【溫馨提示】====【1】設(shè)計包含CAD圖紙 和 DOC文檔，均可以在線預覽，所見即所得，，dwg后綴的文件為CAD圖，超高清，可編輯，無任何水印，，充值下載得到【資源目錄】里展示的所有文件======【2】若題目上備注三維，則表示文件里包含三維源文件，由于三維組成零件數(shù)量較多，為保證預覽的簡潔性，店家將三維文件夾進行了打包。三維預覽圖，均為店主電腦打開軟件進行截圖的，保證能夠打開，下載后解壓即可。======【3】特價促銷，，拼團購買，，均有不同程度的打折優(yōu)惠，，詳情可咨詢QQ：1304139763 或者 414951605======【4】 題目最后的備注【YC系列】為店主整理分類的代號，與課題內(nèi)容無關(guān)，請忽視
附錄1 翻譯原文及譯文
Doc No: P0193-GP-01-1
Doc Name: Analysis of Manufacturing
Process Data Using
QUICK TechnologyTM
Issue： 1
Data： 20 April ，2006
Name(Print)
Signature
Author：
D.Clifton
Reviewer：
S.Turner
22
Table of Contents
1 Executive Summary 4
1.1 Introdution 4
1.2 Techniques Employed 4
1.3 Summary of Results 4
1.4 Observations 4
2 Introdution 6
2.1 Oxford BioSignals Limited 6
3 External References 7
4 Glossary 7
5 Data Description 8
5.1 Data types 8
5.2 Prior Experiment Knowledge 8
5.3 Test Description 8
6 Pre-processing 10
6.1 Removal of Start/Stop Transients 10
6.2 Removal of Power Supply Signal 10
6.3 Frequency Transformation 10
7 Analysis I-Visualisation 13
7.1 Visualisation of High-Dimensional Data 13
7.2 Visualising 5-D Manufacturing Process Data 13
7.3 Automatic Novelty Detection 15
7.4 Conclusion of Analysis I-Visualisation 16
8 Analysis II-Signature Analysis 17
8.1 Constructing Signatures 17
8.2 Visualising Signatures 19
8.3 Conclusion of Analysis II-Signature Analysis 23
9 Analysis III-Template Analysis 24
9.1 Constructing a Template of Normality 24
9.2 Results of Novelty Detection Using Template Analysis 25
9.3 Conclusion of Analysis III-Template Analysis 26
10 Analysis IV-None-linear Prediction 27
10.1 Neural Networks for On-Line Prediction 27
10.2 Results of Novelty Detection using Non-linear Prediction 27
10.3 Conclusion of Analysis IV-Non-linear Prediction 28
11 Overall Conclusion 29
11.1 Methodology 29
11.2 Summary of Tesults 29
11.3 Future Work 29
12 Appendix A-NeuroScale Visualisations 31
Table of Figures
Figure 1- Test 90. From top to bottom: Ax, Ay, Az, AE, SP against time t(s)
Figure 2- Power spectra for Test 19 after removal of 50Hz power supply contribution. The top plot shows a 3-D “l(fā)andspace” plot of each spectrum. The bottom plot shows a “contour” plot of the same information, with increasing signal power shown as increasing colour from black to red
Figure 3- Power spectra for Test 19 after removal of all spectral components beneath power threshold
Figure 4- Az against time (in seconds) for Test 19,before removal of low-power frequency components
Figure 5- Az against time (in seconds) for Test 19, after removal of low-power frequency components
Figure 6- SP for an example test, showing three automatically-detecrmined states:S1-drilling in (shown in green); S2-drill-bit break-through and removal (shown in red); S3-retraction (shown in blue)
Figure 7- Example signature of variable plotted against operating-point
Figure 8- Power spectra for test 51, frequency (Hz) on the x-axis between [0 fs/2]
Figure 9- Average significant frequency
Figure 10- Visualisation of AE signatures for all tests
Figure 11- Visualisation of Ax broadband signatures for all tests
Figure 12- Visualisation of Ax average-frequency signatures for all tests
Figure 13- Novelty detection using a template signature
Figure 14-
1 Executive Summary
1.1 Introduction
The purpose of this investigation conducted by Oxford BioSignals was to examine and determine the suitability of its techniques in analyzing data from an example manufacturing process. This report has been submitted to Rolls-Royce for the expressed of assessing Oxford BioSignals’ techniques with respect to monitoring the example process.
