Fault Diagnostics and Prognostics methods in Nuclear Power ... · Fault Diagnostics and Prognostics...

Fault Diagnostics and Prognostics

methods in Nuclear Power Plants

Piero Baraldi

Politecnico di Milano

22Piero Baraldi

Normal

operation

Remaining Useful Life

Detect Diagnose Predict

Nuclear Power Plant Component)

c2c1 c3

Measuredsignals

Anomalous

operationMalfunctioning type

(classes)

Fault Diagnostics and Prognostics

Data-driven fault diagnostics

4444Piero Baraldi

In This Lecture

1. Fault diagnostics: what is it?

2. Procedural steps for developing a fault diagnostic system

3. Artificial Neural Networks

5555Piero Baraldi

DIAGNOSIS

(correct assignment)

Normal operation

Measured

signals

Forcing

functions

DETECTION

early recognition

Fault diagnostics: What is it 5

Transient

Industrial

system

6666Piero Baraldi

Fault diagnostics: transient classification

Measured signals

Diagnostic

System

Fault Class 1

Fault Class 2

Fault Class c

Classifier

Fault Class 1

Fault Class 2

Fault Class c

Transient

7777Piero Baraldi

In This Lecture

1. Fault diagnostics: what is it?

2. Procedural steps for developing a fault diagnostic system

3. Objectives of a fault diagnostic system

4. Unsupervised classification methods

5. Supervised classification methods

8888Piero Baraldi

Empirical Approach to Fault Classification

1. Identify fault/degradation classes:

▪ System Analysis (FMECA, Event Tree Analysis, …)

▪ Good engineering sense of practice

▪ Analysis of the historical data

{C1 C2}

1x = signal 1

= signal 22x

9999Piero Baraldi

1. Identify fault/degradation classes

2. Collect data couples: <measurements, class>

▪ Historical data

▪ Fault transients in industrial systems may be rare

▪ Information on the class of the fault originating the transient is not always available

1x = representative signal 1

= representative signal 22x

10101010Piero Baraldi

Example: turbine transients in a Nuclear Power Plant

HealthyType 1

malfunctioning

Type 2

malfunctioning

Type 3

malfunctioning

Type 4

malfunctioning

Available data

• 5 signals (operational conditions) + 7 signals (turbine behaviour)

• 149 shut-down transients from a nuclear power plant

• Types of anomalies are unknown

1. Identify fault classes

2. Collect data couples: <measurements, fault class>

▪ Historical plant data

▪ Fault transients in industrial systems may be rare

▪ Information on the class of the fault originating the transient is not always available

▪ Physics-based simulator

1. Identify fault classes

2. Collect data couples: <measurements, fault class>

3. Develop the empirical classification algorithm using as training set the collected data couples: <measurements, fault classes >

Measured signals

Classifier

Fault Class 1

Fault Class 2

Fault Class c

Data-driven fault prognostics approaches

• Machine learning and data mining algorithmso Support Vector Machineso K-Nearest Neighbour Classifiero Fuzzy similarity-based approacheso Artificial Neural Networkso Neurofuzzy Systemso Relevant Vector Machineso …

o Prognostics

o What is it?

o Sources of information

o Prognostic approaches

Fault prognostics: What is it?

Remaining Useful Life

Predict

o Prognostics

o What is it?

• Threshold of failure

• Current degradation

trajectory

• External/operational

conditions

Life durations of a

set of

similar components

• Degradation

trajectories of similar

components

• A physics-based model

of the degradation

Prognostics: Sources of Information

Piero Baraldi

Sources of Information: An example 18

Component: turbine blade

Degradation mechanism: creeping

Component: turbine blade

Degradation mechanism: creeping

Degradation indicator: blade elongation

Prognostics: an example

Length(t) – initial length

initial length tx

Sources of information for prognostics

• Life durations of a set of similar components which have already failed:

𝑇1, 𝑇2, … , 𝑇𝑛

Failure time (days)

• Life durations of a set of similar components which have already failed

• Threshold of failure:

Fault Initiation

• Threshold of failure:

Fault Initiation

«A blade is discarded when the elongation, x, reaches 1.5%»

