Industrial Equipment Research Articles

SCS-JPGD: Single-Channel-Signal Joint Projected Gradient Descent

The fault diagnosis of industrial equipment is crucial for ensuring production safety and improving the efficiency of equipment operation. With the advancement of sensor technologies, the number of data generated in industrial environments has increased dramatically. Deep learning techniques, with their powerful feature extraction and classification capabilities, have become a research hotspot in the field of fault diagnosis. However, deep learning models are vulnerable to adversarial attacks, which can lead to a decrease in diagnostic accuracy and compromise system safety. This paper proposes a Joint Projection Gradient Descent (SCS-JPGD) method based on single-channel signal features. The proposed method first introduces a gradient-based attack approach for signal samples, which can add tiny perturbations to the input samples, causing misclassification in black-box models. Secondly, a joint training strategy is proposed for gradient attacks on signal samples, aiming to enhance the model’s adaptability to small perturbations in a limited range. Experiments were conducted on the CWRU dataset under four different operating conditions. The results show that, under a deep learning model with diagnostic accuracy exceeding 90%, the joint training method allows the model to maintain an average accuracy of 84.6% even after the addition of adversarial samples, which are barely distinguishable by the human eye. The proposed SCS-JPGD method provides a safer and more accurate approach for fault diagnosis in deep learning research.

Investigation of gas-liquid flow hydrodynamics in the industrial-scale stirred tank with inclined impeller

Abstract The inclined-axis stirring system is widely employed in industrial processes due to its exceptional mixing capabilities, ease of industrial retrofitting, and commendable safety and stability features. This study numerically investigates the multiphase flow characteristics within an industrial-scale inclined-axis stirring tank, utilizing the realizable k-ε model and the volume of fluid model. With the validated model, the impact of impeller rotational speed on the flow characteristics in the stirred tank is explored. The findings reveal several noteworthy observations: As the stirring speed increases, liquid level fluctuations intensify. At excessively high stirring speeds, a large number of bubbles are entrained and dispersed into the stirring tank. Multi-scale vortices are observed within the inclined-axis stirred tank. Notably, two relatively large-scale vortices manifest on either side of the rotating blade. Comparatively, the tilted arrangement of the stirring shaft disrupts the symmetry of the flow field. Regions beneath the blades and at the bottom of the stirred tank exhibit elevated liquid phase velocities, radial velocities, and axial velocities. The rising area of the fluid in the stirred tank is near the wall, forming a ring shape, while the center of the ring is characterized by descending fluid. These findings provide valuable theoretical insights for the structural configuration and considerations related to energy conservation in industrial agitation equipment.

Control Design for Electronic Voltage Stabilizer

Vietnam's electrical infrastructure has undergone notable advancements in recent times. Nevertheless, concerns pertaining to under-voltage, over-voltage, and voltage fluctuations persist in rural, mountainous, and industrial regions. This results in the inefficient operation of electrical equipment, disruptions in industrial production processes, data loss, and equipment damage. This paper puts forth a novel control design methodology for electronic voltage stabilizers, with the objective of mitigating the detrimental effects of grid voltage fluctuations on electrical apparatus. A compact and cost-effective AC-AC converter is proposed as a means of regulating the compensation voltage. The paper puts forth the use of the state-space averaging method for system modeling and proposes the combination of feedback and feed-forward controllers to achieve high accuracy and rapid response times. Furthermore, the moving average method is proposed for measuring the Root Mean Square (RMS) voltage, which significantly enhances the control response speed and accuracy. A 10 kVA single-phase electronic voltage stabilizer was constructed and tested in a laboratory setting under a range of grid voltage conditions, from 150V to 290V, and with varying loads. The results demonstrate that the electronic voltage stabilizer is effective in maintaining the load voltage within the desired range. The maximum response time recorded was found to be half a cycle of the grid voltage in the simulation and one cycle in the experiments, which is a significantly faster response time than that of similar designs. Furthermore, the low total harmonic distortion provides additional confirmation of the effectiveness of the designed electronic voltage stabilizer.

