Production Line Equipment Research Articles

A novel attention-based long short term memory and fully connected neutral network approach for production energy consumption prediction under complex working conditions

Continuously growing demands due to the predictable faults or abnormal events of the flexible production line are becoming a challenge to easily cause the energy waste, which needs to accurately predict the real-time energy consumption of the actual production process. By reviewing the related works about prediction model approach and energy consumption analysis in the actual production application, it is necessary to overcome two main challenges: optimal prediction selection and internal relation mining of energy consumption under different equipment working conditions. To deal with the existing challenges, the paper proposes a novel attention-based Long and Short-Term Memory (LSTM) approach to predict energy consumption with temporal series under various equipment working conditions. This method offers forecasting support to form a complete prediction framework for the automatic Miniature Circuit Breaker (MCB) production line, which can be used to predict the specific working condition based on attention-based LSTM approach. By comparing various prediction approaches for energy consumption under the working condition prediction with various equipment of different production line, the Fully Connected Neutral (FCN) network approach can achieve a high accuracy and effectiveness based on MAE, R2 and MSE evaluations.

A Model Based on CNN-LSTM for the Remaining Life Prediction of Equipment in Aircraft Assembly Pulsation Production Line

The aircraft assembly pulsation production line is an advanced and efficient assembly method widely used in aircraft manufacturing. However, equipment malfunctions would occur and can disrupt production takt, affecting the production efficiency. Therefore, accurately predicting the remaining useful life (RUL) of equipment is very crucial. To meet the requirements of both prediction accuracy and efficiency for RUL model used in aircraft pulsation production line, this work proposed a model combining convolutional neural network (CNN) and long short-term memory (LSTM) for RUL prediction. Optimization was performed for the number of neurons in the proposed model with genetic algorithm (GA) to regulate the prediction accuracy and efficiency. Two public datasets representing typical equipment in the pulsation production line were used to validate the proposed model. The results show that the proposed model outperforms the traditional model with substantial improvements in the fitness function of 19.8%, and 30.2% for the two testing datasets. These findings demonstrate the effectiveness of the proposed model in enhancing the accuracy and efficiency of RUL prediction.

PREDICTIVE MAINTENANCE OF A FLEXIBLE PRODUCTION LINE IMPLEMENTED IN MATLAB

In the latest years, the need of new technologies in the industrial environment has increased due to the need of a more cost efficient, resilient, and sustainable production process. One of the main issues that is addressed in this research work is the lack of a technology that allows prediction and prevention of the breakdowns of a production line using digital models and artificial intelligence to take the best decisions based on real-time data. This paper presents a method for collecting data from the production line and feed these data to a database used by the Digital Twin model created in Matlab Predictive Maintenance Toolbox in which, based on this data, a decision about the maintenance activities required will be taken. This approach generates significant value by assisting maintenance engineers in pinpointing the precise timing for equipment maintenance. This capability directly contributes to reducing production line downtime and minimizing failures. Also, the Digital Twin model can be used to enable and test adjustments to the parameters of the production line equipment in order to determine the impact of this changes of the production process without interfering with the production process itself.

Digitization of production line equipment of rail transit vehicles based on index and model

In the process of digital transformation of rail transit vehicles, the digitalization of production line equipment is an important content. Starting from the whole life cycle business of production line equipment, this paper improves the existing production line equipment index system, proposes the production line equipment data acquisition model, describes the equipment portrait, proposes the comprehensive evaluation system based on the equipment index model, and further explores the digital twin architecture of production line equipment based on the integration of multiple models. Improve the digital level of rail transit vehicle manufacturing production line equipment.

Improvement in quantum efficiency of green GaN-based micro-LED by trapezoidal quantum well

The main challenges in the application of GaN-based full-color micro-light-emitting diodes (micro-LEDs) are size-dependent effects and low quantum efficiency, especially for green micro-LEDs. In this study, we propose to use a trapezoidal quantum well (QW) structure in GaN-based green micro-LEDs. The trapezoidal QW structure is able to improve the electron hole wave function overlap, thus increasing the external quantum efficiency (EQE). Green micro-LEDs with active region size of 75 × 64 μm2 are fabricated by metal organic chemical vapor deposition. The peak EQE of the green trapezoidal QW micro-LED reaches 15.8% at a low injection current density of 0.6A/cm2, which is 1.96 times higher than that of conventional rectangular QW. The test results indicate that the trapezoidal QW structure greatly improves the quantum efficiency of green micro-LED, inhibits the blue shift of peak wavelength and improves color purity, which paves the way to single substrate full-color micro-LED display with high-performance. The technology proposed in this paper does not change the production line equipment, but improves the traditional process, so it is expected to significantly improve the external quantum efficiency of the existing green micro-LED under the existing equipment. The production technology of existing InGaN QW micro-LED is directly adopted, and the EQE can be further improved if some new dry etching and passivation methods are applied.

