Economic impact of quality inspection in manufacturing: A proposal for a novel cost modeling

Verna, Elisa; Genta, Gianfranco; Galetto, Maurizio; Franceschini, Fiorenzo

doi:10.1177/09544054221078090

Cited by 7 publications

(4 citation statements)

References 40 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automated quality testing of solder joints is necessary due to the high production volume and short production time, making manual testing impractical. Automatic optical inspection (AOI) can accurately and efficiently identify defects in products without being influenced by human subjectivity, thus reducing production time and costs [4,5]. Research conducted by Ebayyeh [6] demonstrates that AOI can help improve the quality of solder joints and reduce defects in electronic products.…”

Section: Introductionmentioning

confidence: 99%

Enhancing GLCM-Based Feature Extraction for THT Solder Joint Inspection through Log Polar Transformation

2024

IJIES

View full text Add to dashboard Cite

Quality inspection of solder connections in electronic circuit manufacturing is commonly performed using automatic optical inspection (AOI) technology. The utilization of deep learning in AOI has demonstrated high accuracy and fast computation, yet it requires expensive graphics processing unit (GPU) equipped computers. To enable broader and more cost-effective utilization, there is a need for an AOI model that can be embedded in simple central processing unit (CPU) based computers. To pursue this objective, several research efforts have been undertaken to develop AOI models based on classical machine learning techniques. However, the accuracy and speed achieved by these models have not yet matched deep learning-based AOI models. This study aims to enhance the computational efficiency of classic machine learning by processing only pixels containing textural information. The effectiveness enhancement is achieved through the application of log-polar transformation in the extraction of texture features using the gray level co-occurrence matrix (GLCM) to detect defects in trough hole technology (THT) solder joint connections. By transforming cartesian coordinates into polar coordinates, the textural areas to be detected assume a square shape, facilitating efficient texture feature extraction. To ensure a significant improvement in performance, a comparative performance evaluation is conducted on classic machine learning-based AOI models with and without the log-polar transformation. The texture features extracted from both models are classified using the support vector machine (SVM) method. Model testing and evaluation reveals that the proposed enhancement effort is capable of increasing accuracy levels to 95% and reach computation time by 120 milliseconds.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing GLCM-Based Feature Extraction for THT Solder Joint Inspection through Log Polar Transformation

2024

IJIES

View full text Add to dashboard Cite

show abstract

“…Quality control may be located: before the start of the process (control of materials, parts, semi-finished products), "first piece" control (only after obtaining a good so-called first piece, the process can be "released"), during the operation (operational control), or after the operation has been completed (before forwarding the product to the next operation or before sending it to the external recipient -acceptance sampling) [23] [37].…”

Section: Introductionmentioning

confidence: 99%

“…rejection of products which in fact meet requirements. This is associated with a significant and unjustified increase in the cost of control and, as a result, the cost of production [19] [37].…”

Section: Introductionmentioning

confidence: 99%

Ensuring the reliability and reduction of quality control costs by minimizing process variability

Rogalewicz¹,

Kujawińska²,

Feledziak³

2023

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

This paper presents a method for planning the range of quality control while ensuring its reliability and minimizing costs. The method is dedicated to destructive inspection, in which the cost of performing the measurement is significant in relation to the cost of manufacturing a part or product. The methodology was divided into four main stages: (1) selection of the measurement system and definition of the inspection scope and sample size, (2) process control, (3) redefining the scope of control and (4) verification of control cost and reliability after sample size change. The article presents the results of applying the author's procedure to the process of evaluating seat belts in automotive industry. Belts are used in the process of controlling the final product, which is a seat belt anchor plate. This approach allowed to reduce the number of destroyed parts during control while maintaining the credibility of the decision based on the assessment. As a result of double-decreasing the sample size, the costs of seat belt quality control were reduced. Assuming an average of 40 seat belt deliveries per year, the material cost was reduced by 50%. Limiting the sample size to 15 pieces per delivery would reduce the cost of testing from by 45%. It was achieved maintaining the appropriate level of credibility of decisions made greater than 0.8.

show abstract

“…the manufacturing of small customized batches of products with short life cycles 2,3 ), traditional automation may not be a viable costeffective solution. [4][5][6] For this reason, hybrid automation in which human workers and collaborative robots (cobots) interact within production systems is emerging. 7,8 The in-depth study of the interaction between humans and robots is therefore of fundamental importance, especially to investigate possible new hazards from an ergonomic point of view (both physical and cognitive).…”

Section: Introductionmentioning

confidence: 99%

Applications of affective computing in human-robot interaction: State-of-art and challenges for manufacturing

Gervasi

Barravecchia

Mastrogiacomo

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part B:

Self Cite

View full text Add to dashboard Cite

The introduction of collaborative robots aims to make production more flexible, promoting a greater interaction between humans and robots also from physical point of view. However, working closely with a robot may lead to the creation of stressful situations for the operator, which can negatively affect task performance. In Human-Robot Interaction (HRI), robots are expected to be socially intelligent, that is, capable of understanding and reacting accordingly to human social and affective clues. This ability can be exploited implementing affective computing, which concerns the development of systems able to recognize, interpret, process, and simulate human affects. Social intelligence is essential for robots to establish a natural interaction with people in several contexts, including the manufacturing sector with the emergence of Industry 5.0. In order to take full advantage of the human-robot collaboration, the robotic system should be able to perceive the psycho-emotional and mental state of the operator through different sensing modalities (e.g. facial expressions, body language, voice, or physiological signals) and to adapt its behavior accordingly. The development of socially intelligent collaborative robots in the manufacturing sector can lead to a symbiotic human-robot collaboration, arising several research challenges that still need to be addressed. The goals of this paper are the following: (i) providing an overview of affective computing implementation in HRI; (ii) analyzing the state-of-art on this topic in different application contexts (e.g. healthcare, service applications, and manufacturing); (iii) highlighting research challenges for the manufacturing sector.

show abstract

Economic impact of quality inspection in manufacturing: A proposal for a novel cost modeling

Cited by 7 publications

References 40 publications

Enhancing GLCM-Based Feature Extraction for THT Solder Joint Inspection through Log Polar Transformation

Enhancing GLCM-Based Feature Extraction for THT Solder Joint Inspection through Log Polar Transformation

Ensuring the reliability and reduction of quality control costs by minimizing process variability

Applications of affective computing in human-robot interaction: State-of-art and challenges for manufacturing

Contact Info

Product

Resources

About