前言
💖💖作者：计算机程序员小杨 💙💙个人简介：我是一名计算机相关专业的从业者，擅长Java、微信小程序、Python、Golang、安卓Android等多个IT方向。会做一些项目定制化开发、代码讲解、答辩教学、文档编写、也懂一些降重方面的技巧。热爱技术，喜欢钻研新工具和框架，也乐于通过代码解决实际问题，大家有技术代码这一块的问题可以问我！ 💛💛想说的话：感谢大家的关注与支持！ 💕💕文末获取源码联系 计算机程序员小杨 💜💜 网站实战项目 安卓/小程序实战项目 大数据实战项目 深度学习实战项目 计算机毕业设计选题 💜💜
一.开发工具简介
大数据框架：Hadoop+Spark（本次没用Hive，支持定制） 开发语言：Python+Java（两个版本都支持） 后端框架：Django+Spring Boot(Spring+SpringMVC+Mybatis)（两个版本都支持） 前端：Vue+ElementUI+Echarts+HTML+CSS+JavaScript+jQuery 详细技术点：Hadoop、HDFS、Spark、Spark SQL、Pandas、NumPy 数据库：MySQL
二.系统内容简介
智能制造生产效能分析与可视化系统是一套基于大数据技术构建的现代化制造业生产管理平台。该系统采用Hadoop+Spark大数据框架作为核心数据处理引擎，结合Python、Django后端开发技术和Vue+ElementUI+Echarts前端技术栈，构建了完整的制造业生产数据分析解决方案。系统通过HDFS分布式文件系统存储海量生产数据，利用Spark SQL进行高效数据查询和分析，配合Pandas、NumPy等数据科学库实现复杂的数据处理算法。在功能架构上，系统涵盖了用户权限管理、制造生产效能数据管理、设备性能分析、运营优化分析、生产效能分析、质量控制分析、资源持续分析等核心模块，并通过可视化大屏实现数据的直观展示。整个系统以MySQL作为元数据存储，保证了数据的一致性和可靠性，为制造企业提供了从数据采集、存储、处理到可视化展示的全链路生产效能分析能力。
三.系统功能演示
四.系统界面展示
五.系统源码展示
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, avg, sum, count, max, min, when, isnan, isnull
from django.http import JsonResponse
from django.views.decorators.csrf import csrf_exempt
from django.utils.decorators import method_decorator
from django.views import View
import pandas as pd
import numpy as np
import json
from datetime import datetime, timedelta
spark = SparkSession.builder.appName("ManufacturingAnalysis").config("spark.sql.adaptive.enabled", "true").config("spark.sql.adaptive.coalescePartitions.enabled", "true").getOrCreate()
@method_decorator(csrf_exempt, name='dispatch')
class ProductionEfficiencyAnalysis(View):
def post(self, request):
data = json.loads(request.body)
start_date = data.get('start_date')
end_date = data.get('end_date')
production_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/manufacturing").option("dbtable", "production_data").option("user", "root").option("password", "password").load()
filtered_df = production_df.filter((col("production_date") >= start_date) & (col("production_date") <= end_date))
efficiency_metrics = filtered_df.groupBy("production_line", "shift").agg(
avg("actual_output").alias("avg_output"),
avg("planned_output").alias("avg_planned"),
sum("defect_count").alias("total_defects"),
count("*").alias("total_records")
)
efficiency_metrics = efficiency_metrics.withColumn("efficiency_rate", (col("avg_output") / col("avg_planned")) * 100)
efficiency_metrics = efficiency_metrics.withColumn("defect_rate", (col("total_defects") / col("avg_output")) * 100)
efficiency_metrics = efficiency_metrics.withColumn("oee_score", col("efficiency_rate") * (100 - col("defect_rate")) / 100)
quality_analysis = filtered_df.groupBy("product_type").agg(
avg("quality_score").alias("avg_quality"),
count(when(col("quality_score") < 80, 1)).alias("low_quality_count")
)
trend_analysis = filtered_df.groupBy("production_date").agg(
sum("actual_output").alias("daily_output"),
avg("efficiency_rate").alias("daily_efficiency")
).orderBy("production_date")
efficiency_result = efficiency_metrics.toPandas().to_dict('records')
quality_result = quality_analysis.toPandas().to_dict('records')
trend_result = trend_analysis.toPandas().to_dict('records')
overall_efficiency = filtered_df.agg(avg("efficiency_rate").alias("overall_avg")).collect()[0]["overall_avg"]
benchmark_comparison = filtered_df.filter(col("efficiency_rate") > overall_efficiency).count()
total_records = filtered_df.count()
performance_distribution = filtered_df.select("efficiency_rate").rdd.map(lambda x: x[0]).collect()
efficiency_std = np.std(performance_distribution)
response_data = {
