Machine System Research Articles

Fault diagnosis of axial movement for harmonic drive based on deep belief network by using current data of driving servomotor

PurposeHarmonic drives are used widely in aviation, robotics and instrumentation due to their benefits including high transmission ratio, compact structure and zero backlash. One of the common faults of a harmonic drive is the axial movement of the input shaft. In such a case, its input shaft moves in the axial direction relative to the body of the harmonic drive. The purpose of this study is to propose two fault diagnosis methods based on the current signal of the driving servomotor for the axial movement failure in terms of input shafts of harmonic drives.Design/methodology/approachIn the two proposed fault diagnosis methods, the wavelet threshold algorithm is firstly used for filtering noises of the motor current signal. Then, the feature of the denoised current signal is extracted by the empirical mode decomposition (EMD) method and the wavelet packet energy-entropy (WPEE) theory, respectively, obtaining two kinds of feature sets. After a deep learning model based on the deep belief network (DBN) is constructed and trained by using these feature sets, we finally identify the normal harmonic drives and the ones with the axial movement fault.FindingsIn contrast to the traditional back propagation (BP) neural network model and support vector machine (SVM) model, the fault diagnosis methods based on the combination of the EMD (as well as the WPEE) and the DBN model can obtain higher accuracy rates of fault diagnosis for axial movement of harmonic drives, which can be greater than or equal to 97% based on the data of the performed experiment.Originality/valueThe authors propose two fault diagnosis methods based on the current signal of the driving servomotor for the axial movement failure in terms of input shafts of harmonic drives, which are verified by the experiment. The presented study may be beneficial for the development of self-diagnosis and self-repair systems of different robots and precision machines using harmonic drives.

EVENT-TRIGGERED CONTROL OF MILLING PHOTOELECTRIC TRACKING SERVO SYSTEMS BASED ON MULTI-INNOVATION INTEREST PARAMETER IDENTIFICATION

Given the coupling of speed and current and the nonlinearity of electronic devices, the photoelectric tracking servo system for milling machines make it difficult to determine the model parameters, and traditional proportional–integral (PI) control hardly meets the high-performance requirements of milling machine optoelectronic tracking servo systems, especially in the development of system networking. In this study, an event-triggered intelligent PI position control strategy based on a multi-innovation identification model was proposed to improve the low control accuracy and dynamic performance caused by the strong coupling and nonlinearity in the optoelectronic tracking servo system of computerized numerical control (CNC) milling machines. A discredite model of the system was established through a multi-innovation identification model, and the PI control parameter was quickly determined using an improved multiverse optimization (IMVO) algorithm. At the same time, an event-triggering mechanism was introduced, thus reducing the number of controller triggers and saving system resources while ensuring the dynamic performance of the system. Finally, experiment results were compared with typical second-order system engineering design PI (SSED-PI) control, pole placement PI (PP-PI) control, and multiverse optimization (MVO)-PI control. Results demonstrate that the proposed multi-innovation stochastic gradient identification model fully utilizes the historical turning angle information of the optoelectronic tracking servo system and has higher accuracy than traditional stochastic gradient identification (parameter accuracy improved by 6.9 times, quantization error reduced by 6.7 times). The proposed event-triggered IMVO-PI (ET-IMVO-PI) has a triggering frequency of 3.5% compared with time-triggered IMVO-PI, with an overshoot of less than 0.5%, which can meet the needs of most engineering practices (less than 5%). Compared with event-triggered SSED-PI, PP-PI, and IMVO-PI, ET-IMVO-PI has higher dynamic performance and fewer triggering times, which can effectively meet the requirements of high-performance network control. The proposed method serves a crucial theoretical guide and important reference for the upgrading and transformation of the photoelectric tracking servo system of CNC milling machines. Keywords: Event-triggered control, Multiple innovative parameter identification, Multiverse optimization PI, Optoelectronic tracking servo system

A clustering-aided multi-agent deep reinforcement learning for multi-objective parallel batch processing machines scheduling in semiconductor manufacturing

