Basic SPC For Operators Part 1
TUV德国莱茵技术六西格码培训资料BasicStatisticsforSPC
N -1
SPC
分布的位置 Location Mean 均值 Median 中值 Mode 代表值 Quantiles 分位数
Q1 四分之一处 Q2 二分之一处 Q3 四分之三处 P＃％ 机率位置
数据的描述总览
Numercial Graphical
离散度 Spread Range 范围 Standard Deviation 标准偏差 Variance 变差 Stability Factor 稳定因子 Span 跨度 Interquartile Range 内分位宽度 Sum of Squares 平方和
Shape 形状 Histograms 直方图 Run Charts 运行图 Time Plots 时序图 Scatter Plots 散点图 Box Plots 盒状图 Block Chart 块图 Normality Plot 正态性图
Normal Distribution正态分布
fx(x)=
Mean均值
e 1
2ps2
-(x-)2/2s2
Bell-shape Symmetric Distribution
‘倒钟’状对称分布
s
2s s
s 2s
s
Measured by Standard Deviation 用标准偏差为尺度
mean
68.27 %
s
总体标准偏差
Sample Statistics
Estimate
Parameters
Population
统计活动的实质：用样本统计值来估计总体参数，从而了解总体
SPC
Population vs. sample 总体和样本计算公式
Population Mean 总体均值
Basic SPC
Statistical process controlStatistical process control (SPC) is a method of quality control which uses statistical methods. SPC is applied in order to monitor and control a process. Monitoring and controlling the process ensures that it operates at its full potential. At its full potential, the process can make as much conforming product as possible with a minimum (if not an elimination) of waste (rework or Scrap). SPC can be applied to any process where the "conforming product" (product meeting specifications) output can be measured. Key tools used in SPC include control charts; a focus on continuous improvement; and the design of experiments. An example of a process where SPC is applied is manufacturing lines.OverviewObjective analysis of variationSPC must be practiced in 2 phases: The first phase is the initial establishment of the process, and the second phase is the regular production use of the process. In the second phase, we need to decide the period to be examined, depending upon the change in 4-M conditions and wear rate of parts used in the manufacturing process (machine parts, Jigs and fixture and tooling standard). Emphasis on early detectionAn advantage of SPC over other methods of quality control, such as "inspection", is that it emphasizes early detection and prevention of problems, rather than the correction of problems after they have occurred.Increasing rate of productionIn addition to reducing waste, SPC can lead to a reduction in the time required to produce the product. SPC makes it less likely the finished product will need to be reworked. SPC may also identify bottlenecks, waiting times, and other sources of delays within the process. LimitationsSPC is applied to reduce or eliminate process waste. This, in turn, eliminates the need for the process step of post-manufacture inspection. The success of SPC relies not only on the skill with which it is applied, but also on how suitable or amenable the process is to SPC. In some cases, it may be difficult to judge when the application of SPC is appropriate.Variation in manufacturingNo two products or characteristics are exactly same, because any process contains many sources of variability. In mass-manufacturing, traditionally, the quality of a finished article is ensured bypost-manufacturing inspection of the product. Each article (or a sample of articles from a production lot) may be accepted or rejected according to how well it meets its design specifications. In contrast, SPC uses statistical tools to observe the performance of the production process in order to detect significant variations before they result in the production of a sub-standard article. Any source of variation at any point of time in a process will fall into one of two classes.1) "Common Causes" - sometimes referred to as nonassignable, normal sources of variation. Itrefers to many sources of variation that consistently acts on process. These types of causesproduces a stable and repeatable distribution over time.2) "Special Causes" - sometimes referred to as assignable sources of variation. It refers to anyfactor causing variation that affects only some of the process output. They are oftenintermittent and unpredictable.Most processes have many sources of variation; most of them are minor and may be ignored. If the dominant sources of variation are identified, however, resources for change can be focused on them. If the dominant assignable sources of variation is detected, potentially they can be identified and removed. Once removed, the process is said to be "stable". When a process is stable, its variation should remain within a known set of limits. That is, at least, until another assignable source of variation occurs. For example, a breakfast cereal packaging line may be designed to fill each cereal box with 500 grams of cereal. Some boxes will have slightly more than 500 grams, and some will have slightly less. When the package weights are measured, the data will demonstrate a distribution of net weights. If the production process, its inputs, or its environment (for example, the machines on the line) change, the distribution of the data will change. For example, as the cams and pulleys of the machinery wear, the cereal filling machine may put more than the specified amount of cereal into each box. Although this might benefit the customer, from the manufacturer's point of view, this is wasteful and increases the cost of production. If the manufacturer finds the change and its source in a timely manner, the change can be corrected (for example, the cams and pulleys replaced).Application of SPCThe application of SPC involves three main sets of activities:1. The first is understanding of the process