Condition Of Ropes Research Articles

Comparative Analysis of the Performance of Artificial Neural Networks in Assessing the Technical Condition of Steel Ropes

Introduction. Currently, artificial neural networks (ANN) are successfully used for technical diagnostics of steel ropes. Expensive software products with an adapted neural network implementation environment, such as STATISTICA, Amygdala, MatLab Simulink, are often used for this purpose. The most affordable way to build and train an ANN, from a financial point of view, is to write your own program code using interactive libraries such as TensorFlow, PyTorch, Scikit-learn. However, such libraries are not fully adapted for building an ANN, and to use them you need to have basic programming skills. As a result, the quality of an ANN depends not only on its architecture, training data, and composition, but also on the environment in which it is built. The aim of the work was to compare the quality of the ANN, built and trained by various methods according to the criterion of test network performance, confidence levels for assessing the technical condition of the rope, as well as the complexity and speed of training. For this purpose, new software has been developed to solve the problem of assessing the technical condition of a steel rope using a combination of various rejection indicators. Materials and Methods. The basis for an ANN training was a statistical database of typical damages of steel ropes and, an expert assessment of the technical condition of steel ropes. The software was written in the Python programming language. Various methods of programming a neural network were presented: an ANN built on the basis of the STATISTICA software package and an ANN built using the interactive Scikit-learn library. Ten test samples were prepared to verify the operation of the ANN. The ANN quality was assessed based on the test network performance and confidence probabilities (activation levels of the “winning” neuron) of determining the technical condition of the rope. Results. The construction of the ANN using the interactive library Scikit-learn showed a relatively high complexity of construction and a relatively low learning rate of the ANN. Test performance of the network, with a test sample size of ten, turned out to be the same for both built ANNs. At the same time, there was a difference in the indicator of the average confidence level for determining the technical condition of a steel rope between the results of the ANN built on the basis of the STATISTICA software package and the ANN built using the Scikit-learn interactive library. Discussion and Conclusion. The results showed that the ANN built using the STATISTICA software package with the same architecture and network learning parameters had more optimal software algorithms according to the criteria of confidence probability and network learning speed in comparison with the ANN built using the free Skicit-learn library. However, the indicator of the ANN test performance turned out to be the same for both ANNs. This result justified the use of TensorFlow, PyTorch, and Skicit-learn libraries by the world's leading research and commercial centers in the field of artificial intelligence. The obtained scientific result allows us to numerically evaluate and compare the quality of an ANN having the same architecture and learning parameters, but built using different methods. This will be useful for future scientific research in the field and for selecting the optimal environment for constructing ANNs in industrial applications.

Adaptive Threshold and Weighted Frequency Domain Histogram of Local Binary Patterns

Wire ropes are crucial load-bearing components in mining conveyance equipment, and machine vision is one of the methods used to assess the surface damage condition of wire ropes. In response to the light-sensitive nature of local binary patterns, which leads to issues such as differing feature values for similar textures and susceptibility to the influence of excessively large or small pixels within local windows, hindering the accurate reflection of window structure information and exacerbating the introduction of considerable feature noise, an investigation is conducted. To enhance the gradient structural information among pixels within local pixel window, an adaptive threshold binary pattern feature operator is proposed. This operator utilizes the mean and variance within the local window to balance the central pixel value, thereby enhancing the interconnection among neighboring pixels. To perform feature selection on block histograms, a block-weighted approach is employed. This approach utilizes the concept of block weighting and employs correlation coefficients to preprocess feature vectors, thereby enhancing classification accuracy. The algorithm experiments were conducted on a dataset of mine wire ropes. The results indicate that the improved local binary pattern significantly enhances the classification accuracy of the wire rope dataset, achieving an accuracy of 97.3%.

