Production control system for intelligent manufacturing

Abstract

The invention belongs to the technical field of manufacturing and production, and particularly relates to an intelligent manufacturing and production control system, which is characterized in that production data on a production line are collected, and a database is established for the real-time data of the production line according to time nodes and station nodes for storage; carrying out instant report, trend analysis and anomaly detection on the collected data, carrying out deep analysis by comparing historical data, and identifying potential problems or optimization opportunities in production by establishing a prediction model; carrying out production scheduling based on a data analysis result, and carrying out optimal configuration on production line resources according to data analysis and production scheduling; the production strategy is optimized on the basis of the data analysis result in combination with production line production planning, actions are executed through the executor according to the control strategy, production line automatic control is achieved, and the effects of improving production efficiency, reducing cost and promoting intelligent development of the manufacturing industry are achieved.

Description

Technical Field

[0001] This invention relates to the field of manufacturing technology, specifically to a production control system for intelligent manufacturing. Background Technology

[0002] With the rise of global industry, intelligent manufacturing production control systems have become a key technology for promoting technological progress in industrial manufacturing, improving production efficiency and product quality. Intelligent manufacturing production control systems need to integrate computer technology, automatic control technology, communication technology, sensor technology and human-computer interaction technology to achieve intelligent, automated and networked production.

[0003] Currently, various intelligent manufacturing production control systems exist on the market, mainly falling into the following categories: Those that use PLCs (Programmable Logic Controllers) to program and control the production process logically, offering high stability and reliability but lacking flexibility; those that use IPCs to run applications for information integration and interaction, storing and querying production data in databases, but these systems are complex and difficult to maintain; and those that use sensors, RFID, and other technologies to collect production data in real time for remote monitoring and management, but these are costly and heavily reliant on networks. These systems often employ discrete technology stacking, resulting in a lack of organic connection between systems, low integration, and insufficient intelligence. Some systems remain at the data acquisition and transmission level, lacking intelligent analysis and decision support functions.

[0004] To address the aforementioned technical shortcomings, a solution for intelligent manufacturing production control systems is proposed. Summary of the Invention

[0005] To address the above problems, the present invention provides the following technical solution:

[0006] A production control system for intelligent manufacturing includes:

[0007] Collect real-time production data from the production line, and store the real-time production data in a database according to time nodes and workstation nodes;

[0008] The real-time production data is subjected to trend analysis, and compared with historical data to conduct in-depth analysis by establishing a predictive model to obtain data analysis results;

[0009] Production scheduling is performed based on the data analysis results, and production line resources are optimized according to the data analysis results and production scheduling.

[0010] The production line production plan is obtained, and the production strategy is optimized based on the data analysis results and the production line production plan. The actuators then execute actions according to the control strategy to achieve automated control of the production line.

[0011] Furthermore, the step of collecting real-time production data from the production line and establishing a database to store the real-time production data according to time nodes and workstation nodes includes:

[0012] Real-time production data generated during the production process is collected by setting up sensors, wherein the real-time production data includes temperature, pressure, production speed and status data of multiple devices;

[0013] The real-time production data is stored in a local database. The original data in the local database is identified according to the correspondence between production nodes and real-time production data. A data maintenance center is established to maintain the real-time production data.

[0014] The real-time production data is encrypted to obtain an encrypted dataset, and the encrypted dataset is transmitted to the data processing center via the network according to production needs.

[0015] Furthermore, the encryption process for obtaining the encrypted dataset from the real-time production data includes:

[0016] Remove erroneous, incomplete, and duplicate data from real-time production data to obtain qualified production data;

[0017] The qualified production data is standardized and normalized to obtain standard production data;

[0018] The aforementioned standard production data are encrypted to obtain an encrypted dataset.

[0019] Determine the adaptive number of categories for the encrypted dataset, and divide the encrypted dataset into categories based on the adaptive number of categories to obtain multiple encrypted data subsets.

[0020] Furthermore, the step of establishing the prediction model includes:

[0021] Based on the modeling objective, features that have a significant impact on the model are selected from the original data, resulting in multiple first features;

[0022] Based on actual needs, multiple first features are extracted, and the extracted features are transformed and combined to generate multiple second features;

[0023] Principal component analysis and linear discriminant analysis were used to reduce the dimensionality of multiple second features to obtain the modeling dataset.

