Automotive Production Line Research Articles

A parallel strategy for predicting the quality of welded joints in automotive bodies based on machine learning

Due to the complexity of the resistance spot welding process, it is still a challenge to accurately know the operating status of the welding robot under the current parameter settings and to assess the welding quality of electrode caps under different types of plates in real time with large data sizes. To solve this problem, this paper classifies the overall data set and proposes a parallel strategy method for predicting the quality of weld joints using machine learning for subsets of the data with different distribution patterns. Firstly, the PCA dimensionality reduction model was used to set the number of principal components to reduce the dimensionality of the welding process feature value dataset and reduce the difficulty of classifying the data subgroups, and the elbow method was used to set the number of clustering centers to complete the classification of the sub-datasets by applying the k-means model on the basis of the dimensionality reduction data. Finally, the feature parameters of each sub-dataset are used as input for machine learning, and a parallel prediction strategy for weld joint quality is developed based on the data distribution characteristics of each sub-dataset. The test results show that the model in this paper outperforms the static BP neural network in predicting the quality of all types of welded joints, the machine learning parallel strategy tailored to the characteristics of the data population works well with more complexly distributed welded big data. This paper provides accurate and effective estimation of body resistance welding condition, which can provide some guidance for online inspection of body resistance spot welding quality in automotive production lines.

The effect of the supply chain in the quick response manufacturing (QRM) environment in the automotive industry

The manufacturing industry is having an issue regarding the quality of the company's planning to produce efficient performance throughout the year. The improvement needs to be carried out to give customers considerable satisfaction regarding the quality of the products and the delivery time. As the manufacturing industry evolves throughout the decades, the demands are becoming more challenging: faster delivery and better quality of products. The markets will interrupt a good supply chain of a company. The Quick Response Manufacturing (QRM) approach significantly benefits companies whose focus is on lead time reduction. This study aims to reduce the lead time and to improve the supply chain of a selected automotive production line by using Witness software simulation. The improvement also sought to implement the Just-In-Time (JIT) inventory management method. The data collected from company X is simulated to get the percentage of idle, blocked, and overall process time. By using the data from the selected line, the improvement of the overall process time is 27.5%, meaning that the company is ready to implement the JIT inventory management method.

Continuous Productivity Improvement Using IoE Data for Fault Monitoring: An Automotive Parts Production Line Case Study.

This paper presents a case study of continuous productivity improvement of an automotive parts production line using Internet of Everything (IoE) data for fault monitoring. Continuous productivity improvement denotes an iterative process of analyzing and updating the production line configuration for productivity improvement based on measured data. Analysis for continuous improvement of a production system requires a set of data (machine uptime, downtime, cycle-time) that are not typically monitored by a conventional fault monitoring system. Although productivity improvement is a critical aspect for a manufacturing site, not many production systems are equipped with a dedicated data recording system towards continuous improvement. In this paper, we study the problem of how to derive the dataset required for continuous improvement from the measurement by a conventional fault monitoring system. In particular, we provide a case study of an automotive parts production line. Based on the data measured by the existing fault monitoring system, we model the production system and derive the dataset required for continuous improvement. Our approach provides the expected amount of improvement to operation managers in a numerical manner to help them make a decision on whether they should modify the line configuration or not.

Multi-objective optimization of energy-efficient production schedules using genetic algorithms

The optimization of production schedules to be more energy efficient while still meeting production goals is a difficult task: How to schedule and distribute production tasks to meet production goals, while making best use of fluctuating energy market prices and availability of locally installed energy sources? Although a large body of related work exists in this domain, most of those seem to focus on individual aspects and not the whole picture. In this paper, a genetic algorithm for optimization of production schedules with respect to energy consumption, peak shaving, and makespan is presented, that also takes into account that tasks can be performed in different ways, having different characteristics. The algorithm has been successfully employed within the SPEAR project by applying it for optimization of an automotive production line and for the pathway of an automated guided vehicle.

