Condition Monitoring of Elevator Systems using Deep Neural Network

Krishna Mohan Mishra and Kalevi Huhtala

Unit of Automation Technology and Mechanical Engineering, Tampere University, Tampere, Finland

Keywords:

Deep Neural Network, Fault Detection, Feature Extraction, Elevator Systems.

Abstract:

In this research, we propose a generic deep autoencoder model for automatic calculation of highly informative

deep features from the elevator data. Random forest algorithm is used for fault detection based on extracted

deep features. Maintenance actions recorded are used to label the sensor data into healthy or faulty. In our

research, we have included all fault types present for each elevator. The rest of the healthy data is used

for validation of the model to prove its efﬁcacy in terms of avoiding false positives. New extracted deep

features provide 100% accuracy in fault detection along with avoiding false positives, which is better than

statistical features. Random forest was also used to detect faults based on statistical features to compare

results. New deep features extracted from the dataset with deep autoencoder random forest outperform the

statistical features. Good classiﬁcation and robustness against overﬁtting are key characteristics of our model.

This research will help to reduce unnecessary visits of service technicians to installation sites by detecting

false alarms in various predictive maintenance systems.

1 INTRODUCTION

In recent years, apartments, commercial facilities and

ofﬁce buildings are using elevator systems more ex-

tensively. Nowadays, urban areas comprised of 54%

of the worlds population (Desa, 2014). Therefore,

proper maintenance and safety are required by ele-

vator systems. Development of predictive and pre-

emptive maintenance strategies will be the next step

for improving the safety of elevator systems, which

will also increase the lifetime and reduce repair costs

whilst maximizing the uptime of the system (Ebeling,

2011), (Ebeling and Haul, 2016). Predictive mainte-

nance policy are now being opted by elevator produc-

tion and service companies for providing better ser-

vice to customers. They are estimating the remaining

lifetime of the components responsible for faults and

remotely monitoring faults in elevators. Fault detec-

tion and diagnosis are required by elevator systems

for healthy operation (Wang et al., 2009).

State of the art include fault diagnosis methods

having feature extraction methodologies based on

deep neural networks (Zhang et al., 2017), (Jia et al.,

2016), (Bulla et al., 2018) and convolutional neural

networks (Xia et al., 2018), (Jing et al., 2017) for ro-

tatory machines similar to elevator systems. Fault de-

tection methods for rotatory machines are also using

support vector machines (Mart

ınez-Rego et al., 2011)

and extreme learning machines (Yang and Zhang,

2016). However, to improve the performance of tra-

ditional fault diagnosis methods, we have developed

an intelligent deep autoencoder model for feature ex-

traction from the data and random forest performs the

fault detection in elevator systems based on extracted

features.

In the last decade, highly meaningful statistical

patterns have been extracted with neural networks

(Calimeri et al., 2018) from large-scale and high-

dimensional datasets. Elevator ride comfort has also

been improved via speed proﬁle design using neural

networks (Seppala et al., 1998). Nonlinear time series

modeling (Lee, 2014) is one of the successful appli-

cation of neural networks. Relevant features can be

self-learned from multiple signals using a deep learn-

ing network (Fern

andez-Varela et al., 2018). Deep

learning algorithms are frequently used in areas such

as preventive maintenance (Arima et al., 2012), de-

cision support system (Sedlak et al., 2013), fraud

detection (Mendes et al., 2012), forecasting (Fer-

hatosmanoglu and Macit, 2016) and text classiﬁca-

tion (Wang and Choi, 2012). Autoencoding is a pro-

cess based on feedforward neural network (H

anninen

and K

arkk

ainen, 2016) for nonlinear dimension re-

duction with natural transformation architecture. Au-

toencoders (Albuquerque et al., 2018) are very power-

ful as nonlinear feature extractors. Autoencoders can

extract features of high interest from sensor data for

Mishra, K. and Huhtala, K.

Condition Monitoring of Elevator Systems using Deep Neural Network.

