Machining Operations Research Articles

Analysis of the influence of uneveneity of the sintering process of the barch on the operation of the sintering machine

Literature data on the unevenness of temperature and composition of the gas leaving the sintering bed across the width and length of it and their influence on the productivity of sinter machines are considered. An analysis of the technologies reasons for the unevenness of the sintering process was carried out. It is shown that the reasons for the width of the pallets include the distribution of the mix bed in the loading bin, air leaks into the ignition hearth, the wall effect at the side plates of the pallets, the shape and angle of inclination of the sides relative to the grates. Along the length of the sinter machine, the unevenness of gas flow and composition is due to a decrease in the gas-dynamic re-sistance of the bed during the sintering process, segregation of the mix and fuel along the height of the bed, completion of bed drying and gaps between pallets. Using an adapted mathematical model of the sintering process, a comparison was made of the parameters of the basic (non-uniform) and calculated uniform operating modes of the AKM-312 sinter machine of the Steel Plant NLMK. I It has been established that with the vertical installation of the pallet sides accepted in the calculations that an increased gas flow rate at the periphery of the bed is accompanied by an increase in gas temperature with a corresponding decrease in the suction before exhausters. It was found that during the transition from the base to the uniform mode of operation of the sinter machine, the gas temperature in front of the exhausters decreased from 99.6 to 85.1 °C, the suction increased from 13.54 to 14.26 kPa, and in the collecting collector – by 1.15 kPa. The productivity of the sinter machine increased by 4.1%. When installing pallet sides vertically, the effectiveness of increasing the height of the layer on its periphery instead of compacting it and constructive solutions has been justified. Its increase provided an additional productivity of the sinter machine by 1.8%, a total of 5.9%. It has been shown that due to the simultaneous increase in gas temperature over the entire width of the bed in the final period of the sintering process, with a uniform operating mode of the sinter machine, the maximum gas temperature at the end of the process increases with a lower one – in front of the exhausters. From the point of view of the capabilities of exhausters in terms of the created suction, the accepted representation of their gas-dynamic characteristics at a temperature of 150 °C, which is possible only with a high level of unevenness of the sintering process, is not reasoned

Methodology for determining the durability of soil-cultivating machines working bodies of parts

The development and creation of high-performance machines for agricultural production is in many cases limited by the insufficient wear resistance of individual parts and assemblies. Russian scientists, engineers and technicians working on the problem of increasing the durability of machines have achieved significant results. However, theoretical conclusions and prerequisites for increasing durability and the method of calculating parts of agricultural machines for durability are not enough. The durability calculations of agricultural machine parts used in some cases during their design are imperfect. In addition, in most cases, there are no reasonable calculations of allowable wear that would ensure high quality machine operation, i.e. these calculations are not related to the tasks of preventive maintenance and operation of machines. A number of scientists have been studying the abrasive wear of working parts of soil-cultivating and seeding machines for decades, but this issue has not yet been finally resolved. Until now, there is no clear understanding of the essence of abrasive wear and the factors that determine it. Most of the work carried out on the study of abrasive wear of parts of working bodies of soil-cultivating machines is of a private nature. There are no works covering the study of the complex set of phenomena that occur during abrasive wear. At present, very little has been studied about the wear capacity of soils, there is no criterion that determines it, and there is no connection between the phenomena of wear of the working parts of soil-cultivating machines and the basic theoretical principles of agricultural mechanics. The study of the wear capacity of soils, as well as the determination of the magnitude of pressures that arise during the interaction of the working parts of agricultural machines with the soil, can be used when calculating the working parts of these machines for durability.

