Unit health

Scores HVAC units 0 to 100 from meter data. Features from 3 years at Rheem. Built by Alvin Alias.

497 units / 2.88M readings Isolation Forest with an LOF cross-check · no failure labels
AA-2026-04
model waking, first run may take up to a minute
Fleet snapshot · 497 units

The fleet · 497 units, scored from the meter study

pulling the fleet

-- high attention
-- elevated
-- watch
-- normal
-- total

Draws a complete historical reading from curated normal, watch, elevated, and high-attention examples.

Enter readings yourself 


        

          Recent pulls
          

            
Recent pulls

            

              
            

          

        

      


      

        

          --
          health
          
        


        


        

        
        

        

          What moved this score
          

            
What moved this reading score

            

          

        

      

    


    

      

        Calibration record · sensitivity checks and detector agreement
        

          
            
2,876,400 hourly readings scored · 4.18M raw, filtered for rolling-history coverage

            
497 units with at least 90 days of coverage

            
Anomaly rate 5.0% at contamination 0.05 · every point flagged at 0.02 stays flagged at 0.05

            
Unit baseline scores 35.0 to 74.0, median 58.6 · fleet strip shown as rank-relative bands

            
LOF vs Isolation Forest agreement 91.3% on a 100k sample

            
Top factor: 24-hour COP volatility, an intermittent-fault signature, outranking COP level itself

          
        

      

      

        How it works · COP, delta-T, load ratio, from the Rheem years
        
the features are the physics I watched at Rheem: COP as the single best efficiency signal, supply delta-T narrowing as coils foul, refrigerant delta-T widening as charge depletes, load ratio because high load plus falling COP is the danger zone; Isolation Forest scores, LOF cross-checks, no labels required.

      

      

        Notes · no failure labels exist; this reads anomaly structure
        
    
          
  1. This ML demo sleeps after extended inactivity. First wake can take a moment; runs after that are quick.
    2. 
          
  2. No failure labels exist in this data. The score reads anomaly structure, and the LOF cross-check is the only independent witness, which is why it prints with every run.
    3. 
          
  3. The fleet board is a scored snapshot of the study data, not a live feed; every unit on it is real and every score was computed by the model.
    4. 
          
  4. Demo scoring uses complete historical readings with rolling context; manual scoring estimates rolling context from the entered COP and load values.
    5.