绝缘子检验设备布置制造安装
绝缘子检验设备布置制造安装
摘
绝缘子作电气设备缺绝缘元件广泛应变电站电力线路电器盘形悬式瓷绝缘子国国应早广泛绝缘子具良机电性绝缘性耐腐蚀优点课题围绕耐压10KV型号XMP170耐污悬式瓷绝缘子出厂前检验设备学中体测量学设备布置尺寸合理完成检验设备安装施工工艺零部件制造工艺
关键词:悬式瓷绝缘子工程机械制造设备布置
Layout manufacture and installation of insulator inspection equipment
Abstract
Insulators as indispensable insulating elements for electrical equipment are widely used in substations power lines and electrical appliances Discshaped suspended porcelain insulator is the earliest and most widely used insulator in China It has the advantages of good electromechanical performance insulation performance and corrosion resistance This subject is about the predelivery inspection equipment of the XMP170 pollutionresistant suspended porcelain insulator with a voltage of 10KV The human body ergonomics in the human factors make the equipment layout and size reasonable And then complete the installation and construction process of the inspection equipment and the manufacturing process of the main parts
Keywords Insulator Human Factors Engineering
machine manufacturing equipment layout
目 录
1 前言 1
11研究背景 1
12设计目应达技术求 1
2检验设备布置 1
21 拉伸检验设备 2
22拉伸检验设备设计求考虑 2
23 耐压检验设备 5
24耐压检验设备设计求考虑 5
25设备布置安排 6
3检验设备零件加工工艺 7
31 动轴分析 7
311动轴作 7
312零件工艺分析 8
32工艺规程设计 8
321确定毛坯制造形式 8
322制定工艺路线 8
323机械加工余量工序尺寸确定 9
324确定切削量 10
4检验设备施工安装 12
41机械设备安装前基础位置应符合求 12
42 放线位 13
43找正调 13
431找正设备中心 13
432水找正 13
433项校正工作应测量方法 13
44脚螺栓 15
45脚螺栓施工方案 16
46脚螺栓两种误差情况应措施 18
47拉伸试验设备安装 18
48耐压检验设备安装 19
参考文献 20
致 谢 21
附 录 22
1 前言
绝缘子电力系统中许领域里起缺作绝缘设备作电气绝缘机械连接绝缘子材料分分瓷绝缘子玻璃绝缘子复合绝缘子瓷绝缘子国早生产绝缘子目前止悬式瓷绝缘子已具105年运行验[1]具良绝缘性耐热性便组装优点电压等级输电线路里广泛
11研究背景
绝缘子电力系统中广泛应单绝缘子损坏会造成事中部分原出绝缘子达求强度制造质量佳造成绝缘子中劣化速度加快绝缘子损坏常常会造成定范围供电中断现代社会正常运转离开电力供电满足着民日常生活济建设需较长时间供电中断仅影响电力系统运行直接影响企业济效益线民群众生命财产安全[2]
作电网系统里关键零部件绝缘子质量电网安全运行关系谓息息相关保证绝缘子质量劣质产品进入电网出厂前需通检验剔次品
12设计目应达技术求
梁展乔学全建武学合作完成10kv绝缘子出厂检验设备项目该项目分绝缘子出厂前拉伸强调检验设备设计耐压检验设备设计设备布置制造安装三部分设计绝缘子检验设备布置制造安装设计设计体分检验设备布置检验设备零件制造工艺检验设备施工安装组成
提高设备检验效率操作员工作效率设备设计安装时需运工程设备高度设备布置处合理位置设备具非标件需设备零部件编写加工工艺程卡片工序卡保证安装水设备求精度运行提高济效益需编写安装程求施工方案绘制出设备面布置图
2检验设备布置
检验设备完全动化作业离开力中拉伸检验需工绝缘子放检测位置检测结束需检测装置取耐压检验拉伸检验间需绝缘子转运程检验线存检验效率提升工作更效设备布置安排设计程中设备高度方面应充分利工程学原工作业环境安全高效舒适基目两:提高效率提高产质减少失误增加信赖度等等二增进性价值降低工作压力疲劳度增进安全
21 拉伸检验设备
拉伸检验设备绝缘子检验流程里第台设备绝缘子生产车间制造转运拉伸检验设备附等检验拉伸检验合格绝缘子送进行耐压检验拉伸检验设备里检验结构视图侧视图(图211)该设备分3工位安装拉伸卸载设备工作工程名工绝缘子放安装位检验结构电机拖动进行时针转120°第次安装绝缘子转拉伸工位进行拉伸试验时工安装位第二次安装检验绝缘子拉伸工位绝缘子检测完检验结构时针旋转120°第次安装绝缘子进入卸载位等工卸第二次安装绝缘子进入拉伸工位准备开始检验工安装位第三次安装绝缘子旋转120°检验结构回初始位置步骤循环
图211 拉伸检验设备检验结构视图侧视图
22拉伸检验设备设计求考虑
设备里设置两工位工位位设备左边工位位设备右边名工左边安装位放绝缘子名工设备右边卸载位完成拉伸检验卸放转运装置检验结构侧视图(图211)安装位卸载位处高度设备高度参数需考虑第二考虑绝缘子装卸程绝缘子需工手动搬运体手臂定长度设备设计合理会导致装卸困难甚法装卸
(1) 作业岗位选择
根推荐作业岗位选择(图221)绝缘子净重6kg属重载力量参数装卸绝缘子程属重复移动参数作业岗位选择立姿
图221 推荐作业岗位选择
S坐姿ST立姿SST坐立姿STC立姿备座椅
(2) 体百分位数选择
工操作程中设备高度设计时没工作程考虑设计太高太低明显会造成装卸速度慢效率降长期会危害工健康增加事发生率
考虑目前工难招聘年轻代普遍喜欢进工厂工数量越越少情况设计出男女工适设备采男性P90作尺寸限值女性P10作尺寸限值
(3) 设备高度确定
设备高度设计高会增加工次操作疲劳度造成装卸速度变慢设计高度低会工弯腰长期会产生工伤站姿作业面高度作业性质关系(图222)分析单绝缘子重量6kg搬运绝缘子属重荷作业图设备高度应选肘高高度减10cm根国成年体尺寸现行国家标准[3]查表3男性肘高P90位1079mm根国成年体尺寸现行国家标准[3]查表4女性肘高P10913mm设备高度应设计813979mm范围根求先设备高度定900mm面考虑电机减速器安放设计拉伸检验设备学终绝缘子安装位卸载位高度定离1200mm解决方案安装位卸载位工位安放高度300mm垫板
