KL Transform and Neural-Net Based Framework for Failure Modes Classification in Electronics Subjected to Mechanical-Shock

2011 ◽  
Author(s):  
Pradeep Lall ◽  
Prashant Gupta ◽  
Kai Goebel
Keyword(s):  
Failure Mode ◽  
Failure Modes ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Feature Space ◽  
System Level ◽  
Neural Net ◽  
Mechanical Shock ◽  
Time Frequency ◽  
Damage Initiation

Electronic systems under extreme shock and vibration environments including shock and vibration may sustain several failure modes simultaneously. Previous experience of the authors indicates that the dominant failure modes experienced by packages in a drop and shock frame work are in the solder interconnects including cracks at the package and the board interface, pad cratering, copper trace fatigue, and bulk-failure in the solder joint. In this paper, a method has been presented for failure mode classification using a combination of Karhunen Loe´ve transform with parity-based stepwise supervised training of a perceptrons. Early classification of multiple failure modes in the pre-failure space using supervised neural networks in conjunction with Karhunen Loe´ve transform is new. Feature space has been formed by joint time frequency analysis. Since the cumulative damage may be accrued under repetitive loading with exposure to multiple shock events, the area array assemblies have been exposed to shock and feature vectors constructed to track damage initiation and progression. Error Back propagation learning algorithm has been used for stepwise parity of each particular failure mode. The classified failure modes and failure regions belonging to each particular failure modes in the feature space are also validated by simulation of the designed neural network used for parity of feature space. Statistical similarity and validation of different classified dominant failure modes is performed by multivariate analysis of variance and Hoteling’s T-square. The results of different classified dominant failure modes are also correlated with the experimental cross sections of the failed test assemblies. The methodology adopted in this paper can perform real-time fault monitoring with identification of specific dominant failure mode and is scalable to system level reliability.

Failure Mode Clustering is Electronic Assemblies Using Sammon’s Mapping With Supervised Training of Perceptrons

2011 ◽  
Author(s):  
Pradeep Lall ◽  
Prashant Gupta ◽  
Kai Goebel
Keyword(s):  
Failure Mode ◽  
Solder Ball ◽  
Failure Modes ◽  
Feature Vector ◽  
Feature Space ◽  
Image Correlation ◽  
Neural Net ◽  
Sammon’S Mapping ◽  
Electronic Assemblies ◽  
Diagnostic Detection

An anomaly detection and failure mode classification method has been developed for electronic assemblies with multiple failure modes. The presented prognostic health management method targets the pre-failure space of the electronic assembly life to trigger repair or replacement of impending failures. Presently, health monitoring systems focus on reactive diagnostic detection of failure modes. Examples of diagnostic detection include the built in self test and on-board diagnostics. In this paper, damage pre-cursors from time-spectral measurements of the electronic assemblies has been measured under applied vibration and shock stimulus. The time-evolution of spectral content of the damage pre-cursors has been studied using joint time frequency analysis in a full-field manner on the printed circuit assembly. Frequency moments have been used to build a feature vector. Evolution of the feature vector with damage initiation and progression has been studied under shock and vibration. The feature vector from multiple locations in the board assemblies has been mapped into a de-correlated feature space using Sammon’s mapping. Several chip-scale packages have been studied, with SAC305 and SAC405 leadfree second-level interconnects. Transient strain has been measured during the drop-event using digital image correlation and high-speed cameras operating at 100,000 fps. Continuity has been monitored simultaneously for failure identification. In addition, explicit finite element models have been developed and various kinds of failure modes have been simulated such as solder ball cracking, trace fracture, package falloff and solder ball failure. The neural net has been trained using simulated data-sets created from error-seeded models with specific failure modes. The neural net has then been used to identify and classify the failure modes in board assemblies experimentally. Supervised learning of multilayer neural net in conjunction with parity has been used to identify the hard-separation boundaries between failure mode clusters in the de-correlated feature space. The assemblies have been cross-sectioned to verify the identified failure modes. Cross-sections indicate that the experimentally measured failures modes correlate well with the position of the cluster in the de-correlated feature space.

