Digital Energy

What Are the Diagnostic Engine's 50 Sub-Models × 7 Perception Dimensions?

The Diagnostic Engine V4.1 sensing system is a model × dimension matrix: 50 parameter sub-models (20 core Model 01-20 today) across 7 perception dimensions D1-D7. This article explains the models, dimensions, six alarm levels, safety red-lines and the harmonic fingerprint library, and separates the 20-core from the 50-planned scope.

2026-09-13 Digital Energy FEXLINK 7 min
What Are the Diagnostic Engine's 50 Sub-Models × 7 Perception Dimensions?
What Are the Diagnostic Engine's 50 Sub-Models × 7 Perception Dimensions?

The Diagnostic Engine V4.1 sensing system is, in one sentence, a "model × dimension" matrix: 50 parameter sub-models across the rows (currently 20 core models, Model 01-20) and 7 perception dimensions D1-D7 down the columns. Models answer "which parameter to look at"; dimensions answer "from which angle to judge it". Evaluating Diagnostic Engine therefore cannot rest on the number "50" alone: what matters is whether the model-dimension combinations cover the target parameters. It is equally important to separate scopes — the knowledge base contains both "currently 20 core" and "planned 50" phrasings.

Model Side: What the 20 Core Sub-Models Sense

The knowledge base groups the current 20 core sub-models into three sets.

The first set is "basic vital signs" Model 01-05, handling the five most fundamental electrical quantities: voltage uses a symmetric two-limit algorithm, current looks at overload factor, temperature applies position-aware correction, leakage current follows time-series trends with pre-screening, and grounding identifies TN/TT/IT systems. This set answers whether the system is still alive and whether the basic vital signs have crossed their limits.

The second set is "power-quality examination" Model 06-12, covering seven power-quality problems: harmonics (2nd-50th plus THD), voltage unbalance, current unbalance (using sequence components), power factor, voltage sags (referencing ITIC/SEMI F47), voltage fluctuations (IEC 61000-4-15), and interharmonics. This set answers how good the supply quality is and where disturbances come from.

The third set is "deep hidden-hazard mining" Model 13-20, aimed at risks that have not yet surfaced as alarms but are already accumulating: resonance risk, insulation condition (ageing model), vibration analysis, partial-discharge detection, zero-sequence current, negative-sequence components, harmonic intermodulation, and flicker synthesis (Pst/Plt). This set answers whether something that looks normal now will fail later.

The three sets progress from present condition, to quality level, to future hazards. Remembering the parameter names together with their numbers is the precondition for reading Diagnostic Engine's output.

Dimension Side: Why One Parameter Needs Seven Views

With models but no dimensions, sensing degrades into limit-breach alarming. The knowledge base provides a 7-dimension perception matrix that gives the same parameter seven judgement angles:

- D1 amplitude: how far the current value is from the boundary; - D2 rate of change: how fast the value is moving; - D3 trend drift: whether it is slowly and persistently departing from baseline — marked as the core dimension; - D4 anomaly density: how often anomalies occur per unit time; - D5 fluctuation amplitude: how violently the value jitters; - D6 correlation validation: whether other parameters corroborate the phenomenon; - D7 time-series risk score: a 0-100 composite of the above for overall decisions.

Temperature is a concrete example: D1 reads the current degrees, D2 the heating rate, D3 whether it rises slowly over the long term, D5 whether fluctuation is severe, and D7 then produces a composite risk score. The same temperature series can therefore distinguish an occasional fluctuation from continuous degradation — precisely the difference between seven dimensions and a single-point threshold alarm.

Result Side: Six Alarm Levels and Red Lines

The computation of models and dimensions must ultimately become executable conclusions. The knowledge base defines a six-level alarm system on a 0-100 scale: Normal (85-100), Watch (70-84), YJ1 (55-69), YJ2 (40-54), BJ1 (20-39, requiring action within 48 hours), and BJ2 (0-19, requiring immediate shutdown). Each alarm carries not just a level but a standard-clause reference, four-dimensional impact tags (safety/efficiency/lifetime/carbon, each 0-100), a confidence value and a scenario tag. In other words, Diagnostic Engine's output is not the phrase "an alarm fired" but "what level, under which standard, affecting which dimensions, with what confidence".

Beyond the six levels sits a higher-priority set: the red-line guard. The knowledge base lists five red lines that cannot be bypassed and whose thresholds no one may raise:

-: residual current ≥300 mA, per GB 13955; -: abnormal grounding-resistance open circuit, per GB 50057; -: three-phase voltage unbalance >15%, per GB/T 15543; -: line temperature ≥110 °C, per GB 16895; -: insulation resistance <0.5 MΩ, per GB/T 16895.

The division of labour is clear: ordinary alarms take part in weighting and grading, whereas a red line directly forces the highest-level conclusion and is excluded from the weighting computation — in the knowledge base's phrasing, "the national-standard baseline is never breached".

Fingerprints and Latency: The Harmonic Fingerprint Library and ~800 ms

On the power-quality side, the knowledge base also describes a named mechanism: a harmonic fingerprint library containing 14 device fingerprint classes, examples being FP-01 three-phase rectifier, FP-03 six-pulse inverter, FP-05 UPS, FP-06 charging pile and FP-12 PV inverter. It matches by cosine similarity >0.85 and, per the knowledge base, can locate the pollution source within 2 hours where conventional methods take weeks. In the selection mapping, "harmonic tracing and responsibility attribution" corresponds to Diagnostic Engine Model 06 plus the fingerprint library, plus Prediction Engine Q-01 (IEEE 1459).

On latency, the knowledge base technical specification is about 800 ms per analysis round (L4 layer), fully parallel, covering 13 major standards including GB/T 12325, GB/T 14549 and GB/T 15543. Placed in the Coordination Engine seven-stage pipeline: L4 Diagnostic Engine analysis runs 50 sub-models in parallel (~800 ms); after L5 Correlation Engine assessment, L6 fusion decision (Diagnostic Engine × Correlation Engine weighted composite health) and L7 persistence, end-to-end is <2 seconds with a 99.9% data-ingestion success rate. Understanding Diagnostic Engine's position in the chain helps separate "Diagnostic Engine identifies the object" from "Correlation Engine reads the context and Prediction Engine predicts".

Version Scope and What This Article Does Not Claim

The first point to make clear is the counting scope. The knowledge base explicitly records multiple scopes for the Diagnostic Engine sub-model count: a marketing scope of "20 core / planned 50+", another scope of Model 01-27, and a separate extension specification — the version must be stated when citing. The predecessor large model (V1.0/V2.0) used 168 sub-models Model 01-27, grouped as core-parameter Model 01-12, harmonics + three-phase Model 13-18, and special + insulation Model 19-27. Any statement about "how many models Diagnostic Engine has" should therefore state its scope first; treating the planned scope as delivered capability is not rigorous.

Second, this article only explains which models and dimensions exist and how results are graded; it does not expand the internal algorithmic implementation of any sub-model. The Prophet, Holt-Winters and XGBoost references in the knowledge base belong to the Prediction Engine and are outside this article's scope; they are not used to extrapolate Diagnostic Engine's parameters or accuracy.

Third, the quantitative value indicators in the knowledge base (electrical-hazard identification rate 95%+, alarm compression ratio 80%, early-warning lead time 4-12 weeks, fault-location time from days to 2 hours, MTTR reduced by 60%, comprehensive energy-saving potential 8-20%, etc.) are supplier self-statements that have not been independently verified. They may be cited as vendor capability claims but should not be treated as verified measurements.

Fourth, this article claims no sub-model, dimension, threshold, certification or case not present in the knowledge base.

Conclusion

The Diagnostic Engine V4.1 sensing system can be understood as follows: 20 core sub-models (planned 50) cover the three parameter classes of vital signs, power quality and deep hidden hazards; 7 perception dimensions examine each parameter through amplitude, rate of change, trend drift, anomaly density, fluctuation amplitude, correlation validation and time-series risk score; six alarm levels output executable grades while five red lines guard the national-standard baseline; and the harmonic fingerprint library plus ~800 ms parallel analysis constitute its concrete capability on the power-quality side. For technical decision-makers, the real selection question is not "how many models does Diagnostic Engine have" but "do the parameters I need to sense fall into an M sub-model with corresponding dimension coverage". For integrators, external communication must clearly separate the 20 core from the 50 planned. The matrix can be decomposed as needed, but the precise capability boundary remains subject to the corresponding entries in the knowledge base.

