Method and system for determining the real-time flow into a wastewater pump station using analog level sensing technologies. An Accurate Level Generator mechanism supplies an accurate mean value out of multiple readings for each level used to calculate the volume between levels. Two consecutive levels are used to calculate the volume between them using an Accurate Flow Calculator and the time it took to get from one level to the other. A Real Time Inflow Calculator adds results regarding the pumps in operation and overflow events, which are ways for the water to exit the pumping station. At a water level approaching where the pumps start or stop, or when abnormal events occur, a Predictive Abnormal Event Adjuster replaces the highly probable abnormal Real Time Inflow Result by a more stable and possible value, which is the last one calculated plus its variation over time.

Method and system for determining the real-time flow into a wastewater pump station using analog level sensing technologies. An Accurate Level Generator mechanism supplies an accurate mean value out of multiple readings for each level used to calculate the volume between levels. Two consecutive levels are used to calculate the volume between them using an Accurate Flow Calculator and the time it took to get from one level to the other. A Real Time Inflow Calculator adds results regarding the pumps in operation and overflow events, which are ways for the water to exit the pumping station. At a water level approaching where the pumps start or stop, or when abnormal events occur, a Predictive Abnormal Event Adjuster replaces the highly probable abnormal Real Time Inflow Result by a more stable and possible value, which is the last one calculated plus its variation over time.

A data processing method and an array-type sensor, which relate to the technical field of semiconductors. The array-type sensor comprises a processing unit (120) and a plurality of sensing units (110), and the plurality of sensing units (110) are separately connected to the processing unit (120); the sensing units (110) are configured to receive external signals, convert the external signals into unit values, and send the unit values to the processing unit (120) according to a preset rule; the processing unit (120) is configured to perform data processing on the unit values by using a preset algorithm; and when the processed data or processing result sent to a receiving unit (210) meets a preset condition, the sensing units (110) are controlled to send the unit values to the receiving unit (210). The array-type sensor is enabled to perform certain processing on the received data and send same to a data receiver, thus reducing the amount of data received by the data receiver so as to reduce the receiving pressure and calculation pressure of the data receiver.

A modified version of a MEMS self-test procedure is presented that can be used to detect the amplitude and frequency of an external vibration from an ambient environment. The method implements processing circuitry that correlates an output sense signal, s(t), with a plurality of periodic signal portions and a plurality of shifted periodic signal portions to generate a plurality of correlation values. A frequency associated with the external vibration is determined based on the plurality of correlation values.

A system and method model a time series from missing data by imputing missing values, denoising measured but noisy values, and forecasting future values of a single time series. A time series of potentially noisy, partially-measured values of a physical process is represented as a non-overlapping matrix. For several classes of common model functions, it can be proved that the resulting matrix has a low rank or approximately low rank, allowing a matrix estimation technique, for example singular value thresholding, to be efficiently applied. Applying such a technique produces a mean matrix that estimates latent values, of the physical process at times or intervals corresponding to measurements, with less error than previously known methods. These latent values have been denoised (if noisy) and imputed (if missing). Linear regression of the estimated latent values permits forecasting with an error that decreases as more measurements are made.

An embodiment of an equipment health state monitoring method adapted to monitor an equipment having a monitored part, including: obtaining a plurality of first values of the monitored part from a sensor in a first time period; extracting a plurality of first parameters from the first values; generating an equipment health state index model according to the first parameters; obtaining a plurality of second value from the sensor in a second time period after the first time period; extracting a plurality of second parameters from the second values; generating a plurality of equipment health state indices according to the second parameters and the equipment health state index model; generating a health state control chart according to the equipment health state indices; and determining whether each of the equipment health state indices locates in an alert area of the health state control chart and outputting a determination result accordingly.

An embodiment of an equipment health state monitoring method adapted to monitor an equipment having a monitored part, including: obtaining a plurality of first values of the monitored part from a sensor in a first time period; extracting a plurality of first parameters from the first values; generating an equipment health state index model according to the first parameters; obtaining a plurality of second value from the sensor in a second time period after the first time period; extracting a plurality of second parameters from the second values; generating a plurality of equipment health state indices according to the second parameters and the equipment health state index model; generating a health state control chart according to the equipment health state indices; and determining whether each of the equipment health state indices locates in an alert area of the health state control chart and outputting a determination result accordingly.

Aspects of the subject disclosure may include, for example, a process that formulates an inference that a first group of mobile devices are at ground level, and obtains, for the first group of mobile devices, positions and barometric pressure readings. Ground heights with respect to a common reference height are determined for the first group of mobile devices, and reference barometric pressures are calculated for the first group of mobile devices, at the common reference height according to the barometric pressure readings and the determined ground heights. At least a portion of the reference barometric pressures are combined to obtain a reference barometric pressure. Other embodiments are disclosed.

Aspects of the subject disclosure may include, for example, a device, including a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of constructing a composite machine-learning (ML) model for facilities infrastructure from facilities infrastructure data; training the composite ML model with historical availability data, historical performance data, and historical error rates, wherein the composite ML model yields quality of the facilities infrastructure; receiving a query of a facility in an area from a user; predicting a quality of the facility based on recent facilities data using the composite ML model; and providing the quality of the facility responsive to the query. Other embodiments are disclosed.

Aspects of the subject disclosure may include, for example, a device, including a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of constructing a composite machine-learning (ML) model for facilities infrastructure from facilities infrastructure data; training the composite ML model with historical availability data, historical performance data, and historical error rates, wherein the composite ML model yields quality of the facilities infrastructure; receiving a query of a facility in an area from a user; predicting a quality of the facility based on recent facilities data using the composite ML model; and providing the quality of the facility responsive to the query. Other embodiments are disclosed.