How the hottest Er uses JMP for reliability reliab

  • Detail

How Er uses JMP for reliability analysis

reliability is a problem in every link of product design, manufacturing and use. Simply put, the so-called reliability is the degree to which a product is not prone to failure. As we all know, products are usually qualified in the delivery inspection, but with the passage of time, the function and performance of products will gradually change, eventually leading to the occurrence of faults. Although this trend cannot be changed, designing and manufacturing products that do not fail within a specified time is a topic of concern for both enterprises and consumers. From the frequent communication failures of us fighter planes in the early days of World War II to the quality problems of a brand of notebook computers repeatedly exposed during March 15 this year, the essence is that the product reliability is not good. The rational application of reliability analysis can help technicians in R & D, engineering, quality and other departments improve the stability of product quality, reduce the cost of product life cycle and after-sales service, and improve customer satisfaction and loyalty

it is puzzling that many enterprises have realized the importance of reliability analysis, but still deliberately avoid reliability analysis. Why? There are many reasons. One of the main reasons is that the general enterprises feel that the conventional statistical quality management is complex enough, and the reliability research still needs to use a lot of more advanced statistical knowledge, which will be daunting for those who have not been trained in formal statistical methods, which objectively greatly limits the promotion of reliability methods in enterprises

the author has tried to use different software for reliability analysis. Let's learn that 1. The high-end Six Sigma software JMP (trial version can be downloaded) of SAS company with standard configuration is one of them, and its interactive visual analysis feature is also well reflected in reliability. The following is a typical example to see how to use JMP for reliability analysis

example: in order to analyze the reliability of an electronic product, a company collected a batch of service life data of the product. In the future, wet coated diaphragms will gradually become the mainstream data (as shown in Figure 1, when "deletion" =0, it means that "time" is the exact failure time; when "deletion" =1, it means that the exact failure time is unknown, but it must be greater than the value shown in "time"). With this set of representative data, let's study the failure characteristics of the product? When the failure probability is 90%, what is the reliable life of the product

figure I original data table of reliability test (part)

according to the theory of reliability method, to solve these two problems, we need to first solve a basic problem: what distribution does this group of life data obey? In fact, this is not an easy problem to solve. We have to try, compare and verify one by one. There are at least a dozen kinds of Weibull distribution, lognormal distribution, exponential distribution, etc. However, the general quality engineer is dizzy when he hears these professional statistical terms, and the judgment is more complicated because the life data contains the "deletion" feature, which usually needs to be judged through a series of lengthy statistical analysis reports and statistical indicators

when using JMP software for analysis, the author found that there is a command called "fit all distributions" in JMP, which can fit all conventional reliability distributions one by one in a few seconds, and then automatically select the best distribution fitting. For example, in the figure below, "lognormal" distribution is the best distribution found by JMP after quickly comparing all life distributions. If you don't understand the principles of statistics and just want to see what the distribution looks like intuitively, look at the red curve on the graph and the pink confidence interval around it; If you have a good understanding of statistical principles and want to have an in-depth understanding of statistical criteria, you can also look at the relevant indicators in the "model fitting" table below. In short, we can take what we need and complete the most basic task of distribution model identification

the visualization of the comparison of reliability distribution models in Figure 2, coupled with the problem of global shortage of resources, shows

in addition, while obtaining the best fitting distribution, various reliability characteristics related to the product quality (such as reliability life, failure probability, failure probability density, failure rate, etc.) can also be represented graphically. For example, in the figure below, "distribution descriptor" and "quantile descriptor" both show the relationship between failure probability and product life (the main difference between the two is that the variables represented by x-axis and y-axis are just the opposite), The "hazard rate profiler" shows the law that the hazard rate (commonly known as hazard rate) changes with the change of product life (which can be used to realize the most famous "bathtub curve" in reliability theory). The "density profiler" shows the law that the failure probability density changes with the change of product life

Figure 3. The descriptors of main characteristic variables in reliability analysis

these figures can be used to vividly explain the first question "what are the failure characteristics of the product?" Yes. Now let's answer the second question, "when the failure probability is 90%, what is the reliable life of the product?" By inputting "0.9" on the X axis of the "quantile marker", the red value "412.0117" and the blue value "[278.675609.146] can be obtained on the Y axis, indicating that the reliable life should be 412.0117 and the confidence interval should be [278.675609.146]

there are many contents about reliability analysis, such as accelerated life analysis, regression analysis of life data, maintainability analysis, etc. (end)

Copyright © 2011 JIN SHI