← 返回工业工程专业

应用统计学

Applied Statistics

课程介绍 Course Introduction

学分:3 | 先修课:高等数学、概率论 | 学期:春季

应用统计学是工业工程专业的重要基础课程,侧重于统计方法在工程和管理问题中的实际应用。课程内容包括描述性统计、参数估计、假设检验、方差分析、回归分析、实验设计、非参数统计和统计质量控制等。学生将学习使用Minitab、R或Python进行数据分析,掌握从数据收集、整理、分析到得出结论的完整统计思维过程。

Applied Statistics is an important foundational course in industrial engineering, focusing on the practical application of statistical methods to engineering and management problems. Topics include descriptive statistics, parameter estimation, hypothesis testing, analysis of variance, regression analysis, experimental design, nonparametric statistics, and statistical quality control. Students learn to use Minitab, R, or Python for data analysis and develop statistical thinking from data collection to conclusion.

大作业 Final Project

作业标题:工程数据回归分析与实验设计 / Engineering Data Regression Analysis and Design of Experiments

针对指定工程问题开展数据回归分析与实验设计,包括模型拟合、假设检验、方差分析与因子实验。使用R/Python完成数据分析。

Conduct data regression analysis and design of experiments for a specified engineering problem, including model fitting, hypothesis testing, ANOVA and factorial experiments. Use R/Python to complete data analysis.

实施步骤 Implementation Steps

📋 示例:分析一批真实的工程数据,比如某注塑厂的零件尺寸测量数据。你需要做描述性统计、正态性检验和过程能力分析(Cp、Cpk),然后设计一个全因子实验找出影响尺寸精度的关键工艺参数,用Minitab做方差分析。
步骤 1
数据探索分析
本步骤对工业工程问题进行系统分析,识别问题本质和改进机会。工业工程以系统优化为核心,通过数据分析和流程建模,从效率、质量、成本多个维度评估系统现状。采用价值流图、流程分析、数据统计等方法诊断问题根源。

• 进行现场调研和数据收集,使用秒表法、工作抽样法或视频分析法获取作业时间数据
• 绘制价值流图(VSM)或流程图,识别瓶颈工序、浪费环节和改进点
• 运用统计学方法进行数据分析,区分偶然波动和异常因素,确定关键影响变量
产出:现状分析报告(含数据收集表、流程图/价值流图、问题诊断、改进机会分析) | 质量标准:数据充分、分析深入、问题定位准确、改进机会清晰
步骤 2
假设检验与方差分析
本步骤对工业工程问题进行系统分析,识别问题本质和改进机会。工业工程以系统优化为核心,通过数据分析和流程建模,从效率、质量、成本多个维度评估系统现状。采用价值流图、流程分析、数据统计等方法诊断问题根源。

• 进行现场调研和数据收集,使用秒表法、工作抽样法或视频分析法获取作业时间数据
• 绘制价值流图(VSM)或流程图,识别瓶颈工序、浪费环节和改进点
• 运用统计学方法进行数据分析,区分偶然波动和异常因素,确定关键影响变量
产出:现状分析报告(含数据收集表、流程图/价值流图、问题诊断、改进机会分析) | 质量标准:数据充分、分析深入、问题定位准确、改进机会清晰
步骤 3
回归建模
本步骤建立工业系统的数学模型或仿真模型,为定量分析和优化决策提供工具。工业系统建模需要准确描述系统的逻辑关系、资源约束和随机特性,通过抽象和简化抓住系统本质。模型是工业工程分析和优化的基础,其准确性直接影响决策质量。

• 使用Arena、Flexsim或Plant Simulation建立离散事件仿真模型,定义实体、流程、资源和逻辑
• 建立数学规划模型(线性规划、整数规划、非线性规划),使用Lingo、MATLAB或Gurobi求解
• 进行输入数据分析,拟合概率分布,验证输入数据的准确性和代表性
产出:系统模型(含仿真模型/数学模型、输入数据、模型验证结果、参数设置说明) | 质量标准:模型准确、逻辑正确、验证充分、能真实反映系统
步骤 4
实验设计
本步骤进行工业工程系统的方案设计,将改进目标转化为具体的实施方案。工业工程设计强调系统化和整体优化,需在生产效率、产品质量、运营成本和人员安全之间寻求平衡。采用IE方法和工具设计最优解决方案。

• 运用SLP(系统布置设计)方法或流程程序分析进行设施布局和工艺流程设计
• 应用人因工程学原理进行工作站设计,考虑人体测量数据、作业姿势和认知负荷
• 设计质量管理体系或生产控制系统,明确运行流程、职责分工和评价指标
产出:设计方案(含布局图、流程图、作业标准、人员配置、指标体系) | 质量标准:方案系统、方法科学、参数合理、可操作性强
步骤 5
结论与报告
本步骤是工业工程项目的重要环节,运用IE理论和方法系统优化生产与服务系统。工业工程以提高效率、降低成本、保证质量为目标,强调系统观念和持续改进。采用定量化分析方法和专业工具确保改进效果。