Feature Vector Based Failure Mode Identification and Prognostication of Electronics Subjected to Shock and Vibration

2009 ◽  
Author(s):  
Pradeep Lall ◽  
Prashant Gupta ◽  
Arjun Angral ◽  
Jeff Suhling
Keyword(s):  
Experimental Data ◽  
Failure Mode ◽  
Frequency Analysis ◽  
Health Monitoring ◽  
Solder Ball ◽  
Failure Modes ◽  
Feature Space ◽  
Time Frequency ◽  
Fault Mode ◽  
Electronic Assemblies

Failures in electronics subjected to shock and vibration are typically diagnosed using the built-in self test (BIST) or using continuity monitoring of daisy-chained packages. The BIST which is extensively used for diagnostics or identification of failure, is focused on reactive failure detection and provides limited insight into reliability and residual life. In this paper, a new technique has been developed for health monitoring and failure mode classification based on measured damage precursors. A feature extraction technique in the joint-time frequency domain has been developed along with pattern classifiers for fault diagnosis of electronics at product-level. The Karhunen Loe´ve transform (KLT) has been used for feature reduction and de-correlation of the feature vectors for fault mode classification in electronic assemblies. Euclidean, and Mahalanobis, and Bayesian distance classifiers based on joint-time frequency analysis, have been used for classification of the resulting feature space. Previously, the authors have developed damage pre-cursors based on time and spectral techniques for health monitoring of electronics without reliance on continuity data from daisy-chained packages. Statistical Pattern Recognition techniques based on wavelet packet energy decomposition [Lall 2006a] have been studied by authors for quantification of shock damage in electronic assemblies, and auto-regressive moving average, and time-frequency techniques have been investigated for system identification, condition monitoring, and fault detection and diagnosis in electronic systems [Lall 2008]. However, identification of specific failure modes was not possible. In this paper, various fault modes such as solder inter-connect failure, inter-connect missing, chip delamination chip cracking etc in various packaging architectures have been classified using clustering of feature vectors based on the KLT approach [Goumas 2002]. The KLT de-correlates the feature space and identifies dominant directions to describe the space, eliminating directions that encode little useful information about the features [Qian 1996, Schalkoff 1972, Theodoridis 1998, Tou 1974]. The clustered damage pre-cursors have been correlated with underlying damage. Several chip-scale packages have been studied, with leadfree second-level interconnects including SAC105, SAC305 alloys. Transient strain has been measured during the drop-event using digital image correlation and high-speed cameras operating at 100,000 fps. Continuity has been monitored simultaneously for failure identification. Fault-mode classification has been done using KLT and joint-time-frequency analysis of the experimental data. In addition, explicit finite element models have been developed and various kinds of failure modes have been simulated such as solder ball cracking, trace fracture, package falloff and solder ball failure. Models using cohesive elements present at the solder joint-copper pad interface at both the PCB and package side have also been created to study the traction-separation behavior of solder. Fault modes predicted by simulation based pre-cursors have been correlated with those from experimental data.

Anomaly-Detection and Prognostication of Electronics Subjected to Shock and Vibration

2009 ◽  
Author(s):  
Pradeep Lall ◽  
Prashant Gupta ◽  
Arjun Angral ◽  
Jeff Suhling
Keyword(s):  
Experimental Data ◽  
Frequency Analysis ◽  
Health Monitoring ◽  
Solder Ball ◽  
Failure Modes ◽  
Feature Space ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Fault Mode ◽  
Electronic Assemblies

Failures in electronics subjected to shock and vibration are typically diagnosed using the built-in self test (BIST) or using continuity monitoring of daisy-chained packages. The BIST which is extensively used for diagnostics or identification of failure, is focused on reactive failure detection and provides limited insight into reliability and residual life. In this paper, a new technique has been developed for health monitoring and failure mode classification based on measured damage precursors. A feature extraction technique in the joint-time frequency domain has been developed along with pattern classifiers for fault diagnosis of electronics at product-level. The Karhunen Loe´ve transform (KLT) has been used for feature reduction and de-correlation of the feature vectors for fault mode classification in electronic assemblies. Euclidean, and Mahalanobis, and Bayesian distance classifiers based on joint-time frequency analysis, have been used for classification of the resulting feature space. Previously, the authors have developed damage pre-cursors based on time and spectral techniques for health monitoring of electronics without reliance on continuity data from daisy-chained packages. Statistical Pattern Recognition techniques based on wavelet packet energy decomposition [Lall 2006a] have been studied by authors for quantification of shock damage in electronic assemblies, and auto-regressive moving average, and time-frequency techniques have been investigated for system identification, condition monitoring, and fault detection and diagnosis in electronic systems [Lall 2008]. However, identification of specific failure modes was not possible. In this paper, various fault modes such as solder inter-connect failure, inter-connect missing, chip delamination chip cracking etc in various packaging architectures have been classified using clustering of feature vectors based on the KLT approach [Goumas 2002]. The KLT de-correlates the feature space and identifies dominant directions to describe the space, eliminating directions that encode little useful information about the features [Qian 1996, Schalkoff 1972, Theodoridis 1998, Tou 1974]. The clustered damage pre-cursors have been correlated with underlying damage. Several chip-scale packages have been studied, with leadfree second-level interconnects including SAC105, SAC305 alloys. Transient strain has been measured during the drop-event using digital image correlation and high-speed cameras operating at 100,000 fps. Continuity has been monitored simultaneously for failure identification. Fault-mode classification has been done using KLT and joint-time-frequency analysis of the experimental data. In addition, explicit finite element models have been developed and various kinds of failure modes have been simulated such as solder ball cracking, trace fracture, package falloff and solder ball failure. Models using cohesive elements present at the solder joint-copper pad interface at both the PCB and package side have also been created to study the traction-separation behavior of solder. Fault modes predicted by simulation based pre-cursors have been correlated with those from experimental data.