and the specification limits.2. The second is eliminating assignable (special) sources of variation, so that the process is stable.3. The third is monitoring the ongoing production process, assisted by the use of control charts, to detect significant changes of mean or variation.Control chartsThe data from measurements of variations at points on the process map is monitored using control charts. Control charts attempt to differentiate "assignable" ("special") sources of variation from "common" sources. "Common" sources, because they are an expected part of the process,are of much less concern to the manufacturer than "assignable" sources. Using control charts is a continuous activity, ongoing over time.Stable processWhen the process does not trigger any of the control chart "detection rules" for the control chart, it is said to be "stable". A process capability analysis may be performed on a stable process to predict the ability of the process to produce "conforming product" in the future.Excessive variationWhen the process triggers any of the control chart "detection rules", (or alternatively, the process capability is low), other activities may be performed to identify the source of the excessive variation. The tools used in these extra activities include: Ishikawa diagrams, designed experiments, and Pareto charts. Designed experiments are a means of objectively quantifying the relative importance (strength) of sources of variation. Once the sources of variation have been quantified, actions may be taken to reduce or eliminate them. Methods of eliminating a source of variation might include: development of standards; staff training; error-proofing and changes to the process itself or its inputs.Process capability indexIn process improvement efforts, the process capability index or process capability ratio is a statistical measure of process capability: the ability of a process to produce output within specification limits.1] The concept of process capability only holds meaning for processes that are in a state of statistical control. Process capability indices measure how much "natural variation" a process experiences relative to its specification limits and allows different processes to be compared with respect to how well an organization controls them.If the upper and lower specification limits of the process are USL and LSL, the target process mean is T, the estimated mean of the process is and the estimated variability of the process (expressed as a standard deviation) is , then commonly accepted process capability indices include:Index DescriptionEstimates what the process is capable of producingif the process mean were to be centered between thespecification limits. Assumes process output isapproximately normally distributed.Estimates process capability for specifications thatconsist of a lower limit only (for example, strength).Assumes process output is approximately normallydistributed.Estimates process capability for specifications thatconsist of an upper limit only (for example,concentration). Assumes process output isapproximately normally distributed.Estimates what the process is capable of producing,considering that the process mean may not becentered between the specification limits. (If theprocess mean is not centered, overestimatesprocess capability.) if the process meanfalls outside of the specification limits. Assumesprocess output is approximately normallydistributed.Estimates process capability around a target, T.is always greater than zero. Assumes processoutput is approximately normally distributed.is also known as the Taguchi capability index.[2]Estimates process capability around a target, T, andaccounts for an off-center process mean. Assumesprocess output is approximately normallydistributed.is estimated using the sample standard deviation.Recommended valuesProcess capability indices are constructed to express more desirable capability with increasingly higher values. Values near or below zero indicate processes operating off target ( far from T) or with high variation.Fixing values for minimum "acceptable" process capability targets is a matter of personal opinion, and what consensus exists varies by industry, facility, and the process under consideration. For example, in the automotive industry, the Automotive Industry Action Group sets forth guidelines in the Production Part Approval Process, 4th edition for recommended C pk minimum values for critical-to-quality process characteristics. However, these criteria are debatable and several processes may not be evaluated for capability just because they have not properly been assessed.Since the process capability is a function of the specification, the Process Capability Index is only as good as the specification . For instance, if the specification came from an engineering guideline without considering the function and criticality of the part, a discussion around process capability is useless, and would have more benefits if focused on what are the real risks ofhaving a part borderline out of specification. The loss function of Taguchi better illustrates this concept.At least one academic expert recommends[3] the following:Situation Recommended minimum processcapability for two-sidedspecificationsRecommended minimum processcapability for one-sidedspecificationExisting process 1.33 1.25New process 1.50 1.45Safety or criticalparameter for existingprocess1.50 1.45Safety or criticalparameter for newprocess1.67 1.60Six Sigma qualityprocess2.00 2.00It should be noted though that where a process produces a characteristic with a capability index greater than 2.5, the unnecessary precision may be expensive.