Application of Bayesian Forecasting to Change Detection and Prognosis of Gas Turbine Performance

2009 ◽  
Vol 132 (3) ◽  
Author(s):  
Holger Lipowsky ◽  
Stephan Staudacher ◽  
Michael Bauer ◽  
Klaus-Juergen Schmidt
Keyword(s):  
Change Detection ◽  
Probability Density ◽  
Alternative Model ◽  
Detection Rate ◽  
Bayesian Forecasting ◽  
False Detection Rate ◽  
False Detection ◽  
High Detection Rate ◽  
Detection Rates ◽  
High Detection

The performance of gas turbines degrades over time due to deterioration mechanisms and single fault events. While deterioration mechanisms occur gradually, single fault events are characterized by occurring accidentally. In the case of single events, abrupt changes in the engine parameters are expected. Identifying these changes as soon as possible is referred to as detection. State-of-the-art detection algorithms are based on expert systems, neural networks, special filters, or fuzzy logic. This paper presents a novel detection technique, which is based on Bayesian forecasting and dynamic linear models (DLMs). Bayesian forecasting enables the calculation of conditional probabilities, whereas DLMs are a mathematical tool for time series analysis. The combination of the two methods can be used to calculate probability density functions prior to the next observation, or the so called forecast distributions. The change detection is carried out by comparing the current model with an alternative model, where the mean value is shifted by a prescribed offset. If the forecast distribution of the alternative model better fits the actual observation, a potential change is detected. To determine whether the respective observation is a single outlier or the first observation of a significant change, a special logic is developed. In addition to change detection, the proposed technique has the ability to perform a prognosis of measurement values. The developed method was run through an extensive test program. Detection rates >92% have been achieved for changed heights, as small as 1.5 times the standard deviation of the observed signal (sigma). For changed heights greater than 2 sigma, the detection rates have proven to be 100%. It could also be shown that a high detection rate is gained by a high false detection rate (∼2%). An optimum must be chosen between a high detection rate and a low false detection rate, by choosing an appropriate uncertainty limit for the detection. Increasing the uncertainty limit decreases both detection rate and false detection rate. In terms of prognostic abilities, the proposed technique not only estimates the point of time of a potential limit exceedance of respective parameters, but also calculates confidence bounds, as well as probability density and cumulative distribution functions for the prognosis. The conflictive requirements of a high degree of smoothing and a quick reaction to changes are fulfilled in parallel by combining two different detection conditions.

A Approach to Change Detection for HR Image

2014 ◽  
Vol 971-973 ◽  
pp. 1449-1453
Author(s):  
Zuo Wei Huang ◽  
Shu Guang Wu ◽  
Tao Xin Zhang
Keyword(s):  
Change Detection ◽  
Detection Rate ◽  
False Detection Rate ◽  
False Detection ◽  
High Detection Rate ◽  
High Detection ◽  
Self Adaptation ◽  
Ica Algorithm ◽  
Different Characteristics ◽  
Better Than

Hyperspectral remote sensing is the multi-dimensional information obtaining technology,which combines target detection and spectral imaging technology together, In order to accord with the condition of hyperspectral imagery，the paper developed an optimized ICA algorithm for change detection to describe the statistical distribution of the data. By processing these abundance maps, change of different classes of objects can be obtained..A approach is capable of self-adaptation, and can be applied to hyperspectral images with different characteristics. Experiment results demonstrate that the ICA-based hyperspectral change detection performs better than other traditional methods with a high detection rate and a low false detection rate.

