Abstract
Vibration signal diagnosis and analysis plays an important role in the industrial machinery since it enhances the machinery performance under supervision. The information regarding the future condition is given by vibration diagnosis techniques which is growing interest for the scientific and industrial communities. Information for failure diagnostic and prediction are provided by the motor vibration through signal processing. The development of mechanical systems fault prognosis and in the last decades, research is done at a very rapid rate. The examination of vibration signal monitoring is done in this paper with the aid of Cyber-Physical Systems (CPS) and Cloud Technology (CT). The machines maintenance strategies are implemented by using the data collected from machines which are based on the fault prognosis. The cloud computing platform is presented in this paper which is having three layers and the unlabelled data is received to generate an interpreted online decision. Feature extraction of the vibration signal is obtained in terms of range, mean value, root mean square value, and standard deviation and crest values. The performance of the model is evaluated by utilizing the classical statistical metrics such as RMSE Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) of the vibration signal. It is obtained that the proposed technique is 25% and 90% better than the Adaptive Neurofuzzy Inference System and the Single Modeling System respectively in terms of RMSE. The performance in terms of MAPE, then the proposed technique outperforms the existing Adaptive Neurofuzzy Inference System and the Single Modeling System by 8 % and 60% respectively. The presented technique is better than the existing Adaptive Neurofuzzy Inference System and the Single Modeling techniques by average of 15% and 30 % respectively.
1 Introduction
The productivity loss, time loss, safety and environment problems are resulted by the industrial equipment failure. The organization's manufacturing operations are required to be maintained and it is important for availability and reliability of product and production facilities [1, 2]. The maintenance gained less attention as compared to the manufacturing problems and it leads to low maintenance efficiency in industry. The equipment maintenance is very important and critical aspect as the maintenance activities carried by the traditional reactive maintenance only after failure detection. About the periodicity of failure, the periodic maintenance activities are implied by the widespread preventive maintenance. Predictive maintenance is required for cost saving and to prevent the failure of equipment. For various industries, motors are essential and are used for various applications such as electric generators, window lifting motor, etc. Sample of motor is shown in Figure 1. There is an unexpected stop if there are failures in the motor and loss of production time and money is caused by it. The online condition monitoring is developed by the researchers to avoid the motor failure. The fault diagnosis techniques are used for the detection of faults and to provide the diagnostic information of motors. Vibrations signals depend on the motor states and fault is connected with vibration signals [3,4,5,6]. For fault diagnosis, characteristic frequencies and the states of the motor correlation is required.
Sample of motor in industries
The early fault diagnostic methods detect the early fault state and sometimes the motor is damaged in only 5 minutes by short-circuiting. For the permanently damage of motor, faults like air-gap, and broken rotor take much time [7, 8]. The analysis of diagnostic signals is done by the condition monitoring of electric motors. Measurements of acoustic signal and thermal signal can be done without touching the motor.
The fault diagnosis is performed by the model-based methods which are relied on analytical redundancy and analytical models expect the process behavior. The mathematical model is exploited by analytical models of the monitored machine [9]. The residual generation methods based on this explicit model are utilized to obtain signals which are indicative of fault presence in the machine. The vibration signals i.e., the residuals evaluation; the fault detection and isolation are achieved as shown in Figure 2.
Basic block diagram of fault diagnosis
The linear system models, process models and behavioral models have been examined and included in variety of models [10,11,12,13]. The faults diagnosing of mechanical system components such as bearings rotors are applied for model-based methods. A model is built accurately by model-based approaches effectively.
Research gaps:
Information for failure diagnostic and prediction are provided by the motor vibration through signal processing. The fault alarm systems examination and monitoring are not effective in terms of mean value, root mean square value, and standard deviation.
Contribution:
The examination and monitoring of alarm systems, with the aid of Cloud Technology (CT).
Implementation based on the machines fault prognosis by utilizing the machines’ data collection.
The cloud computing platform having three layers and the unlabelled data are received to interpreted online decision generation.
Feature extraction of the vibration signal is obtained in terms of range, mean value, root mean square value, and standard deviation and crest values.