• A sequence of observations collected from the degradation initiation to the

present time (current degradation trajectory): 𝑧1, 𝑧2 … , 𝑧𝑘

Threshold

of failure

present time (current degradation trajectory): 𝑧1, 𝑧2 … , 𝑧𝑘

Elongation measurements = past evolution of the degradation indicator

Threshold

of failure

present time (current degradation trajectory)

• Degradation trajectories of similar components

Fault Initiation

• Information on external/operational conditions (past – present - future)

Past, present and future time evolution of: ,...,,...,, 121 kk uuuu

𝒖𝟏 = T = temperature

𝒖𝟐 =θr = rotational speed

• A physics-based model of the degradation process

1111 ,,,..., kkkkk uxxfx

• Measurement equation

• A physics-based model of the degradation process

Norton law for creep growth

x = blade elongation

T = temperature

φ = Kθr2 = applied stress

θr = rotational speed

A, Q, n = equipment inherent parameters

Arrhenius law

External/operational conditions

o Prognostics

o What is it?

DrivenExperience-

Model-

trajectory

conditions

Life durations of a

set of

similar components

• Degradation

components

of the degradation

Prognostic approaches

DrivenExperience-

Model-

trajectory

conditions

Life durations of a

set of

similar components

• Degradation

components

• Measurement equation

of the degradation

Prognostic approaches

Hybrid

Data driven fault prognostics

o When?

❖ Understanding of first principles of component degradation is not comprehensive

❖ System sufficiently complex that developing an accurate physical model is prohibitively expensive

o Advantages:

❖ Quick and cheap to be developed

❖ They can provide system wide-coverage

o Disadvantages

❖ They require a substantial amount of data for training:

Degradation data are difficult to collect for new or highly reliable systems (running systems to failure can be a lengthy and costly process)

Quality of the data can be low due to difficulty in the signal measurements

Artificial Neural Networks

How to build an empirical

using input/output data?

The problem

x1(1), x2

(1) , x3(1) | t1

(1), t2(1)

x1(2), x2

(2) , x2(2) | t1

(2), t2(2)

What are Artificial Neural Networks (ANN)?

Multivariate, non linear interpolators capable of

reconstructing the underlying complex I/O nonlinear

relations by combining multiple simple functions.

An artificial neural network is composed by several

simple computational units (also called nodes or

neurons)

What Are (Artificial) Neural Networks?

y1 y2 … yn

The computational unit

𝑓′ = 𝑓 1 − 𝑓

y represented

y1 y2 … yn

The computational unit: other representations

ymj = wmjuj

Connection between nodes i and j

The weighted connection

wmj = synapsis weight

between nodes j

An artificial neural network is composed by several simple computational units

(also called nodes or neurons) directionally connected by weighted

connections

An artificial neural network is composed by several simple computational

units (also called nodes or neurons) directionally connected by weighted

connections organized in a proper architecture

An example of ANN architecture

The multilayered feedforward ANN

OUTPUTNumber of connections

117+85=117

ARTIFICIAL NEURAL NETWORKS

INPUT LAYER:

each k-th node (k=1, 2, …, ni) receives the value of the k-th component

of the input vector and delivers the same valuex

HIDDEN LAYER:

each j-th node (j=1, 2, …, nh) receives

jjkk wwx1

and delivers

j wwxfu1

0 with 𝑓ℎ typically sigmoidal

Multilayered Feedforward NN

OUTPUT LAYER:

each l-th node (l=1, 2, …, no) receives

j wwu1

and delivers

l wwufu1

0 f typically linear or sigmoidal

Forward Calculation (hidden-output)

Why are we speaking of “Neural Networks”?

Biological basis of ANN

Human brain is a densely interconnected network of approximately 1011 neurons, each connected to, on average, 104 others.

Neuron activity is excited or inhibitedthrough connections to other neurons.

Biological Motivation

Biological Motivation: the neuron

The dendritesprovide input signals to the cell.

The axon sends output signals to cell 2 via the axon terminals. These axon terminals merge with the dendrites of cell 2.

What is the mathematical basis

behind Artificial Neural Networks?

Neural networks are universal approximators of multivariate

non-linear functions.

KOLMOGOROV (1957):

For any real function continuous in [0,1]n, n2, there

exist n(2n+1) functions ml() continuous in [0,1] such that

),...,,( 21 nxxxf

21 )(),...,,(n

mmlln xxxxf

where the 2n+1 functions l’s are real and continuous.