Matheuristic and learning-oriented multi-objective artificial bee colony algorithm for energy-aware flexible assembly job shop scheduling problem

With the increase of mass customization, flexible job shop scheduling problem considering assembly stage has widely existed in many manufacturing industries, such as die-casting mould factories. This problem is to find a reasonable machine assignment and operation sequence both in fabrication and assembly stages and simultaneously maximize production efficiency. In reality, energy shortages and environmental pollution have given an impetus to the development of energy-aware production scheduling problems. In this study, we address an energy-aware flexible assembly job shop scheduling problem (EFAJSP) with the objectives of minimizing flow time and energy consumption and first develop a mixed-integer linear programming (MILP) model to solve EFAJSP problem. Then, the model-specific characteristics are extracted and applied to a matheuristic decoding method for exploring the Pareto optimal solution. Due to the complexity of EFAJSP problem, a matheuristic and learning-oriented multi-objective artificial bee colony algorithm (MLABC), which combines the advantages of mathematical programming, reinforcement learning and meta-heuristic algorithm, is proposed. In addition, an initialization, destruction/construction operator and population update operator are proposed and work together to improve the exploration and exploitation performance of the proposed MLABC. Finally, numerical experimental results demonstrate the effectiveness of the proposed MILP model and the superiority of the MLABC over other algorithms in the literature.

Selection of the level of vibration signal decomposition and mother wavelets to determine the level of failure severity in spur gearboxes

AbstractSpur gearboxes are an integral component in the operation of rotary machines. Hence, the early determination of the severity level of a failure is crucial. This manuscript delineates a methodology for selecting essential mother wavelets and filters from the wavelet transform (WT) to process the vibration signal within the time‐frequency domain, aiming to ascertain the severity level of failures in spur gearboxes. Initially, information is garnered from the gearbox through vibration signals in the time domain, utilising six accelerometers. Subsequently, the signal is partitioned into various levels, and information from each level is extracted using diverse mother wavelets and their respective filters. The signal is segmented into sub‐bands, from which the condition state is ascertained using an energy operator. After that, the appropriate level of wave decomposition is determined through ANOVA tests and post‐hoc Tukey analyses, evaluating performance in failure classification via the Random Forest (RF) model. Upon establishing the decomposition level, the analysis proceeds to identify which mother wavelets and filters are most suitable for determining the severity level of different types of failure in spur gearboxes. Moreover, this study investigates the impact of sensor positioning and inclination on acquiring the vibration signal. This aspect is explored through factorial ANOVA tests and multiple comparisons of the data derived from the sensors. The RF classification model achieved exceedingly favourable results (accuracy 96% and AUC 98%), with minimal practical influence from the positioning and inclination of a sensor, thereby affirming the proposed methodology's suitability for this type of analysis.

Micro-Grinding Parameter Control of Hard and Brittle Materials Based on Kinematic Analysis of Material Removal

This article explores the intricacies of micro-grinding parameter control for hard and brittle materials, with a specific focus on Zirconia ceramics (ZrO2) and Optical Glass (BK7). Given the increasing demand and application of these materials in various high-precision industries, this study aims to provide a comprehensive kinematic analysis of material removal during the micro-grinding process. According to the grinding parameters selected to be analyzed in this study, the ac-max values are between (9.55 nm ~ 67.58 nm). Theoretical modeling of the grinding force considering the brittle and ductile removal phase, frictional effects, the possibility of grit to cut materials, and grinding conditions is very important in order to control and optimize the surface grinding process. This research introduces novel models for predicting and optimizing micro-grinding forces effectively. The primary objective is to establish a micro-grinding force model that facilitates the easy manipulation of micro-grinding parameters, thereby optimizing the machining process for these challenging materials. Through experimental investigations conducted on Zirconia ceramics, the paper evaluates a mathematical model of the grinding force, highlighting its significance in predicting and controlling the forces involved in micro-grinding. The suggested model underwent thorough testing to assess its validity, revealing an accuracy with average variances of 6.616% for the normal force and 5.752% for the tangential force. Additionally, the study delves into the coefficient of friction within the grinding process, suggesting a novel frictional force model. This model is assessed through a series of experiments on Optical Glass BK7, aiming to accurately characterize the frictional forces at play during grinding. The empirical results obtained from both sets of experiments—on Zirconia ceramics and Optical Glass BK7—substantiate the efficacy of the proposed models. These findings confirm the models’ capability to accurately describe the force dynamics in the micro-grinding of hard and brittle materials. The research not only contributes to the theoretical understanding of micro-grinding processes but also offers practical insights for enhancing the efficiency and effectiveness of machining operations involving hard and brittle materials.