图222 站姿作业面高度作业性质关系
(a)精密作业 (b)般作业 (c)重荷作业
(4) 安装位卸载位设备底座相位置关系
检验结构侧视图(图211)知装卸绝缘子需手臂伸装卸位完成装卸程设备底座设计超出工臂范围装卸工作法完成外需考虑电机减速器安放布置安装位卸载位设备底座相位置应控制合理范围
绝缘子重量6kg单手进行搬运作业会容易导致工疲劳搬运速度降造成检测效率降低装卸工作采双臂作业形式安装卸载位离站垫板相高度900mm根站姿双臂身作业空间(图223)里臂范围手掌离面高度关系安装位设备左边底座水距离超275mm检验结构中心称理卸载位设备右边底座水距离超275mm
图223 站姿双臂身作业空间
23 耐压检验设备
悬式绝缘子完成拉伸检验工检验完绝缘子卸载位卸然转身放耐压检验设备里链条钢板三位置绝缘子着链轮转动进入检验范围5分钟耐压检验耐压检验设备末端需工检验合格绝缘子装置简单说耐压检验设备检验操作程两步放绝缘子绝缘子
24耐压检验设备设计求考虑
设备中工操作装卸两部分组成考虑素设备高度
(1) 作业岗位选择
绝缘子拉伸检测重量变形状变加搬运操作拉伸检测时太差涉参数致作业岗位选择(图221)作业岗位选择立姿
(2) 体尺寸百分位数选择
选择考虑拉伸检验设备样样采男性P90作尺寸限值女性P10作尺寸限值
(3) 设备高度确定
耐压检验设备高度设计高会导致装卸程时间变长会增加绝缘子掉落率稳定性降低检验设备设计低会工装卸程中作出必幅度弯腰蹲动作装卸单绝缘子劳动时间增加样会降低效率根国成年体尺寸现行国家标准[3]查表3男性肘高P901079mm根国成年体尺寸现行国家标准[3]查表4女性肘高P10913mm站姿作业面高度作业性质关系(图222)重荷作业作业面高度应肘高减100mm设备高度应设计813979mm范围范围求两设备作业高度保持致考虑设计耐压检验设备学高度定1200mm
25设备布置安排
里考虑问题两台设备间留少距离问题许绝缘子生产厂家设备布置拉伸检验耐压检验分开距离布置绝缘子完成拉伸检验先设备卸放转运装置绝缘子运送耐压检验设备附名工绝缘子转运装置放耐压检验设备(图251)
样布置里名工两台设备间断返进行运送绝缘子工作样仅造成力浪费时间浪费等绝缘子位造成效率低
设备布置方式定耐压设备安装工位拉伸设备卸载工位合成工位安排方式两台设备间选择合适距离工拉伸检验完成绝缘子拉伸设备卸转身放置耐压检验设备样布置减少两工位缩短绝缘子两台检验设备中转运花费时间
两台设备间距离相隔太造成工转身便甚法进入工位相隔太远工仅仅身体转动完成转运程站姿双臂身作业空间(图223)里臂范围设备面关系两台设备间距离550mm根国成年体尺寸现行国家标准[3]查表718~60岁男性臀宽P99346mm设备距离允许范围346~550mm间两设备距离取500mm综考虑制出检验设备面布置图(图252)
图251 绝缘子放入耐压检验设备程
图252 检验设备面布置图
3检验设备零件加工工艺
31 动轴分析
311动轴作
动轴(图3111)耐压检验设备中零件位传动系统中作减速机传递运动动力通链轮传动检绝缘子进入检验区域φ90轴段位置安装传动齿轮φ100轴段位置安装调心球轴承φ110位置安装输送链轮
(图3111 动轴)
312零件工艺分析
零件图分析三组加工表面三组加工表面详细阐述:
(1)两端中心孔中心加工表面
组加工表面:两端中心孔轴端面加工表面作面加工定位基准中心孔
(2)轴头外圆面中心加工表面
组加工表面φ115轴段外圆面φ110轴段外圆面φ90轴段外圆面三键槽
(3)两轴段外圆面中心加工表面
组加工表面包括φ100轴段外圆面倒角
知组加工表面说先加工两端中心孔根中心孔轴线基准两组表面进行加工
32工艺规程设计
321确定毛坯制造形式
零件材料选45号钢考虑轴起支撑传动件传递转矩作强度求较高铸件机械性较差确保工作时稳定性加动轴零件产量批量生产毛坯材料选锻造成
322制定工艺路线
动轴工艺程表示:
工序
工序名称
工艺容
工艺装备
1
备料
截取棒料
普通车床
2
飞边
普通车床
3
中心孔
钻两端中心孔
钻床
4
粗车外圆
卧式车床C620
5
淬火加高温回火
硬度达220~240HBW
硬度计
6
半精车外圆
卧式车床C620
7
倒角
卧式车床C620
8
铣键槽
铣φ28键槽
X53T
9
铣键槽
铣φ25键槽
X53T
10
粗磨外圆面
普通磨床
11
精磨外圆面
普通磨床
12
毛刺
13
检验入库
323机械加工余量工序尺寸确定
轴零件材料45钢布氏硬度217~255生产类型批生产采锻件作毛坯
轴段需工序
φ90轴段
φ100轴段
φ110轴段
φ115轴段
φ110轴段
φ100轴段
粗车
粗车
粗车
粗车
粗车
粗车
半精车
半精车
半精车
半精车
半精车
半精车
铣键槽
铣键槽
铣键槽
粗磨
粗磨
粗磨
粗磨
粗磨
精磨
精磨
零件形状分析选择锻压形成45号钢棒料作加工毛坯
根零件长度直径查表粗车直径余量取8mm
半精车直径余量根轴段直径长度查表分:φ90轴段11mmφ100轴段11mmφ110轴段11mmφ115轴段12mmφ110轴段11mmφ100轴段11mm
轴段外圆粗磨余量查表φ90轴段04mmφ100轴段04mmφ110轴段04mmφ110轴段04mmφ100轴段04mm
φ100轴段精磨余量查表取02mm
轴段端面车削余量查表分φ90轴段端面12mmφ100轴段端面14mmφ110轴段端面12mmφ115轴段端面16mmφ110轴段端面12mmφ100轴段端面14mm
综述采φ12545钢棒料作毛坯
324确定切削量
(1)车外圆面
工步号
工步容
加工余量(mm)
基尺寸
济精度
01
粗车左端面
2
1195
IT12
02
粗车右端面
2
1242
IT12
03
粗车φ1195外圆面
8
1195
IT12
04
粗车φ1242左端面
2
1242
IT12
05
粗车φ1097外圆面
8
1097
IT12
06
粗车φ1195端面
2
1195
IT12
07
粗车φ995外圆面
8
995
IT12
08
粗车φ1097端面
2
1097
IT12
09
粗车φ1242外圆面
1242
IT12
10
粗车φ1195外圆面
8
1195
IT12
11
粗车φ1242右端面
2
1242
IT12
12
粗车φ1097外圆面
8
1097
IT12
13
粗车φ1195外端面
2
1195
IT12
14
半精车左端面
12
915
IT10
15
半精车右端面
14
1017
IT10
16
半精车φ915外圆面
11
915
IT10
17
半精车φ1017端面
14
1017
IT10
18
半精车φ1017外圆面
11
1017
IT10
19
半精车φ1115端面
12
1115
IT10
20
半精车φ1115外圆面
11
1115
IT10
21
半精车φ1162左端面
16
1162
IT10
22
半精车φ1017外圆面
11
1017
IT10
23
半精车φ1115端面
12
1115
IT10
24
半精车φ1115外圆面
11
1115
IT10
25
半精车φ1162端面
16
1162
IT10
26
半精车φ1162外圆面
12