[4]Relationship to measures of process falloutThe mapping from process capability indices, such as C pk, to measures of process fallout is straightforward. Process fallout quantifies how many defects a process produces and is measured by DPMO or PPM. Process yield is, of course, the complement of process fallout and is approximately equal to the area under the probability density functionif the process output is approximately normally distributed.In the short term ("short sigma"), the relationships are:C pkSigmalevel (σ)Area under the probabilitydensity functionProcess yieldProcess fallout (in terms ofDPMO/PPM)0.33 1 0.6826894921 68.27% 3173110.67 2 0.9544997361 95.45% 455001.00 3 0.9973002039 99.73% 2700 1.33 4 0.9999366575 99.99% 631.67 5 0.9999994267 99.9999% 12.00 6 0.9999999980 99.9999998% 0.002In the long term, processes can shift or drift significantly (most control charts are only sensitive to changes of 1.5σ or greater in process output), so process capability indices are not applicable as they require statistical control.ExampleConsider a quality characteristic with target of 100.00 μm and upper and lower specification limits of 106.00 μm and 94.00 μm respectively. If, after carefully monitoring the process f or a while, it appears that the process is in control and producing output predictably (as depicted in the run chart below), we can meaningfully estimate its mean and standard deviation.If and are estimated to be 98.94 μm and 1.03 μm, respectively, th enIndexThe fact that the process is running off-center (about 1σ below its target) is reflected in the markedly different values for C p, C pk, C pm, and C pkm.Process performance indexIn process improvement efforts, the process performance index is an estimate of the process capability of a process during its initial set-up, before it has been brought into a state of statistical control.Formally, if the upper and lower specifications of the process are USL and LSL, the estimated mean of the process is , and the estimated variability of the process (expressed as a standard deviation) is , then the process performance index is defined as:is estimated using the sample standard deviation. P pk may be negative if the process mean falls outside the specification limits (because the process is producing a large proportion of defective output).Some specifications may only be one sided (for example, strength). For specifications that only have a lower limit, ; for those that only have an upper limit,.Practitioners may also encounter , a metric that does not account for process performance that is not exactly centered between the specification limits, and therefore is interpreted as what the process would be capable of achieving if it could be centered and stabilized.InterpretationLarger values of P pk may be interpreted to indicate that a process is more capable of producing output within the specification limits, though this interpretation is controversial. Strictly speaking, from a statistical standpoint, P pk is meaningless if the process under study is not in control because one cannot reliably estimate the process underlying probability distribution, let alone parameters like and . Furthermore, using this metric of past process performance to predict future performance is highly suspect.From a management standpoint, when an organization is under pressure to set up a new process quickly and economically, P pk is a convenient metric to gauge how set-up is progressing (increasing P pk being interpreted as "the process capability is improving"). The risk is that P pk is taken to mean a process is ready for production before all the kinks have been worked out of it. Once a process is put into a state of statistical control, process capability is described using process capability indices, which are formulaically identical to P pk (and P p). The indices are named differently to call attention to whether the process under study is believed to be in control or not.ExampleConsider a quality characteristic with target of 100.00 μm and upper and lower specification limits of 106.00 μm and 94.00 μm respectively. If, after carefully monitoring the process f or a while, it appears that the process is out of control and producing output unpredictably (as depicted in the run chart below), we can't meaningfully estimate its mean and standard deviation. In the example below, the process mean appears to drift upward, settle for a while, and then drift downward.If and are estimated to be 99.61 μm and 1.84 μm, respectively, thenIndexThe fact that the process mean appears to be unstable is reflected in the relatively low values for P p and P pk. The process is producing a significant number of defectives, and, until the cause of the unstable process mean is identified and eliminated, we really can't meaningfully quantify how this process will perform.。
操作员工SPC基础知识培训
轮胎压力
蛋糕重量
油的粘度
温度
士兵身高
齿轮节圆直径
7
数学家发现正态曲线是以平均值为中心两边对称的曲线。
该曲线被分成6个等分截面。 一个截面被称为一个标准偏差（Sigma）—— Standard Deviation
8
• 大约68%的数据位于中心线两侧1个标准差范围内； • 大约95%的数据位于中心线两侧2个标准差范围内； • 大约99%的数据位于中心线两侧3个标准差范围内。
• 它有可能是客户要求。 •它也可以是内部过程控制的要求。 • 为监测趋势提供一种方法。
14
关键质量特性
• 客户知道什么是重要的。 ——关键质量特性最影响客户满意度。
在OCP上的这些符号◆ ◇，表示这是一个关键质量特性 需要过统计过程控制，即用SPC控制图来监测该尺寸。
15
Interpretation of SPC Chart SPC控制图的理解
SPC Basic Training
1
什么是SPC?
为什么我们需要并使用SPC?
如何有效地执行好SPC?
