Edge-cloud cooperation based intelligent manufacturing workshop management and control method and system

Abstract

The application discloses an intelligent manufacturing workshop management and control method and system based on edge cloud cooperation, and particularly relates to the technical field of workshop management and control; the application divides the equipment into different state grades and matches corresponding reserved coefficients by obtaining an equipment state performance index from the real-time stability, aging degree and fault frequency of the equipment after processing an abnormal state, scientifically improves the production speed from the equipment in a good state, makes up for the delay time under the premise of ensuring the safety of the equipment, balances the production efficiency and the equipment life, and simultaneously optimizes the production resource configuration through a data-driven scheduling strategy to ensure that the production task is delivered on time.

Description

Technical Field

[0001] This invention relates to the field of workshop management technology, and more specifically, to a method and system for intelligent manufacturing workshop management based on edge-cloud collaboration. Background Technology

[0002] With the rapid development of intelligent manufacturing, workshop management systems are playing an increasingly important role in improving production efficiency and ensuring product quality.

[0003] However, current intelligent manufacturing workshop management methods still have the following shortcomings in practical applications:

[0004] On the one hand, existing technologies tend to focus on data collection in a single area (such as only focusing on production equipment or quality inspection), lacking the linkage and integration of data from multiple areas such as equipment processing area, material storage area, and quality inspection area;

[0005] Furthermore, production decision-making and scheduling lack refined support. When adjusting production schedules after handling anomalies, existing technicians often fail to fully consider the real-time status of equipment. Blindly increasing production speed can easily lead to equipment overload or failure, while conservative scheduling may cause delivery delays, making it difficult to balance production efficiency and equipment safety.

[0006] To address this, we have developed a smart manufacturing workshop management and control method and system based on edge-cloud collaboration. Summary of the Invention

[0007] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a method and system for intelligent manufacturing workshop management based on edge-cloud collaboration.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] The intelligent manufacturing workshop management and control method based on edge-cloud collaboration includes:

[0010] Node data processing: Processing data, storage data, and quality data are collected using edge nodes deployed in each divided region; the divided regions include equipment processing areas, material storage areas, and quality inspection areas; processing data includes equipment temperature, pressure, and noise; storage data includes environmental temperature and humidity data of the material storage area; quality data includes image data of the produced products.

[0011] Cloud-based collaborative processing: After anomaly analysis of the processing data, storage data, and quality data of each divided area, the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop are determined.

[0012] Abnormal situation handling: Based on the comparison results of the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop, the abnormal status of each divided area of ​​the workshop is determined and the corresponding steps are executed; among which, abnormal status includes equipment abnormal status, environmental abnormal status, and quality abnormal status;

[0013] Production decision scheduling: After handling abnormal states in the workshop, intelligent scheduling of workshop production progress is carried out based on the current production task requirements of the workshop and the status performance index Si of each piece of equipment in the equipment processing area.

[0014] Specifically, the analysis of processing data in the equipment processing area includes:

[0015] After averaging the temperature data of each processing equipment within a set time zone, the overheating performance value of each processing equipment is obtained.

[0016] After calculating the average pressure data of each processing equipment within the set time zone, the difference between the calculated average and the set reference pressure is calculated, and the absolute value is taken to obtain the pressure deviation value of each processing equipment.

[0017] The noise data of each processing equipment in the set time zone is compared with the set benchmark value. When the noise data at a certain time point in the set time zone is greater than the benchmark value, it is determined to be an out-of-standard state. The process is repeated for each time point in the set time zone. The time points that are determined to be out-of-standard are divided into continuous intervals. The difference between the start time point and the end time of each continuous interval is calculated and summed to obtain the noise duration value of each processing equipment.

[0018] The overheating performance value, pressure deviation value, and noise duration value of each processing equipment were respectively marked as follows: After marking, follow the formula Calculate the processing equipment index Pi for each processing device within the processing area; where... These represent the overheating threshold, pressure deviation threshold, and noise duration threshold, respectively. These are the weighting coefficients for overheating performance value, pressure deviation value, and noise duration value, respectively.

[0019] Specifically, the analysis of the environmental temperature and humidity data of the material storage area includes:

[0020] Extract ambient temperature and humidity data from the edge nodes corresponding to the material storage area, and set the optimal storage temperature and humidity for the material.

[0021] The ambient temperature and humidity of the material storage area are calculated by comparing them with the corresponding set optimal storage temperature and optimal storage humidity. The absolute values ​​are then used to obtain the temperature deviation E1 and humidity deviation E2. These are then used with the formula... The material environment index G corresponding to the material storage area is calculated; where These are the weighting coefficients corresponding to temperature deviation E1 and humidity deviation E2, respectively.