1162
IT10
27
粗磨左端面
04
904
IT8
28
粗磨右端面
04
1006
IT8
29
粗磨φ904外圆面
04
904
IT8
30
粗磨φ1006外圆面
04
1006
IT8
31
粗磨φ1104外圆面
04
1104
IT8
32
粗磨φ1104外圆面
04
1104
IT8
33
粗磨φ1006外圆面
04
1006
IT8
34
精磨φ1002外圆面
02
1002
IT8
35
精磨φ1002外圆面
02
1002
IT6
(2)铣键槽
铣刀选直柄键槽铣刀(根GBT111211997)d8mmI16mmL60mm
采次行程铣键槽切入时进量选40mmmin垂直切入时进量14mmmin
4检验设备施工安装
确保项目质量安全性设置机械装置部件材料必须符合工程设计产品标准规定机械设备安装工程中采种计量检测器具仪器仪表设备必须遵相关国家标准精度等级应满足检测项目精度求
41机械设备安装前基础位置应符合求
机械设备基础位置尺寸应表41规定进行复检
表41 机械设备基础位置尺寸允许偏差
项目
允许偏差(mm)
坐标位置
20
面标高
020
面外形尺寸
±20
凸台面外形尺寸
020
凹穴尺寸
+200
面水度
米
5
全长
10
垂直度
米
5
全高
10
预埋脚螺栓
标高
+200
中心距
±2
预埋脚螺栓孔
中心线位置
10
深度
+200
孔壁垂直度
10
预埋活动脚螺栓锚板
标高
+200
中心线位置
5
带槽锚板水度
5
带螺纹孔锚板水度
2
42 放线位
设备面布置图位置分布完成放线
表421 机械设备定位基准面线点安装基准线面位置标高运行偏差
项目
允许偏差(mm)
面位置
标高
机械设备机械联系
±10
+20
10
机械设备机械联系
±2
±1
43找正调
设备找正调设备安装道重工序设备水度符合求时设备运转时会振动加剧噪音润滑良设备磨损速度加快设备寿命减少
431找正设备中心
设备基础致位根中心标板基准点挂设中心线中心线确定检查横水防线位置找正设备正确位置
设备中心找出检查设备中心基础中心位置否致果致需拨正设备拨正设备方法:撬杆拨正千斤顶拨正等
432水找正
设备调整标高时兼顾设备水找正水找正般水仪设备加工面进行找正
调整标高水度方法般设备垫铁设备升起调整设备水度标高外千斤顶设备起落达找正目
433项校正工作应测量方法
表433项校正工作应测量方法
校正项目
测量方法工具
测量精度范围
备注
直线度
拉钢丝
钢直尺测量
050
內径千分尺 导电测量
水面
003
垂直面
005
距离<8m
读数显微镜
002
距离<03mm
水仪
001
采径千分尺 导电测量
光学直仪
0005
校正长度>10m时分段进行
光学准直仪
002
需配置光靶定心器校正长度达30m
激光准直仪
距离m
精度m
提供见光测量方便激光纬仪测量校正长度较
20
005
20~40
010
40~70
020
面度等高度水偏差
尺
钢直尺测量
050
垂直面测量时距离<8m
径千分尺百分表测量
003
水仪
001
面较时水仪置尺测量
液体连通器
标尺测量
010
注意测量时间较长环境温度变化液体蒸发引起影响
深度千分尺
测量
002
光学准直仪
直线度校正
激光准直仪
直线度校正
轴度称度
尺塞尺
005
校正距离<15m直接读出偏心值
联轴器校正复核
003
校正距离<16m
检棒
001
校正长度1m误差直接测出
工艺轴百分表
002
工艺轴长度般<6m
专校正工具百分表塞尺
002
联轴器校正复核
光学准直仪
直线度校正
激光准直仪
直线度校正
垂直度
尺塞尺
005
漏光检查精度达002mm
吊线锤钢直尺测量
05
金属非金属垂线
吊钢丝垂线径千分尺导电测量
005
校正长度<2m
水仪
直线度校正
校具百分表
002
校具型式圆柱形圆形板型角尺形箱形工件形状相涂色检查百分表测量
行度
尺钢直尺
050
水仪尺
直线度校正
光学准直仪
直线度校正等高光靶代定心器
机械设备找正调定位基准面线点确定找正调程应确定测量位置进行检验做标记复检时应选择原测量位置进行测量免出现问题时产生异议
44脚螺栓
脚螺栓起牢固基基础机械设备连机器作防止运行中设备出现振动位移甚翻倒脚螺栓长度公式计算
L15D+S+(5~10) (式4111)
式中:L长度(mm)D直径(mm)S螺母机座厚度垫铁高度预留量总
脚螺栓应保证敷设时垂直度垂直偏差必须低百分
45脚螺栓施工方案
脚螺栓施工两种方案:预埋脚螺栓预留孔
第种方案通预埋脚螺栓方式等设备位脚螺栓加垫圈拧紧螺母脚螺栓埋放精度垂直度等求偏高出现偏差会设备难安装施工难度
第二种方案脚螺栓位置留预留孔先击钻转出螺栓直径应预留孔钻指定深度脚螺栓直接挂设备等设备位预留孔里灌混凝土固定住设备(图451)第种方案相第二种方案施工程更简单脚螺栓安装允许略误差调整较方便足混凝土凝固脚螺栓垂直度会发生偏差
图451预留孔灌浆方案示意图
出简便选择脚螺栓位置留预留孔方案
根检验设备面布置图位置数安装厂家车间找出规划位置做施工准备
选择预埋脚螺栓方案根设备受力估计设备尺寸分析安装中采型号M12x160 GB799螺栓位置分布图(452)出需4脚螺栓
图452螺栓位置分布图
先根图纸定位螺栓位置孔洞(空洞直径螺栓2mm)保证螺栓位置精确采钢尺定位
表451 脚螺栓直径预留孔尺寸关系
脚螺栓
长度L
螺栓直径d
M6
M8
M10
M12
M16
预留孔深度LH
80
100
100
120
140
140
160
180
180
180
180
220
240
240
240
260
300
320
320
320
400
420
420
420
500
520
520
预留方孔
80*80
80*80
80*80
80*80
100*100
螺纹长
2427
2831
3236
3640
4450
弯钩直径
22
26
35
44
52
根脚螺栓直径预留孔尺寸关系(表451)脚螺栓预埋放位置准备深度180mm尺寸80x80预留孔
膨胀螺栓螺栓分布图根途需两款型号膨胀螺栓拉伸设备处液压站重量较采M655 JBZQ 47632006型号膨胀螺栓4耐压检验设备重量面分布较采M16140 JBZQ 47632006膨胀螺栓28
46脚螺栓两种误差情况应措施
中心距偏差
脚螺栓埋设坏直接影响设备安装质量设备标高位置准确性求严特动化程度高联动设备求更严脚螺栓埋设设备安装前必须进行检查矫正
测量掉螺栓数时发现中心距偏差超合理范围时首工作凿子剔螺纹附混凝土般求剔掉身直径8~15倍厚度混凝土点燃氧乙炔火焰弯曲部位烤850摄氏度左右千斤顶者锤进行校正校正完成增焊钢板弯曲部位避免受力螺栓会出现拉直现象重新灌混凝土
标高偏差
(1)标高正偏差高允许值时应先切掉部分(高出部分)重新加工制出螺纹套螺纹时防止油类滴混凝土基础腐蚀影响基础质量
(2)果螺栓偏低偏差值时(15mm)应先部分混凝土凿掉然氧乙炔火焰螺栓烤红拉长螺栓螺纹外方拉长方法两迭垫板作支座方架块中间孔钢板套脚螺栓面螺母拧紧助拧紧螺母力量螺栓烤红处拉长然直径缩处两旁焊接两条加强细钢筋作加固设备已放基础搬动便机座凸缘强度足够情况直接底座拧紧螺母螺栓拉长拧适长度必须螺母松开免螺栓冷拉力甚压裂底座凸缘
