fault diagnosis of RPMs, this paper proposes a method based on entropy measurement and broad learning system (BLS). Firstly, the modified multi-scale symbolic dynamic entropy (MMSDE) module extracts dynamic characteristics from the collected acoustic signals as entropy features. Then, the fuzzy BLS takes the above entropy features as input to complete model training. Fuzzy BLS introduces the Takagi-Sugeno fuzzy system into BLS, which improves the model’s classification performance while considering computational speed. Experimental results indicate that the proposed method significantly reduces the running time while maintaining high accuracy.

Autonomous Maintenance: A Case Study on Step – 0 to 3 Implementation at Detergent Packing Machine in FMCG industry

Businesses in the Fast-Moving Consumer Goods (FMCG) sector always work to improve the efficiency of their manufacturing processes in order to keep a competitive edge in the fast-paced and cutthroat business. With a focus on the detergent packing machine at an FMCG manufacturing plant, this case study explores the application of autonomous maintenance (AM), a key component of the Total Productive Maintenance (TPM) philosophy. Finding and removing losses from the manufacturing process, especially those involving equipment and plant, is the main goal of AM. The four main phases of the step-by-step process described in the AM technique are Step0, Step1, Step2, and Step3, each of which aims to restore the fundamental machine conditions. The AM process's cornerstone, Step 0, emphasizes the necessity of a change in the maintenance staff's perspective. In this level, operators and maintenance teams would discover the value of autonomous maintenance and be instilled with a sense of ownership and responsibility for the equipment. The emphasis switches to cleaning and inspection tasks in Step 1. The detergent packing machine is thoroughly cleaned and carefully inspected to look for any indications of wear and tear or possible problems. This stage lays the groundwork for future enhancements by attempting to create a baseline for the machine's current state. The second step is to establish performance and cleanliness standards for the machine. For regular cleaning and inspections, standardized protocols are created to provide uniformity and predictability in maintenance tasks. In order to improve operators' and maintenance personnel's abilities to recognize and handle possible problems, this stage also includes training courses for them. Step 3 focuses on maintaining the progress made in the preceding steps. It entails creating an organizational culture of proactive maintenance where the idea of continuous improvement permeates every aspect of the business. To make sure that the set standards are being followed and that any deviations are quickly corrected, audits and reviews are carried out on a regular basis. This case study demonstrates the effective use of autonomous maintenance at the detergent packing machine in the FMCG sector by carefully following these four guidelines. The outcomes include a significant reduction in costly breakdowns, improved machine reliability, and the cultivation of a culture of continuous improvement, contributing to the overall competitiveness of the company's products. The lessons learned from this case study can serve as valuable insights for other companies looking to embark on a similar journey of enhancing their manufacturing processes through Autonomous Maintenance.

Fault diagnosis in rotors using adaptive neuro-fuzzy inference systems

Condition monitoring of rotor dynamic systems is emerging research in recent years. The proposed research is a condition monitoring methodology based on Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to detect the open cracks in the single disk rotor-bearing system. Condition monitoring systems generally requires a large amount of processed data for a specific output. The proposed methodology uses the same input data to train two different ANFIS without compromising on the accuracy of the results. The response of rotor-bearing system is generated by using finite element model analysis and harmonic balance method. All simulations are programed in MATLAB programing software. The effects of open groove or wedge cracks (notch crack) on natural frequency and resultant operational response (nodal deflections) of rotor-bearing systems are analyzed. Response orbit at 3× resonance of first natural frequency is analyzed to diagnose the crack in rotor shaft. Resultant operational response (Absolute response due to crack) is recorded for various crack locations and crack depths. Continuous Wavelet Transforms (CWT) are used, to extract the features from operational deflection shape (from operational response) to detect the crack location and their severity (depth). Location of maximum CWT coefficients provides the close vicinity of crack and their magnitude provides the severity of crack. Crack as small as 1% of crack depth to diameter ratio can be identified by CWT. ANFIS are used as a machine condition monitoring methodology to diagnose the crack and predict the crack parameters (crack location and depth). Two Parallel ANFIS are trained to predict the crack parameters. ANFIS-1 is trained for crack location and ANFIS-2 is trained for crack depth. CWT coefficients, maximum response amplitude at the vicinity of crack, and first three natural frequencies are provided as input to both ANFIS-1 and ANFIS-2 for training. The trained condition monitoring methodology accurately detects (predict) the crack location (ANFIS-1) and crack depth (ANFIS-2) with root mean squared error of 0.0833 and 0.137916 respectively.

New statistical learning perspective for design of a physically interpretable prototypical neural network for machine condition monitoring

Deep and shallow neural networks have lots of weights and hyper-parameters to make them magical and mysterious and their applications for machine condition monitoring appear in exponentially growing publications. In the domain of machine condition monitoring, it is a good time to rethink one critical question existing in state of art neural networks. How to construct a prototypical neural network and physically interpret its weights and correlate them with physically interpretable fault features to support machine health conditions identified from the prototypical neural network? This short communication starts with a statistical learning perspective to artificially design a physically interpretable prototypical neural network that has an exactly same structure with a standard one-hidden-layer neural network. Subsequently, it is shown that weights of the physically interpretable prototypical neural network are highly correlated with fault characteristic frequencies and informative frequency bands. Following, this short communication timely answers the aforementioned question and hopes to motivate readers to specifically design more unique and powerful neural networks for physical condition monitoring and classifications to enrich the domain of machine condition monitoring. Simultaneously, this short communication highlights an essential difference between machine learning algorithms in the domain of machine condition monitoring and those in other domains is that physically interpretable weights are necessary fault features in the domain of machine condition monitoring to scientifically support machine health conditions identified from neural networks.

