Despite the high durability level associated with reinforced concrete bridges, they are nonetheless susceptible to natural hazards and extreme events can impair their performance and serviceability throughout their lifespan. For that reason, maintenance, rehabilitation, and repair actions on existing structures are projected to rise and currently account for about 50% of the construction sector spending in most developed nations. To establish long-term maintenance schedules, it is vital to know the state of a structure and its degradation over time. Therefore, the monitoring of structures has become a necessary task to guarantee their use throughout their lifespan. Maintenance and inspection schemes depend on these systems that periodically or continuously collect information using chemical, optical, sound sensors, among others. However, the reliability of these sensors depends on environmental factors, durability, and even power outages. When any of these factors affect the sensors, their acquisition of information can be interrupted temporarily or permanently. This paper focuses on the competition of this missing data. The study uses one year of data from sensors monitoring a reinforced concrete structure that suffered interruptions in the acquisition processes. To reduce possible uncertainties that affect the analysis of the degradation of the materials and the reliability of the structures, the database of concrete electrical resistivity and concrete temperature of the sensors were analyzed, and time-series analysis method, artificial neural network models and generalized linear and non-linear models were used specifically to fill in the missing database values and perform predictions. Finally, the results are discussed, and recommendations are established for the application of this methodology for the analysis of the sensors used.