Advanced Search
Article Contents
Article Contents

Major project risk assessment method based on BP neural network

  • * Corresponding author: Shenghan Zhou

    * Corresponding author: Shenghan Zhou
The first author is supported by NSFC grant 71501007, 71672006 and 71332003
Abstract Full Text(HTML) Figure(7) / Table(3) Related Papers Cited by
  • In order to prevent risks in major projects, it is of great importance to accurately assess risks in advance. Therefore, in this paper, we propose a novel major project risk assessment method with the BP neural network model. Firstly, we propose an index system for major project risk assessment, which is made up of four parts: 1) Schedule risk, 2) Cost risk, 3) Quality risk, and 4) Resource risk. Secondly, we propose a hybrid BP neural network and particle swarm optimization (PSO) model to evaluate risks in major projects. Especially, major project risk assessment results are achieved from the output layers of the BP neural network which is optimized by the PSO algorithm. In our proposed hybrid model, the fitness for each particle is computed through an optimal function, and then the particle can improve its velocity for the next cycle by searching the optimal value. Furthermore, this process should be repeated when the end condition is satisfied. Finally, experimental results demonstrate that the proposed method is able to evaluate risk level of major projects with high accuracy.

    Mathematics Subject Classification: Primary: 58F15, 58F17; Secondary: 53C35.


    \begin{equation} \\ \end{equation}
  • 加载中
  • Figure 1.  Index system for major project risk assessment

    Figure 2.  Framework of the BP neural network

    Figure 3.  Calculation process of the BP neural network algorithm

    Figure 4.  Strucutre of the BP neural network for major project risk assessment

    Figure 5.  The trend of training error varying

    Figure 6.  Risk assessment results for different major projects

    Figure 7.  Error rates of risk assessment for different major projects

    Table 1.  Testing data of the major project risk assessment problem

    S1 S2 S3 S4 S5 S6 S7 S8
    A1 0.135 0.154 0.228 0.190 0.218 0.184 0.208 0.252
    A2 0.145 0.216 0.195 0.221 0.140 0.287 0.210 0.243
    A3 0.139 0.138 0.363 0.270 0.139 0.306 0.151 0.274
    A4 0.427 0.520 0.599 0.582 0.633 0.618 0.535 0.587
    A5 0.451 0.510 0.638 0.605 0.639 0.616 0.630 0.571
    A6 0.156 0.210 0.493 0.167 0.305 0.393 0.219 0.289
    A7 0.241 0.215 0.390 0.185 0.214 0.334 0.334 0.169
    A8 0.371 0.319 0.343 0.208 0.179 0.397 0.380 0.356
    A9 0.385 0.419 0.312 0.220 0.303 0.323 0.356 0.117
    A10 0.250 0.325 0.383 0.259 0.249 0.366 0.258 0.269
    A11 0.237 0.275 0.357 0.352 0.242 0.310 0.363 0.253
    A12 0.339 0.349 0.325 0.333 0.321 0.328 0.309 0.329
    A13 0.211 0.216 0.329 0.281 0.209 0.295 0.215 0.347
    A14 0.341 0.379 0.307 0.330 0.280 0.332 0.247 0.374
    A15 0.171 0.182 0.319 0.213 0.148 0.348 0.150 0.195
    A16 0.122 0.139 0.577 0.483 0.128 0.481 0.372 0.474
    A17 0.149 0.162 0.400 0.335 0.120 0.478 0.468 0.363
    A18 0.164 0.225 0.320 0.284 0.212 0.351 0.332 0.398
    A19 0.219 0.246 0.176 0.250 0.155 0.316 0.209 0.214
    A20 0.124 0.225 0.239 0.135 0.130 0.309 0.209 0.302
     | Show Table
    DownLoad: CSV

    Table 2.  Risk scores from experts?opinion

    Project S1 S2 S3 S4 S5 S6 S7 S8
    Expert opinion 0.155 0.189 0.362 0.171 0.158 0.347 0.273 0.301
     | Show Table
    DownLoad: CSV