DOI: 10.5220/0009348803810387

In Proceedings of the 9th International Conference on Operations Research and Enterprise Systems (ICORES 2020), pages 381-387

ISBN: 978-989-758-396-4; ISSN: 2184-4372

381

increasing the generalization ability of machine learn-

ing models (Huet et al., 2016). Autoencoders have

been studied for decades and were ﬁrst introduced

by LeCun (Fogelman-Soulie et al., 1987). Tradition-

ally, autoencoders have two main features i.e. fea-

ture learning and dimensionality reduction. Autoen-

coders and latent variable models (Madani and Vlajic,

2018) are theoretically related, which promotes them

to be considered as one of the most compelling sub-

space analysis techniques. Feature extraction method

based on autoencoders are used in systems like induc-

tion motor (Sun et al., 2016) and wind turbines (Jiang

et al., 2018) for fault detection, different from elevator

systems as in our research.

In our previous research, elevator key perfor-

mance and ride quality features were calculated from

mainly acceleration signals of raw sensor data, which

we call here statistical features. Random forest has

classiﬁed these statistical features to detect faults. Ex-

pert knowledge of the domain is required to calculate

statistical domain speciﬁc features from raw sensor

data but there will be loss of information to some ex-

tent. To avoid these implications, we have developed

a deep autoencoder random forest approach for au-

tomated feature extraction from elevator sensor data,

and based on these deep features, faults are detected.

The rest of this paper is organized as follows. Sec-

tion 2 presents the methodology of the paper includ-

ing deep autoencoder and random forest algorithms.

Then, section 3 includes the details of experiments

performed, results and discussion. Finally, section 4

concludes the paper and presents the future work.

2 METHODOLOGY

In this research, we have used 12 different statisti-

cal features describing the motion and vibration of an

elevator. These features are derived from raw sen-

sor data for fault detection and diagnostics of multi-

ple faults. We have developed an automatic feature

extraction technique in this research as an extension

to the work of our previous research (Mishra et al.,

2019) to compare the results using new extracted deep

features. We have analyzed almost nine months of the

data from three traction elevators in this research as an

extension to the work of our previous research. Each

elevator produces around 200 rides per day. Data col-

lected from an elevator system is fed to the deep au-

toencoder model for new feature extraction and then

random forest performs the fault detection task based

on extracted deep features. We have used 70% of the

data for training and rest 30% for testing. Figure 1

shows the fault detection approach used in this pa-

per, which includes elevator data extracted based on

time periods provided by the maintenance data. Data

collected from elevator systems is fed to the deep au-

toencoder model for feature extraction and then ran-

dom forest performs the fault detection task based on

extracted deep features.

Elevator system

Maintenance

data

Elevator car

Deep

autoencoder

Elevator data

Feature

extraction

Random

forest

Fault

detection

Data

selection

Figure 1: Fault detection approach.

2.1 Deep Autoencoder

We have developed a deep autoencoder model based

on deep learning autoencoder feature extraction

methodology. A basic autoencoder is built on feed-

forward neural network with a fully connected three-

layer network including one hidden layer. Input and

output layer of a typical autoencoder have same num-

ber of neurons and reproduces output as its inputs. We

are using a ﬁve layer deep autoencoder (see Figure 2)

including input, output, encoder, decoder and repre-

sentation layers, which is a different approach than

in (Jiang et al., 2018), (Vincent et al., 2008). Every

movement of the elevator generates statistical features

from the vibration signal. In our approach, we ﬁrst

feed the elevator data from each elevator movement

in up and down directions separately in the deep au-

toencoder model to extract new deep features from the

data. Then we apply random forest as a classiﬁer for

fault detection based on new deep features extracted

from the data.

Statistical features

Deep autoencoder

Encoder

Decoder

Deep

features

Input

layer

Output

layer

Representation

Feature vector

Figure 2: Deep autoencoder feature extraction approach.

ND2A 2020 - Special Session on Nonlinear Data Analysis and Applications

382

The encoder transforms the input x into corrupted

input data x

’

using hidden representation h through

nonlinear mapping

h = f (W

’

+ b) (1)

where f(.) is a nonlinear activation function as

the sigmoid function, W

∈ R

k*m

is the weight matrix

and b ∈ R

the bias vector to be optimized in encod-

ing with k nodes in the hidden layer (Vincent et al.,

2008). Then, with parameters W

∈ R

m*k

and c ∈ R

the decoder uses nonlinear transformation to map hid-

den representation h to a reconstructed vector x

”

at the

output layer.