[0024] The modeling dataset is divided into a training set and a test set. The preset model is trained using the training set. During the training process, the parameters of the preset model are adjusted to obtain the preset training model.

[0025] The pre-trained model is validated using a test set to evaluate its performance. The model's prediction results are analyzed and adjusted accordingly to obtain the prediction model.

[0026] Furthermore, the step of production scheduling based on the data analysis results includes:

[0027] Market demand is predicted based on historical data and market trends, and production plans are adjusted accordingly.

[0028] Acquire production equipment status, process parameters, and personnel arrangement data, and predict production capacity data based on the production equipment status, process parameters, and personnel arrangement data;

[0029] Analyze the operating data of production equipment, and adjust production plans and scheduling strategies based on the operating data and production capacity data;

[0030] By using data visualization tools, production progress and equipment status can be monitored in real time, problems can be identified and corrective measures can be taken in a timely manner, and comprehensive scheduling optimization can be carried out while considering production efficiency, energy consumption, production costs and delivery time.

[0031] By leveraging data analysis results, production processes can be optimized, tasks can be allocated to appropriate equipment and time periods, and equipment idle time and changeover time can be reduced.

[0032] Based on production needs and equipment status, allocate personnel, raw materials and other resources rationally to ensure coordinated operation of each production link, analyze the relationship between process parameters and product quality and production efficiency, optimize process parameter settings, and improve production efficiency and product quality.

[0033] Furthermore, the production strategy selection includes analyzing market and customer demands, clarifying product positioning and production targets, assessing existing production resources, including equipment, technology, personnel, and capital, designing multiple production strategy options, evaluating the advantages, disadvantages, and feasibility of each option, using data analysis tools and models to conduct quantitative analysis of each option, selecting the optimal option, implementing the selected production strategy, and monitoring the effects through real-time data, making adjustments and optimizations as necessary.

[0034] Furthermore, the step of achieving automated production line control by having the actuator execute actions according to the control strategy includes:

[0035] Control algorithms are designed based on collected sensor data to achieve precise control of key parameters of the production line;

[0036] The control algorithm is embedded into the programmable logic controller, and the control parameters and execution conditions are configured.

[0037] After the actuator performs the action, the sensor continues to monitor the system status and feeds back the actual value obtained from the monitoring to the control system;

[0038] The control system calculates the error and adjusts the control commands in real time by comparing the feedback value with the preset target value, ensuring that the production process operates stably according to the predetermined strategy.

[0039] A production control system for intelligent manufacturing includes:

[0040] A module is established to collect real-time production data from the production line, and the real-time production data is stored in a database according to time nodes and workstation nodes.

[0041] The analysis module is used to perform trend analysis on the real-time production data and compare it with historical data to conduct in-depth analysis by establishing a predictive model to obtain data analysis results.

[0042] The scheduling module is used to perform production scheduling based on the data analysis results, and to optimize the allocation of production line resources according to the data analysis results and the production scheduling.

[0043] The control module is used to acquire the production line plan, optimize the production strategy based on the data analysis results and the production line plan, and execute actions through actuators according to the control strategy to realize the automated control of the production line.

[0044] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described intelligent manufacturing production control method.

[0045] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps described above for the intelligent manufacturing production control method.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] This invention relates to an intelligent manufacturing production control system. It collects production data from the production line and stores the real-time data in a database based on time nodes and workstation nodes. The collected data is used for real-time reporting, trend analysis, and anomaly detection, and is compared with historical data for in-depth analysis. A predictive model is established to identify potential problems or optimization opportunities in production. Production scheduling is performed based on the data analysis results, and production line resources are optimized according to the data analysis and production scheduling. Based on the data analysis results and production line planning, production strategies are optimized, and actuators execute actions according to the control strategies to achieve automated production line control. This system improves production efficiency, reduces costs, and promotes the intelligent development of the manufacturing industry. Attached Figure Description

[0048] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0049] Figure 1 This is a schematic diagram of a method flow according to an embodiment of the present invention.

[0050] Figure 2 This is a schematic diagram of the device structure according to an embodiment of the present invention.