    Table 3.  Parameters of the propose BP neural network model

    ID Parameter name Value
    1 Number of hidden layer nodes 35
    2 Transfer function type of hidden layer nodes logsig
    3 Neuron excitation function of output layer purelin
    4 Training function trainlm
    5 Learning function learngdm
    6 Maximum iteration number 550
    7 Learning rate 0.00001
    8 Momentum coefficient 0.94
    9 Error rate of network training 0.0001
     | Show Table
    DownLoad: CSV
  • [1] G. D. BossartP. FairA. M. Schaefer and J. S. Reif, Health and Environmental Risk Assessment Project for bottlenose dolphins Tursiops truncatus from the southeastern USA, I. Infectious Diseases, Diseases of Aquatic Organisms, 125 (2017), 141-153. 
    [2] P. Las CasasS. M. Rezende and D. D. Ribeiro, Risk factors assessment for thrombosis in patients with cancer - research project of the federal university of minas gerais, Journal of Thrombosis and Haemostasis, 14 (2016), 83-83. 
    [3] X. M. ChenT. L. WangM. M. DingJ. WangJ. Q. Chen and J. X. Yan, Analysis and prediction on the cutting process of constrained damping boring bars based on PSO-BP neural network model, Journal of Vibroengineering, 19 (2017), 878-893. 
    [4] G. Y. HeC. HuangL. Z. GuoG. M. Sun and D. W. Zhang, Identification and adjustment of guide rail geometric errors based on BP neural network, Measurement Science Review, 17 (2017), 135-144. 
    [5] C. L. JiangS. Q. ZhangC. ZhangH. P. Li and X. H. Ding, Modeling and predicting of MODIS leaf area index time series based on a hybrid. SARIMA and BP neural network method, Spectroscopy and Spectral Analysis, 37 (2017), 189-193. 
    [6] Y. T. KuangR. SinghS. Singh and P. Singh, A novel macroeconomic forecasting model based on revised multimedia assisted BP neural network model and ant Colony algorithm, Multimedia Tools and Applications, 76 (2017), 18749-18770. 
    [7] Z. K. Li and X. H. Zhao, BP artificial neural network based wave front correction for sensor-less free space optics communication, Optics Communications, 385 (2017), 219-228. 
    [8] C. J. LiuW. F. DingZ. Li and C. Y. Yang, Prediction of high-speed grinding temperature of titanium matrix composites using BP neural network based on PSO algorithm, International Journal of Advanced Manufacturing Technology, 89 (2017), 2277-2285. 
    [9] S. D. LiuZ. S. Hou and C. K. Yin, Data-driven modeling for ugi gasification processes via an enhanced genetic bp neural network with link switches, IEEE Transactions on Neural Networks and Learning Systems, 27 (2016), 2718-2729. 
    [10] T. H. Liu and S. L. Yin, An improved particle swarm optimization algorithm used for BP neural network and multimedia course-ware evaluation, Multimedia Tools and Applications, 76 (2017), 11961-11974. 
    [11] C. MaL. ZhaoX. S. MeiH. Shi and J. Yang, Thermal error compensation of high-speed spindle system based on a modified BP neural network, International Journal of Advanced Manufacturing Technology, 89 (2017), 3071-3085. 
    [12] D. L. MaT. ZhouJ. ChenS. QiM. A. Shahzad and Z. J. Xiao, Supercritical water heat transfer coefficient prediction analysis based on BP neural network, Nuclear Engineering and Design, 320 (2017), 400-408. 
    [13] C. Muriana and G. Vizzini, Project risk management: A deterministic quantitative technique for assessment and mitigation, International Journal of Project Management, 35 (2017), 320-340. 
    [14] O. Okmen, Risk assessment for determining best design alternative in a state-owned irrigation project in Turkey, Ksce Journal of Civil Engineering, 20 (2016), 109-120. 
    [15] C. Ou-Yang and W. L. Chen, Applying a risk assessment approach for cost analysis and decision-making: A case study for a basic design engineering project, Journal of the Chinese Institute of Engineers, 40 (2017), 378-390. 
    [16] J. S. Peng, Multi-objective optimization of vibration characteristics of steering systems based on GA-BP neural networks, Journal of Vibroengineering, 19 (2017), 3216-3229. 
