Fotoakustik yöntemi ile katı cisimlerde tahribatsız kusur tespiti
Yükleniyor...
Dosyalar
Tarih
2024
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Bursa Teknik Üniversitesi, Lisansüstü Eğitim Enstitüsü
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Fotoakustik (FA) yöntemi, ışık enerjisinin malzeme üzerinde ısıl enerjiye dönüşmesiyle oluşan akustik dalgaları analiz etme esaslı bir tekniktir. Tahribatsız muayene (TM) için kullanılması, malzemeye zarar vermeden kusurların tespit edilmesini sağlaması ve çeşitli malzemelerde kullanılabilmesi gibi avantajlara sahiptir. Bu yöntemde, lazer ışığı malzemeye gönderilir ve malzeme tarafından emilen ışık, termal enerjiye dönüşür. Termal enerjinin neden olduğu termal genleşme, ses dalgalarının oluşmasına yol açar. Bu ses dalgaları, akustik algılayıcılar tarafından algılanır ve analiz edilir. FA sinyaller, sağlam ve kusurlu malzemelerde farklı özellikler gösterir. Bu özellikler, sinyal genliği, frekans, periyot ve zaman-frekans özellikleri gibi parametrelerle tanımlanabilir. Bu parametreler, makine öğrenmesi (MÖ) yöntemleri aracılığıyla sınıflandırılarak kusurların tespit edilmesi mümkündür. FA sunduğu avantajlardan dolayı son yıllarda malzeme kusur tespitinde popülaritesi giderek artan bir yöntem olmuştur. Bu çalışmada, lazer, mikrofon ve veri toplama kartı ile tasarlanan düzenek ile alüminyum, demir, plastik ve tahta malzemelerinden elde edilen FA sinyallere Görgül Kip Analizi (GKA) tabanlı, zaman ve zaman-frekans düzleminde öznitelik çıkarma yöntemine dayanan, malzemelerde kusur tespiti için bir çerçeve çalışma önerilmiştir. Her malzeme gurubu içerisinde 120 adet sağlam, 120 adet kusurlu toplam 240 örnek ve toplamda 960 örnek kullanılmıştır. Bu örneklerden elde edilen 14 adet öznitelik ile k-en yakın komşu (k-NN), karar ağacı (KA) ve destek vektör makineleri (DVM) sınıflandırıcıları kullanılarak kusurlu ve sağlam malzemeler tespit edilmiştir. Malzemeler hem aynı sınıf içinde hem de tüm malzeme guruplarının dahil olduğu doğrulama teknikleri ile test edilmiştir. Birini dışarıda bırak çapraz doğrulama yöntemi ile sınıf içi ve tüm malzemeler için kusurlu ve sağlam tespit oranı sırasıyla DVM'de %100 ve k-NN'de %97.77 olarak elde edilmiştir. Bu çalışmada önerilen yöntem, FA yönteminin farklı malzemelerdeki yüzey kusurları için etkinliğini artırmaya yönelik önemli bir katkı sağlamaktadır. GKA ile FA sinyaldeki gürültüler süzülmüş, taban kaymasının etkisi azaltılmış ve aynı zamanda özellik çıkarımı için faydalı sinyal elde edilmiştir. Bu şekilde önerilen metodoloji ile FA sinyallerindeki taban kayması elimine edilerek sinyal işleme sürecinin iyileştirdiği gösterilmiştir. Bu sayede, FA sinyal ve GKA yöntemi ile farklı malzemelerdeki kusur tespitinin başarı oranı önemli ölçüde artırılmıştır. Literatürde bir malzeme özelinde yapılan çalışmaların aksine, önerilen yöntem ile farklı kusurların bulunduğu ve farklı malzemeler için ortak bir sınıflandırma çerçevesi geliştirilmiştir.