2
Statistical Process Control (SPC) 统计过程控制
SPC意思是统计过程控制，利用统计的方法来监控过程的状态，确定生产过程 在管制的状态下，以降低产品品质的变异。通过问题分析找出特殊（异常）原 因，采取 改善措施，使过程恢复正常。并借助过程能力分析与标准化，以不断 提升过程 能力 • 控制图是1924年美国品管大师瓦尔特·休哈特在西屋电器公司发明。 • 识别“普通原因变异性（随机）”与“特殊原因变异性（可转变）”。
32
在数据输入界面 双击超差的点
然后点击“注解” 按钮
SPC-basic
背景介绍
SPC是美国休哈特博士在本世纪二十年代所创造的理论。自创立以 SPC 来，即在工业和服务等行业得到广泛应用。
自五十年代以来SPC SPC 在日本工业界的大量推广应用对日本产品质 量的崛起起到了至关重要的作用，使日本跃居世界质量与生产率 的领先地位。
八十年代以后，世界许多大公司纷纷在自己内部积极推广应用 SPC， ISO9000以及QS9000 QS9000中 SPC，并且对供应商也提出了相应要求。在ISO9000 ISO9000 QS9000 也提出了在生产控制过程中应用SPC SPC的要求。 SPC
控制圖的種類
依用途分: 依用途分:
1.管制用管制圖:先有管制界限,后有數據 用於控制制程之品質,如有點子跑出界限時,立即采 取如下措施. A.追查不正常原因. B.迅速消除此原因. C.研究采取防止此項原因重復發生的措施. 2.解析用管制圖:先有數據,后才有管制界限 A.決定方針用. B.制程解析用. C.制程能力研究用. D.制程管制之準備用.
平均值與全距管制圖( 平均值與全距管制圖(XbarXbar-R Chart)
在計量值管制圖中,Xbar-R管制圖系最常用的一種,所謂平 均值與全距管制圖,系平均值管制圖(Xbar-Chart)與全距 管制圖 (R Chart)二者合並使用. 平均值管制系管制平均值的變化,即分配的集中趨勢變化; 全距管制圖則管制變異的程度,即分配的離散趨勢的狀況.
X σ ˆ
X σ ˆ
X σ ˆ
范围
R
范围
R
范围
R
计数型数值和计量型数值
建立 SPC 的步驟 1. 確立製造流程、 確立製造流程、製造流程解析 2. 決定管制項目 3. 實施標準化 4. 管制圖的運用 5. 制程能力分析 6. 問題分析解決 7. 製程的繼續管制
SPC basic - SPC基础培训
The use of items of a new supplier leads to an abrupt change in hardness and the unique of the final product (compared to th度突 然改变，最终导致产品的不一致（与 先前的供应商作比较）
• SPC controls test activities SPC 控制测试活动
• SPC identifies abrasion and supports maintenance SPC 识别损毁以及协助维护保养
• SPC aims for safe and stable processes SPC 旨在安全和稳定的流程
Small variations of items of one supplier leads from batch to batch to a small deviation in hardness 来自一个供应商的产品的细 微变化会导致一批接一批的 产品在硬度上产生细微变化
Deviation because of systematic impacts 因为经常性发生的影响产生的偏差
Statistic Process Control
(SPC) 统计流程控制
Content for today 今日内容
• What is/ means SPC? 什么是SPC？
• Goals of SPC? SPC的目标？
• How can we use SPC? 我们如何使用SPC？
SPC教材FOR Customer
零件数/ 过程数
零件/过程中心偏移 1.5 σ 裝配成品之良品率 %
+ 1σ + 2σ 69.13 2.49 ─ ─ ─ ─ ─ ─ + 3σ 93.32 50.09 3.15 ─ ─ ─ ─ ─ + 4σ 99.3790 93.96 73.24 53.64 4.44 0.20 ─ ─ + 5σ
99.97670
+ 6σ
99.999660
1 10 50 100 500 1000 5000 10000
30.23 ─ ─ ─ ─ ─ ─ ─
99.76 98.84 97.70 89.00 79.21 31.19 9.73
99.9966 99.983 99.966 99.83 99.66 98.31 96.66
2016/3/8
2016/3/8 page 6
第二节 过程控制系统
有反馈的过程控制系统模型 过程的呼声 人 设备 材料 方法 环境 统计方法 顾客
SPC 教材
我 们 的 工 作 的 方 产品或 式/资源的融合 服务
输入
过程/系统
输出
识别不断变化 的需求和期望
顾客的呼声
图1 过程控制系统
2016/3/8
page
7
1、过程： 共同工作以产生输出的供方、生产者、人、 设备、输入材料、方法和环境以及使用输出的顾 客的祝贺。其性能取决于供方和顾客的沟通以及 其设计和运作方式。 2、有关性能的信息 （Information About Performance）
上海八贤企业管理顾问有限公司
Shanghai Baxian Management Consultant Co.,ltd
Baxian Management Consultant
SPC讲义1PPT课件
設備
材料
人員
操作方法 環境
製程之變異
變異的普通原因與特殊原因
普通原因 (共同原因，Common Cause)
-製程所固有之變異，種類很多，它們隨時都存在，但對製程變異的影 響性小。 -約有85%變異原因屬於此類。(戴明)
[SPC手冊中的說明] 1.指的是那些始終作用於過程的多種變異來源。 2.隨著時間的推移，一個過程中的普通原因會產生一個穩
定的且可複的分佈，我們稱之為“處於統計上受控制的 狀態”、“統計受控”，或有時簡稱 “受控”。