APPLICATION OF TRIBOTECHNICAL DIAGNOSTIC METHODS IN CASE OF DETERMINATION OF COEFFICIENT OF OPERATIONAL RELIABILITY OF MACHINE TOOLS

The submitted paper analyses the check of operational capacity and of economic efficiency of the selected machines in case of the use of different types of oil, determination of mode of friction and of machine wear and specification of interval of oil change. The object of the paper is a machine park in the industrial company comprising of five machine tools. Particularly, it is the case of two grinding machines, two lathes and one milling cutter. Having been removed from the greasing systems, the oils were used to gain information on technical condition of the respective machines.

Automatic Risk Assessment for an Industrial Asset Using Unsupervised and Supervised Learning

Monitoring the condition of industrial equipment is fundamental to avoid failures and maximize uptime. The present work used supervised and unsupervised learning methods to create models for predicting the condition of an industrial machine. The main objective was to determine when the asset was either in its nominal operation or working outside this zone, thus being at risk of failure or sub-optimal operation. The results showed that it is possible to classify the machine state using artificial neural networks. K-means clustering and PCA methods showed that three states, chosen through the Elbow Method, cover almost all the variance of the data under study. Knowing the importance that the quality of the lubricants has in the functioning and classification of the state of machines, a lubricant classification algorithm was developed using Neural Networks. The lubricant classifier results were 98% accurate compared to human expert classifications. The main gap identified in the research is that the found classification works only carried out classifications of present, short-term, or mid-term failures. To close this gap, the work presented in this paper conducts a long-term classification.

Study on Excavation Damage Characteristics of Surrounding Rock in Deeply Buried Tunnels by Particle Flow Code Simulation

This study is aimed at investigating the excavation damage characteristics of surrounding rock in Jinping deeply buried marble tunnels, China. According to the acoustic detection results of tunnel cross-sections under the condition of tunnel boring machine (TBM) obtained on site, the PFC microscopic parameters of Types II/III tunnel marble were simulated and calibrated through the PFC2D program. In doing so, the excavation damage characteristics of surrounding rock of deeply-buried sections in Jinping diversion tunnels were simulated. The results reveal that the excavation damage zones (EDZ) of surrounding rock of Types II/III marble sections in Jinping tunnels are unevenly distributed around the tunnels; the largest zone is located from the top arch to the north arch shoulder. The EDZ depth and damage degree of surrounding rock rise with the increase in buried depth, and they also increase with the decrease in rock quality. Generally, the maximum damage depth of Type III surrounding rock is about 1.0 m larger than that of Type II surrounding rock under the same buried depth, which is basically consistent with the detection results of the relaxation depth of surrounding rock. The simulation well discloses the excavation damage characteristics of surrounding rock in Jinping deeply buried tunnels.

Determining RUL Predictive Maintenance on Aircraft Engines Using GRU

Prognostic and health management (PHM) in the aviation industry is expanding because of its effect on economic and human safety. Advanced maintenance shall be applied to this industry to inform aircraft engine conditions. PdM (Predictive Maintenance) is an advanced maintenance technique that can be applied to the aviation industry because of its high-precision prediction. Combining PdM as a technique to calculate the RUL (Remaining Useful Lifetime ) and ML (Machine Learning) as a tool to make high-accuracy predictions is mixed together that accurately forecasts the state of aircraft machine condition and on the best time to get the maintenance or service. In this work, we use the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) data set. This work proposes GRU to determine RUL on aircraft engines to implement a Predictive maintenance strategy. For the training parameters tested in this study, we used a batch size of 512, a learning rate with Adam optimizer of 0.001, then epochs of 200. The essence of the results of this experiment is to obtain a new method with a simpler calculation process and the epoch value and a faster prediction process compared to other methods used, and the results obtained can approach the original value from an economic point of view and the RUL prediction process using the GRU.

Modelling, Temperature Analysis, and Mechanical Properties of Friction Stir Welding of Al-Cu Joints with Hardened OHNS Steel Tools

Friction stir welding (FSW) is a nearly modern welding method with vital advantages over the conventional welding process, such as lower distortion, enhanced mechanical properties, and eco- friendly. In FSW, the joint characteristics mainly depend on heat development during the joining process due to its solid-state joining method. The basic principles of thermomechanical methods during FSW are unknown since it is a new metal joining method. In this investigation, the 2D and 3D models of the tools with different pin forms were designed using SOLIDWORKS. The ANSYS software was used to investigate the temperature distributions near the weld zones. The fixture was designed and made according to the machine conditions. The base plates used were AA6101 and C11000; the tool material used was the Hardened OHNS steel tool with square and circular pin form. The temperature values were measured in each trial while joining of Al-Cu base plates along the weld line. The results reveal that in the joint area, a trial with high temperature leads to high ultimate tensile strength (UTS) and Charpy impact strength (CIS). Made at tool rotation speed 1200 rpm and feed velocity 20 mm/min of Hardened OHNS steel tool with circular pin form. The obtained UTS value at joints was less than that of Al and Cu base plates. The microhardness value detected at the joint area was higher than the Al and Cu base plates, providing high strength, and irregularly dispersed.