(3)果螺栓低时(低求高度15mm) 加热法拉长螺栓周边挖深坑距离坑底约100mm处螺栓切断焊新制作螺栓标高符合求然钢筋加固钢筋长度般螺栓直径4~5倍处理完重新浇灌混凝土
(4)脚螺栓基础松动拧紧脚螺栓时螺栓拔活时应先螺栓调增原位置然螺栓焊横两U形钢筋水坑清洗干净灌浆凝固拧紧螺母
47拉伸试验设备安装
拉伸检验设备安装分两阶段第阶段厂家时调试阶段第二阶段现场安装阶段
设备部件生产厂家完成生产需现场先进行调试确保液压站等部件工作正常防止某部件安装工作异常造成安装程需返工生产厂家调试液压站时需先做时固定进行试车完成调试部件装箱附脚螺栓等紧固件运安装现场
运安装现场通面布置图放线确认膨胀螺栓应位置铅笔水泥做标记击钻换膨胀圈直径相钻头击钻水泥液压站等部件安装固定位置钻孔深度应膨胀螺栓长度稍微深等部件位拧紧六角螺母完成液压站固定脚螺栓采预留孔安装方案预留孔施工已提前完成需机架放应脚螺栓预留孔位置预留孔里灌满混凝土然安装拉伸检验结构部件安装完设备水度垂直度进行测量调整脚螺栓设备进行调找正预留孔安装方案方便调整水度垂直度中心距偏差调整误差允许范围等混凝土凝固设备固定完成
48耐压检验设备安装
拉伸检验设备样耐压检验设备安装分厂家调试阶段现场安装施工阶段
拉伸检验设备厂家阶段调试外需完成部分加工生产厂家种加工设备齐全想着安装工序现场施工做会发现缺少设备工具总意思会造成运输困难运输程导致部件损坏前提厂家时完成安装现场安装时需设备工具少检验工艺里求绝缘子电检时间5分钟设计时便运输制造设备分成许节节需现场调试异常出厂生产单位中需先设备进行时固定找正开始试车方便现场安装节接缝面钻两ø10销孔厂家调试完成销取出拆开销带
现场安装时先根图里位置应脚螺栓预留孔里电机减速器位然现场预留孔里浇灌混凝土紧固脚螺栓然设备位通生产单位预留销孔节销孔节销孔碰起销插设备基拉直然设备方击钻直接水泥钻孔膨胀螺栓拧起实现设备固定调试遍检查两条链否行行机尾位置活动轴承座调节采取目视调等两条链致行固定死
参考文献
[1]吴光亚.国绝缘子发展现状应考虑问题[J].西安:电瓷避雷器2010(2) 711
[2]林俊标.输电线路瓷绝缘子掉串事分析防范措施[J].广东:广东输电变电技术2005(2) 3942
[3]GBT 100001988.中国成年体尺寸[S].北京:国家技术监督局1989
[4]GB 502312009 机械设备安装工程施工验收通规范[S] 北京:中国机械工业联合会 2009
附 录
附录1外文原文译文
How Machine Learning Can Augment the Work of Clinicians
PROGNOSIS
A machinelearning model can learn the patterns of health trajectories of vast numbers of patients This facility can help physicians to anticipate future events at an expert level drawing from information well beyond the individual physician’s practice experience For example how likely is it that a patient will be able to return to work or how quickly will the disease progress At a population level the same type of forecasting can enable reliable identification of patients who will soon have highrisk conditions or increased utilization of health care services this information can be used to provide additional resources to proactively support them
Large integrated health systems have already used simple machinelearning models to automatically identify hospitalized patients who are at risk for transfer to the intensive care unit and retrospective studies suggest that more complex and accurate prognostic models can be built with raw data from EHRs and medical imaging
Building machinelearning systems requires training with data that provide an integrated longitudinal view of a patient A model can learn what happens to patients only if the outcomes are included in the data set that the model is based on However data are currently siloed in EHR systems medical imaging picture archiving and communication systems payers pharmacy benefits managers and even apps on patients’ phones A natural solution would be to systematically place data in the hands of patients themselves We have long advocated for this solution which is now enabled by the rapid adoption of patientcontrolled application programming interfaces
Convergence of a unified data format such as Fast Healthcare Interoperability Resources (FHIR) would allow for useful aggregation of data Patients could then control who had access to their data for use in building or running models Although there are concerns that technical interoperability does not solve the problem of semantic standardization endemic in EHR data the adoption of HTML (Hypertext Markup Language) has allowed Web data which are perhaps even messier than EHR data to be indexed and made useful with search engines