3.普通原因產生的是一個處於偶然原因下的穩定系統。
4.如果一個過程只存在變異的普通原因且不改變時，該過 程的輸出是可預測的。
變異的普通原因與特殊原因
特殊原因 (通常也稱為可查明的原因，Special Cause)
對輸出採取措施
-是最不經濟的。他僅限於對輸出進行探測並矯正不符合規範的 產品，而沒有處理過程中的根本問題。
變異的普通原因與特殊原因
如果僅存在變異的普通原 因，隨著時間的推移，過 程的輸出形成一個穩定的 分佈並可測
如果僅存在變異的特殊原 因，隨著時間的推移，過 程的輸出是不穩定的
變異的來源 變異的來源 (5M & 1E)
我們稱此製程為在管制狀態
（Out of Control）。
（Under Control）。
局部措施和對系統採取的措施
局部措施 1.通常用來消除變異的特殊原因 2.通常由與過程直接相關的人員來實施 3.通常可矯正大約15%的過程問題
對系統採取的措施 1.通常用來消除變異的普通原因 2.幾乎都需要採取管理上的矯正措施 3.通常可矯正大約85%的過程問題
負責第二版的工作小組準備是戴姆勒克來斯勒、Delphi公司、福特 汽車公司、通用汽車公司、Ommex公司和Robert Bosch公司的品質和 供應商評定人員與汽車工業策進會(AIAG)合作組成的。
SPC教材-基础培训专用
0.1
-2.5
-2.0
-1.5
-1.0
-0.5
0
0.5
1.0
1.5
2.0
2.5
Company name
8 January 2015
正态分布的性质Nature of Normal Distribution
机会率 Probaility 0.67 1 50.00 % 68.26 % 95.00 % 95.45 % 99.00 % 99.73 %
0.83
过程变差 Process Variation
Company name
8 January 2015
过程变差Process Variation的原因
过程变差 Process Variation
材料
输入
(材料)
过程
(生产/装配)
输出
(产品)
反馈
(测量/检验) 测量系统
Company name
8 January 2015
Collect, collate, display, analysis, explain of data
• 由样本(sample)推论母体/群体(population) From sample to project the population • 能在不确定情况下作决策 Decision with uncertainty • 是一门科学方法、决策工具
次数划记 Freq Marks X XX XXXXXX XXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXX XXXXXX XXXXXX XXXX X
次数 Freq 1 2 2 6 8 10 10 8 6 6 4 1
SPC统计过程控制程序中英文
QUALITY SYSTEMS PROCEDUREStatistical Process Control统计过程控制REFERENCES: (a)SPC User's Guide(b)STA-200 X(bar)-R(c)STA-300 Capability Studies1.0PURPOSE(目的 )To define the Statistical Process Control applications for our production inspect process.为了规范生产检验过程的SPC的控制。
2.0SCOPE（范围）This procedure is applied to all the production part and process need to SPC control.本文件适用于公司内有SPC监控要求的所有产品及工艺。
3.0 FUNCTIONS AFFECTED（涉及部门）Quality（质量部）Production （生产）Project （项目）Design （设计）Engineering （工程）Quality System （质量系统）4.0DEFINITIONS（定义）4.1 The primary determinate in control chart selection is Data Type.选择控制图最基本的决定条件是数据类型。
4.1.1 Continuous data: the data from testing, for example: label dimensions.计量型数据: 通过测量得到的数据,如标签尺寸。
4.1.2 Attribute data: the data from counting, the attribute data have two outcome (Pass/Fail,Good/NG).计数型数据: 通过点数得到的数据, 计数型数据只有两个值(合格/不合格, 通过/不通过)。
MSA 、SPC测量系统分析表格
1.00 0.90 0.80 0.70 0.60 0.50 0.40 0.30 0.20 0.10 0.00
Operator 1 Operator 2 Operator 3
2
3
4
5
6
7
8
9
10
Page 2
0 0
备注NOTE:不能缺失数据 不能缺失数据FILL WHITE CELLS ONLY 备注 不能缺失数据 操作者Operator2 操作者Operator2 Operator 试 验 试 验 试 验 Trial 3 Trial 1 Trial 2
0 0
试 验 Trial 1
试 验 Trial 2
贡献%Contribution 公差%Tolerance
零件响应图 Response by Part ID
1.00 0.90 0.80 0.70 0.60 0.50 0.40 0.30 0.20 0.10
Process Capability StudyInfo on uncomplete filled datatable
公差% Tolerance
没有交互作用GR&R分析 Gauge R&R Without Operator*Part Interaction
