Metric
Heating performance coefficient
- Value
- 1.38W/W
- Condition
- 25°C ambient, 250m³/h airflow, 150°C setpoint
- Why it matters
- Measured in an accredited lab and suitable for procurement evidence.
Deployable dual technology solutions
Warmth + Vision
From purchasable heating sheets and warm-care products to scenario-trained vision models, Runxintian helps customers bring safety, occupational health, and operational efficiency into real sites.
Heating COP 1.38W/W1M+ flex cyclesCNAS L1045Conditioned fire-smoke metricsEstablished 2021-04-13
Bandgap heating use
Wearable warmth
Custom vision system
AI vision, field-ready
Heating COP 1.38W/W
1M+ flex cycles
CNAS L1045
Core Offerings
Choose by need: buy heating products or customize recognition models
Bandgap heating solves warm-care, cold protection, and product development needs; custom AI vision solves fire alerts, inspection, maturity grading, and safety behavior recognition.
Purchasable heating core
Wearable warmth
Buyers can validate efficiency, flex durability, water resistance, low voltage, and battery safety before extending the platform into knee supports, vests, insoles, waist supports, and more.
1.38W/W
Verified COP
IPX7
Water resistance
-20℃
Low-temperature operation
Occupational protection
Wearable thermal protection for fisheries, oil fields, forestry, and cold-chain environments.
Safety-first engineering
Solid-state batteries, low-voltage power, NTC control, and anti-scald logic create a safer foundation.
Commercialized product matrix
Six products cover industrial workers, outdoor users, and senior-care scenarios.
Models trained for customer scenes
AI vision, field-ready
Beyond standardized VisionFire, the service supports apple ripeness, pinecone maturity, industrial defects, safety behavior, and other custom target recognition.
96.8%
Sample-conditioned accuracy
<3%
Scene-tuned false-alarm target
Quarterly updates
Update cadence
Scenario-specific training
Models are tuned to customer risk sources, camera perspectives, and false-positive patterns.
Flexible deployment
Supports non-intrusive access, edge deployment, private servers, or API integration.
Ongoing model operations
Quarterly reviews prevent the model from drifting away from real operations.
Compliance & Verification
Building trust through verifiable empirical data
All metrics include conditions or context notes
1.38W/W
Heating performance coefficient
At 25°C ambient, 250m³/h airflow, and 150°C setpoint
100万次+
Bending life
Laboratory flex testing
96.8%
Accuracy under sample conditions
Based on current training and validation records, not an unconditional guarantee for every site
<3%
Scene-tuned false-alarm target
Requires review against camera angles, lighting, and site interference
50+
Served enterprise accounts
Across chemicals, manufacturing, logistics, and more
Core technical parameters
Transparent and precise technical specifications
Every metric includes conditions, deployment context, or a business explanation to support procurement and compliance review.
Bandgap heating parameters
| Metric | Value | Condition | Why it matters |
|---|---|---|---|
| Heating performance coefficient | 1.38W/W | 25°C ambient, 250m³/h airflow, 150°C setpoint | Measured in an accredited lab and suitable for procurement evidence. |
| Bending durability | 1,000,000+ cycles | Lab flex-life testing | Well beyond traditional wire-based solutions for repeated wear and folding. |
| Temperature control | 38-42°C constant heat with ±1°C precision | NTC precision sensing | Safer for seniors and extended wear by reducing overheating risk. |
| Far-infrared care | Supported | Verified by spectral analysis | Adds comfort-care value alongside thermal performance. |
| Waterproof rating | IPX7 | Sealed structure | Suitable for fisheries, cold-chain operations, and wet environments. |
| Battery safety | Solid-state battery, impact resistant | Impact and thermal-runaway testing | Reduces combustion risk at the source for enterprise buyers. |
| Cold-weather operation | Operates at -20°C | Low-temperature discharge testing | Supports extreme winter outdoor work. |
| Low-voltage safety design | 5V low-voltage power, far below the 36V human-safety threshold | Product safety design note | Makes anti-scald, low-voltage, and timer protection explicit for buyers. |
Metric
Bending durability
- Value
- 1,000,000+ cycles
- Condition
- Lab flex-life testing
- Why it matters
- Well beyond traditional wire-based solutions for repeated wear and folding.
Metric
Temperature control
- Value
- 38-42°C constant heat with ±1°C precision
- Condition
- NTC precision sensing
- Why it matters
- Safer for seniors and extended wear by reducing overheating risk.
Metric
Far-infrared care
- Value
- Supported
- Condition
- Verified by spectral analysis
- Why it matters
- Adds comfort-care value alongside thermal performance.
