Integration of ANN and RSM to Optimize the Sawing Process of Wood by Circular Saw Blades

At a Glance

Metadata	Details
Publication Date	2025-09-19
Journal	Applied Sciences
Authors	Mihai Ispas, Sergiu Răcășan, Bogdan Bedelean, A. Angelescu
Institutions	Transylvania University of Brașov
Analysis	Full AI Review Included

Technical Analysis and Documentation: Optimization of Sawing Processes

This document analyzes the research paper “Integration of ANN and RSM to Optimize the Sawing Process of Wood by Circular Saw Blades” and connects the findings and limitations to the advanced material solutions offered by 6CCVD (6ccvd.com).

Executive Summary

The research successfully utilized hybrid modeling (ANN and RSM) to optimize wood sawing parameters, focusing on minimizing cutting power (Pc) and surface roughness (Ra). The findings underscore the critical role of tool material and geometry, presenting a direct opportunity for 6CCVD’s advanced diamond tooling solutions.

Optimization Goal: Minimize cutting power (Pc) and surface roughness (Ra) during the longitudinal sawing of Beech and Spruce wood.
Methodology: Artificial Neural Networks (ANN) were used for predictive modeling, followed by Response Surface Methodology (RSM) for optimization.
Key Factor Identified: Feed speed (X₂) was the most influential factor affecting both power consumption and surface quality.
Optimal Regime: Low feed speed (3.5 m/min) and high rotational speed (6000 rpm) yielded the best results (Ra ~8.41 µm).
Tooling Limitation: The study used conventional carbide-tipped blades, noting uncertainty regarding the specific influence of tooth geometry versus tooth count—a gap addressable by precision diamond tooling.
Model Accuracy: The developed ANN models demonstrated high predictive capability, with correlation coefficients (R) exceeding 0.98 for both Pc and Ra.
6CCVD Value Proposition: The need for superior, geometrically precise tooling to maintain low roughness and high efficiency points directly to the use of MPCVD Polycrystalline Diamond (PCD) for enhanced wear resistance and consistent performance.

Technical Specifications

The following hard data points were extracted from the experimental section of the research paper:

Parameter	Value	Unit	Context
Wood Species Tested	Beech, Spruce	N/A	Samples cut longitudinally
Average Wood Density (Beech)	604.3	kg/m³	Fagus sylvatica
Average Wood Density (Spruce)	456.3	kg/m³	Picea abies
Blade Diameter	190	mm	Machine constraint
Kerf Width (b)	2.3	mm	Used for both blades
Blade Rotation Speed (X₁) Range	3500 to 6000	rpm	Tested numerical factor
Feed Speed (X₂) Range	3.5 to 27	m/min	Tested numerical factor
Minimum Roughness (Ra) Achieved	7.85	µm	Spruce, z=54 blade, 4500 rpm, 3.5 m/min
Optimal Roughness (Ra) (z=24)	8.41	µm	Beech/Spruce, 6000 rpm, 3.5 m/min
Maximum Cutting Power (Pc)	1.85	kW	Beech, z=54 blade, 27 m/min
ANN Model Correlation (R)	0.987	N/A	Cutting Power (Pc) Training Phase
ANN Model Correlation (R)	0.985	N/A	Roughness (Ra) Training Phase
Roughness Stylus Tip Radius	2	µm	Mahr MarSurf XT20 system

Key Methodologies

The experimental design focused on combining empirical testing with advanced computational modeling to derive optimal machining parameters.

Material Selection: Beech (Fagus sylvatica) and Spruce (Picea abies) wood strips (600 x 100 x 18 mm) were prepared with moisture content around 8.1% to 8.6%.
Tooling: Two carbide-tipped circular saw blades (190 mm diameter) were used:
- Tool 1 (z=24): Alternate Top Bevel teeth (wedge angle β = 60°, hook angle γ = 20°).
- Tool 2 (z=54): Flat Top Teeth (wedge angle β = 65°, hook angle γ = 15°).
Machining Setup: Cutting was performed longitudinally on a FELDER F 900 M spindle moulder, utilizing an industrial power feeder for uniform feed speed.
Data Acquisition: 24 cutting regimes were tested per wood species. Active power consumption (Pc) was measured using a Camille Bauer Sineax P530/Q531 transducer (Class 0.5 accuracy).
Surface Quality Measurement: Surface roughness (Ra) was measured perpendicular to the grain using a Mahr MarSurf XT20 system. Roughness profiles were filtered using a Gaussian regression filter (2.5 mm cut-off length) according to ISO 16610-31:2016.
Modeling and Optimization:
- Data was split into training (48 values) and validation (20 values) sets.
- Artificial Neural Network (ANN) models were developed using NeuralWare’s Predict Software to accurately predict Pc and Ra.
- Response Surface Methodology (RSM) using Face Central Composite Design (FCCD) was applied to the validated models to identify optimal parameters for minimum Pc and Ra.

6CCVD Solutions & Capabilities

The research successfully optimized sawing parameters using conventional carbide tooling, but the authors noted a critical ambiguity: the specific influence of tooth geometry versus tooth count remains unclear, and tool wear is a known limitation in wood processing. 6CCVD’s MPCVD diamond materials provide the necessary precision and durability to eliminate these limitations, enabling researchers and manufacturers to achieve superior, consistent results.

Applicable Materials

To replicate and extend this research, particularly focusing on tool longevity and achieving ultra-low roughness, Polycrystalline Diamond (PCD) is the ideal material.