[0051] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0053] like Figure 1-Figure 3 As shown, a production control system for intelligent manufacturing includes:

[0054] This invention collects real-time production data from the production line, stores this data in a database based on time nodes and workstation nodes, and sequentially performs instant reporting, trend analysis, and anomaly detection on the real-time production data. It also compares the data with historical data and conducts in-depth analysis using a predictive model to obtain data analysis results. Based on these results, production scheduling is performed, and production line resources are optimized according to the data analysis results and production scheduling to obtain a production line production plan. The production strategy is then optimized based on the data analysis results and the production line production plan, and actuators execute actions according to the control strategy to achieve automated production line control. This invention, through real-time data analysis and automated control, enables rapid adjustment of production plans, reduces downtime and production bottlenecks. Data-driven scheduling and optimization help to rationally allocate production resources, reduce waste, and improve productivity. Trend analysis and predictive models can identify potential problems in advance, reducing failures and maintenance costs. In-depth analysis based on historical and real-time data supports more accurate decision-making and strategy adjustments, enabling rapid adaptation to market changes and demand fluctuations, and improving the production line's responsiveness and flexibility.

[0055] Specifically, the step of collecting real-time production data from the production line and storing the real-time production data in a database according to time nodes and workstation nodes includes:

[0056] Real-time production data generated during the production process is collected by setting up sensors. This real-time production data includes temperature, pressure, production speed, and status data from multiple devices. The data is stored in a local database, with raw data in the local database mapped one-to-one with each production node. A data maintenance center is established to maintain the real-time production data. The real-time production data is encrypted to obtain an encrypted dataset, which is then transmitted to the data processing center via network according to production needs. Collecting production data from the production line also includes standardizing the settings for equipment ports and transmission ports on the production line. This includes defining the port ranges for different types of services in the system, uniformly assigning specific port numbers to services and applications with the same or similar functions, assigning clear names and usage descriptions to each port for easy management and recording, defining external access control policies through firewalls or network devices, opening only necessary ports and closing unused or insecure ports to reduce the attack surface, exposing internal services to the outside through port mapping to ensure the use of unified external ports for easy management and access, and regularly auditing port usage to ensure no unauthorized or accidentally opened ports and to detect potential security risks.

[0057] Specifically, the encryption process for obtaining the encrypted dataset from the real-time production data includes:

[0058] This invention removes erroneous, incomplete, and duplicate data from real-time production data to obtain qualified production data. The qualified production data is then standardized and normalized to obtain standard production data. Multiple standard production data sets are then encrypted to obtain an encrypted dataset. An adaptive number of categories is determined for the encrypted dataset, and the encrypted dataset is categorized according to this adaptive number of categories to obtain multiple encrypted data subsets. In this invention, the removal of erroneous, incomplete, and duplicate data ensures the accuracy and integrity of the data, providing a reliable foundation for subsequent analysis. Standardization and normalization eliminate the influence of dimensions in the data, allowing data from different sources to be compared and analyzed under the same standard. Encryption protects data privacy and security, preventing unauthorized access or tampering during transmission and storage. The adaptive number of categories is determined adaptively to improve the accuracy and effectiveness of data classification. Dividing the encrypted dataset into multiple subsets allows for more detailed analysis and processing, improving the accuracy and operability of the analysis results. Accurate classification and analysis enable timely adjustments to production scheduling and optimization of resource allocation, improving the flexibility and responsiveness of the production line.

[0059] It should be noted that data encryption, including protecting data confidentiality during network transmission, commonly uses protocols such as HTTPS, VPN, and SSL / TLS. Encryption of at-rest data is frequently used in databases, file storage, and cloud storage to ensure data remains encrypted from sender to receiver, a common application in communication applications such as WhatsApp and Signal. Encryption of the entire hard drive or storage device uses tools like BitLocker and FileVault. Secure random number generators are used to create encryption keys, ensuring key strength and unpredictability. Keys should be securely stored in a Hardware Security Module (HSM) or an encrypted key management system, avoiding plaintext key storage. Keys should be distributed through secure channels to prevent interception during transmission. Keys should be changed regularly to reduce the risk of key cracking. Expired or unused keys should be securely destroyed to prevent malicious recovery.

