Die casting machine equipment monitoring management and transmission system and method based on data analysis

Abstract

The invention discloses a die-casting machine equipment monitoring management and transmission system and method based on data analysis, and relates to the technical field of die-casting machine equipment data transmission, and the system comprises a database, a multi-source data collection module, a data preprocessing and feature extraction module, a process switching intelligent decision module, a template optimization module, and a data transmission and cloud platform interaction module. The database stores historical die-casting product information and matches the initial process parameter template according to the received features; the multi-source data acquisition module acquires operation data of the die casting machine and transmits the operation data to the data preprocessing and feature extraction module; the process switching intelligent decision-making module collects new order product features, calls a template to be input into a die-casting machine, and analyzes operation data feature errors; the template optimization module optimizes the template; according to the system, when a new order exists, a product template is accurately called, errors are analyzed, process parameters are continuously optimized, it is ensured that the process is accurately matched with various products, and market requirements are flexibly met.

Description

Technical Field

[0001] The present invention relates to the technical field of die-casting machine equipment data transmission, and in particular to a die-casting machine equipment monitoring management and transmission system and method based on data analysis. Background Art

[0002] In the development history of the die-casting industry, traditional die-casting equipment management faces many difficulties, including complex production processes and quality control problems: the die-casting process involves many parameters, such as die-casting temperature, injection pressure, holding time, etc., each of which affects each other and needs to accurately match product characteristics. Traditional production relies on manual experience to set the initial process parameters. Different operators have different understandings and controls of the parameters, resulting in unstable product quality and high scrap rates. Once the product order is changed, it is time-consuming and laborious to adjust the process parameters; Equipment operation status monitoring lag: Die-casting machines are in a high temperature, high pressure, and high speed operating environment for a long time, and key equipment components are prone to potential failures. In the past, equipment was monitored through regular manual inspections, but the intervals were long, making it difficult to capture sudden abnormalities in the equipment in a timely manner. Repairs were often carried out only after a failure occurred, resulting in long periods of downtime; Inefficiency of data management and collaboration: As die-casting enterprises expand in size, workshops generate massive amounts of production data, including product feature information, equipment operation data, etc. However, these data are stored in a decentralized manner and lack unified and effective management, making it impossible to form data assets to assist production decision-making. In addition, information flow between different levels and departments of the workshop is not smooth, and production site data is difficult to be fed back to process R&D and management in a timely manner, hindering the improvement of the overall collaborative efficiency of the enterprise; Therefore, people need a die-casting machine equipment monitoring, management and transmission system and method based on data analysis to solve the above problems. Summary of the invention

[0003] The purpose of the present invention is to provide a die-casting machine equipment monitoring management and transmission system and method based on data analysis to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a die-casting machine equipment monitoring management and transmission system based on data analysis, the system comprising: a database, a multi-source data acquisition module, a data preprocessing and feature extraction module, a process switching intelligent decision module, a template optimization module and a data transmission and cloud platform interaction module; The database stores product feature information of historical die-cast products, and when receiving the product feature information, the database can match the initial process parameter template according to the product feature information; The multi-source data acquisition module collects the die-casting machine operation data and transmits it to the data preprocessing and feature extraction module; The data preprocessing and feature extraction module preprocesses the operation data of the die-casting machine, extracts the feature of the equipment operation data and transmits it to the process switching intelligent decision-making module; When the die-casting machine receives a new order, the process switching intelligent decision-making module collects the feature information of the new product, calls the initial process parameter template in the database and inputs it into the die-casting machine equipment, and analyzes the error between the real operation data feature and the template operation data feature; The template optimization module analyzes the die-casting result and optimizes the initial process parameter template; The data transmission and cloud platform interaction module uses a communication method combining wired and wireless to transmit the real operation data feature and the template operation data feature.