• 运用工业工程基础方法(方法研究、作业测定、流程分析)诊断和改进系统
• 使用专业工具(Arena/Flexsim/Minitab/Lingo等)进行建模、仿真和数据分析
• 从技术、经济、人因多角度评价方案,确保系统整体最优
产出:工业工程报告(含现状分析、改进方案、效果预测、实施建议) | 质量标准:方法科学、数据充分、方案可行、效果显著

Steps

Step 1
Exploratory Data Analysis
This step performs systematic analysis of industrial engineering problems, identifying the nature of problems and improvement opportunities. Industrial engineering focuses on system optimization, evaluating system status from efficiency, quality, cost dimensions through data analysis and process modeling. Diagnose root causes using value stream mapping, process analysis, statistical data and other methods.

• Conduct site investigation and data collection, obtain operation time data using stopwatch method, work sampling or video analysis
• Draw value stream map (VSM) or process flow chart, identify bottleneck processes, waste links and improvement points
• Apply statistical methods for data analysis, distinguish random fluctuations from abnormal factors, determine key influencing variables
Deliverable: Current state analysis report (including data collection table, process flow/VSM, problem diagnosis, improvement opportunity analysis) | Quality standard: Sufficient data, in-depth analysis, accurate problem定位, clear improvement opportunities
Step 2
Hypothesis Testing and ANOVA
This step performs systematic analysis of industrial engineering problems, identifying the nature of problems and improvement opportunities. Industrial engineering focuses on system optimization, evaluating system status from efficiency, quality, cost dimensions through data analysis and process modeling. Diagnose root causes using value stream mapping, process analysis, statistical data and other methods.

• Conduct site investigation and data collection, obtain operation time data using stopwatch method, work sampling or video analysis
• Draw value stream map (VSM) or process flow chart, identify bottleneck processes, waste links and improvement points
• Apply statistical methods for data analysis, distinguish random fluctuations from abnormal factors, determine key influencing variables
Deliverable: Current state analysis report (including data collection table, process flow/VSM, problem diagnosis, improvement opportunity analysis) | Quality standard: Sufficient data, in-depth analysis, accurate problem定位, clear improvement opportunities
Step 3
Regression Modeling
This step establishes mathematical models or simulation models of industrial systems, providing tools for quantitative analysis and optimal decision-making. Industrial system modeling requires accurate description of system logical relationships, resource constraints and stochastic characteristics, capturing system essence through abstraction and simplification. Models are the foundation of industrial engineering analysis and optimization, their accuracy directly affecting decision quality.

• Build discrete event simulation models using Arena, Flexsim or Plant Simulation, define entities, processes, resources and logic
• Establish mathematical programming models (linear programming, integer programming, nonlinear programming), solve using Lingo, MATLAB or Gurobi
• Perform input data analysis, fit probability distributions, verify accuracy and representativeness of input data
Deliverable: System model (including simulation model/mathematical model, input data, model validation results, parameter setting description) | Quality standard: Accurate model, correct logic, sufficient validation, realistically reflecting system
Step 4
Design of Experiments
This step performs scheme design of industrial engineering systems, translating improvement goals into specific implementation plans. Industrial engineering design emphasizes systematization and overall optimization, requiring balance among production efficiency, product quality, operating cost and personnel safety. Design optimal solutions using IE methods and tools.

• Apply SLP (Systematic Layout Planning) method or process procedure analysis for facility layout and process flow design
• Apply ergonomics principles for workstation design, considering anthropometric data, working posture and cognitive load
• Design quality management system or production control system, clarify operational processes, responsibility division and evaluation indicators
Deliverable: Design scheme (including layout diagram, process flow chart, work standards, staffing, indicator system) | Quality standard: Systematic scheme, scientific method, reasonable parameters, strong operability
Step 5
Conclusions and Report
This step is an important element in industrial engineering projects, using IE theory and methods to systematically optimize production and service systems. Industrial engineering aims to improve efficiency, reduce costs and ensure quality, emphasizing system concept and continuous improvement. Adopt quantitative analysis methods and professional tools to ensure improvement effects.

• Apply industrial engineering basic methods (method study, work measurement, process analysis) to diagnose and improve systems
• Use professional tools (Arena/Flexsim/Minitab/Lingo, etc.) for modeling, simulation and data analysis
• Evaluate schemes from technical, economic, ergonomic perspectives, ensuring overall system optimization
Deliverable: Industrial engineering report (including current state analysis, improvement scheme, effect prediction, implementation suggestions) | Quality standard: Scientific method, sufficient data, feasible scheme, significant effects
← 返回工业工程 下一门:人因工程 → 🎲 Random Course
Prerequisites · International Exams · Contact · Back to top · Home