DIAGNOSIS
Every patient is unique but the best doctors can determine when a subtle sign that is particular to a patient is within the normal range or indicates a true outlier Can statistical patterns detected by machine learning be used to help physicians identify conditions that they do not diagnose routinely
The Institute of Medicine concluded that a diagnostic error will occur in the care of nearly every patient in his or her lifetime and receiving the right diagnosis is critical to receiving appropriate care This problem is not limited to rare conditions Cardiac chest pain tuberculosis dysentery and complications of childbirth are commonly not detected in developing countries even when there is adequate access to therapies time to examine patients and fully trained providers
With data collected during routine care machine learning could be used to identify likely diagnoses during a clinical visit and raise awareness of conditions that are likely to manifest later However such approaches have limitations Less skilled clinicians may not elicit the information necessary for a model to assist them meaningfully and the diagnoses that the models are built from may be provisional or incorrect may be conditions that do not manifest symptoms (and thus may lead to overdiagnosis) may be influenced by billing or may simply not be recorded However models could suggest questions or tests to physicians on the basis of data collected in real time these suggestions could be helpful in scenarios in which highstakes misdiagnoses are common (eg childbirth) or when clinicians are uncertain The discordance between diagnoses that are clinically correct and those recorded in EHRs or reimbursement claims means that clinicians should be involved from the outset in determining how data generated as part of routine care should be used to automate the diagnostic process
Models have already been successfully trained to retrospectively identify abnormalities across a variety of image types However only a limited number of prospective trials involve the use of machinelearning models as part of a clinician’s regular course of work
TREATMENT
In a large health care system with tens of thousands of physicians treating tens of millions of patients there is variation in when and why patients present for care and how patients with similar conditions are treated Can a model sort through these natural variations to help physicians identify when the collective experience points to a preferred treatment pathway