Model-based offline reinforcement learning framework for optimizing tunnel boring machine operation

Research on automation and intelligent operation of tunnel boring machine (TBM) is receiving more and more attention, benefiting from the increasing construction data. However, most studies on TBM operations optimization were trained by the labels of human drivers’ decisions, which were subjective and stochastic. As a result, the control parameters suggested by these models could hardly surpass the performance of a human driver, even the possibility of subjective incorrect decisions. Considering that the geomechanical feedback to TBM under drivers’ actions is objective, in this paper, a transformer-based model called the geological response for tunnel boring machine (GRTBM), is proposed to learn the relationship between operation-adjust and TBM monitoring changes. Additionally, with the model-based offline reinforcement learning, this paper provided a novel approach to optimizing the TBM excavation operations. The decision processes, recorded in the Yin-song TBM project for a waterway tunnel in Jilin Province of China, were used for the validation of the model. By adopting an implicit perception of geological conditions in the GRTBM model, the suggested method achieved the desired state within a single action, greatly outperformed the practical adjustments where 500 s were taken, revealing the fact that the proposed model has the potential to surpass the capability of human beings.

Effect of the Axial Profile of a Ceramic Grinding Wheel on Selected Roughness Parameters of Shaped Surfaces Obtained in the Grinding Process with a Dual-Tool Grinding Head.

The use of CNC equipment that integrates several machining operations eliminates downtime due to changes in setup and clamping of workpieces in more than one machining device. A review of CNC equipment and tools known from the literature and from manufacturers' offerings indicates that new technical solutions are being developed to integrate two or more technological operations. However, these examples have numerous limitations and are mostly not suitable for machining surfaces with complex shapes. An example of such solutions is the use of a dual-tool grinding head, which integrates the process of rough grinding with a ceramic grinding wheel and finish grinding with a flexible grinding wheel. Unfortunately, it has the disadvantage of being limited by the angular shape of the ceramic grinding wheel, making it unable to adapt to the complex geometries of the shaped surfaces being ground. The need to overcome this limitation became the motivation for the research work described in this article. By means of experimental research, it was verified what effect the radial outline on the periphery of a ceramic grinding wheel realized by rough grinding would have on the surface roughness parameters obtained in the process of grinding shaped surfaces. For this purpose, grinding processes using a ceramic wheel with a conical and radial outline were compared. The result of the study was a summary of the surface roughness parameters Sa, St, Sq, Spk, Str, and Sds obtained after two-stage machining (rough and finish grinding). The obtained analysis results showed that changing the axial outline of the ceramic grinding wheel makes it possible to significantly expand the range of applications of the dual-tool head without negatively affecting the quality of the machined surface. Thus, such an improvement will make it possible to increase the applicability of the head by grinding shaped surfaces with a radial profile of curvature.

Three-dimensional DNA nanomachine biosensor coupled with CRISPR Cas12a cascade amplification for ultrasensitive detection of carcinoembryonic antigen.

The detection of carcinoembryonic antigen (CEA) holds significant importance in the early diagnosis of cancer. However, current methods are hindered by limited accessibility and specificity. This study proposes a rapid and convenient Cas12a-based assay for the direct detection of CEA in clinical serum samples, aiming to address these limitations. The protocol involves a rolling machine operation, followed by a 5-min Cas12a-mediated cleavage process. The assay demonstrates the capability to detect human serum with high anti-interference performance and a detection limit as low as 0.2ng/mL. The entire testing procedure can be accomplished in 75min without centrifugation steps, and successfully reduced the limit of detection of traditional DNA walking machine by 50 folds. Overall, the testing procedure can be easily implemented in clinical settings.