[0005] The database stores the feature information of historical die-cast products and the initial process parameter template. The product feature information includes: product material, product size and product shape complexity. By analyzing the three-dimensional model of the product, the principal curvature of each point on the surface is calculated, and then the change range and frequency of the curvature are statistically analyzed. For example, a product with a smooth surface has relatively small curvature changes; while a product with multiple protrusions, depressions or complex surface transitions has large curvature changes and high shape complexity. Gaussian curvature and mean curvature can be used to quantify this change, and an index reflecting the degree of surface change can be obtained by integrating or statistically analyzing the distribution of these curvature values over the entire surface. The initial process parameter template includes: die-casting temperature, injection pressure, injection speed setting value, holding pressure time, mold opening and closing speed and stroke, template operation data feature and product completion result. The template operation data feature is obtained by the data preprocessing and feature extraction module when the die-casting machine processes historical die-cast products. The product completion result is the average dimensional deviation degree of the product; The database has an intelligent classification and retrieval function, matches the most similar initial process parameter template according to the product feature information, and deeply analyzes a large amount of production data accumulated by the enterprise itself in the die-casting production process. These data include the process parameters adopted during the actual production of different products, as well as the corresponding product quality inspection results, production efficiency data and other information. Through data mining technology, process parameter combinations with stable production process and excellent product quality are screened out. For example, for the die-cast shell of a certain electronic product, find the die-casting temperature, injection speed and other parameters corresponding to the production batches with a scrap rate lower than a certain threshold (such as 5%) from the historical data, and organize them into the parameter template related to this product in the database.

[0006] The multi-source data acquisition module collects the original data through sensors. The sensors include a furnace temperature sensor, a hydraulic sensor, a mold pressure sensor, a mold temperature sensor, a transmission vibration sensor, a transmission speed sensor and a molten metal flow sensor; A furnace temperature sensor is set at the furnace part of the die-casting machine to monitor the temperature of the molten metal in real time; a hydraulic sensor is arranged in the hydraulic system to measure the injection pressure and the clamping force in real time; a die temperature sensor and a die pressure sensor are installed inside and around the die to monitor the temperature distribution and the stress condition of the die during the die-casting process in real time; a transmission vibration sensor and a transmission speed sensor are equipped on the transmission mechanism to detect the operating state of the mechanical components in real time; a molten metal flow sensor is installed in the molten metal flow area to monitor the flow rate of the molten metal. The data acquisition module has a high sampling frequency and data accuracy, and can continuously and stably collect data during the process switching process and the entire die-casting production cycle, and preliminarily verify and sort out the collected data, removing obvious abnormal data points to ensure the reliability and availability of the data.

[0007] The data preprocessing and feature extraction module preprocesses the collected original data. The preprocessing includes: using low-pass filtering to remove the pressure data fluctuations caused by high-frequency electromagnetic interference, using a smoothing algorithm to correct the temperature data jumps caused by environmental factors. There are many other devices in the working environment of the die-casting machine, such as nearby furnaces, heating devices or cooling devices. If there are heating devices such as furnaces around, the heat they emit may be conducted to the temperature sensor, causing the detected temperature to rise and data jumps to occur. Using a lossless compression algorithm to compress the data. The data preprocessing and feature extraction module extracts the operating data features of the equipment. The operating data features include: extracting the vibration frequency, amplitude and kurtosis from the data collected by the transmission vibration sensor; extracting the temperature features and the time nodes when the data appears from the data collected by the furnace temperature sensor. The temperature features include: the temperature change rate, the highest temperature and the lowest temperature; extracting the pressure peak value, the pressure rising rate, and the pressure stability during the pressure holding stage from the data collected by the die pressure sensor. The analysis method for the pressure stability during the pressure holding stage is: calculating statistical quantities such as the mean, variance or standard deviation of the pressure data, and obtaining the pressure stability during the pressure holding stage according to the pressure fluctuation situation; it also includes the hydraulic feature data, die temperature feature data, transmission speed feature data and molten metal flow feature data extracted from the data collected by the hydraulic sensor, die temperature sensor, transmission speed sensor and molten metal flow sensor. The hydraulic feature data includes the hydraulic peak value and the time interval when the hydraulic peak value appears. The die temperature feature data includes the die temperature change rate, the highest die temperature and the lowest die temperature. The transmission speed feature data includes the average rotational speed of the transmission system; the molten metal flow feature data includes the average flow velocity of the molten metal in the equipment.