A straightforward application is to compare what is prescribed at the point of care with what a model predicts would be prescribed and discrepancies could be flagged for review (eg other clinicians tend to order an alternative treatment that reflects new guidelines) However a model trained on historical data would learn only the prescribing habits of physicians not necessarily the ideal practices To learn which medication or therapy should be prescribed to maximize patient benefit requires either carefully curated data or estimates of causal effects which machinelearning models do not necessarily — and sometimes cannot with a given data set — identify
Traditional methods used in comparative effectiveness research and pragmatic trials have provided important insights from observational data However recent attempts at using machine learning have shown that it is challenging to generate curated data sets with experts update the models to incorporate newly published evidence tailor them to regional prescribing practices and automatically extract relevant variables from EHRs for ease of use
Machine learning can also be used to automatically select patients who might be eligible for randomized controlled trials on the basis of clinical documentation or to identify highrisk patients or subpopulations who are likely to benefit from early or new therapies under study Such efforts can empower health systems to subject every clinical scenario for which there is equipoise to more rigorous study with decreased cost and administrative overhead
CLINICIAN WORKFLOW
The introduction of EHRs has improved the availability of data However these systems have also frustrated clinicians with a panoply of checkboxes for billing or administrative documentation clunky user interfaces increased time spent entering data and new opportunities for medical errors
The same machinelearning techniques that are used in many consumer products can be used to make clinicians more efficient Machine learning that drives search engines can help expose relevant information in a patient’s chart for a clinician without multiple clicks Data entry of forms and text fields can be improved with the use of machinelearning techniques such as predictive typing voice dictation and automatic summarization Prior authorization could be replaced by models that automatically authorize payment based on information already recorded in the patient’s chart The motivation behind adopting these abilities is not just convenience to physicians Making the process of viewing and entering the most clinically useful data frictionless is essential to capturing and recording health care data which in turn will enable machine learning to help give the best possible care to every patient Most importantly increased efficiency ease of documentation and improved automated clinical workflow would allow clinicians to spend more time with their patients
Even outside the EHR system machinelearning techniques can be adapted for realtime analysis of video of the surgical field to help surgeons avoid critical anatomical structures or unexpected variants or even handle more mundane tasks such as accurate counting of surgical sponges Checklists can prevent surgical error and unstinting automated monitoring of their implementation provides additional safety
