Complex structure sand mold numerical control machining multi-source sensing and intelligent decision-making system and method
By combining multi-source sensor modules, data preprocessing, and intelligent decision-making modules, the CNC machining parameters of complex sand molds are optimized in real time, solving the problem of real-time detection that is difficult in traditional methods, and improving machining quality and efficiency.
Patent Information
- Application Number
- CN202511622421.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-07
- Publication Date
- 2026-01-16
AI Technical Summary
In the CNC machining of complex sand molds, traditional methods are difficult to detect in real time, leading to quality problems being discovered after machining, which affects machining quality and efficiency.
Data is collected using a multi-source sensor module, data quality and reliability are improved through a data preprocessing module, in-depth analysis is performed using an intelligent decision-making module, and machining parameters, including cold storage refrigeration, cutting force and running speed, are optimized in real time through a CNC machining parameter adjustment module.
It has achieved stability and accuracy in the CNC machining process of complex sand molds, improved production efficiency and product quality, simplified data processing procedures, enhanced real-time adjustment capabilities, and adapted to constantly changing processing conditions.
Smart Images
Figure CN121348973A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of frozen sand mold processing technology, specifically relating to a multi-source sensing and intelligent decision-making system and method for CNC machining of complex structure sand molds. Background Technology
[0002] In the CNC machining of complex sand molds, the complexity of the workpiece and the variability of the machining environment make it difficult for traditional machining methods to perform real-time monitoring during the process. This leads to the discovery of quality problems only after machining is completed, requiring repairs or even remapping, which seriously affects machining quality and efficiency.
[0003] Therefore, how to effectively collect various data during the processing and make intelligent decisions in real time to optimize the processing environment and process has become an urgent problem to be solved. Summary of the Invention
[0004] The purpose of this invention is to provide a multi-source sensing and intelligent decision-making system and method for CNC machining of complex sand molds, in order to solve the problem that traditional machining methods often cannot guarantee machining quality and efficiency due to the complexity of the machining object and the variability of the machining environment.
[0005] To achieve the above objectives, the present invention provides a multi-source sensing and intelligent decision-making system for CNC machining of complex sand molds. The system includes: a multi-source sensor module, a data preprocessing module, an intelligent decision-making module, and a CNC machining parameter adjustment module.
[0006] As a further design feature of this solution, the multi-source sensor module plays a crucial role in the complex CNC machining of sand molds, responsible for collecting various data, including but not limited to sand mold temperature, ambient temperature, cutting pressure, and sand mold shape. This module can integrate a series of data acquisition sensors such as temperature, pressure, vision, and vibration sensors, which can be freely matched and combined according to the process requirements of the equipment.
[0007] As a further design feature of this solution, the data preprocessing module is responsible for preprocessing the various data collected by the multi-source sensor module to improve data quality and reliability. This module employs a series of data processing methods, including data cleaning and data standardization, to ensure data integrity and consistency, and to provide a standardized data format for subsequent analysis.
[0008] As a further design feature of this scheme, the intelligent decision-making module is the core of the entire system. It is responsible for conducting in-depth analysis of the preprocessed data and outputting corresponding control signals. This module employs fuzzy logic and PID control algorithms to control key parameters, while simultaneously using a comparison algorithm to monitor the shape of the sand mold.
[0009] As a further design of this solution, the CNC machining parameter adjustment module adjusts the CNC machining parameters in real time based on the output results of the intelligent decision module to optimize the machining process. The CNC machining parameters include cold storage refrigeration, cutting force, running speed, and running status.