”

= g(W

h + c) (2)

where g(.) is again nonlinear function (sigmoid

function). In this study, the weight matrix is W

, which is tied weights for better learning performance

(Japkowicz et al., 2000).

2.2 Random Forest

Random forest is type of ensemble classiﬁer selecting

a subset of training samples and variables randomly

to produce multiple decision trees (Breiman, 2001).

High data dimensionality and multicollinearity can be

handled by a RF classiﬁer while imbalanced data af-

fect the results of the RF classiﬁer. It can also be used

for sample proximity analysis, i.e. outlier detection

and removal in train set (Belgiu and Dr

agut¸, 2016).

The ﬁnal classiﬁcation accuracy of RF is calculated

by averaging the probabilities of assigning classes re-

lated to all produced trees (t). Testing data (d) that

is unknown to all the decision trees is used for eval-

uation by voting method. Selection of the class is

based on the maximum number of votes (see Figure

3). Random forest classiﬁer provides variable impor-

tance measurement that helps in reducing the dimen-

sions of hyperspectral data in order to identify the

most relevant features of data, and helps in selecting

the most suitable reason for classiﬁcation of a certain

target class.

Speciﬁcally, let sensor data value v

have training

sample l

in the arrived leaf node of the decision tree

t ∈ T , where l ∈ [1, ..., L

] and the number of train-

ing samples is L

in the current arrived leaf node of

decision tree t. The ﬁnal prediction result is given by

(Huynh et al., 2016):

µ =

∑

t∈T

∑

l∈[1,...,L

]

∑

t∈T

(3)

All classiﬁcation trees providing a ﬁnal decision

by voting method are given by (Liu et al., 2017):

H(a) = argmax

∑

i∈[1,2,...,Z]

I(h

(a) = y

) (4)

Vote 1

Vote t

Tree 1

Tree t

Assign Class (Majority Vote)

d d

Figure 3: Classiﬁcation phase of random forest classiﬁer.

where j= 1,2,...,C and the combination model is

H(a) , the number of training subsets are Z depending

on which decision tree model is h

(a) , i ∈ [1, 2, ..., Z]

while output or labels of the P classes are y

, j=

1,2,...,P and combined strategy is I(.) deﬁned as:

I(x) =

(

1, h

(a) = y

0, otherwise

(5)

where output of the decision tree is h

(a) and i

class label of the P classes is y

, j= 1,2,...,P .

2.3 Evaluation Parameters

Evaluation parameters used in this research are de-

ﬁned with the confusion matrix in Table 1.

Table 1: Confusion matrix.

Predicted (P) (N)

Actual (P) True positive (TP) False negative (FN)

(N) False positive (FP) True negative (TN)

The rate of positive test result is sensitivity,

Sensitivity =

T P

T P + FN

∗ 100% (6)

The ratio of a negative test result is speciﬁcity,

Speci f icity =

T N

T N + FP

∗ 100% (7)

The overall measure is accuracy,

Accuracy =

T P + T N

T P + FP + T N + FN

∗ 100% (8)

Condition Monitoring of Elevator Systems using Deep Neural Network

383

3 RESULTS AND DISCUSSION

In this research, we have included all three elevators

E001, E002, E003 and their combined version (All)

similar to our previous research. First, we selected

the faulty data based on time periods provided by the

maintenance data. In the next step, an equal amount

of healthy data was also selected and labelled as class

0 for healthy, with class 1 for faulty data. Finally, the

deep autoencoder model is used for feature extraction

from the data.

3.1 Up Movement

We have analyzed up and down movements separately

because the traction based elevator usually produces

slightly different levels of vibration in each direction.

Healthy and faulty data with class labels are fed to the

deep autoencoder model and the generated deep fea-

tures are shown in Figure 4. In Figure 4, we can see

that both features with class labels are perfectly sep-

arated, which results in better fault detection. These

are called deep features or latent features in deep au-

toencoder terminology, which shows hidden represen-

tations of the data.

-1.0

-0.5

0.0

0.5

1.0

-1.0 -0.5 0.0 0.5 1.0

Feature axis 1

Feature axis 2

class

Deep features (All-up)

Figure 4: Extracted deep autoencoder features for combined

version (All) (Visualization of the features w.r.t class vari-

able).

