---

These days the accurate estimation of seismic demand and capacity of structures are truly significant in the field of performance based earthquake engineering. Several methods exist to determine these parameters such as non-linear time history analysis and Incremental dynamic analysis (IDA). Because the history of seismic accelerogram records refers to the current century, in some areas there still exists no appropriate seismic record to perform the analyses; therefore in these cases we need to generate artificial accelerograms. In this paper a new combinational method is introduced to generate far-field artificial accelerograms using artificial neural network and wavelet packet transform (WPT) methods. In this method according to the geoseismic characteristics of the site and non-linear characteristics of the equivalent single degree of freedom (SDOF) system, several artificial accelerograms are generated. In order to consider the non-linear parameters to generate the accelerograms, IDA method is used. The values of intensity measure (IM) for all IDA curves are determined at specific levels of damage measure (DM) and are considered as the input data of the multilayer feed forward (MLFF) neural network. Accelerograms which are selected according to the geoseismic characteristics of the site are changed to standard forms and then decomposed using wavelet packet transform. The effective wavelet packet coefficients are selected according to an appropriate desired effective variance ratio of wavelet packet coefficient. Then, effective coefficient of each packet is considered as the output of a neural network. In order to enhance the efficiency of the network, principal components analysis (PCA) is used to reduce the number of the input data dimensions. In this paper neural network is trained by backpropagation algorithm as repetitive. After training the MLFF neural network, we should test the network for accelerograms not included in the training set. For this purpose we should use the IDA curve of each accelerogram out of the training set as the input of the neural network to generate the effective WPT coefficients. When a neural network is trained properly, we can now generate artificial accelerograms using a 50% fractile IDA curve as the input of the neural network. Adding a Gaussian random number to the output of each neuron in the neural network layers, we are able to generate several accelerograms according to 50% fractile IDA curve. In order to improve the condition of generated accelerograms according to 50% fractile IDA curve, a correction factor is used repeatedly for detail coefficients of discrete wavelet transform in jth level of generated accelerogram. Finally a SDOF system with perfectly elasto-plastic initial loading curve is used to show the efficiency of the proposed method to generate artificial accelerogram. The accuracy of this method depends on the accuracy of the trained neural networks. If the neural networks are trained appropriately with IDA curve, the generated accelerogram can estimate the IDA parameters of the SDOF system more properly. Also it is shown that suggested method can generate artificial accelerograms with frequency content almost close to the initial earthquake records.

---

Materials are often damaged during the process of detecting mass fractions by traditional methods. In this work, acoustic emission (AE) technology combined with wavelet packet analysis is used to evaluate the mass fractions of graphite/ epoxy composites. Attenuation characteristics of AE signals across the composites with different mass fractions are investigated. The AE signals are decomposed by wavelet packet technology to obtain the relationships between the energy and amplitude attenuation coefficients of feature wavelet packets and mass fractions as well. Furthermore, the relationship is validated by test samples. The results show that the lower proportion of graphite will correspond to the less attenuation. The attenuation characteristics of feature wavelet packets with the frequency range from 125 kHz to 171.85 kHz are more suitable for the detection of mass fractions than those of the original AE signal. The error of the graphite mass fraction calculated by the feature wavelet packet (1.9%) is lower than that of the original signal (4.75%). Therefore, the AE detection base on wavelet packet analysis is an ideal NDT method for evaluate mass fractions of composite.

---

Signal processing has a key role in signal based fault diagnosis in rotating machinery for finding beneficial discriminating features. Task of Signal processing is conversion of the raw data into beneficial features to facilitate the diagnostic operations. the features should be robust regarding noise and working condition of the machine and simultaneously sensitive to the machine defects. Therefore, assignment of more efficient analyzing techniques in order to achieve more beneficial features of the signal and faster and more accurate fault detection is taken into consideration by researchers. In order to finding such features, the current research applies at first wavelet packet denoising and then applies wavelet packet based Hilbert transform as well as improved Hilbert-Huang transform separately to decompose vibration signal into narrow frequency bands in order to extracting instantaneous frequencies. The findings show that the wavelet packet based Hilbert transform generates better results in comparison to the improved Hilbert-Huang transform in detecting frequencies of the broken rotor bar fault.

---

---

Gears are a very important part of mechanical equipment in industry. Due to the fact that in mechanical processes, the teeth are subjected to long-term load, the surface of their teeth is usually rusty, worn out and even broken. Timely fault detection cannot only increase the life cycle of the gears, however it can even prevent property losses and losses due to breakdowns. Therefore, it is necessary to monitor and diagnose the health of the gears to ensure the normal operation of the invaluable machines in industry. In this research, fault detection in polymer gears using audio signal is considered as a non-contact inspection method. Sound signals were recorded from 50 pairs of gears in normal condition, worn teeth and broken teeth at two speeds of 66 and 99 rpm. In the following, using wavelet packet transformation (WPT), the sound signal is analyzed in the time-frequency domain and 12 statistical features are extracted from the 16 coefficients of the fourth level of WPT. In order to study the performance of the fault detection algorithm, four classifications of linear discriminant analysis, K-nearest neighbor, decision tree and support vector machine have been used. The values of accuracy, true positive rate, true negative rate, positive predictive value, negative predictive value, geometric-mean, F1 score, and Matthews correlation coefficient have shown that by using WPT, a significant distinction can be found between normal and faulty gears. Therefore, the proposed method is a suitable approach for timely error detection of polymer gears used in mechanical equipment.