登录查看更多内容

How can you collect data for statistical process control?

由人工智能和领英社区提供技术支持

Statistical process control (SPC) is a method of monitoring and improving the quality of a process by using data and statistical tools. SPC can help you identify and reduce variation, prevent defects, and optimize performance. To apply SPC, you need to collect data that reflects the characteristics and outcomes of your process. How can you collect data for statistical process control? Here are some steps to follow.

此文章中的业界达人

由社区从 4 条内容中精选。了解更多

Carlos Goribar

Quality Engineer II at Nordson Medical Tecate
Amar Kulkarni

PolyWorks Evangelist | Empowering Manufacturing with 3D Metrology

1 Define your purpose

Before you start collecting data, you need to have a clear purpose and objective for your SPC project. What are you trying to measure, control, or improve? What are the key quality indicators or specifications of your process? How will you use the data to make decisions and take actions? Having a well-defined purpose will help you plan and execute your data collection effectively and efficiently.

添加您的观点

Carlos Goribar

Quality Engineer II at Nordson Medical Tecate
举报内容
Although SPC has been around since 1920s (created by Walter A. Shewhart and later popularized by Ed. Deming) the level of misunderstanding of the tool is outstanding. First of all, SPC was a tool developed for the understanding of process variation and its subsequently stabilization. This enables improvement. Comprenhension of variation->Process stabilization->process improvement. Keep it in mind when you define the purpose.

已翻译

赞

2 Choose your variables

Next, you need to choose the variables that you want to collect data on. Variables are the factors that affect or reflect the quality of your process. They can be classified into two types: input and output variables. Input variables are the inputs or resources that you use in your process, such as materials, equipment, or methods. Output variables are the outputs or results that you produce from your process, such as products, services, or customer satisfaction. You should select the variables that are relevant, measurable, and controllable for your purpose.

添加您的观点

Carlos Goribar

Quality Engineer II at Nordson Medical Tecate
(已编辑)
举报内容
In my experience at several companies, when SPC is implemented, engineers tend to measure the output variables; however, input variables should be preferred to control over outputs. This is especially true for processes with intrinsic time delay such as baking. By the time the outcome is measured, it may be too late, and remember SPC is essentially a preventative tool. Companies typically do not measure input variables, so it can be difficult at the beginning of implementation. Another recommendation is to take into account that the variables to be measured must be relevant to the process. The design of experiments (DOE) is the appropriate tool for this.

已翻译

赞

3 Design your data collection plan

Once you have chosen your variables, you need to design your data collection plan. This involves deciding how, when, where, and by whom you will collect the data. You should consider the type of data, the source of data, the frequency of data collection, and the sample size of the data. Depending on your data type, you may need different tools and techniques to collect and record your data. Primary data sources are those that you collect directly from your process, while secondary sources are those obtained indirectly from other sources. The frequency of data collection can be continuous or discrete; choose one that is appropriate, feasible, and consistent for your purpose. Additionally, choose a sample size that is representative, sufficient, and random for your purpose. Reporting and documenting the incident will help you inform and reassure the stakeholders, as well as provide valuable insights for improving your cloud security posture.

添加您的观点

4 Collect your data

After you have designed your data collection plan, you need to execute it and collect your data. You should follow the plan as closely as possible and use the tools and techniques that you have selected. You should also ensure that your data collection is accurate, consistent, and unbiased. You should avoid any errors, mistakes, or variations that could affect the quality and validity of your data. You should also document and record your data in an organized and clear manner. You can use different formats and methods to document and record your data, such as forms, charts, tables, or software.

添加您的观点

5 Analyze your data

Finally, you need to analyze your data and use it for your SPC project. You should apply the appropriate statistical tools and methods to your data and interpret the results. You should look for patterns, trends, relationships, or anomalies in your data that could indicate the performance and variation of your process. You should also compare your data to your quality indicators or specifications and identify any gaps or deviations. You should use your data analysis to draw conclusions, make recommendations, or take actions to improve your process quality.

添加您的观点

6 Here’s what else to consider

This is a space to share examples, stories, or insights that don’t fit into any of the previous sections. What else would you like to add?

添加您的观点

Amar Kulkarni

PolyWorks Evangelist | Empowering Manufacturing with 3D Metrology
举报内容
How much would you depend on software or AI to give you results of your SPC analysis? Would you prefer to still conduct manual analysis? Also, I am curious to know, are there different levels of SPC analysis that manufacturing companies do? For eg the QC Metrologist does different SPC compared to a Production Engg or Pre-production Engg lead? If so, what would be the difference?

已翻译

赞
Aqtedar Atwar mehdi Rizvi

Technical Inspector Sr.Lic.AME
举报内容
Yes, careful analysis of data will surely result in getting amicable solutions to do away with the recurring issues, from beginning the companies should implement this policy of capturing each n every task not after audits or after some incidents,but the problem with companies are due to cost cutting bug they tend to sacrifice safety & other progressive trends,to capture and analyse data into proper program implementation it requires correct manpower and systems,today all companies want to adopt best of the IT systems program but they bother least about the quality and consistency of staff to work on programs ,the same will affect yeilds. HR has to do away with their mentality of employ people without considering experience & qlty resources

已翻译

赞

Quality Management

+ 关注

给文章评分

我们借助人工智能创建了此文章。您认为这篇文章怎么样？

很棒不太好

举报此文章

查看全部

How can you collect data for statistical process control?

1

2

3

4

5

6

1 Define your purpose

2 Choose your variables

3 Design your data collection plan

4 Collect your data

5 Analyze your data

6 Here’s what else to consider

Quality Management

给文章评分

感谢您的反馈

更多Quality Management相关文章

更多相关阅读内容

How can you collect data for statistical process control?

1

2

3

4

5

6

1 Define your purpose

2 Choose your variables

3 Design your data collection plan

4 Collect your data

5 Analyze your data

6 Here’s what else to consider

Quality Management

给文章评分

感谢您的反馈

查看其他技能