An unmanned rice seeder with WiFi based mobile-control system for drudgery reduction

An unmanned rice seeder (URS) with WiFi based wireless communication system was developed to reduce surface seed dispersion, drudgery, human involvement, Occupational health hazards and environmental pollution. An android mobile phone with WIFI connectivity acts as wireless communication system to control the developed URS with operating range of 144.6 m which was surplus for small farms in hilly terrains of Sikkim. The factors of URS are found to be forward speed (Fs) and hopper fill level (HL) w.r.t responses of co-efficient of variation of number of seeds per hill (Cv), Seed rate (Sr), hill spacing uniformity (Us,), missing hill index (MI) and mean hill span (Hs). The optimum results of soil bin study are of Fs and HL of 2.4 km.h−1 and 75% w.r.t responses of Cv, Sr, MI, Us, Hs are 0.28, 18.5 kg. ha−1, 7.3%, 91.7%, and 6.4 cm. Test results showed that the seeding performance of developed seeder was similar to manual drum seeder. But, due to higher speed of operation in developed seeder showed better results in field operation. The results from the field evaluation revealed that URS has increase in field capacity of 41%, reduces labor requirement of 50% than manual rice seeder. In economic evaluation URS has reduced cost of operation (₹ ha−1) of 90% and increase net benefit (₹ year−1), Payback period of 61% and 91% over manual rice seeder (MRS). The operator's workload was decreased by up to 95% due to the machine's mobile operation as compared to the manual operation.

Virtual prototyping of vision-based tactile sensors design for robotic-assisted precision machining

Vision-Based Tactile Sensors (VBTS) play a key role in enhancing the accuracy and efficiency of machining operations in robotic-assisted precision machining systems. Equipped with VBTS, these systems offer contact-based measurements, which are essential in machining accurate components for industries such as aerospace, automotive, medical devices, and electronics. This paper presents a novel approach to virtual prototyping of VBTS, specifically in perpendicularity measurements using Computer-Aided Design (CAD) generation of VBTS designs, Finite Element Analysis (FEA) simulations, and Sim2Real deep learning to achieve VBTS with high precision measurements. The virtual prototyping approach enables an understanding of the contact between VBTS with different designs and machined surfaces in terms of contact module shape, thickness, markers’ density. Additive manufacturing was employed to fabricate the molds of VBTS contact module, followed by experimental validation of the robotic arm to confirm the effectiveness of the optimized VBTS design. The results show that deviation from the hemispherical shape reduces the data quality captured by the camera, hence increasing the prediction errors. Additionally, reducing the thickness of the contact module enhances the precision of perpendicularity measurements. Importantly increasing markers’ distribution density significantly enhances the accuracy of up to 92 markers at which above it the rate of improvement becomes less pronounced. An VBTS with height of 20mm, thickness of 2mm, and 169 markers was found to be within the stringent perpendicularity standards of the aerospace manufacturing industry of 0.58∘ as a root mean square error, and 1.64° as a max absolute error around the roll and pitch axis of rotation. The established virtual prototyping methodology can be transferred to a wide variety of elastomer-based sensors.

Comparative Ergonomic Posture Analysis of CNC Milling Machine Workers through Digital Human Modeling and Artificial Neural Networks

Objectives: To analyze the critical postures of the CNC milling machine operators by RULA (Rapid Upper Limb Assessment) scores and develop an ANN (Artificial Neural Network) prediction model. Methods: The methodology includes a postural analysis of 40 male CNC milling machine operators across Bangladesh, employing both manual (using manual RULA assessment worksheet) and digital (using CATIA V5R21 software) RULA methods complemented by an ANN prediction model. Finally, Digital RULA scores through DHM (Digital Human Modeling) and ANN predicted RULA scores would be compared. Findings: Digital RULA analysis reveals that lifting, carrying, and positioning are the most crucial ergonomic postures, and the most prominent high-risk category limbs are wrist and arm. The overall initial RULA score for lifting, carrying, and positioning are 7, 6, and 7, respectively, and reduced to 3, 3 and 4 respectively for ergonomically designed posture. The ANN model, structured with input, hidden, and output layers of 7, 10, and 1 nodes, significantly refines ergonomic risk prediction by aligning predicted scores closely with actual outcomes during the first stage, emphasized for training. It demonstrates a perfect correlation (R=1) in training, testing, validation, and overall performance for using manual RULA scores. The model's accuracy is further evidenced by minimal prediction offsets across all datasets for digital RULA score in the second stage, with correlation coefficients of 0.87003 (training), 0.93676 (validation), 0.89113 (testing), and (0.88395) for overall. This study contributes significant advancements in ergonomic risk assessment, highlighting the adoption of improved postures to reduce musculoskeletal disorders. Novelty: Employing both manual and DHM methods for RULA score calculation combined with ANN model, which can predict postural risk as floating number and fit a wider range of parameters. Keywords: ANN, CNC, Digital Human Modeling (DHM), Ergonomics, RULA