[0010] This invention also provides a multi-source sensing and intelligent decision-making method for CNC machining of complex sand molds, the method comprising the following steps: Step 1: Collect various data during the CNC sand mold machining process using a multi-source sensor module. This data includes, but is not limited to, ambient temperature, sand mold temperature, cutting pressure, and sand mold shape. Real-time monitoring of these parameters ensures the accuracy and completeness of the data. Step 2: The collected raw data needs to be preprocessed to improve its quality and reliability. This step includes data cleaning and data standardization. Data cleaning involves removing or filling in missing values, outliers, or invalid data to ensure the integrity and consistency of the dataset. Simultaneously, the data is standardized by calculating minimum and maximum values to better compare and analyze the scale of different features. Step 3: The preprocessed data is analyzed in depth using the intelligent decision-making module. This step involves the use of fuzzy logic, PID control algorithms, and comparative algorithms. The fuzzy logic algorithm returns adjustment values based on temperature data to control the power of the heater or cooler, achieving intelligent temperature control. Simultaneously, the PID control algorithm controls the cutting pressure, calculating adjustment values based on errors and outputting them to the CNC machining parameter adjustment module for real-time adjustment of the cutting pressure. Furthermore, the comparative algorithm monitors the shape of the sand mold, capturing and comparing the 3D data of the sand mold and the model. If a machining anomaly is detected, the subsequent machining path is automatically optimized. Step 4: Based on the output of the intelligent decision-making module, adjust the CNC machining parameters in real time to optimize the machining process. This step ensures the stability and accuracy of the machining process, improving production efficiency and product quality. By continuously adjusting and optimizing parameters, comprehensive monitoring and intelligent control of the sand mold CNC machining process can be achieved.
[0011] The beneficial effects of this invention are: Through a multi-source sensor module, the system can comprehensively collect various data during the CNC machining process of sand molds. After preprocessing, this data is analyzed in depth using an intelligent decision-making module. The algorithm can identify anomalies and optimization opportunities in real time, ensuring the stability and accuracy of the machining process. Based on the output of the intelligent decision-making module, the system can adjust CNC machining parameters in a timely manner, further optimizing the machining process. This method effectively improves machining quality and efficiency, bringing significant advantages to the field of CNC sand mold machining. This optimization method not only simplifies the data processing flow but also enhances the ability to analyze data and make real-time adjustments. Through continuous parameter adjustment and optimization, this method can adapt to constantly changing machining conditions, ensuring the high efficiency and precision of CNC sand mold machining. Attached Figure Description
[0012] Figure 1 This is a schematic diagram of the multi-source sensor module described in an embodiment of the present invention.
[0013] Figure 2 This is a schematic diagram of the data preprocessing module described in an embodiment of the present invention.
[0014] Figure 3 This is a schematic diagram of the intelligent decision-making module described in an embodiment of the present invention.
[0015] Figure 4 This is a schematic diagram of the CNC machining parameter adjustment module according to an embodiment of the present invention.
[0016] Figure 5 This is a schematic diagram of the process of the present invention.
[0017] Figure descriptions: 101-Cutting axis; 102-3D vision sensor; 103-Digital temperature sensor; 104-Machining sand mold; 105-Infrared thermal imaging sensor; 106-Three-dimensional force sensor. Detailed Implementation
[0018] The present invention will be further illustrated below with reference to the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. It should be noted that the terms "front," "rear," "left," "right," "up," and "down" used in the following description refer to directions in the accompanying drawings, and the terms "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.
[0019] As shown in the figure, this embodiment provides a multi-source sensing and intelligent decision-making system for CNC machining of complex sand molds, including: a multi-source sensor module, a data preprocessing module, an intelligent decision-making module, and a CNC machining parameter adjustment module.
[0020] In the multi-source sensor module for complex sand mold CNC machining, the specific details of each sensor and related structure are as follows: The cutting axis (101) is a key component of a CNC machine tool for performing cutting operations. It is made of high-strength metal and features high precision and rigidity. Under the control of the CNC system, the cutting axis can move precisely along a preset path and speed, driving the cutting head to perform cutting on the sand mold (104). It is typically equipped with a high-precision drive motor and transmission mechanism to ensure the accuracy and stability of the cutting action.