The extracted deep features are fed to the random

forest algorithm for classiﬁcation and the results pro-

vide 100% accuracy in fault detection, as shown in

Table 2. We have also calculated accuracy in terms of

avoiding false positives from both features and found

that the new deep features generated in this research

outperform the statistical features. We have used the

rest of the healthy data to analyze the number of false

positives. This healthy data is labelled as class 0 and

fed to the deep autoencoder to extract new deep fea-

tures from the data, as presented in Figure 5. These

new deep features are then classiﬁed with the pre-

trained deep autoencoder random forest model to test

the efﬁcacy of the model in terms of false positives.

Figure 5: Extracted deep features (only healthy data) for

combined version (All).

Table 2 presents the results for upward movement

of the elevator in terms of accuracy, sensitivity and

speciﬁcity. We have also included the accuracy of

avoiding false positives as evaluation parameters for

this research. The results show that the new deep fea-

tures provide better accuracy in terms of fault detec-

tion and avoiding false positives from the data, which

is helpful in detecting false alarms for elevator predic-

tive maintenance strategies. It is extremely helpful in

reducing the unnecessary visits of maintenance per-

sonnel to installation sites.

Table 2: Fault detection analysis (False positives ﬁeld re-

lated to analyzing rest of the healthy data after the training

and testing phase).

Deep features Statistical features

Accuracy 1 0.78

Sensitivity 1 0.78

Speciﬁcity 1 0.78

False positives 1 0.94

3.2 Down Movement

For downward motion, just as in the case of up move-

ND2A 2020 - Special Session on Nonlinear Data Analysis and Applications

384

ment, we feed both healthy and faulty data with class

labels to the deep autoencoder model for the extrac-

tion of new deep features, as shown in Figure 6.

-1.0

-0.5

0.0

0.5

1.0

-1.0 -0.5 0.0 0.5

Feature axis 1

Feature axis 2

class

Deep features (All-down)

Figure 6: Extracted deep features for combined version

(All).

Finally, the new extracted deep features are clas-

siﬁed with random forest model, and the results are

shown in Table 3. After this, the rest of the healthy

data with class label 0 is used to analyze the num-

ber of false positives. The extracted deep features are

presented in Figure 7. Table 3 presents the results for

fault detection with deep autoencoder random forest

model in the downward direction. The results are sim-

ilar to the upward direction, but we can see signiﬁcant

change in terms of accuracy when analyzing the fault

detection and number of false positives with new deep

features.

Table 3: Fault detection analysis.

Deep features Statistical features

Accuracy 1 0.74

Sensitivity 1 0.78

Speciﬁcity 1 0.70

False positives 1 0.89

4 CONCLUSIONS AND FUTURE

WORK

In this research, we propose a novel fault detection

technique for health monitoring of elevator systems.

We have developed a generic model for automated

feature extraction and fault detection in the health

state monitoring of elevator systems. Our approach

Figure 7: Extracted deep features (only healthy data) for

combined version (All).

with new extracted deep features provided 100% ac-

curacy in detecting faults and in avoiding false pos-

itives. The results show that we have succeeded in

developing a generic model, which can also be appli-

cable to other machine systems for automated feature

extraction and fault detection. The results are useful

in terms of detecting false alarms in elevator predic-

tive maintenance. If the analysis results are utilized

to allocate maintenance resources, the approach will

also reduce unnecessary visits of maintenance person-

nel to installation sites. Our developed model can also

be used for solving diagnostics problems with auto-

matically generated highly informative deep features

in different predictive maintenance solutions. Our

model outperforms because of new deep features ex-

tracted from the dataset as compared to statistical fea-

tures calculated from the raw sensor dataset of the

same elevators. No prior domain knowledge is re-

quired for the automated feature extraction approach.

Robustness against overﬁtting and dimensionality re-

duction are the two main characteristics of our model.

Our generic model is feasible as shown by the exper-

imental results, which will increase the safety of pas-

sengers. Robustness of our model is tested in the case

of a large dataset, which proves the efﬁcacy of our

model.

In future work, we will extend our approach on

more elevators and real-world big data cases to val-

idate its potential for other applications and improve

its efﬁcacy.