Design of real-time monitoring method for production line equipment status based on cloud computing and Internet of Things technology

Design of real-time monitoring method for production line equipment status based on cloud computing and Internet of Things technology

Equipment Identification and Localization Method Based on Improved YOLOv5s Model for Production Line

Intelligent video surveillance based on artificial intelligence, image processing, and other advanced technologies is a hot topic of research in the upcoming era of Industry 5.0. Currently, low recognition accuracy and low location precision of devices in intelligent monitoring remain a problem in production lines. This paper proposes a production line device recognition and localization method based on an improved YOLOv5s model. The proposed method can achieve real-time detection and localization of production line equipment such as robotic arms and AGV carts by introducing CA attention module in YOLOv5s network model architecture, GSConv lightweight convolution method and Slim-Neck method in Neck layer, add Decoupled Head structure to the Detect layer. The experimental results show that the improved method achieves 93.6% Precision, 85.6% recall, and 91.8% mAP@0.5, and the Pascal VOC2007 public dataset test shows that the improved method effectively improves the recognition accuracy. The research results can substantially improve the intelligence level of production lines and provide an important reference for manufacturing industries to realize intelligent and digital transformation.

Achievement of 25.54% power conversion efficiency by optimization of current losses at the front side of silicon heterojunction solar cells

AbstractParasitic absorption in the front window layers of transparent conductive oxide (TCO) films and carrier selective collection layers and the optical shading losses from the metallic finger grid mainly limit the current generation in silicon heterojunction (SHJ) solar cells. In this work, we demonstrate an improved short‐circuit current density (Jsc) of 40.24 mA/cm2 through a combination of novel window layers composed of transition metal doped indium oxide (IMO) and hydrogenated nanocrystalline silicon oxide (nc‐SiOx:H) films and Cu plating for SHJ solar cells. By introducing water vapor during direct current (DC) magnetron sputtering deposition process, IMO films show a large optical band gap (Eg) of about 3.88 eV and high mobility up to 83.2 cm2/V·s, while maintaining a low carrier concentration, which leads to high transparency and low near‐infrared (NIR) free carrier absorption (FCA). In addition to its high deposition rate and crystalline volume fraction, we found that nc‐SiOx:H films deposited by very high frequency (VHF) excited plasma‐enhanced chemical vapor deposition (PECVD) show an excellent surface passivation quality, which not only improves the open circuit voltage (Voc) of SHJ cells but also increases the Jsc through improved carrier selective collection. The quantified Jsc breakdown analysis was performed to identify the room for improvement, and it showed that the front shading loss (about 1.32 mA/cm2) is the largest portion. By combining the benefits of these window layer enhancements with the further use of fine line width and conductivity of Cu plating, SHJ solar cells, with a Jsc improvement of 0.57 mA/cm2 and a certified efficiency of 25.54%, were achieved on a total area of 274.5 cm2 using in‐house pilot production line equipment.

Retracted] Computational Intelligence and Things Technology‐Based Collection and Design of Inheritance Characteristics of Tea Product Packaging Art Form