[0021] A 3D vision sensor (102) is installed on the follower part of the cutting head, and can move in real time with the movement of the cutting head, always maintaining an effective scanning angle on the sand mold (104). This sensor uses technologies such as laser or structured light to emit light onto the surface of the sand mold, and acquires three-dimensional information of the sand mold surface by receiving the reflected light. Its working principle is based on the principles of triangulation or time-of-flight, enabling it to quickly and accurately construct a three-dimensional shape model of the sand mold. The acquired sand mold shape data is transmitted in real time to the multi-source sensor module via cable, providing accurate shape reference for subsequent processing.
[0022] The digital temperature sensor (103) is manufactured using silicon technology and features a PTAT structure. This structure enables the sensor to generate a voltage or current signal proportional to the absolute temperature based on temperature changes, thereby accurately measuring the ambient temperature. The sensor is installed within 0.5m of the CNC machine tool to ensure accurate sensing of temperature changes in the machining environment. It converts the measured ambient temperature into a digital signal, which is transmitted directly to the multi-source sensor module via cable, enabling real-time acquisition and uploading of ambient temperature data, providing reliable data for temperature monitoring during the machining process.
[0023] The sand mold (104) is the object of CNC machining. It is usually made of a specific sand mold material and has a certain strength and plasticity. During the machining process, the sand mold is fixed on the worktable of the CNC machine tool and receives cutting operations from the cutting axis driven by the cutter head. The shape and size of the sand mold are determined according to the specific machining requirements, and its surface quality and shape accuracy directly affect the quality of the final machined product. The various sensors in the multi-source sensor module collect data around the sand mold to comprehensively monitor various parameters during the machining process.
[0024] The infrared thermal imaging sensor (105) employs a non-contact measurement method, accurately measuring the temperature of the sand mold by receiving infrared radiation emitted from its surface. The sensor is equipped with a highly sensitive infrared detector that converts the received infrared radiation into an electrical signal, which is then processed to generate a temperature image. This non-contact measurement method avoids collisions with the sand mold during processing, ensuring the safety and accuracy of the measurement. The infrared thermal imaging sensor is installed in a suitable location, and the collected sand mold temperature data is transmitted in real-time to the multi-source sensor module via cable, enabling real-time monitoring of the sand mold temperature.
[0025] A three-dimensional force sensor (106) is mounted on a CNC machine tool, and a sand mold (104) is positioned above the sensor for cutting. This sensor converts external force into structural deformation, and then measures the deformation using internally attached strain gauges to calculate the magnitude and direction of the applied force. A strain gauge is a sensitive element that converts mechanical deformation into a change in resistance. When the sensor is subjected to external force, the structure deforms, and the resistance of the strain gauge changes accordingly. The magnitude of the external force can be obtained by measuring the change in resistance. The three-dimensional force sensor can simultaneously measure forces in three directions: X, Y, and Z axes. The collected cutting pressure data is transmitted in real-time to a multi-source sensor module via cables, providing important data for monitoring cutting forces and optimizing the machining process.
[0026] Meanwhile, depending on the different processing requirements, the corresponding sensors can be flexibly replaced and connected to the multi-source sensor module for data acquisition to meet diverse process requirements.
[0027] The data preprocessing module plays a crucial role in complex sand mold CNC machining systems. Its core task is to process various types of data collected by the multi-source sensor module to improve data quality and reliability, and to provide standardized data formats for subsequent analysis. The following is a detailed description of this module: Data cleaning, as the first step in data preprocessing, employs asynchronous methods for non-blocking processing and introduces an adaptive mechanism to improve cleaning effectiveness. Outlier detection and removal: Traditional IQR methods are limited in effectiveness when data distribution changes; this module improves upon this by dynamically adjusting the outlier detection threshold. The system continuously records the data distribution within a certain time window and calculates the mean and standard deviation of the data within that window. When a new data point arrives, combining IQR detection with an evaluation based on the mean and standard deviation, if the data point deviates from the mean by more than a certain multiple of the standard deviation and is identified as an anomaly by IQR detection, it is considered an outlier and removed.