[0060] Determine the privacy data aggregation value of each header and each encrypted data subset in the privacy data;

[0061] Select a title, compare the privacy data clustering value of the title with that of each encrypted data subset, and divide the privacy data corresponding to the title into the privacy data cluster corresponding to the smallest privacy data clustering value of the title. For the remaining titles, repeat the above steps to complete the division of the remaining titles and obtain multiple privacy data clusters.

[0062] The privacy data aggregation value of each header and each encrypted data subset in the privacy data can be determined using the following formula:

[0063]

[0064] Among them, G ij Let N represent the privacy data aggregation value of the i-th title and the j-th encrypted data subset, where N represents the total number of node data in the i-th title, and M represents the total number of node data in the j-th encrypted data subset. This represents the similarity between the nth node data in the i-th title and the m-th node data in the j-th encrypted data subset. Let n represent the influence factor of the nth node data in the i-th heading, where n = 1, 2, ..., N, and m = 1, 2, ..., M.

[0065] It should be noted that the similarity in this application can be determined using existing machine learning models. The influence factor of each node's data can be set from 0 to 1 according to the desensitization requirements, and the sum of the total influence factors is 1. Other methods can also be used in other embodiments, and no specific limitations are made here.

[0066] Select a privacy data cluster, determine the explicit boundary of the privacy data cluster, and explicitly remove the privacy data cluster according to the explicit boundary to obtain multiple implicit privacy data shrinkage clusters. Determine the privacy data desensitization value of each implicit privacy data shrinkage cluster according to the encrypted data subset corresponding to the privacy data cluster.

[0067] The explicit boundaries of this privacy data cluster can be determined by the following steps:

[0068] Determine multiple data judgment values ​​for this privacy data cluster;

[0069] Select one of the data judgment values. If the data judgment value exceeds the preset explicit threshold, then the privacy data corresponding to the data judgment value will be made explicit data.

[0070] For the remaining data judgment values, repeat the above steps to compare the remaining data judgment values ​​with the explicit threshold to obtain the explicit data corresponding to the remaining data judgment values;

[0071] The set of all explicit data is taken as the explicit boundary of this privacy data cluster.

[0072] Specifically, starting from the first node data, the implicit privacy data cluster is traversed. The first to the second sensitive node data in the implicit privacy data cluster that are the same as the corresponding encrypted data subset are taken as the first group of data, and the data judgment value of this group of data is determined. The second to the third sensitive node data in the implicit privacy data cluster that are the same as the corresponding encrypted data subset are taken as the second group of data, and the data judgment value of this group of data is determined. This process is repeated to determine multiple data judgment values ​​for the implicit privacy data cluster. If the data judgment value exceeds the explicit threshold, the data between the first and last sensitive node data in the privacy data corresponding to the data judgment value is taken as explicit data.

[0073] It should be noted that the explicit boundary in this application represents the set of privacy data that does not need to be anonymized from the acquired privacy data. Explicit data refers to the data in the acquired privacy data that does not need to be anonymized. Specifically, it can be represented as the privacy data in the privacy data cluster whose data judgment value is less than the explicit threshold. The explicit threshold represents the judgment criterion for classifying privacy data as explicit data. The explicit threshold can be set according to needs, and is generally set to 1.2 times the average value of all historical data judgment values. In other embodiments, other methods can also be used to set the data judgment value, which is not limited here.

[0074] In some embodiments, the data determination value of this set of data can be determined using the following formula:

[0075]

[0076] Where P represents the data judgment value of the data set, β represents the data judgment factor, Z represents the number of node data in the data set, S represents the number of numbers in the data set, and δ represents the number judgment coefficient.

[0077] It should be noted that in this application, when there is a period separating the first sensitive node data that is the same as the corresponding encrypted data subset and the second sensitive node data that is the same as the corresponding encrypted data subset in the data set, the number of node data after the period is divided by the number of node data in the data set, and the quotient is used as the data determination factor of the data set. The data factor represents the degree of correlation between the two sensitive node data in the data set. The larger the data determination factor, the smaller the degree of correlation between the two sensitive node data. The numerical determination coefficient in this application can be set according to historical experimental data, and is generally a positive integer.