Integral Risk Assessment in Steel Ropes Diagnostics Using Computer Vision

Introduction. Currently, the technical condition of ropes of cable-working machines is evaluated periodically according to regulatory documentation. At the same time, methods of visual and instrumental control are used, which depend on the skills and physical capabilities (vision) of the personnel performing the work. There is no unified system of continuous assessment of the technical condition based on a set of factors that does not depend on the human factor. As a result, emergencies occur even when all routine maintenance is carried out on time. To correct this situation, it is proposed to use a computer vision system and neural networks, which allows determining its suitability for further operation by risk levels based on the totality of detected and identified defects, with the interpretation of their results in the color scheme: green — acceptable, yellow — increased, red — high. The work objective is to propose an integral method for risk assessment of operating machines with rope traction when defects and their combinations are detected in a steel rope using computer vision while excluding the influence of the human factor. Materials and Methods. Training of the neural network was carried out on the basis of statistical data of defects obtained from the results of technical inspections of machines with rope traction, on sections of the rope, multiples of its six and thirty nominal diameters according to GOST 33 718. Indexing of risks in the color scheme was carried out according to GOST 55 234.3 to develop a strategy for steel ropes maintenance. A certificate of registration of a computer program was obtained for the neural network program code. The neural network processes visual and measurement control data based on computer vision. Results. An integrated risk assessment system has been created for the diagnosis of steel ropes using computer vision, which allows you to detect defects in steel ropes timely, assess the existing risk of further operation and give recommendations to specialists of operating organizations in real time. This will dramatically reduce the risk of accidents, injury and death of people at facilities using steel ropes. Discussion and Conclusion. The proposed integrated risk assessment system can be applied in any facility that uses rope traction. These are elevators for various purposes, funiculars, cable cars, cranes and many other machines. It should be noted that the estimated commercial cost of the system is low; therefore, the system is available to a wide range of consumers.

Analysis of the operation of the electrical current supply scheme to two cables of a multilayer wire rope

Purpose. Regular inspection of cables on cable-stayed bridges is key to ensuring the safety of people's lives. However, the detection signals are usually complicated by the interwoven structures of the ropes, which cause the rope defect signal and the strand signal to be mixed. To ensure the working capacity of the wire rope, it is necessary to regularly check the integrity of the cables. Research methodology. Analytical methods of observations and mathematical and statistical data processing are used in the work; system analysis when developing criteria for assessing the actual technical condition of wire ropes; the method of mathematical modeling in the development of prognostic models of cable breaks. Research results. The paper analyzes the cable rope control system when changing the parameters of the lengths of the electric current applied to two cables, and shows the nature of the distribution when the number of the damaged cable is changed to another. The obtained results demonstrate the necessity of using this method of input, because the system clearly works in different cases. Scientific novelty. The automatic cable break detection system with the function of determining the place of damage allows in automatic mode during the operation of a lifting machine equipped with a flat rubber rope to monitor the technical condition of the cables vulcanized in a rubber shell and to stop the machine in the event of a break of any cable. The change in the electric voltage between the ends of the twisted cable depends on the length of the rope as follows: with a rope length of 10 m - the potential difference does not exceed 7V, and at 100 m - 106, at 300 m - 1015 proportionally depends on the square root and the product of the electrical resistance of the cable and the specific conductivity of rubber layers of rope. Practical value. The introduction of an automatic control system will make it possible to quickly make decisions aimed at eliminating damage to flat single-layer and cable-stayed multi-layer ropes, stop the "development" of damage, reduce time spent on restoring the working condition of the lifting machine, and most importantly - increase its reliability and safety of operation.

Оперативная оценка технического состояния стальных канатов по данным магнитной дефектоскопии