No Spec. Limits Available 差异源 方差 Source VarComp Total Gauge R&R 0.00E+00 重复性 Repeatability 0.00E+00 再现性 Reproducibility0.00E+00 操作者 Operator 0.00E+00 零件Part - To - Part 0.00E+00 总变差Total Variation 0.00E+00 标准偏差 Stdev 0.00E+00 0.00E+00 0.00E+00 0.00E+00 0.00E+00 0.00E+00 贡献 % Contribution #DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0! 公差% Tolerance No Spec. Limits Available
BOSCH SPC 培训材料
SPC
1. What is SPC ? SPC是什么？
SPC:
¾ SPC is a standard method for visualizing and controlling (open or closed loop) processes, based on measurements of random samples. SPC是通过对随机样本的测量而对过程（开环或闭环）进行观察和控 制的一种标准方法。
SPC
1. What is SPC ? SPC是什么？
Process 过程:
¾ A process is a series of activities and/or procedures that transform raw materials or preprocessed parts/components into an output product. 过程是将原材料或半成品转变为输出产品的一系列的活动和或程序。
SPC
Process Control System 过程控制系统
10
CP/IPA-CN | 6/22/2006 | © Robert Bosch GmbH reserves all rights even in the event of industrial property rights. We reserve all rights of disposal such as copying and passing on to third parties.
SPC
Table of Contents 目录
Part 1 SPC Overview 第一章 SPC 概览
1. What is SPC ? SPC是什么？
BOSCHSPC培训材料
7
CP/IPA-CN | 6/22/2006 | © Robert Bosch GmbH reserves all rights even in the event of industrial property rights. We reserve all rights of disposal such as copying and passing on to third parties.
SPC
1. What is SPC ? SPC是什么？
SPC:
¾ SPC is a standard method for visualizing and controlling (open or closed loop) processes, based on measurements of random samples. SPC是通过对随机样本的测量而对过程（开环或闭环）进行观察和控 制的一种标准方法。
10. Selection of control charts 控制图的选用
4
CP/IPA-CN | 6/22/2006 | © Robert Bosch GmbH reserves all rights even in the event of industrial property rights. We reserve all rights of disposal such as copying and passing on to third parties.
5. Defining “out-of-control” signals 定义不受控信号
3
CP/PIN-CN | 6/22/2006 | © Robert Bosch GmbH reserves all rights even in the event of industrial property rights. We reserve all rights of disposal such as copying and passing on to third parties.
SPC basic concept training
CL
LCL
7
1.5 管制界限 Control Limit
1. 若某一組數據是常態分佈, 根據經驗法則, 只有 0.27% 的數據點會超出其平均值 正負三個標準差 的範圍 2. 管制圖的管制界限定義為 : 管制上限(UCL) = 平均值 + 3 標準差 管制下限(LCL) = 平均值 - 3 標準差 3.數據點超出管制界限的範圍時, 表示已有特定誤差產生 管制界限至少每半年review一次(SMIC每季review一次)
Statistic Process Control
Instructor: QE/SPC
1
1.1 SPC 的定義 Statistical (统计) Process (工艺/制程) Control (管制)
自工艺中收集资料，加以统计分析，并从分析中发觉 异常原因，采取改正行动，使工艺恢复正常，保持稳定 ，并持续不断提升工艺能力的方法。
20
创建统计制程控制图（SPC chart）
1. 选择需要建立管制图的制程(PIE, TCP) 2. 确定抽样方法和计划(PIE, EDC Plan) 3. 测量和收集原始数据 4. 计算适当的统计量(Xbar, RS)
5. 决定管制界限，管制规则等(Xbar/RS control,
WECO Rule)
SMIC: WECO1 is at least for all SPC charts, Xbar and RS charts should add at least one other rule.