[0078] Specifically, based on the explicit boundaries, the privacy data cluster is explicitly removed to obtain multiple implicit privacy data shrinkage clusters. Privacy data corresponding to the explicit boundaries in the implicit privacy data cluster is deleted. The remaining privacy data in the implicit privacy data cluster is shrunk using a clustering method in the prior art to obtain multiple implicit privacy data shrinkage clusters. In this application, the implicit privacy data shrinkage cluster represents the data set after the privacy data is shrunk.

[0079] The following steps can be used to determine the privacy data anonymization value of each hidden privacy data shrinkage cluster based on the encrypted data subset corresponding to that hidden privacy data cluster:

[0080] Determine the similarity between the v-th sensitive node data in the k-th implicit privacy data contraction cluster and the w-th sensitive node data in the encrypted data subset corresponding to that implicit privacy data contraction cluster.

[0081] Obtain the total number W of sensitive node data in the encrypted data subset corresponding to the k-th implicit privacy data shrinking cluster;

[0082] Obtain the total number V of sensitive node data in the k-th implicit privacy data shrinking cluster;

[0083] Determine the sensitivity factors of the v-th sensitive node data in the k-th implicit privacy data shrinking cluster.

[0084] Obtain the average of all data judgment values ​​for the k-th implicit privacy data shrinking cluster.

[0085] Get the maximum value of all data judgment values ​​for the k-th implicit privacy data shrinking cluster.

[0086] Obtain the minimum value of all data judgment values ​​for the k-th implicit privacy data shrinking cluster.

[0087] Based on the similarity between the v-th sensitive node data in the k-th implicit privacy data contraction cluster and the w-th sensitive node data in the encrypted data subset corresponding to that implicit privacy data contraction cluster. The total number W of sensitive node data in the encrypted data subset corresponding to the k-th implicit privacy data contraction cluster, the total number V of sensitive node data in the k-th implicit privacy data contraction cluster, and the sensitivity factor of the v-th sensitive node data in the k-th implicit privacy data contraction cluster. The average of all data judgment values ​​of the k-th implicit privacy data contraction cluster The maximum value of all data judgment values ​​of the k-th implicit privacy data contraction cluster. The minimum value of all data determination values ​​of the k-th implicit privacy data shrinking cluster. Determine the privacy data anonymization value for each implicit privacy data shrinking cluster, wherein the privacy data anonymization value can be determined using the following formula:

[0088]

[0089] Among them, T k This represents the privacy data anonymization value of the k-th implicit privacy data shrinking cluster.

[0090] Specifically, for example: There are 3 sensitive node data in the k-th implicit privacy data contraction cluster, and 4 sensitive node data in the encrypted data subset corresponding to this implicit privacy data contraction cluster. The similarity between the first sensitive node data in the implicit privacy data contraction cluster and each sensitive node data in the encrypted data subset is 0.9, 0.8, 0.9, and 0.6, respectively; the similarity between the second sensitive node data and each sensitive node data in the encrypted data subset is 0.8, 0.8, 0.9, and 0.6, respectively; and the similarity between the third sensitive node data and each sensitive node data in the encrypted data subset is 0.7, 0.8, 0.9, and 0.6, respectively. The sensitivity factors of the first, second, and third sensitive node data in the implicit privacy data contraction cluster are respectively... The average of all data judgment values ​​for this implicit privacy data shrinkage cluster. Maximum Minimum If the values ​​are 14, 18, and 10 respectively, then the privacy data anonymization value of the k-th implicit privacy data shrinking cluster is T. k =1.08.

[0091] Specifically, the steps for establishing the prediction model include:

[0092] Based on the modeling objective, features that have a significant impact on the model are selected from the original data, resulting in multiple first features;

[0093] Based on actual needs, multiple first features are extracted, and the extracted features are transformed and combined to generate multiple second features;

[0094] Principal component analysis and linear discriminant analysis are used to reduce the dimensionality of multiple second features to reduce computational complexity and obtain the modeling dataset;

[0095] The modeling dataset is divided into a training set and a test set. The preset model is trained using the training set. During the training process, the parameters of the preset model are adjusted so that the model accurately describes the inherent laws of the data, thus obtaining the preset training model.

