Industrial intelligent manufacturing system based on big data

Abstract

The invention relates to the field of industrial intelligent manufacturing, and discloses an industrial intelligent manufacturing system based on big data, and the system comprises a scheduling background server which is used for obtaining the production equipment data and order data of a target manufacturing factory, generating an emergency order insertion number group, and determining an order insertion mode according to the order number and the delivery time limit; determining a production equipment identification sequence in combination with the target process name, and generating request information of each emergency order insertion number; and the big data interaction end is used for displaying the order insertion influence degree corresponding to each production equipment identifier and promoting the scheduling background server to generate an emergency order insertion scheme after receiving a request confirmation instruction. Therefore, efficient and green order insertion scheduling control is realized.

Description

Technical Field

[0001] The present invention relates to the field of industrial intelligent manufacturing, and in particular to an industrial intelligent manufacturing system based on big data. Background Art

[0002] In recent years, with the rapid development of digitalization, informatization, networking, automation, and artificial intelligence technologies, intelligent manufacturing has ushered in new development opportunities and has become a new development direction for modern advanced manufacturing. Big data technology can efficiently process and analyze the large amounts of real-time data generated during the manufacturing process. This data is often massive, complex, and multidimensional, providing strong support for subsequent decision-making and production scheduling. At the same time, with the increasing global attention to environmental protection and sustainable development, the manufacturing industry also needs to pay attention to carbon emissions during production and their impact on the environment.

[0003] In the existing industrial intelligent manufacturing process, the following technical problems often exist: First, existing manufacturing systems rely on manual judgment to process insertion orders, failing to consider the balance between delivery time and carbon emissions. Furthermore, they lack quantitative assessment of equipment status, leading to irrational production scheduling, equipment overload, or excessive carbon emissions, making efficient and green insertion scheduling difficult. Second, existing technologies struggle with assessing the future impact of urgent orders. These often rely on manual estimation or lack targeted forecasting tools, resulting in inaccurate forecasts, delayed information delivery, and inflexible displays. This makes it difficult for decision makers to foresee potential risks, and managers are prone to mishandling ongoing orders when adjusting plans, ultimately impacting production efficiency and overall operational stability. Third, carbon emission control in existing manufacturing systems mainly relies on static standards and manual experience for judgment. There is a lack of systematic analysis and hierarchical management based on equipment operating performance, process emission levels and energy usage structure. This can easily lead to high-emission equipment not being identified in a timely manner or improperly handled, affecting the overall carbon emission control efficiency and scientific decision-making of the factory. Summary of the Invention

[0004] This summary is intended to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] The present invention proposes an industrial intelligent manufacturing system based on big data to solve one or more of the technical problems mentioned in the above background technology section.

[0006] The present invention provides an industrial intelligent manufacturing system based on big data, comprising: a scheduling backend server, the scheduling backend server being used to obtain production equipment data and order data of a target manufacturing plant, the production equipment data comprising multiple production equipment identifiers, each of which has a corresponding process name; the order data comprising multiple order numbers, the order status corresponding to each order number, the order quantity, and the delivery date; analyzing the delivery date to obtain the delivery deadline corresponding to each order number and generate an emergency order number group; According to the order quantity and delivery deadline corresponding to each emergency order number in the emergency order number group, the emergency order number sequence and the order insertion mode corresponding to each emergency order number are determined, and the order insertion mode is the delivery time priority mode or the carbon emission minimization mode; for the target process name, the corresponding production equipment identification group is determined; according to the production equipment identification group and the order insertion mode, the first production equipment identification sequence and the second production equipment identification sequence are determined; according to each emergency order number, the first production equipment identification sequence and the second production equipment identification sequence in the emergency order number sequence, the request information corresponding to each emergency order number is generated and sent to the big data interaction terminal; The big data interaction terminal is used to display the impact degree of the insertion order corresponding to each production equipment identification. The impact degree of the insertion order is used by the user to determine whether to accept the request for the emergency insertion order number; after receiving the request confirmation instruction, the request confirmation instruction is sent to the scheduling background server to enable the scheduling background server to generate the corresponding emergency insertion order plan.

[0007] Optionally, analyze the delivery date to obtain the delivery deadline corresponding to each order number and generate an emergency order number group, including: The delivery date corresponding to each order number is analyzed to determine the delivery deadline corresponding to each order number; the order number whose delivery deadline is less than the preset delivery deadline or the order quantity is greater than the preset order quantity among multiple order numbers is determined as an emergency order number to obtain an emergency order number group.

[0008] Optionally, the production equipment data also includes the production rate, real-time equipment health score and carbon emission data corresponding to each production equipment identifier, as well as Determining a first production equipment identification sequence and a second production equipment identification sequence according to the production equipment identification group and the order insertion mode includes: Based on the production rate and real-time equipment health score corresponding to the production equipment identification, the first production equipment identification sequence corresponding to the delivery time priority mode is determined; based on the carbon emission data corresponding to the production equipment identification, the second production equipment identification sequence corresponding to the carbon emission minimization mode is determined.

[0009] Optionally, according to each emergency order number in the emergency order number sequence, the first production equipment identification sequence, and the second production equipment identification sequence, generating request information corresponding to each emergency order number and sending it to the big data interaction terminal, including: Match each emergency order number in the emergency order number sequence with the corresponding production equipment identification. If the order mode corresponding to the emergency order number is the delivery time priority mode, match it in the first production equipment identification sequence; if the order mode corresponding to the emergency order number is the carbon emission minimization mode, match it in the second production equipment identification sequence; generate request information corresponding to each emergency order number based on each emergency order number and the corresponding production equipment identification, and send the request information corresponding to each emergency order number to the big data interaction terminal.

[0010] Optionally, a real-time device health score is determined by the following steps: Obtaining a service life and multiple real-time parameters corresponding to each of the multiple production equipment identifications, analyzing each of the multiple real-time parameters corresponding to each of the production equipment identifications with a corresponding preset standard parameter interval, determining a real-time parameter in the multiple real-time parameters corresponding to each of the production equipment identifications that exceeds the corresponding preset standard parameter interval as an abnormal parameter, obtaining an abnormal parameter group, and determining the number of abnormal parameters in the abnormal parameter group corresponding to each of the production equipment identifications; Obtain the normal operation time and total operation time corresponding to each production equipment identification, calculate the normal operation time and total operation time corresponding to each production equipment identification, and obtain the normal operation ratio corresponding to each production equipment identification; Obtain an equipment health score table, which includes multiple numbers of abnormal parameters, a score for the number of abnormal parameters corresponding to each number of abnormal parameters, multiple normal operating ratios, a score for the normal operating ratio corresponding to each normal operating ratio, multiple service years, and a service life score corresponding to each service life; match the number of abnormal parameters, normal operating ratio, and service life corresponding to each production equipment identifier in the equipment health score table to obtain the score for the number of abnormal parameters, the score for the normal operating ratio, and the service life score corresponding to each production equipment identifier; Weights are configured for the abnormal parameter quantity score, normal operation ratio score, and service life score corresponding to the production equipment identification. The abnormal parameter quantity score, normal operation ratio score, and service life score corresponding to each production equipment identification are weighted and summed up using the weights to obtain the real-time equipment health score corresponding to each production equipment identification.

[0011] Optionally, the order data also includes the part name corresponding to each order number, and The insertion mode for each emergency insertion order number is determined by the following steps: Obtain a historical production data record set, where each historical production data record in the historical production data record set includes multiple historical production part names, the order quantity corresponding to each historical production part name, and the production duration; match the part name and order quantity corresponding to each emergency order number in the historical production data record set, determine a target historical production data record group corresponding to each emergency order number, determine the production duration included in the target historical production data record group as the estimated production duration, and obtain an estimated production duration group corresponding to each emergency order number; Calculate the average of the estimated production time groups corresponding to the emergency order numbers to obtain the estimated average production time corresponding to each emergency order number; The estimated average production time and corresponding delivery deadline corresponding to each emergency order number are compared. If the estimated average production time is greater than or equal to the corresponding delivery deadline, the delivery time priority mode is matched; if the estimated average production time is less than the corresponding delivery deadline, the carbon emission minimization mode is matched.

[0012] Optionally, the scheduling backend server is also used to: When a prediction request corresponding to a target emergency order number is received, the prediction request corresponding to the target emergency order number is analyzed to determine the requesting user type, the target prediction demand type, and the target order mode; wherein the target prediction demand type includes one of the following: order delivery time prediction, order carbon emission prediction; Obtain a pre-built forecast model library. Each forecast model in the forecast model library has a corresponding forecast demand type and forecast accuracy. Based on the target forecast demand type, determine whether there is a forecast model in the forecast model library that matches the target forecast demand type. If not, obtain a new forecast model group from the cloud based on the target forecast demand type and the forecast accuracy corresponding to each new forecast model in the new forecast model group.