The rest of the paper is organized as follows. Section 2 provides an overview of the exhaustive literature survey followed by a methodology adopted in section 3. A detailed discussion of obtained results is in section 4. Finally, concluding remarks are provided in Section 5.
2 Literature review
Many researchers have worked on the motor vibration diagnosis based on cloud computing in the previous years. The electric motors are monitored in real-time; the author details the testing of an Industrial Internet of Things (IIoT) system [14]. For the capability comparison, the frequency domain analysis is carried out in the gateway. The edge and fog computing is advantageous which is carried by the complement to cloud computing. In an industrial dairy plant, testing of the prototype is done in the laboratory. The author presents the diagnosing failures in rotary machines method by utilizing the Machine Learning techniques [15]. For fault diagnosis of the rotational unbalance, author proposed a support vector machine algorithm in the rotor. For vibration analysis, the most popular classification methods is support vector machines (SVMs). The vibration-based fault diagnosis techniques are presented by the author in this paper which is based on the motor [16]. The signal processing methods and the vibration signals are utilized by the proposed method. The three states of healthy CM, CM with broken tooth on sprocket, CM with broken rotor coil recognition efficiency are analyzed by the authors. The prediction through signal processing and the information for failure diagnostic are provided by the motor vibration [17]. The IoT-based monitoring system is presented by the author in this paper for recording the vibration of the induction motor. The vibration data from the motor is collected by the 27mm piezoelectric. The 3 scenarios experiments are conducted for the vibration data collection from different positions. The recorded vibration is sent by the each node vibration to the cloud with an average delay of 1 sec.
In the last few decades, fault prognosis have been researched and developed in mechanical systems at a very rapid rate [18]. The approaches-based fault diagnosis and prognosis are investigated in this paper by the authors and predictive maintenance knowledge is obtained. For fault prognosis, the applications of the data mining methods are illustrated in the case study. The author in this paper presents a remote observing system dependent on Internet of Things (IoT) for protected and economic data communication [19]. The parameters like Temperature, vibrations, speed, motor current and voltage of induction machine are screened by the module of transducers and sensors. The Automatic ON/OFF for faulty conditions is additionally presented by the system which shows the information on LCD show and data is passed on. The model gives information to WIFI IoT applications to make the system quick and easy to understand. Due to the potential advantages, the considerable subjects of system are the Machine fault prognostic techniques [20]. There is rapid growth from the past few years in the machine fault diagnosis and prognosis. The wide range of statistical approaches is covered by the publications to model-based approaches. Also, the challenges and the opportunities are also discussed in machine prognosis field. Author details the considerable condition-based maintenance system i.e., faults prognostic techniques of machine [21]. The decreasing maintenance costs and increasing machine availability, potential advantages are gained by the maintenance strategies. There is rapid development of the machine fault diagnosis and prognosis research. The recent published techniques in diagnosis and prognosis of rotating machinery are summarized and classified by synthesizing and providing the information of these researches. In the field of machine prognosis, various challenges and the opportunities are discussed by the authors for conducting advance research. The machine vision, feature extraction, and support vector machine (SVM) are utilized and detailed by the authors in this study for the vibration monitoring system (VMS) to composition [22]. A vision-based data-driven methodology is presented by the author for industrial robot health assessment. The experimental evidence of the methodology is provided on the system which comprises the five binary squared fiducial markers and two monocular cameras. The deviation of the end-effect or is accurately tracked by the fiducial marker system. The trajectory deflection is monitored by utilizing the weights attached to the end-effect or [23]. The supervised learning regression models are trained by tracing the trajectory information. The presented protocol is robust, rigorous and reliable and identifies the mechanical element that produces the non-kinematic errors. The presented VMS technique's experiment setup is straightforward and the surveillances are cooperated in industrial environments.
3 Methodology
The motor monitoring status is detected by the several types of data collection methods. There are different types of signals from which the vibration signal is the common fault detection technique. The vibration signal is analyzed and illustrated here in this section.
3.1 Analysis of vibration signal features
The feature extraction is the vibration signal's first step. The rotating system failure status is diagnosed by these forms [23,24,25]. The diagnosis technique's accuracy is improved by extracting the hidden data. The times domains feature calculation from the vibration signal areas given in equations.