Batch processing machines are often the bottleneck in semiconductor manufacturing and their scheduling plays a key role in production management. Pioneer researches on multi-objective batch machines scheduling mainly focus on evolutionary algorithms, failing to meet the online scheduling demand. To deal with the challenges confronted by incompatible job families, dynamic job arrivals, capacitated machines and multiple objectives, we propose a clustering-aided multi-agent deep reinforcement learning approach (CA-MADRL) for the scheduling problem. Specifically, to achieve diverse nondominated solutions, an offline multi-objective scheduling algorithm named Multi-Subpopulation fast elitist Non-Dominated Sorting Genetic Algorithm (MS-NSGA-II) is firstly developed to obtain the Pareto Fronts, and a clustering algorithm based on cosine distance is employed to analyze the distribution of Pareto frontier solution, which would be used to guide reward functions design in multi-agent deep reinforcement learning. To realize multi-objective optimization, several reinforcement learning base models are trained for different optimization directions, each of which composed of batch forming agent and batch scheduling agent. To alleviate time complexity of model training, a parameter sharing strategy is introduced between different reinforcement learning base model. By validating the proposed approach with 16 instances designed based on actual production data from a semiconductor manufacturing company, it has been demonstrated that the approach not only meets the high-frequency scheduling requirements of manufacturing systems for parallel batch processing machines but also effectively reduces the total job tardiness and machine energy consumption.

ARTIFICIAL INTELLIGENCE IN LABOUR RELATIONS: A THREAT TO HUMAN RIGHTS OR NEW OPPORTUNITIES?

This article explores the possibility of using artificial intelligence in the field of labour relations. Modern technologies provide new opportunities, but at the same time, they give rise to a number of complex issues, solving new approaches to the realization of the right to work and proper social security by able-bodied citizens, which is important today, when Ukraine is defending its sovereignty and independence from military aggression by the Russian Federation. The use of machine learning algorithms and systems can lead to significant improvements related to the professional training of labour resources, management of production processes, labour protection and other aspects of labour relations.We came to the conclusion that the modernization of labour law involves expanding the circle of participants in labour relations and revising the meaning of the term "employee". Thus, the presence or absence of access to technology will create new forms of inequality in the interaction between "employee-to-employee" and "worker-robot (AI)".A proactive approach is proposed to mitigate the consequences of possible threats to the use of artificial intelligence in labour relations through an in-depth study of all possible threats arising in connection with the use of modern technologies. A proposal is made to take as a basis the international experience of using AI in the social structure of the state and adapt it to the life of the state, which, in turn, will contribute to the promotion of important theses on the quality and accessibility of data at the country level, and in cities in particular, promoting participation in data exchange schemes at the level of the private and public sectors.

2850: The first proton minibeam system for single-gantry proton machine

2850: The first proton minibeam system for single-gantry proton machine

Polishing Machine Control System Based on B-Spline Curve Trajectory

In this study, a B-spline trajectory control algorithm is presented, showcasing its ability to achieve smooth trajectory control within an embedded motion control system. Traditional surface machining methods involve converting interpolated trajectories into G-code using numerical control (NC) software, which is then downloaded and executed on the numerical control system. This research introduces a specialized third-degree B-spline interpolation method tailored for curved surface trajectories, aiming to enhance machining efficiency. A significant strength of this project lies in the holistic design of an embedded system, encompassing both hardware circuitry and software logic. Utilizing the cost-effective STM32 architecture, a B-spline discrete velocity interpolation algorithm is implemented, validated through experiments conducted on a polishing machine system. The project involves MATLAB software for data simulations and experiments on a polishing machine using B-spline curve interpolation, confirming the practicality and effectiveness of the third-degree B-spline algorithm within an embedded system.

Cardiac autonomic responses in relation to cognitive workload during simulated military flight

Understanding the operator's cognitive workload is crucial for efficiency and safety in human–machine systems. This study investigated how cognitive workload modulates cardiac autonomic regulation during a standardized military simulator flight. Military student pilots completed simulated flight tasks in a Hawk flight simulator. Continuous electrocardiography was recorded to analyze time and frequency domain heart rate variability (HRV). After the simulation, a flight instructor used a standardized method to evaluate student pilot's individual cognitive workload from video-recorded flight simulator data. Results indicated that HRV was able to differentiate flight phases that induced varying levels of cognitive workload; an increasing level of cognitive workload caused significant decreases in many HRV variables, mainly reflecting parasympathetic deactivation of cardiac autonomic regulation. In conclusion, autonomic physiological responses can be used to examine reactions to increased cognitive workload during simulated military flights. HRV could be beneficial in assessing individual responses to cognitive workload and pilot performance during simulator training.

