Real-time Manufacturing Process Research Articles

A data-driven distributed process monitoring method for industry manufacturing systems

Process monitoring technology can help make the right decisions in manufacturing, but the complexity and scale of modern process industry processes render process monitoring difficult. Existing data-driven process monitoring methods utilize abundant monitoring data that are accumulated in industrial processes, but nonlinearity, high coupling, noise effects, and other problems continuously appear in process industry monitoring data. This study proposes a process monitoring method based on variational autoencoder and long short-term memory techniques. The method reconstructs the monitoring data by learning their distribution and time series characteristics under the controlled state, and then it monitors the state of the manufacturing process in real time by calculating the statistics. Evaluation is conducted using the Tennessee Eastman process case verification and experimental comparison method. Then, the proposed method is compared with the centralized process via principal component analysis and kernel principal component analysis. The results show that the proposed method can more significantly improve the effect of fault detection in distributed system process monitoring compared with the traditional method, and it has a better process monitoring effect.

Automated coplanarity inspection of BGA solder balls by structured light

The coplanarity of BGA (Ball Grid Array) solder balls is critical for reliable connectivity in semi-conductor units. However, existing ball height inspection techniques require high-cost equipment and skilled operators, which are not feasible for using in real-time manufacturing process. In this paper, a fast measurement method of coplanarity inspection of solder balls is developed based on structured light technique. The hardware of the system includes a camera and a projector. The digital-light-processing (DLP) projector emits programmed image patterns and the digital complementary-metal-oxide-semiconductor (CMOS) camera captures distorted image patterns on solder balls. The image processing software is developed to compare the original and distorted image patterns to reconstruct the three-dimensional (3D) solder balls. The method has been calibrated extensively and exhibits accuracy within 5 μm mean squared error compared to ground truth values determined by X-ray computed tomography. The proposed method achieves reliable, in-line ball height measurement and could be potentially used for real-time in-line coplanarity inspection of BGA chip during manufacturing.

Novel Benchtop Magnetic Particle Spectrometer for Process Monitoring of Magnetic Nanoparticle Synthesis.

Magnetic nanoparticles combine unique magnetic properties that can be used in a variety of biomedical applications for therapy and diagnostics. These applications place high demands on the magnetic properties of nanoparticles. Thus, research, development, and quality assurance of magnetic nanoparticles requires powerful analytical methods that are capable of detecting relevant structural and, above all, magnetic parameters. By directly coupling nanoparticle synthesis with magnetic detectors, relevant nanoparticle properties can be obtained and evaluated, and adjustments can be made to the manufacturing process in real time. This work presents a sensitive and fast magnetic detector for online characterization of magnetic nanoparticles during their continuous micromixer synthesis. The detector is based on the measurement of the nonlinear dynamic magnetic response of magnetic nanoparticles exposed to an oscillating excitation at a frequency of 25 kHz, a technique also known as magnetic particle spectroscopy. Our results underline the excellent suitability of the developed magnetic online detection for coupling with magnetic nanoparticle synthesis based on the micromixer approach. The proven practicability and reliability of the detector for process monitoring forms the basis for further application fields, e.g., as a monitoring tool for chromatographic separation processes.

A Real-Time Quality Control System Based on Manufacturing Process Data

Quality prediction is one of the key links of quality control. Benefitting from the development of digital manufacturing, manufacturing process data have grown rapidly, which allows product quality predictions to be made based on a real-time manufacturing process. A real-time quality control system (RTQCS) based on manufacturing process data is presented in this paper. In this study, the relationship between the product real-time quality status and processing task process was established by analyzing the relationship between the product manufacturing resources and the quality status. The key quality characteristics of the product were identified by analyzing the similarity of the product quality characteristic variations in the manufacturing process based on the big data technology, and a quality-resource matrix was constructed. Based on the quality-resource matrix, the RTQCS was established by introducing an association-rule incremental-update algorithm. Finally, the RTQCS was applied in actual production, and the performance of RTQCS was verified by experiments. The experiments showed that the RTQCS can effectively guarantee the quality of product manufacturing and improve the manufacturing efficiency during production.