The analysis conducted by Oxford BioSignals (OBS) was limited to a fixed timescale, a fixed set of challenge data for a single process (as provided by Rolls-Royce and Aachen university of Technology), with no prior domain knowledge, nor information of system failure .
1.2 Techniques Employed
OBS used a number of analysis techniques given the limited timescales:
I-Visualisation, and Cluster Analysis
This powerful method allowed the evolution of the system state (fusing all available data types) to be visualised throughout the series of tests. This showed several distinct modes of operation during the series, highlighting major events observed within the data, later correlated with actual changes to the system’s operation by domain experts.
Cluster analysis automatically detects which of these events may be considered to be “abnormal”, with respect to previously observed system behavior .
II-Signature represents each test as a single point on a plot, allowing changes between tests to be easily identified. Abnormal tests are shown as outlying points, with normal tests forming a cluster.
Modeling the normal behavior of several features selected from the provided data, this method showed that advance warning of system failure could be automatically detected using these features, as well as highlighting significant events within the life of the system.
III-Template Analysis
This method allows instantaneous sample-by –sample novelty detection, suitable for on-line implementation.
Using a complementary approach to Signature Analysis, this method also models normal system behavior. Results confirmed the observation made using previous methods.
IV-Neural network Predictor
Similarly useful for on-line analysis, this method uses an automated predictor of system behaviour(a neural network predictor), in which previously identified events were confirmed, and further significant episodes were detected.
1.3 Summary of Results
Early warning of system failure was independently identified by the various analysis methods employed.
Several significant events during the life of the process were correlated with actual known events later revealed by system experts.
Changes in sensor configurations are identified, and periods of system stability (in which tests are similar to one another) are highlighted.
This report shall be used as the basis for further correlation of detected events against actual occurrences within the life of the system, to be performed by Aachen University of Technology.
1.4 Observations
Based on this limited study, OBS are confident that their techniques are applicable to condition monitoring of the example manufacturing process as follows:
Evidence shows that automated detection of system novelty is possible, compared to its “normal” operation.
Early warning of system distress may be provided, giving adequate time to take preventative maintenance actions such that system failure may be avoided.
Provision “fleet-wide” analysis is possible using the techniques considered within this investigation.
The involvement of domain knowledge from system experts alongside OBS engineers will be crucial in developing future implementations. While this “blind” analysis showed that OBS modelling techniques are appropriate for process monitoring, it is the coupling of domain knowledge with OBS modelling techniques that may provide optimal diagnostic and prognostic analysis.
2 Introduction
2.1 Oxford BioSignals Limited
This document reports on the initial analysis conducted by Oxford BioSignals of manufacturing process challenge data provided by Rolls-Royce, in conjunction with Aachen University of Technology(AUT).
Oxford BioSignals Limited(OBS) is a world-class provider of Acquisition, Data Fusion, Neural Networks and other Advanced Signal Processing techniques and solutions branded under the collective name QUICK Technology. This technology not only provides for health and quality assurance monitoring of the operational performance of equipment and plant.
QUICK Technology has been extensively proven in the field of gas turbine monitoring with both on-line and off-line implementations at multiple levels: as a research tool, a test bed system, a ground support tool, an on-board monitoring system, an off-line analysis tool and a “fleet” manager.
Many of the techniques employed by OBS may be described as novelty detection methods. This approach has a significant advantage over many traditional classification techniques in that it is not necessary to provide fault data to the system during development. Instead, providing a sufficiently comprehensive model of the condition can be identified automatically. As information is discovered regarding the causes of these deviations it is then possible to move from novelty detection to diagnosis, but the ability to identify previously unseen abnormalities is retained at all stages.
3 External References
Accompanying documentation providing further information on the data sets is available in unnumbered documents.
4 Glossary
AUT- Aachen University of Technology
GMM- Gaussian Mixture Model
MLP- Multi-Layer Perception
OBS- Oxford BioSignals Ltd.
5 Data Description
The following sections give a brief overview of the data set obtained by visual inspection of the data.
4.1 Data types
The data provided were recorded over a number of tests. Each test consisted of a similar procedure, in which an automated drill unit moved towards a static metallic disk at a fixed velocity (“feed”), a hole was drilled in the disk at that same feed-rate.