In view of the core process data such as temperature and humidity of the tea product packaging process and the automatic control operation parameters of the production line, this paper designs a smart tea product packaging 5G Internet of Things gateway system, which realizes the 5G Internet of Things onsite monitoring and remote monitoring of the tea product packaging production line equipment. The design and implementation of the 5G Internet of Things gateway system are divided into three aspects, namely, 5G Internet of Things gateway configuration design, data communication protocol conversion. First, the 5G Internet of Things gateway configuration is to design the relevant control information of the tea processing production line equipment and complete the configuration storage of the PLC controller; secondly, the data communication protocol conversion is to pass the Modbus/TCP OPC standard to transfer the collected 5G Internet of Things. The sensor data undergoes unified standardized conversion, and then the standardized converted data is sent to the database and server using the MQTT protocol; the data processing of the 5G Internet of Things gateway system is the design of the internal data of the 5G Internet of Things gateway. Finally, the test was carried out and the results were obtained, which proved that the designed 5G Internet of Things gateway system is useable, reliable, has good stability and scalability, and provides an important solution for the construction of smart tea product packaging in the industry. The tea product packaging system based on 5G Internet of Things technology compiles electronic production management files for tea garden production, tea picking, tea processing, tea packaging and other links in accordance with the requirements of the national agricultural product quality and safety related systems and industry standards, and has become the traceability of tea quality The recorded important production management information provides important information support for the traceability of the whole process of tea.

Construction and Evolution of Fault Diagnosis Knowledge Graph in Industrial Process

The steel industry production line is complicated and contains a substantial amount of equipment, leading to serious problems in fault diagnosis such as wrong inspection strategies, fault location, maintenance, and so on. To realize accurate and efficient equipment fault diagnosis, this paper proposes a steel production line equipment fault diagnosis knowledge graph (SPLEFD-KG) based on a novel relation-oriented model with global context information for jointly extracting overlapping relations and entities (ROMGCJE). A low-level self-learning SPLEFD-KG is first constructed using the triples extracted by ROMGCJE. However, this low-level SPLEFD-KG is incomplete, and only contains sparse paths for fault reasoning. To overcome this problem, a reinforcement learning framework is applied to mine hidden semantic knowledge to complete the missing relation. Besides, the graph neural networks are introduced to compute the embedding vector of new entities outside of the SPLEFD-KG for continuously completing missing entities. Finally, the low-level self-learning SPLEFD-KG evolves to one high-level SPLEFD-KG, which can provide information-rich and accurate fault-related knowledge. Extensive experiments conducted on the steel production line equipment failure dataset indicate that the novel SPLEFD-KG significantly improves fault diagnosis results and provides effective maintenance programs.

Performance of Priority-Based Traffic Coexistence Strategies in 5G mmWave Industrial Deployments

Recently standardized New Radio (NR) technology supports both ultra-reliable low-latency (URLLC) service and conventional enhanced mobile broadband (eMBB) service. Owing to extreme latency and reliability requirements an explicit prioritization needs to be provided to URLLC service when these traffic types are mixed up at the air interface. In this work, we consider simultaneous support of these two services in an industrial environment, where production line equipment utilizes URLLC service for reorganization and synchronous operation while eMBB service is used for remote monitoring. By utilizing the tools of stochastic geometry and queuing theory, we formalize the model with pre-emptive priority service at NR base station (BS) with and without direct device-to-device (D2D) communications. Our numerical results indicate that the priority-based implementation of URLLC and eMBB coexistence allows us to isolate the former traffic efficiently and requires no external control. D2D-aware strategy, where the BS explicitly reserves some resources for direct communications, drastically outperforms those, where no explicit reservation is utilized, as well as the baseline strategy where all the traffic goes through the BS. This strategy can achieve 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−5</sup> of URLLC drop probability when the baseline strategy produces just <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5\times 10^{-3}$ </tex-math></inline-formula> , leading to three orders of magnitude reduction in drop probability and without significant impact produced on eMBB session drop probability. The developed model can be utilized to estimate the NR BS density required to support prescribed performance guarantees for all the considered strategies.

A Digital Twin-Oriented Lightweight Approach for 3D Assemblies

In the design and operation scenarios driven by Digital Twins, large computer-aided design (CAD) models of production line equipment can limit the real-time performance and fidelity of the interaction between digital and physical entities. Digital CAD models often consist of combined parts with characteristics of discrete folded corner planes. CAD models simplified to a lower resolution by current mainstream mesh simplification algorithms might suffer from significant feature loss and mesh breakage, and the interfaces between the different parts cannot be well identified and simplified. A lightweight approach for common CAD assembly models of Digital Twins is proposed. Based on quadric error metrics, constraints of discrete folded corner plane characteristics of Digital Twin CAD models are added. The triangular regularity in the neighborhood of the contraction target vertices is used as the penalty function, and edge contraction is performed based on the cost. Finally, a segmentation algorithm is employed to identify and remove the interfaces between the two CAD assembly models. The proposed approach is verified through common stereoscopic warehouse, robot base, and shelf models. In addition, a scenario of a smart phone production line is applied. The experimental results indicate that the geometric error of the simplified mesh is reduced, the frame rate is improved, and the integrity of the geometric features and triangular facets is effectively preserved.