Digital twin–based cyber-physical system for automotive body production lines

At automotive manufacturing sites, meeting the delivery schedule is difficult owing to the occurrence of unpredictable abnormal scenarios such as product defects and equipment failures. To overcome this, manufacturing technologies developed as part of the Fourth Industrial Revolution are employed to meet the delivery schedule set by the customer. We propose a digital twin (DT)–based cyber-physical system (CPS) that can predict whether a product can be manufactured as per the schedule requested by a customer at an automotive body production line where abnormal scenarios occur. We designed a product, process, plan, plant, and resource information model for automotive body production lines; the proposed DT employs this model. Unlike in previous research on DTs focusing on independent engineering application development, we designed and implemented a CPS combined with a DT and other components for a Web-based integrated manufacturing platform. To the best of our knowledge, this is the first time a DT-based CPS is implemented for abnormal scenarios involving automotive body production lines; the capability of the proposed system was verified via experiments. The experimental results indicate that the proposed system achieved an average prediction performance of 96.83% for the actual production plan. We confirmed that the DT-based CPS can be applied to automotive body production lines, and it provides an advanced solution to predict whether production is possible according to the production plan.

Click-event sound detection in automotive industry using machine/deep learning

In the automotive industry, despite the robotic systems on the production lines, factories continue employing workers in several custom tasks getting for semi-automatic assembly operations. Specifically, the assembly of electrical harnesses of engines comprises a set of connections between electrical components. Despite the task is easy to perform, employees tend not to notice that a few components are not being connected properly due to physical fatigue provoked by repetitive tasks. This yields a low quality of the assembly production line and possible hazards. In this work, we propose a sound detection system based on machine/deep learning (ML/DL) approaches to identify click sounds produced when electrical harnesses are connected. The purpose of this system is to count the number of connections properly made and to feedback to the employees. We collect and release a public dataset of 25,000 click sounds of 25 ms length at 22 kHz during three months of assembly operations in an automotive production line located in Mexico. Then, we design an ML/DL-based methodology for click sound detection of assembled harnesses under real conditions of a noisy environment (noise level ranging from −16.67 dB to −12.87 dB) including other machinery sounds. Our best ML/DL model (i.e., a combination between five acoustic features and an optimized convolutional neural network) is able to detect click sounds in a real assembly production line with an accuracy of 94.55±0.83 %. To the best of our knowledge, this is the first time a click sounds detection system in assembling electrical harnesses of engines for giving feedback to the workers is proposed and implemented in a real-world automotive production line. We consider this work valuable for the automotive industry on how to apply ML/DL approaches for improving the quality of semi-automatic assembly operations.

Forming a Flanged Hole When Quenching Press-Hardened Steel for Mechanical Fastening

The recent stringent regulations on vehicle safety and reducing CO2 emissions have led to a continuous increase in the application of press-hardened steel (PHS) in automobiles. Similar to other high-strength steels, assembling PHS components using the common welding techniques employed in automotive production lines is significantly difficult because of the surface coating layers and the additives within. This difficulty in post-processing, attributed to its high strength, also limits the mechanical fastening of PHS components. Therefore, this study aims to develop a process for forming a structure enabling mechanical fastening by sequentially applying piercing and hole-flanging operations during the hot stamping process. Our experimental apparatus was designed to perform the hole-flanging operation after the piercing operation within a single stroke at a specific temperature during the quenching process of PHS. At high temperatures of 440 °C or higher, the hole-flanging process was conducted in a direction opposite to that of the piercing operation for creating the pilot hole. An extruded collar with a height of 8.0 mm and a diameter of 17.5 mm was achieved, which is hole expansion ratio(HER) of 82.5%.

A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder

This paper investigates the unsupervised automatic feature extraction method with a large amount of unlabeled data for the fault diagnosis of rolling bearings in automobile production line, where the fault information is hard to identify due to the low-level features of a single category and the massive fault data is difficult to process. Different from the existing methods, which only combine the compressive sensing with single category of low-level features, or extract features from raw data, a novel intelligent fault diagnosis method for rolling bearings based on the compressive sensing and a stacked multi-granularity convolution denoise auto-encoder network is proposed, which utilizes the nonlinear projection to achieve the compressed acquisition and resolves issues with character unicity by extracting a diverse category of high-level features. Moreover, a regularization method called ‘dropout’ is used to prevent overfitting during the training process. The amount of measured data that contained all the information of faults is reduced and the classification accuracy is improved by extracting more robust features based on the proposed method. Finally, the effectiveness of the proposed method is validated using data sets from rolling bearings in an automotive production line and the analysis result show that it is superior to the existing methods and is able to obtain high diagnostic accuracies.