[0008] When the die-casting machine receives a new order, the process switching intelligent decision-making module collects the new product feature information of the new order, calls the initial process parameter template in the database and inputs it into the die-casting machine equipment, and takes the average dimensional deviation α of the product in the initial process parameter template0 As the result of this production prediction, the template operation data features obtained by the process switching intelligent decision-making module through the database are Z = {Z 1 , Z 2 , …, Z n}, and the die-casting machine operates according to the template operation data features. During the operation of the die-casting machine, the real operation data features obtained in real time through the data preprocessing and feature extraction module are z = {z 1 , z 2 , …, z n}, where n represents that there are n real operation data features and template operation data features respectively. Furthermore, the error coefficient C between the real operation data features and the template operation data features is calculated: ; where Z e represents the e-th real operation data feature, and z e represents the e-th real operation data feature, e = 1, 2, …, m T . Relying on the rich historical data stored in the database, the system can quickly match the initial process template for new products, eliminate the differences in manual experience, ensure the stable product quality, and reduce the scrap rate. When a new order arrives, the process switching intelligent decision-making module accurately calls the template and deeply analyzes the error between the real and template operation data features, continuously optimizing the process parameters, helping the enterprise flexibly respond to diverse orders, and ensuring the accurate adaptation of products and processes.

[0009] The template optimization module obtains the average deviation degree α of the product size of this die-casting. When α > α 0 , the real operation data features are deleted; when α ≤ α 0 , compare the sizes of Z e and z e . If (1 - C) * Z e < z e < (1 + C) * Z e , replace the Z e in the template operation data features with the real operation data feature z e . Replace the template operation data features in the template with the qualified real operation data features to realize the dynamic optimization of the process parameter template, make the die-casting process continuously approach the actual optimal state, ensure the stable improvement of product quality, flexibly adopt coping strategies according to different product deviation situations, enable the die-casting machine system to quickly self-adjust according to real-time production feedback, and optimize the process methodically whether dealing with regular production fluctuations or occasional abnormal conditions, greatly enhancing the adaptability of the system to complex and changeable production environments, and helping the enterprise efficiently and stably produce high-quality die-casting products; The data transmission and cloud platform interaction module transmits the real operation data characteristics to the cloud platform; the data transmission and cloud platform interaction module adopts a communication method combining wired and wireless. Inside the workshop, industrial Ethernet is preferentially used for data transmission. When data backup is required, mobile communication technology is used to upload the data to the cloud server.

[0010] A die-casting machine equipment monitoring, management and transmission method based on data analysis, characterized by including the following steps: S1: Store the product characteristic information of historical die-cast products. When receiving the product characteristic information, match the initial process parameter template according to the product characteristic information; S2: Collect the operation data of the die-casting machine; S3: Preprocess the operation data of the die-casting machine, and at the same time extract the equipment operation data characteristics; S4: When the die-casting machine receives a new order, collect the new product characteristic information, call the initial process parameter template in the database and input it into the die-casting machine equipment, and analyze the error between the real operation data characteristics and the template operation data characteristics; S5: Analyze the die-casting result and optimize the initial process parameter template; S6: Adopt a communication method combining wired and wireless to transmit the real operation data characteristics and the template operation data characteristics.

[0011] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: On the one hand, the system database stores historical product characteristics and process parameter templates. When receiving new product characteristics, it can quickly match the initial process template, avoid the differences in manual experience, stabilize the product quality, reduce the scrap rate. When a new order arrives, the process switching intelligent decision-making module accurately calls the template and analyzes the error, continuously optimizing the process parameters, enabling the enterprise to quickly adapt to order changes, ensuring the precise adaptation of the process to diverse products, and flexibly responding to market demands; On the one hand, the multi-source data acquisition module combines with the data preprocessing and feature extraction module to use a variety of sensors to collect the operation data of the die-casting machine in real time, closely monitor key information such as the temperature of the melting furnace and the pressure of the mold, and can give early warnings of potential faults when there are abnormal fluctuations in the data, changing the lag of manual inspection; On the other hand, the database uniformly stores and intelligently classifies and retrieves the scattered data, converting the massive product and equipment information into the data basis of the resume template. The data transmission and cloud platform interaction module adopts a combination of wired and wireless means to break through the information obstruction between workshop levels and departments, realize real-time data interconnection, and improve the overall efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings: Figure 1 It is the structural diagram of the die-casting machine equipment monitoring, management and transmission system based on data analysis of the present invention; Figure 2 It is the flow chart of the die-casting machine equipment monitoring, management and transmission method based on data analysis of the present invention. Specific embodiments