[0022] Specifically, the analysis of image data in the quality detection area includes:

[0023] Image data of the manufactured product is extracted from the edge nodes corresponding to the quality inspection area. Defects in the image data are identified and classified into defect types, where the defect type is represented by x, x=1,2,...,h, and h is the total number of defect types.

[0024] For various defects in image data, after counting the number of pixels and converting the actual area based on the image resolution, the defect area of ​​each type of defect in the manufactured product is obtained, denoted by Vx; according to the formula... Calculate the quality assessment index N of the manufactured products; where These are the weighting coefficients corresponding to various types of defects.

[0025] Specifically, determining the abnormal status of each divided area of ​​the workshop includes:

[0026] Preset the equipment threshold index, environmental threshold index, and quality threshold index corresponding to the processing equipment index Pi, material environment index G, and quality assessment index N, respectively.

[0027] If the processing equipment index Pi of a certain device in the processing area is higher than the preset equipment threshold index, it is marked as an abnormal warning device. After the abnormal warning device is shut down, the status of the processing area is determined to be an abnormal equipment status.

[0028] If the material environment index G of the material storage area is higher than the preset environmental threshold index, the adjustment signal is first triggered to the air conditioning and ventilation equipment of the material storage area. After adjusting the air conditioning and ventilation equipment, the material environment index of the material storage area is obtained again after a set time. If it is still higher than the preset environmental threshold index, the state of the material storage area is determined to be an abnormal environmental state.

[0029] If the quality assessment index N of a certain product in the quality inspection area is higher than the preset quality threshold index, it is marked as a non-conforming product. At the same time, the abnormal warning device in the equipment processing area is identified. If the equipment number marked in the production number of the non-conforming product is the same as the number of the abnormal warning device, it is determined that the product is non-conforming due to equipment abnormality; otherwise, the status of the quality inspection area is determined to be a quality abnormality state.

[0030] Specifically, the steps for determining the abnormal states of each divided area of ​​the workshop and executing the corresponding procedures are as follows:

[0031] After determining the abnormal status of each area in the workshop, obtain the work status of each maintenance personnel at the current time; the work status includes online, busy, and offline; identify the maintenance personnel whose work status is online as the selected personnel;

[0032] Historical processing times are extracted from the work logs of personnel at each selection point. For each historical processing time of personnel at each selection point, it is classified according to the area it is located in to obtain the number of times the personnel are familiar with the area Qn, where n=1,2 or3, representing the equipment processing area, material storage area and quality inspection area respectively.

[0033] After analyzing the time consumed by each selected person in each historical processing in different division areas and calculating the average value, the average time Rn of the mature area for each selected person in different division areas is obtained.

[0034] Location feedback signals are sent to the mobile devices of each selected personnel. After receiving and confirming the location feedback signals, each selected personnel determines their location at the current time. Based on the location of each selected personnel, the distance between them and different division areas is calculated to obtain the travel status value Cn of each selected personnel to reach different division areas.

[0035] Identify the specific areas in the workshop that are determined to be in an abnormal state. After identification, extract the number of times the work area is in a familiar state (Qn), the average time in the familiar state (Rn), and the travel status value (Cn) for each selected person in the corresponding area. Then, apply the formula... Calculate the anomaly value Zn for each selected person within the corresponding division area; where These are the weighting coefficients for the number of times the mature area is reached (Qn), the average time of the mature area (Rn), and the travel condition value (Cn), respectively.

[0036] Based on the anomaly value Zn of each selected personnel, the selected personnel with the highest anomaly value Zn are selected as the personnel to handle the abnormal status of the corresponding division area, and a processing signal is sent to the personnel's mobile device.

[0037] Specifically, the intelligent scheduling of workshop production progress based on the status performance index Si of each piece of equipment within the equipment processing area is as follows:

[0038] Extract the required production quantity and delivery date from the current production tasks in the workshop. Calculate the difference between the required production quantity and the quantity already produced to obtain the remaining production quantity. Within a set time window after handling abnormal conditions in the workshop, obtain the production efficiency quantity within the equipment processing area within the set time window.

[0039] Divide the remaining production quantity by the production efficiency quantity within the set time zone to obtain the theoretical completion date of the current production task. Compare the theoretical completion date with the delivery date in the production task. If the theoretical completion date is later than the delivery date in the production task, calculate the time difference between the theoretical completion date and the delivery date as the delay duration, and trigger scheduling signaling to obtain the status performance index Si of each device in the equipment processing area.