Generalized Composite Multiscale Diversity Entropy and Its Application for Fault Diagnosis of Rolling Bearing in Automotive Production Line

This paper considers the entropy based feature extraction method for the fault diagnosis of rolling bearings in automobile production line, where the fault information is difficult to identify due to the strong nonlinear and non-stationary characteristics of the fault vibration signals. In our work, a novel entropy based method called generalized composite multiscale diversity entropy (GCMDiEn) is developed. This method can effectively track the inside pattern changes of the time series by the description of cosine similarity between adjacent orbits. Unlike most of the existing entropy based results which concentrate on the static orderliness, we analyze the dynamic complexity characteristics of the arbitrary time series. Moreover, compared with the multiscale diversity entropy, GCMDiEn calculates all coarse-grained time series entropy value with the same scale and extends the first-order moment to second-order moment to mitigate the shortcomings of the short time series instability and losing part of the frequency region information. This paper proposed a new rolling bearing fault diagnosis framework which combined the GCMDiEn with the empirical wavelet transform (EWT), Laplacian score (LS), and particle swarm optimization-based support vector machine (PSO-SVM). Finally, the simulation results show the superiority of the GCMDiEn method over the multiscale diversity entropy method. The proposed framework has a higher fault recognition rate (99.38%) than the existing methods.

Measuring sequence stability in automotive production lines

ABSTRACT We consider the question of how stability in automotive manufacturing systems should be analysed. This topic is motivated by the need of original equipment manufacturers to evaluate the performance of their production system to ensure efficiency and long-term competitiveness. In order to deal with the increasing complexity of the manufacturing process, original equipment manufacturers need to focus on efficiency in the manufacturing process and supply chain. Since stability is one determining factor of efficiency they need to implement indicators to quantify and visualise stability. While the overall target for the long-, mid- and short-term planning processes remain the same, the application of and specifications for performance measures differ. We present, analyse and evaluate different indicators and reveal their capability to represent the status of stabilised production facilities. We also describe the challenges that arise when implementing these performance measures in real-world production facilities and give recommendations on how to manage these challenges. We provide a framework to assign indicators to planning problems. The transparency provided by accurately chosen indicators fosters understanding of the overall performance of the system and enhances the management of stabilised production.

Investigation of Oil Palm Empty Fruit Bunch (OPEFB) Embedded with Artocarpus Odorattisimus Mechanical Behaviour as an Alternative Replacement for Raw Material in Wood Industry

This paper presented the investigation of Oil Palm Empty Fruit Bunch (OPEFB) reinforced with Artocarpus Odorattisimus (Mahang/Tarap) board in which fabricated manually using hand lay method and hot pressed in order to determine a suitable alternative fiber board as a replacement for the usage of woods as raw materials in various types of industry. The idea of conducting this research came due to the worldwide community attention on major deforestation which may lead to natural disaster throughout the world. The effects of adding Artocarpus Odorattisimus (Mahang/Tarap) to the oil palm empty fruit bunch (OPEFB) on certain dry weight ratios are being studied and the main objective of this research is to determine certain mechanical properties of the board especially tensile strength to be compared to the pure oil palm empty fruit bunch (OPEFB) board (4.712 Nmm-2)[22]. The experimental process is carried out in accordance to test standard of ASTM D3039/3039m-17. Morphological structure study by using Scanning Electron Microscope (SEM) also conducted on the tested samples to further understand the board properties.Practically, aluminium swarf (chips) collected from an automotive production line is less likely to have any contaminants once the lubricants are removed. In theory, metals do not degrade in value and can be used infinitely.

Application of Virtual Manufacturing Technology Based on Computer in Automotive Stamping Production Line

With the rapid progress of information technology, it has been widely used in various fields and made a lot of achievements. The application of virtual manufacturing technology can analyze and manage the process of automotive stamping production. It can improve the usage of various resources and the decision-making ability in the process of automotive stamping. It can also analyze the automotive manufacturing process from many angles in order to ensure the efficiency of stamping technology. In this paper, through the generalization of virtual manufacturing technology and automotive stamping production line, it analyses and summarizes the application process of virtual manufacturing technology in automotive stamping line.