[0013] Optionally, the scheduling backend server is also used to: Sort the newly added prediction model groups in descending order of prediction accuracy to obtain a newly added prediction model sequence, and use the newly added prediction model ranked first in the newly added prediction model sequence as the target prediction model; Obtain the target data group corresponding to the target emergency order number, input the target data group into the target prediction model, and obtain the prediction result; Acquire multiple display modes, determine display data items according to the requesting user type and the target insertion mode, select a target display mode from the multiple display modes according to the display data items, and display the prediction results through the target display mode.

[0014] Optionally, the scheduling backend server is also used to: When receiving the adjustment information corresponding to the displayed emergency order number sequence from the user, the emergency order number included in the adjustment information is determined as the emergency order number to be adjusted; The order status corresponding to the emergency order number to be adjusted is verified to determine whether the order status corresponding to the emergency order number to be adjusted is in a waiting state. If it is in a waiting state, the updated emergency order number sequence is obtained; if it is in a production state, an adjustment-unable prompt message is generated and sent to the big data interaction terminal.

[0015] The present invention has the following beneficial effects: 1. Improved the intelligence and greenness of production scheduling. Specifically, by analyzing the order delivery deadline and part type, and combining historical production data to infer the expected production time of emergency orders, and automatically matching the delivery time priority or carbon emission minimization mode accordingly, the order insertion decision is more targeted and reasonable. At the same time, a real-time equipment health scoring mechanism is introduced, and factors such as the number of abnormal parameters, normal operation ratio and service life are included in the comprehensive scoring system to ensure that the equipment involved in the order insertion scheduling is in good operating condition, and effectively reduce the risk of delivery delays or increased carbon emissions due to equipment failure. The system also dynamically evaluates the delivery time or carbon emissions based on the big data prediction model, and matches the corresponding visualization display scheme according to the user type and order insertion mode, thereby improving the decision-making auxiliary value of the prediction information. The overall solution significantly improves the intelligence and greenness of production scheduling, realizes the multi-objective coordinated optimization of delivery efficiency, production safety and environmental protection indicators, and has good industrial application value and promotion prospects; 2. Improved adaptability of prediction models and display methods, boosting production efficiency. Specifically, by introducing a "prediction model library + prediction accuracy + user profiling + display mode matching" mechanism, the system significantly enhances the intelligence and customization of the emergency order insertion prediction module. Upon receiving a user prediction request, the system automatically parses the user type (e.g., decision maker or analyst), the target forecast requirement type (e.g., delivery time or carbon emissions), and the current order insertion mode. It prioritizes matching models in the local model library. If no match exists, it dynamically calls a cloud-based model to form a candidate group. The optimal model is then automatically selected after ranking by prediction accuracy, improving prediction reliability and adaptability. After the prediction is complete, the system intelligently selects a matching display mode based on user type and order insertion mode. For example, a simple mode allows decision makers to quickly access key indicators, while a multi-dimensional mode provides analysts with rich information for in-depth analysis, thereby improving information readability and decision-making efficiency. Furthermore, the system's order status verification mechanism prevents users from accidentally modifying orders that have already entered production. The system promptly provides "unable to adjust" notifications, avoiding scheduling confusion and enhancing system stability and user experience. The overall solution effectively solves core issues in existing technologies, such as poor forecast adaptability, rigid display, and uncontrollable production scheduling. 3. Improves the accuracy and real-time performance of carbon emission management, and enhances the efficiency of scientific decision-making for equipment replacement and energy efficiency optimization. Specifically, by establishing a carbon emission identification and classification mechanism based on big data analysis, comprehensive assessment and intelligent classification of various types of production equipment in the manufacturing system during the carbon emission control process are achieved. Specifically, this application first screens out carbon emission risk equipment based on equipment carbon emission data. Based on a preset performance matching table, it generates equipment performance scores based on the equipment's age and production rate. Equipment is then classified as "to be upgraded" or "to be replaced," ensuring more targeted resource investment. At the same time, the system further evaluates the average carbon emission level of each process. After identifying processes that exceed the standard, it generates parameter adjustment information and energy replacement recommendations based on standard processing time and energy type, providing a basis for optimizing high-carbon emission processes. Furthermore, all analysis results and adjustment recommendations are intuitively displayed through a big data interactive terminal, assisting managers in timely adjusting equipment operation and maintenance and production strategies. As a result, this application not only improves the accuracy and real-time performance of carbon emission management, but also improves the efficiency of scientific decision-making for equipment replacement and energy efficiency optimization, helping manufacturing companies achieve smarter and greener production management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features, advantages, and aspects of the various embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the elements are not necessarily drawn to scale.

[0017] Figure 1 This is an exemplary architecture diagram of an industrial intelligent manufacturing system based on big data of the present invention; Figure 2 This is a flowchart of a big data-based industrial intelligent manufacturing system for generating request information; Figure 3 This is a flow chart of abnormal parameter detection in an industrial intelligent manufacturing system based on big data of the present invention; Figure 4 This is a flowchart of a target prediction model acquisition process of an industrial intelligent manufacturing system based on big data according to the present invention; Figure 5 This is a flowchart of a target display mode selection process for an industrial intelligent manufacturing system based on big data according to the present invention. DETAILED DESCRIPTION

[0018] The present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features of the embodiments of the present invention may be combined with each other.

[0020] It should be noted that the concepts of "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices of the present invention are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] like Figure 1 FIG. 1 is an exemplary architecture diagram of an industrial intelligent manufacturing system based on big data according to the present invention, wherein the industrial intelligent manufacturing system includes a scheduling backend service terminal 101 and a big data interaction terminal 102 .

[0025] Among them, the scheduling background server 101 is used to obtain the production equipment data and order data of the target manufacturing plant. The production equipment data includes multiple production equipment identifications, and each production equipment identification has a corresponding process name; the order data includes multiple order numbers, the order status corresponding to each order number, the order quantity and the delivery date; the delivery date is analyzed to obtain the delivery deadline corresponding to each order number and generate an emergency order number group.

[0026] In some embodiments, the scheduling backend server 101 may be the scheduling backend server 101, and the target manufacturing plant may be a manufacturing plant specified by the user for research. The target manufacturing plant terminal stores the production equipment data and order data of the target manufacturing plant. The target manufacturing plant terminal establishes a communication connection with the scheduling backend server. On this basis, the production equipment data and order data of the target manufacturing plant are obtained from the target manufacturing plant terminal. The production equipment data includes multiple production equipment identifiers, each of which has a corresponding process name. The order data includes multiple order numbers, the part name corresponding to each order number, the order status, the order quantity, and the delivery date. Specifically, the production equipment refers to the machine used to produce parts in the target manufacturing plant. The production equipment identifier is a unique number for each production equipment, which is used to distinguish different production equipment. The multiple production equipment identifiers can be production equipment A, production equipment B, production equipment C, and so on. The process name can refer to a technical step or work link set up to complete a specific task in the production process, which can be spheroidizing annealing, shelling and descaling, cold forging, threading, heat treatment, surface treatment, and so on.