μx and μy = average of x and y.
σ2x and σ2y = variance of x and y.
σx,y = Covariance of x and y.
3.2 The clustering analysis
The vibration signal information is illustrated and the nodes are found between the classes by feature utilization after the vibration signals analysis. Basic clustering analysis presentation is shown in Figure 3. The homogenous objects are characterized by the clustering analysis deal with the complex data-sets.
Clustering analysis
The best clusters are obtained by the K-mean clustering as it is commonly utilized algorithm [26,27,28]. The sums of squared distances are minimized by the clustering process. Some steps are utilized by this technique.
The randomness of K centroid is the initial based.
To the nearest centroid, each point of the dataset is allocated.
Each data point is recomputed to the cluster of centroid cluster for intra-cluster reduction.
3.3 Logical Analysis of Data (LAD)
The pattern recognition based phenomena is allowed by data-driven LAD technique, training and testing are the two stages which are applied. The data is utilized as training data for patterns extraction [29]. The training data is well balanced to build the diagnosis model for healthy and failure classes.
3.4 Data binarization
By using a binarization technique, the transformation of raw data into binary data in which each numerical feature is translated into the set of binary attributes. The data set in ascending order are utilized by the binarization technique [30]. Between every two values, the cut point is inserted and then the average is calculated, value as shown in equation.
3.5 Pattern generation
The formulation of a mixed-integer and linear programming based on pattern generation. The discriminating powers between the different classes are controlled by the approach [31]. By the pattern generation algorithm, the generated number of patterns has no limit to create more patterns finding possibilities.
3.6 Unlabelled remote diagnosis system architecture
In maintenance innovation, Cloud technologies (CT) are becoming the trend for the machines maintenance and industrial process. CT is cost effective and has merits of unlimited storage space and security. The machines are required to be continuously monitored for the achievement of near-zero breaks down [32,33,34]. The architecture of cyber-physical system maintenance is detailed in Figure 3.
Sensor Layer: The multisource unlabelled data is provided by the sensors consisted in the sensor layer. The wireless communication capability of the sensor enables the data transfer for the decision making layer [35]. The machining process is reported by the intelligent sensors and shares with the process controller.
Decision-making layer: The unlabelled data is then transferred by the analyzer software and then sent back to the maintenance team.
The internet-based services which are cloud services offer all the things that are provided by the computer system. There is an overwhelming data flow due to the data collation increment and CT has the merits of virtualized resources and data service integrated with scalable storage of data. The best performance is provided by the virtualized machine with low cost. Figure 4 shows the unlabelled cyber-physical system's proposed architecture.
Cyber-physical system
The sensor in the model takes a monitored machine signal. The online remote diagnosis center converts the collected unlabelled data into the useful data and then the status of the machine is determined. An alarm and corrective action are sent by the system to prepare the required element. The system accuracy is improved by the cloud.
4 Results and discussion
4.1 Analysis of the system
To test and analyze the system, there is a development of cyber-physical maintenance system of rolling element failure simulation model to test the system. The samples of the datasets are publically available and can access online. A snapshot of the vibration signal is collected by the card until a failure occurred. Table 1 illustrates feature extraction using MATLAB Software.
Feature extraction of samples
| Samples | Range | Mean | Standard Deviation | Root Mean Square | Crest Factor |
|---|---|---|---|---|---|
| 1 | 0.834 | −0.002 | 0.071 | 0.074 | 6.120 |
| 2 | 0.729 | −0.019 | 0.073 | 0.079 | 7.621 |
| 3 | 0.183 | −0.021 | 0.078 | 0.032 | 6.865 |
| 4 | 0.729 | −0.003 | 0.038 | 0.054 | 6.678 |
| 5 | 0.319 | −0.042 | 0.021 | 0.210 | 7.562 |
| 6 | 1.872 | −0.038 | 0.359 | 0.261 | 8.572 |
| 7 | 3.210 | −0.041 | 0.048 | 0.311 | 5.563 |
| 8 | 1.628 | −0.218 | 0.029 | 0.201 | 6.672 |
| 9 | 0.873 | −0.331 | 0.071 | 0.022 | 7.352 |
| 10 | 2.577 | −0.214 | 0.063 | 0.182 | 6.563 |
The vibration signal feature extraction is tabulated in above table in terms of range, mean, standard deviation, root mean square and the crest values. For better visualization and analysis these obtained values are graphically represented in Figures 5–9 for different samples.