'efficiency_metrics': efficiency_result,
'quality_analysis': quality_result,
'trend_analysis': trend_result,
'overall_efficiency': float(overall_efficiency),
'above_average_count': benchmark_comparison,
'total_records': total_records,
'efficiency_std': float(efficiency_std),
'analysis_period': f"{start_date} to {end_date}"
}
return JsonResponse(response_data)
@method_decorator(csrf_exempt, name='dispatch')
class EquipmentPerformanceAnalysis(View):
def post(self, request):
data = json.loads(request.body)
equipment_ids = data.get('equipment_ids', [])
analysis_period = data.get('analysis_period', 30)
end_date = datetime.now()
start_date = end_date - timedelta(days=analysis_period)
equipment_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/manufacturing").option("dbtable", "equipment_data").option("user", "root").option("password", "password").load()
if equipment_ids:
equipment_df = equipment_df.filter(col("equipment_id").isin(equipment_ids))
equipment_df = equipment_df.filter((col("timestamp") >= start_date.strftime('%Y-%m-%d')) & (col("timestamp") <= end_date.strftime('%Y-%m-%d')))
performance_metrics = equipment_df.groupBy("equipment_id", "equipment_type").agg(
avg("utilization_rate").alias("avg_utilization"),
avg("efficiency_score").alias("avg_efficiency"),
sum("downtime_minutes").alias("total_downtime"),
count("*").alias("operation_hours"),
avg("temperature").alias("avg_temperature"),
avg("vibration_level").alias("avg_vibration"),
max("error_count").alias("max_errors")
)
health_score = performance_metrics.withColumn("health_score",
(col("avg_efficiency") * 0.4 +
(100 - col("avg_utilization")) * 0.3 +
when(col("total_downtime") > 1440, 0).otherwise(100 - (col("total_downtime") / 1440) * 100) * 0.3))
maintenance_prediction = equipment_df.groupBy("equipment_id").agg(
avg("vibration_level").alias("vibration_trend"),
avg("temperature").alias("temp_trend"),
count(when(col("error_count") > 5, 1)).alias("high_error_days")
)
maintenance_prediction = maintenance_prediction.withColumn("maintenance_urgency",
when((col("vibration_trend") > 8.0) | (col("temp_trend") > 85.0) | (col("high_error_days") > 3), "High")
.when((col("vibration_trend") > 6.0) | (col("temp_trend") > 75.0) | (col("high_error_days") > 1), "Medium")
.otherwise("Low"))
failure_analysis = equipment_df.filter(col("status") == "failure").groupBy("equipment_id", "failure_type").agg(
count("*").alias("failure_count"),
avg("repair_time_hours").alias("avg_repair_time")
)
cost_analysis = equipment_df.groupBy("equipment_id").agg(
sum("maintenance_cost").alias("total_maintenance_cost"),
sum("energy_consumption").alias("total_energy_cost"),
avg("production_value").alias("avg_production_value")
)
cost_analysis = cost_analysis.withColumn("roi_score",
col("avg_production_value") / (col("total_maintenance_cost") + col("total_energy_cost")))
performance_result = health_score.toPandas().to_dict('records')
maintenance_result = maintenance_prediction.toPandas().to_dict('records')
failure_result = failure_analysis.toPandas().to_dict('records')
cost_result = cost_analysis.toPandas().to_dict('records')
equipment_ranking = health_score.orderBy(col("health_score").desc()).limit(10).select("equipment_id", "health_score").toPandas().to_dict('records')
response_data = {
'performance_metrics': performance_result,
'maintenance_predictions': maintenance_result,
'failure_analysis': failure_result,
'cost_analysis': cost_result,
'top_performers': equipment_ranking,
'analysis_period_days': analysis_period
}
return JsonResponse(response_data)