Thus, a total of n(2n+1) functions ml() and 2n+1 functions l

of one variable represent a function of n variables

What is the mathematical basis behind Artificial Neural Networks?

Neural networks are universal approximators of multivariate

non-linear functions.

CYBENKO (1989):

Let (•) be a sigmoidal continuous function. The linear combinations

jijij wx0 1

What is the mathematical basis behind Artificial Neural Networks?

How to train an ANN?

Setting the ANN parameters

The ANN parameters to be set

• Once the ANN architecture has been fixed (number of

layers, number of nodes for layer), the only parameters

to be set are the synapsis weights (wlj , wjk)

x1(1), x2

(1) | t(1)

x1(2), x2

(2) | t(2)

x1(p), x2

(p) | t(p)

x1(np), x2

(np) | t(np)

Synapsis

Weights

Available input/output patterns

Setting the ANN Parameters: Training Phase

The Training Objective

Training Objective: minimize the average squared

output deviation error (also called Energy Function):

p lp o

E u tn n

TRUE l-th output of

the p-th training

pattern

ANN l-th output of

the p-th training

pattern

The Training objective: graphical representation

• E is a function of

the ANN outputs

• E is a function of

the synapsis

weights [wjk]

The error back propagation algorithm

gradientLearning coefficient

Error Backpropagation (hidden-output)

𝐸 =1

2𝑛𝑜

𝑙=1

𝑛𝑜

𝑢𝑙𝑜 − 𝑡𝑙

𝐸 =1

2𝑛𝑜

𝑙=1

𝑛𝑜

𝜕𝐸

𝜕𝑤𝑙𝑗=

2 𝑢𝑙𝑜 − 𝑡𝑙

2𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑤𝑙𝑗

Output layer neuron

𝑦𝑙1𝑜 𝑦𝑙𝑗

𝑜 𝑦𝑙𝑛ℎ

𝐸 =1

2𝑛𝑜

𝑙=1

𝑛𝑜

𝜕𝐸

𝜕𝑤𝑙𝑗=

2𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑤𝑙𝑗=

𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑦𝑙𝑜

𝜕𝑤𝑙𝑗

=𝑢𝑙

𝑜 − 𝑡𝑙

𝑛𝑜𝑓′(𝑦𝑙

𝑜)𝜕 σ

𝑗′=1𝑛ℎ 𝑦𝑙𝑗′

𝜕𝑤𝑙𝑗

Output layer neuron

𝑦𝑙1𝑜 𝑦𝑙𝑗

𝑜 𝑦𝑙𝑛ℎ

𝐸 =1

2𝑛𝑜

𝑙=1

𝑛𝑜

𝜕𝐸

𝜕𝑤𝑙𝑗=

2𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑤𝑙𝑗=

𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑦𝑙𝑜

𝜕𝑤𝑙𝑗

=𝑢𝑙

𝑜−𝑡𝑙

𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑦𝑙𝑜

𝜕 σ𝑗′=1

𝑛ℎ 𝑦𝑙𝑗′𝑜

𝜕𝑤𝑙𝑗=

𝑢𝑙𝑜−𝑡𝑙

𝑛𝑜

𝜕𝑢𝑙𝑜

𝜕𝑦𝑙𝑜 𝑢𝑗

ℎ 𝑦𝑙𝑗𝑜

𝑢𝑗ℎ

𝑦𝑙𝑗𝑜 = 𝑤𝑙𝑗 ∙ 𝑢𝑗

𝐸 =1

2𝑛𝑜

𝑙=1

𝑛𝑜

momentum

Error Backpropagation (input- hidden)

Error Backpropagation (hidden-input)

Updating weight wjk (hidden-input connections)

Similarly to the updating of the output-hidden weigths,

1( ) ( 1)i

jk j j jk

w n u w nn

Learning coefficient Momentum

After training:

• Synaptic weights fixed

• New input retrieval of information in the weights output

Capabilities:

• Nonlinearity of sigmoids NN can learn nonlinear mappings

• Each node independent and relies only on local info (synapses)

Parallel processing and fault-tolerance

Utilization of the Neural Network

CONCLUSIONS [ANN]

Advantages:

➢No physical/mathematical modelling efforts.

➢Automatic parameters adjustment through a training phase based on available input/output data. Adjustments to obtain the best interpolation of the functional relation between input and output.