    [17] J. S. ReifA. M. SchaeferG. D. Bossart and P. A. Fair, Health and Environmental Risk Assessment Project for bottlenose dolphins Tursiops truncatus from the southeastern USA, II. Environmental aspects, Diseases of Aquatic Organisms, 125 (2017), 155-166. 
    [18] A. Salah and O. Moselhi, Risk identification and assessment for engineering procurement construction management projects using fuzzy set theory, Canadian Journal of Civil Engineering, 43 (2016), 429-442. 
    [19] G. L. Su, Human exercise physiology index evaluation method based on a BP neural network, Agro Food Industry Hi-Tech, 28 (2017), 2112-2116. 
    [20] A. X. SunX. Jin and Y. B. Chang, Research on the process optimization model of micro-clearance electrolysis-assisted laser machining based on BP neural network and ant colony, International Journal of Advanced Manufacturing Technology, 88 (2017), 3485-3498. 
    [21] T. TuviaM. KatsC. AloezosM. ToA. Ozdoba and L. Gallo, A quality improvement project focused on assessment of risk level of outpatient psychiatry patients, European Psychiatry, 41 (2017), S898-S898. 
    [22] D. Y. WangH. Y. LuoO. GrunderY. B. Lin and H. X. Guo, Multi-step ahead electricity price forecasting using a hybrid model based on two-layer decomposition technique and BP neural network optimized by firefly algorithm, Applied Energy, 190 (2017), 390-407. 
    [23] F. WangH. ZhuY. P. Li and Y. F. Liu, Combined transmission laser spectrum of core-offset fiber and bp neural network for temperature sensing research, Spectroscopy and Spectral Analysis, 36 (2016), 3732-3736. 
    [24] J. WangY. Q. WenY. D. GouZ. Y. Ye and H. Chen, Fractional-order gradient descent learning of BP neural networks with Caputo derivative, Neural Networks, 89 (2017), 19-30. 
    [25] J. D. WangK. J. FangW. J. Pang and J. W. Sun, Wind power interval prediction based on improved pso and bp neural network, Journal of Electrical Engineering & Technology, 12 (2017), 989-995. 
    [26] W. WangX. D. GuL. Ma and S. S. Yan, Temperature error correction based on BP neural network in meteorological wireless sensor network, International Journal of Sensor Networks, 23 (2017), 265-278. 
    [27] X. WangJ. ZhuF. B. MaC. H. LiY. P. Cai and Z. F. Yang, Bayesian network-based risk assessment for hazmat transportation on the middle route of the south-to-north water transfer project in china, Stochastic Environmental Research and Risk Assessment, 30 (2016), 841-857. 
    [28] S. B. WuJ. X. Liu and Y. Yu, Prediction of cut size for pneumatic classification based on a back propagation (BP) neural network, Zkg International, 69 (2016), 64-71. 
    [29] B. XuH. C. Dan and L. Li, Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network, Applied Thermal Engineering, 120 (2017), 568-580. 
    [30] Z. YouJ. LiuJ. DaiW. LiuW. SongX. Wang and C. Zhang, BP neural network-based smog environment and the risk model of mood driving, Applied Ecology and Environmental Research, 15 (2017), 1753-1763. 
    [31] Q. W. Zhang, Personal credit risk assessment of bp neural network commercial banks based on PSO-GA algorithm optimization, Agro Food Industry Hi-Tech, 28 (2017), 2580-2584. 
    [32] X. M. ZhangX. M. Zhao and N. Wu, Credit risk assessment model for cross-border e-commerce in a bp neural network based on PSO-GA, Agro Food Industry Hi-Tech, 28 (2017), 411-414. 
    [33] Z. H. ZhangY. HuC. MaJ. H. XuS. G. Yuan and Z. Chen, Incentive-punitive risk function with interval valued intuitionistic fuzzy information for outsourced software project risk assessment, Journal of Intelligent & Fuzzy Systems, 32 (2017), 3749-3760. 
    [34] H. J. ZhaoS. G. ShiH. Z. JiangY. Zhang and Z. F. Xu, Calibration of AOTF-based 3D measurement system using multiplane model based on phase fringe and BP neural network, Optics Express, 25 (2017), 10413-10433. 
    [35] X. B. ZhaoB. G. Hwang and Y. Gao, A fuzzy synthetic evaluation approach for risk assessment: A case of Singapore's green projects, Journal of Cleaner Production, 115 (2016), 203-213. 
  • 加载中
Open Access Under a Creative Commons license




Article Metrics

HTML views(1534) PDF downloads(511) Cited by(0)

Access History

Other Articles By Authors



    DownLoad:  Full-Size Img  PowerPoint