In their personal lives clinicians probably use variants of all these forms of technology on their smartphones Although there are retrospective proofofconcept studies of application of these techniques to medical contexts the major barriers to adoption involve not the development of models but technical infrastructure legal privacy and policy frameworks across EHRs health systems and technology providers
EXPANDING THE AVAILABILITY OF CLINICAL EXPERTISE
There is no way for physicians to individually interact with all the patients who may need care Can machine learning extend the reach of clinicians to provide expertlevel medical assessment without personal involvement For example patients with new rashes may be able to obtain a diagnosis by sending a picture that they take on their smartphones thereby averting unnecessary urgentcare visits A patient considering a visit to the emergency department might be able to converse with an automated triage system and when appropriate be directed to another form of care When a patient does need professional assistance models could identify physicians with the most relevant expertise and availability Similarly to increase comfort and lower cost patients who otherwise may need to be hospitalized could stay at home if machines can remotely monitor their sensor data
The delivery of insights from machine learning directly to patients has become increasingly important in the areas of the world where access to direct medical expertise is in limited supply and sophistication Even in areas where the supply of expert clinicians is abundant these clinicians are concerned about their ability and the effort required to provide timely and accurate interpretation of the tsunami of patientdriven digital data from sensor or activitytracking devices worn by patients Indeed one of the hopes with regard to machinelearning models trained with data from millions of patient encounters is that they can equip health care professionals with the ability to make better decisions For instance nurses might be able to take on many tasks that are traditionally performed by doctors primary care doctors might be able to perform some of the roles traditionally performed by medical specialists and medical specialists could devote more of their time to patients who would benefit from their particular expertise
A variety of mobile apps or Web services that do not involve machine learning have been shown to improve medication adherence and control of chronic diseases However machine learning in directtopatient applications is hindered by formal retrospective and prospective evaluation methods
机器学医学中应
病情预断
机器学模型学量患者健康轨迹模式该功帮助医生专家医师实践验外信息中获取专家级未事件例患者够重返工作性者疾病发展速度快?口水相类型预测识发生高危疾病增加医疗保健服务利率患者信息提供资源积极帮助
型综合医疗系统已简单机器学模型动识转移重症监护病房住院患者回顾性研究表明理台医学成原始数构建更复杂准确预模型医学图
建立机器学系统需提供患者综合视图数进行培训结果包含模型基数集中时模型解患者会发生什然目前数理台系统医学成图片存档通信系统付款药房福利理甚患者电话应程序中孤立然解决方案系统数放患者手中直张种解决方案现通快速采患者控制应程序编程接口实现
统数格式(快速医疗保健互操作性资源)融合允许数聚合然患者控制谁访问数构建运行模型担心技术互操作性解决理台数中特语义标准化问题超文标记语言采理台数更混乱网页数够索引搜索引擎
诊断
位患者独二医生确定患者特微妙征兆时正常范围指示出真正异常值通机器学检测统计模式否帮助医生识法常规诊断疾病?
