Intelligent mold production monitoring method and system based on artificial intelligence

Abstract

The invention relates to an intelligent mold production monitoring method based on artificial intelligence, and aims to improve the production efficiency and the product quality and reduce the rate of defective products at the same time. According to the method, mold production model information is matched through a product information base, and key production basic data is obtained; historical and real-time parameter data of production equipment are recorded by using a public time axis, and a detailed data set is constructed; judging whether the product is qualified or not by comparing the actual parameters of the product with the basic parameters and combining a defective product error threshold value; and further analyzing the equipment parameters in the abnormal production time period, predicting the working trend of the equipment, and comparing the predicted trend with the abnormal working trend to identify potential production risks. And finally, equipment parameters are automatically adjusted according to the risk early warning regulation and control strategy, and defective products are prevented from being generated. Intelligent monitoring and regulation in the production process are achieved, and the product quality and production efficiency of mold production are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mold production monitoring, and in particular to an artificial intelligence-based intelligent mold production monitoring method and system. Background Art

[0002] In the field of mold production, existing technologies usually rely on manual operation and traditional monitoring systems. These methods often rely on production personnel to patrol production equipment and conduct spot checks on products, mainly relying on the operator's experience and preset parameter standards to judge equipment abnormalities.

[0003] The existing technology has the following technical defects: due to the large number of mold equipment and their easy dispersion during production, it is difficult for technical personnel to grasp the specific production status of the equipment in real time, resulting in the untimely discovery of abnormal conditions, thereby reducing the product quality and production efficiency of mold production, so improvement is needed. Summary of the invention

[0004] In order to improve the product quality and production efficiency of mold production, the present application provides an artificial intelligence-based intelligent monitoring method and system for mold production.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: An intelligent monitoring method for mold production based on artificial intelligence, the method comprising the steps of: Obtain model information of mold production, and input the model information into a pre-set product information library for matching, so as to output basic production data corresponding to the model, wherein the basic production data includes basic parameter data of production equipment, basic data of production environment, basic product parameter data corresponding to each production link, and defective product error threshold corresponding to each production link; Obtain the historical parameter data of the production equipment at each stage, and record the historical parameter data of the production equipment based on a preset public timeline to construct a historical production equipment working parameter data set; Acquire actual product parameter data corresponding to each production link, and compare the actual product parameter data with the basic product parameter data to generate actual error data; Defective product judgment is performed on the actual error data based on the defective product error threshold. If the actual error data exceeds the defective product error threshold, the product is judged as defective, and the corresponding production time is marked as an abnormal production time period according to a preset time length; According to the correlation between the common time axis and the historical parameter data of the production equipment, the historical parameter data of the production equipment corresponding to the abnormal production time period is extracted and marked as abnormal production equipment parameter data; The preset production equipment analysis model analyzes the abnormal production equipment parameter data based on a machine self-learning algorithm to identify abnormal working trends of the production equipment; Obtain the real-time parameter data of production equipment in each link, and record the real-time parameter data of production equipment based on a preset public timeline to build a real-time production equipment working parameter data set; The preset production equipment trend prediction model analyzes the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes predicted production equipment working parameters at a corresponding time point; The preset equipment trend comparison model compares the predicted production equipment working trend with the abnormal working trend of the production equipment, and determines whether there is an abnormal risk; If there is an abnormal risk, the preset equipment control abnormal control model generates a risk warning control strategy, and the risk warning control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

[0006] By adopting the above technical solutions, this solution integrates advanced artificial intelligence technology and machine self-learning algorithms to achieve comprehensive intelligent monitoring of the mold production process, thereby significantly improving production efficiency and product quality. Specifically, by real-time collection and analysis of key parameters in the mold production process, this solution can accurately identify and predict abnormal situations that may occur in the production process, and adjust the working parameters of the production equipment in a timely manner, effectively avoiding the production of defective products, thereby improving product quality. In addition, this solution can also predict the maintenance needs of the mold by analyzing historical data and real-time data, realize predictive maintenance, reduce production interruptions caused by equipment failures, and further improve the continuity and stability of production, thereby improving production efficiency.

[0007] In a preferred example, the present application can be further configured as follows: after obtaining the historical parameter data of the production equipment in each link and recording the historical parameter data of the production equipment based on a preset common time axis to construct a historical production equipment working parameter data set, the following steps are included: Acquire energy consumption data of production equipment and input it into the production equipment working parameter data set, and associate the energy consumption data of production equipment with the working parameter data based on the common time axis to construct the equipment energy consumption data set; The preset energy consumption analysis model analyzes the equipment energy consumption data set based on a machine self-learning algorithm to generate an equipment energy consumption factor, wherein the equipment energy consumption factor is used to represent the correlation between energy consumption and equipment operating parameters; The preset energy consumption prediction model generates a predicted energy consumption trend based on the equipment energy consumption factor and the predicted production equipment working trend, and the predicted energy consumption trend corresponds one-to-one with the predicted production equipment working trend based on the common time axis; If the predicted energy consumption trend exceeds a preset energy consumption fluctuation threshold, an energy consumption adjustment strategy is generated, and the energy consumption adjustment strategy is used to adjust the working parameters of the production equipment to prevent the production energy consumption from exceeding the energy consumption fluctuation threshold.

[0008] By adopting the above technical scheme, the intelligent monitoring method for mold production of the present invention can effectively monitor and adjust the energy consumption of production equipment to achieve automatic energy saving. Compared with traditional manual monitoring and regular maintenance, the method can achieve real-time monitoring and predictive adjustment, significantly improve energy utilization efficiency, and reduce production costs. In addition, by automatically adjusting the working parameters of production equipment, the method can reduce energy waste caused by improper operation or slow response, and improve production flexibility and response speed.

[0009] In a preferred example, the present application may be further configured as follows: after obtaining the energy consumption data of the production equipment and inputting it into the production equipment working parameter data set, the energy consumption data of the production equipment is associated with the working parameter data based on the common time axis to construct the equipment energy consumption data set, the following steps are included: Acquire historical production environment data, and associate the historical production environment data with the historical parameter data of the production equipment based on the common time axis to construct an environment-operating parameter data set; The pre-set environmental impact analysis model analyzes the environment-working parameter data set based on a machine self-learning algorithm to generate environmental impact factors; The preset production equipment prediction model corrects the predicted production equipment working trend according to the environmental influencing factors to generate a corrected production equipment working trend, wherein the corrected production equipment working trend includes corrected predicted production equipment working parameters at the corresponding time point.