Application of Bayesian Forecasting to Change Detection and Prognosis of Gas Turbine Performance

2009 ◽  
Author(s):  
Holger Lipowsky ◽  
Stephan Staudacher ◽  
Michael Bauer ◽  
Klaus-Juergen Schmidt
Keyword(s):  
Change Detection ◽  
Probability Density ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Alternative Model ◽  
Linear Models ◽  
Current Model ◽  
Distribution Functions ◽  
Cumulative Distribution ◽  
Bayesian Forecasting

This paper presents a novel technique for automatic change detection of the performance of gas turbines. In addition to change detection the proposed technique has the ability to perform a prognosis of measurement values. The proposed technique is deemed to be new in the field of gas turbine monitoring and forms the basic building block of a patent pending filed by the authors [1]. The technique used is called Bayesian Forecasting and is applied to Dynamic Linear Models (DLMs). The idea of Bayesian Forecasting is based on Bayes’ Theorem, which enables the calculation of conditional probabilities. In combination with DLMs (which break down the chronological sequence of the observed parameter into mathematical components like value, gradient, etc.) Bayesian Forecasting can be used to calculate probability density functions prior to the next observation, so called forecast distributions. The change detection is carried out by comparing the current model with an alternative model which mean value is shifted by a prescribed offset. If the forecast distribution of the alternative model better fits the actual observation, a potential change is detected. To determine whether the respective observation is a single outlier or the first observation of a significant change, a special logic is developed. Studies have shown that a confident change detection is possible for a change height of only 1.5 times the standard deviation of the observed signal. In terms of prognostic abilities the proposed technique not only estimates the point of time of a potential limit exceedance of respective parameters, but also calculates confidence bounds as well as probability density and cumulative distribution functions for the prognosis.

scholarly journals Detection Thresholds and Bias Correction in Polarized Intensity

2012 ◽  
Vol 29 (3) ◽  
pp. 214-220 ◽  
Author(s):  
Samuel J. George ◽  
Jeroen M. Stil ◽  
Ben W. Keller
Keyword(s):  
Gaussian Noise ◽  
Bias Correction ◽  
Detection Rate ◽  
Detection Threshold ◽  
False Detection Rate ◽  
False Detection ◽  
Detection Thresholds ◽  
Detection Rates ◽  
Rotation Measure ◽  
Non Gaussian

AbstractDetection thresholds in polarized intensity and polarization bias correction are investigated for surveys where the polarization information is obtained from rotation measure (RM) synthesis. Considering unresolved sources with a single RM, a detection threshold of 8 σQU applied to the Faraday spectrum will retrieve the RM with a false detection rate less than 10−4, but polarized intensity is more strongly biased than Ricean statistics suggest. For a detection threshold of 5 σQU, the false detection rate increases to ∼4%, depending also on λ2 coverage and the extent of the Faraday spectrum. Non-Gaussian noise in Stokes Q and U due to imperfect imaging and calibration can be represented by a distribution that is the sum of a Gaussian and an exponential. The non-Gaussian wings of the noise distribution increase the false detection rate in polarized intensity by orders of magnitude. Monte Carlo simulations assuming non-Gaussian noise in Q and U give false detection rates at 8 σQU similar to Ricean false detection rates at 4.9 σQU.

Detection of Atherosis in Preeclamptic Placentas: Comparison of Two Gross Sampling Protocols

2005 ◽  
Vol 8 (1) ◽  
pp. 61-65 ◽  
Author(s):  
Norman Walford ◽  
Kyaw Htun ◽  
Meenakshi Akhilesh
Keyword(s):  
Detection Rate ◽  
Current Practice ◽  
High Detection Rate ◽  
Detection Rates ◽  
Sampling Protocols ◽  
En Face ◽  
High Detection ◽  
Vascular Compromise ◽  
Flat Membrane ◽  
Criteria For Diagnosis

Two standardized gross sampling protocols were compared with the intention of maximizing the histologic detection rate of atherosis in at-risk (i.e., preeclamptic) placentas. The first, 4-block, protocol was designed to be broadly representative of good current practice (central, edge, en face shave, and membrane roll blocks). A second, 5-block, protocol incorporated all of protocol 1 with the addition of a block composed of multiple flat membrane leaves stacked and sectioned 5 times at 200-μm intervals. Data were available on the first protocol from 80 consecutive accessioned cases of singleton preeclamptic placentas and on the second protocol from 40 cases. Criteria for diagnosis for atherosis were relatively rigorous and excluded “burnt-out” fibrinoid lesions in which foam cells were not positively identified. With the first protocol, atherosis was detected in 30 of 80 (37.5%) of placentas studied. With the second protocol, atherosis was detected in 25 of 40 (62.5%) of placentas studied. This increase was related to a high detection rate of 50% in the flat membrane stack block. Evaluation of the more traditional forms of block produced atherosis detection rates of 2.5% for central full-thickness blocks, 14% for edge blocks, 10% for en face shave blocks, and 25% for membrane rolls. The flat membrane stack was found to be the single most sensitive block for detection of atherosis. When used in conjunction with traditional blocking techniques, it offers significantly increased reliability for detection of atherosis in placentas when maternal vascular compromise is suspected.