[0013] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0014] Please refer to Figure 1 and Figure 2 The present invention provides a technical solution: a die-casting machine equipment monitoring, management and transmission system based on data analysis. The system includes: a database, a multi-source data acquisition module, a data preprocessing and feature extraction module, a process switching intelligent decision-making module, a template optimization module, and a data transmission and cloud platform interaction module; The database stores the product feature information of historical die-cast products. When receiving the product feature information, the database can match the initial process parameter template according to the product feature information; The multi-source data acquisition module collects the die-casting machine operation data and transmits it to the data preprocessing and feature extraction module; The data preprocessing and feature extraction module preprocesses the die-casting machine operation data, and at the same time extracts the equipment operation data features and transmits them to the process switching intelligent decision-making module; When the die-casting machine receives a new order, the process switching intelligent decision-making module collects the new product feature information, calls the initial process parameter template in the database and inputs it into the die-casting machine equipment, and analyzes the error between the real operation data features and the template operation data features; The template optimization module analyzes the die-casting results and optimizes the initial process parameter template; The data transmission and cloud platform interaction module uses a communication method combining wired and wireless to transmit the real operation data features and the template operation data features.

[0015] Further, the database stores the characteristic information of historical die-cast products and the initial process parameter template. The product characteristic information includes: product material, product size, and product shape complexity. By analyzing the three-dimensional model of the product, the principal curvature of each point on the surface is calculated, and then the change range and frequency of the curvature are statistically analyzed. For example, a product with a smooth surface has relatively small curvature changes; while a product with multiple protrusions, depressions, or complex surface transitions has large curvature changes and high shape complexity. Gaussian curvature and mean curvature can be used to quantify this change, and an index reflecting the degree of surface change is obtained by integrating or statistically analyzing the distribution of these curvature values over the entire surface. The initial process parameter template includes: die-casting temperature, injection pressure, injection speed setting value, holding pressure time, mold opening and closing speed and stroke, template operation data characteristics, and product completion result. The template operation data characteristics are obtained through the data preprocessing and feature extraction module when the die-casting machine processes historical die-cast products. The product completion result is the average dimensional deviation degree of the product. The database has an intelligent classification and retrieval function, which matches the most similar initial process parameter template according to the characteristic information of the product, and deeply analyzes a large amount of production data accumulated by the enterprise itself in the die-casting production process. These data include the process parameters adopted during the actual production of different products, as well as the corresponding product quality inspection results, production efficiency data, and other information. Through data mining technology, process parameter combinations with stable production processes and excellent product quality are screened out. For example, for the die-cast shell of a certain electronic product, the die-casting temperature, injection speed, and other parameters corresponding to the production batches with a scrap rate lower than a certain threshold (such as 5%) are found from the historical data and sorted into the parameter template related to this product in the database.

[0016] Further, the multi-source data acquisition module collects raw data through sensors. The sensors include a furnace temperature sensor, a hydraulic sensor, a mold pressure sensor, a mold temperature sensor, a transmission vibration sensor, a transmission speed sensor, and a molten metal flow sensor; A furnace temperature sensor is set at the furnace part of the die-casting machine to monitor the molten metal temperature in real time; a hydraulic sensor is arranged in the hydraulic system to measure the injection pressure and clamping force in real time; a mold temperature sensor and a mold pressure sensor are installed inside and around the mold to monitor the temperature distribution and force condition of the mold during die-casting in real time; a transmission vibration sensor and a transmission speed sensor are equipped on the transmission mechanism to detect the operation state of mechanical components in real time; a molten metal flow sensor is installed in the molten metal flow area to monitor the molten metal flow. The data acquisition module has a high sampling frequency and data accuracy, can continuously and stably collect data during the process switching process and the entire die-casting production cycle, and preliminarily checks and sorts the collected data to remove obvious abnormal data points to ensure the reliability and availability of the data.

[0017] Further, the data preprocessing and feature extraction module preprocesses the collected raw data. The preprocessing includes: using low-pass filtering to remove the pressure data fluctuations caused by high-frequency electromagnetic interference, using a smoothing algorithm to correct the temperature data jumps caused by environmental factors. There are many other devices in the die-casting machine working environment, such as nearby furnaces, heating devices or cooling equipment. If there are heat-generating devices such as furnaces around, the heat emitted may be conducted to the temperature sensor, causing the detected temperature to rise and resulting in data jumps. Using a lossless compression algorithm to compress the data.