Metric
Waterproof rating
- Value
- IPX7
- Condition
- Sealed structure
- Why it matters
- Suitable for fisheries, cold-chain operations, and wet environments.
Metric
Battery safety
- Value
- Solid-state battery, impact resistant
- Condition
- Impact and thermal-runaway testing
- Why it matters
- Reduces combustion risk at the source for enterprise buyers.
Metric
Cold-weather operation
- Value
- Operates at -20°C
- Condition
- Low-temperature discharge testing
- Why it matters
- Supports extreme winter outdoor work.
Metric
Low-voltage safety design
- Value
- 5V low-voltage power, far below the 36V human-safety threshold
- Condition
- Product safety design note
- Why it matters
- Makes anti-scald, low-voltage, and timer protection explicit for buyers.
Custom AI vision parameters
| Metric | Value | Condition | Why it matters |
|---|---|---|---|
| Fire recognition accuracy | 96.8% | Based on current training and validation records | Communicates capability under current sample conditions, not an unconditional guarantee for every site. |
| False alarm rate | <3% | Tuned separately for chemical plants, charging sites, and small premises | Presented as a scene-tuning target that still requires review against real camera angles, lighting, and interference. |
| Alert response time | Real-time / near-real-time | Real-time or near-real-time modes | Response mode depends on site network, edge nodes, and deployment form. |
| Lead time | Project-record based | Requires confirmation through real-scenario review | Prevents demo or sample conclusions from becoming formal site promises. |
| Model update cadence | Quarterly updates | Updated based on business and model changes | Moves from one-off delivery to ongoing capability growth. |
| Deployment modes | Non-intrusive / edge / private / API | Supports offline training and local deployment | Balances security, IT fit, and rollout speed. |
| Custom use cases | Apple ripeness / Pinecone maturity / Industrial defects / Safety behavior | Self-supervised Learning & Few-shot Object Detection | Enables rapid cold-start with minimal samples, reducing training cycles and data costs. |
Metric
Fire recognition accuracy
- Value
- 96.8%
- Condition
- Based on current training and validation records
- Why it matters
- Communicates capability under current sample conditions, not an unconditional guarantee for every site.
Metric
False alarm rate
- Value
- <3%
- Condition
- Tuned separately for chemical plants, charging sites, and small premises
- Why it matters
- Presented as a scene-tuning target that still requires review against real camera angles, lighting, and interference.
Metric
Alert response time
- Value
- Real-time / near-real-time
- Condition
- Real-time or near-real-time modes
- Why it matters
- Response mode depends on site network, edge nodes, and deployment form.
Metric
Lead time
- Value
- Project-record based
- Condition
- Requires confirmation through real-scenario review
- Why it matters
- Prevents demo or sample conclusions from becoming formal site promises.
Metric
Model update cadence
- Value
- Quarterly updates
- Condition
- Updated based on business and model changes
- Why it matters
- Moves from one-off delivery to ongoing capability growth.
Metric
Deployment modes
- Value
- Non-intrusive / edge / private / API
- Condition
- Supports offline training and local deployment
- Why it matters
- Balances security, IT fit, and rollout speed.
Metric
Custom use cases
- Value
- Apple ripeness / Pinecone maturity / Industrial defects / Safety behavior
- Condition
- Self-supervised Learning & Few-shot Object Detection
- Why it matters
- Enables rapid cold-start with minimal samples, reducing training cycles and data costs.
Commercial product matrix
Heating products ready for procurement and sampling
Wearable thermal products cover six warming SKUs that can be selected by role, audience, and channel.
Product
Heated Knee Support
Far-infrared heat and flexible support for cold-weather work and senior joint comfort.
38-42°CFar infraredFlexible fit
Product
Heated Vest
A 360° thermal layer for the torso, designed for cold industrial work and winter activity.
360° warmthOutdoor workLayer-ready
Product
Heated Insole
An insole-core thermal management system delivering 42°C constant warmth and 12+ hours of runtime at 0°C.
42°C constant12+ hours1000mAh battery
Product
Heated Waist Support
A waist-focused thermal support for sedentary work, heavy labor, and recovery use.
Waist careFlexible wearDaily use
Product
Heated Sleeping Bag
A lightweight heated sleeping bag for camping, emergency response, and overnight home warmth.
70g fill-10°C supportEmergency-ready
Product
Heated Seat Cushion
A portable, detachable, solid-state battery cushion for wheelchairs, home care, and outdoor rest.
PortableSafe batterySenior friendly
Huiyan VisionFire Systems
Start with VisionFire, then expand into more custom recognition targets
The standardized fire-monitoring offer makes AI value easy to assess, then expands into defects, maturity grading, and safety behavior recognition.