[0040] Set three index intervals corresponding to the state performance index Si, and each index interval corresponds to a state performance level, which includes a good level, an average level and a poor level.

[0041] The status performance index Si of each device is matched with three sets of index intervals to determine the status performance level of each device, and different status performance levels correspond to a set of reserved coefficients.

[0042] Obtain the rated production speed and current actual production speed of each piece of equipment within the processing area, and calculate the safe lifting speed based on the corresponding reserve coefficient. ;in These represent the rated production speed, the reserve factor, and the current actual production speed, respectively.

[0043] Start by increasing the speed of safety upgrades from equipment that is classified as good. The scheduling will be stopped when the accumulated additional output of the equipment in the processing area exceeds the required additional output.

[0044] Specifically, the state performance index Si of each piece of equipment within the equipment processing area is obtained as follows:

[0045] Obtain the processing equipment index Pi of each device within the set time zone's processing area, combine it with the device's service life Ji and historical maintenance frequency Di, and substitute it into the formula. The state performance index Si of each device is obtained through comprehensive calculation; where These are the weighting coefficients for the processing equipment index Pi, the years of use Ji, and the number of historical maintenance Di, respectively.

[0046] The intelligent manufacturing workshop management and control system based on edge-cloud collaboration includes:

[0047] The node data transmission module is used to collect processing data, storage data, and quality data of the corresponding divided areas in real time using each edge node, and transmit them to the cloud processing module;

[0048] The cloud processing module is used to perform anomaly analysis on the processing data, storage data, and quality data of each divided area, and then determine the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop.

[0049] The anomaly handling module is used to determine the abnormal status of each area of ​​the workshop and execute the corresponding steps based on the comparison results of the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop.

[0050] After handling abnormal states in the workshop, the scheduling module intelligently schedules the workshop production progress based on the current production task requirements of the workshop and the status performance index Si of each piece of equipment in the equipment processing area.

[0051] The technical effects and advantages of this invention are as follows:

[0052] (1) By deploying edge nodes in the equipment processing area, material storage area and quality inspection area respectively, the comprehensive collection of processing data, storage data and quality data is realized. Based on multi-dimensional data, the processing equipment index, material environment index and quality assessment index are constructed to realize the quantitative assessment of equipment operation status, material storage environment and product quality, and avoid the limitations of single indicator judgment.

[0053] (2) By extracting the number of times the online maintenance personnel are familiar with the area, the average time of the familiar area, and the travel status value, and calculating the outlier value, the personnel with the highest outlier value are selected to handle the corresponding area anomaly. This achieves a precise match between the maintenance personnel's skills, area familiarity and anomaly needs, reduces processing delays or errors caused by personnel mismatch, and improves the efficiency of anomaly handling.

[0054] (3) After handling abnormal conditions, the equipment status performance index is obtained by combining the real-time stability, aging degree and failure frequency of the equipment. The equipment is divided into different status levels and matched with corresponding reserved coefficients. Starting from the equipment in good condition, the production speed is scientifically improved. Under the premise of ensuring equipment safety, the delay time is made up to achieve a balance between production efficiency and equipment life. At the same time, the production resource allocation is optimized through data-driven scheduling strategy to ensure that production tasks are delivered on time. Attached Figure Description

[0055] Figure 1 This is a flowchart of the intelligent manufacturing workshop management and control method based on edge-cloud collaboration of the present invention;

[0056] Figure 2 This is a schematic diagram of the intelligent manufacturing workshop management and control system based on edge-cloud collaboration of the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Example 1

[0059] like Figure 1 As shown, the intelligent manufacturing workshop management and control method based on edge-cloud collaboration includes:

[0060] Node data organization: Based on the equipment layout, production process and control requirements of the smart manufacturing workshop, the workshop is divided into equipment processing area, material storage area and quality inspection area. Each area is set up with an edge node, and the data objects collected by different edge nodes are defined. The processing data, storage data and quality data of the corresponding area are collected in real time by each edge node.

[0061] The processing data includes equipment temperature, pressure, and noise; the storage data includes ambient temperature and humidity data of the material storage area; and the quality data includes image data of the produced products.

[0062] The edge-cloud architecture is pre-deployed within the workshop. The edge-cloud architecture includes an edge node layer and a cloud layer. The edge node layer consists of multiple edge nodes deployed within the smart manufacturing workshop.