A combined approach to the prompt analysis of technical condition of steel wire ropes of various functions is proposed. It is based on the bearing capacity (strength) criterion and the magnetic testing results. The principals are stated related to the strength assessment of degraded rope with measured local wire breaks and loss of metallic area due to corrosion (abrasion). After processing the received diagnostic charts the strength analysis is performed by means of appropriate mechanical model in terms of weak element hypotheses used in structure mechanics. Stress analysis gives the conservative strength estimates which will be referred to reliability margin. The stress safety factor is evaluated regarding the steady and cyclic loading. Because the measured data are of random nature and do not account for the distribution of faults at cross-section the statistical modeling of wear location over wires is performed. The total strength decrease is determined by superposition of strength reduction due to metallic area loss, and due to the wire breaks. Thus, the stress safety factor is considered as a probabilistic indicator of the state of the rope strength. The rope in service should be discarded if its stress safety factor becomes less than the empirical allowable strength factor which defines the rope margin of survival capability as a partially worn-out structure. Adjusted for regulatory disposal rules, three categories of worn rope condition are considered: serviceable, with a limited service life, and inoperative. These categories are presented by the green-yellow-red ranges at so-called «rope status map» in specified coordinates «Number of wire breaks — Loss of metallic section». The rope bearing capacity is promptly assessed by placing two mentioned testing data in corresponding position at the status map. An example is given related to the assessment of the status map for the load-carrying cable rod of the well pumping unit. Based on the obtained results the recommendations are formulated for application of the rope status maps as the templates for service personnel concerning further operation.

Контроль канатов при эксплуатации машин с канатной тягой

The methods of rope control during the operation of lifting structures, elevators, freight and passenger cable cars, funiculars and other machines with cable traction are considered. It is indicated that the main indicator of the technical condition of ropes is the appearance, development and interaction of defects that reduce the strength of ropes, contribute to their destruction and, accordingly, an emergency situation. The analysis of existing methods of rope control is carried out, the designs of flaw detectors are described, with the help of which the technical condition of ropes can be assessed during operation. It is established that one of the promising methods of control of steel ropes is optical based on machine vision and artificial intelligence technologies.

Detecting Discontinuities in Steel Wire Ropes of Personal Lifts Based on the Analysis of Their Residual Magnetic Field

Steel wire rope is essential to many rope transport devices. As steel ropes are used, they become damaged, the identification of which is often very difficult or time-consuming. The criteria for retiring steel wire ropes are rigorous—sometimes, ropes that remain fit for further operation are replaced. This article aims to define a novel method of identifying the condition of steel ropes based on their residual magnetic field measurements and their potential use in other industries in the event of damage. This article presents a methodology for detecting discontinuities in steel ropes, which allows for determination of their suitability for further operation. The work uses a rope as a load-bearing element of a personal lift. The initial signal was recorded with a SpinMeter-3D magnetometer. The obtained results were subjected to the extraction of features, the analysis of which allowed identifying the damage. The obtained results enable us to conclude that this procedure is crucial in the context of sustainable development.

Development of a System for Continuous Automatic Monitoring of the Cable Rope Condition

Development of a System for Continuous Automatic Monitoring of the Cable Rope Condition

Condition Classification of Fibre Ropes during Cyclic Bend over Sheave testing Using Machine Learning

Fibre ropes have been shown to be a viable alternative to steel wire rope for offshore lifting operations. Visual inspection remains a common method of fibre rope condition monitoring and has the potential to be further automated by machine learning. This would provide a valuable aid to current inspection frameworks to make more accurate decisions on recertification or retirement of fibre ropes in operational use. Three different machine learning algorithms: decision tree, random forest and support vector machine are compared to classical statistical approaches such as logistic regression, k-nearest neighbours and Naïve-Bayes for condition classification for fibre ropes under cyclic-bend-over-sheave (CBOS) testing. By measuring the rope global elongation throughout the CBOS tests, a binary classification system has been used to label recorded samples as healthy or close to rupture. Predictions are made on one rope through leave-one-out cross validation. The models are then assessed through calculating the accuracy, probability of detection, probability of false alarm and Matthew’s Correlation Coefficient, and ranked based on the results. The results show that both machine learning and classical statistical methods are effective options for condition classification of fibre ropes under CBOS regimes. Typical values for Matthews Correlation Coefficient (MCC) were shown to exceed 0.8 for the best performing methods.