Self-Adaptive Incremental PCA-Based DBSCAN of Acoustic Features for Anomalous Sound Detection

In modern industry, maintaining continuous machine operations is important for improving production efficiency and reducing costs. Therefore, the smart technology of acoustic monitoring to detect anomalous machine conditions earlier before breakdowns works as part of predictive maintenance and is applied not only in industry fault detection but also in safety monitoring and surveillance systems. This paper proposes a self-adaptive unsupervised machine learning algorithm with dimension-reduction technology to detect anomalous sounds after extracting acoustic machine features. Technically, the automatic EPS calculation algorithm-based genetic algorithm optimizes the automatic clustering algorithm’s configuration for incremental principal component analysis and density-based spatial clustering algorithms with noise. IPCA is enhanced by the sequential Karhunen–Loeve (SKL) algorithm, and the condensation algorithm works as the second layer of the algorithm to reduce the number of effective components. This architecture could select an optimized set of parameters based on different test environments and keeps performance quality with fewer computational requirements. In the experiments, 228 sets of normal sounds and 100 sets of anomaly sounds are used. The sound files are collected from the same machine type (stepper motors) at a real plant site. We compare the proposed algorithm with K-means++, one-class SVM, agglomerative clustering, DCGAN and DCNN-Autoencoder, and this new algorithm performs best, with an AUC of 0.84 and the shortest execution time. The algorithm is generic and can be applied to detect anomalies in machines to provide early warning to people to avoid serious accidents or disasters.

DESIGN AND FABRICATION OF AUTOMATED SIEVE MACHINE

The paper describes the basic model and operation of a smart multifunctional sieving machine. The sieving machine is a multi-layer sieving machine that can be used for a variety of tasks such as sieving sand, eliminating stone from grains, and so on. The size and number of sieves may be adjusted depending on the need. This article covers the idea of the Design and Fabrication of a Multi-purpose Sieving Machine, which was primarily completed for manufacturing-based enterprises. Because of technological innovation, every work in today's world has become faster and faster, and every industry aspires to retain a high production rate while preserving the quality and standard of the product at a low average cost. We created a conceptual idea of a machine that can conduct several tasks concurrently and quickly. In this machine, we drive to the main shaft with a motor that is directly connected to the slider-crank mechanism; the slider-crank mechanism is employed in the sieving operation. With the assistance of a wiper motor, the table is fastened with a crank that rotates the tray to vibrate it and function as a separator. Consequently, the purpose of designing and manufacturing the Sieving Machine is to assist industrialists and farmers on the global market. The benefit is the ability to easily separate objects based on mesh, as well as cost savings linked with power use, an improvement in productivity rate, and the production of less space, among other things. We have further automated this sieving process and can operate the machine via the blynk interface Key Words: Sieving, slider crank mechanism, blynk, multi-purpose, multi-layer, technology, productivity

Fast and accurate Zero-defect manufacturing using collaborative real-time photogrammetry

Abstract. For the machining of industrial components, their accurate alignment on operative machines is a crucial step with significant impacts on the whole process, especially when dealing with large-scale elements. To achieve this alignment, a trained operator is needed along with expensive equipment, such as laser trackers, whose correct use requires the measurements of many significant points and is time-consuming. The lack of a precise alignment comes with possible incorrect parts machining, resulting in quality concerns and potentially expensive rework. To face this problem, collaborative real-time photogrammetry is an effective solution for guiding untrained users in correctly positioning various measured and codified components to generate the best solution for machining high-volume parts. The solution proposed in this contribution is part of the TACCO project, co-financed by EIT Manufacturing (co-funded by the EU). It takes advantage of the TACCO system, where auxiliary components (scale bars, dome-shaped components, coded targets and a cross-reference system) are placed on the object to be measured for their correct positioning in order to obtain an optimal photogrammetric reconstruction. This allows the reduction of the error ellipsoids on several uncoded targets, which are calculated through an iterative simulation carried out in a MATLAB environment. Unskilled operators are then guided through an Augmented Reality headset for their correct placement on the real-world object and for defining the positions and orientations from which to acquire images. This methodology will lead to an accurate measurement of the target points to be machined and, thus, a precise alignment process for the subsequent machining operations.