A methodology for energy efficiency redesign of smart production systems

Abstract In the recent years, many methodologies and tools to support the energy efficiency re-design of production systems have been developed, however, they do not investigate the real-time manufacturing process. In this paper, a methodology for energy efficiency re-design of production systems in a context of smart manufacturing is proposed. The continuous production-machine data collection with operator feedbacks enables the creation of a knowledge-based repository that provides useful support during the design of manufacturing systems. A case study in an automotive sector company has allowed to implement the methodology and to assess its effectiveness.

Coloured Petri net-based active sensing system of real-time and multi-source manufacturing information for smart factory

The wide use of Internet of Things (IoT) technologies in manufacturing shop-floor creates an opportunity to turn the traditional manufacturing factories into smart ones. The synchronous operation between the real shop-floor frontline and virtual production management system is vital in the establishment of smart factories. However, managing a wide variety of sensing devices and processing the large amount of raw captured manufacturing data are difficult for general production operators. In this article, the Coloured Petri net (CPN) technology is combined with IoT technologies to establish an active sensing system of real-time and multi-source manufacturing information (CPN-MIASS). It aims to establish a systematic graphics-based modelling approach for the sensing of manufacturing information and the management of sensor, which can assist the general operators in monitoring and controlling the real-time manufacturing process easily and dynamically. Based on this system and its key components, the multiple sensors can be managed in a ???Plug-and-play??? manner, and the high-level manufacturing information can be obtained efficiently. In addition, a prototype system is used to validate the usability of the proposed CPN-MIASS.

Productive and environmental performance indicators analysis by a combined LCA hybrid model and real-time manufacturing process monitoring: A grinding unit process application

Among machining processes, grinding has been used to achieve high dimensional tolerances and surface quality on workpieces. Yet, high levels of energy expenditure per volume of removed material and the need for cutting fluids make grinding one of the most environmentally impactful machining processes. Furthermore, changes in parameters such as grain and bond specifications of the grinding wheel, cutting speed, and specific material removal rate can lead to different productive and environmental results. Thus, the analysis of grinding processes should not be aggregated and leveraged into a single and broad output parameter. Instead, comprehensive study should be performed, in which the most relevant process parameters, inputs and outputs are considered. This paper presents a detailed study of grinding process, including the characterization of machine subunits and production modes, along with the use of a combined life cycle assessment hybrid model and real-time monitoring system to evaluate the consumption of energy, tooling, cutting fluid and compressed air. A detailed cradle-to-gate life cycle assessment study using eleven different impact categories and a productive performance assessment were performed to evaluate the effects on varying specific material removal rate and wheel type. For equal values of specific material removal rate, the change from a conventional wheel to a cubic boron nitride represented a power requirement increase of 19–24%. Cubic boron nitride wheel achieved remarkably better results on the wheel wear and part roughness indicators for all tested conditions. The environmental performance assessment showed a strict relation between the process environmental impacts and the consumption of electric energy and cutting fluid. To conclude, despite the higher power requirements, the combination of cubic boron nitride wheel with high values of specific material removal rate optimizes both the productive and the environmental results.

Evaluation of Diffuse Reflectance near Infrared Fibre Optical Sensors in Measurements for Chemical Identification and Quantification for Binary Granule Blends

In recent years, the pharmaceutical industry has focused on a better understanding of the real-time manufacturing process with online measurements. Near infrared (NIR) spectroscopy is perhaps the most used and acceptable technique in such a highly regulated industry. However, one of the big challenges in using NIR systems for in-line manufacturing processes is the acquisition of measurements in real-time simultaneously at different locations. To this end, a series of different optical set-ups were investigated. Results are presented here using a multipoint NIR system based on a Fabry–Pérot Interferometer capable of recording simultaneously four independent spectra in four different points. NIR spectra of cellulose and sucrose granule mixtures were evaluated by the partial least-squares (PLS) regression method. By interpreting score values, loading of the principal components and the root mean square errors of cross-validation ( RMSECV), differences between two sensors composed of fibre optics and the effect of sampling (static or motion) were analysed. Sensors that allow large illumination and detection areas against small granule sizes showed better results in reducing the prediction errors ( RMSECV = 1.8%) than sensors with small illumination and detection areas against samples with large granule sizes ( RMSECV = 9.6%). These results are important to better understand errors associated with optic fibre probes and their configuration in multipoint NIR spectroscopy for monitoring the pharmaceutical manufacturing process.

