大家好我是Java1234_小鋒老師分享一套鋒哥原創的基于Spark實時物聯網設備故障預警 數據分析與預測 系統(Java版本可視化大屏KafkaSpringBootVue3)項目介紹隨著工業互聯網與智能制造的快速發展物聯網設備在生產現場的部署規模持續擴大。傳統依賴人工巡檢與閾值告警的運維方式難以應對高頻、多維、持續到達的設備傳感器數據容易出現故障發現滯后、誤報漏報較多、運維成本居高不下等問題。針對上述背景本文設計并實現了一套基于 Spark 思想的實時物聯網設備故障預警系統綜合運用 Java、Spring Boot、Vue3、Kafka、MySQL 等主流技術完成了從數據采集、實時分析、風險評分、故障預警到可視化展示與風險預測的完整閉環。系統后端采用 Spring Boot 構建 RESTful 服務結合 Spring Security 與 JWT 實現管理員身份認證與接口鑒權前端采用 Vue3、Element Plus 與 ECharts 實現管理后臺與數據可視化大屏數據采集側通過 Kafka 消息主題device_telemetry 緩沖設備遙測數據并在 Kafka 不可用時自動降級為純 Java 寫庫保證演示與實驗環境的可用性。系統以窗口聚合方式統計設備數量、告警數量、平均溫度、平均振動、故障率與風險評分基于溫度、振動、電流等指標計算設備故障風險并利用多元線性回歸對風險評分序列進行預測輸出 RMSE、MAE、MAPE 等誤差指標。數據庫采用 MySQL庫名為 db_iot_fault核心數據表包括管理員表、設備類型表、設備表、傳感器數據表、故障預警表、實時統計表、預測結果表與誤差指標表。系統實現了登錄認證、首頁統計、設備管理、傳感器數據查詢、故障預警處理、實時分析、預測分析、可視化大屏以及個人中心資料修改、頭像上傳、密碼修改等功能。測試結果表明系統能夠穩定完成實時數據采集、預警生成與預測分析界面交互流暢滿足本科畢業設計對完整性、實用性與技術綜合性的要求。源碼下載鏈接: https://pan.baidu.com/s/1YtIlK_Xw-u7Z8Qu_Mr16Bw?pwd1234提取碼: 1234系統展示核心代碼package com.java1234.spark; import com.java1234.config.AppProperties; import org.apache.kafka.clients.producer.KafkaProducer; import org.apache.kafka.clients.producer.ProducerConfig; import org.apache.kafka.clients.producer.ProducerRecord; import org.apache.kafka.common.serialization.StringSerializer; import org.springframework.stereotype.Component; import java.util.List; import java.util.Properties; /** * Kafka 遙測生產者可選失敗時降級 */ Component public class KafkaTelemetryProducer { private final AppProperties appProperties; public KafkaTelemetryProducer(AppProperties appProperties) { this.appProperties appProperties; } /** * 嘗試發送事件到 Kafka */ public boolean trySend(ListTelemetryEvent events) { Properties props new Properties(); props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, 127.0.0.1:9092); props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName()); props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName()); props.put(ProducerConfig.REQUEST_TIMEOUT_MS_CONFIG, 3000); props.put(ProducerConfig.DELIVERY_TIMEOUT_MS_CONFIG, 5000); props.put(ProducerConfig.MAX_BLOCK_MS_CONFIG, 500); props.put(ProducerConfig.RETRIES_CONFIG, 0); try (KafkaProducerString, String producer new KafkaProducer(props)) { for (TelemetryEvent event : events) { String json toJson(event); producer.send(new ProducerRecord(appProperties.getKafkaTopic(), json)).get(); } return true; } catch (Exception ex) { System.out.println([Simulator] Kafka 發送失敗使用純 Java 寫庫: ex.getMessage()); return false; } } /** * 將遙測事件序列化為 JSON */ private String toJson(TelemetryEvent event) { return String.format( {\device_id\:%d,\temperature\:%s,\vibration\:%s,\current\:%s,\voltage\:%s,\humidity\:%s,\is_fault\:%d,\risk_score\:%s,\event_time\:\%s\}, event.getDeviceId(), event.getTemperature(), event.getVibration(), event.getCurrent(), event.getVoltage(), event.getHumidity(), event.getIsFault(), event.getRiskScore(), event.getEventTime().format(java.time.format.DateTimeFormatter.ofPattern(yyyy-MM-dd HH:mm:ss)) ); } }template div classpage-container div classpage-card div classpage-title故障風險預測分析/div div classerror-cards div classerror-carddiv classmetric-labelRMSE (均方根誤差)/divdiv classmetric-value{{ errorMetric.rmse }}/div/div div classerror-carddiv classmetric-labelMAE (平均絕對誤差)/divdiv classmetric-value{{ errorMetric.mae }}/div/div div classerror-carddiv classmetric-labelMAPE (平均絕對百分比誤差 %)/divdiv classmetric-value{{ errorMetric.mape }}%/div/div /div div refcompareRef classpred-chart/div div refresidualRef classpred-chart pred-residual/div el-table :datatableData stripe border el-table-column propwindow_time label時間窗口 min-width170 template #default{ row }{{ formatWindowTime(row.window_time) }}/template /el-table-column el-table-column proptrue_score label真實風險分 min-width120 template #default{ row }span