[0018] Further, the data preprocessing and feature extraction module extracts the device operation data features. The operation data features include: extracting the vibration frequency, amplitude and kurtosis from the data collected by the transmission vibration sensor; extracting the temperature features and the time nodes when the data appears from the data collected by the furnace temperature sensor. The temperature features include: the temperature change rate, the highest temperature and the lowest temperature; extracting the pressure peak value, the pressure rising rate, and the pressure stability during the pressure holding stage from the data collected by the die pressure sensor. The method for analyzing the pressure stability during the pressure holding stage is: calculating statistical quantities such as the mean, variance or standard deviation of the pressure data, and obtaining the pressure stability during the pressure holding stage based on the pressure fluctuation situation; also including the hydraulic feature data, die temperature feature data, transmission speed feature data and molten metal flow feature data extracted from the data collected by the hydraulic sensor, die temperature sensor, transmission speed sensor and molten metal flow sensor. The hydraulic feature data includes the hydraulic peak value and the time interval when the hydraulic peak appears. The die temperature feature data includes the die temperature change rate, the highest die temperature and the lowest die temperature. The transmission speed feature data includes the average transmission system speed; the molten metal flow feature data includes the average flow velocity of the molten metal in the device.

[0019] Further, when the die-casting machine receives a new order, the process switching intelligent decision module collects the new product feature information of the new order, calls the initial process parameter template in the database and inputs it into the die-casting machine equipment, and takes the average dimensional deviation α of the product in the initial process parameter template 0 as the production prediction result of this time. The template operation data features obtained by the process switching intelligent decision module through the database are Z = {Z 1 , Z 2 , …, Z n}, and the die-casting machine operates according to the template operation data features. The real operation data features obtained in real time by the data preprocessing and feature extraction module during the operation of the die-casting machine are z = {z 1 , z 2 , …, z n}, where n represents that there are n real operation data features and template operation data features respectively. Furthermore, calculate the error coefficient C of the real operation data features and the template operation data features: ; Among them, Z e represents the e-th real operation data feature, and z e represents the e-th real operation data feature, where e = 1, 2, …, m T , relying on the rich historical data stored in the database, the system can quickly match the initial process template for new products, eliminate the differences in manual experience, ensure the stable product quality, and reduce the scrap rate. When a new order arrives, the intelligent decision-making module for process switching accurately calls the template and deeply analyzes the error between the real and template operation data features, continuously optimizing the process parameters, helping the enterprise flexibly respond to diverse orders, and ensuring the accurate adaptation of products and processes.

[0020] Furthermore, the template optimization module obtains the average deviation degree α of the product size of the current die-casting. When α > α 0 , delete the real operation data feature; when α ≤ α 0 , compare Z e and z e . If (1 - C) * Z e < z e < (1 + C) * Z e , replace the Z e in the template operation data feature with the real operation data feature z e , replace the template operation data feature in the template with the qualified real operation data feature, realize the dynamic optimization of the process parameter template, make the die-casting process continuously approach the actual optimal state, ensure the stable improvement of product quality, flexibly adopt corresponding strategies according to different product deviation situations, enable the die-casting machine system to quickly self-adjust according to real-time production feedback, and can optimize the process methodically whether it is dealing with regular production fluctuations or occasional abnormal conditions, greatly enhancing the adaptability of the system to complex and changeable production environments, and helping the enterprise produce high-quality die-casting products efficiently and stably.

[0021] Furthermore, the data transmission and cloud platform interaction module transmits the real operation data feature to the cloud platform; the data transmission and cloud platform interaction module adopts a communication method combining wired and wireless. Inside the workshop, industrial Ethernet is preferentially used for data transmission. When data backup is required, mobile communication technology is used to upload the data to the cloud server.

[0022] The die-casting machine equipment monitoring, management and transmission method based on data analysis includes the following steps: S1: Store the product feature information of historical die-cast products, and when receiving the product feature information, match the initial process parameter template according to the product feature information; S2: Collect the operation data of the die-casting machine; S3: Preprocess the operation data of the die-casting machine and extract the characteristics of the equipment operation data simultaneously; S4: When the die-casting machine receives a new order, collect the new product feature information, call the initial process parameter template in the database and input it into the die-casting machine equipment, and analyze the error between the real operation data characteristics and the template operation data characteristics; S5: Analyze the die-casting results and optimize the initial process parameter template; S6: Adopt a communication method combining wired and wireless to transmit the real operation data characteristics and the template operation data characteristics.