[0010] By adopting the above technical solution, the operating parameters of production equipment can be predicted and adjusted more accurately to adapt to environmental changes, thereby improving production efficiency and product quality. The implementation of this method enables the production monitoring system to not only respond to changes in the equipment itself, but also predict and adapt to changes in the external environment, thereby achieving more refined and intelligent production management.

[0011] In a preferred example, the present application may be further configured as follows: after the step of using the preset production equipment prediction model to correct the predicted production equipment working trend according to the environmental impact factor to generate a corrected production equipment working trend, the following steps are included: Comparing the real-time parameter data of the production equipment with the corrected predicted production equipment operating parameters at the corresponding time point to calculate the deviation parameter data; Associating the deviation parameter data with the production environment data based on the common time axis and constructing a deviation-environment data set; The preset deviation analysis model analyzes the deviation-environment data set based on a machine self-learning algorithm to generate a deviation correction factor; The environmental impact factor is corrected based on the deviation correction factor to generate a corrected environmental impact factor.

[0012] By adopting the above technical solution, real-time monitoring and dynamic adjustment of the working parameters of production equipment can be achieved to adapt to the ever-changing production environment and conditions. The implementation of this method enables the production monitoring system to not only respond to changes in the equipment itself, but also optimize the prediction model according to deviations in actual production, thereby achieving more refined and intelligent production management.

[0013] In a preferred example, the present application may be further configured as follows: after judging the actual error data as a defective product based on the defective product error threshold, if the actual error data exceeds the defective product error threshold, the actual error data is judged as a defective product, the following steps are included: Classify the defective products according to the preset defect types to construct a defect profile; The abnormal working trend of the equipment is classified accordingly according to the defect portrait, and a correlation relationship between the abnormal working trend of the equipment and the defect portrait is constructed for predicting the defect type.

[0014] By adopting the above technical solutions, defect classification enables the system to clearly identify different types of defects, providing data support for subsequent quality improvement and production optimization. At the same time, by building a correlation between abnormal equipment working trends and defect portraits, the system can predict potential defect types in future production, thereby taking preventive measures in advance.

[0015] In a preferred example, the present application may be further configured as follows: after the step of classifying the defective products according to the preset defect types to construct a defect portrait, the following steps are included: Acquire historical operation records, and associate the defect profile with corresponding historical operation records based on the common timeline; Based on the relationship between the defect profile and the corresponding historical operation record, a defect-causing operation habit profile is constructed; When an operation record similar to the defect-forming operation habit profile is detected, a defect warning alert is issued to remind the operator to monitor the product to avoid defective products.

[0016] By adopting the above technical solution, the production monitoring system can not only respond to defects that have already occurred, but also predict and prevent defects that may occur in the future, significantly improving the intelligence and automation level of the production process. Compared with the traditional method that relies on manual monitoring and experience judgment, this method can more accurately identify and warn of potential production risks through a data-driven approach, reduce the generation of defective products, and improve production efficiency and product quality.

[0017] In a preferred example, the present application can be further configured as follows: the machine self-learning algorithm includes a convolutional neural network and an unsupervised learning algorithm.

[0018] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions: An intelligent monitoring device for mold production based on artificial intelligence, the device comprising: a production basic data output unit, used to obtain model information of mold production, and input the model information into a pre-set product information library for matching, so as to output production basic data corresponding to the model, wherein the production basic data includes production equipment basic parameter data, production environment basic data, product basic parameter data corresponding to each production link, and defective product error threshold corresponding to each production link; A historical production equipment working parameter data set construction unit, used to obtain the historical parameter data of the production equipment in each link, and record the historical parameter data of the production equipment based on a preset public time axis to construct a historical production equipment working parameter data set; An actual error data generating unit, used for acquiring actual parameter data of the product corresponding to each production link, and comparing the actual parameter data of the product with the basic parameter data of the product to generate actual error data; A defective product judging unit, configured to judge the actual error data as defective products based on the defective product error threshold, and if the actual error data exceeds the defective product error threshold, the actual error data is judged as a defective product, and the corresponding production time is marked as an abnormal production time period according to a preset time length; The abnormal production equipment parameter data marking unit is used to extract the production equipment historical parameter data corresponding to the abnormal production time period according to the association relationship between the common time axis and the production equipment historical parameter data, and mark it as abnormal production equipment parameter data; An equipment abnormal operation trend generating unit is used to analyze the abnormal production equipment parameter data based on a machine self-learning algorithm using a pre-set production equipment analysis model to generate abnormal operation trends of the production equipment; A real-time production equipment working parameter data set construction unit, used to obtain the real-time parameter data of the production equipment in each link, and record the real-time parameter data of the production equipment based on a preset public time axis to construct a real-time production equipment working parameter data set; A predicted production equipment working trend generating unit, which is used to pre-set a production equipment trend prediction model to analyze the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes predicted production equipment working parameters at corresponding time points; An abnormal risk judgment unit, which is pre-set with an equipment trend comparison model to compare the predicted production equipment working trend with the abnormal working trend of the production equipment, and judge whether there is an abnormal risk; The risk warning and control strategy generating unit is used to pre-set an abnormal equipment control model, and when there is an abnormal risk, generate a risk warning and control strategy, wherein the risk warning and control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

[0019] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned intelligent monitoring method for mold production based on artificial intelligence when executing the computer program.