Business to Business (B2b) Marketing Strategy for Construction Industry Equipment Manufacturing Company, CV. Ziaulhaq Solution

aaa

A Predictive Maintenance Framework for Offshore Industrial Equipment: Digital Transformation for Enhanced Reliability

This review presents a novel predictive maintenance framework designed to enhance the reliability of offshore industrial equipment by integrating artificial intelligence (AI), the Internet of Things (IoT), and 3D modeling. In offshore energy operations, maintaining equipment reliability is paramount due to the harsh environmental conditions and the critical nature of uninterrupted service. Traditional maintenance approaches, such as reactive or preventive methods, often fall short in addressing the complexity and unpredictability of offshore environments. The proposed framework leverages real-time monitoring, lifecycle management, and predictive analytics to anticipate equipment failures before they occur, optimizing operational uptime and minimizing downtime costs. The framework focuses on three key components: AI-driven predictive analytics, IoT-based real-time data collection, and 3D modeling for virtual equipment monitoring. AI algorithms analyze vast datasets from sensors to detect patterns and predict potential failures, allowing for proactive maintenance scheduling. IoT sensors continuously monitor equipment health, providing real-time insights into operational conditions, such as vibrations, temperature, and pressure. Furthermore, 3D modeling offers a visual representation of offshore equipment, helping to forecast potential failures and visualize maintenance needs more effectively. This integrated approach addresses the unique challenges of offshore operations by providing more accurate predictions, reducing risks associated with equipment failure, and enhancing the overall efficiency of offshore energy operations. The framework's novelty lies in its fusion of cutting-edge technologies, which together form a comprehensive solution to redefine reliability engineering in offshore industries. The model aims to drive the digital transformation of maintenance practices, improving safety, reducing costs, and ensuring the continued performance of critical offshore infrastructure.

CONELPABO: composite networks learning via parallel Bayesian optimization to predict remaining useful life in predictive maintenance

Abstract Maintaining equipment and machinery in industries is imperative for maximizing operational efficiency and prolonging their lifespan. The adoption of predictive maintenance enhances resource allocation, productivity, and product quality by proactively identifying and addressing potential equipment anomalies through rigorous data analysis before they escalate into critical issues. Consequently, these measures strengthen market competitiveness and generate favorable economic outcomes. In many applications, sensors operate at high frequencies or capture data over extended periods. This work introduces CONELPABO (Composite Networks Learning via Parallel Bayesian Optimization), a framework for analyzing long time series data, particularly for predicting the remaining useful life of a system or component. It uses a divide-and-conquer strategy to manage the exponential growth in the hyperparameter search space during Bayesian Optimization and to accelerate model training by 50%. Additionally, this strategy enables the training of deeper networks with limited resources. The usefulness of the framework is demonstrated through two case studies, in which it achieves state-of-the-art results, showing that CNN-CNN and RNN-RNN architectures are highly effective for long time-series data. These architectures outperform many existing approaches and challenge the common academic focus on CNN-RNN hybrids.

Fluid‐Structure Interaction and Heat Transfer Characteristics of a Thin Flexible Heater Submersed in Non‐Newtonian Fluids Inside a Shear‐Driven Cavity

ABSTRACTThis study examines fluid‐structure interaction (FSI)–induced flow and heat transfer phenomena in a double‐sided shear‐driven, that is, lid‐driven cavity filled with non‐Newtonian power‐law fluids. A flexible thin heater positioned at the center of the cavity serves as the heat source, while the moving side walls maintained at constant low temperature perform as a heat sink. The numerical approach adopts the finite element Galerkin method, integrating the Arbitrary Lagrangian–Eulerian framework with moving mesh technique to solve the associated flow, thermal, and stress fields. The thermoelastodynamic system behavior is analyzed through streamline, isothermal, and heater deformation visualizations, along with an evaluation of heat transfer performance, namely, the average Nusselt number. FSI‐induced internal stress scenario in the heater is also studied in terms of maximum von Mises stress. Variation of system conditions necessarily includes mixed convection strength, shearing effect, fluid rheology, and flexibility of the heater manifested by four governing system parameters, namely, the Richardson number (0.1 ≤ Ri ≤ 10), Reynolds number (100 ≤ Re ≤ 300), power‐law index (0.6 ≤ n ≤ 1.4), and Cauchy number (10⁻⁴ ≤ Ca ≤ 10⁻⁸). The findings of this study reveal a significant improvement in heat transfer for shear‐thinning fluids, with the most notable enhancement occurring at the highest Richardson number (Ri), where the heat transfer rate shows an increase of up to 33.33% compared with Newtonian fluids. The insights of this study might be helpful in heat transfer enhancement of industrial process equipment, particularly in applications such as food processing, electronics cooling, and chemical engineering, where non‐Newtonian fluids are extensively used in reactors and related thermofluid systems.

