A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions
The growing diversity and number of industrial robots make energy consumption prediction and optimization increasingly essential. Current data-driven approaches, particularly those based on multi-layer perception (MLP), have shown feasibility but typically overlook the variability or unknown nature...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Actuators |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0825/13/12/516 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850050672521641984 |
|---|---|
| author | Qing Chang Tiantian Yuan Haifeng Li Yuxiang Chen Xuehao Wang Sen Gao Hongsheng Ren Xiangyun Zhao Lingyu Wang |
| author_facet | Qing Chang Tiantian Yuan Haifeng Li Yuxiang Chen Xuehao Wang Sen Gao Hongsheng Ren Xiangyun Zhao Lingyu Wang |
| author_sort | Qing Chang |
| collection | DOAJ |
| description | The growing diversity and number of industrial robots make energy consumption prediction and optimization increasingly essential. Current data-driven approaches, particularly those based on multi-layer perception (MLP), have shown feasibility but typically overlook the variability or unknown nature of load-related parameters in real-world applications. This paper presents a KAN-LSTM model designed to accurately predict energy consumption under unknown load conditions, alongside a particle swarm optimization (PSO) algorithm for minimizing energy use. First, an industrial robot dynamics and energy consumption model is established. Then, the KAN-LSTM model is trained on datasets from the AUBO-E5 robot, with its predictions compared to alternative network models. Finally, PSO is applied to optimize energy consumption. Experimental results indicate that the KAN-LSTM model achieves high prediction accuracy (95.7–97.1%) and offers substantial energy optimization potential (53.1–64.7%). Optimized industrial robots are particularly suitable for tasks such as picking and palletizing in the courier industry, saving operational costs and increasing the sustainability of automated systems in logistics environments. |
| format | Article |
| id | doaj-art-ef89d5b176d84e8c94989df48c31db3c |
| institution | DOAJ |
| issn | 2076-0825 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Actuators |
| spelling | doaj-art-ef89d5b176d84e8c94989df48c31db3c2025-08-20T02:53:22ZengMDPI AGActuators2076-08252024-12-01131251610.3390/act13120516A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load ConditionsQing Chang0Tiantian Yuan1Haifeng Li2Yuxiang Chen3Xuehao Wang4Sen Gao5Hongsheng Ren6Xiangyun Zhao7Lingyu Wang8School of Mechanical Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Mechanical Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Information Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Swanson Engineering, University of Pittsburgh, 4200 Fifth Avenue, Pittsburgh, PA 15260, USASchool of Mechanical Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Science, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Information Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Mechanical Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaSchool of Mechanical Engineering, Tianjin University of Commerce, No. 409 Guangrong Roud, Beichen District, Tianjin 300134, ChinaThe growing diversity and number of industrial robots make energy consumption prediction and optimization increasingly essential. Current data-driven approaches, particularly those based on multi-layer perception (MLP), have shown feasibility but typically overlook the variability or unknown nature of load-related parameters in real-world applications. This paper presents a KAN-LSTM model designed to accurately predict energy consumption under unknown load conditions, alongside a particle swarm optimization (PSO) algorithm for minimizing energy use. First, an industrial robot dynamics and energy consumption model is established. Then, the KAN-LSTM model is trained on datasets from the AUBO-E5 robot, with its predictions compared to alternative network models. Finally, PSO is applied to optimize energy consumption. Experimental results indicate that the KAN-LSTM model achieves high prediction accuracy (95.7–97.1%) and offers substantial energy optimization potential (53.1–64.7%). Optimized industrial robots are particularly suitable for tasks such as picking and palletizing in the courier industry, saving operational costs and increasing the sustainability of automated systems in logistics environments.https://www.mdpi.com/2076-0825/13/12/516industrial robotsenergy consumption predictionunknown load conditionsKAN-LSTM modelenergy consumption optimization |
| spellingShingle | Qing Chang Tiantian Yuan Haifeng Li Yuxiang Chen Xuehao Wang Sen Gao Hongsheng Ren Xiangyun Zhao Lingyu Wang A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions Actuators industrial robots energy consumption prediction unknown load conditions KAN-LSTM model energy consumption optimization |
| title | A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions |
| title_full | A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions |
| title_fullStr | A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions |
| title_full_unstemmed | A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions |
| title_short | A Data-Driven Method for Predicting and Optimizing Industrial Robot Energy Consumption Under Unknown Load Conditions |
| title_sort | data driven method for predicting and optimizing industrial robot energy consumption under unknown load conditions |
| topic | industrial robots energy consumption prediction unknown load conditions KAN-LSTM model energy consumption optimization |
| url | https://www.mdpi.com/2076-0825/13/12/516 |
| work_keys_str_mv | AT qingchang adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT tiantianyuan adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT haifengli adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT yuxiangchen adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT xuehaowang adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT sengao adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT hongshengren adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT xiangyunzhao adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT lingyuwang adatadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT qingchang datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT tiantianyuan datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT haifengli datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT yuxiangchen datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT xuehaowang datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT sengao datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT hongshengren datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT xiangyunzhao datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions AT lingyuwang datadrivenmethodforpredictingandoptimizingindustrialrobotenergyconsumptionunderunknownloadconditions |