The following data streams were recorded during each test, each sampled at a rate of 20 KHz:
Ax – acceleration of the disk-mounting unit in the x-plane1 ,
Ay- acceleration of the disk-mounting unit in the y-plane1 ,
Az- acceleration of the disk-mounting unit in the z-plane1 ,
AE-RMS acoustic emission, 50-400 KHz2,
SP-power delivered to the drill spindle3.
Tests considered in this investigation used three drill-prices (of identical product specification) as shown in Table 1.
Table 1-Experiment Parameters by Test
Drill Number
Test Numbers
Drill Rotation Rate
Feed Rate
1
[12]
1700RPM
80 mm/min
2
[3127]
1700RPM
80 mm/min
3
[130194]
1700RPM
120mm/min
Note that tests 16,54,128,129 were not provided, thus a series of 190 tests are analysed in this investigation. These 190 tests are labeled as shown in Table 2.
Table 2 –Test indices used in this report against actual test numbers
Test Indices
Actual Test Number
[115]
[115]
[1652]
[1753]
[53125]
[55127]
[126190]
[130194]
4.2 Prior Experiment Knowledge
4.2.1 Normal Tests
AUT indicated that tests [10110] could be considered “normal processes”.
4.2.2 AE Sensor Placement
AUT noted that the position of the acoustic emission sensor was altered prior to test 77, and was adjusted prior to subsequent tests. From inspection of AE data, it appears that AE measurements are consistent after test 84, and so:
·AE is assumed to be unusable for tests [176] –the sensor records only white noise;
·AE is assumed to be usable, but possibly abnormal, for tests [7783] –the sensor position is being adjusted, resulting in extreme variation in measurements;
·AE is assumed to be usable for tests [94190] –the sensor position is held constant during these tests.
Thus, the range of tests assumed to be normal [10110] should be reduced to [84110] when AE is considered.
4.3 Test Description
Data recorded for during a typical test are shown in Figure 1. The duration of this test is approximately t=51 seconds. This section uses this test to illustrate a typical process, as described by AUT.
Drill power-on and power-off events may be seen at the start and end of the test as transient spikes in SP.
The drill unit is then moved towards the static disk at the constant feed rata specified in Table 1, between t=12 and 27 seconds. This corresponds to approximately constant values of SP during that period, approximately zero AE, and very lowamplitude acceleration in x-,y-,and z- planes.
At t=27 seconds, the drill makes contact with the static disk and begins to drill into the metal. This corresponds to a step-change in SP to a higher lever, staying approximately constant until t=38 seconds. During this time, AE increases significantly to a largely constant but non-zero value. The values Ax and Az increase throughout this drilling operation, while the value of Ay remains approximately zero (as it does throughout the test).
At t=38 seconds, the tip of the drill-bit passes through the rear face of the disk. The value of SP increases until t=44 seconds. During this period, AE reaches correspondingly high values, while Ax and Az decrease in amplitude.
At t=44 seconds, the direction of the drill unit is reversed, and the drill is retracted from the metal disk. Until t=46 seconds, the value of SP and AE decrease rapidly. A transient is observed in Ax and Az at t =44 seconds, with vibration amplitude decreasing until t=46 seconds.
At t=46 seconds, the drill-bit has been completely retracted from the metal disk, and the unit continues to be withdrawn at the feed rate until the end of the test. The value of SP decreases during this period(noting the power-off transient at the very end of the test), while the values of all three acceleration channels and AE are approximately zero.
6 .Pre-processing
4.4 Removal of Start/Stop Transients
Assuming that normal and abnormal system behaviour will be evident from data acquired during the drilling process, prior to analysis, each test was shortened by retaining only data between the start and stop events, shown as transients in SP. For example, for the test shown in Figure 1, this corresponds to retaining the period [1350] seconds.
4.5 Removal of Power Supply Signal
The 50 Hz power supply appears with in each channel, and was removed prior to analysis by application of a band-stop filter with stop-band [4951] Hz.
4.6 Frequency Transformation
Data for each test were divided into windows of 4096 points. A 4096-point FFT for was performed using data within each window, for Ax,Ay and Az channels. This corresponds to approximately 5 FFTs per second of data，similar to the QUICK system used in aerospace analysis， shown to provide sufficient resolution for identifying frequency-based events indicative of system abnormality.
For the analyses performed in this investigation, all spectral components of Ax, Ay, and Ay occurring at frequency f with power Pf below some threshold Pf
收藏