[0063] The smart sensors at each edge node collect corresponding data in real time according to the set data objects and collection frequency, and transmit the collected data to the edge gateway of the edge node in real time.

[0064] After receiving data transmitted from smart sensors, the edge gateways at each edge node perform local preprocessing on the data, including data cleaning to remove invalid and duplicate data caused by sensor failures, transmission interference, etc.; data format conversion to convert heterogeneous data collected by different types of sensors into a unified data format for easier subsequent processing and transmission; and data compression to compress the data, reduce the amount of data, and improve transmission efficiency.

[0065] The edge gateway marks the pre-processed data, labeling information such as the edge node number, collection time, and data object type, and stores it according to the data object type, which facilitates subsequent anomaly analysis and data transmission.

[0066] The cloud layer includes cloud servers, which are used for big data analysis, global optimization decisions, and so on.

[0067] Cloud-based collaborative processing: After anomaly analysis of the processing data, storage data, and quality data of each divided area through the cloud server, the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop are determined; where i represents the number of each piece of equipment in the equipment processing area; i=1,2,...,g, and g is the total number of pieces of equipment in the equipment processing area.

[0068] Specifically:

[0069] Extract the temperature, pressure, and noise data of each processing device in a set time zone from the edge nodes corresponding to the processing area of ​​the equipment;

[0070] Equipment temperature: Temperature data is collected by temperature sensors placed in key parts of the equipment (such as bearings, motors, spindles, etc.) to monitor temperature changes during equipment operation and determine whether there is a risk of overheating.

[0071] Pressure: Collect pressure data from hydraulic systems, pneumatic systems, or during processing to ensure that the pressure is within the normal operating range of the equipment and to avoid decreased processing accuracy or equipment damage due to abnormal pressure;

[0072] Noise: The noise level generated during equipment operation is collected by noise sensors. Abnormal noise may be a signal of equipment failure or unstable processing.

[0073] After averaging the temperature data of each processing equipment within a set time zone, the overheating performance value of each processing equipment is obtained.

[0074] After calculating the average pressure data of each processing equipment within the set time zone, the difference between the calculated average and the set reference pressure is calculated, and the absolute value is taken to obtain the pressure deviation value of each processing equipment.

[0075] The noise data of each processing device in the set time zone is compared with the set benchmark value. The benchmark value is the noise performance of the device under normal operation. When the noise data at a certain time point in the set time zone is greater than the benchmark value, it is judged as an excessive state. The process is to traverse every time point in the set time zone, divide the time points judged as excessive into continuous intervals, calculate the difference between the start time point and the end time of each continuous interval, and sum them to obtain the noise duration value of each processing device.

[0076] The overheating performance value, pressure deviation value, and noise duration value of each processing equipment were respectively marked as follows: After marking, follow the formula Calculate the processing equipment index Pi for each processing device within the processing area; where... These represent the overheating threshold, pressure deviation threshold, and noise duration threshold, respectively. These are the weighting coefficients for overheating performance value, pressure deviation value, and noise duration value, respectively.

[0077] Simultaneously monitor multiple key indicators such as temperature, pressure, and noise, and comprehensively quantify these indicators through the processing equipment index Pi to fully reflect the operating status of the equipment;

[0078] Extract ambient temperature and humidity data from the edge nodes corresponding to the material storage area, and set the optimal storage temperature and humidity for the materials based on the type of materials produced in the workshop;

[0079] The ambient temperature and humidity of the material storage area are calculated by comparing them with the corresponding set optimal storage temperature and optimal storage humidity. The absolute values ​​are then used to obtain the temperature deviation E1 and humidity deviation E2. These are then used with the formula... The material environment index G corresponding to the material storage area is calculated; where These are the weighting coefficients corresponding to temperature deviation E1 and humidity deviation E2, respectively.

[0080] Analyze the temperature and humidity of the storage environment based on the material type to avoid the material affecting the production schedule of subsequent products due to the storage environment.

[0081] Image data of the manufactured products is extracted from the edge nodes corresponding to the quality inspection area. By default, the acquired images are processed by denoising, enhancement, binarization and other processes to improve the image clarity and the accuracy of feature extraction. Computer vision algorithms are used to identify defects in the image data and classify the defect types, where the defect types are represented by x, x=1,2,...,h, and h is the total number of defect types.

[0082] For various defects in image data, after counting the number of pixels and converting the actual area based on the image resolution, the defect area of ​​each type of defect in the manufactured product is obtained, denoted by Vx.