Experimental Investigation and Optimization of Coaxiality Error Analysis with CNC Turning Process on Delrin for Assembly Fit

This paper mainly deals with the machining operation like turning operation, Material Removal Rate and Surface Roughness are the important parameter which is to be considered for quality product. The material selected for the experiment is DELRIN 500. Turning is one of the important processes that is widely used to create cylindrical components and it is also used for surface finish the product to make it smooth. Nowadays, plastic materials are widely used for making variety of components. To make a component with high dimensional accuracy, turning operation is used. The main concerns of turning are tooling cost and the effect of process on machinability characteristics. It can be seen that the output responses value has a minimum roughness average and a high degree of geometrical quality precision. High degree surface finish is induced by medium speed, feed rate, and small nose radius. The coaxial error was minimized by using medium speed, feed and larger nose radius. Experimentally found that third specimen (RPM -750) (FEED -0.08 mm/Rev) and (NOSE RADIUS 0.8) obtained minimum geometrical error along with minimum Surface roughness. Delrin is a crystalline plastic that offers an excellent balance of properties that bridge the gap between metals and plastics. Delrin possesses high tensile strength, creep resistance and toughness. It also exhibits low moisture absorption

Impact of Cutting Data on Cutting Forces, Surface Roughness, and Chip Type in Order to Improve the Tool Operation Reliability in Sintered Cobalt Turning.

The authors present the results of laboratory tests analysing the impact of selected cutting data and tool geometry on surface quality, chip type and cutting forces in the process of orthogonal turning of sintered cobalt. The selected cutting data are cutting speed and feed rate. During the experiments, the cutting speed was varied in the range of vc = 50-200 m/min and the feed rate in the range of f = 0.077-0.173 mm/rev. In order to measure and acquire cutting force values, a measuring setup was assembled. It consisted of a Kistler 2825A-02 piezoelectric dynamometer with a single-position tool holder, a Kistler 5070 signal amplifier and a PC with DynoWare software (Version 2825A, Kistler Group, Winterthur, Switzerland)). The measured surface quality parameters were Ra and Rz. The components of the cutting forces obtained in the experiment varied depending on the feed rate and cutting speed. The obtained test results will make it possible to determine the optimal parameters for machining and tool geometry in order to reduce the machine operating time and increase the life of the cutting insert during the turning of sintered cobalt, which will contribute to sustainable technology.

Bearing fault diagnosis of induction machines using VMD-DWT and composite multiscale weighted permutation entropy

PurposeBearings play a critical role in the reliable operation of induction machines, and their failure can lead to significant operational challenges and downtime. Detecting and diagnosing these defects is imperative to ensure the longevity of induction machines and preventing costly downtime. The purpose of this paper is to develop a novel approach for diagnosis of bearing faults in induction machine.Design/methodology/approachTo identify the different fault states of the bearing with accurately and efficiently in this paper, the original bearing vibration signal is first decomposed into several intrinsic mode functions (IMFs) using variational mode decomposition (VMD). The IMFs that contain more noise information are selected using the Pearson correlation coefficient. Subsequently, discrete wavelet transform (DWT) is used to filter the noisy IMFs. Second, the composite multiscale weighted permutation entropy (CMWPE) of each component is calculated to form the features vector. Finally, the features vector is reduced using the locality-sensitive discriminant analysis algorithm, to be fed into the support vector machine model for training and classification.FindingsThe obtained results showed the ability of the VMD_DWT algorithm to reduce the noise of raw vibration signals. It also demonstrated that the proposed method can effectively extract different fault features from vibration signals.Originality/valueThis study suggested a new VMD_DWT method to reduce the noise of the bearing vibration signal. The proposed approach for bearing fault diagnosis of induction machine based on VMD-DWT and CMWPE is highly effective. Its effectiveness has been verified using experimental data.