@method_decorator(csrf_exempt, name='dispatch')
class QualityControlAnalysis(View):
def post(self, request):
data = json.loads(request.body)
product_lines = data.get('product_lines', [])
quality_threshold = data.get('quality_threshold', 85.0)
analysis_days = data.get('analysis_days', 7)
end_date = datetime.now()
start_date = end_date - timedelta(days=analysis_days)
quality_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/manufacturing").option("dbtable", "quality_data").option("user", "root").option("password", "password").load()
if product_lines:
quality_df = quality_df.filter(col("product_line").isin(product_lines))
quality_df = quality_df.filter((col("inspection_date") >= start_date.strftime('%Y-%m-%d')) & (col("inspection_date") <= end_date.strftime('%Y-%m-%d')))
quality_metrics = quality_df.groupBy("product_line", "product_type").agg(
count("*").alias("total_inspections"),
count(when(col("quality_score") >= quality_threshold, 1)).alias("passed_inspections"),
avg("quality_score").alias("avg_quality_score"),
min("quality_score").alias("min_quality_score"),
max("quality_score").alias("max_quality_score")
)
quality_metrics = quality_metrics.withColumn("pass_rate", (col("passed_inspections") / col("total_inspections")) * 100)
defect_analysis = quality_df.filter(col("quality_score") < quality_threshold).groupBy("defect_type", "product_line").agg(
count("*").alias("defect_count"),
avg("severity_level").alias("avg_severity")
).orderBy(col("defect_count").desc())
process_correlation = quality_df.groupBy("process_step").agg(
avg("quality_score").alias("step_avg_quality"),
count(when(col("quality_score") < quality_threshold, 1)).alias("step_failures")
)
process_correlation = process_correlation.withColumn("failure_rate", (col("step_failures") / count("*")) * 100)
inspector_performance = quality_df.groupBy("inspector_id").agg(
count("*").alias("inspections_performed"),
avg("inspection_time_minutes").alias("avg_inspection_time"),
count(when(col("rework_required") == True, 1)).alias("rework_identified")
)
trend_analysis = quality_df.groupBy("inspection_date").agg(
avg("quality_score").alias("daily_avg_quality"),
count(when(col("quality_score") < quality_threshold, 1)).alias("daily_failures")
).orderBy("inspection_date")
correlation_matrix = quality_df.select("temperature", "humidity", "pressure", "quality_score").toPandas()
correlation_results = correlation_matrix.corr()['quality_score'].to_dict()
spc_analysis = quality_df.select("quality_score").rdd.map(lambda x: x[0]).collect()
control_limits = {
'mean': float(np.mean(spc_analysis)),
'ucl': float(np.mean(spc_analysis) + 3 * np.std(spc_analysis)),
'lcl': float(np.mean(spc_analysis) - 3 * np.std(spc_analysis))
}
quality_result = quality_metrics.toPandas().to_dict('records')
defect_result = defect_analysis.toPandas().to_dict('records')
process_result = process_correlation.toPandas().to_dict('records')
inspector_result = inspector_performance.toPandas().to_dict('records')
trend_result = trend_analysis.toPandas().to_dict('records')
response_data = {
'quality_metrics': quality_result,
'defect_analysis': defect_result,
'process_analysis': process_result,
'inspector_performance': inspector_result,
'quality_trends': trend_result,
'environmental_correlation': correlation_results,
'control_limits': control_limits,
'analysis_summary': {
'threshold_used': quality_threshold,
'analysis_period': analysis_days,
'total_lines_analyzed': len(product_lines) if product_lines else 'all'
}
}
return JsonResponse(response_data)
六.系统文档展示
结束
💕💕文末获取源码联系 计算机程序员小杨