Improved Artificial BP Neural Networks and Genetic Algorithm Used to Predict the Purity of the Artificial Synthetic Hydrotalcite

2007 ◽  
Vol 280-283 ◽  
pp. 495-498
Author(s):  
Qiang Luo ◽  
Qing Li Ren
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Prediction Model ◽  
Process Parameters ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Raw Material ◽  
Algorithm Analysis ◽  
Neural Net ◽  
Bp Neural Networks

A prediction model for purity of the artificial synthetic hydrotalcite under varied process parameters based on improved artificial back-propagation (BP) neural networks is developed. And the non-linear relationship between the hydrotalcite purity and the raw material adding amount of NaOH, MgCl2 and AlCl3 was established based on BP learning algorithm analysis and convergence improvement. The hydrotalcite purity can be predicted by means of the trained neural net. Thus, by virtue of the prediction model, the future hydrotalcite purity can be evaluated under random complicated raw material amounts. Moreover, the best processing technology is optimized using the genetic algorithm.

Design of a robust fault-tolerant control algorithm based on failure mode effects criticality analysis for a three-axis satellite

2017 ◽  
Vol 233 (1) ◽  
pp. 91-110
Author(s):  
Mohammad Reza Abedini ◽  
Mostafa Abedi
Keyword(s):  
Failure Mode ◽  
Control Algorithm ◽  
Failure Modes ◽  
Fault Tolerant ◽  
Equilibrium Points ◽  
Fault Tolerant Control ◽  
System Level ◽  
Fault Estimation ◽  
Mode Effects ◽  
Criticality Analysis

This paper proposes a robust fault-tolerant control algorithm for a three-axis satellite. In this regard, an adaptive sliding attitude control algorithm is suggested, which has the capability of fault estimation in the satellite actuators and correction of their effects. For this, the disturbances due to environmental effects and actuator failures and also the satellite unknown parameters are estimated by the adaptive updating law; the sliding mode algorithm compensates the errors due to estimation process. In the suggested design process, the sliding surface is selected so that the unwinding and singularity problems are solved, and also a compensator part is included to remove unstable equilibrium points. In this paper, the failure mode effects criticality analysis have been done to classify different failure modes of reaction wheel according to their severity and probability of occurrence. Accordingly, the critical failure modes and their effects at the control system level are derived. It is shown that the derived critical failures lead to small or severe variations in the generated torques of reaction wheels for which a supervision level will be proposed to correct their effects. Finally, different simulations are conducted to validate expected performance of the suggested algorithms.

Failure-Mode Clustering for Electronics Under Shock and Vibration Using Neural-Net Based Self-Organized Maps

2010 ◽  
Author(s):  
Pradeep Lall ◽  
Prashant Gupta
Keyword(s):  
High Speed ◽  
Solder Ball ◽  
Failure Modes ◽  
Remaining Useful Life ◽  
Image Correlation ◽  
Electronic Systems ◽  
Neural Net ◽  
Multiple Failure Modes ◽  
Explicit Finite Element ◽  
Damage Initiation

