Dynamic sensor compensation using analogue adaptive filter compatible with digital technology

Jafaripanah, M.; Al-Hashimi, Bashir M.; White, Neil

doi:10.1049/ip-cds:20045146

Cited by 9 publications

(3 citation statements)

References 12 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, classification of the dynamically weighted eggs according to the weight categories set forth in the Ministry of Food, Agriculture and Animal-Turkish Food Codex Egg Communique was realized with raw data directly by using the support vector machines. [8], zamanla değişen filtre parametreleri [4], bulanık mantık [9], yapay sinir ağları [10,11], hareketli araç ağırlık ölçüm sisteminden alınan sinyalin üzerindeki gürültünün giderildiği [12] ve fiber optik hareketli araç tartım sistem ölçüm verisindeki gürültülerin giderildiği [13,14] dalgacık dönüşümü, ağırlık belirleme algoritmalarının tasarlandığı sistem tanıma ve genişletilmiş Kalman filtreleme teoremine dayanan adaptif filtre [1], pasif devre elemanları olmadan sadece CMOS transistörler ile oluşturulan analog adaptif filtre [15] ve dinamik tartım sistemi için ağırlık filtresi olarak Kalman filtresinin kullanıldığı [16] çalışmaları adaptif filtre, başlıkları altında toplayabiliriz.…”

Section: Doiunclassified

Destek vektör makineleri kullanarak dinamik yumurta ağırlıklarının sınıflandırılması

Yabanova¹,

Yumurtacı²

2018

Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

• Dynamically weighed eggs were classified by support vector machines. • Classification was made according to the weight classes specified in Ministry of Food, Agriculture and Animal-Turkish Food Codex Egg Communique • Egg classification was determined successfully using the raw measurement data in the classification process. Today, speed in the manufacturing sector has become an important factor. Dynamic weighing systems have been developed to realize the weighing transactions speedily. In the dynamic weighing systems, the products are weighted while they are passing from on the weighing platform in motion and they can reach to desired weighing speeds in this manner. However, in the dynamic weighing systems, mechanic vibrations resulting from weighing of product in motion creates an undesired distorting effect in the measuring signal. Traditionally, the weighing weight of product at the moment it becomes stable after the signal is filtered is tried to be determined by using a method. In general, the products are classified according to definite weight categories after their weights are determined. In this study egg classification was determined successfully using the raw measurement data in the classification process with support vector machines. Purpose: In this study, classification of the dynamically weighted eggs according to the weight categories set forth in the Ministry of Food, Agriculture and Animal-Turkish Food Codex Egg Communique was realized with raw data directly by using the support vector machines. Theory and Methods: In this study, a dynamic egg weighing system was realized mechanically and electronically. By applying SVM to the data received from the system, it is ensured that the eggs are separated according to weight classes. Conventional methods in dynamic weighing systems, the measurement signal is filtered using various methods to obtain a noiseless weight signal, and then a method is applied to this signal to determine the weight value at which the measurement signal is stabilized. The weight class of the egg is determined by comparing with the values stated in this weight value egg notification. In the study, the SVM method was applied to the raw measurement signal obtained from the dynamic weighing system to classify the eggs. Results: In this study, 11 weight data from the fall of the egg to the measurement platform were applied directly to the SVM classifier without any processing. At the output of the SVM, one of the tags given according to weight classes (1, 2, 3, 4) is obtained. During the formation of SVM model, 29 egg weight data were used for training and 14 egg weight data were used in the test of the model. As a result of the test procedure, all eggs were correctly classified according to the weight group labels given. Conclusion: With the proposed method, it is possible to detect directly with the SVM without applying a pre-signal processing method to the class measurement data suitable for the weight without leaving the egg measuring platform.

show abstract

Section: Doiunclassified

Destek vektör makineleri kullanarak dinamik yumurta ağırlıklarının sınıflandırılması

Yabanova¹,

Yumurtacı²

2018

Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

show abstract

“…However, the compensation method of its nonlinear errors is not discussed in this paper. A linear time-varying continuoustime filter [9], a fuzzy logic weight filter [10], an analog adaptive filter [11], and a Kalman filter [12] can improve the dynamic performances of the load cell or the weighing system. However, it is not beneficial to its static performances, such as the nonlinear error and the repeatability.…”

mentioning

confidence: 99%

Nonlinear Error Compensation for Load Cells Based on the Optimal Neural Network With an Augmented Lagrange Multiplier

Lin

Wang

et al. 2015

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

This paper presents a new approach for compensating nonlinear errors of a load cell, based on the optimal neural network with an augmented Lagrange multiplier (ALMNN). The load cell has serious nonlinear errors, which lower the accuracy of the weighing results. In this proposed approach, first, we construct the constraints for training the neural network (NN) using the load cell's prior knowledge, i.e., the monotonic increasing property of a load cell's input-output function. Second, we create the augmented Lagrange function with a multiplier and a penalty factor to serve as an NN's performance index, and then deduce the ALMNN's detailed training algorithm. The penalty factor plays an important role in ALMNN, thus the reasonable range of numerical value is discussed in this paper. Meanwhile, the weighing principle of a strain gauge load cell is introduced and its nonlinear error model is established. Finally, the experimental results demonstrate the effectiveness of ALMNN. By comparing with the conventional data induction method (DINN, i.e., the training of NN not with the prior knowledge but only the data samples), ALMNN significantly improves the NN's generalization ability, especially in the case of lacking training samples. In addition, the applicability of ALMNN is verified by three additional experiments.Index Terms-First-order derivative constraint, Lagrange multiplier, load cell, monotonicity, neural networks (NNs), nonlinear error compensation.

show abstract

“…Mass production of such elements led to the achievement of their high technological level and low production costs -the development of new constructions and technologies in this field is a particularly difficult task [1,2].…”

Section: Introductionmentioning

confidence: 99%

Inductive Sensor for Weighing of Mass

Lewandowski¹

2011

Metrology and Measurement Systems

View full text Add to dashboard Cite

A new method measuring of mass in electronic system of scales has been described. The main element of this system is inductive measuring load cell, which was compared with strain gauge load cell. The aim of the paper is described advantages of the inductive measuring system of mass and explain some main problems of this system. Digital correction of the mechanical errors of the beam like: hysteresis, creep material of the beam under constant load, influence of ambient temperature was described.

show abstract

Dynamic sensor compensation using analogue adaptive filter compatible with digital technology

Cited by 9 publications

References 12 publications

Destek vektör makineleri kullanarak dinamik yumurta ağırlıklarının sınıflandırılması

Destek vektör makineleri kullanarak dinamik yumurta ağırlıklarının sınıflandırılması

Nonlinear Error Compensation for Load Cells Based on the Optimal Neural Network With an Augmented Lagrange Multiplier

Inductive Sensor for Weighing of Mass

Contact Info

Product

Resources

About