[0020] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned artificial intelligence-based intelligent monitoring method for mold production.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. This solution integrates advanced artificial intelligence technology and machine self-learning algorithms to achieve comprehensive intelligent monitoring of the mold production process, thereby significantly improving production efficiency and product quality. Specifically, by real-time collection and analysis of key parameters in the mold production process, this solution can accurately identify and predict abnormal situations that may occur in the production process, and timely adjust the working parameters of production equipment, effectively avoiding the production of defective products, thereby improving product quality. In addition, this solution can also predict the maintenance needs of molds by analyzing historical data and real-time data, realize predictive maintenance, reduce production interruptions caused by equipment failures, and further improve the continuity and stability of production, thereby improving production efficiency; 2. The mold production intelligent monitoring method of the present invention can effectively monitor and adjust the energy consumption of production equipment to achieve automatic energy saving. Compared with traditional manual monitoring and regular maintenance, the method can achieve real-time monitoring and predictive adjustment, significantly improve energy utilization efficiency, and reduce production costs. In addition, by automatically adjusting the working parameters of production equipment, the method can reduce energy waste caused by improper operation or slow response, and improve production flexibility and response speed; 3. Defect classification enables the system to clearly identify different types of defects, providing data support for subsequent quality improvement and production optimization. At the same time, by building a correlation between abnormal equipment working trends and defect portraits, the system can predict potential defect types in future production, so as to take preventive measures in advance; 4. The production monitoring system can not only respond to defects that have already occurred, but also predict and prevent defects that may occur in the future, significantly improving the intelligence and automation level of the production process. Compared with the traditional method that relies on manual monitoring and experience judgment, this method can more accurately identify and warn of potential production risks through a data-driven approach, reduce the generation of defective products, and improve production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of the steps of an intelligent monitoring method for mold production based on artificial intelligence in one embodiment of the present application; Figure 2 This is a principle block diagram of an intelligent monitoring device for mold production based on artificial intelligence in one embodiment of the present application; Figure 3 It is a schematic diagram of an electronic device in an embodiment of the present application.

[0023] Figure Number: 1. Production basic data output unit; 2. Historical production equipment working parameter data set construction unit; 3. Actual error data generation unit; 4. Defective product judgment unit; 5. Abnormal production equipment parameter data marking unit; 6. Equipment abnormal working trend generation unit; 7. Real-time production equipment working parameter data set construction unit; 8. Prediction of production equipment working trend generation unit; 9. Abnormal risk judgment unit; 10. Risk warning and control strategy generation unit. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses an intelligent monitoring method for mold production based on artificial intelligence, which specifically includes the following steps: S010: Obtain model information of mold production, and input the model information into a pre-set product information library for matching, so as to output basic production data corresponding to the model; The basic production data includes basic parameter data of production equipment, basic data of production environment, basic parameter data of products corresponding to each production link, and error threshold of defective products corresponding to each production link; Specifically, when producing a car bumper, the operator obtains the model information of the mold by scanning the QR code label on the mold. This information is input into the pre-set product information library for matching, and the system outputs the basic production data corresponding to the model according to the matching results. These data include the basic parameter data of the injection molding machine (such as injection speed, pressure, temperature, etc.), the basic data of the production environment (such as humidity, temperature, etc.), the basic parameter data of the product corresponding to each production link (such as size, weight, etc.), and the defective product error threshold corresponding to each production link. S020: Obtain historical parameter data of production equipment in each link, and record the historical parameter data of production equipment based on a preset public time axis to construct a historical production equipment working parameter data set; Specifically, by connecting to the data interface of the injection molding machine, the historical parameter data of the production equipment in each production link is obtained in real time. These data are recorded on a preset public timeline to build a data set of production equipment working parameters. For example, the system records the temperature and pressure changes of the injection molding machine in different time periods, the number of mold opening and closing, etc., as well as the specific production parameter setting values ​​of the equipment.

[0026] S030: Acquire actual product parameter data corresponding to each production link, and compare the actual product parameter data with the basic product parameter data to generate actual error data; Specifically, after the injection molding process is completed, the actual size and weight parameter data of the finished product are automatically obtained through the online measuring equipment. These data are compared with the basic product parameter data preset in the product information library to generate actual error data. For example, if the preset bumper size tolerance is ±0.3mm, and the actual measurement result exceeds this range, the system will generate the corresponding error data as the actual error data.

[0027] S040: Determine the actual error data as a defective product based on the defective product error threshold. If the actual error data exceeds the defective product error threshold, the product is determined to be a defective product, and the corresponding production time is marked as an abnormal production time period according to a preset time length; Specifically, the actual error data is judged according to the defective product error threshold, and if the actual error exceeds the preset threshold, the product will be judged as a defective product. In the embodiment of the present application, if the size error of the bumper exceeds ±0.5mm, the system will mark the product as a defective product and mark the time period in which the product is produced as an abnormal production time period.

[0028] S050: extracting the historical parameter data of the production equipment corresponding to the abnormal production time period according to the association relationship between the common time axis and the historical parameter data of the production equipment, and marking it as abnormal production equipment parameter data; Specifically, according to the correlation between the common time axis and the historical parameter data of the production equipment, the historical parameter data of the injection molding machine in the abnormal production time period is extracted. In the embodiment of the present application, if multiple products produced in a certain time period are defective products, the system will extract the temperature, pressure and other parameter data of the injection molding machine in the time period and the specific production parameter setting values ​​of the production equipment, and mark them as abnormal production equipment parameter data.

[0029] S060: The preset production equipment analysis model analyzes the abnormal production equipment parameter data based on the machine self-learning algorithm to determine the abnormal working trend of the production equipment; Specifically, the pre-set production equipment analysis model uses a machine self-learning algorithm to analyze abnormal production equipment parameter data to identify abnormal working trends of production equipment. For example, by analyzing historical data, the system found that the size error of the bumper produced by the injection molding machine when the fuselage temperature was high was large, and thus concluded that the working trend of the fuselage temperature rising was the abnormal working trend that led to defective products.

[0030] It should be noted that in the embodiments of the present application, the machine self-learning algorithm includes a convolutional neural network and an unsupervised learning algorithm; among them, the convolutional neural network (CNN) can be used to automatically extract features from a large amount of production data for software defect prediction. In mold production, CNN can be used to analyze image data on the mold surface and identify tiny defects such as scratches or bubbles. Through multiple layers of convolution and pooling operations, CNN can deeply mine features in the data, thereby performing learning classification with better performance and higher stability. Unsupervised learning algorithms, such as K-means cluster analysis, can be used to discover patterns and structures in the production process. In mold production, cluster analysis can help identify natural groupings in production data, for example, grouping similar defect types or production conditions to facilitate analysis and optimization of the production process.

[0031] S070: Acquire real-time parameter data of production equipment in each link, and record the real-time parameter data of production equipment based on a preset public time axis to construct a real-time production equipment working parameter data set; Specifically, real-time parameter data of production equipment in each link is obtained, and these data are recorded based on a preset public timeline to update the production equipment working parameter data set. In an embodiment of the present application, the system monitors the temperature and pressure changes of the injection molding machine during the production process in real time, and records these data for further analysis.

[0032] S080: The preset production equipment trend prediction model analyzes the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend; The predicted production equipment working trend includes predicted production equipment working parameters at corresponding time points; Specifically, the pre-set production equipment trend prediction model uses a machine self-learning algorithm to analyze the production equipment working parameter data set to generate a predicted production equipment working trend. This trend includes the predicted production equipment working parameters at the corresponding time point. For example, the system predicts that in the next 30 minutes, if the temperature of the injection molding machine continues to rise, more defective products may be produced.

[0033] S090: The preset equipment trend comparison model compares the predicted production equipment working trend with the abnormal working trend of the production equipment, and determines whether there is an abnormal risk; Specifically, the pre-set production equipment trend prediction model uses a machine self-learning algorithm to analyze the production equipment working parameter data set to generate a predicted production equipment working trend. This trend includes the predicted production equipment working parameters at the corresponding time point. For example, the system predicts that in the next 30 minutes, if the temperature of the injection molding machine continues to rise, more defective products may be produced.

[0034] S100: If there is an abnormal risk, the pre-set equipment control abnormal control model generates a risk warning control strategy; The risk early warning and control strategy is used to adjust the working parameters of the production equipment to avoid defective products; Specifically, if it is determined that there is an abnormal risk, the pre-set equipment control abnormal control model will generate a risk warning control strategy. These strategies are used to adjust the working parameters of the production equipment to avoid defective products. In the embodiment of the present application, the cooling system of the injection molding machine is automatically adjusted to reduce the mold temperature, thereby avoiding production under predicted high temperature conditions and reducing the generation of defective products.

[0035] In summary, this solution integrates advanced artificial intelligence technology and machine self-learning algorithms to achieve comprehensive intelligent monitoring of the mold production process, thereby significantly improving production efficiency and product quality. Specifically, by real-time collection and analysis of key parameters in the mold production process, this solution can accurately identify and predict abnormal situations that may occur in the production process, and timely adjust the working parameters of production equipment, effectively avoiding the production of defective products, thereby improving product quality. In addition, this solution can also predict the maintenance needs of the mold by analyzing historical data and real-time data, realize predictive maintenance, reduce production interruptions caused by equipment failures, and further improve the continuity and stability of production, thereby improving production efficiency.

[0036] Compared with the existing technology, this solution automatically optimizes monitoring parameters through adaptive learning algorithms, achieving refined management of the production process. Most of the existing technologies rely on manual experience and regular maintenance, making it difficult to achieve real-time monitoring and automatic adjustment. Secondly, this solution uses deep learning technology to identify the correlation between production parameters and predict potential production problems. This method has not been widely used in existing technologies. Thirdly, this solution provides user-customized monitoring functions, allowing users to set monitoring parameters and alarm thresholds according to specific needs, thereby improving the flexibility and applicability of the monitoring system.

[0037] After the step S020: obtaining the historical parameter data of the production equipment in each link, and recording the historical parameter data of the production equipment based on a preset common time axis to construct a historical production equipment working parameter data set, the following steps are included: S021: Acquire energy consumption data of production equipment and input it into the production equipment working parameter data set, and associate the energy consumption data of production equipment with the working parameter data based on the common time axis to construct the equipment energy consumption data set; Specifically, by connecting to the energy consumption monitoring interface of production equipment (such as injection molding machines, heat treatment furnaces, etc.), the energy consumption data of the equipment is obtained in real time, including but not limited to the consumption of electricity, water, compressed air, etc. These energy consumption data are input into the production equipment working parameter data set, and the energy consumption data is associated with the working parameter data based on the preset common time axis to build the equipment energy consumption data set. For example, the system may record the power consumption of the injection molding machine in a specific time period, as well as the working status of the machine in this period (such as injection speed, temperature, etc.), and associate these data for energy consumption analysis.

[0038] S022: The preset energy consumption analysis model analyzes the device energy consumption data set based on a machine self-learning algorithm to generate a device energy consumption factor, where the device energy consumption factor is used to represent the correlation between energy consumption and device operating parameters; Specific: The pre-set energy consumption analysis model uses a machine self-learning algorithm to conduct an in-depth analysis of the equipment energy consumption data set to generate equipment energy consumption factors, which are used to represent the correlation between energy consumption and equipment operating parameters. For example, the energy consumption analysis model may find that at high injection speeds, the energy consumption of the injection molding machine increases significantly, while at lower mold temperatures, the energy consumption is relatively low. Through this analysis, the system can identify the key operating parameters that affect energy consumption and generate corresponding energy consumption factors.

[0039] S023: The preset energy consumption prediction model generates a predicted energy consumption trend based on the equipment energy consumption factor and the predicted production equipment working trend, wherein the predicted energy consumption trend corresponds one-to-one with the predicted production equipment working trend based on the common time axis; Specifically, the preset energy consumption prediction model generates predicted energy consumption trends based on the equipment energy consumption factor and the predicted production equipment working trend. These predicted energy consumption trends correspond one-to-one with the predicted production equipment working trend based on a common time axis. For example, if the predicted production equipment working trend shows that the injection speed of the injection molding machine will gradually increase over a period of time in the future, the energy consumption prediction model will predict the increasing trend of energy consumption based on the previously generated energy consumption factor, thereby generating a predicted trend of future energy consumption.

[0040] S024: if the predicted energy consumption trend exceeds a preset energy consumption fluctuation threshold, an energy consumption adjustment strategy is generated, wherein the energy consumption adjustment strategy is used to adjust the working parameters of the production equipment to prevent the production energy consumption from exceeding the energy consumption fluctuation threshold; If the predicted energy consumption trend exceeds the preset energy consumption fluctuation threshold, the system will generate energy consumption adjustment strategies. These strategies are used to adjust the operating parameters of production equipment to prevent production energy consumption from exceeding the energy consumption fluctuation threshold. For example, if the predicted energy consumption trend shows that energy consumption will exceed the threshold, the system may automatically adjust the injection speed of the injection molding machine, or adjust the mold temperature to reduce energy consumption and keep it within the preset energy consumption fluctuation threshold.

[0041] To sum up, the intelligent monitoring method for mold production of the present invention can effectively monitor and adjust the energy consumption of production equipment to achieve automatic energy saving. Compared with traditional manual monitoring and regular maintenance, the present method can achieve real-time monitoring and predictive adjustment, significantly improve energy utilization efficiency, and reduce production costs. In addition, by automatically adjusting the working parameters of production equipment, the present method can reduce energy waste caused by improper operation or slow response, and improve production flexibility and response speed.

[0042] After the step of S021: acquiring energy consumption data of production equipment and inputting it into the production equipment working parameter data set, and associating the energy consumption data of production equipment with the working parameter data based on the common time axis to construct the equipment energy consumption data set, the following steps are included: S0211: Acquire historical production environment data, and associate the historical production environment data with the historical parameter data of the production equipment based on the common time axis to construct an environment-working parameter data set; Specifically, historical production environment data is acquired in real time by deploying various sensors in the production environment, such as temperature sensors, humidity sensors, etc. These data include environmental parameters such as temperature, humidity, and cleanliness of the production workshop. They are recorded on a pre-set public timeline and associated with the historical parameter data of the production equipment to build an environment-working parameter data set. In the embodiment of the present application, the cooling time, injection speed and other parameters of the injection molding machine under high temperature and high humidity environment are recorded, and these data are associated with the environmental conditions of a specific time period.

[0043] S0212: The pre-set environmental impact analysis model analyzes the environment-working parameter data set based on a machine self-learning algorithm to generate environmental impact factors; Specifically, the pre-set environmental impact analysis model uses a machine self-learning algorithm to analyze the environment-operating parameter data set to generate environmental impact factors. These factors are used to indicate the degree of impact of environmental parameters on the operating parameters of production equipment. For example, the system may find that in a high temperature environment, in order to maintain product quality, the injection molding machine requires a higher cooling rate, thereby generating an environmental impact factor that reflects the impact of temperature on cooling time.

[0044] S0213: The preset production equipment prediction model corrects the predicted production equipment working trend according to the environmental influencing factor to generate a corrected production equipment working trend, wherein the corrected production equipment working trend includes a corrected predicted production equipment working parameter at a corresponding time point; Specifically, the pre-set production equipment prediction model corrects the predicted production equipment working trend according to the environmental impact factor and generates a corrected production equipment working trend. This corrected trend contains the corrected predicted production equipment working parameters at the corresponding time point. For example, if it is predicted that the temperature in the production environment will increase in the future, the system will adjust the predicted working parameters of the injection molding machine according to the previously generated environmental impact factor, such as increasing the cooling rate, to adapt to environmental changes and ensure product quality.

[0045] In summary, by implementing steps S0211 to S0213, the mold production intelligent monitoring method of the present invention can more accurately predict and adjust the working parameters of the production equipment to adapt to environmental changes, thereby improving production efficiency and product quality. The implementation of this method enables the production monitoring system to not only respond to changes in the equipment itself, but also predict and adapt to changes in the external environment, thereby achieving more refined and intelligent production management.

[0046] Compared with traditional monitoring methods, this method improves the adaptability and flexibility of the production process by introducing the analysis and prediction of environmental factors. When environmental conditions change, the system can automatically adjust the working parameters of the production equipment, reduce production fluctuations caused by environmental changes, and reduce the defective product rate. In addition, this method can also improve energy utilization efficiency, reduce energy waste by optimizing production parameters, and achieve energy saving and consumption reduction.

[0047] After the step of S0213: the preset production equipment prediction model corrects the predicted production equipment working trend according to the environmental impact factor to generate a corrected production equipment working trend, the following steps are included: S02131: Compare the real-time parameter data of the production equipment with the corrected predicted production equipment working parameters at the corresponding time point to calculate deviation parameter data; S02132: Associating the deviation parameter data with the production environment data based on the common time axis, and constructing a deviation-environment data set; S02133: The preset deviation analysis model analyzes the deviation-environment data set based on a machine self-learning algorithm to generate a deviation correction factor; S02134: Correcting the environmental impact factor based on the deviation correction factor to generate a corrected environmental impact factor.

[0048] Specifically for the above steps, the real-time collected production equipment parameter data, such as the current injection molding machine temperature and pressure, are compared with the revised predicted production equipment operating parameters at the corresponding time point. This comparison is to calculate the deviation between the actual parameters and the predicted parameters and generate deviation parameter data. For example, if the prediction model predicts that the temperature of the injection molding machine should be 260°C at a certain point in time, and the actual temperature is 265°C, the system will record this 5°C deviation.

[0049] Based on the common timeline, the system associates the deviation parameter data calculated in step S02131 with the production environment data. This means that the system records the environmental conditions under which the temperature deviation occurred, such as the workshop temperature and humidity at the time, and constructs a deviation-environmental data set. For example, the system may record that the injection molding machine has a temperature deviation of 5°C that exceeds the prediction in an environment with a humidity of 45% and a temperature of 28°C.

[0050] The pre-set deviation analysis model uses a machine self-learning algorithm to analyze the deviation-environment data set to generate deviation correction factors. These correction factors reflect the degree of deviation between the actual production parameters and the predicted parameters under specific environmental conditions. For example, the system may analyze that in an environment with high humidity, the actual temperature of the injection molding machine is often higher than the predicted temperature, thereby generating a deviation correction factor that takes into account the influence of humidity.

[0051] Based on the deviation correction factor generated in step S02133, the previously obtained environmental impact factor is corrected to generate a corrected environmental impact factor. This step ensures that the environmental impact factor can more accurately reflect the deviation between the actual production conditions and the prediction, and improves the accuracy of the prediction model. For example, if the deviation correction factor indicates that the effect of humidity on the temperature of the injection molding machine is greater than originally predicted, the system will adjust the environmental impact factor to more accurately predict the equipment operating parameters under different humidity conditions.

[0052] To sum up, the intelligent monitoring method for mold production of the present invention can realize real-time monitoring and dynamic adjustment of the working parameters of production equipment to adapt to the ever-changing production environment and conditions. The implementation of this method enables the production monitoring system to not only respond to changes in the equipment itself, but also optimize the prediction model according to deviations in actual production, thereby realizing more refined and intelligent production management.