Range values (M) of the different samples
Mean values (M) of the different samples
Standard Deviation (SD) of the different samples
Root Mean Square (RMS) of the different samples
Crest Factor (CF) of the different samples
A healthy or unhealthy condition is lead by the machine operation status after detecting by the characteristics patterns by using the new data after clustering as exhibited in Table 2. The negative patterns in the condition of health status are discovered by positive patterns as generated by LAD.
Results of K-mean clustering
| Sample | Class | Quantity |
|---|---|---|
| 1 | Healthy | 750 |
| 2 | Unhealthy | 205 |
The quality of the healthy and unhealthy class is presented graphically in Figure 10.
Quantity of healthy and unhealthy class
The data set file sent the vibration signal to the cloud file in the Drop-box application via internet. Two centers are included in it, the physical center and the cyber center. The sensors, actuators and the maintenance team of the monitoring machine are included in it. The data from the physical center is received by the cyber center which is then converted into the useful information for proper monitoring and controlling of physical world. The local maintenance team is allowed by the system to see a live view of the running machine interaction. Additionally, the cyber-physical system code is built by the MATLAB. The signals are sent and received by the gateway and cyber-physical center generates the corrective action via the internet. High scalability and lower costs are the benefits of using this gateway. Analysis of the received data and the generation of suitable decision, every certain time is run by the built governing code. The positive pattern is identified and an alarm report is automatically sent by the system including the decision and the corrective action. The gateway carrier sent the generated decision to the machine controller. The Drop Box file stores the data for the improvement of the offline governor patterns generation accuracy. The stored historical data is used for the automatic software update.
4.2 Statistical analysis of the signal vibration in system
The performances of the models are assessed by utilizing the classical statistical metrics such as RMSE Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). These are the basic and mostly used performance metrics which are accepted by the research community. These are used for the models development is analyzed by the RMSE. This parameter is the amplitude sensitive. The forecast evaluation is done by the MAE and it is insensitive to the outliers. The mean deviation of each sample determination is done by the MAPE and amplitude normalizes the samples. It also helps to unify the scale and can be used to errors of signals comparison with different levels of amplitudes. Four scenarios have been considered for analysis, that is, the healthy condition (HC), a bearing failure (BF) condition, a half-broken rotor bar (HBRB) condition, and full-broken rotor bar (FBRB). These different parameters obtained for four different scenarios by the proposed method as shown in Table 3. It is also represented graphically in Figure 11 for better visualization and analysis.
Different parameters obtained for four different scenarios by the proposed method
| Different Scenarios | Proposed Method | ||
|---|---|---|---|
| RMSE | MAPE (%) | MAE | |
| Healthy condition | 0.010 | 1.55 | 0.112 |
| Bearing failure | 0.016 | 2.18 | 0.120 |
| Half-broken rotor | 0.018 | 2.70 | 0.129 |
| Full-broken rotor bar | 0.021 | 3.35 | 0.134 |
Parameters obtained for four different scenarios
From the Figure 10, it is clear that the all these parameters are high for full broken rotor case. The RMSE, MAPE and MAE are less for the healthy rotor. These parameters go worse with the condition of rotor. So these parameters are beneficial to check the condition of rotor. The quality parameters like SNR and SSIM are also checked to check the performance of the technique as shown in Table 4.
PSNR and SSIM obtained for four different scenarios by the proposed method
| Different Scenarios | Proposed Method | |
|---|---|---|
| PSNR (dB) | SSIM | |
| Healthy condition | 56 | 0.92 |
| Bearing failure | 49 | 0.88 |
| Half-broken rotor | 40 | 0.79 |
| Full-broken rotor bar | 34 | 0.71 |
Higher the value of the PSNR, higher will be the quality, the healthy condition rotor have the high PSNR value as compared to the bearing failure, half-broken rotor and the full-broken rotor bar. The value of SSIM is in between the 0 and 1. If the value approaches to 1 shows the high quality.
