Technical failures in machines are major sources of unplanned downtime in any production and result in reduced efficiency and system reliability. Despite the well-established potential of Machine Learning techniques in condition-based maintenance (CBM), the lack of access to failure data in production machines has limited the development of a holistic approach to address machine-level CBM. This paper presents a practical approach for failure mode prediction using multiple sensors installed in a bearing ring grinder for process control as well as condition monitoring. Bearing rings are produced in a set of 7 experimental runs, including 5 frequently occurring production failures in the critical subsystems. An advanced data acquisition setup, implemented for CBM in the grinder, is used to capture information about each individual grinding cycle. The dataset is pre-processed and segmented into grinding cycle stages before time and frequency domain feature extraction. A sensor ranking algorithm is proposed to optimize feature selection for failure classification and the installation cost. Random forest models, benchmarked as best performing classifiers, are trained in a two-step classification framework. The presence of failure mode is predicted in the first step and the failure mode type is identified in the second step using the same feature set. Defining the feature set in the failure detection step improves the predictor generalization with the classifiers’ performance accuracy of $$99\%$$99% on the test dataset. The presented approach demonstrates an efficient failure mode classification by selecting crucial sensors resulting in a cost-effective CBM implementation in a bearing ring grinder.

Grinding processes’ stochastic nature poses a challenge in predicting the quality of the resulting surfaces. Post-production measurements for form, surface roughness, and circumferential waviness are commonly performed due to infeasibility in measuring all quality parameters during the grinding operation. Therefore, it is challenging to diagnose the root cause of quality deviations in real-time resulting from variations in the machine’s operating condition. This paper introduces a novel approach to predict the overall quality of the individual parts. The grinder is equipped with sensors to implement condition-based maintenance and is induced with five frequently occurring failure conditions for the experimental test runs. The crucial quality parameters are measured for the produced parts. Fuzzy c-means $\left(FCM\right)$ and Hotelling’s T-squared $\left(T^2\right)$ have been evaluated to generate quality labels from the multi-variate quality data. Benchmarked random forest regression models are trained using fault diagnosis feature set and quality labels. Quality labels from the $T^2$ statistic of quality parameters are preferred over $FCM$ approach for their repeatability. The model, trained from $T^2$ labels achieves more than $94\%$ accuracy when compared to the measured ring disposition. The predicted overall quality using the sensors’ feature set is compared against the threshold to reach a trustworthy maintenance decision.

Grinding processes’ stochastic nature poses a challenge in predicting the quality of the resulting surfaces. Post-production measurements for form, surface roughness, and circumferential waviness are commonly performed due to infeasibility in measuring all quality parameters during the grinding operation. Therefore, it is challenging to diagnose the root cause of quality deviations in real-time resulting from variations in the machine’s operating condition. This paper introduces a novel approach to predicting the overall quality of the individual parts. The grinder is equipped with sensors to implement condition-based maintenance and is induced with five frequently occurring failure conditions for the experimental test runs. The crucial quality parameters are measured for the produced parts. Fuzzy c-means (FCM) and Hotelling’s T-squared (T2) have been evaluated to generate quality labels from the multi-variate quality data. Benchmarked random forest regression models are trained using fault diagnosis feature set and quality labels. Quality labels from the T2 statistic of quality parameters are preferred over FCM approach for their repeatability. The model, trained from T2 labels achieves more than 94% accuracy when compared to the measured ring disposition. The predicted overall quality using the sensors’ feature set is compared against the threshold to reach a trustworthy maintenance decision.

Technical failures in machines are major sources of unplanned downtime in any production and result in reduced efficiency and system reliability. Despite the well established potential of Machine Learning techniques in condition-based maintenance (CBM), the lack of access to failure data in production machines has limited the development of a holistic approach to address machine-level CBM. This paper presents a practical approach for failure mode prediction using multiple sensors installed in a bearing ring grinder for process control as well as condition monitoring. Bearing rings are produced in a set of 7 experimental runs, including 5 frequently occurring production failures in the critical subsystems. An advanced data acquisition setup, implemented for CBM in the grinder, is used to capture information about each individual grinding cycle. The dataset_* is pre-processed and segmented into grinding cycle stages before time and frequency domain feature extraction. A sensor ranking algorithm is proposed to optimize feature selection for failure classification and the installation cost. Random forest models, bench-marked as best performing classifiers, are trained in a two-step classification framework. The presence of failure mode is predicted in the first step and the failure mode type is identified in the second step using the same feature set. Defining the feature set in the failure detection step improves the predictor generalization with the classifiers' performance accuracy of 99% on the test dataset. The presented approach demonstrates an efficient failure mode classification by selecting crucial sensors resulting in a cost effective CBM implementation in a bearing ring grinder

Grinding is a process that still today largely depends on the skill and experience of the operator. For grinding, no generalized computer-aided manufacturing tool exists as for milling, and the grinding machine manufacturers have their proprietary process planning tools for the path planning. The success of a grinding process furthermore depends on a suitable conditioning of the grinding wheel and not only on the appropriate selection of the process parameters. Skilled operators are, on the one hand, capable of setting up the process in shorter time than their less skilled colleagues and with immediate success. Artificial intelligence, driven by sufficiently increased computational performance, is increasingly capable of handling manufacturing processes, particularly as these processes become more complicated and experience-based. Therefore, extending the machine’s ability towards what today is the task of the operator, namely process planning feeding the vision of “operator integrated” is a breakthrough in zero defect manufacturing and first part right for grinding processes. The paper conceptualizes an intelligent grinding machine that uses ontologies, applies rule-based planning tools, makes use of physical as well as autonomous modeling, and is capable of learning. Moreover, the processes of grinding and dressing are fully monitored so that a self-learning ability is provided. Learning is fed from different sources, from monitoring, from other machines requiring filters built on physical models, and from the operator with the ability to deal with incomplete, unstructured, and unreliable data. From this the way, how such a machine communicates with operators must be completely different than today. Research results and literature are provided to discuss the different aspects like machine state monitoring, process monitoring, and parameter selection for an optimized grinding process.