In this paper prognostic framework for electronic systems has been developed with neural network based self organizing maps for clustering of failure modes. The presented approach resides in the pre-failure space with a focus on electronic systems with multiple failure modes. Portable electronic products subjected to transient shock may exhibit multiple failure modes in vicinity of the interconnects. Failure is often diagnosed by loss of functionality using techniques including the built-in self test, which provides limited insight into reliability and remaining useful life. Unsupervised learning of the neural net has been used to train the neural net for identification of individual failure modes. Feature vectors have been developed based on damage pre-cursors from time-spectral measurements. The clustered damage pre-cursors have been correlated with failure modes of the underlying damage. Several chip-scale packages have been studied, with leadfree second-level interconnects including SAC305, SAC405 alloys. Transient strain has been measured during the drop-event using digital image correlation and high-speed cameras operating at 100,000 fps. Continuity has been monitored simultaneously for failure identification. In addition, explicit finite element models have been developed and various kinds of failure modes have been simulated such as solder ball cracking, trace fracture, package falloff and solder ball failure. Fault modes predicted by simulation based pre-cursors have been correlated with those from experimental data. Activation of different neurons in the lattice for various failure modes and combinations of failure modes has been demonstrated. Previously the authors have developed techniques based on statistical pattern recognition for leading indication of impending failure and detection of damage initiation and progression [Lall 2006a, 2007a, 2008]. Early classification of multiple failure modes in the pre-failure space is new.

CFMA: An Effective FMEA Tool for Analysis and Selection of the Concept for a New Product

1999 ◽  
Author(s):  
Amihud Hari ◽  
Menachem P. Weiss
Keyword(s):  
Failure Mode ◽  
Conceptual Design ◽  
Failure Modes ◽  
New Product ◽  
System Level ◽  
Mode Analysis ◽  
Design Phase ◽  
Concept Selection ◽  
Conceptual Design Phase ◽  
Potential Failure

Abstract It has been established and widely accepted that the early phases of the engineering design process are the most critical to the technical and economical success of a new product. Most of the product’s performance and failures are determined and more than 75% of its life cycle cost is committed during the conceptual design phase. A major step in all conceptual design methodologies is the concept selection phase, where out of the many concepts generated, one is selected and it becomes the basis for the favored solution. Such a selection must be influenced by the potential failure modes, that the product, which is based on the chosen concept, may suffer from and will be exposed to in the future. In the past, the well established Failure Mode and Effects Analysis - FMEA was used for this purpose, but in the system level only. The proposed, new Conceptual Failure Mode Analysis - CFMA is a modified version of FMEA, that was developed for use in the conceptual design phase of a new product. CFMA enables to select the preferred concept (out of many generated), based also on future potential failure modes. CFMA is considered by the authors, as a major and important attribute in concept selection, that can now be taken into account in new concepts evaluation. CFMA is also shown as a vital part of the prescriptive Integrated, Customer Driven, Conceptual Design Method - ICDM, that has recently been introduced by the authors. It is the aim of this paper to introduce CFMA as a substantial additional tool for concept selection.

scholarly journals Molecular Dynamics Simulations on the Tensile Deformation and Failure of a Polyethylene/Copper Interface

2018 ◽  
Author(s):  
Lijuan Liao ◽  
Changyu Meng ◽  
Chenguang Huang
Keyword(s):  
Molecular Dynamics ◽  
Yield Strength ◽  
Failure Mode ◽  
Failure Modes ◽  
Loading Rate ◽  
Tensile Deformation ◽  
Material Strength ◽  
Face Centered Cubic ◽  
Cohesive Failure ◽  
Damage Initiation

In this study, a microscale interface consisting of amorphous polyethylene (PE) chains with the united-atom (UA) model and face-centered cubic (FCC) crystal copper as the substrate was established. Moving the copper layer with a given rate, the damage evolution of the interface during the tensile deformation was examined by molecular dynamics (MD) simulations. The stress-strain relationship was obtained to capture the evolution of tensile deformation. The distribution of the temperature field was adopted to predict the damage initiation and the failure mode. The phase diagram of the failure mode with respect to the thickness of the PE layer and the loading rate was provided. The results show that the PE layer with smaller thickness brings higher load-bearing capacity with larger yield strength. As for the rate-dependence, a rate-hardening followed by a rate-softening of yield strength was observed. In addition, the failure modes evolves from cohesive failure to interfacial one as the loading rate of tension increases progressively. It can be assumed that the control parameter on the failure mode changes from pure material strength of PE to the bonding strength between PE and copper. Furthermore, a larger thickness of PE layer leads to the cohesive failure with higher probability under a narrow range of loading rate with small values. However, the thickness-dependence of failure mode attenuates gradually and diminishes ultimately under higher loading rate, which leads to the transformation from mixed mode to interfacial one.

Sign in / Sign up

Export Citation Format

Share Document