[0053] Compared with traditional monitoring methods, this method improves the adaptability and flexibility of the production process through real-time monitoring and dynamic correction. When environmental conditions and equipment operating parameters change, the system can automatically adjust the operating parameters of the production equipment, reduce production fluctuations caused by inaccurate predictions, and reduce the defective product rate. In addition, this method can also improve energy utilization efficiency, reduce energy waste by optimizing production parameters, and achieve energy saving and consumption reduction.

[0054] After the step of S040: judging the actual error data as a defective product based on the defective product error threshold, and judging the actual error data as a defective product if the actual error data exceeds the defective product error threshold, the following steps are included: S041: classifying the defective products according to the preset defect types to construct a defect profile; Specifically, the defective products are classified according to the preset defect types to construct defect portraits. For example, if a batch of molds are found to have dimensional deviations, surface scratches, and bubbles during the production process, the system will classify them as "dimensional defects", "surface defects", and "material defects" based on the characteristics of these defects. In this way, the system can form defect portraits for each defect type, which is convenient for subsequent analysis and processing.

[0055] S042: Classifying the abnormal working trend of the equipment according to the defect portrait, and establishing a correlation relationship between the abnormal working trend of the equipment and the defect portrait for predicting the defect type; Specifically, the abnormal working trend of the equipment is associated with the defect profile to predict the defect type. For example, if the temperature and pressure of the injection molding machine fluctuate greatly during a certain period of time, and the products during this period mainly have "dimensional defects", the system will record this association. By analyzing historical data, the system can identify the relationship between specific equipment working trends and defect types, thereby providing a prediction basis for future production processes.

[0056] The intelligent mold production monitoring method of the present invention can achieve systematic management and analysis of defective products. Defect classification enables the system to clearly identify different types of defects, providing data support for subsequent quality improvement and production optimization. At the same time, by building a correlation between abnormal equipment working trends and defect portraits, the system can predict potential defect types in future production, so as to take preventive measures in advance.

[0057] Compared with traditional defect handling methods, this method significantly improves the efficiency and accuracy of defect management through intelligent defect analysis and correlation prediction. Traditional methods often rely on manual experience to judge and handle defects, which easily miss potential problems. This solution can monitor and analyze various parameters in the production process in real time through data-driven methods, and achieve more accurate defect prediction and management. This innovative approach not only improves the intelligence level of the production process, but also provides a strong guarantee for the company's quality control and production efficiency.

[0058] After the step of S041: classifying the defective products according to the preset defect types to construct a defect profile, the following steps are included: S0411: Obtain historical operation records, and associate the defect profile with the corresponding historical operation records based on the common timeline; S0412: constructing a defect-causing operation habit profile based on the relationship between the defect profile and the corresponding historical operation record; S0413: When an operation record similar to the defect-forming operation habit profile is detected, a defect warning warning is issued to remind the operator to monitor the product to avoid defective products.

[0059] For steps S0411-S0413, historical operation records are collected and analyzed, and these records are associated with defect profiles on a common timeline. For example, if in past production, the operator frequently generated bubble defects at a specific temperature setting of the injection molding machine, the system associates this operation record with the defect profile of "material defect". Such association helps to identify the operation mode or conditions that lead to specific types of defects.

[0060] Based on the association established in step S0411, the system further analyzes and learns to construct a defect-forming operating habit profile. This profile reflects the tendency to cause defects under specific conditions, such as equipment parameter settings, operator behavior habits, etc. For example, the system may find that in a high-temperature environment, some operators tend to set a higher injection speed, which is associated with a high incidence of "dimensional defects". In this way, the system can identify high-risk operating habits and provide a basis for subsequent risk warnings.

[0061] When the system detects an operation record similar to the defect-forming operation habit profile, it will automatically issue a defect warning. This warning reminds the operator to monitor the current production process in particular to avoid the appearance of defective products. For example, if the system detects that an operator starts to set a higher injection speed in a high temperature environment, the system will immediately issue an early warning to remind the operator of possible risks and recommend taking corresponding preventive measures, such as adjusting the injection speed or checking the mold temperature.

[0062] By implementing steps S0411 to S0413, the mold production intelligent monitoring method of the present invention can achieve early identification and early warning of potential defects in the production process. The implementation of this method enables the production monitoring system to not only respond to defects that have already occurred, but also predict and prevent defects that may occur in the future, significantly improving the intelligence and automation level of the production process. Compared with traditional methods that rely on manual monitoring and experience judgment, this method can more accurately identify and warn of potential production risks, reduce the production of defective products, and improve production efficiency and product quality in a data-driven manner. In addition, this method also helps to improve the operator's quality awareness and operational standardization, and promote continuous improvement and optimization of the production process.

[0063] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0064] In one embodiment, a mold production intelligent monitoring device based on artificial intelligence is provided, and the mold production intelligent monitoring device based on artificial intelligence corresponds to the mold production intelligent monitoring method based on artificial intelligence in the above embodiment. Figure 2 As shown, the mold production intelligent monitoring device based on artificial intelligence includes: The production basic data output unit 1 is used to obtain the model information of the mold production, and input the model information into the preset product information library for matching, so as to output the production basic data corresponding to the model, wherein the production basic data includes the basic parameter data of the production equipment, the basic data of the production environment, the basic parameter data of the product corresponding to each production link, and the defective product error threshold corresponding to each production link; A historical production equipment working parameter data set construction unit 2 is used to obtain the historical parameter data of the production equipment in each link, and record the historical parameter data of the production equipment based on a preset common time axis to construct a historical production equipment working parameter data set; The actual error data generating unit 3 is used to obtain the actual parameter data of the product corresponding to each production link, and compare the actual parameter data of the product with the basic parameter data of the product to generate actual error data; A defective product judging unit 4 is used to judge the actual error data as defective products based on the defective product error threshold. If the actual error data exceeds the defective product error threshold, the product is judged as a defective product, and the corresponding production time is marked as an abnormal production time period according to a preset time length; The abnormal production equipment parameter data marking unit 5 is used to extract the production equipment historical parameter data corresponding to the abnormal production time period according to the association relationship between the common time axis and the production equipment historical parameter data, and mark it as abnormal production equipment parameter data; The equipment abnormal operation trend generating unit 6 is used for analyzing the abnormal production equipment parameter data based on the machine self-learning algorithm using a pre-set production equipment analysis model to generate the abnormal operation trend of the production equipment; A real-time production equipment working parameter data set construction unit 7, used to obtain the real-time parameter data of the production equipment in each link, and record the real-time parameter data of the production equipment based on a preset common time axis to construct a real-time production equipment working parameter data set; A predicted production equipment working trend generating unit 8, which is used to pre-set a production equipment trend prediction model to analyze the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes predicted production equipment working parameters at a corresponding time point; An abnormal risk judgment unit 9 is used to pre-set an equipment trend comparison model to compare the predicted production equipment working trend with the abnormal working trend of the production equipment, and judge whether there is an abnormal risk; The risk warning control strategy generating unit 10 is used to pre-set an abnormal equipment control model, and generate a risk warning control strategy when there is an abnormal risk, wherein the risk warning control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

