Open Access

Analysis of automation technology education reform based on industrial internet and smart manufacturing promotion

Nan Zhang

Nan Zhang

School of Control Engineering, Wuxi institute of TechnologyWuxi, China
Search for this author on
Sciendo|Google Scholar
Zhang, Nan
 and 
Maolong Xi

Maolong Xi

School of Control Engineering, Wuxi institute of TechnologyWuxi, China
Search for this author on
Sciendo|Google Scholar
Xi, Maolong
  
Sep 26, 2025
Analysis of automation technology education reform based on industrial internet and smart manufacturing promotion's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Sep 26, 2025
Received: Jan 24, 2025
Accepted: May 06, 2025
DOI: https://doi.org/10.2478/amns-2025-1052
Keywords
© 2025 Nan Zhang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Two-dimensional section of the k-means
Two-dimensional section of the k-means

Figure 2.

Flowchart of the machine learning model
Flowchart of the machine learning model

Logical regression analysis table

B S.E Wals df Sig. Exp(B)
Step1 Base selection 0.969 0.128 59.064 1 0.000 2.632
Internship process 0.765 0.125 38.456 1 0.000 2.154
Training process 0.823 0.119 46.156 1 0.000 2.285
Intelligent manufacturing facilities 0.735 0.124 35.146 1 0.000 2.074
Constants 0.157 0.113 1.954 1 0.158 1.165

Student type ratio

Categories Quantity Proportion/%
Class1 155 12.92
Class2 421 35.08
Class3 468 39
Class4 156 13

Model summary

Step -2 Logarithmic likelihood Cox&Snell R2 Nagelkerke R2
1 483.654a 0.304 0.409

Classification table

Self-observation Self-prediction
Whether the general body of the electrical automation major is satisfied Percentage correction/%
Yes No
Step1 Whether the general body of the electrical automation major is satisfied Yes 160 40 80
No 28 172 86
Total percentage 83.2

Sample correlation validation results

Dimension name W-test (w) Pearson correlation coefficient (r)
Effective operation number of automated technologies 0.7256 0.6396
Total length 0.4958 0.8312
After-school hours 0.6554 0.8024
Course length 0.3895 0.8935
Comprehensive achievement 0.3936 -

Custering analysis of primitive sample Numbers

Student number Effective number of operations Total length/min After class/min Course length/min Comprehensive score
1 240 436 90 350 59
2 456 523 163 365 69
3 618 1029 410 614 76
4 458 757 189 563 75
5 525 797 230 572 82
6 379 254 23 225 77
7 661 999 254 741 88
8 551 649 201 453 86
9 759 1348 653 696 89
10 590 746 563 490 93

K-means clustering analysis

Categories Quantity Category description Feature
Class1 155 The effective command in the automated technology experiment is high, and the total length is large The ability of automatic technology experiment is strong and comprehensive performance
Class2 421 The effective command number in the automated technology experiment is large The automatic technology experiment is usually less practical
Class3 468 The effective command number in automatic technology experiment is large The automatic technology experiment is slightly stronger, and the practice time is more
Class4 156 The effective command in the automatic technology experiment is low and the total length is smaller The automatic technology experiment is less effective and the upper machine time is relatively small
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed