Metaheuristic-Optimized Conditional Diffusion Networks

for Industrial Sensor Data Synthesis: An Applied Computational

Intelligence Benchmark

Khaled Sh. Gaber1 Mahmoud Elshabrawy Mohamed1,*

1 Computer Science and Intelligent Systems Research Center, Blacksburg 24060, Virginia, USA

Received: March 26, 2026 Revised: May 31, 2026 Accepted: July 14, 2026 ⋆ Corresponding author

ABSTRACT

Synthetic industrial telemetry can alleviate scarcity and confidentiality constraints, but its value depends on more than

distributional similarity. Generated sequences must support downstream engineering analysis, limit disclosure risk,

and satisfy operational relations. This paper presents a reproducible three-axis benchmark and a differential-evolution

calibration layer for conditional denoising diffusion. Six generators–bootstrap resampling, a shrinkage-Gaussian

model, Fourier surrogates, a conditional variational autoencoder, a conditional diffusion model, and its calibrated

counterpart–are evaluated on chronologically partitioned manufacturing telemetry. The protocol covers 18,000

generated 80-minute windows and combines train-synthetic/test-real alarm classification, marginal and temporal

fidelity measures, record-proximity and membership-inference tests, and five engineering-rule audits. Differential

evolution selects four post-generation controls using validation data only. Relative to the uncalibrated diffusion

model, calibration reduces the aggregate physical-violation rate by 94.7% and the Wasserstein error by 29.2%,

while increasing mean downstream ROC–AUC by 0.009. The improvement is accompanied by a 0.073 increase in

membership-inference AUC and a small deterioration in autocorrelation error. Bootstrap resampling provides the

strongest mean predictive utility but exactly reproduces 77.9% of its outputs; the conditional variational autoencoder

attains the lowest Wasserstein error (0.046) with a 0.020% physical-violation rate. No generator dominates utility,

privacy, and plausibility simultaneously. Synthetic industrial data should therefore be selected through deploymentspecific

acceptance regions rather than a single realism score.

Keywords: Synthetic industrial data Conditional diffusion Differential evolution Industrial sensor data Privacy

auditing Physical plausibility Predictive maintenance Benchmark

1. INTRODUCTION

Industrial analytics often develops under a mismatch between

abundant routine telemetry and limited fault, alarm, or transition

records. Data sharing is further constrained by commercial

confidentiality, plant cybersecurity, and the possibility

that multivariate operating traces reveal production schedules

or equipment behavior. Synthetic data can support predictive

maintenance, quality monitoring, process simulation, and

model validation, but only when its intended use and associated

risks are examined explicitly [1, 2, 3, 4]. The availability

of a recent anonymized discrete-manufacturing corpus with

machine-level operational variables enables this question to

be studied with reproducible measurements rather than illustrative

samples [5].

Diffusion models have become a major generative paradigm