[0065] For the specific definition of an intelligent monitoring device for mold production based on artificial intelligence, please refer to the definition of an intelligent monitoring method for mold production based on artificial intelligence above, which will not be repeated here. Each module in the above-mentioned intelligent monitoring device for mold production based on artificial intelligence can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0066] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a database. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an intelligent monitoring method for mold production based on artificial intelligence is implemented.

[0067] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain model information of mold production, and input the model information into a pre-set product information library for matching, so as to output basic production data corresponding to the model, wherein the basic production data includes basic parameter data of production equipment, basic data of production environment, basic product parameter data corresponding to each production link, and defective product error threshold corresponding to each production link; Obtain the historical parameter data of the production equipment at each stage, and record the historical parameter data of the production equipment based on a preset public timeline to construct a historical production equipment working parameter data set; Acquire actual product parameter data corresponding to each production link, and compare the actual product parameter data with the basic product parameter data to generate actual error data; Defective product judgment is performed on the actual error data based on the defective product error threshold. If the actual error data exceeds the defective product error threshold, the product is judged as defective, and the corresponding production time is marked as an abnormal production time period according to a preset time length; According to the correlation between the common time axis and the historical parameter data of the production equipment, the historical parameter data of the production equipment corresponding to the abnormal production time period is extracted and marked as abnormal production equipment parameter data; The preset production equipment analysis model analyzes the abnormal production equipment parameter data based on a machine self-learning algorithm to identify abnormal working trends of the production equipment; Obtain the real-time parameter data of production equipment in each link, and record the real-time parameter data of production equipment based on a preset public timeline to build a real-time production equipment working parameter data set; The preset production equipment trend prediction model analyzes the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes predicted production equipment working parameters at a corresponding time point; The preset equipment trend comparison model compares the predicted production equipment working trend with the abnormal working trend of the production equipment, and determines whether there is an abnormal risk; If there is an abnormal risk, the preset equipment control abnormal control model generates a risk warning control strategy, and the risk warning control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

[0068] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain model information of mold production, and input the model information into a pre-set product information library for matching, so as to output basic production data corresponding to the model, wherein the basic production data includes basic parameter data of production equipment, basic data of production environment, basic product parameter data corresponding to each production link, and defective product error threshold corresponding to each production link; Obtain the historical parameter data of the production equipment at each stage, and record the historical parameter data of the production equipment based on a preset public timeline to construct a historical production equipment working parameter data set; Acquire actual product parameter data corresponding to each production link, and compare the actual product parameter data with the basic product parameter data to generate actual error data; Defective product judgment is performed on the actual error data based on the defective product error threshold. If the actual error data exceeds the defective product error threshold, the product is judged as defective, and the corresponding production time is marked as an abnormal production time period according to a preset time length; According to the correlation between the common time axis and the historical parameter data of the production equipment, the historical parameter data of the production equipment corresponding to the abnormal production time period is extracted and marked as abnormal production equipment parameter data; The preset production equipment analysis model analyzes the abnormal production equipment parameter data based on a machine self-learning algorithm to identify abnormal working trends of the production equipment; Obtain the real-time parameter data of production equipment in each link, and record the real-time parameter data of production equipment based on a preset public timeline to build a real-time production equipment working parameter data set; The preset production equipment trend prediction model analyzes the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes predicted production equipment working parameters at a corresponding time point; The preset equipment trend comparison model compares the predicted production equipment working trend with the abnormal working trend of the production equipment, and determines whether there is an abnormal risk; If there is an abnormal risk, the preset equipment control abnormal control model generates a risk warning control strategy, and the risk warning control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

[0069] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0070] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0071] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent monitoring method for mold production based on artificial intelligence, characterized in that: The method comprises the steps of: obtaining model information of mold production, and inputting the model information into a pre-set product information library for matching, so as to output basic production data corresponding to the model, wherein the basic production data comprises basic parameter data of production equipment, basic data of production environment, basic product parameter data corresponding to each production link, and defective product error threshold corresponding to each production link; Obtain the historical parameter data of the production equipment at each stage, and record the historical parameter data of the production equipment based on a preset public timeline to construct a historical production equipment working parameter data set; Acquire actual product parameter data corresponding to each production link, and compare the actual product parameter data with the basic product parameter data to generate actual error data; Defective product judgment is performed on the actual error data based on the defective product error threshold. If the actual error data exceeds the defective product error threshold, the product is judged as defective, and the corresponding production time is marked as an abnormal production time period according to a preset time length; According to the correlation between the common time axis and the historical parameter data of the production equipment, the historical parameter data of the production equipment corresponding to the abnormal production time period is extracted and marked as abnormal production equipment parameter data; The preset production equipment analysis model analyzes the abnormal production equipment parameter data based on a machine self-learning algorithm to identify abnormal working trends of the production equipment; Obtain the real-time parameter data of production equipment in each link, and record the real-time parameter data of production equipment based on a preset public timeline to build a real-time production equipment working parameter data set; The preset production equipment trend prediction model analyzes the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes predicted production equipment working parameters at a corresponding time point; The preset equipment trend comparison model compares the predicted production equipment working trend with the abnormal working trend of the production equipment, and determines whether there is an abnormal risk; If there is an abnormal risk, the preset equipment control abnormal control model generates a risk warning control strategy, and the risk warning control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

2. The method for intelligent monitoring of mold production based on artificial intelligence according to claim 1, characterized in that: After obtaining the historical parameter data of the production equipment in each link and recording the historical parameter data of the production equipment based on a preset common time axis to construct a historical production equipment working parameter data set, the following steps are included: Acquire energy consumption data of production equipment and input it into the production equipment working parameter data set, and associate the energy consumption data of production equipment with the working parameter data based on the common time axis to construct the equipment energy consumption data set; The preset energy consumption analysis model analyzes the equipment energy consumption data set based on a machine self-learning algorithm to generate an equipment energy consumption factor, wherein the equipment energy consumption factor is used to represent the correlation between energy consumption and equipment operating parameters; The preset energy consumption prediction model generates a predicted energy consumption trend based on the equipment energy consumption factor and the predicted production equipment working trend, and the predicted energy consumption trend corresponds one-to-one with the predicted production equipment working trend based on the common time axis; If the predicted energy consumption trend exceeds a preset energy consumption fluctuation threshold, an energy consumption adjustment strategy is generated, and the energy consumption adjustment strategy is used to adjust the working parameters of the production equipment to prevent the production energy consumption from exceeding the energy consumption fluctuation threshold.