4.3 Comparison with other techniques
The results obtained by the presented technique for the four different scenarios are also compared with the existing techniques for the validation purpose. Comparison of the presented technique is done on the basis of RMSE, MAPE and MAE as tabulated in Table 5.
Comparison of the presented technique over existing techniques
| Different Scenarios | Adaptive Neurofuzzy Inference System [38] | Single Modeling System [38] | Proposed Method | ||||||
|---|---|---|---|---|---|---|---|---|---|
| RMSE | MAPE (%) | MAE | RMSE | MAPE (%) | MAE | RMSE | MAPE (%) | MAE | |
| Healthy condition | 0.013 | 1.69 | 0.135 | 0.203 | 3.45 | 0.129 | 0.010 | 1.55 | 0.112 |
| Bearing failure | 0.020 | 2.27 | 0.125 | 0.275 | 6.77 | 0.265 | 0.016 | 2.18 | 0.120 |
| Half-broken rotor | 0.022 | 2.82 | 0.133 | 0.478 | 6.92 | 0.184 | 0.018 | 2.70 | 0.129 |
| Full-broken rotor bar | 0.025 | 3.44 | 0.139 | 0.394 | 8.93 | 0.192 | 0.021 | 3.35 | 0.134 |
From the table, it is clear that the minimum error is obtained by the proposed technique as compared to other existing techniques. The percentage improvement of the proposed technique is also calculated and shown in Table 6.
Percentage improvement of the proposed technique over existing techniques
| Different Scenarios | Percentage Improvement of the Proposed Technique | |||||
|---|---|---|---|---|---|---|
| In terms of RMSE over | In terms of MAPE over | In terms of MAE over | ||||
| Adaptive Neuro-fuzzy Inference System | Single Modeling System | Adaptive Neuro-fuzzy Inference System | Single Modeling System | Adaptive Neuro fuzzy Inference System | Single Modeling System | |
| Healthy condition | 30.00 % | 95.07% | 9.03% | 55.07% | 20.54% | 13.18% |
| Bearing failure | 25.00% | 94.18% | 4.13% | 67.80% | 4.17% | 54.72% |
| Half-broken rotor | 22.22% | 96.23% | 4.44% | 60.98% | 3.10% | 29.89% |
| Full-broken rotor bar | 19.05% | 94.67% | 2.69% | 62.49% | 3.73% | 30.21% |
The graphical representation is also shown in Figure 12 for better analysis and visualization. It is obtained that the proposed technique is around 25% and 90% better than the Adaptive Neurofuzzy Inference System and the Single Modeling System respectively in terms of RMSE.
Percentage improvement of the proposed technique over existing techniques
If one see the performance in terms of MAPE, then the proposed technique outperforms the existing Adaptive Neurofuzzy Inference System and the Single Modeling System by 8% and 60%, respectively. The presented technique is better than the existing Adaptive Neurofuzzy Inference System and the Single Modeling techniques by average of 15% and 30%, respectively.
Applications:
Development of fault diagnosis and prognosis strategies that achieved extensive utility in a wide range of application domains in recent years. Typically, there are two major classes: Model based and data-driven.
A model-based technique depends on dynamic system model accuracy. It uses actual technique for generation of the difference between the two outputs, indicative of a fault condition.
The anticipated fault condition is addressed by the data-driven techniques where a fault model collects the constructs like neural networks which must be trained first with prototype fault patterns.
5 Conclusion
The diagnosis of machine performance is done by building the Maintenance-CPS platform and unlabelled data is explored. The expert's expensive onsite visit, reduction of training cost and the non-zero breakdown is achieved by the continuous monitoring; these are the merits of the proposed system. The proposed layers of cyber-physical system are connected to the Cloud technologies. The different layers of the system are sensor, analysis, and decision making. Based on an interpretable method dealing with data, decision making and analysis is done. The rolling element bearing are used to test the presented system. Finally, the cloud technologies and the future fault prognosis systems maintenance field are discussed. The performances of the models are evaluated by utilizing the classical statistical metrics such as RMSE Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). It is obtained that the proposed technique is around 25% and 90% better than the Adaptive Neurofuzzy Inference System and the Single Modeling System respectively in terms of RMSE. Higher the PSNR, higher will be the quality, the healthy condition rotor have the high PSNR value as compared to the bearing failure, half-broken rotor and the full-broken rotor bar. The future work will focus on the development of an automatic anomaly detection in the gateway.