Condition Monitoring of Elevator Systems using Deep Neural Network

385

REFERENCES

Albuquerque, A., Amador, T., Ferreira, R., Veloso, A., and

Ziviani, N. (2018). Learning to rank with deep autoen-

coder features. In 2018 International Joint Conference

on Neural Networks (IJCNN), pages 1–8. IEEE.

Arima, S., Sumita, U., and Yoshii, J. (2012). Development

of sequential association rules for preventing minor-

stoppages in semi-conductor manufacturing. In Pro-

ceedings of the International Conference on Oper-

ations Research and Enterprise Systems (ICORES),

pages 349–354.

Belgiu, M. and Dr

agut¸, L. (2016). Random forest in remote

sensing: A review of applications and future direc-

tions. ISPRS Journal of Photogrammetry and Remote

Sensing, 114:24–31.

Breiman, L. (2001). Random forests. Machine learning,

45(1):5–32.

Bulla, J., Orjuela-Ca

on, A. D., and Fl

orez, O. D. (2018).

Feature extraction analysis using ﬁlter banks for faults

classiﬁcation in induction motors. In 2018 Interna-

tional Joint Conference on Neural Networks (IJCNN),

pages 1–6. IEEE.

Calimeri, F., Marzullo, A., Stamile, C., and Terracina, G.

(2018). Graph based neural networks for automatic

classiﬁcation of multiple sclerosis clinical courses. In

European Symposium on Artiﬁcial Neural Networks,

Computational Intelligence and Machine Learning

(ESANN).

Desa (2014). World urbanization prospects, the 2011 revi-

sion. Population Division, Department of Economic

and Social Affairs, United Nations Secretariat.

Ebeling, T. (2011). Condition monitoring for elevators–an

overview. Lift Report, 6:25–26.

Ebeling, T. and Haul, M. (2016). Results of a ﬁeld trial aim-

ing at demonstrating the permanent detection of ele-

vator wear using intelligent sensors. In Proc. ELEV-

CON, pages 101–109.

Ferhatosmanoglu, N. and Macit, B. (2016). Incorporating

explanatory effects of neighbour airports in forecast-

ing models for airline passenger volumes. In Proceed-

ings of the International Conference on Operations

Research and Enterprise Systems (ICORES), pages

178–185.

Fern

andez-Varela, I., Athanasakis, D., Parsons, S.,

Hern

andez-Pereira, E., and Moret-Bonillo, V. (2018).

Sleep staging with deep learning: a convolutional

model. In Proceedings of the European Symposium

on Artiﬁcial Neural Networks, Computational Intelli-

gence and Machine Learning (ESANN).

Fogelman-Soulie, F., Robert, Y., and Tchuente, M. (1987).

Automata networks in computer science: theory and

applications. Manchester University Press and Prince-

ton University Press.

anninen, J. and K

arkk

ainen, T. (2016). Comparison

of four-and six-layered conﬁgurations for deep net-

work pretraining. In European Symposium on Artiﬁ-

cial Neural Networks, Computational Intelligence and

Machine Learning (ESANN).

Huet, R., Courty, N., and Lef

evre, S. (2016). A new penal-

isation term for image retrieval in clique neural net-

works. In European Symposium on Artiﬁcial Neural

Networks, Computational Intelligence and Machine

Learning (ESANN).

Huynh, T., Gao, Y., Kang, J., Wang, L., Zhang, P., Lian,

J., and Shen, D. (2016). Estimating ct image from

mri data using structured random forest and auto-

context model. IEEE transactions on medical imag-

ing, 35(1):174.

Japkowicz, N., Hanson, S. J., and Gluck, M. A. (2000).

Nonlinear autoassociation is not equivalent to pca.

Neural computation, 12(3):531–545.

Jia, F., Lei, Y., Lin, J., Zhou, X., and Lu, N. (2016). Deep

neural networks: A promising tool for fault character-

istic mining and intelligent diagnosis of rotating ma-

chinery with massive data. Mechanical Systems and

Signal Processing, 72:303–315.

Jiang, G., Xie, P., He, H., and Yan, J. (2018). Wind turbine

fault detection using a denoising autoencoder with

temporal information. IEEE/ASME Transactions on

Mechatronics, 23(1):89–100.