Performance assessment of the multi-nozzle injection MQL system for cleaner machining of hardened AISI D2 steel concerning power consumption

ABSTRACT Sustainable hard machining is a pressing need in manufacturing industries for techno-social, economic and environmental benefits to machine difficult-to-cut materials. Thus the present study investigates finish turning of hardened AISI D2 steel using a MTCVD coated carbide insert (TiN-TiCN-Al2O3) with geometry CNMG120408FW and grade WK05CT under a multi-nozzle MQL system using LRT 30 mineral oil (50 ml/hr flow rate, 6 bar compressed air pressure, 30 mm nozzle distance from tool tip) for minimal quantity lubrication at both the rake and flank zones for assessment of machinability. Flank wear lies between 0.79 and 0.155 mm and within the failure criterion limit of 0.2 mm. Arithmetic surface roughness trials have been within 0.361–0.877 microns and within the 1.6 microns acceptable range. The cutting temperature has been between 80.7°C and 226.9°C and even below 200°C in the majority of runs. The cutting power lies within 0.432kW–0.804kW. The optimal parametric combination has been found to be d=0.1 mm, f=0.05 mm/rev and v=80 m/min respectively and improvement has been observed over dry cutting. RSM models are found to be statistically significant. Application of multi-nozzle MQL in machining of hardened steel outperformed through machinability assessment and may be adopted in shopfloor for sustainability..

Evaluation of radiation leakage in X-ray security inspection machine using a CZT spectrometer

Leakage radiation from X-ray security inspection machines is important, and measurement based on ionization chamber or scintillator detector is widely used. The leakage radiation is closely related to the size and the passing time of the luggage, the lead equivalent, the opening angle of the lead curtain, and the response time of the measuring instrument. To characterize the distribution of leakage radiation from the X-ray security inspection machine accurately, a small-volume CZT(CdZnTe) spectrometer was used to measure the energy spectra at a distance of 5 cm from the surface of the inspection machine. By designing and controlling the opening angle of the lead curtain according to the size of the luggage passing through the entrance and exit, the radiation dose was determined based on the measured energy spectra combined with the G(E)-function method. The results show that the maximum relative deviation between the air kerma rate and the ambient dose equivalent rate calculated by the G(E) function method with the standard dose rate does not exceed ±5%. The maximum relative deviation of the dose rate linear verification in the 137Cs radiation field is less than 2.5%. A calibrated CZT detector was utilized to measure the radiation leakage on the surface of the X-ray security inspection machine. It was discovered that the presence of the luggage items and the opening angle of the lead curtain will increase the leakage radiation dose on the surface of the security inspection machine system. This study provides a new approach for measuring scattered radiation of X-ray security inspection machines.

Method for vibration suppression in rotary machines using multiple automatic ball balancers

An automatic ball balancer (ABB) is a device that is used to automatically balance an eccentric rotor; these are typically used in rotary machines with unknown or variable imbalances. The typical construction of an ABB consists of several balls in a ring race. The balls can move freely inside the race, which changes the eccentricity radius and phase angles relative to the rotor. The automatic balancing process requires an ABB unit to be installed on an eccentric rotor's axis; thus, its application is quite limited and usually requires the redesign of a rotary machine. This paper presents a new method for eliminating vibrations in rotary machines by using multiple ABBs that are mounted away from the rotor's axis. In this application, ABBs can be considered to be unbalanced rotary masses with adjustable eccentricity radii and phases. Theoretically, this ability allows for the total reduction of the inertial force from an eccentric rotor; however, the parameters of the ABBs must be set correctly. The process of setting the eccentricity radius and phase in each ABB occurs due to a self-synchronization phenomenon and generally depends on the physical parameters of either a rotary machine or ABBs. Both analytical and numerical investigations that were based on the mathematical model of a system of a rotary machine with a pair of ABBs allowed us to formulate basic rules to apply such a system in existing rotary machines without interference on the rotors.

