Intelligent machine control

The study for predicting the velocity profiles in pultrusion by Gorthala et aL (1994) used a variable viscosity model. A comprehensive two-dimensional mathematical model in cylindrical coordinates was developed for resin flow, cure and heat transfer. A control-volume-based finite difference method (FDM) (Patankar method) was used for solving the governing equations. The use of artificial neural networks (ANNs) for pultrusion modelling in terms of the real process data and their potential for intelligent machine control was proposed by Wilcox and Wright (1998). Liu et al. (2000 Liu, 2001 Liu and Hillier, 1999) implemented a finite element/control volume... 

Bernhardt, A., et al., Rationalization of Molding Machine Intelligent Setting Control, SPE-IMD Newsletter, No. 54, Summer... 

MS is the heart of proteomic analysis and the success of proteomic experiments depends largely on the sensitivity and accuracy of MS equipment used to identify peptide sequences. MS machines have three main components (Figure 2) a source, which generates peptide ions, a mass analyzer, which separates peptide ions based on mass to charge ratio (m/z), and a detector that detects the ion resolved by the mass analyzer. All the modern MS machines are computer controlled and assisted by highly intelligent software. 

The components can be extended for machine learning based on cybernetics by reflecting the output from the component on the control input so that the component can adjust the functional behavior based on the result of the previous processing. This facility enables the component to learn from experience and dynamically adjust its behavior and thus improve the intelligence and dynamic adaptability of the software component as shown in the Figure 8.10. For example, a software component for de-identification of protected personal information to comply with the privacy laws in one country or a specific industry may need to be re-developed, as shown in the Figure 8.11, to address the specific requirements in other countries, since de-identification rules are subject to the statutory requirements in each country and to the institutional privacy policies. 

The controller This is the hardware element that has intelligence. It receives the information from the measuring devices and decides what action should be taken. The older controllers were of limited intelligence, could perform very simple operations, and could implement simple control laws. Today, with increasing use of digital computers as controllers, the available machine intelligence has expanded tremendously, and very complicated control laws can be implemented. 

Control Types (Force or Position Control). Force or position control strategies affect the machine intelligence requirements. Depending on the application, force or position control, or both, could be required. A position-controlled machine requires the least intelligence, and a machine with a combination of position and force control requires the most intelligence. Each of the solutions has merit in different applications. 

Friction shr welding typically requires more intelligence than machining. For example, force control may be needed for FSW. This means that the base machine must possess a controller with an open architecture if not. 

The retractable pin tool is essentially an FSW tool where the pin can retract up into the shoulder. This can be used in applications where the exit hole of the FSW process is not acceptable. In most situations, the exit hole is not an issue, because it is no worse than a start or stop in other welding processes. If the exit hole is a potential issue, it can often be placed in an area where it is not an issue. The retractable pin requires a more complex spindle, with the ability to shift the FSW tool pin with respect to the shoulder. Thus, it adds cost and complexity to the application and requires a machine with more intelligence capability (additional control). The retractable pin can be considered for circumferential applications where the exit hole may not be acceptable. An example of a retractable pin tool is shown in Fig. 11.8. 

In our postulation, how to automate machines in terms of operations will soon be a routine problem because of the technological maturity of actuators, sensors, and controllers. The application of automation technology will then focus on the issues of intelligence, integration, and autonomy. Another emerging trend involves the incorporation of micro-electromechanical systems (MEMSs) as sensors and controllers of automation and the microscale. However, education and training of workers who interact with intelligent and autonomous machines may be another important research issue in the future. 

Nonanalytic control is a technique that attempts to mimic the organization found in biological systems. Nonanalytic control considers the system operation as a block box. Heuristics or machine intelligence or both are used to determine the mappings between inputs and outputs of the specific system operation that are adequate for the implementation of nonanalytic external control (Figure 15.1c). 

---