[0096] The pre-trained model is validated using a test set to evaluate its performance, including metrics such as accuracy, precision, recall, and F1 score. The model's prediction results are then analyzed and adjusted accordingly to obtain the final prediction model.

[0097] Specifically, the step of production scheduling based on the data analysis results includes:

[0098] Market demand is predicted based on historical data and market trends, and production plans are adjusted accordingly to meet expected market demand.

[0099] Acquire data on production equipment status, process parameters, and personnel arrangements, and predict production capacity data based on the aforementioned data to ensure the feasibility of the production plan;

[0100] Analyze the operating data of production equipment, predict potential equipment failures and arrange maintenance in advance to avoid production interruptions. Adjust production plans and scheduling strategies based on the operating data and production capacity data, and handle emergencies such as urgent orders and equipment failures to minimize production interruptions and resource waste.

[0101] By using data visualization tools, production progress and equipment status can be monitored in real time, problems can be identified and corrective measures can be taken in a timely manner, and comprehensive scheduling optimization can be carried out while considering production efficiency, energy consumption, production costs and delivery time.

[0102] By leveraging data analysis results, production processes can be optimized, tasks can be allocated to appropriate equipment and time periods, and equipment idle time and changeover time can be reduced.

[0103] Based on production needs and equipment status, allocate personnel, raw materials and other resources rationally to ensure coordinated operation of each production link, analyze the relationship between process parameters and product quality and production efficiency, optimize process parameter settings, and improve production efficiency and product quality.

[0104] Specifically, the production strategy selection includes analyzing market and customer demand, clarifying product positioning and production goals, assessing existing production resources, including equipment, technology, personnel, and capital, designing multiple production strategy options, evaluating the advantages, disadvantages, and feasibility of each option, using data analysis tools and models to conduct quantitative analysis of each option, selecting the optimal option, implementing the selected production strategy, and monitoring the effect through real-time data, making adjustments and optimizations as necessary.

[0105] Specifically, the step of achieving automated production line control by having the actuator execute actions according to the control strategy includes:

[0106] Control algorithms are designed based on collected sensor data to achieve precise control of key parameters of the production line;

[0107] The control algorithm is embedded into the programmable logic controller, and the control parameters and execution conditions are configured.

[0108] After the actuator performs the action, the sensor continues to monitor the system status and feeds back the actual value obtained from the monitoring to the control system;

[0109] The control system calculates the error and adjusts the control commands in real time by comparing the feedback value with the preset target value, ensuring that the production process operates stably according to the predetermined strategy.

[0110] The present invention also provides a production control system for intelligent manufacturing, comprising:

[0111] A module is established to collect real-time production data from the production line, and the real-time production data is stored in a database according to time nodes and workstation nodes.

[0112] The analysis module is used to perform trend analysis on the real-time production data and compare it with historical data to conduct in-depth analysis by establishing a predictive model to obtain data analysis results.

[0113] The scheduling module is used to perform production scheduling based on the data analysis results, and to optimize the allocation of production line resources according to the data analysis results and the production scheduling.

[0114] The control module is used to acquire the production line plan, optimize the production strategy based on the data analysis results and the production line plan, and execute actions through actuators according to the control strategy to realize the automated control of the production line.

[0115] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described intelligent manufacturing production control method.

[0116] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps described above for the intelligent manufacturing production control method.

[0117] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments 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 a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0118] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0119] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for intelligent manufacturing production control, characterized in that: include: Collect real-time production data on the production line, and establish a database to store the real-time production data according to time nodes and workstation nodes; Perform trend analysis on the real-time production data, and compare it with historical data to conduct in-depth analysis by establishing a prediction model to obtain data analysis results; Performing production scheduling based on the data analysis results, and optimizing the configuration of production line resources according to the data analysis results and the production scheduling; Obtain the production plan of the production line, optimize the production strategy based on the data analysis results and the production plan of the production line, and execute actions according to the control strategy through the actuator to realize automatic control of the production line.