scholarly journals [18F]-JK-PSMA-7 PET/CT Under Androgen Deprivation Therapy in Advanced Prostate Cancer

2020 ◽  
Author(s):  
Felix Dietlein ◽  
Peter Mueller ◽  
Carsten Kobe ◽  
Heike Endepols ◽  
Melanie Hohberg ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Androgen Deprivation Therapy ◽  
Detection Rate ◽  
Androgen Deprivation ◽  
High Detection Rate ◽  
Detection Rates ◽  
Pet Ct ◽  
Significant Difference ◽  
High Detection

Abstract Purpose PSMA imaging is frequently used for monitoring of androgen deprivation therapy (ADT) in prostate cancer. In a previous study, [18F]-JK-PSMA-7 exhibited favorable properties for tumor localization after biochemical recurrence. In this retrospective study, we evaluated the performance of [18F]-JK-PSMA-7 under ADT. Procedures We examined the performance of [18F]-JK-PSMA-7 in 70 patients (first cohort) with increasing or detectable PSA values under ADT (PSA < 2 ng/ml for 21/70 patients). We further analyzed 58 independent patients with PSA levels < 2 ng/ml under ADT, who were imaged with [68Ga]PSMA-11 or [18F]DCFPyL (second cohort). Finally, we compared detection rates between [18F]-JK-PSMA-7, [68Ga]PSMA-11, and [18F]DCFPyL. Results In the first cohort, we detected [18F]-JK-PSMA-7-positive lesions in 63/70 patients. In patients with PSA levels ≥ 2 ng/ml, the detection rate was 100 % (49/49). In patients with PSA < 2 ng/ml, the detection rate was significantly lower (66.7 %, 14/21, p = 9.7 × 10−5) and dropped from 85.7 % (12/14, PSA levels between 0.3 and 2.0 ng/ml) to 28.6 % (2/7) for PSA levels < 0.3 ng/ml (p = 1.73 × 10−2). In the second cohort (PSA < 2 ng/ml), the detection rate was 79.3 % (46/58) for [68Ga]PSMA-11 or [18F]DCFPyL. Again, the detection rate was significantly higher (p = 1.1 × 10−2) for patients with PSA levels between 0.3 and 2.0 ng/ml (87.0 %, 40/46) relative to those with PSA levels < 0.3 ng/ml (50 %, 6/12). No significant difference was found between [18F]-JK-PSMA-7 and [68Ga]PSMA-11 or [18F]DCFPyL in patients with PSA levels < 2 ng/ml (p = 0.4295). Conclusion [18F]-JK-PSMA-7 PET showed a high detection rate in patients with PSA levels ≥ 0.3 ng/ml under ADT. The lower PSA threshold of 0.3 ng/ml for high detection rates was consistent across the three PSMA ligands. Thus, PSMA imaging is suitable for clinical follow-up of patients with increasing PSA levels under ADT.

Faster multi-defect detection system in shield tunnel using combination of FCN and faster RCNN

2019 ◽  
Vol 22 (13) ◽  
pp. 2907-2921 ◽  
Author(s):  
Xinwen Gao ◽  
Ming Jian ◽  
Min Hu ◽  
Mohan Tanniru ◽  
Shuaiqing Li
Keyword(s):  
Boundary Layer ◽  
Defect Detection ◽  
Detection Rate ◽  
Layer Structure ◽  
Detection System ◽  
Identification Accuracy ◽  
Shield Tunnel ◽  
False Detection Rate ◽  
False Detection ◽  
Data Set