[0027] In some embodiments, the order number is a unique number for each order, used to distinguish different orders. Multiple order numbers may include Order 1001, Order 1002, and Order 1003, and so on. Each order number has a corresponding part name. For example, Order 1001 may have a corresponding part name of P1 bolt. The order status refers to the production progress of the corresponding part name and may include the following: waiting, production, and completed. The order quantity is the quantity to be produced. For example, the order quantity of P1 bolts in Order 1001 is 100 pieces. The delivery date is the estimated time when the order is completed and delivered. For example, the delivery date of Order 1001 is January 15, 2024. Based on this, the delivery date corresponding to each order number is analyzed to determine the corresponding delivery deadline for each order number. Among the multiple order numbers, the order number with a delivery deadline less than the preset delivery deadline or an order quantity greater than the preset order quantity is identified as an emergency insertion order number, thereby obtaining an emergency insertion order number group. Specifically, the time difference between the current time and the delivery date is calculated as the delivery deadline. For example, if today is May 14th and the order delivery date is May 20th, the delivery deadline is 6 days. The system then iterates through multiple order numbers and, for each order number, compares whether the current order's delivery deadline is less than a preset delivery deadline. This typically indicates that the order is very close to the deadline. Alternatively, it compares whether the current order's quantity is greater than a preset quantity. This may indicate that the order volume is too large, requiring special resources or longer preparation time. If any of the following conditions (delivery deadline less than the preset value or order quantity greater than the preset value) is met, the order number is identified as an urgent insertion order. All order numbers identified as urgent insertion orders are collected and formed into a list or data structure, known as the urgent insertion order group. The preset delivery deadline refers to a time threshold set by the system to determine whether an order requires urgent processing due to a tight delivery schedule. It is typically based on historical production cycles and customer demand. For example, if a factory's average production cycle is 5 days, the preset delivery deadline might be set to 7 days (allowing for a buffer time). If the customer has strict requirements for certain orders (such as delivery within 3 days), this value can be adjusted for specific order types. The preset order quantity refers to an order quantity threshold set by the system, which is used to determine whether an order requires special scheduling due to excessive production volume. It is often based on the factory production capacity and equipment load capacity. For example: if a single device can produce a maximum of 200 pieces per day, 1,000 pieces may take 5 days to complete, so 1,000 pieces is set as the threshold. If the factory's production capacity is tight during the peak season, this value can be lowered (such as 500 pieces) to provide earlier warning. The emergency order number is a unique identifier for orders that require priority processing or special arrangements due to approaching delivery deadlines or excessive order quantities. The emergency order number group is a collection of all emergency order numbers.

[0028] The scheduling backend service terminal 101 is also used to determine the emergency order number sequence and the order insertion mode corresponding to each emergency order number according to the order quantity and delivery deadline corresponding to each emergency order number in the emergency order number group, and the order insertion mode is the delivery time priority mode or the carbon emission minimization mode; for the target process name, determine the corresponding production equipment identification group; according to the production equipment identification group and the order insertion mode, determine the first production equipment identification sequence and the second production equipment identification sequence; according to each emergency order number, the first production equipment identification sequence and the second production equipment identification sequence in the emergency order number sequence, generate the request information corresponding to each emergency order number and send it to the big data interaction terminal 102.

[0029] In some embodiments, the sequence of emergency order numbers is determined by the following steps: the target manufacturing plant terminal stores an order ranking table, based on which the scheduling backend server 101 establishes a communication connection with the target manufacturing plant terminal to obtain the order ranking table, which includes multiple order quantities, order quantity scores corresponding to each order quantity, multiple delivery deadlines, and delivery deadline scores corresponding to each delivery deadline. The order quantity and delivery deadline of each emergency order number in the emergency order number group are matched in the order ranking table to obtain the order quantity score and delivery deadline score of each emergency order number, and the order quantity score and delivery deadline score of each emergency order number are respectively assigned weights. The order quantity score and delivery deadline score of each emergency order number are weighted and summed according to the weights to obtain the urgency score of each emergency order number. The emergency order number group is sorted in descending order of the urgency score to obtain the emergency order number sequence and determine the order mode corresponding to each emergency order number. The emergency order number sequence is an ordered list of orders in the emergency order number group sorted according to a certain priority (such as the urgency of the delivery deadline). The insertion order mode is a scheduling strategy assigned to each urgent insertion order number. The insertion order mode can be either delivery time priority or carbon emission minimization mode. The delivery time priority mode prioritizes ensuring on-time delivery of orders, with the goal of ensuring urgent orders are completed as quickly as possible. The carbon emission minimization mode prioritizes energy conservation and emissions reduction by selecting equipment with lower carbon emissions, prioritizing environmental protection for orders with ample delivery time. The target process name refers to the production steps required for a specific urgent insertion order (e.g., the P1 bolt in order 1001), such as "cold forging." Based on this target process name, the scheduling backend server 101 queries its stored production equipment data (including the process name of each production equipment) and selects all production equipment identifiers capable of performing the target process name, forming a production equipment identifier group. For example, if the "cold forging" process can be performed by production equipment A and production equipment C, a production equipment identifier group is generated that includes production equipment A and production equipment C. A production equipment identifier group is the set of all production equipment identifiers capable of performing the target process name (e.g., "cold forging").

[0030] In some embodiments, the production equipment data also includes the production rate, real-time equipment health score and carbon emission data corresponding to each production equipment identifier. Based on the production rate and real-time equipment health score corresponding to the production equipment identifier, the first production equipment identifier sequence corresponding to the delivery time priority mode is determined. Based on the carbon emission data corresponding to the production equipment identifier, the second production equipment identifier sequence corresponding to the carbon emission minimization mode is determined. Among them, the production rate refers to the number of parts that each production equipment can produce per unit time. For example, the production rate of production equipment A is 50 pieces / hour. The real-time equipment health score indicates the health level of the current operating status of the equipment, usually expressed as a score (for example, 0-100). For example, the real-time equipment health score of production equipment A is 85 points. Carbon emission data refers to the carbon emissions generated by each production equipment during the production process, usually expressed as carbon emissions per unit product. The carbon emission data of different production equipment are different. Specifically, high-efficiency equipment uses advanced technology, consumes less energy, and produces fewer carbon emissions. Low-efficiency equipment consumes more energy and produces higher carbon emissions. High-speed mechanical stamping equipment, while capable of high production rates, also produces high carbon emissions due to its huge instantaneous power requirements. Energy-saving CNC equipment, while capable of lower production rates, consumes very little overall energy. Older equipment, however, has low operating efficiency, long setup times, and continues to consume high energy even when idle. For example, the carbon emissions for production equipment A are 0.5 kg CO₂e per unit.

[0031] In some embodiments, the first production equipment identification sequence is determined by the following steps: the target manufacturing plant terminal stores a preconfigured production equipment scoring table. Based on this, the scheduling backend server 101 establishes a communication connection with the target manufacturing plant terminal to obtain the preconfigured production equipment scoring table, which includes multiple production rates and a corresponding production rate score for each production rate. The production rate of each production equipment identification is matched against the production equipment scoring table to obtain a production rate score for each production equipment identification. Weights are assigned to the production rate score and real-time equipment health score of each production equipment identification. The weighted sum of the production rate score and real-time equipment health score for each production equipment identification is calculated using the weights to obtain a comprehensive production rate and health score for each production equipment identification. The multiple production equipment identifications in the production equipment identification group are sorted in descending order of their comprehensive production rate and health scores to obtain a first production equipment identification sequence corresponding to the delivery time priority mode. The delivery time priority mode requires completing production tasks in the shortest possible time, therefore prioritizing equipment that is both high-speed and stable. The production rate measures execution efficiency, while the health score ensures reliability; both contribute to the goals of the delivery time priority mode. On the other hand, the second production equipment identification sequence can be determined by directly sorting the production equipment identification group in ascending order of carbon emission data based on the carbon emission data of each production equipment identification, thereby obtaining a second production equipment identification sequence suitable for the carbon emission minimization mode. The first production equipment identification sequence refers to the equipment arrangement sequence obtained by sorting the production equipment identification group according to the comprehensive production capacity of each equipment in the "delivery time priority mode" under the "delivery time priority mode." The second production equipment identification sequence refers to the equipment arrangement sequence obtained by sorting the production equipment identification group according to the carbon emission per unit output of each equipment in the "carbon emission minimization mode" under the "carbon emission minimization mode" under the "carbon emission minimization mode" under the "carbon emission minimization mode" under the "carbon emission minimization mode" under the "carbon emission minimization mode" under the "carbon emission per unit output" of each equipment.

[0032] In some embodiments, each emergency order number in the emergency order number sequence is matched to a corresponding production equipment identifier. If the order mode corresponding to the emergency order number is a delivery time priority mode, a match is performed in the first production equipment identifier sequence; if the order mode corresponding to the emergency order number is a carbon emission minimization mode, a match is performed in the second production equipment identifier sequence. Based on each emergency order number and its corresponding production equipment identifier, a request message corresponding to each emergency order number is generated and sent to the big data interaction terminal 102. Specifically, for each emergency order number in the emergency order number sequence, a determination is first made as to whether the corresponding order mode is a delivery time priority mode or a carbon emission minimization mode. Based on the determination result, a suitable device is selected from the corresponding production equipment identifier sequence. If the delivery time priority mode is selected, a matching production device is sequentially searched in the first production equipment identifier sequence. If the carbon emission minimization mode is selected, a matching production device is searched in the second production equipment identifier sequence. After successfully assigning a suitable device to a particular emergency order number, the scheduling backend server 101 binds the emergency order number to the selected production equipment identifier in a one-to-one correspondence. On this basis, the dispatching backend server 101 will generate a request message for each bound emergency order number, such as Figure 2 As shown, it is a flowchart of a process of generating request information of an industrial intelligent manufacturing system based on big data of the present invention, and sending it to the big data interaction terminal 102 through a preset communication protocol and interface. Among them, the request information request information refers to the data packet automatically generated and encapsulated by the scheduling background service terminal 101 for each emergency order number. Its core purpose is to send the emergency order recommendation plan obtained by the system after complex calculations and intelligent decision-making to the big data interaction terminal 102 in a clear, comprehensive and easy-to-understand manner for users to review, confirm and make final decisions. The request information includes at least the following contents: emergency order number, matching production equipment identification, order mode and other contents.