Energy efficiency identification and surface roughness prediction using cutting force signal for computer numerical controlled machine systems

The energy efficiency identification of machining process plays an indispensable part in achieving energy-efficient manufacturing and improving energy utilization as well as productivity and surface quality. However, there is a great difficulty to track energy efficiency in real-time based on one kind of traditional power signal. Because energy consumption is affected by many factors such as machine tool current performance, tool wear conditions and cutting parameters selection. This paper puts forward an energy efficiency recognition method as well as surface roughness prediction model based on the cutting force signals. The CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) algorithm is employed to decompose the cutting force signal into multiple IMF (intrinsic mode function) components; and characterization of energy efficiency of machining process is recognized through proportion of components based on PCA—Fast ICA algorithm. Then, a surface roughness prediction model is proposed using support vector regression (SVR) based on specific cutting energy consumption (SCEC). The orthogonal test is designed considering spindle speed, feed rate, depth of cutting and width of cutting in 3 levels to obtain the influence degree of cutting parameters on cutting force, specific energy consumption, and the surface roughness. The energy efficiency of 27 group experiments is classified into high, medium and low levels according to energy efficiency value. Finally, using the data of orthogonal test, energy efficiency state was identified. The result show that time–frequency of cutting force signals for high, medium and low energy efficiency could be extracted, and the average absolute error of surface roughness predict is 0.058. That illustrated that the proposed method could meet the industry requirement for energy efficiency monitoring and surface roughness prediction to achieve sustainable manufacturing.

A Proven Translation from a UML State Machine Subset to Timed Automata

Although Unified Modeling Language (UML) state machines constitute a convenient modeling formalism that is widely used in many applications, the lack of formal semantics impedes carrying out automatic processing, such as formal verification. In this article, we aim to achieve a proven translation from a subset of UML state machines to timed automata. A generic abstract syntax is defined for state machines that allows us to specify state machines as a tree-like structure, explicitly illustrating the hierarchical relationships within the model. Based on this syntax, a formal asynchronous semantics for state machines and systems of state machines is established. Additionally, the semantics of timed automata is specified. Then, a translation relation from the considered set of state machines to timed automata is defined and a strong equivalence relation — namely, a timed bisimulation between the source and target models — is formally proven. The proof is carried out inductively while considering continuous (time) and discrete transitions separately. This proof allows us to demonstrate a strong similitude between these models.

Accuracy of Autonomous Artificial Intelligence-Based Diabetic Retinopathy Screening in Real-Life Clinical Practice.

Background: In diabetic retinopathy, early detection and intervention are crucial in preventing vision loss and improving patient outcomes. In the era of artificial intelligence (AI) and machine learning, new promising diagnostic tools have emerged. The IDX-DR machine (Digital Diagnostics, Coralville, IA, USA) represents a diagnostic tool that combines advanced imaging techniques, AI algorithms, and deep learning methodologies to identify and classify diabetic retinopathy. Methods: All patients that participated in our AI-based DR screening were considered for this study. For this study, all retinal images were additionally reviewed retrospectively by two experienced retinal specialists. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated for the IDX-DR machine compared to the graders' responses. Results: We included a total of 2282 images from 1141 patients who were screened between January 2021 and January 2023 at the Jules Gonin Eye Hospital in Lausanne, Switzerland. Sensitivity was calculated to be 100% for 'no DR', 'mild DR', and 'moderate DR'. Specificity for no DR', 'mild DR', 'moderate DR', and 'severe DR' was calculated to be, respectively, 78.4%, 81.2%, 93.4%, and 97.6%. PPV was calculated to be, respectively, 36.7%, 24.6%, 1.4%, and 0%. NPV was calculated to be 100% for each category. Accuracy was calculated to be higher than 80% for 'no DR', 'mild DR', and 'moderate DR'. Conclusions: In this study, based in Jules Gonin Eye Hospital in Lausanne, we compared the autonomous diagnostic AI system of the IDX-DR machine detecting diabetic retinopathy to human gradings established by two experienced retinal specialists. Our results showed that the ID-x DR machine constantly overestimates the DR stages, thus permitting the clinicians to fully trust negative results delivered by the screening software. Nevertheless, all fundus images classified as 'mild DR' or greater should always be controlled by a specialist in order to assert whether the predicted stage is truly present.