[0023] Example 1: In a certain die-casting workshop, there are multiple die-casting machines running, producing various precision die-castings. Here, a die-casting machine equipment monitoring, management and transmission system based on data analysis is deployed, and the core process switching intelligent decision-making module plays a key role.

[0024] After the system starts, the process switching intelligent decision-making module retrieves the template operation data characteristics of a specific die-casting product from the database. Suppose this time, a certain automotive part is produced, and its template operation data characteristics Z = {Z 1 , Z 2 , …, Z n}, these data cover parameters such as the pressure setting value, temperature curve, and mold opening and closing speed of the die-casting machine, and the die-casting machine starts to run according to these precise settings.

[0025] Meanwhile, the data preprocessing and feature extraction module real-time collects the real operation data characteristics z = {z 1 , z 2 , …, z n} during the operation of the die-casting machine. For example, during the die-casting process, the current actual pressure value, real-time mold temperature, etc. are collected every 0.1 second.

[0026] Then, the system calculates the error coefficient C between the real operation data characteristics and the template operation data characteristics. Suppose at a certain moment, the 3rd real operation data characteristic Z 3 represents the standard mold temperature value of 200 °C, while the real-time collected z 3 is 203 °C, and the error coefficient C is calculated through a predefined formula to measure the deviation degree of the die-casting machine operation state from the ideal template.

[0027] When entering the template optimization link, the template optimization module obtains the average dimensional deviation degree α of the product die-cast this time. If α > α 0 , for example, the dimensional deviation of a batch of produced parts is too large, exceeding the allowable α 0 value. At this time, the system determines that the current operation data is unreliable and directly deletes the corresponding real operation data characteristics to avoid interfering with the subsequent template optimization. And when α ≤ α 0When the dimensions of the produced components are qualified, the system compares Z e and z e in magnitude. If (1 - C) * Z e < z e < (1 + C) * Z e , the true operating data feature z e will replace Z e in the template operating data feature, realizing dynamic optimization of the template, ensuring continuous, efficient and stable production of the die-casting machine, significantly improving the production accuracy and stability of the die-casting machine, greatly reducing the scrap rate, and providing a higher product intelligent production process for the enterprise.

[0028] Finally, it should be noted that the above are only preferred examples of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. The die-casting machine equipment monitoring management and transmission system based on data analysis is characterized by: The system includes: a database, a multi-source data acquisition module, a data preprocessing and feature extraction module, a process switching intelligent decision module, a template optimization module, and a data transmission and cloud platform interaction module; The database stores product feature information of historical die-cast products, and when receiving the product feature information, the database can match the initial process parameter template according to the product feature information; The multi-source data acquisition module collects the die-casting machine operation data and transmits it to the data preprocessing and feature extraction module; The die-casting machine operation data is preprocessed by the data preprocessing and feature extraction module, and the equipment operation data features are extracted and transmitted to the process switching intelligent decision module; The process switching intelligent decision module collects new product feature information when the die-casting machine receives a new order, calls the initial process parameter template in the database to input the die-casting machine equipment, and analyzes the error between the real operation data feature and the template operation data feature; Analyze the die-casting results through the template optimization module and optimize the initial process parameter template; The data transmission and cloud platform interaction module adopts a communication method combining wired and wireless to transmit the real operation data characteristics and the template operation data characteristics.

2. The die-casting machine equipment monitoring, management and transmission system based on data analysis according to claim 1 is characterized in that: The database stores product feature information and initial process parameter templates of historical die-cast products, wherein the product feature information includes: product material, product size and product shape complexity, and the initial process parameter template includes: die-casting temperature, injection pressure, injection speed setting value, holding time, mold opening and closing speed and stroke, template operation data features and product completion results, wherein the template operation data features are obtained through data preprocessing and feature extraction modules when the die-casting machine processes historical die-cast products, and the product completion result is the average deviation of product size; The database has intelligent classification and retrieval functions, and can match the initial process parameter template according to the characteristic information of the product.