An approach for end-to-end QoS and network resources management

In this paper, we address the problem of the end-to-end QoS management for multimedia and real-time applications. We would focus on the presentation of a multi-profile communication environment and its reliability in ensuring end-to-end QoS management in the network communication processes. This communication environment, called Virtual Communication Support (VCS), provides a dynamic assignment of application requirements to the network resources reservation and protocol layers invocation. The advantage of this model is that it performs the capabilities of the network by abstracting the details of all communication stacks-layers that must be invoked in the communication process from application specificities and needs. A great attention is devoted to the end-to-end QoS management in the VCS communication model. We would present our approach for the development of a transport middleware for end-to-end QoS control. This middleware performs the QoS management with an adaptive and predictive algorithm based on the network jitter measurement. The main contribution of this paper is that it provides a solution to predict congestion during communication process and then it can avoid network overloading. This is of several importances when we are streaming multimedia real-time packets. In fact, when real-time application losses some packets it may lead to unfavorable situations. Our approach for the specification and the design of the middleware is based on the use of the Specification and Description Language (SDL). This is a formal description technique that enables model validation extension and reusability. The dynamic behavior of this model is being checked with the Message Sequence Chart (MSC). The simulation and validation of this middleware was performed for the VCS. It was simulated by The Network Simulator (NS). Some profiles with the JAVA language on the Fast-Ethernet Local Area Network. Its testing was performed for a real-time manufacturing process and multimedia supervision for control processes.

A review of neural networks for statistical process control

This paper aims to take stock of the recent research literature on application of Neural Networks (NNs) to the analysis of Shewhart's traditional Statistical Process Control (SPC) charts. First appearing in the late 1980s, most of the literature claims success, great or small, in applying NNs for SPC (NNSPC). These efforts are viewed in this paper as useful steps towards automatic on-line SPC for continuous improvement of quality and for real-time manufacturing process control. A standard NN approach that can parallel the universality of the traditional Shewhart charts has not yet been developed or adopted, although knowledge in this area is rapidly increasing. This paper attempts to provide a practical insight into the issues involved in application of NNs to SPC with the hope of advancing the use of NN techniques and facilitating their adoption as a new and useful aspect of SPC. First, a brief review of control chart analysis prior to the introduction of NN technology is presented. This is followed by an examination and classification of the NNSPC existing literature. Next, an extensive discussion of implementation issues with reference to significant research papers is presented. Finally, after summarising the survey, a set of general guidelines for future applications of NNs to SPC is outlined.

An empirical bayes strategy for analysing manufacturing data in real time

AbstractThis paper discusses and develops a real‐time strategy to monitor manufacturing process control data. The strategy presented in this paper is designed to intercept, analyse and monitor data as measurements are generated from a high‐volume information‐intensive manufacturing process. Empirical Bayes theory is used to develop a method to monitor and analyse continuous type measurements generated by a manufacturing process in real time. Several specific techniques will be proposed for detecting manufacturing process problems and examples of applying these techniques will be shown.

Integration strategy for distributed intelligent systems

In this article, we describe a new framework for designing real-time intelligent control systems. An integrated intelligent system is a large knowledge integration environment that consists of both symbolic reasoning systems (expert systems) and numerical computation packages. These modular software programs are controlled by a meta-system which manages the selection, operation, and communication of these programs. This new architecture can serve as a universal configuration to develop high-performance intelligent systems for many complicated application domains in the real-time manufacturing process. As an example, an intelligent optimal control is utilized to illustrate the integrated intelligent control system.

An Application of Statistical Databases in Manufacturing Testing

This paper discusses some applications of statistical and database techniques for integrating tests in manufacturing products. It shows how statistical databases can be used for automatically controlling a manufacturing process in real time. Some new statistical methods of manufacturing testing, e. g., test-compression, testing-by-sampling, testing-by-factorial-design, are discussed. All these techniques are possible because of the availability of a statistical database.