Automated Condition Monitoring with Remaining Lifetime Assessment for Wire Ropes in Ladle Cranes

The hazards and deterioration of operating wire ropes on overhead cranes, which articulate the ladle in the basic oxygen steelmaking process and are subjected to intensive periodic loads and exposure to high temperatures, are discussed. An automated condition monitoring system (ACMS) based on a magnetic flux leakage testing (MFL) flaw detector permanently installed on the rope under test is used. An algorithm of the rope’s residual tensile strength assessment is provided. A specially developed software that submits a decision on the rope’s condition to the crane operator is described. The practice of combining magnetic rope testing (MRT) and tensile strength analysis for the quantitative assessment of rope condition is reviewed. Practical issues are also discussed, such as how to establish the condition monitoring process, set loss thresholds for rope metallic cross-sectional area, and safely prolong the service life of rope.

Steel Rope Diagnostics by Magnetic NDT: From Defect Detection to Automated Condition Monitoring

Today it is hard to imagine an industry or an application that uses steel wire ropes in which the application of a magnetic flaw detector would be unsuitable. The ropes of loading cranes, mine hoists, ropeways, cable-stayed bridges, flare stacks, antenna masts, overhead power transmission lines, and other installations are not only subject to regular inspections (Sukhorukov and Mironenko 2003; Kotelnikov and Sukhorukov 2006; Sukhorukov et al. 2014), but the appropriate guidelines for these rope types are now described in industrial standards such as the International Organization for Standardization (ISO) standard for crane ropes, ISO 4309 (ISO 2017); the European Standards (EN) standard for ropeways, EN 12927 (BSI 2019); and the International Marine Contractors Association (IMCA) standards for offshore ropes, IMCA LR 004, IMCA HSSE 023, and IMCA M 197 Rev.1 (IMCA 2018). This paper examines how magnetic flux leakage testing (MFL) is used as the basis for an automated wire rope condition monitoring system, in which the human factor is completely removed.

Substantiation of research of diagnostic methods for variable section rope

Purpose. The paper analyzes the diagnostic methods for ropes with variable cross-section. The rationale consists in increasing the level of efficiency, safety and identifying a reliable method for monitoring the condition, service life of mine hoisting installations with main rubber-cord ropes. Research methodology. The analytical research method was used when receiving signals arising from a cable break. It was found that certain types of defects in which signals arise and are transmitted to the sensor when the cable breaks. Research results. Based on these results, it was proposed to diagnose the ropes using electrical resistance and develop a device. So, diagnostics consists in applying voltage to the ends of the rope ropes according to the selected schemes and in a given sequence, establishing the magnitude of the current arising in the conductors that are supplied with voltage, analyzing certain currents, providing information about the state of the ropes and, if necessary, stopping the machine. The received signals can be used as diagnostic parameters when monitoring the condition of the rope ropes by a special system for automatic detection of rupture of rubber-rope ropes. Scientific novelty. Improving the safety of lifting machines, in particular elevators, can be achieved by providing continuous and automatic control of the traction of ropes - the integrity of their traction elements of the cables. It is known that the control system works with the formulation, transmission and processing of the signal. The dependences of the resistance value as a diagnostic parameter of the system for monitoring the state of the main rubber-cord rope, during operation on a mine hoist, have been clarified, which make it possible to determine the currents arising in the ropes at the points of supply of the potential difference for a rope with intact ropes and in case of damage and automatically monitor the integrity of the rope base of the rope, than to increase the safety of operation of mine hoisting complexes. Practical value. The effective norms of exploitation of rubber cord hoisting ropes have been determined; the parameters of the control system for diagnostics of integrity have been substantiated and methods for monitoring the technical condition of ropes have been developed, protected by patents for invention.

Diagnostics of operational wear in hybrid load-carrying cables

Along with the development of lifting devices, the new hybrid load-carrying cables were introduced to the market. The solutions of this type covered both, steel ropes of circular section and belts being a hybrid combination of many steel ropes potted with plastic coating into a single flat friction belt. Such design of ropes as compared to the traditional round steel ropes enabled to reduce the drive wheel diameter while maintaining frictional contact conditions and required ratio of the drive wheel and load-carrying cable diameters that is at least 40. Despite the above-mentioned advantages, a research issue that is of interest but so far has not been fully investigated is the process of wear of the hybrid load-carrying cables and evaluation of the technical condition of ropes being the load-carrying elements in the applied solutions, especially during the long-term operation. This article presents the possibilities of applying the magnetic method for evaluation of the technical condition of steel ropes being the load-carrying element of hybrid belts. The authors have presented their solution of the measuring head for magnetic testing of the load-carrying hybrid cables, elaborated by the team of employees of the Department of Machine Engineering and Transport at University of Science and Technology in Cracow, that enables the quantitative assessment of the hybrid load-carrying cable wear.