2. The method for intelligent manufacturing production control according to claim 1, characterized in that: The step of collecting real-time production data on the production line and establishing a database to store the real-time production data according to time nodes and workstation nodes includes: Collecting real-time production data generated during the production process by setting sensors, wherein the real-time production data includes temperature, pressure, production speed and status data of multiple devices; The real-time production data is stored in a local database, the original data in the local database is marked in one-to-one correspondence with the production nodes and the real-time production data, and a data maintenance center is established to maintain the real-time production data; The real-time production data is encrypted to obtain an encrypted data set, and the encrypted data set is transmitted to a data processing center via a network according to production requirements.

3. The method for intelligent manufacturing production control according to claim 2, characterized in that: The encrypting of the real-time production data to obtain the encrypted data set includes: Remove erroneous, incomplete and duplicate data from real-time production data to obtain qualified production data; Standardizing and normalizing the qualified production data to obtain standard production data; Encrypting a plurality of the standard production data to obtain an encrypted data set; The number of adaptive classifications of the encrypted data set is determined, and the encrypted data set is classified according to the number of adaptive classifications to obtain a plurality of encrypted data subsets.

4. The method for intelligent manufacturing production control according to claim 1, characterized in that: The step of establishing the prediction model comprises: Select features that have an important impact on the model from the original data according to the modeling goal, and obtain multiple first features; Extracting a plurality of the first features according to actual needs, and converting and combining the extracted features to generate a plurality of second features; Principal component analysis and linear discriminant analysis are used to reduce the dimensions of multiple second features to obtain a modeling data set; The modeling data set is divided into a training set and a test set, a preset model is trained by the training set, and parameters of the preset model are adjusted during the training process to obtain a preset training model; The trained preset training model is verified through the test set, the performance of the model is evaluated, the prediction results of the model are analyzed and adjusted accordingly to obtain the prediction model.

5. The method for intelligent manufacturing production control according to claim 1, characterized in that: The step of performing production scheduling based on the data analysis result includes: Predict market demand based on historical data and market trends, and adjust production plans according to market demand; Acquire production equipment status, process parameters and personnel arrangement data, and predict production capacity data based on the production equipment status, process parameters and personnel arrangement data; Analyze the operating data of production equipment and adjust the production plan and scheduling strategy according to the operating data and production capacity data; Use data visualization tools to monitor production progress and equipment status in real time, identify problems in a timely manner and take corrective measures. Take into account production efficiency, energy consumption, production costs and delivery time, and conduct comprehensive scheduling optimization; Use data analysis results to optimize production processes and assign tasks to appropriate equipment and time periods; According to production needs and equipment status, rationally allocate personnel, raw materials and other resources, analyze the relationship between process parameters and product quality and production efficiency, and optimize process parameter settings.

6. The method for intelligent manufacturing production control according to claim 1, characterized in that: The production strategy selection includes analyzing market demand and customer demand, clarifying product positioning and production goals, evaluating existing production resources, including equipment, technology, personnel and funds, designing multiple production strategy plans, evaluating the advantages and disadvantages and feasibility of each plan, using data analysis tools and models to conduct quantitative analysis of each plan, selecting and implementing production strategies, and monitoring the results through real-time data.

7. The method for intelligent manufacturing production control according to claim 1, characterized in that: The step of implementing automated control of the production line by executing actions according to the control strategy through the actuator includes: Design control algorithms based on collected sensor data; Embed the control algorithm into the programmable logic controller and configure the control parameters and execution conditions; After the actuator performs the action, the sensor continues to monitor the system status and feeds back the actual value obtained from the monitoring to the control system; The control system compares the feedback value with the preset target value, calculates the error and adjusts the control command in real time.

8. A production control system for intelligent manufacturing, characterized in that: include: Establishing a module for collecting real-time production data on the production line, and establishing a database to store the real-time production data according to time nodes and workstation nodes; An analysis module is used to perform trend analysis on the real-time production data and to compare historical data with the historical data by establishing a prediction model to perform in-depth analysis and obtain data analysis results; A scheduling module, used to perform production scheduling based on the data analysis results, and optimize the configuration of production line resources according to the data analysis results and production scheduling; The control module is used to obtain the production plan of the production line, optimize the production strategy according to the data analysis results combined with the production plan of the production line, and execute actions according to the control strategy through the actuator to realize automatic control of the production line.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images