[0033] The big data interaction terminal 102 is used to display the impact degree of the insertion order corresponding to each production equipment identification. The impact degree of the insertion order is used by the user to determine whether to accept the request for the emergency insertion order number; after receiving the request confirmation instruction, the request confirmation instruction is sent to the scheduling background server 101, so that the scheduling background server 101 generates the corresponding emergency insertion order plan.

[0034] In some embodiments, the big data interaction terminal 102 is a user interface that communicates with the scheduling backend server 101 and can be a web console, desktop application, or mobile app. It is used to receive scheduling recommendations, display key parameters, and support user confirmation. The big data interaction terminal 102 includes a device status prompt information display window, which displays device status prompts. This prompt information includes the impact level of each production equipment identifier associated with the insertion order. For example, it can display information such as "Current Scheduling Status of Production Equipment A," "Delay Amount If a New Insert Order Is Accepted," and "Current Health Score" in the form of a list, chart, or color icon. The device status prompt information display window is a specific area or module within the big data interaction terminal 102 specifically designed to present dynamic device information. The device status prompt information includes the real-time operating status of all devices and a collection of data on the potential chain effects of an insertion order. Its core component is the impact level of the insertion order. The impact level of the insertion order is a quantitative indicator that measures the positive or negative impact an urgent insertion order may have on existing production plans and resources (specifically, a specific piece of production equipment). It serves as a key basis for users to decide whether to accept an urgent insertion order request. It is not a single numerical value, but may be a composite information containing multiple indicators. The impact degree of an emergency order insertion is a quantitative indicator used to measure the comprehensive impact that an emergency order insertion may have on the existing production plan, the operating status of production equipment, resource consumption, and the environmental footprint. The calculation process of the impact degree of an emergency order insertion is as follows: W1 multiplied by the equipment utilization impact degree score plus W2 multiplied by the equipment health impact degree score plus W3 multiplied by the carbon emission impact degree score plus W4 multiplied by the production plan impact degree score, that is, the weighted sum is used to obtain the impact degree score of the order insertion; based on the impact degree score of the order insertion, the impact degree level table of the order insertion is queried to determine the impact degree of the order insertion. The impact degree score of the order insertion can be divided into multiple levels, for example, 0-40 points: mild impact (displayed in green); 41-70 points: moderate impact (displayed in yellow); 71-00 points: severe impact (red warning). Among them, W1, W2, W3 and W4 are the weights of each factor, which are dynamically adjusted according to demand.

[0035] In some embodiments, the degree of impact of equipment utilization is the increase in equipment utilization after the order is inserted divided by the maximum allowable utilization of the equipment. For example, the current utilization of the equipment is 60%, it is expected to be 85% after the order is inserted, and the maximum allowable utilization is 90%. The degree of impact of equipment utilization is: 85% minus 60% divided by 90%, which is approximately equal to 0.28. The degree of impact of equipment health is the real-time health score of the equipment before the order is inserted minus the predicted value of the real-time health score of the equipment after the order is inserted to obtain a first result, and the first result is divided by the real-time health score of the equipment before the order is inserted. For example, the score before the order is 90 and the predicted score after the order is 80. The degree of impact of equipment health is: 90 minus 80 divided by 90, which is approximately equal to 0.11. The degree of impact of carbon emissions is the increase in carbon emissions of the production equipment after the order is inserted divided by the carbon emissions before the order corresponding to the equipment before the order is inserted. For example, if the original emissions were 0.5 kg CO₂e / unit and increased to 0.6 kg CO₂e / unit after the order insertion, the carbon emissions impact is 0.6 minus 0.5 divided by 0.5, which equals 0.2. The production plan impact is the delay of other orders caused by the order insertion divided by the sum of the original planned completion times of those other orders. For example, if the order insertion caused a total delay of 10 hours for three orders, while their original total duration was 100 hours, the impact is 10 divided by 100, which equals 0.1. The impact on equipment utilization, equipment health, carbon emissions, and production plan is matched against a preconfigured impact comparison table to obtain the equipment utilization impact score, equipment health impact score, carbon emissions impact score, and production plan impact score. For example, the equipment utilization impact is 0.28, and the corresponding score is 65; the equipment health impact is 0.11, and the corresponding score is 60; the carbon emission impact is 0.2, and the corresponding score is 55; the production plan impact is 0.1, and the corresponding score is 50. The scheduling backend server 101 stores a pre-configured impact comparison table, which includes multiple equipment utilization impacts, the equipment utilization impact scores corresponding to each equipment utilization impact, multiple equipment health impacts, the equipment health impact scores corresponding to each equipment health impact, multiple carbon emission impacts, the carbon emission impact scores corresponding to each carbon emission impact, multiple production plan impacts, and the production plan impact scores corresponding to each production plan impact.

[0036] In some embodiments, the big data interaction terminal 102 displays the degree of impact of each device's access to the order. After browsing, the user makes a judgment on whether to agree to execute; after receiving the emergency order number request confirmation instruction for the user, the emergency order number request confirmation instruction is sent to the scheduling background server 101, so that the scheduling background server 101 generates the corresponding emergency order plan. Among them, the emergency order number request confirmation instruction is the feedback information generated by the user clicking the "Confirm Order" button after browsing the device status prompt information. The emergency order plan is a detailed production plan that the scheduling background server 101 finally generates and starts to execute based on this confirmation information after receiving the emergency order number request confirmation instruction. It includes the specific production resources, time schedule, process allocation, etc. required for the emergency order. For example: Production equipment A will access order 1001 at 12:00 on June 26, and the original task will be postponed for 2 hours.

[0037] The real-time device health score is determined through the following steps: Step 1: Obtain the service life and multiple real-time parameters corresponding to each of the multiple production equipment identifications, analyze each of the multiple real-time parameters corresponding to each production equipment identification and the corresponding preset standard parameter range, determine the real-time parameters in the multiple real-time parameters corresponding to each production equipment identification that exceed the corresponding preset standard parameter range as abnormal parameters, obtain an abnormal parameter group, and determine the number of abnormal parameters in the abnormal parameter group corresponding to each production equipment identification.

[0038] In some embodiments, the real-time equipment health score is a comprehensive indicator used to evaluate the current operating status of production equipment. It is combined with the service life, operating stability and key operating parameters of the equipment as an important basis for equipment selection and order impact assessment. The scheduling background server 101 establishes a communication connection with the terminal of the target manufacturing plant to obtain the service life and multiple real-time parameters corresponding to each equipment identifier in multiple production equipment identifiers. Service life refers to the cumulative time since the equipment was put into use. Multiple real-time parameters refer to the key operating status data or physical parameters collected and recorded in real time during the operation of each production equipment, including but not limited to the temperature, pressure, vibration, current load and other operating status indicators of the equipment. The scheduling background server 101 compares each real-time parameter with its corresponding preset standard parameter interval. If a real-time parameter does not exceed the corresponding preset standard parameter interval, it is marked as a normal parameter. If a real-time parameter exceeds the corresponding preset standard parameter interval, it is marked as an abnormal parameter. All abnormal parameters are combined to form an abnormal parameter group, and the number of abnormal parameters therein is counted, such as Figure 3Figure 2 shows a flowchart for abnormal parameter detection in a big data-based industrial intelligent manufacturing system according to the present invention. For example, a piece of production equipment has a temperature of 85°C, a vibration of 0.2mm, and a current load of 15A. The preset standard ranges are: 20°C-80°C for temperature, 0.1mm-0.15mm for vibration, and 10A-20A for current load. The temperature and vibration parameters of this equipment do not conform to the preset ranges, forming an abnormal parameter group, with two abnormal parameters. The preset standard parameter range refers to the allowable range of values ​​for various real-time operating parameters (such as temperature, pressure, vibration, and current) of the production equipment, based on factory settings, industry standards, or historical operating data. This range is used to determine whether the equipment is in normal operating condition. This range can be customized and dynamically adjusted based on the specific equipment model, manufacturer recommendations, or factory experience data, and serves as an important benchmark for evaluating equipment health. An abnormal parameter group is a collection of all real-time operating parameters of a piece of production equipment that do not conform to the normal range at a specific point in time. It reflects the dimensionality and number of abnormalities currently existing in the equipment.