Convolutional Autoencoder-Based Flaw Detection for Steel Wire Ropes.

Visual perception-based methods are a promising means of capturing the surface damage state of wire ropes and hence provide a potential way to monitor the condition of wire ropes. Previous methods mainly concentrated on the handcrafted feature-based flaw representation, and a classifier was constructed to realize fault recognition. However, appearances of outdoor wire ropes are seriously affected by noises like lubricating oil, dust, and light. In addition, in real applications, it is difficult to prepare a sufficient amount of flaw data to train a fault classifier. In the context of these issues, this study proposes a new flaw detection method based on the convolutional denoising autoencoder (CDAE) and Isolation Forest (iForest). CDAE is first trained by using an image reconstruction loss. Then, it is finetuned to minimize a cost function that penalizes the iForest-based flaw score difference between normal data and flaw data. Real hauling rope images of mine cableways were used to test the effectiveness and advantages of the newly developed method. Comparisons of various methods showed the CDAE-iForest method performed better in discriminative feature learning and flaw isolation with a small amount of flaw training data.

Nondestructive Evaluation of Track and Haulage Ropes of Aerial Ropeway Installation in India—A Case Study

The wire ropes in steel material are generally used in harbours, on ships, haulage applications in mine winders, aerial ropeway carrying, haulage/track ropes for transportation of passengers and in many industrial fields. The properties of high axial strength and flexibility in bending, convert wire ropes into imperative load transmission components for many industrial applications. The exhaustive usage of these ropes deteriorates with its use over the course of period. The conduct of wire rope inspection has make one’s way expeditiously over the past few decades. To perform nondestructive tests of rope is a way how to analyse the real condition of ropes during their running operation. It became very necessary to evaluate ropes during their live condition in the interest to facilitate substitution of the rope in stipulated period and also for strengthening risk-free duration of working when discard requirements failed to attained. Available magnetic rope flaw detectors are now became much easier to set off and yield a paramount component of steel wire ropes verification or evaluation. The results of tests from these equipment’s capable of providing certain appraises of safety concern regarding steel wire rope parameters such as loss of metallic cross-sectional area and localised faults. It also provides further accurate baseline in establishing the state and rest duty period of a wire rope. A conducted research result depicts the level and the wide range of flaws, distribution pattern of localized defects such as concentrated or dispersive broken wires. This technical paper on nondestructive evaluation work being sponsored by Indian industry, illustrates the method of nondestructive testing applied and analysis of condition of haulage and track ropes including safety recommendations for further continuance in service.

Computer vision and thermal monitoring of HMPE fibre rope condition during CBOS testing

Fibre rope usage in deep sea lifting operations is gaining more prominence in recent times. With rope minimum break loads (MBL) comparable to that of their steel wire counterparts, the use of high modulus polyethylene (HMPE) ropes is seen as a viable option for use in subsea construction cranes. The ropes are worn out during use and visual inspection remains one of the main methods of determining whether a fibre rope is to be retired from use, therefore a natural extension is condition monitoring through computer vision. Creep and temperature are constraining with HMPE ropes and should be monitored continuously, particularly when the rope is cyclically bent over sheaves. Additionally, interpreting the thermal history of the rope during use could give insight into deterioration. In this paper, a condition monitoring system based on combined computer vision and thermal monitoring is used during cyclic bend over sheave tests performed on 560 kN break load of 12 strand braided HMPE ropes. New monitoring features such as local length and width through computer vision algorithms combined with surface thermal monitoring and global elongation are presented and their effectiveness as condition monitoring features is assessed.