stylecolor:#409eff;font-weight:600{{ row.true_score }}/span/template /el-table-column el-table-column proppred_score label預測風險分 min-width120 template #default{ row }span stylecolor:#67c23a;font-weight:600{{ row.pred_score }}/span/template /el-table-column el-table-column label誤差 min-width100 template #default{ row } span :style{ color: Math.abs(row.true_score - row.pred_score) 5 ? #f56c6c : #909399 } {{ (row.true_score - row.pred_score).toFixed(2) }} /span /template /el-table-column el-table-column propcreate_time label生成時間 min-width170 template #default{ row }{{ formatDateTime(row.create_time) }}/template /el-table-column /el-table el-pagination stylemargin-top:16px;justify-content:flex-end v-model:current-pagepage v-model:page-sizesize :totaltotal layouttotal, prev, pager, next changeloadTable / /div /div /template script setup /** * 預測分析頁面真實 vs 預測對比 誤差分析 */ import { ref, onMounted, onUnmounted } from vue import * as echarts from echarts import request from /utils/request import { formatDateTime, formatWindowTime } from /utils/format const errorMetric ref({ rmse: 0, mae: 0, mape: 0 }) const tableData ref([]) const page ref(1) const size ref(10) const total ref(0) const compareRef ref(null) const residualRef ref(null) let charts [] let pollTimer null function axisLabel() { return { rotate: 30, interval: auto, formatter(val) { const t formatWindowTime(val); return t.length 16 ? ${t.slice(0,10)}\n${t.slice(11)} : t } } } function initCompareChart(data) { if (!compareRef.value) return const chart echarts.init(compareRef.value) const labels data.map(d formatWindowTime(d.window_time)) chart.setOption({ title: { text: 真實風險分 vs 預測風險分 對比, left: center, textStyle: { fontSize: 15 } }, tooltip: { trigger: axis }, legend: { data: [真實風險分, 預測風險分], top: 32 }, grid: { left: 20, right: 24, bottom: 28, top: 72, containLabel: true }, xAxis: { type: category, data: labels, axisLabel: axisLabel() }, yAxis: { type: value, name: 風險評分 }, series: [ { name: 真實風險分, type: line, smooth: true, data: data.map(d Number(d.true_score)), itemStyle: { color: #409eff }, lineStyle: { width: 3 } }, { name: 預測風險分, type: line, smooth: true, data: data.map(d Number(d.pred_score)), itemStyle: { color: #67c23a }, lineStyle: { width: 3, type: dashed } }, ], }) charts.push(chart) } function initResidualChart(data) { if (!residualRef.value) return const chart echarts.init(residualRef.value) const labels data.map(d formatWindowTime(d.window_time)) const residuals data.map(d Number((Number(d.true_score) - Number(d.pred_score)).toFixed(2))) chart.setOption({ title: { text: 預測殘差分析 (真實值 - 預測值), left: center, textStyle: { fontSize: 15 } }, tooltip: { trigger: axis }, grid: { left: 20, right: 24, bottom: 28, top: 56, containLabel: true }, xAxis: { type: category, data: labels, axisLabel: axisLabel() }, yAxis: { type: value, name: 殘差 }, series: [{ type: bar, data: residuals.map(v ({ value: v, itemStyle: { color: v 0 ? #409eff : #f56c6c } })), barWidth: 20 }], }) charts.push(chart) } async function loadData() { const [errorRes, compareRes] await Promise.all([ request.get(/prediction/error), request.get(/prediction/compare), ]) errorMetric.value errorRes.data charts.forEach(c c.dispose()) charts [] initCompareChart(compareRes.data || []) initResidualChart(compareRes.data || []) } async function loadTable() { const res await request.get(/prediction/list, { params: { page: page.value, size: size.value } }) tableData.value res.data.items total.value res.data.total } onMounted(() { loadData() loadTable() pollTimer setInterval(loadData, 5000) }) onUnmounted(() { clearInterval(pollTimer); charts.forEach(c c.dispose()) }) /script style scoped .pred-chart { width: 100%; height: 420px; margin-bottom: 24px; } .pred-residual { height: 360px; } /style