[0083] According to the formula Calculate the quality assessment index N of the manufactured products; where These are the weighting coefficients corresponding to various types of defects;

[0084] Image analysis technology has enabled the automation, quantification, and intelligentization of quality inspection, providing high-precision and high-efficiency quality control methods for intelligent manufacturing, and significantly improving production efficiency and product competitiveness.

[0085] Abnormal situation handling: Based on the comparison results of the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop, the abnormal status of each divided area of ​​the workshop is determined and the corresponding steps are executed; among which, abnormal status includes equipment abnormal status, environmental abnormal status, and quality abnormal status;

[0086] Specifically:

[0087] Preset the equipment threshold index, environmental threshold index, and quality threshold index corresponding to the processing equipment index Pi, material environment index G, and quality assessment index N, respectively.

[0088] If the processing equipment index Pi of a certain device in the processing area is higher than the preset equipment threshold index, it is marked as an abnormal warning device. After the abnormal warning device is shut down, the status of the processing area is determined to be an abnormal equipment status.

[0089] If the material environment index G of the material storage area is higher than the preset environmental threshold index, an adjustment signal will first be triggered to the air conditioning and ventilation equipment of the material storage area, including but not limited to air conditioning equipment, ventilation equipment, dehumidifiers, etc. After adjusting the air conditioning and ventilation equipment, wait for a set time and then obtain the material environment index of the material storage area. If it is still higher than the preset environmental threshold index, the set time is, for example, 30 minutes. Then the state of the material storage area will be judged as an abnormal environmental state.

[0090] If the quality assessment index N of a certain product in the quality inspection area is higher than the preset quality threshold index, it is marked as a non-conforming product. At the same time, the abnormal warning device in the equipment processing area is identified. If the equipment number marked in the production number of the non-conforming product is the same as the number of the abnormal warning device, it is determined that the product is non-conforming due to equipment abnormality; otherwise, the status of the quality inspection area is determined to be a quality abnormality state.

[0091] If there are multiple abnormality warning devices, the device number marked in the production number of the non-conforming product will be matched with the number of each abnormality warning device.

[0092] After determining the abnormal status of each area in the workshop, obtain the work status of each maintenance personnel at the current time; the work status includes online, busy, and offline; identify the maintenance personnel whose work status is online as the selected personnel;

[0093] Historical processing times are extracted from the work logs of personnel at each selection point. For each historical processing time of personnel at each selection point, it is classified according to the area it is located in to obtain the number of times the personnel are familiar with the area Qn, where n=1,2 or3, representing the equipment processing area, material storage area and quality inspection area respectively.

[0094] For example, when n=1, Q1 represents the number of times each selected person processes the equipment within the processing area;

[0095] The types of anomalies vary greatly in different areas (e.g., the equipment processing area focuses on mechanical failures, while the quality inspection area focuses on testing equipment calibration). By classifying areas by familiarity, we can achieve a precise match between personnel skills and area needs, reducing processing errors caused by unfamiliarity with area characteristics.

[0096] After analyzing the time consumed by each selected person in each historical processing in different division areas and calculating the average value, the average time Rn of the mature area for each selected person in different division areas is obtained.

[0097] Location feedback signals are sent to the mobile devices of each selected personnel. After receiving and confirming the location feedback signals, each selected personnel determines their location at the current time. Based on the location of each selected personnel, the distance between them and different division areas is calculated to obtain the travel status value Cn of each selected personnel to reach different division areas.

[0098] Identify the specific areas in the workshop that are determined to be in an abnormal state. After identification, extract the number of times the work area is in a familiar state (Qn), the average time in the familiar state (Rn), and the travel status value (Cn) for each selected person in the corresponding area. Then, apply the formula... Calculate the anomaly value Zn for each selected person within the corresponding division area; where These are the weighting coefficients for the number of times the mature area is reached (Qn), the average time of the mature area (Rn), and the travel condition value (Cn), respectively.

[0099] Based on the anomaly value Zn of each selected personnel, the selected personnel with the highest anomaly value Zn are selected as the personnel to handle the anomaly status of the corresponding division area, and the processing signal is sent to the mobile device of the personnel.

[0100] By identifying and determining the corresponding division areas of abnormal states and calculating the handling value of each selected personnel, the system achieves a precise match between maintenance resources and abnormal needs. This not only ensures the speed and quality of abnormal handling but also optimizes personnel management efficiency, providing key support for the stable operation of the intelligent manufacturing workshop.