Accuracy Improvement in Resolver Offset Detection Based on Angle Tracking Observer with Coordinate Transformation

It is necessary to obtain the rotor position of the Interior Permanent Magnet Synchronous Motor (IPMSM) for instantaneous torque control in an electric vehicle system. A resolver is mostly used as a rotor position sensor, each motor has a resolver offset according to the fit tolerance of the resolver pressed into the rotor shaft when the motor is manufactured. This resolver offset is having a huge effect on IPMSM output characteristics. Therefore, resolver offset detection equipment with a method for high precision of detection is required in production lines in order to make uniform characteristics of IPMSM. It is also necessary to have robust performance in many different kinds of the noise of equipment in the production line. This paper presents a highly precise Resolver to Digital Converter (RDC) that is implemented with LabVIEW of National Instruments and a resolver offset detecting method that has the robust performance to noise based on coordinate transformation algorithm. Experiments with and without the proposed method were performed and a comparative analysis is conducted to test the validity.

The Design of Automatic Carton Packing System of Tobacco Based on STM32

This article is aimed at the requirements of a cigarette factory’s off-site technical transformation task, and it needs to transfer part of the stem and expanded silk produced by the new factory to the old factory. Therefore, it is necessary to construct a set of fully automatic carton packing system for shredded tobacco to improve production efficiency and reduce labor intensity. The system is divided into mechanical equipment layer, equipment control layer and production monitoring layer. The mechanical equipment layer is the design of the process flow between the various machinery and equipment of the tobacco packing production line; the equipment control layer is based on the STMicroelectronics32(STM32) single-chip microcomputer as the control core, through Modbus The protocol controls each device and performs data transmission, and communicates with the upper computer through the industrial Ethernet and Modbus Transmission Control Protocol(Modbu TCP) protocol; the production monitoring layer is based on the Qt programming tool for interface design and data transmission with the lower computer, and the relevant data is stored in My Structured Query Language (MySQL) In the database. This solution realizes the automation, networking and intelligence of industrial production lines, liberating manpower and improving efficiency.

Application on Mobile Learning by Video Manual: A Study of HRD from Bicycle Manufacturing.

Video messages are easier to receive than text messages because of the lack of language and text barriers. In the past, when on-the-job training for junior employees were conducted in the manufacturing industry, they often carried out technical training with “mentorship system” or “work manual”. This study aims at how video makes effects to those who work in manufacturing industries, especially those from other countries. Migrant workers from abroad or companies with manufacturing plants overseas have gradually used video manual as teaching materials for enterprise education and training, especially when COVID-19 becomes a global epidemic crisis. This study used in-depth interview research methods to investigate both workers and managers in the same manufacturing industry. The results found that when using digital cameras to record and edit, the production line equipment can achieve the following effects: (1) Promoting junior workers’ self-efficacy; (2) Use of different language translations can provide simultaneous education and training for workers from multiple countries; (3) Putting digital teaching materials on cloud will make employees to use digital mobile vehicles to download and learn, that can save more time for employees.

Application of reusable flat-membrane in electro-membrane extraction for tamsulosin hydrochloride determination in cleaning validation samples of sterile production line equipment by RP-HPLC

In order to ensure compliance with the current Good Manufacturing Practice (cGMP), cleaning process of pharmaceutical manufacturers should be validated. This study was aimed to utilize a reusable flat-membrane in the electromembrane extraction (EME) for isolation of tamsulosin hydrochloride (TMS) from rinse samples of sterile production of pharmaceutical line. Moreover, validation of mentioned method was done. The residual concentration of TMS was determined by RP-HPLC. Effective parameters such as pH, applying voltage and extraction time were optimized individually. Optimum conditions were found 12, 100 V and 10 min for pH, applying voltage and extraction time, respectively. Figures of merit were calculated under optimum conditions, therefore, linear range and limit of detection (LOD) were obtained 0.5-1000 ng mL−1 with a good coefficient of determination (R2=0.9901) and 0.05 ng mL−1, respectively. Last but not least, RSD of determination was found 0.67% which shows a satisfactory repeatability. According to the obtained results, proposed method is a precise, accurate, relatively fast and applicable route to determine TMS concentrations in rinse samples.