With the large-scale construction of urban subways, the detection of tunnel defects becomes particularly important. Due to the complexity of tunnel environment, it is difficult for traditional tunnel defect detection algorithms to detect such defects quickly and accurately. This article presents a deep learning FCN-RCNN model that can detect multiple tunnel defects quickly and accurately. The algorithm uses a Faster RCNN algorithm, Adaptive Border ROI boundary layer and a three-layer structure of the FCN algorithm. The Adaptive Border ROI boundary layer is used to reduce data set redundancy and difficulties in identifying interference during data set creation. The algorithm is compared with single FCN algorithm with no Adaptive Border ROI for different defect types. The results show that our defect detection algorithm not only addresses interference due to segment patching, pipeline smears and obstruction but also the false detection rate decreases from 0.371, 0.285, 0.307 to 0.0502, respectively. Finally, corrected by cylindrical projection model, the false detection rate is further reduced from 0.0502 to 0.0190 and the identification accuracy of water leakage defects is improved.

scholarly journals A Deep Learning Approach of Vehicle Multitarget Detection from Traffic Video

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Xun Li ◽  
Yao Liu ◽  
Zhengfan Zhao ◽  
Yue Zhang ◽  
Li He
Keyword(s):  
Detection Rate ◽  
Detection Method ◽  
Training Model ◽  
Learning Approach ◽  
Flow State ◽  
False Detection Rate ◽  
False Detection ◽  
Road Vehicles ◽  
Traffic Video ◽  
Flow States

Vehicle detection is expected to be robust and efficient in various scenes. We propose a multivehicle detection method, which consists of YOLO under the Darknet framework. We also improve the YOLO-voc structure according to the change of the target scene and traffic flow. The classification training model is obtained based on ImageNet and the parameters are fine-tuned according to the training results and the vehicle characteristics. Finally, we obtain an effective YOLO-vocRV network for road vehicles detection. In order to verify the performance of our method, the experiment is carried out on different vehicle flow states and compared with the classical YOLO-voc, YOLO 9000, and YOLO v3. The experimental results show that our method achieves the detection rate of 98.6% in free flow state, 97.8% in synchronous flow state, and 96.3% in blocking flow state, respectively. In addition, our proposed method has less false detection rate than previous works and shows good robustness.

HE-YOLO: Aerial Target Detection Based On Improved YOLOv3

2021 ◽  
Author(s):  
Yuqing Zhao ◽  
Jinlu Jia ◽  
Di Liu ◽  
Yurong Qian
Keyword(s):  
Target Detection ◽  
Loss Function ◽  
Detection Rate ◽  
Aerial Image ◽  
Experimental Comparison ◽  
Small Scale ◽  
Detection Accuracy ◽  
False Detection Rate ◽  
False Detection ◽  
Bounding Box

Aerial image-based target detection has problems such as low accuracy in multiscale target detection situations, slow detection speed, missed targets and falsely detected targets. To solve this problem, this paper proposes a detection algorithm based on the improved You Only Look Once (YOLO)v3 network architecture from the perspective of model efficiency and applies it to multiscale image-based target detection. First, the K-means clustering algorithm is used to cluster an aerial dataset and optimize the anchor frame parameters of the network to improve the effectiveness of target detection. Second, the feature extraction method of the algorithm is improved, and a feature fusion method is used to establish a multiscale (large-, medium-, and small-scale) prediction layer, which mitigates the problem of small target information loss in deep networks and improves the detection accuracy of the algorithm. Finally, label regularization processing is performed on the predicted value, the generalized intersection over union (GIoU) is used as the bounding box regression loss function, and the focal loss function is integrated into the bounding box confidence loss function, which not only improves the target detection accuracy but also effectively reduces the false detection rate and missed target rate of the algorithm. An experimental comparison on the RSOD and NWPU VHR-10 aerial datasets shows that the detection effect of high-efficiency YOLO (HE-YOLO) is significantly improved compared with that of YOLOv3, and the average detection accuracies are increased by 8.92% and 7.79% on the two datasets, respectively. The algorithm not only shows better detection performance for multiscale targets but also reduces the missed target rate and false detection rate and has good robustness and generalizability.

Sign in / Sign up

Export Citation Format

Share Document