Waste to Energy Conversion and Predictive maintenance in Circular Economics Through AI

This paper explores the transformative role of artificial intelligence (AI) in advancing the circular economy through waste-to-energy (WtE) conversion and predictive maintenance. By leveraging AI, waste management processes can be optimized to enhance the efficiency of resource recovery, minimize environmental impact, and generate renewable energy. Predictive maintenance, driven by AI, ensures the smooth operation of industrial equipment, reducing downtime and extending machinery lifespan. This integration supports sustainable production and aligns with important circular economy principles, including biomimicry, lean manufacturing, and the Butterfly Model. The study underscores the potential of AI-driven technologies in fostering a resilient and sustainable future by addressing critical environmental challenges and promoting efficient resource utilization.

Bearing Fault Diagnosis for Cross-Condition Scenarios Under Data Scarcity Based on Transformer Transfer Learning Network

Motor-bearing fault diagnosis is critical for industrial equipment reliability, yet traditional data-driven methods require extensive labeled data, which are often scarce in real-world applications. To address this challenge, we propose a Transformer transfer learning network (TTLN) for accurate fault diagnosis under cross-condition scenarios, particularly when target domain data are limited. First, we develop a Transformer-based fault diagnosis model that captures long-range dependencies in sequential data through self-attention, achieving high accuracy under single operating conditions. Second, we introduce the TTLN framework, which integrates domain adaptation to align marginal and conditional distributions, enabling robust cross-condition fault diagnosis with minimal target domain samples. Finally, we validated the proposed method on the CWRU and PU datasets, demonstrating the TTLN’s superior performance in data-scarce scenarios. For example, the TTLN achieved over 95% accuracy with only 100 target samples, outperforming traditional methods and fine-tuning-based approaches. The results underscore the TTLN’s effectiveness in cross-condition fault diagnosis, offering a practical solution for industrial applications with limited labeled data.

The Impact of Environmental Regulation Compliance and Market Competitiveness Degree on Performance: The Case of the Portuguese Enterprise Ecosystem

ABSTRACTThe EU Directive 2002/96/EC concerning the re‐use, recycling, and other forms of recovery of waste of electrical and electronic equipment (WEEE) sets criteria for collecting, treating, and recovering WEEE. In Portugal, since 2006, firms operating in these industries must comply with the WEEE Directive. In this study, we examine the impact of compliance with this environmental regulation on corporate performance across different degrees of market competitiveness. We collected a sample of Portuguese‐based firms from the electrical and electronic equipment industries from the Orbis Europe database between 2003 and 2022 and identified the ones that comply with the law—the treatment group. Our final sample consists of 219 firms, corresponding to 2718 matched pairs formed of treated and control observations. Our results show no differences in performance between firms that comply (the treatment group) and those that do not (the control group), except for firms operating in more competitive markets. In such cases, compliance negatively affects firms' performance. The profitability of treated firms assigned in the group of high market competitiveness is, on average, three percentage points lower than that of their counterparts. This evidence poses a challenge to the EU regulators, who should focus on enforcing EU Directive to create a common ground across member states to avoid free riders from emerging.

Smart Glove for Maintenance of Industrial Equipment

Maintenance and service are important tasks for any industrial enterprise. This article presents a methodology for technical maintenance that employs a smart glove equipped with tactile sensors, an electronic unit responsible for processing and transmitting information, and a unit designed to interpret the results. Tactile sensors are graphene-based. The main idea of the method is to use sensors to record the strength of contact between the operator’s fingertips and the equipment. Afterwards, these values are recorded, transferred to processing, and the output signal from the sensors is compared with the steps of various repair works. The work contains methods for creating each component of the glove, their effectiveness is evaluated, and experiments are described to assess the feasibility of using the developed device for the maintenance and repair of equipment. The device discussed in this work is a wearable device. The obtained results demonstrate the applicability of the smart glove for equipment maintenance and repair.