[0039] Step 2: Obtain the normal operation time and total operation time corresponding to each production equipment identification, calculate the normal operation time and total operation time corresponding to each production equipment identification, and obtain the normal operation ratio corresponding to each production equipment identification.

[0040] In some embodiments, the target manufacturing plant terminal stores the normal operating hours and total operating hours for each production equipment identifier. Based on this, the scheduling backend server 101 establishes a communication connection with the target manufacturing plant terminal to obtain the normal operating hours and total operating hours for each production equipment identifier. Normal operating hours refer to the time the equipment continuously operates without faults or anomalies, while total operating hours refer to the cumulative operating time of the equipment since it was put into operation. Based on this, the normal operating hours for each production equipment identifier are divided by the total operating hours to obtain the normal operating ratio for each production equipment identifier. The normal operating ratio refers to the proportion of time the equipment has been operating in a stable and fault-free state since its commissioning. It is used to measure the stability of the equipment's operation and is one of the key calculation indicators for the equipment health score. For example, if a piece of equipment has accumulated 900 hours of normal operation and a total operating time of 000 hours, the normal operating ratio is 900 divided by 1000, which is 0.9 (i.e., 90%), indicating that the equipment has been operating stably and healthily for 90% of its lifecycle.

[0041] Step three, obtain the equipment health score table, which includes multiple numbers of abnormal parameters, the number of abnormal parameters scores corresponding to each number of abnormal parameters, multiple normal operation ratios, the normal operation ratio scores corresponding to each normal operation ratio, multiple years of use, and the years of use scores corresponding to each year of use; match the number of abnormal parameters, normal operation ratio and years of use corresponding to each production equipment identification in the equipment health score table to obtain the number of abnormal parameters scores, normal operation ratio scores and years of use scores corresponding to each production equipment identification.

[0042] In some embodiments, the target manufacturing plant terminal stores an equipment health score table. Based on this, the scheduling backend server 101 establishes a communication connection with the target manufacturing plant terminal to obtain the equipment health score table. The equipment health score table includes multiple abnormal parameter counts, a corresponding abnormal parameter count score for each abnormal parameter count, multiple normal operating ratios, a corresponding normal operating ratio score for each normal operating ratio, and multiple service life scores, each corresponding service life score. The equipment health score table can be developed by the target manufacturing plant based on historical operation and maintenance data, industry standards, recommended parameter ranges provided by the equipment manufacturer, and long-term monitoring results. Each score in the equipment health score table is generated through statistical modeling or expert experience calibration and configured before deployment at the manufacturing plant. Based on this, the abnormal parameter count, normal operating ratio, and service life identified for each production equipment item are matched against the equipment health score table to obtain the corresponding abnormal parameter count score, normal operating ratio score, and service life score. For example, a piece of equipment may have two abnormal parameters, an 85% normal operating ratio, and a service life of six years. According to the scoring table, the score for the number of abnormal parameters is 60 points, the score for the normal operation ratio is 75 points, and the score for the service life is 40 points. Taking the score for the number of abnormal parameters as an example, the equipment health scoring table can divide the number of abnormal parameters into multiple scoring levels. For example, when the number of abnormal parameters is 0, the corresponding score is 100 points, when it is 1, the corresponding score is 80 points, and when it is 2 or more, the corresponding score is 60 points. The scoring level division is based on the empirical relationship between equipment operation stability and abnormality rate. In actual application, the scheduling background server 101 matches the number of abnormal parameters corresponding to each production equipment identifier, retrieves and obtains the corresponding number of abnormal parameters score in the equipment health scoring table, and obtains the normal operation ratio score and service life score by analogy.

[0043] Step 4: Configure weights for the abnormal parameter quantity score, normal operation ratio score, and service life score corresponding to the production equipment identification. Use the weights to perform a weighted sum of the abnormal parameter quantity score, normal operation ratio score, and service life score corresponding to each production equipment identification to obtain the real-time equipment health score corresponding to each production equipment identification.

[0044] In some embodiments, weights are assigned to the three aforementioned scores. These weights can be dynamically set based on business needs or historical assessment data, and are denoted as Q1 (abnormal parameter score weight), Q2 (normal operation ratio score weight), and Q3 (service life score weight). The three scores are multiplied by their corresponding weights and summed to obtain the real-time equipment health score for the production equipment.

[0045] The order data also includes the part name corresponding to each order number, and The insertion mode for each emergency insertion order number is determined by the following steps: Step 1: Obtain a set of historical production data records, where each historical production data record in the set includes multiple historical production part names, the order quantity and production duration corresponding to each historical production part name; match the part name and order quantity corresponding to each emergency order number in the historical production data record set, determine the target historical production data record group corresponding to each emergency order number, determine the production duration included in the target historical production data record group as the estimated production duration, and obtain the estimated production duration group corresponding to each emergency order number; Step 2: Calculate the average of the estimated production time groups corresponding to the emergency order numbers to obtain the estimated average production time corresponding to each emergency order number.

[0046] In some embodiments, the scheduling backend server 101 establishes a communication connection with a target manufacturing plant terminal to obtain a set of historical production data records. The set of historical production data records contains production information for past orders recorded by the target manufacturing plant terminal. Each production data record in the set includes multiple historical production part names, the order quantity corresponding to each historical production part name, and the production duration. Based on this, the scheduling backend server 101 matches the part name and order quantity corresponding to the current emergency order number within the set of historical production data records, filtering out historical records with similar part types and similar order quantities to form a target historical production data record group. The "production duration" of each historical record contained in this target historical production data record group is extracted to form an estimated production duration group for the current emergency order number. An estimated production duration group is a collection of production durations extracted from historical production records matching the current order conditions. Statistical analysis is then performed on the production duration data of the multiple historical records in the estimated production duration group, and their average value is calculated to obtain the estimated average production duration corresponding to the emergency order number. The estimated average production time is the value obtained by averaging multiple duration values ​​in the estimated production time group. It is used to predict the average time required to complete the production of the current order.

[0047] Step three: Compare the estimated average production time and the corresponding delivery deadline for each emergency order number. If the estimated average production time is greater than or equal to the corresponding delivery deadline, the delivery time priority mode is matched; if the estimated average production time is less than the corresponding delivery deadline, the carbon emission minimization mode is matched.

[0048] In some embodiments, the estimated average production time is compared with the delivery deadline for the urgent order number. Specifically, if the estimated average production time is greater than or equal to the delivery deadline, indicating that the production task is extremely urgent, the scheduling system will prioritize ensuring delivery time and thus adopt the delivery time priority mode. If the estimated average production time is less than the delivery deadline, indicating that there is still room for production tasks, the carbon emission minimization mode will be adopted to achieve energy conservation and environmental protection goals.

[0049] In these embodiments, the intelligence and greenness of production scheduling are improved. Specifically, by analyzing the order delivery period and part type, combining historical production data to infer the expected production time of emergency orders, and automatically matching the delivery time priority or carbon emission minimization mode accordingly, the order insertion decision is made more targeted and reasonable. At the same time, a real-time equipment health scoring mechanism is introduced, and factors such as the number of abnormal parameters, normal operation ratio and service life are included in the comprehensive scoring system to ensure that the equipment involved in the order insertion scheduling is in good operating condition, effectively reducing the risk of delivery delays or increased carbon emissions due to equipment failure. The system also dynamically evaluates the delivery time or carbon emissions based on the big data prediction model, and matches the corresponding visualization display scheme according to the user type and order insertion mode, thereby improving the decision-making auxiliary value of the prediction information. The overall solution significantly improves the intelligence and greenness of production scheduling, realizes the multi-objective coordinated optimization of delivery efficiency, production safety and environmental protection indicators, and has good industrial application value and promotion prospects.

[0050] In some embodiments, to further address the second technical problem described in the background technology section, namely, "How does the existing technology handle the future impact assessment of emergency orders? It usually relies on manual experience estimation or lacks targeted forecasting tools, resulting in inaccurate forecast results, untimely information transmission, and inflexible display. This makes it difficult for decision makers to foresee potential risks, and managers are prone to misoperating orders in production when adjusting plans, ultimately affecting production efficiency and overall operational stability." In some embodiments of the present invention, a big data-based industrial intelligent manufacturing system is provided, and the scheduling backend server is further used to: Step 1: When a prediction request corresponding to a target emergency order number is received, the prediction request corresponding to the target emergency order number is analyzed to determine the requesting user type, target prediction demand type, and target order mode; wherein the target prediction demand type includes one of the following: order delivery time prediction, order carbon emission prediction.