Effect of depositional strategy on surface roughness of Al-5%Mg wall fabricated via Cold Metal Transfer based Wire Arc Additive Manufacturing

Cold Metal Transfer (CMT) based Wire Arc Additive Manufacturing (WAAM) is the future-driven novel technology for fabricating complex metal components, having advantages like high deposition rates, increased material efficiency, lesser lead time, low heat input, and low cost. Despite of above advantages, the CMT-WAAM process possesses few limitations in terms of producing metal components with high geometrical accuracy. Al-Mg alloys are particularly appealing for their lightweight and exceptional mechanical properties, making them attractive for various industrial applications such as marine, automobile, aerospace, etc. In this study, an Al-5%Mg alloy single wall has been built through CMT-WAAM using Current at 110A, Travel Speed (TS) of 7 mm/sec, and Gas Flow Rate (GFR) of 15L /min. The effect of unidirectional and bidirectional deposition direction on the surface quality of the fabricated sample has been investigated. Surface roughness (Ra) tests were conducted at three different zones (upper, middle, and bottom) of the specimen wall before the machining operation using a taylor hobson surtronic tester. It is concluded from the results that the S2 wall (unidirectional) has more Ra value than the S1 wall (bidirectional) in all zones due to the presence of a humping defect which results in more waviness over the S2 wall’s surface. In the bidirectional strategy, the roughness value reduces by 8.567 % (upper zone), 9.95 % (middle zone), and 13.019 % (bottom zone) than the unidirectional strategy. Thereby establishing that the deposition direction tends to build WAAM wall with a better surface finish.

Investigation and perspectives of using Graph Neural Networks to model complex systems: the simulation of the helium II bayonet heat exchanger in the LHC

Large cryogenic systems, like those installed at CERN, are complex systems relying on many diverse physical processes and phenomena that are difficult to simulate and monitor in detail. With only a limited number of properties measured and made available for monitoring and control purposes, several processes contributing to the dynamics of the systems are ignored. This lack of information can reduce the accuracy and the capability of a model to track, predict, and anticipate the behavior of the system. Accurate analytical or numerical computer modeling can be developed to simulate the non-linear dynamics of the processes but they are complex, computationally intensive, and cumbersome to test, validate, and implement with different configurations and limited measurements of the hidden properties. In this work, we present our investigation of using Graph Neural Networks (GNN) to build a model of the helium II bayonet heat exchanger operating in the LHC at CERN. We are proposing to use a hybrid machine learning approach, where the parameters of the GNN model are estimated by a combination of supervised learning algorithms trained on experimental data and bounding physics equations and parameters. The GNN model was initially trained on data from the experiments performed on the LHC prototype magnet strings and validated on data extracted during the operation of the LHC machine. We demonstrate the model’s accuracy, repeatability, and robustness in various configurations. The model is also well inspectable and explainable, providing the time evolution of all variables. We report on the results and expected applications, which include predictive control, diagnostic, and operator training.

A Fault Diagnosis Method for Key Components of the CNC Machine Feed System Based on the DoubleEnsemble–LightGBM Model

To solve the problem of fault diagnosis for the key components of the CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and an ensemble learning model is proposed in this study. First, various monitoring signals including vibration signals, noise signals, and current signals are collected. Then, the monitoring signals are preprocessed and the time domain, frequency domain, and time–frequency domain feature indices are extracted to construct a multi-dimensional mixed-domain feature set. Finally, the feature set is entered into the constructed DoubleEnsemble–LightGBM model to realize the fault diagnosis of the key components of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the widely used dataset and the feed system test bench dataset, and the average overall accuracy is 91.07% and 98.06%, respectively. Compared with XGBoost and other advanced ensemble learning models, this method demonstrates better accuracy. Therefore, the proposed method provides technical support for the stable operation and intelligence of CNC machines.