A Research on the Combined Maintenance Strategy for Production Line Equipment Based on Mixed Failure Rate

In order to improve the reliability of the production line and reduce its maintenance costs, this paper establishes preventive maintenance (PM) models of the equipment, which are classified into different levels based on mixed failure rate. The differential and targeted maintaining strategies are formulated as well. First, a method for dividing important equipment and secondary equipment of a production line based on grey interval Analytic Hierarchy Process- (AHP-) Entropy method is proposed. Next, the dynamic service age regression factor and the dynamic failure rate increasing factor are combined to establish a mixed failure rate model. Finally, for the important equipment and secondary equipment, two PM models are established with the constraint of reliability, the objective of maximum availability, and minimum maintenance cost rate to determine the optimal number of PM and cycles. Combined with an example of production line equipment, the optimal maintenance strategies for important equipment and secondary equipment are obtained. The result verified the feasibility of the model, which effectively improved the reliability of the production line equipment and reduced maintenance costs.

Programmable Motion-Fault Detection for a Collaborative Robot

Smart factories should be able to respond to catastrophic situations proactively, such as recalls caused by production line disruptions and equipment failures. Therefore, the necessity for predictive maintenance technology, such as fault detection or diagnosis of equipment has increased in recent years. In particular, predicting the faults of collaborative robots is becoming increasingly crucial because smart factories pursue efficient collaboration between humans and devices. However, collaborative robots have the characteristic of executing programmable motions designed by an operator, rather than performing fixed tasks. If existing fault diagnosis methods are applied to non–fixed programmable motions, problems arise in terms of setting absolute criteria for fault analysis, interpreting the meanings of detected values, and fault tracking or fault cause analysis. Therefore, we propose a method of programmable motion-fault detection by analyzing motion residuals to solve the three problems mentioned above. The proposed method can expand the fault diagnostic range of collaborative robots.

Research on Logistics Simulation and Optimization of Die Forging Production Line Based on Flexsim

Long forging production cycle and low equipment utilization are the important problems currently facing domestic die forging ring production lines. To solve this problem, a simulation optimization method for die forging production line based on Flexsim was proposed. Firstly, the ECRS theory method was used to analyze the bottleneck process of the production line. Then, built a logistics simulation model of die forging production line based on Flexsim, The parallel and cycle processing steps was set reasonable parameters and simulated. Next, through logic analysis, methods such as adding processing equipment, improving equipment efficiency and balancing equipment handling tasks were used to optimize and improve the production line. Finally, compared and analyzed the original and optimized model. The simulation results show that the optimized production line equipment task allocation tends to be rationalized, the equipment utilization rate is increased by 4.34%, and the product cycle time is reduced by 27.65%, and optimized planning and design are achieved.

Using PDE model and system dynamics model for describing multi-operation production lines

Two classes of models for describing production flow lines are analyzed. The use of models of these classes for the design of highly efficient control systems of production lines, the technological route of which consists of a large number of technological operations, is analyzed. The division of the technological route into a large number of operations is caused by the development trend of modern production lines. Synchronization of production line equipment performance is provided by an accumulating buffer. A formalized description of the production line was used as a foundation for constructing equations for each models class. The common features of using each models class in the description of production systems, as well as the conditions for their application are shown. The form of the system dynamics model and PDE model equations is substantiated. The assumption about a deterministic rate of processing parts and the absence of a time delay and feedback between the parameters of technological operations was made when deriving the equations. The use of generalized technological operations in the system dynamics model as a way to reduce the number of model equations is discussed. Two limiting transitions from the PDE model equations to the system dynamics equations are demonstrated. It is shown that the system dynamics equations are a special case of the PDE model equations, the result of aggregation of production line parameters within the technological operation. The method for constructing level equations for the system dynamics model is substantiated. For production lines with a different number of operations, the solution to the problem of processing parts along a production line is presented. The comparative analysis of the solutions obtained using the system dynamics and PDE model equations is obtained.