Material Recommendation	Application Focus	6CCVD Capability
PCD Plates/Wafers	Tool inserts for circular saw blades (PCD-tipped tools)	Superior wear resistance for abrasive materials like wood and wood composites (particleboard, MDF), drastically reducing tool dulling observed in the literature.
Optical Grade SCD	Potential use in advanced sensor or thermal management components integrated into the blade body (e.g., temperature monitoring)	SCD offers the highest thermal conductivity (up to 2200 W/mK), ideal for managing the peak heat observed at the blade’s outer edge during high-speed cutting.
Custom BDD	Future research into electro-chemical machining or sensing applications	Boron-Doped Diamond (BDD) films can be integrated for highly stable electrochemical sensing or specialized surface treatments.

Customization Potential

The study’s limitation regarding the separation of tooth count versus tooth geometry effects can be overcome using 6CCVD’s custom fabrication services, allowing for precise control over the diamond cutting edge.

Custom Dimensions: 6CCVD supplies PCD plates and wafers up to 125mm in diameter, suitable for manufacturing large, high-performance saw blade segments.
Precision Geometry: We provide custom diamond blanks that can be laser-cut and ground to exact specifications, enabling researchers to isolate and test specific geometric parameters (e.g., rake angle, clearance angle, bevel angle) independent of material wear.
Ultra-Low Roughness Polishing: While the study achieved Ra ~8 µm with carbide, 6CCVD offers polishing services for PCD down to Ra < 5nm (for inch-size PCD), ensuring that the cutting edge itself is ultra-smooth, leading to superior machined surface quality and reduced friction.
Metalization Services: We offer in-house metalization (Au, Pt, Pd, Ti, W, Cu) necessary for robust brazing and mounting of PCD segments onto the steel blade body, ensuring maximum stability at the high rotational speeds (up to 6000 rpm) used in the experiment.

Engineering Support

The optimization study confirms that tool type is a significant factor in both power consumption and surface quality. 6CCVD’s in-house PhD team specializes in the material science of diamond tooling and can provide expert consultation.

Tool Design Consultation: We assist tool manufacturers and researchers in selecting the optimal diamond grade and geometry for high-speed, low-wear applications, specifically addressing the trade-offs between productivity and surface quality identified in this Wood Circular Sawing Optimization project.
Performance Modeling: Our team can integrate material properties (e.g., PCD hardness and thermal stability) into computational models like ANN/RSM to predict performance improvements over conventional carbide tools.
Global Supply Chain: We ensure reliable, global shipping (DDU default, DDP available) of custom diamond materials, supporting international research and industrial partners.

For custom specifications or material consultation, visit 6ccvd.com or contact our engineering team directly.

View Original Abstract

Various parameters, like blade design, rotational speed, feed speed, tooth geometry, wood moisture content, and wood species, influence the efficiency and quality of sawing processes. Knowing the optimal combination of these factors could lead to lower power consumption and high surface quality during wood processing. Therefore, in this study, we applied a novel method that could be used to optimize the cutting of wood with circular saw blades. The analyzed factors included rotational speed, feed speed, blade type (the number of cutting teeth and blade geometries), and two wood species, such as beech and spruce. The samples were cut longitudinally using two circular saw blades. The power consumption and the roughness of the processed surfaces were experimentally measured using an active/reactive electrical power transducer and a DAQ connected to a computer and a diamond stylus roughness meter, respectively. Once the data were gathered and processed, an artificial neural network modeling technique was involved in designing two models: one model for the cutting power and the other for surface roughness. Both models are characterized by high values of performance indicators. Therefore, the models could be considered a reliable tool that could be used to predict the cutting power and the surface roughness for the cutting of wood with circular saw blades. Next, response surface methodology was used to identify how each factor affects the cutting power and the surface quality, and to find the optimal values for both. The results showed that the most important factor that influences the roughness of the processed surfaces is the feed speed; the second factor is the blade rotation speed; the third factor is the tool type (the number of cutting teeth combined with their geometry). The optimal machining conditions recommended by the optimization algorithm (low power consumption and low roughness) imply minimum feed speed values (3.5 m/min) and medium (4500 rpm for 54-tooth blade) or high (6000 rpm for 24-tooth blade) blade rotation speeds. A further study will be conducted to consider the behavior of wood species during the circular sawing of wood and to clarify the influence of the different constructive parameters of the blades (number of teeth, tooth geometry) on their performance.

Tech Support

Original Source

DOI: https://doi.org/10.3390/app151810206

References

1971 - On the Behaviour of Circular Sawblades during Cutting—Part II: Effect of the Cutting Conditions on the Quality of Sawn Wood Surfaces [Crossref]
1992 - Effect of tooth front bevel angle on cutting accuracy and chip formation for circular rip saws [Crossref]
2011 - Specific cutting energy consumption in a circular saw for Eucalyptus stands VM01 and MN463 [Crossref]
2012 - Economical Wood Sawing with Circular Saw Blades of a New Design [Crossref]
2013 - Industrial Sawing of Pinus sylvestris L. Power Consumption
2014 - Effect of the saw blade construction on the surface quality when transverse sawing spruce lumber on crosscut miter saw
2015 - The Dependence of Surface Quality on Tool Wear of Circular Saw Blades during Transversal Sawing of Beech Wood [Crossref]
2017 - The influences of circular saws with sawteeth of mic-zero-degree radial clearance angles on surface roughness in wood rip sawing [Crossref]
2018 - Quality of machined surfaces and specific cutting energy in wood of two African mahogany species
2019 - Practical Guideline in the Design and use of Woodworking Tools [Crossref]