[0101] Production decision scheduling: After handling abnormal states in the workshop, intelligent scheduling of the workshop production progress is carried out based on the current production task requirements of the workshop and the status performance index Si of each piece of equipment in the equipment processing area; the production task requirements include the required production quantity and delivery date, etc.

[0102] Specifically:

[0103] Extract the required production quantity and delivery date from the current production tasks in the workshop. Calculate the difference between the required production quantity and the quantity already produced to obtain the remaining production quantity. Within a set time window after handling abnormal conditions in the workshop, obtain the production efficiency quantity within the equipment processing area within the set time window.

[0104] Divide the remaining production quantity by the production efficiency quantity within the set time zone to obtain the theoretical completion date of the current production task. Compare the theoretical completion date with the delivery date in the production task. If the theoretical completion date is later than the delivery date in the production task, calculate the time difference between the theoretical completion date and the delivery date as the delay duration and trigger scheduling signaling.

[0105] For the processing equipment index Pi of each piece of equipment within the set time zone's processing area, combined with the equipment's service life Ji and historical maintenance frequency Di, we substitute it into the formula. The state performance index Si of each device is obtained through comprehensive calculation; where These are the weighting coefficients for the processing equipment index Pi, the years of use Ji, and the number of historical maintenance Di, respectively.

[0106] Si integrates the processing equipment index Pi (real-time operational stability), years of use Ji (equipment aging level), and historical maintenance frequency Di (failure frequency). The higher the value, the better the current condition of the equipment (stable operation, less aging, fewer failures), and the greater the potential for increasing production speed.

[0107] Three index intervals are set for the state performance index Si, and each index interval corresponds to a state performance level, which includes a good level, an average level, and a poor level; the higher the state performance index Si, the higher the probability of matching a good level.

[0108] The status performance index Si of each device is matched with three sets of index intervals to determine the status performance level of each device, and different status performance levels correspond to a set of reserved coefficients.

[0109] The reserve coefficient for a "good" rating is 0.8; for a "moderate" rating, it is 0.6; and for a "poor" rating, it is 0.4. The specific reserve coefficient values ​​can be dynamically adjusted based on actual circumstances.

[0110] Obtain the rated production speed and current actual production speed of each piece of equipment within the processing area, and calculate the safe lifting speed based on the corresponding reserve coefficient. ;in These represent the rated production speed, the reserve factor, and the current actual production speed, respectively. The reserve factor allows for a safety margin of a set percentage to avoid failures caused by reaching the limit value.

[0111] Start by increasing the speed of safety upgrades from equipment that is classified as good. The scheduling will be stopped when the cumulative additional output of the equipment in the processing area exceeds the required additional output, and an audit signal will be sent to the technician's mobile device for auditing.

[0112] Additional production required ;in Indicates the delay duration; A1 represents the production efficiency within the set time window; A2 represents the remaining time to complete the task.

[0113] Example 2

[0114] Please see Figure 2 As shown, based on the edge-cloud collaborative intelligent manufacturing workshop management and control method provided in Embodiment 1 of this application, Embodiment 2 of this application proposes an edge-cloud collaborative intelligent manufacturing workshop management and control system. Embodiment 2 is merely a preferred embodiment of Embodiment 1, and the implementation of Embodiment 2 will not affect the separate implementation of Embodiment 1.

[0115] Specifically, the difference in the edge-cloud collaborative intelligent manufacturing workshop management system provided in Embodiment 2 of this application is that it includes a node data transmission module, a cloud processing module, an anomaly handling module, and a scheduling module.

[0116] The node data transmission module is used to collect processing data, storage data, and quality data of the corresponding divided areas in real time using each edge node, and transmit them to the cloud processing module;

[0117] The cloud processing module is used to perform anomaly analysis on the processing data, storage data, and quality data of each divided area, and then determine the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop.

[0118] The anomaly handling module is used to determine the abnormal status of each area of ​​the workshop and execute the corresponding steps based on the comparison results of the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop.

[0119] After handling abnormal conditions in the workshop, the scheduling module intelligently schedules the workshop production progress based on the current production task requirements of the workshop and the status performance index Si of each piece of equipment in the equipment processing area.