Using Of Artificial Intelligence In The Cultural And Creative Industries: A Public Administration Perspective

The purpose of this article is to explore the specific aspects of implementing artificial intelligence (AI) in the cultural and creative industries from a public administration perspective. The article analyses the main opportunities and directions for incorporating AI into public management for the development of these sectors in Ukraine. It highlights that digital transformation, facilitated by AI technologies, requires adherence to structural-functional, informational-communicative, and organizational-technological approaches. These approaches ensure decentralization, modernization of information infrastructure, and optimization of management processes. The article outlines the prospects and directions for AI integration into public administration in the cultural and creative sectors in Ukraine. It identifies the main benefits of AI, such as the ability to analyse large volumes of data, predict trends, automate routine processes, and support informed decision-making. These benefits can enhance the quality and accessibility of cultural products and create new channels and consumption models. This includes applications like the digitization of cultural heritage, management of cultural institutions, and the creation of personalized experiences for visitors. The article also identifies potential risks associated with implementing AI in public administration for the cultural and creative industries in Ukraine. These risks include issues related to copyright protection, ethics, and transparency in decision-making. Despite the significant potential, the integration of AI in public administration is still in its early stages. It faces numerous challenges, such as a lack of clear methodological approaches and practical tools, as well as risks related to privacy, algorithm transparency, and employment impacts. The article emphasizes that using AI in creating creative products raises important considerations regarding the value-based foundations of the cultural and creative sectors. It transforms creativity from an individual to a collective endeavor, where the role of machine systems becomes comparable to that of humans. Additionally, the article proposes a refined definition of «creative industries» in Ukrainian legislation, considering the specificities of creating creative products with AI.

Generation of uniform micro-textured structures by two-dimensional modulation fly-cutting

Micro-textured structures are widely applied in the fields of aerospace, military and medical etc. because of their unique properties such as self-cleaning, structural color and antibacterial effects. The traditional fast tool servo technology is believed to be an ideal machining method for the fabrication of micro-textured structures, however, its frequency response is limited by the varied linear velocity along the radial direction of workpieces, which make it difficult to machine uniform micro-textured structures. In this paper, a novel two-dimensional modulation fly-cutting system is developed to machine uniform micro-textured structures. In the machining system, the principal cutting motion is generated by a fly-cutting while a sinusoidal excitation motion as the assistive modulation is generated by a two-dimensional vibration platform. The two-dimensional vibration platform can apply excitation both in the x- and z-directions to the workpiece. By changing the excitation frequency, tool rotation radius and feed rate in X-axis, the corresponding optimal offset angle, length-width ratio and density of micro-textured structures can be obtained. Also, uniform concave-convex micro-textured structures are fabricated further by two-dimensional modulation of the principal cutting motion. According to the experimental results, uniform concave-convex micro-textured structures have good quality, which proves that the present machining method is effective. The present study provides an effective machining method for fabrication of micro-textured structures, and also serves as a reference for the fabrication of other similar micro-textured structures.

Multi-attribute optimization of eco-manufacturing based criteria in CNC manufacturing systems using an evolutionary algorithm

Manufacturing technology has evolved over the years with the development of CNC manufacturing systems, flexible manufacturing, rapid prototyping, smart manufacturing etc Simultaneously, the development of new and exotic materials to match specific requirements has shaped new problems in manufacturing. The materials developed thus far require special tools, lubricating agents, and extra-care in machining without compromising the quality. Further the study of carbon emissions in manufacturing sector has also gained unusual spotlight in view of their deleterious effect on the ecological balance. The manufacturing systems have to be consequently designed and developed, such that they generate minimal quantity of emissions without forfeiting the prime objectives of quality and tool morphology. The present work is principally intended to analyse the effect of cutting parameters on the emission rate of greenhouse gases, tool wear and work-piece temperature concurrently. These studies are accomplished in both dry and wet conditions on computer numerical control machining system. The machining process involved plain facing of a Ti-6Al-4V hardened material. The experimental studies are realized using both single point and multi-point cutting tools and are supplemented with the application of Multi-Objective Genetic Algorithm (MOGA). The MOGA generated set of pareto-fronts for the four machining conditions were subjected to VIKOR, TOPSIS and LINMAP decision making approaches to arrive at the optimum values of decision variables. The optimum cutting parameters obtained in single point cutting tool machining in dry conditions are speed (873.2 rpm), feed (0.199 mm rev−1) and depth of cut (0.25 mm), while the corresponding values of responses are tool wear (67.19 μm), work-piece temperature (39.36 °C) and carbon emission (0.138 Kg-CO2). The equivalent values for multi-point cutting were determined as 899.8 rpm, 0.195 mm rev−1 and 0.25 mm, while the responses for these optimal conditions are 69.92 μm, 39.48 °C and 0.137 Kg-CO2 in that order.

