Optimalisation of Flying Shears Control Structure Using AI Methods

Tadeáš Kmecik; Matej Hric; Peter Girovský; František Ďurovský

doi:10.2478/pead-2026-0006

.blurhash-client-img { display: none !important; }

Optimalisation of Flying Shears Control Structure Using AI Methods

Power Electronics and Drives

Volume 11 (2026): Issue 1 (January 2026)

By: Tadeáš Kmecik , Matej Hric , Peter Girovský and František Ďurovský

Open Access

|Feb 2026

Figures & Tables

An example of steel sheet cutting on MPL. *Source:* Siemens AG (2025). MPL, material processing lines.

Important areas of rotary shears trajectory. *Source:* Siemens AG (2025). ESR, end of the synchronous range; FR, formatting range; PP, parking position; RP, reference point; SR, synchronous range; SSR, start of the synchronous range.

Ideal shears trajectory during the cutting process. *Source:* Ďurovský et al. (2023).

Table 1.

Shears’ position and torque during cut.

Parameters	Shears’ angle (°)	Shears’ arm (mm)	Torque on motor side
Parameters	Shears’ angle (°)	Shears’ arm (mm)	(Nm)	(% of TR)
Beginning of cut	339	34.045	1,872.2	76.14
End of cut	345	24.588	1,352.1	55

Table 2.

The shears’ angular velocity drop during the cut considering freewheeling shears (i.e. without controllers).

Steady state (rad/s)	After cut (rad/s)	Difference (rad/s)	Difference (%)
20	14.74	7.63	7.11	48.34
50	36.847	34.021	2.862	7.77
80	58.938	57.180	1.758	2.98

Table 3.

Rotary shears motor parameters.

Parameters	Symbol	Unit	Value
Rated power	P_R	kW	190
Rated voltage	V_R	V	400
Rated speed	n_R	rpm	800
Motor inertia	J_mot	kg/m²	4.2
Rated current	I_R	A	335
Rated frequency	f_R	Hz	27.2
Rated torque	T_R	Nm	2,328
Maximum torque	T_max	Nm	4,250
Rated power factor	cos(ϕ)	-	0.942
Rated efficiency	η	%	89
Torque control loop time constant	τ_T	ms	2

The rotary shears control structure. *Source*: Ďurovský et al. (2023).

Compensation torque and actual cutting torque during the shearing process.

Membership functions of the inputs and output. NM, negative medium; NS, negative small; PM, positive medium; PS, positive small.

Table 4.

Fuzzy control rules.

e(k)/Δe(k)	NM	NS	Z	PS	PM
NM	NM	NM	NM	NS	Z
NS	NM	NM	NS	Z	PS
Z	NM	NS	Z	PS	PM
PS	NS	Z	PS	PM	PM
PM	Z	PS	PM	PM	PM

[i] NM, negative medium; NS, negative small; Z, zero; PM, positive medium; PS, positive small.

Table 5.

Parameters of NN predictive model.

Parameters	Value/description
Network type	Feedforward NN (MLP)
Output	Prediction of motor torque ${\hat{T}}_{mot} (k + 1)$
Input vector	[T_ref (k), T_ref (k − 1), T_mot (k), T_mot(k − 1), T_load (k), T_load(k − 1)]
Hidden layers	2
Number of neurons	10–10
Activation functions	Tansig (hidden layers), linear (output layer)
Training algorithms	Levenberg–Marquardt
Input and output normalisation	Range [−1, 1]
Sampling period	T_s = 100 μs

[i] MLP, multilayer perceptron; NN, neural network.

Table 6.

Performance metrics of the NN torque predictor.

Abbreviation	Full name	Value	Unit
MAE	Mean absolute error	1.7645	Nm
RMSE	Root mean square error	2.3071	Nm
RMSE	Percentage RMSE	0.0991	%
MaxE	Maximum absolute error	5.7528	Nm
R²	Coefficient of determination	0.9999	-

[i] NN, neural network.

Detailed view of torque prediction error between view of torque prediction error between NN output and measured torque. NN, neural network.

Flowchart of the NN-based torque compensation algorithm. NN, neural network.

Input signals used for NN training in the time domain. NN, neural network.

Comparison of the 1D lookup-table-based compensation torque and the load torque. LUT, lookup table; NN, neural network.

Simulation results of cutting 3 mm thick and 1,600 mm wide strip at 40 m/min. (a) P-type controller without compensation, (b) PI-type controller without compensation, (c) P-type controller with compensation, (d) P-type controller with anticipative compensation, (e) P-type controller with Fuzzy feedforward, (f) P-type controller NN-based LUT compensation. LUT, lookup table; NN, neural network.

Table 7.

Summary of dynamic performance metrics for all tested control structures and compensation strategies at different strip speeds.

Strip speed [m/min]	Control structure	Compensation	Speed drop [%]	Absolutely speed drop [m/min]	Speed overshoot [%]	Settling time [ms]
20	P	No	10.71	2.144	0.115	54.2
	PI	No	9.12	1.824	1.534	82.3
	P	Yes	4.74	0.948	4.38	50.1
P	Anticipative	5.71	1.143	4.21	50.7
P + fuzzy	No	1.66	0.332	0	34.7
P	NN compensation	1.07	0.214	0.06	35.7
40	P	No	5.03	2.014	0.32	34.5
	PI	No	4.35	1.740	4.48	53.1
	P	Yes	1.16	0.464	1.62	25.5
P	Anticipative	0.78	0.311	1.58	16.6
P + fuzzy	No	0.86	0.344	0	16.2
P	NN compensation	0.55	0.222	0.02	19.4
80	P	No	2.28	1.825	0.13	23.5
	PI	No	2.03	1.621	1.47	44.2
	P	Yes	0.56	0.448	0.52	19.8
P	Anticipative	0.47	0.377	0.45	19.5
P + fuzzy	No	0.43	0.344	0	8.3
P	NN compensation	0.28	0.226	0.01	10

[i] NN, neural network; PI, proportional–integral.

References

Authors

Metrics

Articles in this issue

DOI: https://doi.org/10.2478/pead-2026-0006 | Journal eISSN: 2543-4292 | Journal ISSN: 2451-0262

Journal RSS Feed

Language: English

Page range: 111 - 127

Submitted on: Dec 30, 2025

Accepted on: Feb 23, 2026

Published on: Feb 21, 2026

Published by: Wroclaw University of Science and Technology

In partnership with: Paradigm Publishing Services

Keywords:

artificial intelligence,

flying shears,

control structure optimisation,

neural network,

intelligent control

Related subjects:

Computer sciences,

Artificial intelligence,

Engineering,

Electrical engineering,

Electronics

© 2026 Tadeáš Kmecik, Matej Hric, Peter Girovský, František Ďurovský, published by Wroclaw University of Science and Technology
This work is licensed under the Creative Commons Attribution 4.0 License.

Volume 11 (2026): Issue 1 (January 2026)

Optimalisation of Flying Shears Control Structure Using AI Methods

Figures & Tables

Figure 1.

Figure 2.

Figure 3.

Table 1.

Table 2.

Table 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Table 4.

Table 5.

Table 6.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Table 7.

Paradigm

My account