[0051] In some embodiments, the prediction request corresponding to a target emergency order number includes a user account, a target prediction demand type, and a target order mode. The user account is queried in a preconfigured user information table to obtain the requesting user type, which can be a decision maker or a data analyst. The target emergency order number is the unique identifier of the specific emergency order for which the user wishes the system to perform predictive analysis. A prediction request is a command issued by the user (via the big data interaction terminal 102) to the scheduling backend server 101, requesting the system to predict the future state of a specific aspect of a target emergency order number. The user information table includes multiple user accounts and the user type corresponding to each user account. The target emergency order number has a corresponding target order mode. For example, when the target emergency order number is emergency order number 1001, the corresponding target order mode is delivery time priority. The target prediction demand type explicitly specifies the specific content or indicator that the user wishes to predict in the prediction request, including order delivery time prediction or order carbon emissions prediction. Order delivery time prediction is a type of target prediction demand type. This system predicts the time required to complete and deliver a specific order based on historical production data, equipment status, current production schedules, characteristics of rush orders (such as quantity and process complexity), and other real-time data. Order carbon emissions forecasting is a type of target forecasting demand. It predicts the total carbon emissions generated throughout the production of a specific order based on the order's production process path, the type of production equipment to be used, estimated run time, material consumption, and historical carbon emission efficiency data. Multiple user accounts are unique credentials used to identify and authenticate different system users. Each user has a separate account used to log in to the system and perform operations. These accounts are typically associated with basic user information and permissions. User type is a classification label assigned by the system based on each user account's responsibilities, permissions, and focus. Different user types have different operational permissions and information views within the system, ensuring the effectiveness and security of information transmission. User type is particularly important in forecasting functions because it determines how forecast results are presented.

[0052] Step 2: Obtain a pre-built prediction model library. Each prediction model in the prediction model library has a corresponding prediction demand type and prediction accuracy. Based on the target prediction demand type, determine whether there is a prediction model in the prediction model library that matches the target prediction demand type. If not, obtain a new prediction model group and the prediction accuracy corresponding to each new prediction model in the new prediction model group from the cloud based on the target prediction demand type. Step 3: Sort the newly added prediction model groups in descending order of prediction accuracy to obtain a newly added prediction model sequence, and use the newly added prediction model ranked first in the newly added prediction model sequence as the target prediction model.

[0053] In some embodiments, the scheduling background server 101 locally stores a pre-built prediction model library, and on this basis, the target prediction demand type is matched in the prediction model library to determine whether there is a prediction model that matches the target prediction demand type in the prediction model library. If there is a prediction model that matches the target prediction demand type in the prediction model library, the alternative prediction model group is directly filtered out. If not, the newly added prediction model group corresponding to the target prediction demand type and the prediction accuracy corresponding to each newly added prediction model in the newly added prediction model group are obtained from the cloud. Among them, the prediction demand type refers to the classification of specific content or indicators covered by the various prediction services that the system can provide. It defines what types of predictions can be made in the entire system. The prediction accuracy measures the reliability of the prediction model. On this basis, the newly added prediction model groups are sorted in order from high to low in prediction accuracy, and the prediction model with the highest prediction accuracy is selected as the target prediction model, such as Figure 4 The figure shows a flowchart of an industrial intelligent manufacturing system based on big data for obtaining a target prediction model according to the present invention.

[0054] Step 4: Obtain the target data group corresponding to the target emergency order number, input the target data group into the target prediction model, and obtain the prediction result.

[0055] In some embodiments, after selecting a prediction model, the scheduling backend server 101 establishes a communication connection with the target manufacturing plant terminal to obtain the input data required for the prediction and input it into the model to obtain a prediction result. The target data set refers to all data directly related to the prediction task (such as delivery time or carbon emissions) collected and integrated by the system to perform a specific type of prediction for a specific emergency order. Think of it as a customized input data package for a specific prediction model. This data contains various historical and real-time information about the predicted object (i.e., the target emergency order) and its associated production equipment. For example, if the target prediction demand type corresponding to the target emergency order number is order delivery time prediction, the target data set for order delivery time prediction may include multiple historical operating hours, temperatures, pressures, operating status, equipment load, equipment health score, failure rate, and downtime for the production equipment identifier A corresponding to the target emergency order number. Based on this, the target data set is input into the target prediction model to obtain a prediction result. The target prediction model may be a convolutional neural network, pre-trained with a large number of historical production equipment datasets, to obtain the prediction result (order delivery time). The training process involves inputting a historical dataset of production equipment into a convolutional neural network to obtain the neural network's output. This output is then compared with the true value (previously manually annotated) to calculate the loss function. Based on the gradient of the loss function, the loss function is then backpropagated from the output layer to the input layer. The gradient of each layer's parameters is calculated using the chain rule. During the parameter update process, optimization algorithms such as gradient descent are used to update the parameters of each layer to minimize the loss function. This process requires multiple iterations until the neural network's performance meets the preset requirements or the maximum number of iterations is reached, completing the training.

[0056] Step 5: Obtain multiple display modes, determine display data items according to the requesting user type and the target order insertion mode, select the target display mode from the multiple display modes according to the display data items, and display the prediction results through the target display mode.

[0057] In some embodiments, after the prediction is completed, the scheduling background server 101 further matches the target display mode in the display mode library. Among them, the scheduling background server 101 locally stores multiple display modes. The display mode is an information expression method for presenting the prediction results. It aims to intuitively display data characteristics and analysis results through different visualization methods to facilitate user understanding and decision-making. Specifically, if the requesting user type is a decision maker and the target order insertion mode is the delivery time priority mode, the displayed data items include the predicted delivery time corresponding to the target emergency order and the deviation from the planned delivery time, and the matched target display mode is the simple mode; if the requesting user type is a data analyst, the displayed data items include the predicted delivery time corresponding to the target emergency order, the deviation from the planned delivery time, the priority of the current order in the overall production schedule, the target production equipment load and the potential risks, and the matched target display mode is the multi-dimensional mode. If the requesting user type is a decision maker and the target order insertion mode is the carbon emission minimization mode, the displayed data items include the carbon emission forecast of the target emergency order and the impact of the current order insertion plan on the total carbon emissions (increased or decreased carbon emissions), such as Figure 5 The figure below is a flowchart of the target display mode selection process for a big data-based industrial intelligent manufacturing system. The simple mode is concise and clear for decision makers, facilitating rapid identification of trends and patterns, leading to rapid strategic decision-making. The multi-dimensional mode, on the other hand, provides data analysts with more detailed information, supporting complex data analysis and in-depth problem exploration.

[0058] Among them, the industrial intelligent manufacturing system based on big data and the scheduling backend server are also used for: When the user receives adjustment information corresponding to the displayed emergency order number sequence, the emergency order number included in the adjustment information is determined as the emergency order number to be adjusted; the order status corresponding to the emergency order number to be adjusted is verified to determine whether the order status corresponding to the emergency order number to be adjusted is a waiting state. If it is a waiting state, the updated emergency order number sequence is obtained; if it is a production state, an adjustment failure prompt message is generated and sent to the big data interaction terminal.

[0059] In some embodiments, the scheduling backend server 101 is also used to respond to the user's request for order adjustment. When the user adjusts the currently displayed emergency order number sequence through the big data interaction terminal 101, the scheduling backend server 101 receives the adjustment information and extracts the emergency order number to be adjusted. Subsequently, the scheduling backend server verifies the order status corresponding to the emergency order number to be adjusted to determine whether it is in a "waiting" state. Among them, the order status can be queried from the order data. If the order status is a waiting state, it means that the order has not yet entered the production process. The scheduling backend server 101 updates the emergency order number sequence according to the adjustment information, forms a new production order and uses it for subsequent scheduling. If the order status is a production state, it means that the order has been put into production and can no longer be adjusted. At this time, the scheduling backend server 101 generates a prompt message that cannot be adjusted, and feeds the prompt message back to the big data interaction terminal to prompt the user that the current operation is invalid.