Disadvantages:

“black box” : difficulties in interpreting the underlying physical model.

ANN for fault diagnostics

Objective

• Build and train a neural network to classify different malfunctions in the plant component

Input/Output patterns

• Input: Signal Measuraments

• Output: number (label )of the class of the failure

Training set

classxxxxxx

classtxtxtxtxtxtx

classxxxxxx

)35()36()35()36()35()36(

)()1()()1()()1(

)1()()1()()1()(

)1()2()1()2()1()2(

10102211

ANN for fault prognostics

• Possible approaches• Learning directly from data the component RUL

• Modeling cumulative damage (health index) and then extrapolating out to a damage (health) threshold

ANN for fault prognostics

• Possible approaches• Learning directly from data the component RUL

• Modeling cumulative damage (health index) and then extrapolating out to a damage (health) threshold

Direct RUL Prediction: The model

…RUL

Information necessary to develop the model

)(1 tx

• Signal measurements for a set of N similar components from degradation onset to failure

Similar Component 1:Data available

Information necessary to develop the model

)(1 tx

• Signal measurements for a set of N similar components from degradation onset to failure

ANN training data

Input Output

RUL… … …

1… … …

Trajecto

… … … … … …. … ….

𝑡𝑓(1)

− 𝑚 − 1

𝑡𝑓(𝑁)

− 𝑚 − 1

How to set the ANN architecture

1 2 3 4 5 6 7 8 9 10 …

Error on the validation set

Fault Diagnostics and Prognostics methods in Nuclear Power ... · Fault Diagnostics and Prognostics...

Documents

bñ'b. * — 7— F: prognostics. 2011 30 12 @ (2002bñ'b. * — 7— F: prognostics. 2011 30 12 @ (2002

Actuator Systems Prognostics - NASA · Actuator Systems Prognostics Edward Balaban, Abhinav Saxena, Prasun Bansal, Kai Goebel Prognostics Center of Excellence, NASA ARC Overview Challenges

“RELIABILITY, SAFETY AND RISK ANALYSIS” · · 2018-02-26is determined by the reliability of the weak link ... • Reliability • Safety • Risk Analysis. Piero Baraldi The

Prognostics Requirement Specification final

Ernest Baraldi - Jolie cadence ( orchestration ) ( polka marche ).pdf

Modern Reliability and Maintenance Engineering for …sites.ieee.org/italy/files/2016/09/TUTORIAL-2.pdfModern Reliability and Maintenance Engineering for Modern Industry Piero Baraldi,

Prognostics Overview Electronic Prognostics · defense, military, medical, and other sectors. To ensure high levels of reliability and performance, prognostics technology developers

Prognostické metody bezpečnostních fenoménů Prognostics

A Data-Driven Failure Prognostics Method.pdf

Portfolio Mary Baraldi Makeup

Baraldi Advocacia Empresariallancamentoejf.analise.com/wp-content/uploads/2019/06/patrocinado… · Informe do Patrocinador Baraldi Advocacia Empresarial Rua Gomes de Carvalho, 1069

Monte Carlo and Possibilistic Methods for Uncertainty Analysis...Example 1: Uncertainty in Event Tree Analysis Safety system 1 Safety system 2 Piero Baraldi Example 2: Reliability

LECTURE 14 MAINTENANCE: BASIC CONCEPTS · BASIC CONCEPTS Piero Baraldi Politecnico di Milano, Italy. piero.baraldi@polimi.it. Piero Baraldi 2 LECTURE 14 ... Piero Baraldi 11 Corrective

1111111111111111111inuuu1111111111u~ - NASA · R.Pino,R., and Pazienza, G. (eds), Springer Verlag. Baraldi, A. and Alpaydin, E. (1998). Simplified ART: Anew class ... Baraldi, Andrea

MATEMATICOPIACERE - Baraldi Celeste

Baraldi impaginato catalogo new series 2014 lowres

Aven Terje Aven | Piero BArAldi | roger FlAge | enrico Zio ...download.e-bookshelf.de/download/0000/8276/62/L-G-0000827662... · Uncertainty in Risk Assessment The Representation

GoProDxTM Prostate Cancer Prognostics

Prognostics with optimization

TEREZA CRISTINA ALBIERI BARALDI A VIOLÊNCIA DOMÉSTICA