Performance Evaluation of 42 mm Diameter Stranded Ungalvanised Haulage Rope in a Mono-Cable Passenger Ropeway

Most common conventional method of rope condition evaluation is visual method i.e. watching the exterior strand and outer surface only. Core damage cannot be detected. To assess the rope condition, magnetic nondestructive method is the most suitable method. Periodic rope assessment is necessary to prevent rope failures and extension of rope life. Flaw detectors in the Magnetic Rope Tester detect LMA (loss in metallic area) and LF (localized faults) [1, 2]. This paper describes the performance of a haulage rope in two years.

Анализ эксплуатационной надежности грузовых канатов заливочных кранов сталеплавильного производства

When performing technological operations of casting the cast iron into the converter, the steel ropes of bridge casting cranes in steelmaking workshops are subjected to cyclic power and high-intensity thermal loading. These operational factors lead to a decrease in the load-bearing capacity of the cargo ropes. Corrosion and abrasive wear of the ropes is accompanied by the change in the mechanical characteristics of the wires metal as a result of thermal cycling. Therefore, monitoring the current technical condition of cargo ropes is of great importance for ensuring filling cranes safe operation. Therefore, monitoring the current technical condition of cargo ropes is of great importance for ensuring hot-metal cranes safe operation. The article reflects the results of laboratory experiments and field tests concerning the study of the operating factors influence on the performance of the ropes of the hot-metal cranes of the converter steelmaking shop at PAO Severstal. Recommendations are given on the organization of monitoring, correction of the limit value of the allowable loss of cross-section for metal and the extension of the standard service life of cargo ropes of the mechanisms of the main lifting for filling cranes.

Мониторинг состояния стальных канатов автоматизированными средствами технического диагностирования

Technical condition of steel ropes in the scope of various technical and lifting devices plays an important role in ensuring safety of these objects. To ensure safe operation of lifting devices, more than 30 years ago the uniform norms for rope rejection were developed and put into practice based on their inspection using different non-destructive testing methods. At the same time, for safe operation of various technical and lifting devices it is required to provide automation of processes for monitoring of steel ropes technical condition over a certain period of time. The need for such control is caused by the necessity to create the ropes monitoring system with the development of appropriate non-destructive testing devices, methods, substantiations, data processing systems and their transmission to the control center. Monitoring of ropes with automated non-destructive testing means creates the conditions for improving safety of operation of the drilling rigs, mine hoists, hot-metal crane of the metallurgical plants and other hazardous objects. At the same time, a significant economic effect arises due to a more complete use of the rope service life, elimination of the temporary shut-down of the technological process for its technical control, and the reduction in the number of the qualified personnel for conducting non-destructive testing. Creation of the automated means of non-destructive testing for rope monitoring is impossible without ensuring high reliability of the equipment in the difficult operating conditions, developing specialized software, as well as solving other important tasks. As an example, the automated magnetic flaw detector INTROS-AUTO and the experience of its application in various hazardous objects are considered. The timeliness of creating the regulatory-technical base for monitoring and automated diagnostics of steel ropes is shown.

Effects of the vortex rope dynamic characteristics on the swirling flow in the draft tube cone

As the Francis turbine operated at the off-design conditions, the hydraulic instability may occurs due to the vortex rope developed in the draft tube. The swirling flow produced at the blade trailing edge has been proved to have a direct effect on the vortex rope characteristics. Research on the swirling flow is meaningful for understanding the hydraulic instability mechanisms. In this paper, the different swirling flow characteristics at part load and overload conditions were studied by numerical method. The relations between the vortex rope dynamic characteristics and the swirling flows were deeply investigated. The results showed the swirl number, which was chosen to stand for the strength of the swirling flow, changed with the vortex rope evolution. The swirl number fluctuations and its frequency were closely related to the vortex rope precession and its diameter and length. The dominant frequencies of the swirling flow in spiral vortex rope flow field were consistent with the vortex rope. However, the swirl number frequency turned out to be the vortex rope harmonic frequencies in the columnar vortex rope condition. Besides, the propagation laws of the swirling flow in the draft tube cone were also different in the different vortex rope flow fields.