Funding information:
The authors state no funding involved.
Author contributions:
All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Conflict of interest:
The authors state no conflict of interest.
References
[1] Wu D, Liu S, Zhang L, Terpenny J, Gao RX, Kurfess T, et al. A fog computing-based framework for process monitoring and prognosis in cyber-manufacturing. J Manuf Syst. 2017;43:25–34.10.1016/j.jmsy.2017.02.011Search in Google Scholar
[2] Qian G, Lu S, Pan D, Tang H, Liu Y, Wang Q. Edge computing: A promising framework for real-time fault diagnosis and dynamic control of rotating machines using multi-sensor data. IEEE Sens J. 2019;19(11):4211–20.10.1109/JSEN.2019.2899396Search in Google Scholar
[3] Poongodi M, Sharma A, Vijayakumar V, Bhardwaj V, Sharma AP, Iqbal R, et al. Prediction of the price of Ethereum blockchain cryptocurrency in an industrial finance system. Comput Electr Eng. 2020;81:106527.10.1016/j.compeleceng.2019.106527Search in Google Scholar
[4] Lu S, Zhou P, Wang X, Liu Y, Liu F, Zhao J. Condition monitoring and fault diagnosis of motor bearings using undersampled vibration signals from a wireless sensor network. J Sound Vibrat. 2018;414:81–96.10.1016/j.jsv.2017.11.007Search in Google Scholar
[5] Sharma A, Kumar R. Service-level agreement—energy cooperative quickest ambulance routing for critical healthcare services. Arab J Sci Eng. 2019;44(4):3831–48.10.1007/s13369-018-3687-zSearch in Google Scholar
[6] Al Sunny SN, Liu X, Shahriar MR. Remote monitoring and online testing of machine tools for fault diagnosis and maintenance using MTComm in a cyber-physical manufacturing cloud. 2018 IEEE 11th International Conference on Cloud Computing (CLOUD); 2018 Jul 2–7; San Francisco USA. 2018 p. 532–539. IEEE. https://doi.org/10.1109/CLOUD.2018.00074.10.1109/CLOUD.2018.00074Search in Google Scholar
[7] Deng W, Zhang S, Zhao H, Yang X. A novel fault diagnosis method based on integrating empirical wavelet transform and fuzzy entropy for motor bearing. IEEE Access. 2018;6:35042–56.10.1109/ACCESS.2018.2834540Search in Google Scholar
[8] Medoued A, Mordjaoui M, Soufi Y, Sayad D. Induction machine bearing fault diagnosis based on the axial vibration analytic signal. Int J Hydrogen Energy. 2016;41(29):12688–95.10.1016/j.ijhydene.2016.02.116Search in Google Scholar
[9] Huo Z, Mukherjee M, Shu L, Chen Y, Zhou Z. Cloud-based data-intensive framework towards fault diagnosis in large-scale petrochemical plants. 2016 International Wireless Communications and Mobile Computing Conference (IWCMC). 2016 Sept 5–9. Paphos, Cyprus; 2016 p. 1080–1085. IEEE.10.1109/IWCMC.2016.7577209Search in Google Scholar
[10] Li B, Chow MY, Tipsuwan Y, Hung JC. Neural-network-based motor rolling bearing fault diagnosis. IEEE Trans Ind Electron. 2000;47(5):1060–9.10.1109/41.873214Search in Google Scholar
[11] Shao S, Sun W, Wang P, Gao RX, Yan R. (2016, August). Learning features from vibration signals for induction motor fault diagnosis. 2016 International Symposium on Flexible Automation (ISFA); 2016 Aug 1–3; Cleveland, USA. IEE; 2016 p. 71–76.Search in Google Scholar
[12] Iorgulescu M, Beloiu R. (2012, October). Study of DC motor diagnosis based on the vibration spectrum and current analysis. 2012 International Conference on Applied and Theoretical Electricity (ICATE); 2012 Oct 25–27; Craiova, Romania. IEE; 2012 p. 1–4.Search in Google Scholar
