Predictive maintenance software

User-friendly software and hardware The premise of predictive maintenance is that existing plant staff must be able to understand the operation of both the data logger and software program. Since plant staff normally have little, if any, computer or microprocessor background, the system must use simple, straightforward operation of both the data acquisition instrument and software. Complex... 

Accuracy Decisions on machine-train or plant system condition will be made based on the data acquired and reported by the predictive maintenance system. It must be accurate and repeatable. Errors can be input by the microprocessor and software as well as the operators. The accuracy of commercially available predictive maintenance system varies. While most will provide at least minimum acceptable accuracy, some are well below the acceptable level. 

Many of the predictive systems manufacturers are strictly hardware and software oriented. Therefore, they offer minimal training and no application training or technical support. Few plants can achieve minimum benefits from predictive maintenance without training and some degree of technical support. It is therefore imperative that the selected system or system vendors provide a comprehensive support package that includes both training and technical support. 

The software program provided with each predictive maintenance system is the heart of a successful program. It is also the hardest to evaluate before purchase. The methodology used by vendors of predictive maintenance systems varies greatly. Many appear to have all of the capabilities required to meet the demands of a total plant predictive maintenance program. However on close inspection, usually after purchase, they are found to be lacking. 

Kraft, J., Kienle, H. M., Nolte, T., Cmkovic, 1. Hansson, H. (2011). Software maintenance research in the PROGRESS project for predictable embedded software systems, 15th LEEE European Conference on Software Maintenance and Reengineering (CSMR 2011) pp. 335-338. 

Cyclops PPM and Cyclops PPM+ ER Hand-held units for predictive maintenance applications, featuring uncooled 320 x 240 or 160 x 120 element BST FPA detectors, 7-14 pm extensive diagnostic software. 

The positioner can be programmed to carry out partial closure testing sequences at frequent intervals to verify that the valve mechanism is stroking correctly with the correct time/travel response. It can also measure the friction load in the actuator and with the aid of supporting software this can be used to predict maintenance needs. 

This information is compiled and, through either software or statistical analysis, the condition of the equipment can be established at a point in time or a prediction of when equipment maintenance should be performed (in terms of frequency or run time) can be made. 

There are three basic maintenance requirements for computers hardware maintenance, operating system maintenance, and software maintenance. Each of these areas will be addressed individually. The modem microcomputer has an effective life span of about 10 yr. Capacitors drift over time. It takes about 10 yr for critical capacitors to lose enough of their capacitance to adversely affect the rehabiUty of the machine. Computers older than 8 yr are Uving on borrowed time. Other critical components also fail with time (microprocessor, chipset, etc). While the actual life of these components cannot be accurately predicted, the incidence of failure increases very rapidly after 10 yr. 

The RWO initiative was driven in part by the need to upgrade or replace software applications that were not Y2K compliant. In addition, the project reduced application maintenance costs because the same software versions are used throughout the plant, and because modem control and optimization software is more user-fiiendly than it was in the 1980s, when Suncor first began implementing model-predictive control and online optimization. 

Software diversity has been advocated as a means of improving the reliability of safety related software and in particular safety systems that react to a demand, where a 1 out of 2 or a 2 out of 3 voting scheme can be used to ensure that some safety action is performed. This approach is used in industry (e.g. for railway interlocking), but development and maintenance is costlier than for a non-diverse system and it is not easy to predict in advance the likely safety improvement that can be achieved. 

---