VisionFire
Fire and smoke risk recognition with traceable alert handling
Connect camera intake, fire-smoke recognition, alert delivery, response records, evidence archive, and reporting into one traceable duty workflow.
Real platform screenshots
For hazchem, storage, and small-premises sites
Assists duty teams without automating fire-control systems
Camera intake
Connect existing cameras, streams, or edge nodes with minimal site changes.
Fire-smoke recognition
Recognize suspected smoke, flame, and critical-zone anomalies with sample-condition notes.
Alert delivery
Send risk alerts to the console and duty channel instead of stopping at detection.
Does not replace statutory fire systems：The system is for risk recognition, alerting, evidence retention, and response support.
Scenario
Hazchem and lithium sites
Specialized negative-sample training addresses steam, welding glare, and complex heat sources to reduce false alarms in high-risk plants.
Scene tuned
False-alarm control
Human review
Response boundary
Quarterly
Model review
Scenario
Charging and storage sites
Focuses on early thermal runaway warnings and headlight suppression for more reliable station-level monitoring.
Project review
Warning window
Real-time
Monitoring mode
API
Integration mode
Scenario
Small-premises scenario
For workshops, timber sites, and small shops where budgets are tight but risk remains real, with an emphasis on affordable deployment.
Standard template
Scenario package
Light deployment
Deployment mode
Policy friendly
Policy fit
Delivery process
From feasibility review to quarterly updates, keeping AI capability usable over time
Our standardized delivery framework and technical support ensure your customized AI algorithm is deployed rapidly and reliably.
1
Discovery | 1-2 business days
Clarify industry, risk points, camera conditions, and target outputs to decide between standardized products and custom modeling.
2
Data collection and labeling
Work with the customer to complete the dataset, especially around false-positive triggers and high-risk targets.
3
Training and validation | 2-4 weeks
Tune accuracy, false alarms, and inference latency in iterative validation rounds.
4
Deployment and integration
Deploy on private servers, edge nodes, or integrate through APIs.
5
Quarterly optimization
Continue improving models and alert thresholds based on field feedback and scenario changes.
Case studies
Real-world cases validating technical capabilities and commercial value
Proven track records across fire monitoring, occupational health gear, and custom industrial QA, with fully transparent results.
Huiyan VisionFire3%
Chemical plant fire-monitoring optimization in Maoming
Pain point: A previous AI system produced nearly 30% false alarms and frequent shutdown checks.
Solution: Deployed VisionFire with dedicated negative training for steam and welding glare.
Outcome: Project review records show scene tuning reduced false alarms below 3% and produced safety-review materials.
Full customer name is withheld by request; verification materials can be provided offline.
Wearable thermal products76%
Deck thermal protection upgrade for an offshore fisheries company
Pain point: Wet cold decks caused a high frost-risk rate and traditional warm gear performed poorly in moisture.
Solution: Provided a 42°C heated insole and heated vest bundle for deck and shift use.
Outcome: Project feedback records show frost-related incidents dropped by 76%, with improved comfort during prolonged wet-cold shifts.
Full customer name is withheld by request; scenario proof can be provided offline.
Custom AI vision300%
Defect detection model for an automotive parts plant
Pain point: Manual inspection was slow, inconsistent, and missed defects.
Solution: Delivered a custom defect-detection model with quarterly iteration against new process changes.
Outcome: Pilot review records show inspection efficiency improved by about 300%, with missed defects down to 0.5%.
Full customer name is withheld by request; implementation proof can be provided offline.
Business identity
Company facts, grounded in real files
The site prioritizes the business license, test reports, and product files. Patents, copyrights, and marketing files are not promoted without proof.
License photo
Real file first, then proof materials
Legal identity fields are grouped on the About page. The homepage keeps the real license entry instead of large disconnected number cards.
Files and reports
Public reports and files first
This area shows currently connected public files and test evidence. CNAS and CMA references are stated as report or testing-organization evidence.
Proof point
CNAS accredited laboratory certificate
The testing organization is CNAS accredited and suitable for procurement evidence review.
Proof point
Inspection and testing qualification certificate
Inspection and testing qualification ID for tender and compliance review.
Proof point
Stamped bandgap heating equipment test report
Issued by Jianke Huanneng Technology Co., Ltd.; tested at 25°C, 250m³/h airflow, and 150°C setpoint with 590W heating output, 430.3W input, and 1.38W/W COP.
Download reportPDF | 5.2 MB
Proof point
Success Design Awards certificate
The 0.01 kWh heating pad received a Success Design Awards recognition in health and wellness.
Download certificatePDF | 342 KB