volume: 47, issue: 1
Modern forest harvesting machinery generate an abundance of underutilised data in their control systems. The Controller Area Network (CAN) bus data stream offers the opportunity to investigate the operation of the machinery in detail while in real-world harvesting scenarios. This study uses CAN data to assess a component of operator workload in forwarder operations, by introducing a method to interpret forwarder joystick movements. The data was captured in a clearfell logging operation case study in Canterbury, New Zealand. The joystick data was then analysed to determine the time and number of operator input movements per load cycle (»grab«) totalling 418 grabs. This, combined with video analysis, identified independent variables that describe the grab cycle such as time of day, number of logs per grab, log grade, and the activities of »pencilling« (vertical drop of logs in grab to align large ends) and »dropping« (releasing logs from the grab before loading). Factors that significantly affected the operators' time taken to complete the grab and the number of required joystick movements included number of logs, pencilling and dropping. For example, the average load cycle was 18-seconds for four logs, and this increased by 6.1-seconds and 14.4-seconds per grab when pencilling or dropping, respectively. Average total joystick movements were ~108 per grab. This case study demonstrated that CAN bus data can be used to improve our understanding of the operation of harvesting equipment such as forwarders. An example use of the result is to share and compare this with the harvester operator (who crosscuts and sets out the logs for forwarder-collection) as the need for pencilling and dropping is a consequence of misalignment or debris caught in the piles. The method used also presents an opportunity for human factors research, particularly in operator fatigue management and training through the measurement of joystick movements with a genuine possibility of real-time performance feedback.
volume: issue, issue:
As the New Zealand forestry industry progresses toward the implementation of Forestry 4.0 and 5.0 concepts, the use of machine data for operational monitoring and analysis is becoming increasingly valuable. This study investigates the application of machine learning to automate time studies of forwarders by predicting machine activity using Controller Area Network data. Data were collected from two John Deere 1910E forwarders over three harvesting sites (295 cycles) in the South Island of New Zealand. Four machine learning models, Random Forest, Classification and Regression Tree, Long Short-Term Memory, and Gated Recurrent Unit, were trained on data of Forwarder One at an 80:20 (training:testing) split (185 cycles). The models were then further evaluated for generalisability using data of Forwarder Two (110 cycles). Initial trials revealed that machine learning models struggled to distinguish between machine activities such as Loading and Unloading or Driving Loaded and Unloaded, with the neural network models (Long Short-Term Memory and Gated Recurrent Unit) demonstrating superior performance in capturing temporal dependencies. After relabelling and reducing feature complexity, the Gated Recurrent Unit model achieved a validation accuracy of 95.51%, outperforming all other models. Comparison with existing methods from the literature showed that this model provided lower error rates for cycle time, with a percent error of 0.05% and a Root Mean Square Error of 0.02 minutes. At the machine activity level, the model was significantly better, with a decrease in percent error of up to approximately 130% and Root Mean Square Error of up to approximately 1.8 minutes, compared to previous literature. This research demonstrates the feasibility of using machine learning to automate forwarder time studies with high accuracy, providing a scalable and replicable framework that could extend to other forestry machinery. The findings support the integration of these models into Cyber-Physical Systems for real-time monitoring, though challenges such as data access and model generalisation must be addressed to fully realise the benefits of Forestry 4.0.
volume: 48, issue: 1
As the New Zealand forestry industry progresses toward the implementation of Forestry 4.0 and 5.0 concepts, the use of machine data for operational monitoring and analysis is becoming increasingly valuable. This study investigates the application of machine learning to automate time studies of forwarders by predicting machine activity using Controller Area Network data. Data were collected from two John Deere 1910E forwarders over three harvesting sites (295 cycles) in the South Island of New Zealand. Four machine learning models, Random Forest, Classification and Regression Tree, Long Short-Term Memory, and Gated Recurrent Unit, were trained on data of Forwarder One at an 80:20 (training:testing) split (185 cycles). The models were then further evaluated for generalisability using data of Forwarder Two (110 cycles). Initial trials revealed that machine learning models struggled to distinguish between machine activities such as Loading and Unloading or Driving Loaded and Unloaded, with the neural network models (Long Short-Term Memory and Gated Recurrent Unit) demonstrating superior performance in capturing temporal dependencies. After relabelling and reducing feature complexity, the Gated Recurrent Unit model achieved a validation accuracy of 95.51%, outperforming all other models. Comparison with existing methods from the literature showed that this model provided lower error rates for cycle time, with a percent error of 0.05% and a Root Mean Square Error of 0.02 minutes. At the machine activity level, the model was significantly better, with a decrease in percent error of up to approximately 130% and Root Mean Square Error of up to approximately 1.8 minutes, compared to previous literature. This research demonstrates the feasibility of using machine learning to automate forwarder time studies with high accuracy, providing a scalable and replicable framework that could extend to other forestry machinery. The findings support the integration of these models into Cyber-Physical Systems for real-time monitoring, though challenges such as data access and model generalisation must be addressed to fully realise the benefits of Forestry 4.0.