Development of a risk-based maintenance decision making approach for automotive production line

Automotive industries require effective and reliable maintenance strategies to ensure high levels of availability and safety. Risk-based maintenance approach is a useful tool for maintenance decision making with the aim of reducing the overall risk in operating activities. In this paper, a Failure Mode and Effect Analysis (FMEA) model as one of the risk assessment techniques is developed with subjective information derived from domain experts. To overcome the drawbacks of traditional FMEA for risk priority number (RPN) estimation, a linguistic fuzzy set theory, through effective decision attributes in complex automotive equipment is conducted. The main attributes of this approach include the effect of experts’ traits, scales variation, using various membership functions and defuzzification algorithms on reliable Fuzzy-RPN (FRPN) estimation. The result of the proposed model revealed that altering membership functions and defuzzification algorithms had no significant effect on the FRPN estimation, but their values are highly affected by the number of scales. The sensitivity analysis showed that experts’ traits have no sensible impact on experts’ opinion for FRPN estimation, while the detectability index has more impact on FRPN variation. The result of risk classification number showed that the maintenance decision making could be included for the failure modes with the highest RPN values as a priority, which it would be useful to achieve the high level of availability and safety.

An improved fuzzy inference system-based risk analysis approach with application to automotive production line

Reliability and safety in the process industries like automotive industry are important key success factors for upgrading availability and preventing catastrophic failures. In this context, failure mode and effect analysis (FMEA) technique is a proactive diagnostic tool for evaluating all failure modes which reduces the highest risk priority failures. However, it still suffers from subjective uncertainty and ambiguity which are important factors in risk analysis procedures. Hence, this paper provides a comprehensive survey to overcome the drawbacks of the traditional FMEA through improved FMEA, incorporating the fuzzy inference system (FIS) environment. For this purpose, the effective attributes, such as; various scales and rules, various membership functions, different defuzzification algorithms and their impacts on fuzzy RPN (FRPN) have been investigated. Moreover, three types of sensitivity analysis were performed to identify the effect and authority control of risk parameters, i.e., severity, occurrence and detection on FRPN. To demonstrate the feasibility of the proposed framework, as a practical example, the method was implemented in complex equipment in an automotive production line. The result of FIS-FMEA model revealed that the proposed framework could be useful in recognizing the failure modes with critical risk values compared to the traditional FMEA. Given the potential applications of this approach, suitable maintenance actions can be recommended to improve the reliability and safety of process industry, such as automotive production line.

Event-Driven Online Machine State Decision for Energy-Efficient Manufacturing System Based on Digital Twin Using Max-Plus Algebra

Energy-efficient manufacturing is an important aspect of sustainable development in current society. The rapid development of sensing technologies can collect real-time production data from shop floors, which provides more opportunities for making energy saving decisions about manufacturing systems. In this paper, a digital twin-based bidirectional operation framework is proposed to realize energy-efficient manufacturing systems. The data view, model view, and service view of a digital twin manufacturing system are formulated to describe the physical systems in virtual space, to perform simulation analysis, to make decisions, and to control the physical systems for various energy-saving purposes. For online energy-saving decisions about machines in serial manufacturing systems, an event-driven estimation method of an energy-saving window based on Max-plus Algebra is presented to put the target machine to sleep, considering real-time production data of a system segment. A practical, simplified automotive production line is used to illustrate the effectiveness of the proposed method by simulation experiments. Our method has no restriction on machine failure mode and predefined parameters for energy-saving decision of machines. The proposed approach has potential use in synchronous and asynchronous manufacturing systems.

Operational reliability evaluation-based maintenance planning for automotive production line

ABSTRACTReliability evaluation plays a critical role in upgrading the availability and productivity of automotive manufacturing industries by adopting the well-planned maintenance. Due to the lack of operation management studies in automotive industry, this paper addresses an operational reliability evaluation through failure behavior trend in an automotive production line. The main approaches for reliability analysis in this study include statistical structure and Monte Carlo simulation model. The statistical structure consists of three steps: data acquisition and homogenization process, validity of the trend hypothesis and parameters estimation. The reliability evaluation under statistical approach identified the main bottlenecks through the recognized behavior trend of system so that needs to be considered as a priority. Besides, K–R algorithm as Monte Carlo simulation was carried out to simulate reliability regarding failure distribution function. The result of Monte Carlo simulation with different iterations provides a high prediction accuracy of reliability with the lowest error. In addition, regarding the computed reliability through the proposed approaches and total expected cost, a reliability-based maintenance optimization model was conducted. The proposed maintenance intervals could be useful for improving the operational performance of critical components in automotive system.