Photoacoustic (PA) is a technique that utilizes acoustic waves generated by the conversion of light energy into thermal energy to detect material defects. The PA method is advantageous since it allows for non-destructive testing (NDT), thereby enabling defect detection without causing any damage to the material, and it can be applied to a wide variety of materials. In this method, laser light is sent into the material and the light absorbed by the material is converted into thermal energy. The thermal energy results in thermal expansion, which in turn results in the generation of sound waves. The sound waves are then detected by the acoustic sensors for analysis. PA signals show different characteristics from intact and defective materials. These characteristics can be described by parameters such as signal amplitude, frequency, duration and time-frequency characteristics. Machine learning (ML) methods are used for classification of these parameters to detect defects. Photoacoustic has become an increasingly popular method for material defect detection in recent years due to its advantages. In this study, we propose a framework for material defect detection based on Empirical Mode Decomposition (EMD) based feature extraction in time and time-frequency domain for PA signals obtained from aluminum, iron, plastic and wood materials using a laser, microphone and data acquisition board. Within each material group, a total of 240 samples (120 intact samples and 120 defective samples) and a total of 960 samples were used. With 14 features extracted from these samples, k-nearest neighbor (k-NN), decision tree (DT) and support vector machine (SVM) classifiers were used to classify defective and intact materials. Materials were classified both within the same class and within the class including all material groups. With the leave-one-out cross-validation method, the defective and intact detection rates for all materials and within the class were 100% for SVM and 97.77% for k-NN, respectively. The method proposed in this study makes a significant contribution to improve the effectiveness of the PA method for surface defects in different materials. With EMD, the noise in the PA signal is filtered out, the effect of the baseline drift is reduced and at the same time a useful signal is obtained for feature extraction. The proposed method effectively improves the signal processing by eliminating the baseline drift in the PA signals while performing two different tasks at the same time. In this way, the accuracy rate of defect detection in different materials is significantly improved. In contrast to the material-specific studies in the literature, with the proposed method, a common classification framework was developed for different materials with different defects.
Photoacoustic (PA) is a technique that utilizes acoustic waves generated by the conversion of light energy into thermal energy to detect material defects. The PA method is advantageous since it allows for non-destructive testing (NDT), thereby enabling defect detection without causing any damage to the material, and it can be applied to a wide variety of materials. In this method, laser light is sent into the material and the light absorbed by the material is converted into thermal energy. The thermal energy results in thermal expansion, which in turn results in the generation of sound waves. The sound waves are then detected by the acoustic sensors for analysis. PA signals show different characteristics from intact and defective materials. These characteristics can be described by parameters such as signal amplitude, frequency, duration and time-frequency characteristics. Machine learning (ML) methods are used for classification of these parameters to detect defects. Photoacoustic has become an increasingly popular method for material defect detection in recent years due to its advantages. In this study, we propose a framework for material defect detection based on Empirical Mode Decomposition (EMD) based feature extraction in time and time-frequency domain for PA signals obtained from aluminum, iron, plastic and wood materials using a laser, microphone and data acquisition board. Within each material group, a total of 240 samples (120 intact samples and 120 defective samples) and a total of 960 samples were used. With 14 features extracted from these samples, k-nearest neighbor (k-NN), decision tree (DT) and support vector machine (SVM) classifiers were used to classify defective and intact materials. Materials were classified both within the same class and within the class including all material groups. With the leave-one-out cross-validation method, the defective and intact detection rates for all materials and within the class were 100% for SVM and 97.77% for k-NN, respectively. The method proposed in this study makes a significant contribution to improve the effectiveness of the PA method for surface defects in different materials. With EMD, the noise in the PA signal is filtered out, the effect of the baseline drift is reduced and at the same time a useful signal is obtained for feature extraction. The proposed method effectively improves the signal processing by eliminating the baseline drift in the PA signals while performing two different tasks at the same time. In this way, the accuracy rate of defect detection in different materials is significantly improved. In contrast to the material-specific studies in the literature, with the proposed method, a common classification framework was developed for different materials with different defects.
Açıklama
Anahtar Kelimeler
Elektrik ve Elektronik Mühendisliği, Electrical and Electronics Engineering, Mekatronik Mühendisliği, Mechatronics Engineering