3. The method for intelligent monitoring of mold production based on artificial intelligence according to claim 2 is characterized in that: After the step of acquiring the energy consumption data of the production equipment and inputting it into the production equipment working parameter data set, and associating the energy consumption data of the production equipment with the working parameter data based on the common time axis to construct the equipment energy consumption data set, the following steps are included: Acquire historical production environment data, and associate the historical production environment data with the historical parameter data of the production equipment based on the common time axis to construct an environment-operating parameter data set; The pre-set environmental impact analysis model analyzes the environment-working parameter data set based on a machine self-learning algorithm to generate environmental impact factors; The preset production equipment prediction model corrects the predicted production equipment working trend according to the environmental influencing factors to generate a corrected production equipment working trend, wherein the corrected production equipment working trend includes corrected predicted production equipment working parameters at the corresponding time point.

4. The method for intelligent monitoring of mold production based on artificial intelligence according to claim 3 is characterized in that: After the step of correcting the predicted production equipment working trend according to the environmental impact factor by the preset production equipment prediction model to generate a corrected production equipment working trend, the following steps are included: Comparing the real-time parameter data of the production equipment with the corrected predicted production equipment operating parameters at the corresponding time point to calculate deviation parameter data; Associating the deviation parameter data with the production environment data based on the common time axis and constructing a deviation-environment data set; The preset deviation analysis model analyzes the deviation-environment data set based on a machine self-learning algorithm to generate a deviation correction factor; The environmental impact factor is corrected based on the deviation correction factor to generate a corrected environmental impact factor.

5. The method for intelligent monitoring of mold production based on artificial intelligence according to claim 1, characterized in that: After the step of judging the actual error data as a defective product based on the defective product error threshold and judging the actual error data as a defective product if the actual error data exceeds the defective product error threshold, the following steps are included: Classify the defective products according to the preset defect types to construct a defect profile; The abnormal working trend of the equipment is classified accordingly according to the defect portrait, and a correlation relationship between the abnormal working trend of the equipment and the defect portrait is constructed for predicting the defect type.

6. The method for intelligent monitoring of mold production based on artificial intelligence according to claim 5, characterized in that: After the defective products are classified according to the preset defect types to construct a defect profile, the following steps are included: Acquire historical operation records, and associate the defect profile with corresponding historical operation records based on the common timeline; Based on the relationship between the defect profile and the corresponding historical operation record, a defect-causing operation habit profile is constructed; When an operation record similar to the defect-forming operation habit profile is detected, a defect warning alert is issued to remind the operator to monitor the product to avoid defective products.

7. The method for intelligent monitoring of mold production based on artificial intelligence according to claim 1, characterized in that: The machine self-learning algorithm includes a convolutional neural network and an unsupervised learning algorithm.

8. An intelligent monitoring device for mold production based on artificial intelligence, applied to an intelligent monitoring method for mold production based on artificial intelligence according to any one of claims 1 to 7, characterized in that: The device comprises: A production basic data output unit (1) is used to obtain model information of mold production, and input the model information into a pre-set product information library for matching, so as to output production basic data corresponding to the model, wherein the production basic data includes production equipment basic parameter data, production environment basic data, product basic parameter data corresponding to each production link, and defective product error threshold corresponding to each production link; A historical production equipment working parameter data set construction unit (2), used for obtaining the historical parameter data of the production equipment at each link, and recording the historical parameter data of the production equipment based on a preset common time axis to construct a historical production equipment working parameter data set; An actual error data generating unit (3) is used to obtain actual product parameter data corresponding to each production link, and compare the actual product parameter data with the basic product parameter data to generate actual error data; A defective product judgment unit (4) is used to judge the actual error data as a defective product based on the defective product error threshold, and if the actual error data exceeds the defective product error threshold, the product is judged as a defective product, and the corresponding production time is marked as an abnormal production time period according to a preset time length; An abnormal production equipment parameter data marking unit (5) is used to extract the production equipment historical parameter data corresponding to the abnormal production time period according to the association relationship between the common time axis and the production equipment historical parameter data, and mark it as abnormal production equipment parameter data; An equipment abnormal operation trend generating unit (6) is used to analyze the abnormal production equipment parameter data based on a machine self-learning algorithm using a pre-set production equipment analysis model to generate an abnormal operation trend of the production equipment; A real-time production equipment working parameter data set construction unit (7), used to obtain the real-time parameter data of the production equipment in each link, and record the real-time parameter data of the production equipment based on a preset common time axis to construct a real-time production equipment working parameter data set; A predicted production equipment working trend generating unit (8), which is used to pre-set a production equipment trend prediction model to analyze the production equipment working parameter data set based on a machine self-learning algorithm to generate a predicted production equipment working trend, wherein the predicted production equipment working trend includes the predicted production equipment working parameters at a corresponding time point; An abnormal risk judgment unit (9) is used to pre-set an equipment trend comparison model to compare the predicted production equipment working trend with the abnormal working trend of the production equipment, and judge whether there is an abnormal risk; A risk warning control strategy generating unit (10) is used to pre-set an abnormal control model for equipment control, and to generate a risk warning control strategy when an abnormal risk exists, wherein the risk warning control strategy is used to adjust the working parameters of the production equipment to avoid defective products.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the mold production intelligent monitoring method based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of an artificial intelligence-based intelligent monitoring method for mold production as described in any one of claims 1 to 7 are implemented.

Images