[0028] Data standardization, building upon the min-max standardization method, introduces a multi-dimensional data standardization strategy using Principal Component Analysis (PCA). First, PCA analysis is performed on multi-dimensional data such as ambient temperature, sand mold temperature, and cutting pressure to extract principal components. These components represent most of the information in the original data and are uncorrelated. Next, principal components are standardized to achieve zero mean and unit variance, eliminating differences in characteristic scales, uncovering the underlying structure of the data, and improving the accuracy of subsequent analyses. Missing value imputation: The fixed use of the median for imputation is abandoned; instead, imputation is dynamically selected based on the data type and distribution characteristics. For normally distributed data, the median is still used for imputation; for skewed distributed data, quantile imputation is used, selecting an appropriate quantile based on the location of the missing value to maintain the original data distribution.
[0029] The data fusion employs a Bayesian-based method. Given the varying reliability and accuracy of data from different sensors, the system assigns prior probabilities based on the historical performance and accuracy of each sensor. When new data arrives, the posterior probabilities are updated using Bayes' formula, resulting in more accurate and reliable fused data. This approach fully considers data uncertainty and improves preprocessing quality.
[0030] The data preprocessing module works in concert with multiple methods to ensure high-quality and consistent data input to subsequent modules, laying the foundation for accurate system analysis and decision-making. Furthermore, preprocessing methods and strategies can be flexibly adjusted for different processing techniques and sensor data.
[0031] The intelligent decision-making module is the core of the entire system. It is responsible for in-depth analysis of the preprocessed data and outputting control signals to achieve intelligent monitoring and adjustment of the processing. The following is a detailed description of this module: The fuzzy logic temperature control optimization incorporates an adaptive fuzzy rule adjustment mechanism and neural network technology. Adaptive fuzzy rule adjustment: Traditional fuzzy logic uses fixed fuzzy sets and rules. This module dynamically adjusts the membership function of the fuzzy sets and the fuzzy rules based on real-time temperature trends and processing requirements. When temperature changes rapidly, the membership function is adjusted to make control more sensitive; under different processing stages and sand mold material characteristics, the fuzzy rules are adjusted to achieve precise temperature control. Neural network optimization: Combining neural network technology, it predicts the effects of different temperature control strategies by learning from a large amount of historical data, providing more reasonable adjustment values for the fuzzy logic, further improving the accuracy and stability of temperature control.
[0032] The improved PID cutting pressure control incorporates an adaptive parameter adjustment mechanism and model predictive control (MPC). Adaptive parameter adjustment: Unlike traditional PID controllers with fixed parameters, this module dynamically adjusts parameters based on real-time changes in cutting pressure and machining conditions. Parameters are increased to improve response speed during large pressure fluctuations and decreased to avoid integral saturation during stable pressure periods. MPC combined with PID: MPC predicts future cutting pressure changes based on the system's dynamic model, adjusting PID parameters in advance for more precise and stable cutting pressure control.
[0033] The sand mold shape comparison algorithm has been upgraded to incorporate machine learning technology for anomaly detection and path optimization. Machine learning anomaly detection: The machine learning model is trained on a large amount of historical processing data and normal / abnormal sand mold shape data to learn shape characteristics and anomaly patterns. When new point cloud data arrives, the model quickly and accurately determines whether anomalies exist. Path optimization: Based on the type and severity of the anomaly, the machine learning model refers to similar situations in historical data to provide precise path adjustment suggestions, improving processing quality and efficiency.
[0034] The intelligent decision-making module comprehensively monitors and intelligently adjusts the complex CNC machining process of sand molds through the integrated application of various advanced algorithms and strategies, improving machining stability, accuracy, production efficiency, and product quality. Furthermore, it can flexibly adopt different intelligent decision-making methods and strategies based on different machining processes and sensor data.