Issues of modern maintenance of feed industry equipment

The article examines the evolution of maintenance methods in the feed industry, in particular, the transition from reactive to proactive strategies. It examines the implementation of preventive maintenance technologies, equipment condition-based monitoring, and data-driven decision-making to optimize equipment uptime, minimize downtime, and improve product quality. The role of automation, remote diagnostics, and advanced training programs for maintenance personnel is also discussed.

A novel thermochromic bistable display device based on cholesteric liquid crystals and reversible thermochromic materials

ABSTRACT In this paper, a novel thermochromic bistable display device was designed based on the planar and focal conic texture characteristics of cholesteric liquid crystal maintained without electric field and the reversible discoloration of thermochromic materials with temperature changes, enriching the functions of traditional bistable displays. The feasibility of the novel thermochromic bistable display was verified by analysing and comparing the measured chromaticity coordinates and spectral curves. The contrast and other properties of this device were also studied. The device exhibits a good visual effect whether it is in the same display state at different temperatures, or in the different display states at same temperature. Therefore, it can be used in price tags, signs, industrial equipment, and other prompt scenarios to make up for the dullness of traditional monochrome bistable liquid crystal display.

Multi-Condition Remaining Useful Life Prediction Based on Mixture of Encoders.

Accurate Remaining Useful Life (RUL) prediction is vital for effective prognostics in and the health management of industrial equipment, particularly under varying operational conditions. Existing approaches to multi-condition RUL prediction often treat each working condition independently, failing to effectively exploit cross-condition knowledge. To address this limitation, this paper introduces MoEFormer, a novel framework that combines a Mixture of Encoders (MoE) with a Transformer-based architecture to achieve precise multi-condition RUL prediction. The core innovation lies in the MoE architecture, where each encoder is designed to specialize in feature extraction for a specific operational condition. These features are then dynamically integrated through a gated mixture module, enabling the model to effectively leverage cross-condition knowledge. A Transformer layer is subsequently employed to capture temporal dependencies within the input sequence, followed by a fully connected layer to produce the final prediction. Additionally, we provide a theoretical performance guarantee for MoEFormer by deriving a lower bound for its error rate. Extensive experiments on the widely used C-MAPSS dataset demonstrate that MoEFormer outperforms several state-of-the-art methods for multi-condition RUL prediction.

Integral UV Spectrophotometric Methods for Determination of Clopidogrel Bisulphate and Metamizole Sodium in Rinse Waters from Industrial Equipment

Integral UV Spectrophotometric Methods for Determination of Clopidogrel Bisulphate and Metamizole Sodium in Rinse Waters from Industrial Equipment

Nusselt and Friction Factor Correlations for Gasketed Plate Heat Exchangers in Variable Inlet Conditions

Abstract Gasketed plate heat exchangers (GPHEs) are essential equipment in many industries due to their efficiency and compact design. They are particularly valued owing to their versatility, but GPHE designing and sizing are challenging due to divergences in Nusselt number and friction factor correlations. In addition to the influence of Reynolds and Prandtl numbers on the abovementioned correlations, recent studies have shown that GPHE performance is also affected by geometrical plate features, GPHE assembly accuracy quantified by the tightening distance, and inlet conditions in the branches. Despite the noticeable effort in the literature to develop more accurate GPHE correlations, no study to date has presented correlations affected by the plate thickness, tightening distance, and branches' inlet conditions (differences in the inlet pressures). Therefore, new correlations were created that filled this gap, including the influences of the chevron angle and the corrugation aspect ratio. With the aid of multiple linear regressions, the trends and large variations of our experimental databases were satisfactorily reproduced. The results have been compared to relevant literature.