[0120] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0121] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0122] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0123] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0126] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0127] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0128] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A smart manufacturing workshop management and control method based on edge-cloud collaboration, characterized in that, include: Node data processing: Collect, store, and process data and quality data using the edge nodes deployed in each divided region; The areas are divided into equipment processing areas, material storage areas, and quality inspection areas; The processing data includes equipment temperature, pressure, and noise; the storage data includes ambient temperature and humidity data of the material storage area; and the quality data includes image data of the produced products. Cloud-based collaborative processing: After anomaly analysis of the processing data, storage data, and quality data of each divided area, the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop are determined. Abnormal situation handling: Based on the comparison results of the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop, the abnormal status of each divided area of ​​the workshop is determined and the corresponding steps are executed; among which, abnormal status includes equipment abnormal status, environmental abnormal status, and quality abnormal status; Production decision scheduling: After handling abnormal states in the workshop, intelligent scheduling of workshop production progress is carried out based on the current production task requirements of the workshop and the status performance index Si of each piece of equipment in the equipment processing area.

2. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 1, characterized in that, Anomaly analysis is performed on the processing data of each of the aforementioned regions, specifically as follows: After averaging the temperature data of each processing equipment within a set time zone, the overheating performance value of each processing equipment is obtained. After calculating the average pressure data of each processing equipment within the set time zone, the difference between the calculated average and the set reference pressure is calculated, and the absolute value is taken to obtain the pressure deviation value of each processing equipment. The noise data of each processing equipment in the set time zone is compared with the set benchmark value. When the noise data at a certain time point in the set time zone is greater than the benchmark value, it is determined to be an out-of-standard state. The process is repeated for each time point in the set time zone. The time points that are determined to be out-of-standard are divided into continuous intervals. The difference between the start time point and the end time of each continuous interval is calculated and summed to obtain the noise duration value of each processing equipment. The overheating performance value, pressure deviation value, and noise duration value of each processing equipment were respectively marked as follows: After marking, follow the formula Calculate the processing equipment index Pi for each processing device within the processing area; where These represent the overheating threshold, pressure deviation threshold, and noise duration threshold, respectively. These are the weighting coefficients for overheating performance value, pressure deviation value, and noise duration value, respectively.

3. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 1, characterized in that, Anomaly analysis is performed on the stored data in each of the aforementioned partitioned regions, specifically as follows: Extract ambient temperature and humidity data from the edge nodes corresponding to the material storage area, and set the optimal storage temperature and humidity for the material. The ambient temperature and humidity of the material storage area are calculated by comparing them with the corresponding set optimal storage temperature and optimal storage humidity. The absolute values ​​are then used to obtain the temperature deviation E1 and humidity deviation E2. These are then used with the formula... The material environment index G corresponding to the material storage area is calculated; where These are the weighting coefficients corresponding to temperature deviation E1 and humidity deviation E2, respectively.

4. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 1, characterized in that, Anomaly analysis was performed on the quality data of each of the defined regions, specifically as follows: Image data of the manufactured product is extracted from the edge nodes corresponding to the quality inspection area. Defects in the image data are identified and classified into defect types, where the defect type is represented by x, x=1,2,...,h, and h is the total number of defect types. For various defects in image data, after counting the number of pixels and converting the actual area based on the image resolution, the defect area of ​​each type of defect in the manufactured product is obtained, denoted by Vx; according to the formula... Calculate the quality assessment index N of the manufactured products; where These are the weighting coefficients corresponding to various types of defects.

5. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 1, characterized in that, The determination of abnormal states in each divided area of ​​the workshop specifically includes: Preset the equipment threshold index, environmental threshold index, and quality threshold index corresponding to the processing equipment index Pi, material environment index G, and quality assessment index N, respectively. If the processing equipment index Pi of a certain device in the processing area is higher than the preset equipment threshold index, it is marked as an abnormal warning device. After the abnormal warning device is shut down, the status of the processing area is determined to be an abnormal equipment status. If the material environment index G of the material storage area is higher than the preset environmental threshold index, the adjustment signal is first triggered to the air conditioning and ventilation equipment of the material storage area. After adjusting the air conditioning and ventilation equipment, the material environment index of the material storage area is obtained again after a set time. If it is still higher than the preset environmental threshold index, the state of the material storage area is determined to be an abnormal environmental state. If the quality assessment index N of a certain product in the quality inspection area is higher than the preset quality threshold index, it is marked as a non-conforming product. At the same time, the abnormal warning device in the equipment processing area is identified. If the equipment number marked in the production number of the non-conforming product is the same as the number of the abnormal warning device, it is determined that the product is non-conforming due to equipment abnormality; otherwise, the status of the quality inspection area is determined to be a quality abnormality state.

6. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 5, characterized in that, The steps for determining the abnormal states of each divided area of ​​the workshop and executing the corresponding procedures are as follows: After determining the abnormal status of each area in the workshop, obtain the work status of each maintenance personnel at the current time; the work status includes online, busy, and offline; identify the maintenance personnel whose work status is online as the selected personnel; Historical processing times are extracted from the work logs of personnel at each selection point. For each historical processing time of personnel at each selection point, it is classified according to the area it is located in to obtain the number of times the personnel are familiar with the area Qn, where n=1,2 or3, representing the equipment processing area, material storage area and quality inspection area respectively. After analyzing the time consumed by each selected person in each historical processing in different division areas and calculating the average value, the average time Rn of the mature area for each selected person in different division areas is obtained. Location feedback signals are sent to the mobile devices of each selected personnel. After receiving and confirming the location feedback signals, each selected personnel determines their location at the current time. Based on the location of each selected personnel, the distance between them and different division areas is calculated to obtain the travel status value Cn of each selected personnel to reach different division areas. Identify the specific areas in the workshop that are determined to be in an abnormal state. After identification, extract the number of times the work area is in a familiar state (Qn), the average time in the familiar state (Rn), and the travel status value (Cn) for each selected person in the corresponding area. Then, apply the formula... Calculate the anomaly value Zn for each selected person within the corresponding division area; where These are the weighting coefficients for the number of times the mature area is reached (Qn), the average time of the mature area (Rn), and the travel condition value (Cn), respectively. Based on the anomaly value Zn of each selected personnel, the selected personnel with the highest anomaly value Zn are selected as the personnel to handle the abnormal status of the corresponding division area, and a processing signal is sent to the personnel's mobile device.

7. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 1, characterized in that, The intelligent scheduling of workshop production progress is achieved by combining the status performance index Si of each piece of equipment within the processing area. Extract the required production quantity and delivery date from the current production tasks in the workshop. Calculate the difference between the required production quantity and the quantity already produced to obtain the remaining production quantity. Within a set time window after handling abnormal conditions in the workshop, obtain the production efficiency quantity within the equipment processing area within the set time window. Divide the remaining production quantity by the production efficiency quantity within the set time zone to obtain the theoretical completion date of the current production task. Compare the theoretical completion date with the delivery date in the production task. If the theoretical completion date is later than the delivery date in the production task, calculate the time difference between the theoretical completion date and the delivery date as the delay duration, and trigger scheduling signaling to obtain the status performance index Si of each device in the equipment processing area. Set three index intervals corresponding to the state performance index Si, and each index interval corresponds to a state performance level, which includes a good level, an average level, and a poor level. The status performance index Si of each device is matched with three sets of index intervals to determine the status performance level of each device, and different status performance levels correspond to a set of reserved coefficients. Obtain the rated production speed and current actual production speed of each piece of equipment within the processing area, and calculate the safe lifting speed based on the corresponding reserve coefficient. ;in These represent the rated production speed, the reserve factor, and the current actual production speed, respectively. Start by increasing the speed of safety upgrades from equipment that is classified as good. The scheduling will be stopped when the accumulated additional output of the equipment in the processing area exceeds the required additional output.

8. The intelligent manufacturing workshop management and control method based on edge-cloud collaboration according to claim 7, characterized in that, The state performance index Si of each device within the processing area of ​​the equipment is obtained, specifically as follows: Obtain the processing equipment index Pi of each device within the set time zone's processing area, combine it with the device's service life Ji and historical maintenance frequency Di, and substitute it into the formula. The state performance index Si of each device is obtained through comprehensive calculation; where These are the weighting coefficients for the processing equipment index Pi, the years of use Ji, and the number of historical maintenance Di, respectively.

9. An edge-cloud collaborative intelligent manufacturing workshop management and control system, applied to any one of the edge-cloud collaborative intelligent manufacturing workshop management and control methods described in claims 1-8, characterized in that, include: The node data transmission module is used to collect processing data, storage data, and quality data of the corresponding divided areas in real time using each edge node, and transmit them to the cloud processing module; The cloud processing module is used to perform anomaly analysis on the processing data, storage data, and quality data of each divided area, and then determine the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop. The anomaly handling module is used to determine the abnormal status of each area of ​​the workshop and execute the corresponding steps based on the comparison results of the processing equipment index Pi, material environment index G, and quality assessment index N of the corresponding equipment processing area, material storage area, and quality inspection area in the workshop. After handling abnormal states in the workshop, the scheduling module intelligently schedules the workshop production progress based on the current production task requirements of the workshop and the status performance index Si of each piece of equipment in the equipment processing area.

Images