19
1.7 控制图的种类
WECO rule 2~5 is only for Xbar and RS chart
UCL(+3x)
SPC Basic
讨论过程能力的前提假设
过程处于统计稳定状态； 过程的各测量值服从正态分布； 工程及其它规范准确地代表顾客的需求； 设计目标值位于规范的中心； 测量变差相对较小。
关键定义
正态分布
一种用于计量型数据的、连续的、对称的钟形频率 分布，它是计量型数据用控制图的基础。当一组测 量数据服从正态分布时，有大约68.26%的测量值 落在平均值处正负一个标准差的区间内，大约 95.44%的测量值落在平均值处正负两个标准差的 区间内，大约99.73%的值落在平均值处正负三个 标准差的区间内。这些百分数是控制界限或控制图 分析的基础，也是许多过程能力确定的基础。
两个要点
提高过程能力
为了提高过程能力（从而改进性能），将精 力集中在减少普通原因上，为此通常要求对 系统采取管理措施，加以纠正。
对改变的过程制作控制图并分析
通过连续监视控制图确保系统改进的有效性。
损失函数的概念
传统的“目标柱”思维方法：规范内的 都是好的；规范外的，不论它们偏离规 范多远，都是坏的； 损失函数模式：形式为一抛物线并且利 用随着某特定的特性值偏离规范目标值 越远，顾客或社会蒙受的损失呈二次方 增加。
10
1.78 0.22 0.31 3.08
* 对于样本容量小于7的情况，LCLR可能技术上为一个负值。 在这种情况下没有下控制限。
统计控制（Statistical Control）
描述一个过程的状态，这个过程中所有的特 殊原因变差都已排除，并且仅存在普通原因。 即：观察到的变差可归咎于恒定系统的偶然 原因；在控制图上表现为不存在超出控制限 的点或在控制限范围内不存在非随机性的图 形。
关键定义
统计过程控制（Statistical Process Control）
SPC基本认识培训教材英文
0.33
1
317311 ppm
Where ppm = parts per million and ppb = parts per billion.
2021/7/11
12
9、 人的价值，在招收诱惑的一瞬间被决定 。21.7.1 721.7.1 7Saturd ay , July 17, 2021 10、低头要有勇气，抬头要有低气。2 0:36:39 20:36:3 920:36 7/17/20 21 8:36:39 PM
n 1
due to both common and
special cause.
Cpk
The 6 range of a process’s inherent variation, for statistically stable processes only, where is usually
R
estimated by d2
Cpk 1 Ca Cp
Two-sided symmetrical specification tolerances
Cpk min(Cpu ,Cpl )
C pu
USL ˆ 3 ˆ
C pl
ˆ LSL 3 ˆ
One-sided specification tolerances
Cpk Cp Cpu or Cpl
A grade
0.125 |Ca | 0.25
B grade
0.25 |Ca| 0.5
C grade
• 改善方向 0.5 | Ca |
D grade
(1)調整模具, 製程參數, 材料等以達到規格中心值
(2)與客戶討論變更規格中心值, 但需考慮組裝性問題
(3)與客戶討論變更規格公差, 但需考慮組裝性問題
SPC Basic算法
Statistical Process Control 统计过程控制基本概念：特性产品一般安全、法规关键KPCS配合、功能过程一般关键KCCS一般特性：只要是合格就可以；关键特性：不仅仅合格，还要尽可能接近目标值。
检验分类：●计数型：检验时仅分为合格、不合格；●计量型：检验时可确定值的大小。
第一章持续改进及统计过程控制概述应用统计技术来控制产生输出的过程时，才能在改进质量、提高生产率、降低成本上发挥作用。
第一节预防与检测检测-------- 容忍浪费预防-------- 避免浪费第二节过程控制系统过程共同工作以产生输出的供方、生产者、人、设备、输入材料、方法和环境以及使用输出的顾客之集合。
过程性能取决于： 1.供方和顾客之间的沟通；2.过程设计及实施的方式；3.动作和管理方式。
过程控制重点：过程特性过程控制步骤：确定特性的目标值；监测我们与目标值的距离是近还是远；对得到的信息作出正确的解释，确定过程是在正常的方式下运行；必要时，采取及时准确的措施来校正过程或刚产生的输出；监测采取措施后的效果，必要时进一步分析及采取措施。
注：仅对输出进行检验并随之采取措施，只可作为不稳定或没有能力的过程的临时措施。
不能代替有效的过程管理。
第三节变差：普通及特殊原因任何过程都存在引起变差的原因，产品的差距总是存在。
虽然单个的测量值可能全都不同，但形成一组后它们趋于形成一个可以描述的分布的图形。
（例图）影响因素：普通原因：难以排除，具有稳定、可重复的分布；此时输出可以预测。
特殊原因：必须排除，偶然发生、影响显著；此时将有不可预测方式影响输出。
生产过程控制就是要清除系统性因素（特殊原因）。
第四节局部措施和对系统采取措施局部措施：针对特殊原因由直接操作人采取适当纠正措施。
此时大约可纠正15%的过程问题。
系统措施：解决变差的普通原因，由管理人员来采取措施。
此时大约可纠正85%的过程问题。
采取措施类型不正确，将给机构带来在的损失，劳而无功，延误问题的解决。
- 1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。
ACCEPT REJECT
LOWER SPECIFICATION LIMIT
Target Value
UPPER SPECIFICATION LIMIT
last updated by apv 9/3/04
Control Charts Link to Quality Improvement
Incomplete Mold
Bentleads
Defective • Unit of product containing one or more defects
CY7C102120ZC PHI 9829 E 04 702881
Defective unit #1has Incomplete Mold & Bentleads defects
last updated by apv 9/3/04
Definition of Terms
Control Chart
• Enables a visual assessment of a process with regards to its location and dispersion.