[0035] The CNC machining parameter adjustment module adjusts CNC machining parameters in real time based on the output of the intelligent decision-making module to optimize the machining process. These parameters include cold storage refrigeration, cutting force, operating speed, and operating status. A fuzzy logic algorithm processes data on ambient temperature and sand mold temperature to regulate cold storage refrigeration in real time, ensuring that both ambient and sand mold temperatures consistently meet machining requirements. A PID control algorithm processes data on cutting pressure to regulate the cutting pressure of the CNC machine tool in real time, ensuring that the cutting pressure consistently meets machining requirements. A sand mold shape comparison algorithm monitors the sand mold shape and regulates the operating status of the CNC machine tool in real time. If any mismatch is detected, an alarm is triggered in the system for timely manual intervention. It is worth noting that adjustments to the CNC machine tool may be necessary for different machining processes and intelligent decision-making methods and strategies.
[0036] The technical means disclosed in this invention are not limited to those disclosed in the above embodiments, but also include technical solutions composed of any combination of the above technical features.
Claims
1. A multi-source sensing and intelligent decision-making system for CNC machining of complex sand molds, characterized in that, The system includes a multi-source sensor module, a data preprocessing module, an intelligent decision-making module, and a CNC machining parameter adjustment module. The multi-source sensor module is responsible for collecting various data during the complex sand mold CNC machining process, including but not limited to sand mold temperature, ambient temperature, cutting pressure, and sand mold shape. The data preprocessing module is used to preprocess the various data collected by the multi-source sensor module. The intelligent decision-making module uses the intelligent decision-making module to perform in-depth analysis of the preprocessed data and outputs corresponding control algorithms. The CNC machining parameter adjustment module adjusts the CNC machining parameters in real time according to the control algorithm to optimize the machining process.
2. The multi-source sensing and intelligent decision-making method and system for CNC machining of complex structure sand molds according to claim 1, characterized in that, The multi-source sensor module integrates temperature, pressure, and vision sensors, and can be freely matched and combined according to the equipment's process requirements.
3. The multi-source sensing and intelligent decision-making method and system for CNC machining of complex structure sand molds according to claim 1, characterized in that, The data preprocessing module employs data processing methods, including data cleaning and data standardization, to ensure the integrity and consistency of the data and to provide a standardized data format for its subsequent intelligent decision analysis.
4. The multi-source sensing and intelligent decision-making method and system for CNC machining of complex structure sand molds according to claim 1, characterized in that, The intelligent decision-making module uses fuzzy logic and PID control algorithms to control key parameters, while using a comparison algorithm to detect the shape of the sand mold.
5. The multi-source sensing and intelligent decision-making method and system for CNC machining of complex structure sand molds according to claim 1, characterized in that, The CNC machining parameter adjustment module adjusts the CNC machining parameters in real time, including ambient temperature, cutting pressure, cutting state, and machining path.
6. A multi-source sensing and intelligent decision-making method for CNC machining of complex sand molds, characterized in that, Based on the system as described in any one of claims 1-5, the system includes the following steps: Step 1: Collect various data during the CNC machining process of sand molds using a multi-source sensor module, including but not limited to ambient temperature, sand mold temperature, cutting pressure, and sand mold shape; Step 2: The data preprocessing module preprocesses the collected raw data, including data cleaning and data standardization. Data cleaning involves deleting or filling missing values, outliers, or invalid data. The data is standardized by calculating the minimum and maximum values to better compare and analyze the scale of different features. Step 3: The intelligent decision-making module performs in-depth analysis of the preprocessed data using fuzzy logic, PID control algorithms, and comparison algorithms. Specifically: the fuzzy logic algorithm returns adjustment values based on temperature data to control the power of the heater or cooler, achieving intelligent temperature control; simultaneously, the PID control algorithm controls the cutting pressure, calculates adjustment values based on errors, and outputs them to the CNC machining parameter adjustment module for real-time adjustment of cutting pressure; furthermore, the comparison algorithm monitors the shape of the sand mold, captures and compares the 3D data of the sand mold and the model, and automatically optimizes subsequent machining paths if machining anomalies are detected. Step 4: The CNC machining parameter adjustment module adjusts the CNC machining parameters in real time based on the output of the intelligent decision module to optimize the machining process; by continuously adjusting and optimizing the parameters, comprehensive monitoring and intelligent control of the sand mold CNC machining process is achieved.