[13] Chen HX, Chua PS, Lim GH. Adaptive wavelet transform for vibration signal modeling and application in fault diagnosis of water hydraulic motor. Mech Syst Signal Process. 2006;20(8):2022–45.10.1016/j.ymssp.2005.04.007Search in Google Scholar
[14] Magadán L, Suárez FJ, Granda JC, García DF. Low-cost real-time monitoring of electric motors for the Industry 4.0. Procedia Manuf. 2020;42:393–8.10.1016/j.promfg.2020.02.057Search in Google Scholar
[15] Pinheiro AA, Brandao IM, Da Costa C. Vibration Analysis in Turbomachines Using Machine Learning Techniques. European Journal of Engineering and Technology Research. 2019;4(2):12–6.10.24018/ejers.2019.4.2.1128Search in Google Scholar
[16] Sakthivel NR, Sugumaran V, Babudevasenapati S. Vibration based fault diagnosis of monoblock centrifugal pump using decision tree. Expert Syst Appl. 2010;37(6):4040–9.10.1016/j.eswa.2009.10.002Search in Google Scholar
[17] Firmansah A, Mufti N, Affandi AN, Zaeni IA. Self-powered IoT Based Vibration Monitoring of Induction Motor for Diagnostic and Prediction Failure. IOP Conf Series Mater Sci Eng. 2019 Aug;588(1):012016.10.1088/1757-899X/588/1/012016Search in Google Scholar
[18] Li Z, Wang Y, Wang KS. Intelligent predictive maintenance for fault diagnosis and prognosis in machine centers: Industry 4.0 scenario. Adv Manuf. 2017;5(4):377–87.10.1007/s40436-017-0203-8Search in Google Scholar
[19] Shyamala D, Swathi D, Prasanna JL, Ajitha A. IoT platform for condition monitoring of industrial motors. 2017 2nd International Conference on Communication and Electronics Systems (ICCES); 2017 Oct. 19–20; Coimbatore, India. IEE; 2017 p. 260–265. https://doi.org/10.1109/CESYS.2017.8321278.10.1109/CESYS.2017.8321278Search in Google Scholar
[20] Van Tu ng T, Yang BS. Machine fault diagnosis and prognosis: the state of the art. Int J Fluid Mach Syst. 2009;2(1):61–71.10.5293/IJFMS.2009.2.1.061Search in Google Scholar
[21] Firmansah A, Mufti N, Affandi AN, Zaeni IA. Self-powered IoT Based Vibration Monitoring of Induction Motor for Diagnostic and Prediction Failure IOP Conf Series Mater Sci Eng. 2019;588(1):012016.10.1088/1757-899X/588/1/012016Search in Google Scholar
[22] Chang CY, Chang EC, Huang CW. In Situ Diagnosis of Industrial Motors by Using Vision-Based Smart Sensing Technology. Sensors. 2019;19(24):5340.10.3390/s19245340Search in Google Scholar PubMed PubMed Central
[23] Izagirre U, Andonegui I, Eciolaza L, Zurutuza U. Towards manufacturing robotics accuracy degradation assessment: A vision-based data-driven implementation. Robot Comput-Integr Manuf. 2021;67:102029.10.1016/j.rcim.2020.102029Search in Google Scholar
[24] Ilonen J, Kamarainen JK, Lindh T, Ahola J, Kalviainen H, Partanen J. Diagnosis tool for motor condition monitoring. IEEE Trans Ind Appl. 2005;41(4):963–71.10.1109/TIA.2005.851001Search in Google Scholar
[25] Sharma A, Kumar R. A framework for pre-computated multi-constrained quickest QoS path algorithm. J Telecommun Electron Comput Eng. 2017;9(3–6):73–7.Search in Google Scholar
[26] Lu S, Zhou P, Wang X, Liu Y, Liu F, Zhao J. Condition monitoring and fault diagnosis of motor bearings using undersampled vibration signals from a wireless sensor network. J Sound Vibrat. 2018;414:81–96.10.1016/j.jsv.2017.11.007Search in Google Scholar