[0060] These embodiments improve the adaptability of prediction models and display methods, thereby increasing production efficiency. Specifically, by introducing a "prediction model library + prediction accuracy + user profiling + display mode matching" mechanism, the intelligence and customization of the emergency order insertion prediction module are significantly enhanced. Upon receiving a user prediction request, the system automatically analyzes the user type (e.g., decision maker or analyst), the target forecast requirement type (e.g., delivery time or carbon emissions), and the current order insertion mode. It prioritizes matching models in the local model library. If no matching model exists, it dynamically calls a cloud-based model to form a candidate model group. The optimal model is then automatically selected after ranking by prediction accuracy, improving prediction reliability and adaptability. After the prediction is complete, the system intelligently selects a matching display mode based on user type and order insertion mode. For example, a simple mode allows decision makers to quickly access key indicators, while a multi-dimensional mode provides analysts with rich information for in-depth analysis, thereby improving information readability and decision-making efficiency. Furthermore, through an order status verification mechanism, the system prevents users from accidentally modifying orders that have already entered production. The system provides timely feedback indicating "unable to adjust," avoiding scheduling confusion and enhancing system stability and user experience. The overall solution effectively solves core problems in existing technologies, such as poor forecast adaptability, rigid display, and uncontrollable production scheduling.

[0061] In some embodiments, to further address the third technical issue described in the background technology section, namely, "Carbon emission control in existing manufacturing systems primarily relies on static standards and manual experience for judgment, lacking systematic analysis and hierarchical management based on equipment operating performance, process emission levels, and energy usage structure, which can easily lead to high-emission equipment not being identified in a timely manner or being improperly handled, affecting the overall carbon emission control efficiency and scientific decision-making of the factory," in some embodiments of the present invention, the scheduling backend server is also used to: Step 1: For each of the multiple process names, identify the production equipment identifiers in the corresponding production equipment identifier group whose carbon emission data is greater than a preset carbon emission data as carbon emission risk production equipment identifiers, thereby obtaining a carbon emission risk production equipment identifier group. The preset carbon emission data is a baseline threshold set by the system based on national or industry carbon emission standards, historical equipment performance, or customer requirements.

[0062] Step 2: Determine the equipment performance score corresponding to each carbon emission risk production equipment identifier in the carbon emission risk production equipment identifier group based on the service life and production rate corresponding to each carbon emission risk production equipment identifier; wherein, the equipment performance score corresponding to each carbon emission risk production equipment identifier is determined by the following steps: obtaining a pre-configured equipment performance matching table, the equipment performance matching table including multiple service lives, service life scores corresponding to each service life, multiple production rates, and production rate scores corresponding to each production rate; matching the service life and production rate corresponding to each carbon emission risk production equipment identifier in the pre-configured equipment performance matching table, determining the service life score and production rate score corresponding to each carbon emission risk production equipment identifier, configuring weights for the service life score and production rate score corresponding to the carbon emission risk production equipment identifier, and performing weighted summation of the service life score and production rate score corresponding to each carbon emission risk production equipment identifier using the weights to obtain the equipment performance score corresponding to each carbon emission risk production equipment identifier. The pre-configured equipment performance matching table is stored in the local scheduling background server 101. For example, the weight of age is A1, and the weight of production rate is A2. A weighted summation is then performed: A1 multiplied by the age score, plus A2 multiplied by the production rate score, to obtain the equipment performance score. The equipment performance score is a numerical indicator used to quantitatively assess the comprehensive operational performance of a piece of production equipment in carbon emissions management. A higher score indicates better performance in terms of efficiency, energy conservation, and low carbon emissions, making it a priority for upgrades. A lower score indicates poorer performance, and replacement is recommended.

[0063] In step three, carbon emission risk production equipment identifiers within the carbon emission risk production equipment identifier group whose equipment performance scores exceed the preset equipment performance score threshold are designated as carbon emission production equipment identifiers for upgrade; carbon emission risk production equipment identifiers whose equipment performance scores are less than or equal to the preset equipment performance score threshold are designated as production equipment identifiers for replacement. The preset equipment performance score threshold is typically determined based on the equipment operation and maintenance strategy and upgrade budget and is used to identify equipment targets for priority optimization and mandatory replacement. Production equipment identifiers for upgrade refer to production equipment identifiers whose carbon emissions exceed the standard during the assessment but whose equipment performance scores exceed the preset threshold. Such equipment exhibits a certain level of performance and can be continued at a lower cost through parameter optimization or component replacement. The system recommends prioritizing its inclusion in the upgrade plan. Production equipment identifiers for replacement refer to production equipment identifiers whose carbon emission data exceeds the standard and whose equipment performance scores are less than or equal to the preset threshold. Such equipment exhibits low energy efficiency and outdated performance, lacking promising upgrade prospects, and the system recommends replacement.

[0064] Step 4: Obtain the average carbon emission data corresponding to each process name among the multiple process names, and determine the process name whose average carbon emission data among the multiple process names is greater than the corresponding preset average carbon emission data as the process name with excessive carbon emissions.

[0065] In some embodiments, the target manufacturing plant terminal stores the average carbon emission data corresponding to each process name, and on this basis, the average carbon emission data corresponding to each process name is obtained from the target manufacturing plant terminal. The average carbon emission data corresponding to each process name is obtained by averaging the carbon emission data of each production equipment identifier in the production equipment identifier group corresponding to each process name. Among them, the average carbon emission data refers to the average value of the carbon emission data per unit time of all production equipment participating in a specific process. It is used to determine whether a process is a process with excessive carbon emissions and is also a key basis for carbon emission assessment. The name of a process with excessive carbon emissions refers to the name of a process whose corresponding average carbon emission data is greater than the pre-set carbon emission standard value for the process. It is an important indicator for determining whether the process is a carbon emission bottleneck and is one of the triggering conditions for optimization operations (parameter adjustment, energy replacement, etc.).

[0066] Step 5: Obtain the processing time and current energy type corresponding to each production equipment identifier in the production equipment identifier group corresponding to the name of the process with excessive carbon emissions; determine whether the processing time of the production equipment identifier in the production equipment identifier group corresponding to the name of the process with excessive carbon emissions is within the standard processing time range; if not, generate parameter adjustment information corresponding to the corresponding production equipment identifier, wherein the parameter adjustment information includes the name of the process with excessive carbon emissions, the production equipment identifier, and the adjustment parameter group; In some embodiments, the target manufacturing plant terminal stores the processing time and current energy type corresponding to each production equipment identifier in the production equipment identification group corresponding to the name of the process with excessive carbon emissions. On this basis, the processing time and current energy type corresponding to each production equipment identifier in the production equipment identification group corresponding to the name of the process with excessive carbon emissions are obtained from the target manufacturing plant terminal. Processing time refers to the time required for production equipment to perform a specific process. The standard processing time interval is set based on process specifications and energy efficiency experience. The adjustment parameter group may include temperature, pressure, power, etc., which is obtained by querying the production equipment parameter table. Specifically, the scheduling background server locally stores the production equipment parameter table, which includes multiple production equipment identifiers and an adjustment parameter group corresponding to each production equipment identifier. Parameter adjustment information refers to the adjustment instructions generated by the scheduling background server 101 for production equipment with excessive carbon emissions based on its operating conditions and performance parameters, combined with the optimization direction recommended by the standard parameter table.

[0067] Step 6: Determine whether the current energy type of the production equipment identification in the production equipment identification group corresponding to the name of the process with excessive carbon emissions is in the standard green energy type group. If not, generate current energy type adjustment information corresponding to the corresponding production equipment identification, wherein the current energy type adjustment information includes the name of the process with excessive carbon emissions and the production equipment identification; In some embodiments, the standard green energy type group refers to a set of low-carbon or zero-carbon energy sources pre-set by the system that meets green manufacturing requirements, and may include wind power, solar power, hydropower, etc. Current energy type adjustment information refers to control information generated by the scheduling backend server 101 to prompt a change in energy type when it identifies that the energy type used by a certain production equipment does not belong to the standard green energy type group.

[0068] Step seven: Send the carbon emission production equipment identification to be upgraded, the production equipment identification to be replaced, the parameter adjustment information corresponding to the production equipment identification, and the current energy type adjustment information to the big data interaction terminal so that the scheduling decision makers can view and make scheduling adjustments.