UCL
Centerline
Normal Distribution and Control Chart
Control Chart Divisions
– A control chart is divided into three zones – Each zone is one standard deviation wide – The centerline is XBB (Average of averages)
• Section 5 - Cpk & Z-Score
• Section 6 - Control Charts Patterns & Interpretations
last updated by apv 9/3/04
Course Objectives
Upon completion of this course, you will be able to: – Define Control Charts and Its Purpose – Identify the Link of Control Chart to Quality Improvement – Calculate Control Limits
UCL A B C C B A CL+2s CL+1s CL CL-1s CL-2s LCL
last updated by apv 9/3/04
Rules to Determine Out of Control
• Rule 2
– Out of control if 2 of the last 3 successive data points are on the same side of the centerline and are in Zone A or beyond.
last updated by apv 9/3/04
Response Level for Handling OOC points Level Response Definition
• Level 0 - No action taken (ignore violation) • Level 1 - E-mail message to the responsible engineer • Level 2 - Operator warning message of out of control process is displayed (with screen background red on color terminals) and e-mail sent to responsible engineer. Lot is place on the Problem Lot List (PLL). • Level 3 - Process is shutdown along with all actions of Level 2 • Level 4 - Same actions as for level 3 except that the lot is placed on the PLL only if the data is out of specification.
last updated by apv 9/3/04
Course Outline
• Section 1 - Definition of Terms
• Section 2 - Control Charts Link to Quality Improvement
• Section 3 - Rules to Determine Out of Control & Out of Control Points Response Levels • Section 4 - Control Chart Types & Control Limits Calculations
UCL A B C C B A CL+2s CL+1s CL CL-1s
CL-2s
LCL
last updated by apv 9/3/04
Rules to Determine Out of Control
• Rule 5
– Out of control if the last 9 successive data points are on the same side of the centerline
Zone A Zone B Zone C Zone C Zone B Zone A
Upper Control Limit, UCL
Centerline, CL
Lower Control Limit, LCL
last updated by apv 9/3/04
Section 3
• Rules to Determine Out of Control (OOC) points
• A tool to determine process stability.
• A device used to analyze data and obtain information about the process. • A tool used to separate the common-caused events from special-caused events.
Control Charts Link to Quality Improvement
QUALITY
means
CONFORMANCE TO REQUIREMENTS
REJECT
ACCEPT
REJECT
LOWER SPECIFICATION LIMIT
UPPER SPECIFICATION LIMIT
UCL A B C CL C B A CL-1s CL-2s LCL CL+2s CL+1s
last updated by apv 9/3/04
Response Level for Handling OOC Points
Response Levels
• Response levels are used to identify what action needs to be taken in dealing with out of control events.
UCL A B C CL C B A CL-1s CL-2s LCL CL+2s CL+1s
last updated by apv 9/3/04
Rules to Determine Out of Control
• Rule 4
– Out of control if the last 15 successive data points are in Zone C
• Response Level Requirements for OOC conditions
last updated by apv 9/3/04
Rules to Determine Out of Control
• Rule 1
– Out of control if the last data point falls outside of the control limits
last updated by apv 9/3/04
Control Charts Link to Quality Improvement
BUT….. TO ACHIEVE
QUALITY IM VARIABILITY FROM THE TARGET VALUE
– Determine the Rules to Catch Out of Control(OOC) Events
– Identify what response to take when OOC is encountered – Determine if Charts are failing in capability and stability – Interpret the Common and Uncommon Patterns in the Control Charts
last updated by apv 9/3/04
Section 1
• Definition of Terms
last updated by apv 9/3/04
Definition of Terms Control Chart
• A graphical tool used to describe the process; if “in control” or “out of control” conditions are present.