Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network

Alelaumi, Shrouq; Khader, Nourma; He, Jingxi; Lam, Sarah S.; Yoon, Sang Won

doi:10.1016/j.rcim.2020.102041

Cited by 15 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [25], the stakeholder theory is used to construct a DM system, and the concept of NNs is used to improve the accuracy versus uncertainties. In [26], recurrent NNs are used in designing DM systems, and their efficiency is examined in a stencil cleaning application. e functional magnetic resonance is developed in [27], and the speed of DM is analyzed.…”

Section: Introductionmentioning

confidence: 99%

A New Decision-Making GMDH Neural Network: Effective for Limited and Fuzzy Data

Hong

Zhao

Kausar

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This paper presents a new approach to solve multi-objective decision-making (DM) problems based on neural networks (NN). The utility evaluation function is estimated using the proposed group method of data handling (GMDH) NN. A series of training data is obtained based on a limited number of initial solutions to train the NN. The NN parameters are adjusted based on the error propagation training method and unscented Kalman filter (UKF). The designed DM is used in solving the practical problem, showing that the proposed method is very effective and gives favorable results, under limited fuzzy data. Also, the results of the proposed method are compared with some similar methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Decision-Making GMDH Neural Network: Effective for Limited and Fuzzy Data

Hong

Zhao

Kausar

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Similarly, switching on both the battery and linear load simultaneously will lead to the sag in voltage in the system. The voltage sag mainly occurs due to the transient load conditions, changing climatic conditions, and various short circuit failures [30].…”

Section: Voltage Sagmentioning

confidence: 99%

Red deer optimized recurrent neural network for the classification of power quality disturbance

Dawood¹,

Babulal²

2023

Electr Eng

View full text Add to dashboard Cite

Power Quality Disturbance (PQD) in a power grid distribution destroys the quality of power to the user. Thus, early detection of disturbances in the power grid distribution is essential to diagnose the network before failure. Several disturbances in the power grid may cause voltage sag, voltage swell, or occurrence of both. In the proposed method deep recurrent neural network (DRNN) is used for classifying the PQD as well as Red Deer Optimization (RDO) algorithm is used for optimizing the weight from DRNN. Based on the behaviour of deer roaring rate will optimize the weight of DRNN from RDO. Signal processing is done by S-transform (ST) because of the better performance in signals detection in terms of a high order of noise. The proposed method is implemented in Simulink tool and the results are compared with the existing methods. The result shows that the power disturbances are classified with high accuracy of 99.95% and precision of 99.98% that are higher than the existing methods.

show abstract

“…The physical change in solder paste leads to dynamic changes between the printer environment and process parameters during the printing process. Alelaumi et al (2021) proposed a novel predictive model to control the stencil cleaning configuration through a neural network. This would help the stencil printing process production line to select the appropriate template cleaning configuration in time.…”

Section: Introductionmentioning

confidence: 99%

Predictive model of the solder paste stencil printing process by response surface methodology

Chen

Wang

Kao

et al. 2022

SSMT

View full text Add to dashboard Cite

Purpose This paper aims to establish the predictive equations of height, area and volume of printed solder paste during solder paste stencil printing (SPSP) process in surface mount technology (SMT) to better understand the effect of process parameters on the printing quality. Design/methodology/approach An experiment plan is proposed based on the response surface method (RSM). Experiments with 30 different combinations of process parameters are performed using a solder paste printer. After printing, the volume, area and height of the printed SAC105 solder paste are measured by a solder paste inspection machine. Using RSM, the predictive equations associated with the printing parameters and the printing quality of the solder paste are formed. Findings The optimal printing parameters are 175.08 N printing pressure, 250 mm/s printing speed, 0.1 mm snap-off height and 15.7 mm/s stencil snap-off speed if the target height of solder paste is 100 µm. As the target printing area of solder paste is 1.1 mm × 1.3 mm, the optimized values of the printing parameters are 140.29 N, 100.52 mm/s, 0.63 mm and 20.25 mm/s. When both the target printing height and area are optimized together, the optimal values for the four parameters are 86.67 N, 225.76 mm/s, 0.15 mm and 1.82 mm/s. Originality/value A simple RSM-based experimental method is proposed to formulate the predictive polynomial equations for height, area and volume of printed solder paste in terms of important SPSP parameters. The predictive equation model can be applied to the actual SPSP process, allowing engineers to quickly predict the best printing parameters during parameter setting to improve production efficiency and quality.

show abstract

Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network

Cited by 15 publications

References 17 publications

A New Decision-Making GMDH Neural Network: Effective for Limited and Fuzzy Data

A New Decision-Making GMDH Neural Network: Effective for Limited and Fuzzy Data

Red deer optimized recurrent neural network for the classification of power quality disturbance

Predictive model of the solder paste stencil printing process by response surface methodology

Contact Info

Product

Resources

About