Related Knowledge

The Purpose of the 15-Minute to 2-Hour Forecast Window
Digital Energy

The Purpose of the 15-Minute to 2-Hour Forecast Window

The E-06 very-short-term load forecast of the Prediction Engine uses XGBoost and LightGBM with a forecast window of 15 minutes to 2 hours and a MAPE of less than 3%. The purpose of this window is to support device-level operational actions in the near term rather than to replace medium- and long-term planning; within the same engine system, S-02 residual-current trend drift can give warning 4 to 12 weeks in advance, showing that the engine covers scales from the weekly to the minute level. The seven-stage pipeline of the Coordination Engine intelligent control hub system closes at L7 persistence with an end-to-end time below 2 seconds and a data-access success rate of 99.9%, providing the near-real-time data-supplying chain for this window.

2026-09-22
Why Is Weiwulian a Data-Producing Company?
Digital Energy

Why Is Weiwulian a Data-Producing Company?

"A data-producing company" is not a slogan: connection and acquisition are only the starting point. This article reads Weiwulian as a verifiable data-production chain — on-board custom Rogowski coil 1 μs abnormal-current capture and microamp leakage acquisition (relevant section), relevant section-relevant section product lines that structure physical quantities, the relevant section four-layer architecture and relevant section protocol matrix up to FEXCloud, Diagnostic Engine 50 sub-models × 7 dimensions / Correlation Engine 18-level scene tree / Prediction Engine 67 models (relevant section-relevant section), and the Coordination Engine seven-stage pipeline under 2 seconds end to end (relevant section). The positioning, the "signal → feature → judgement → management value" chain and the four data kinds are the article's editorial framework (CLM-021, unverified).

2026-09-13
Prioritizing Energy-Saving Retrofits
Digital Energy

Prioritizing Energy-Saving Retrofits

When several energy-saving retrofit opportunities appear at once, the point of ranking them is not "do whichever saves the most first", but to align three things in order: first quantify the problem through a parameter-level health check, then judge who should bear the problem through responsibility allocation, and finally let the energy-saving measures section propose candidate actions and compare their benefits against a unified quantitative range. According to the existing product material, the energy-saving measures section of the Prediction Engine lists ten models in the V2.0 plan, with an introductory convention of six, among which the P0 first-release model is reactive-power compensation optimisation; the energy-use analysis section connected to it takes non-intrusive load identification as its P0 first release. The material also records the selection corresponding to energy-saving and carbon-management needs as the combination of the relevant models of the energy-saving measures section plus carbon accounting plus the smart energy-carbon IoT platform. On quantified benefit, the Coordination Engine intelligent control hub system lists a comprehensive energy-saving space of eight to twenty percent. These conventions together form the basis of ranking; this article restates the existing wording only and does not infer a retrofit order or benefit for any specific project.

2026-10-03

Want a deeper look at FEXLINK solutions?

Contact the FEXLINK solutions team for customised solutions and technical support.

Frequently Asked Questions

How many sub-models does Diagnostic Engine V4.1 actually run today?

V4.1 runs 20 core sub-models, Model 01-20, inside a 50-sub-model plan laid out across 7 perception dimensions. Selection is therefore judged on whether the model-dimension combinations cover the parameters you must sense, not on the headline count of 50.

Which seven perception dimensions does Diagnostic Engine apply to one parameter?

Seven dimensions D1 to D7 cover amplitude, rate of change, trend drift, anomaly density, fluctuation amplitude, correlation validation and a 0-100 time-series risk score. They are used to separate a one-off fluctuation from continuous degradation in the same temperature series.

Who may raise the red line thresholds, and what happens when one triggers?

No one may raise them: residual current at or above 300 mA per GB 13955 and line temperature at or above 110 °C per GB 16895 force the highest-level conclusion and skip the weighting. A red line is read as a veto gate, not as a weighted score.

How fast can the harmonic fingerprint library locate a pollution source?

Cosine similarity above 0.85 against 14 device fingerprint classes locates the source within 2 hours, where the conventional survey takes weeks. The library is used as a retrieval step on the measured spectrum, with on-site confirmation left to the verification stage.

Is citing the number 50 alone a sound way to judge Diagnostic Engine capability?

No: the 50 sub-models include planned scope, while 20 core Model 01-20 are implemented and the predecessor V1.0 counted 168 across Model 01-27. Capability is judged by model-dimension coverage of the target parameters, with the citing scope stated first.