3. The die-casting machine equipment monitoring, management and transmission system based on data analysis according to claim 2 is characterized in that: The multi-source data acquisition module acquires raw data through sensors, and the sensors include a furnace temperature sensor, a hydraulic pressure sensor, a mold pressure sensor, a mold temperature sensor, a transmission vibration sensor, a transmission speed sensor, and a molten metal flow sensor; A furnace temperature sensor is installed in the furnace of the die-casting machine to monitor the temperature of the molten metal in real time. A hydraulic sensor is arranged in the hydraulic system to measure the injection pressure and clamping force in real time. Mold temperature sensors and mold pressure sensors are installed inside and around the mold to monitor the temperature distribution and stress of the mold during the die-casting process in real time. Transmission vibration sensors and transmission speed sensors are installed on the transmission mechanism to detect the operating status of mechanical parts in real time. A molten metal flow sensor is installed in the molten metal circulation area to monitor the molten metal flow.

4. The die-casting machine equipment monitoring, management and transmission system based on data analysis according to claim 3 is characterized in that: The data preprocessing and feature extraction module preprocesses the collected raw data, and the data preprocessing includes: using low-pass filtering to remove pressure data fluctuations caused by high-frequency electromagnetic interference, using a smoothing algorithm to correct temperature data jumps caused by environmental factors, and using a lossless compression algorithm to compress the data monitored by the sensor. The pressure data includes data monitored by the mold pressure sensor, and the temperature data includes data monitored by the mold temperature sensor and data monitored by the furnace temperature sensor. The data preprocessing and feature extraction module extracts the equipment operation data features, and the operation data features include: extracting vibration frequency, amplitude and kurtosis from the data collected by the transmission vibration sensor; extracting the molten metal temperature features and the time node of the data appearance from the data collected by the furnace temperature sensor, and the molten metal temperature features include: the molten metal temperature change rate, the maximum molten metal temperature and the minimum molten metal temperature; extracting the pressure peak value, the pressure rise rate and the pressure stability in the holding stage from the data collected by the mold pressure sensor; and also including the hydraulic characteristic data, the mold temperature characteristic data, the transmission speed characteristic data and the molten metal flow characteristic data extracted from the data collected by the hydraulic sensor, the mold temperature sensor, the transmission speed sensor and the molten metal flow sensor.

5. The die-casting machine equipment monitoring, management and transmission system based on data analysis according to claim 4 is characterized in that: When the die-casting machine receives a new order, the process switching intelligent decision module collects new product feature information of the new order, calls the initial process parameter template in the database to input the die-casting machine equipment, and uses the average deviation α0 of the product size in the initial process parameter template as the prediction result of this production.

6. The die-casting machine equipment monitoring management and transmission system based on data analysis according to claim 5 is characterized in that: The template operation data characteristics obtained by the process switching intelligent decision module through the database are Z={Z1,Z2,…,Z n }, the die-casting machine runs according to the template running data features. The real running data features obtained in real time by the data preprocessing and feature extraction module during the operation of the die-casting machine are z={z1,z2,…,z n }, where n represents that there are n real running data features and n template running data features, and then the error coefficient C between the real running data features and the template running data features is calculated.

7. The die-casting machine equipment monitoring, management and transmission system based on data analysis according to claim 6 is characterized in that: The template optimization module obtains the average deviation α of the product size of this die-casting. When α>α0, the real operation data features are deleted; when α≤α0, Z is compared. e and z e The size of, if (1-C)*Z e <z e <(1+C)*Z e , the real running data feature z e Replace the Z in the template run data feature e .

8. The die-casting machine equipment monitoring, management and transmission system based on data analysis according to claim 7 is characterized in that: The data transmission and cloud platform interaction module transmits the real operation data characteristics to the cloud platform; the data transmission and cloud platform interaction module adopts a communication method that combines wired and wireless, and industrial Ethernet is preferentially used for data transmission within the workshop. When data backup is required, mobile communication technology is used to upload data to the cloud server.

9. A die-casting machine equipment monitoring, management and transmission method based on data analysis, the method being applied to a die-casting machine equipment monitoring, management and transmission system based on data analysis as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: S1: storing product feature information of historical die-cast products, and matching the initial process parameter template according to the product feature information when receiving the product feature information; S2: Collect die-casting machine operation data; S3: pre-process the die-casting machine operation data and extract the equipment operation data features; S4: When the die-casting machine receives a new order, it collects new product feature information, calls the initial process parameter template in the database to input the die-casting machine equipment, and analyzes the error between the real operation data feature and the template operation data feature; S5: Analyze die casting results and optimize the initial process parameter template; S6: A communication method combining wired and wireless is used to transmit the real operation data characteristics and the template operation data characteristics.

Images