[0069] These embodiments improve the accuracy and real-time performance of carbon emission management and enhance the efficiency of scientific decision-making for equipment replacement and energy efficiency optimization. Specifically, by establishing a carbon emission identification and grading mechanism based on big data analysis, comprehensive assessment and intelligent classification of various types of production equipment in the manufacturing system during carbon emission control are achieved. Specifically, this application first screens out carbon emission risk equipment based on equipment carbon emission data. Based on a preset performance matching table, the equipment performance scores are generated based on the equipment's age and production rate. The equipment is then classified as "to be upgraded" or "to be replaced," ensuring more targeted resource investment. Simultaneously, the system further evaluates the average carbon emission level of each process. After identifying processes that exceed the standard, parameter adjustment information and energy replacement recommendations are generated based on standard processing time and energy type, providing a basis for optimizing high-carbon emission processes. Furthermore, all analysis results and adjustment recommendations are intuitively displayed through a big data interactive terminal, assisting managers in timely adjusting equipment operation and maintenance and production strategies. As a result, this application not only improves the accuracy and real-time performance of carbon emission management, but also improves the efficiency of scientific decision-making for equipment replacement and energy efficiency optimization, helping manufacturing companies achieve smarter and greener production management.

[0070] The above descriptions are merely some preferred embodiments of the present invention and illustrate the underlying technical principles. Those skilled in the art should understand that the scope of the present invention is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. An industrial intelligent manufacturing system based on big data, characterized in that: include: The scheduling backend server is used to obtain the production equipment data and order data of the target manufacturing plant. The production equipment data includes multiple production equipment identifiers, each of which has a corresponding process name; the order data includes multiple order numbers, the order status corresponding to each order number, the order quantity, and the delivery date; the delivery date is analyzed to obtain the delivery deadline corresponding to each order number and generate an emergency order number group; According to the order quantity and delivery deadline corresponding to each emergency order number in the emergency order number group, the emergency order number sequence and the order insertion mode corresponding to each emergency order number are determined, and the order insertion mode is the delivery time priority mode or the carbon emission minimization mode; for the target process name, the corresponding production equipment identification group is determined; according to the production equipment identification group and the order insertion mode, the first production equipment identification sequence and the second production equipment identification sequence are determined; according to each emergency order number, the first production equipment identification sequence and the second production equipment identification sequence in the emergency order number sequence, the request information corresponding to each emergency order number is generated and sent to the big data interaction terminal; The big data interaction terminal is used to display the impact degree of the insertion order corresponding to each production equipment identification. The impact degree of the insertion order is used by the user to determine whether to accept the request for the emergency insertion order number; when the request confirmation instruction is received, the request confirmation instruction is sent to the scheduling background server to enable the scheduling background server to generate the corresponding emergency insertion order plan.

2. The industrial intelligent manufacturing system based on big data according to claim 1 is characterized in that: The analysis of the delivery date to obtain the delivery deadline corresponding to each order number and generate an emergency order number group includes: The delivery date corresponding to each order number is analyzed to determine the delivery deadline corresponding to each order number; the order number whose delivery deadline is less than the preset delivery deadline or the order quantity is greater than the preset order quantity among the multiple order numbers is determined as an emergency order number to obtain an emergency order number group.

3. The industrial intelligent manufacturing system based on big data according to claim 2 is characterized in that: The production equipment data also includes the production rate, real-time equipment health score and carbon emission data corresponding to each production equipment identifier, and The determining of the first production equipment identification sequence and the second production equipment identification sequence according to the production equipment identification group and the order insertion mode includes: Based on the production rate and real-time equipment health score corresponding to the production equipment identification, the first production equipment identification sequence corresponding to the delivery time priority mode is determined; based on the carbon emission data corresponding to the production equipment identification, the second production equipment identification sequence corresponding to the carbon emission minimization mode is determined.

4. The industrial intelligent manufacturing system based on big data according to claim 3 is characterized in that: The method of generating request information corresponding to each emergency insertion order number in the emergency insertion order number sequence, the first production equipment identification sequence, and the second production equipment identification sequence and sending the request information to the big data interaction terminal includes: Match the corresponding production equipment identification for each emergency order number in the emergency order number sequence. If the order mode corresponding to the emergency order number is the delivery time priority mode, match it in the first production equipment identification sequence; if the order mode corresponding to the emergency order number is the carbon emission minimization mode, match it in the second production equipment identification sequence; generate request information corresponding to each emergency order number based on each emergency order number and the corresponding production equipment identification, and send the request information corresponding to each emergency order number to the big data interaction terminal.

5. The industrial intelligent manufacturing system based on big data according to claim 4 is characterized in that: The real-time device health score is determined by the following steps: Obtaining a service life and multiple real-time parameters corresponding to each of the multiple production equipment identifiers, analyzing each of the multiple real-time parameters corresponding to each production equipment identifier with a corresponding preset standard parameter interval, determining a real-time parameter in the multiple real-time parameters corresponding to each production equipment identifier that exceeds the corresponding preset standard parameter interval as an abnormal parameter, obtaining an abnormal parameter group, and determining the number of abnormal parameters in the abnormal parameter group corresponding to each production equipment identifier; Obtain the normal operation time and total operation time corresponding to each production equipment identification, calculate the normal operation time and total operation time corresponding to each production equipment identification, and obtain the normal operation ratio corresponding to each production equipment identification; Obtain an equipment health score table, the equipment health score table including a plurality of abnormal parameter quantities, an abnormal parameter quantity score corresponding to each abnormal parameter quantity, a plurality of normal operating ratios, a normal operating ratio score corresponding to each normal operating ratio, a plurality of service years, and a service life score corresponding to each service life; match the abnormal parameter quantity, normal operating ratio, and service life corresponding to each production equipment identifier in the equipment health score table to obtain the abnormal parameter quantity score, normal operating ratio score, and service life score corresponding to each production equipment identifier; Weights are configured for the abnormal parameter quantity score, normal operation ratio score, and service life score corresponding to the production equipment identification. The abnormal parameter quantity score, normal operation ratio score, and service life score corresponding to each production equipment identification are weighted and summed up using the weights to obtain the real-time equipment health score corresponding to each production equipment identification.

6. The industrial intelligent manufacturing system based on big data according to claim 5 is characterized in that: The order data also includes the part name corresponding to each order number, and The insertion mode of each emergency insertion order number is determined by the following steps: Obtain a historical production data record set, wherein each historical production data record in the historical production data record set includes multiple historical production part names, order quantities corresponding to each historical production part name, and production duration; match the part name and order quantity corresponding to each emergency insertion order number in the historical production data record set, determine a target historical production data record group corresponding to each emergency insertion order number, determine the production duration included in the target historical production data record group as the estimated production duration, and obtain an estimated production duration group corresponding to each emergency insertion order number; Calculate the average of the estimated production time groups corresponding to the emergency order numbers to obtain the estimated average production time corresponding to each emergency order number; The estimated average production time and corresponding delivery deadline corresponding to each emergency order number are compared. If the estimated average production time is greater than or equal to the corresponding delivery deadline, the delivery time priority mode is matched; if the estimated average production time is less than the corresponding delivery deadline, the carbon emission minimization mode is matched.

7. The industrial intelligent manufacturing system based on big data according to claim 6 is characterized in that: The scheduling backend server is also used to: When a prediction request corresponding to a target emergency order number is received, the prediction request corresponding to the target emergency order number is analyzed to determine the requesting user type, the target prediction demand type, and the target order mode; wherein the target prediction demand type includes one of the following: order delivery time prediction, order carbon emission prediction; Obtain a pre-built prediction model library, where each prediction model in the prediction model library has a corresponding prediction demand type and prediction accuracy; based on the target prediction demand type, determine whether there is a prediction model in the prediction model library that matches the target prediction demand type; if not, obtain a new prediction model group and the prediction accuracy corresponding to each new prediction model in the new prediction model group from the cloud based on the target prediction demand type.

8. The industrial intelligent manufacturing system based on big data according to claim 7 is characterized in that: The scheduling backend server is also used to: Sort the newly added prediction model groups in descending order of prediction accuracy to obtain a newly added prediction model sequence, and use the newly added prediction model ranked first in the newly added prediction model sequence as the target prediction model; Obtaining a target data group corresponding to a target emergency order number, inputting the target data group into the target prediction model, and obtaining a prediction result; Acquire multiple display modes, determine display data items according to the requesting user type and the target insertion mode, select a target display mode from the multiple display modes according to the display data items, and display the prediction results through the target display mode.

9. The industrial intelligent manufacturing system based on big data according to claim 8, characterized in that: The scheduling backend server is also used to: When receiving adjustment information corresponding to the displayed emergency order number sequence from the user, determining the emergency order number included in the adjustment information as the emergency order number to be adjusted; The order status corresponding to the emergency order number to be adjusted is verified to determine whether the order status corresponding to the emergency order number to be adjusted is a waiting state. If it is a waiting state, the updated emergency order number sequence is obtained; if it is a production state, an adjustment-unable prompt message is generated and the adjustment-unable prompt message is sent to the big data interaction terminal.

Images