[27] Wang J, Fu P, Zhang L, Gao RX, Zhao R. Multilevel information fusion for induction motor fault diagnosis. IEEE/ASME Trans Mechatron. 2019;24(5):2139–50.10.1109/TMECH.2019.2928967Search in Google Scholar
[28] Shifat TA, Hur JW. An effective stator fault diagnosis framework of BLDC motor based on vibration and current signals. IEEE Access. 2020;8:106968–81.10.1109/ACCESS.2020.3000856Search in Google Scholar
[29] Alwodai A, Gu F, Ball AD. A comparison of different techniques for induction motor rotor fault diagnosis. J Phys Conf Ser. 2012 May;364(1):012066.10.1088/1742-6596/364/1/012066Search in Google Scholar
[30] Liu HC, Lin QL, Ren ML. Fault diagnosis and cause analysis using fuzzy evidential reasoning approach and dynamic adaptive fuzzy Petri nets. Comput Ind Eng. 2013;66(4):899–908.10.1016/j.cie.2013.09.004Search in Google Scholar
[31] Gritli Y, Di Tommaso AO, Miceli R, Rossi C, Filippetti F. Diagnosis of mechanical unbalance for double cage induction motor load in time-varying conditions based on motor vibration signature analysis. 2013 International Conference on Renewable Energy Research and Applications (ICRERA); 2013 Oct 20–23; Madrid, Spain. IEE; 2013 p. 1157–1162.Search in Google Scholar
[32] Finley WR, Howdowanec MM, Holter WG. Diagnosing motor vibration problems. Conference Record of 2000 Annual Pulp and Paper Industry Technical Conference (Cat. No. 00CH37111); 2000 Jun 19–23; Atlanta, USA. IEE; 2000 p. 165–180.Search in Google Scholar
[33] Iorgulescu M, Beloiu R, Popescu MO. (2010, May). Vibration monitoring for diagnosis of electrical equipment's faults. 2010 12th International Conference on Optimization of Electrical and Electronic Equipment; 2010 May 20–22; Brasov, Romania. IEE; 2010 p. 493–499. IEEE. https://doi.org/10.1109/OPTIM.2010.5510332.10.1109/OPTIM.2010.5510332Search in Google Scholar
[34] Gangsar P, Tiwari R. Comparative investigation of vibration and current monitoring for prediction of mechanical and electrical faults in induction motor based on multiclass-support vector machine algorithms. Mech Syst Signal Process. 2017;94:464–81.10.1016/j.ymssp.2017.03.016Search in Google Scholar
[35] Sharma A, Kumar R. Computation of the reliable and quickest data path for healthcare services by using service-level agreements and energy constraints. Arab J Sci Eng. 2019;44(11):9087–104.10.1007/s13369-019-03836-4Search in Google Scholar
[36] Gupta V, Kaur BP, Jangra S. An efficient method for fault tolerance in cloud environment using encryption and classification. Soft Comput. 2019;23(24):13591–602.10.1007/s00500-019-03896-6Search in Google Scholar
[37] Kannan R, Manohar SS, Kumaran MS. IoT-Based Condition Monitoring and Fault Detection for Induction Motor. Proceedings of 2nd International Conference on Communication, Computing and Networking; 2018 Sept 8; Chandigarh, India. Springer, Singapore; 2018 p. 205–215.10.1007/978-981-13-1217-5_21Search in Google Scholar
[38] Zurita-Millán D, Delgado-Prieto M, Saucedo-Dorantes JJ, Cariño-Corrales JA, Osornio-Rios RA, Ortega-Redondo JA, et al. Vibration signal forecasting on rotating machinery by means of signal decomposition and neurofuzzy modeling. Shock Vib. 2016;2016.10.1155/2016/2683269Search in Google Scholar
© 2021 Zhe Mi et al., published by De Gruyter
This work is licensed under the Creative Commons Attribution 4.0 International License.