Particle Swarm Optimization for a redundant repairable machining system with working vacations and impatience in a multi-phase random environment

With the increasing reliance on cloud computing as the foundational manufacturing systems with intricate dynamics, featuring multiple service areas, varying job arrival rates, diverse service requirements, and the interplay of failures and impatience, significant analytical challenges arise. Queueing networks offer a powerful stochastic modeling framework to capture such complex dynamics. This paper develops a novel, exhaustive queueing model for a finite-capacity redundant multi-server system operating in a multi-phase random environment. The proposed model uniquely integrates real-world factors, including server breakdowns and repairs, waiting servers, synchronous working vacations, and state dependent balking and reneging, into a single queueing model, representing a significant advancement in the field. Using the matrix-analytic method, we establish the steady-state solution and derive key performance metrics. Numerical experiments and sensitivity analyses elucidate the impact of system parameters on performance measures. Additionally, a cost model is formulated, enabling cost optimization analysis using direct search method and Particle Swarm Optimization (PSO) to identify efficient operating configurations.

Identification of required power for air transport system of the cotton-picking machine MX-2.4

Abstract This article addresses the issues in the air transport system of semi-suspended MX-1.8 and MX-2.4 cotton pickers with a vertical spindle. Given that semi-suspended machines currently pick cotton crops with 60 cm row spacing, the goal is to eliminate the shortcomings of these machines and optimize the technological parameters of this machine. The power required for fan operation is calculated, taking into account the additional aerodynamic resistance caused by the complexity of the air transport system design. The results of the calculations are presented in the form of a histogram.

Electro-hydraulic servo position control of bending machine based on Single Neuron PID

Abstract Due to the fixed parameters, inadequate dynamic performance, and significant tracking error of the traditional PID control algorithm, it is challenging to satisfy the increasingly stringent precision demands for position control of the slider in the hydraulic servo system of the bending machine. Given the significant impact of external load on the position accuracy of the bending machine’s slider, a single neuron network is employed to dynamically adjust parameters in response to external load interference, thereby compensating for the limitations of traditional algorithms. Consequently, this paper proposes the design of a single neuron PID (SN-PID) controller to enhance system control accuracy. Through multiple simulation comparisons, it is evident that the SN-PID controller system exhibits superior anti-interference capabilities, enhanced adaptability, and reduced following error compared to traditional PID control algorithms in achieving slider position accuracy.

An integrated optimization method for measurement points layout and error modeling for digital twin of CNC machine tools

Thermal error significantly influences the accuracy of precision computer numerical control (CNC) machine tools. The key to compensating thermal error lies in selecting appropriate temperature measurement points and establishing an accurate error prediction model. Traditional methods separate measurement points selection and prediction modeling, that is, selecting temperature measurement points first and then establishing the prediction model using these points. These methods are difficult to achieve optimal matching between measurement points and the prediction model, resulting in shortcomings in modeling accuracy. To address these challenges, an integrated optimization method for measurement points layout and error modeling for digital twin of CNC machine tools is proposed. A dual-stage attention-based long short-term memory combined with convolutional neural network (DA-CLSTM) error modeling method is proposed to accurately predict the thermal error for different numbers of temperature measurement points. Then, an integrated method of virtual-real temperature measurement points layout and error modeling is proposed, which ensures the temperature measurement points and the error prediction model are closely matched, offering rational sensors layout and high-accuracy prediction. Finally, experiments are conducted on the spindle system test bench to validate the method proposed in this research. Through integrated optimization of measurement points layout and the prediction model, the proposed method achieves high-accuracy thermal error prediction across various sensor counts and maintains reliable prediction ability when the number of sensors is reduced. This method is applied to a digital twin system of MKL7150 grinding machine, and effectively improves the accuracy of actual machining.