Baidu AI Cloud Manufacturing China Translated from Chinese

SANY Heavy Machinery Co., Ltd. (三一重机)

Predictive Maintenance

SANY needed to uphold its 'solve within one day' service standard for excavators and other machinery even when remote field engineers lacked deep experience and half of faults could not be diagnosed accurately without dispatching central experts onsite.

Before the project, as many as 50% of problems could not be diagnosed accurately.
Engineers can accept an app-submitted work order within 15 minutes.
If parts are needed, urgent demand can usually be met within 3 days.
If parts are not needed, issues can be resolved within 24 hours.

Reported impact

Business outcome

SANY scaled remote repair support across multiple machinery lines, reduced unnecessary expert travel, increased work-order throughput, and began turning maintenance sessions and media into reusable industrial knowledge.

  • Cost Reduction
  • Productivity Improvement
  • Scalability

Solution

SANY and Baidu AI Cloud built an industrial AR remote-assistance system that combines mobile apps, AR glasses, PC tools, and a web management console to support machinery repair. The solution uses audiovisual calling, cloud recording, call-center workflows, an enterprise knowledge base, and AR annotations so a remote expert can inspect a machine's digital model, mark suspected fault points, and guide an onsite engineer step by step. The project also had to integrate with SANY's CRM, PLM, and EVI systems so remote support could be digitized and managed transparently. In operation, an app-based service request is routed to engineers, who can arrive onsite quickly and resolve many issues with expert guidance instead of waiting for physical escalation. AI extensions such as the 'AI Little Bee' module and parts-authenticity photo verification further enrich the maintenance flow, turning previously experience-heavy service work into a repeatable, knowledge-backed remote maintenance process.

Data flow

Field engineers submit service requests through the app, then use AR devices and video links to stream live repair context to remote experts. Experts review digital models, annotate suspected fault points, push guidance back to the现场 engineer, and the resulting session data is recorded in the cloud and linked to enterprise service-management systems.

Solution architecture

3 components · 3 layers
  1. Compute
    • Intelligent Industrial Quality Inspection Supports AI-assisted inspection and authenticity-check capabilities inside the maintenance process.
  2. Serving
    • Industrial AR Remote Assistance System Provides the multi-end repair-assistance environment used for expert guidance, cloud recording, AR annotation, and knowledge-base access.
  3. Orchestration
    • Tiangong Edge-Cloud Integrated IoT Platform Supplies the cloud and IoT backbone that supports remote maintenance workflows and device connectivity.

Architecture clues

  • Core functions include audio-video calls, cloud recording, call-center workflows, knowledge-base access, and AR annotations
  • The platform spans app, AR glasses, PC, and web back-office endpoints
  • The solution integrates with CRM, PLM, and EVI systems for digitized service management

Evidence from the source

Before the project, as many as 50% of issues could not be diagnosed accurately and backend experts still had to travel onsite (original: 多达50%的问题无法准确诊断,还需要三一重机在后端的技术专家赶赴现场).
SANY and Baidu AI Cloud built an industrial AR remote intelligent repair system that combines AI and AR for remote diagnosis and maintenance of construction machinery (original: 三一重机联合百度智能云打造工业AR远程智能维修系统,通过"AI+AR"技术融合实现工程机械故障的远程诊断与维修).
The industrial AR remote-assistance system covers four platforms and includes audio-video calling, cloud recording, a call center, enterprise knowledge base, and AR annotation (original: “工业 AR 远程协助系统”涵盖了手机APP、AR眼镜、PC端和WEB管理后台四个平台,拥有音视频通话、云端录像、呼叫中心、企业知识库、AR标注等核心能力).
The system already handles more than 4,000 work orders each month, and except for factory-return cases, problems can be solved properly through the remote system (original: 每个月处理的工单量已经超过4000单,除了需要返厂维修的问题,都可以通过远程系统妥善解决).
The target was to integrate with SANY's existing CRM, PLM, and EVI systems and digitize remote support with AR smart glasses (original: 与三一现有的CRM/PLM/EVI系统集成…运用AR智能眼镜技术解放服务人员双手).
Transparency Evidence & methodology 95/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value95/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    5 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Baidu AI Cloud

    SANY Heavy Machinery Co., Ltd. (三一重机) customer story

    First-party
    https://cloud.baidu.com/customer/case/sany.html
    Source type
    Vendor-published customer story
    Published
    Apr 8, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Apr 8, 2026 · Baidu AI Cloud · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.