Jing, L., Wang, T., Zhao, M., and Wang, P. (2017). An adap-

tive multi-sensor data fusion method based on deep

convolutional neural networks for fault diagnosis of

planetary gearbox. Sensors, 17(2):414.

Lee, C.-C. (2014). Gender classiﬁcation using m-estimator

based radial basis function neural network. In Signal

Processing and Multimedia Applications (SIGMAP),

2014 International Conference on, pages 302–306.

IEEE.

Liu, Z., Tang, B., He, X., Qiu, Q., and Liu, F. (2017).

Class-speciﬁc random forest with cross-correlation

constraints for spectral–spatial hyperspectral image

classiﬁcation. IEEE Geoscience and Remote Sensing

Letters, 14(2):257–261.

Madani, P. and Vlajic, N. (2018). Robustness of deep

autoencoder in intrusion detection under adversarial

contamination. In Proceedings of the 5th Annual Sym-

posium and Bootcamp on Hot Topics in the Science of

Security, page 1. ACM.

Mart

ınez-Rego, D., Fontenla-Romero, O., and Alonso-

Betanzos, A. (2011). Power wind mill fault detection

via one-class ν-svm vibration signal analysis. In Neu-

ral Networks (IJCNN), The 2011 International Joint

Conference on, pages 511–518. IEEE.

Mendes, L. P., Dias, J., and Godinho, P. (2012). Bi-level

clustering in telecommunication fraud. In Proceed-

ings of the International Conference on Operations

Research and Enterprise Systems (ICORES), pages

126–131.

Mishra, K. M., Krogerus, T., and Huhtala, K. (2019). Fault

detection of elevator systems using deep autoencoder

feature extraction. In Research Challenges in Infor-

mation Science (RCIS), 2019 13th International Con-

ference on, pages 43–48. IEEE.

Sedlak, O., Cileg, M., and Kis, T. (2013). Decision support

system with mark-giving method. In Proceedings of

the International Conference on Operations Research

and Enterprise Systems (ICORES), pages 338–342.

ND2A 2020 - Special Session on Nonlinear Data Analysis and Applications

386

Seppala, J., Koivisto, H., and Koivo, H. (1998). Modeling

elevator dynamics using neural networks. In Neural

Networks Proceedings, 1998. IEEE World Congress

on Computational Intelligence. The 1998 IEEE Inter-

national Joint Conference on, volume 3, pages 2419–

2424. IEEE.

Sun, W., Shao, S., Zhao, R., Yan, R., Zhang, X., and Chen,

X. (2016). A sparse auto-encoder-based deep neural

network approach for induction motor faults classiﬁ-

cation. Measurement, 89:171–178.

Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.-

A. (2008). Extracting and composing robust features

with denoising autoencoders. In Proceedings of the

25th international conference on Machine learning,

pages 1096–1103. ACM.

Wang, P., He, W., and Yan, W. (2009). Fault diagnosis of

elevator braking system based on wavelet packet algo-

rithm and fuzzy neural network. In Electronic Mea-

surement & Instruments, 2009. ICEMI’09. 9th Inter-

national Conference on, pages 4–1028. IEEE.

Wang, Y. and Choi, I.-C. (2012). A text classiﬁcation

method based on latent topics. In Proceedings of the

International Conference on Operations Research and

Enterprise Systems (ICORES), pages 212–214.

Xia, M., Li, T., Xu, L., Liu, L., and de Silva, C. W.

(2018). Fault diagnosis for rotating machinery us-

ing multiple sensors and convolutional neural net-

works. IEEE/ASME Transactions on Mechatronics,

23(1):101–110.

Yang, Z.-X. and Zhang, P.-B. (2016). Elm meets rae-elm:

A hybrid intelligent model for multiple fault diagnosis

and remaining useful life predication of rotating ma-

chinery. In Neural Networks (IJCNN), 2016 Interna-

tional Joint Conference on, pages 2321–2328. IEEE.

Zhang, R., Peng, Z., Wu, L., Yao, B., and Guan, Y. (2017).

Fault diagnosis from raw sensor data using deep neu-

ral networks considering temporal coherence. Sen-

sors, 17(3):549.

Condition Monitoring of Elevator Systems using Deep Neural Network

387