医学研究出结位患者生护理中会出现诊断错误接受正确诊断接受适护理关重问题罕见情况发展中国家足够治疗手段足够时间检查患者接受充分培训提供者通常会发现心脏性胸痛肺结核痢疾分娩发症
通常规护理期间收集数机器学识床访视期间诊断提高稍出现病症认识方法局限性技欠佳床医生会获取模型需必信息效帮助建立模型诊断时正确没表现出症状(导致度诊断)会受账单影响根记录然模型基实时收集数医生提出问题测试建议助高风险误诊常见(例分娩)床医生确定情况床正确诊断理台报销索赔中记录诊断间致意味着床医生应该开始参确定作常规护理生成数动化诊断程
已成功训练模型回顾性识种图类型异常限前瞻性试验涉机器学模型作床医生常规工作部分
治疗
拥数万名医生治疗数千万患者型医疗保健系统中时医治疗具类似状况患者存差异模型否通然变化进行分类帮助医生确定集体验时指首选治疗途径?
种直接应护理时开处方模型预测开处方进行较标记出差异进行审查(例床医生倾订购反映新指南代疗法)基历史数训练模型仅学医师处方惯定学理想做法解应开出种药物治疗方法程度患者受益需精心挑选数估计果效应种机器学模型定(时法定数集)确定
较效性研究实试验传统方法提供观察数重见解然机器学尝试表明专家起生成策划数集更新模型包含新发布证定制区域处方实践动理台中提取相关变量便种做法具挑战性
机器学根床文档动选择资格进行机试验患者识受益研究早期新疗法高风险患者亚群样努力卫生系统够床方案进行治疗方案适合进行更严格研究时降低成理开销
床医生工作流程
电子病历引入提高数性系统床医生感厌烦量计费理文档复选框笨拙户界面数输入时间增加新医疗错误出现率
消费产品中相机器学技术提高床医生效率驱动搜索引擎机器学帮助床医生患者图表中公开相关信息需次单击表单文字段数输入通机器学技术(例预测输入语音识动汇总)改善基已记录患者图表中信息动授权付款模型代事先授权采功动机仅仅医生带便利获取记录床数程变畅捕获记录医疗保健数关重反机器学够帮助位患者获佳护理重提高效率简化文档记录改进动化床工作流程床医生更时间花患者身
理台系统外机器学技术适手术领域视频实时分析帮助外科医生避免关键解剖结构意外变形甚处理更务例准确计数手术海绵检查表防止手术错误实施动监测提供额外安全性
生活中床医生会智手机形式技术变体然技术应医学背景回顾性概念验证研究采障碍模型开发技术基础设施电子病历中法律隐私政策框架卫生系统技术提供者
扩床专业知识性
医生法需护理需护理患者单独互动机器学否扩展床医生覆盖范围没参情况提供专家级医疗评估?例患新皮疹患者够通发送智手机拍摄片获诊断避免必门诊找医生诊断考虑急诊科诊患者够动分流系统适时引导种形式护理中患者确实需专业帮助时模型识具相关专业知识性医生样提高舒适度降低成果机器远程监控传感器数需住院患者留家中
世界直接供应限复杂医疗专业知识区机器学直接患者提供见解变越越重专家床医生供应丰富区床医生担心力患者佩戴传感器活动踪设备时准确解释患者驱动海量数需精力确关机器学模型训练成数百万患者数种希医疗保健专业员具做出更决策力例护士够承担传统医生执行许务初级保健医生够执行传统医学专家执行角色医学专家更时间花特定专业知识
已证明涉机器学种移动应程序网页改善药物赖性控制慢性病
文档香网(httpswwwxiangdangnet)户传
《香当网》用户分享的内容,不代表《香当网》观点或立场,请自行判断内容的真实性和可靠性!
该内容是文档的文本内容,更好的格式请下载文档