Concrete Mixer Sensor Data Processing Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor information processing techniques for monitoring fresh concrete in concrete mixers are inadequate in terms of accuracy and speed, and fail to effectively identify hidden features in the vast data sets generated by multiple sensors, leading to potential quality issues due to unsatisfactory mixing or ingredient imbalances.
Innovation Solution
A system equipped with sensors such as rheological probes, hydraulic pressure sensors, drum speed sensors, and high-energy photon probes, coupled with a controller using trained machine learning engines for supervised or unsupervised learning, to determine properties like viscosity, density, and air content in real-time, generating alerts for abnormal conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor information processing techniques are used, then the system structure is simple, but the accuracy and speed of determining fresh concrete properties are insufficient
Solution Approach 1:
The patent replaces traditional mechanical sensor information processing techniques with machine learning-based data processing engines. These engines use algorithms to automatically analyze sensor data from multiple sources (rheological probes, pressure sensors, temperature sensors, etc.) to determine fresh concrete properties such as viscosity, yield stress, and slump, achieving higher accuracy without manual intervention.
Solution Approach 2:
The patent transforms raw sensor parameters into meaningful concrete properties through machine learning models. The data processing engines process multiple sensor parameters (pressure, temperature, vibration, acoustic signals) and convert them into critical quality parameters like viscosity, yield stress, and slump, enabling real-time monitoring of fresh concrete quality.
2Loss of information
If multiple sensors are deployed to monitor various properties, then the measurement coverage is comprehensive, but the data processing speed and ability to identify hidden features are insufficient
Solution Approach 1:
The patent implements preliminary action by pre-training machine learning engines with extensive datasets before actual concrete monitoring. The data processing engines are prepared in advance to recognize patterns and hidden features in sensor data, enabling them to quickly analyze real-time measurements without delay when fresh concrete is being mixed and transported.
Solution Approach 2:
The patent uses copying by creating virtual models of fresh concrete properties through machine learning. The data processing engines generate digital representations of concrete quality parameters based on sensor data, allowing rapid analysis and prediction of concrete properties without physical testing, thus reducing processing time while maintaining comprehensive monitoring.
3Reliability
If real-time monitoring of fresh concrete properties is implemented, then the quality control is improved, but the computational requirements and processing complexity increase
Solution Approach 1:
The patent applies partial action by selectively monitoring and processing only the most critical quality parameters of fresh concrete in real-time using machine learning. The data processing engines focus on determining key properties such as viscosity, yield stress, and slump, while less critical parameters are processed with lower priority or in batches, reducing overall computational energy consumption while maintaining reliable quality control.
Data Source
AI summary
A system for a concrete mixer having a drum receiving fresh concrete therein. The system generally has: a sensor measuring a set of measurand values indicative of a measurand associated with at least one of the fresh concrete, the drum and components of the concrete mixer; and a controller communicatively coupled to the sensor, the controller performing the steps of: accessing the set of measurand values generated by the sensor; using a trained data processing engine stored on the non-transitory memory, at least one of determining a property value indicative of a property of the fresh concrete, determining a parameter value indicative of a parameter of the drum, and determining that the set of measurand values are indicative of some operating conditions of the concrete mixer; and outputting a signal based on said determining.