Using Sensory Tool Holder Data for Optimizing Production Processes

In many discourses, popular as well as scientific, it is suggested that the "massive" use of Artificial Intelligence (AI), including Machine Learning (ML), and reaching the point of "singularity" through so-called Artificial General Intelligence (AGI), and Artificial Super-Intelligence (ASI), will completely exclude humans from decision making, resulting in total dominance of machines over human race. Speaking in terms of manufacturing systems, it would mean that the intelligence and total automation would be achieved (once the humans are excluded). The hypothesis presented in this paper is that there is a limit of AI/ML autonomy capacity, and more concretely, the ML algorithms will be not able to become totally autonomous and, consequently, the human role will be indispensable. In the context of the question, the authors of this paper introduce the notion of the manufacturing singularity and present an intelligent machine architecture towards the manufacturing singularity, arguing that the intelligent machine will always be human dependent. In addition, concerning the manufacturing, the human will remain in the centre of Cyber-Physical Systems (CPS) and in Industry 4.0. The methodology to support this argument is inductive, similarly to the methodology applied in a number of texts found in literature, and based on computational requirements of inductive inference based machine learning. The argumentation is supported by several experiments that demonstrate the role of human within the process of machine learning. Based on the exposed considerations, a generic architecture of intelligent CPS, with embedded ML functional modules in multiple learning loops, is proposed in order to evaluate way of use of ML functionality in the context of CPS. Similar to other papers found in literature, due to the (informal) inductive methodology applied, considering that this methodology does not provide an absolute proof in favour of, or against, the hypothesis defined, the paper represents a kind of position paper. The paper is divided into two parts. In the first part a review of argumentation from literature in favour of and against the thesis on the human role in future was presented, as well as the concept of the manufacturing singularity was introduced. Furthermore, an intelligent machine architecture towards the manufacturing singularity was proposed, arguing that the intelligent machine will be always human dependent _____________

Section: On Readiness Of the Present Technologies And Knowledge To Upgrade Manufacturing Systems To I N -Cpsmentioning

confidence: 99%

Machine Learning in Cyber-Physical Systems and Manufacturing Singularity – It Does Not Mean Total Automation, Human is Still in the Centre: Part II – In-CPS and a View from Community on Industry 4.0 Impact on Society

Putnik¹,

Shah²,

Putnik³

et al. 2021

“…A fast response and a specific adaption of the process are required for a feedback loop, so that a control system can cover stochastic process effects. The instrumented tool holder has been proven capable of chatter detection and mitigation [85,86], as well as cutting edge chipping detection [87]. In the case, that a process is classified to be unstable, an automated adaption of spindle speed and feed rate can be applied in the real-time control loop.…”

Section: Heavy Duty Millingmentioning

confidence: 99%

Tooling systems with integrated sensors enabling data based process optimization

Bleicher¹,

Ramsauer²,

Leonhartsberger³

et al. 2021

Self Cite

Sensor integration into machining equipment has become an important factor for gaining deep process insights mainly driven by increasingly smaller and cheaper sensors and transmitters. Due to advances in microelectronics and communication technology, a broader field of applications in production processes and machine tools can be addressed using sensing devices and their implementation potentials. Ensuring a sensitive but robust data stream from close to the actual process allows not only reliable monitoring but also process and quality control based on sensor information. This paper provides an overview of the utilization of sensor data for the purpose of condition monitoring, model fitting and real-time control coping with stochastic effects. Examples of sensor integration in fields of injection molding, roll forming and heavy-duty milling comprise the state of the art of sensor implementation, data evaluation and possible feedback loops in the respective application scenarios.

“…This modified tool holder detects vibration very close to the cutting zone with little influence by the machine's characteristics or the position within the working area. Furthermore, not only online _____________ 1 FT -Institute for Production Engineering and Photonic Technologies, TU Wien, Austria * E-mail: ramsauer@ift.at http://doi.org/10.36897/jme/131918 measurement but also setting countermeasures by adapting cutting parameters or sending feedback to higher level monitoring systems is possible [5]. This system's most prominent applications are drilling and milling operations, especially, for chatter detection and its very successful prevention [6,7].…”

Section: Introductionmentioning

confidence: 99%

“…−̈](5) where: m -vibratory mass, [Δx, Δy, Δz] Tdynamic position vector and its derivatives in time, [xA, yA, zA] Tposition vector of excitation of point A and its derivatives in time written in machine's frame of reference, [x0, y0, z0] Tstatic position vector, ttime, ωSprotational speed of spindle, kx,y,zlinear spring coefficients in the corresponding direction, cx,y,zlinear damping coefficients in the corresponding direction.…”

mentioning

confidence: 99%

New method for determining single cutting edge breakage of a multi-tooth milling tool based on acceleration measurements by an instrumented tool holder

Ramsauer¹,

Bleicher²

2021

Self Cite

In machining applications predominantly for automated machining cells, tool life is often not used to its full extend and cutting tools are exchanged prematurely to avoid tool breakage and thus machine downtime or even damage at work piece or machine. Both effective process monitoring and adequate process control require reliable data from sensors and derived indicators that enable meaningful evaluation. Acceleration measurement by the instrumented tool holder provides signals with high quality from close to the cutting zone. Using the monitoring system, the gained data of the instrumented tool holder can be analyzed especially for the use case of unexpected tool wear, chipping of the cutting edge or breakouts at end mills. This paper describes the data analysis based on the rotational sensor and the corresponding effects on the measurement, an advanced assessment of the spectral distribution in the frequency domain and the experimental results of a test series.