A mini review: Lean management tools in assembly line at automotive industry

Malaysia is active in automotive manufacturing activity for decades. The needs in continuing development of lean manufacturing tools are not exempt to be pressurised, which enable the regional demand for vehicles. Several research studies clearly indicate significant opportunities for efficiency improvement in the automotive industry through implementation and a higher level of lean management utilization. Apparently, there is still a small number of study for Lean Management Tools in a Malaysian Automotive Assembly Line. The emphasis for the study is to investigate practices of lean tools applied in the production line and proposing an implementation of lean management tools available to apply in the Malaysian automotive production line work practice. A review study of literature from different journal publication sources related to lean management tools was made to understand more on how to best identify practices of lean tools. From this literature study review, three lean management tools have been investigated and identified such as 5S, Value Stream Mapping (VSM) and Work Standardization are to be studied for proposed application in the Malaysian automotive assembly production line. The impact of implementing lean tools is studied based on the results gathered from previous studies related to 5S, VSM and Work Standardization. The conclusion of this paper is to investigate the practices and implementation of Lean Management Tools in the Malaysian Automotive Assembly. It is to be suggested that a future case study on the proposed lean tools using time study and observational survey to be implemented in Malaysian automotive assembly line and measuring the improvements gained from utilizing the selected lean tools. The result from this review is that among the lean tools highlighted here, 5S is applied everywhere in an automotive assembly line, supported by VSM with its overview of the whole process and also Work Standardization to standardize the method and flow of work in an assembly line and improve the consistency of work. Therefore, concluding this study would be the importance of 5S, VSM and Work Standardization as the implemented tools in an automotive assembly line, in view of overcoming the challenges of the constant change in customer demand.

A TPM strategy implementation in an automotive production line through loss reduction

In this paper the implementation of a total productive maintenance (TPM) plan is described for the reliability of an automotive production line of machining and assembly. This production line is considered critical for the industrial unit in this case study. In order to improve the current state of the machines operating on the production line, several steps were made in order to identify the potential anomalies. The used strategy is the reduction of losses caused by machine failures, the focus of which is the development of problem identification actions such as accelerated degradations, forced degradations and subsequent correction of anomalies. Another focus is the restoration of the state of reference, in case of being in agreement with the current process, and the development of actions to avoid the occurrence of new malfunctions and faults. Several improving actions were performed after identifying several challenges. In this analysis, it was possible to assess that the operating income of the line evolved positively from the moment the actions began to be implemented. In the end an 18% increase was obtained in operating results compared to the initial period of analysis.

Assembly line design using a hybrid approach of lean manufacturing and balancing models

ABSTRACTThis manuscript presents a method to design automotive production assembly lines that integrate lean manufacturing approaches and line balancing algorithms. In this work, we develop a clustering algorithm and task mutuality index for the assembly tasks to redesign and rebalance an assembly production line with a fixed layout and machinery. Moreover, we consider the product demand variability and the introduction of new product models. This paper describes the current and the future states of an automotive engines assembly production line using quantitative performance parameters and assembly tasks content flow charting, along with the analysis and results obtained from the proposed approach. The results show a reduction in required modeling and optimization efforts and a reduction in the required time to generate a feasible redesign of an assembly line while reaching the required takt time based on the demand forecast.

Implementing TPM supported by 5S to improve the availability of an automotive production line

The maintenance management is a topic of strategic importance for automotive manufacturers. In fact, an effective maintenance process and a preventive maintenance (PM) procedure can significantly reduce the risk of equipment failures that can lead to downtime on the production lines. However, due to the complexity of an automotive production system, the risk of failure on a crucial piece of the production equipment cannot be entirely avoided. The study made in this paper aims at improving the availability of a critical production line through the total productive maintenance (TPM) methodology and supported by Lean Maintenance tools. An analysis is made of the initial condition of the line where the main problems are identified by employing several tools for this purpose, such as Mean Time between Failures (MTBF), Mean Time to Repair (MTTR), Overall Equipment Efficiency (OEE) and Availability (A). In response to the identified problems, an action plan is developed and implemented in order to find the root cause of the high number of malfunctions and faults in one of the line’s equipment with the use of 5S tools, visual management, and maintenance progress, as well as the development of a training program to increase operators’ skills. The results of such actions were positive as the line became more organized, the value of the MTBF increased, the MTTR value decreased, and consequently the overall availability increased.