Lubrication for macroscopic friction pairs with single-layer graphene coating

With its strong mechanical properties, graphene has shown potential in applications for reducing friction and wear, but the underlying mechanisms for its macroscopic lubrication remain relatively unexplored. Here, we systematically study the lubrication effect of chemical vapor deposition graphene coated on the surfaces of macroscopic friction pairs made of different materials. Our findings reveal an apparent lubrication by single-layer graphene coating, as well as correlation between the COF and the brittleness of the substrate. Through a comprehensive characterization using Raman spectroscopy, we propose a protective mechanism by which graphene can effectively dissipate the resulting shear stress generated during friction and delay the wear generation until the graphene layer fails and the bare material surface starts to rub directly, which is confirmed by finite element analysis simulation. We believe our results can provide important support for the practical application of graphene coatings in lubrication for macroscopic friction pairs in industrial equipment.

Utilization of Wastewater from Air Conditioner Circulation Systems for Clean Water Energy Efficiency and Industrial Equipment Maintenance

There is significant wasteful use of clean water for operating equipment during field and laboratory practice. Additionally, damage to laboratory equipment has been reported due to the use of untreated water. These issues, along with previous research on managing air conditioner (AC) wastewater at the Lampung State Polytechnic, form the basis for our initiative to utilize AC wastewater as a sustainable resource. Proper management of this abundant water source can support the operation and maintenance of laboratory equipment. The research findings demonstrate that circulating AC wastewater to operate a Soxhlet extraction system for 4.5 hours can reduce clean water consumption by 0.65 cubic meters, equivalent to a cost savings of IDR 43,200. Furthermore, the results indicate improved efficiency, effectiveness, and overall equipment performance when using AC wastewater compared to conventional methods. Contribution to Sustainable Development Goals (SDGs) SDG 6 – Clean Water and SanitationSDG 9 – Industry, Innovation, and Infrastructure:SDG 12 - Responsible Consumption and ProductionSDG 13 - Climate Action

Reconstruction of Defect Paths Using Eddy Current Testing Array 3D Imaging

In a world where the reliability and lifespan of industrial equipment are critical, our research aims to go beyond the traditional limits of non-destructive testing. We seek to achieve accurate detection and comprehensive imaging of defects in their various forms by harnessing the capabilities of eddy current testing with multiplexing technology on multi-element sensors. This approach allows us to save time and ensure the quality of results. This paper presents a method for detecting and imaging different defect paths on an aluminium plate. Our methodology involves the strategic deployment of multi-sensor techniques specifically designed for eddy current testing. To address the inherent challenge of mutual magnetic induction between these sensors, we employ the alternating feed method, which is an advanced technology that ensures data integrity and significantly accelerates scanning times. By combining this technology with multi-sensor techniques, we capture signals that provide valuable insights into the presence of defects. Additionally, we produce 3D imaging that enables us to trace their paths, regardless of size. These preliminary results lay the foundation for future research aimed at accurately characterizing and visualizing the shapes and dimensions of these defects, thereby contributing to a more comprehensive understanding of defect behaviour.

Research on safety input behaviour decision of tower crane from a collaborative perspective

PurposeAs tower cranes are highly dangerous, the problem of insufficient investment in tower safety needs to be solved urgently, and this study aims to solve the problem of insufficient investment in safety caused by the imbalance of interests of tower safety-related subjects and to propose targeted solutions.Design/methodology/approachTower crane rental enterprises, contractors and government departments are selected to construct the game model, calculate the equilibrium point and stability and determine the optimal stabilization strategy. Finally, MATLAB software is used to model and simulate the impact of parameter changes on each party’s choice of strategies.Findings(1) The optimal combination of strategies is safety input by tower companies, leasing of qualified towers by contractors and providing non-financial incentives by the government. (2) The degree of synergistic coefficient γ, the level of government penalty coefficient α and the increase in accident probability p positively affect the adoption of proactive safety measures by tower crane leasing enterprises and contractors. (3) Excessive differences in safety costs may lead firms to adopt hostile safety measures.Originality/valueThis paper creatively uses safety input and tower crane leasing enterprises as the perspective and object of research on tower security. The research results are of great significance in guiding the government to formulate regulatory and incentive policies and in promoting enterprises to implement safety input to ensure construction safety collaboratively. It also provides new research cases for promoting the entire special equipment industry to realize adequate and effective safety input.