Real-time early warning method, system and equipment for garment production process and medium

Abstract

The invention provides a real-time early warning method, system and device for a garment production process and a medium. The method comprises the following steps: acquiring operation state data of a target device; performing multi-dimensional data processing based on the running state data to obtain an analysis result; performing dynamic early warning processing based on the analysis result to obtain early warning information; and performing linkage processing based on the early warning information. According to the invention, production data such as the production state, the work reporting quantity and the quality inspection quantity of the production equipment and equipment fault data are monitored in real time, intelligent analysis is performed, and early warning is triggered, so that the production efficiency is improved, the production cost is reduced, and the product quality is guaranteed; the problems that in the prior art, abnormal conditions such as equipment faults, production schedule lag and quality problems often occur in the production process, and due to the fact that an early warning mechanism is not comprehensive and not timely, production efficiency is low and production cost is high are solved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data processing, and relates to a real-time warning method, system, device and medium for a garment production process. BACKGROUND

[0002] In the traditional garment production and manufacturing field, production efficiency and quality control are highly dependent on manual experience and discrete management mode. Due to the lack of real-time and intelligent production monitoring means, abnormal situations such as equipment sudden failure, production progress lag, process quality fluctuation, etc. exist in the production process. If such problems are not discovered and intervened in time, it will directly lead to production line shutdown, raw material waste, order delay, low production efficiency, and thus increase production cost and reduce enterprise market competitiveness.

[0003] In order to optimize production management, the prior art proposes to realize basic informatization through a manufacturing execution system (MES). However, the existing MES system has significant limitations in the warning function, which are as follows:

[0004] The warning mechanism is not comprehensive, limited to single-dimensional (such as equipment failure or production progress) monitoring, and cannot comprehensively analyze the impact of multiple factors on production; the data integration is insufficient, and multi-source data such as production equipment, materials and personnel are difficult to synchronize in real time, leading to delayed warning; the abnormality detection capability is weak, relying on manual experience to judge abnormalities, with high false positive rate and inability to predict potential risks; the warning response speed is slow, and rapid linkage processing cannot be achieved, leading to problem amplification. SUMMARY

[0005] The application provides a real-time warning method, system, device and medium for a garment production process, which is used to solve the problem that abnormal situations such as equipment failure, production progress lag, quality problems, etc. often occur in the production process in the prior art, and the warning mechanism is not comprehensive and timely, resulting in low production efficiency and high production cost.

[0006] In a first aspect, the application provides a real-time warning method for a production process, which comprises: acquiring running state data of a target equipment; establishing a warning threshold based on the running state data, performing multi-dimensional data analysis according to the running state data and the warning threshold, and acquiring an abnormality analysis result; performing dynamic warning processing based on the abnormality analysis result, and acquiring warning information; and performing linkage processing based on the warning information.

[0007] In an implementation form of the first aspect, the running state data comprises parameter data and production data of the target device, the pre-warning threshold is established based on the running state data, the multi-dimensional data analysis is performed based on the running state data and the pre-warning threshold, and the abnormal analysis result is obtained by: performing time dimension segmentation based on the production data to obtain a corresponding running parameter subset; performing data preprocessing based on each running parameter subset to obtain a corresponding multi-dimensional data feature; obtaining production plan data based on the parameter data and each multi-dimensional data feature; the production plan data comprises a preset time plan yield and a pre-warning threshold; performing multi-dimensional data analysis based on each multi-dimensional data feature, the preset time plan yield and the pre-warning threshold to obtain an abnormal analysis result.

[0008] In an implementation form of the first aspect, the data preprocessing based on each running parameter subset to obtain a corresponding multi-dimensional data feature comprises: receiving each running parameter subset of the target device by using an edge computing device; performing missing value filling processing based on each running parameter subset to obtain corresponding data after missing value filling; performing abnormal value identification based on each data after missing value filling to obtain corresponding data after abnormal value processing; performing feature extraction based on each data after abnormal value processing to obtain a corresponding multi-dimensional data feature.

[0009] In an implementation form of the first aspect, the feature extraction based on each data after abnormal value processing to obtain a corresponding multi-dimensional data feature comprises: performing average value calculation based on the data after abnormal value processing to obtain a corresponding average yield; performing sorting processing based on the data after abnormal value processing to obtain a corresponding median yield; performing standard deviation calculation based on the data after abnormal value processing and the corresponding average yield to obtain a corresponding standard deviation; performing coefficient of variation calculation based on the standard deviation and the average yield to obtain a coefficient of variation; performing abnormal rate calculation based on the data after abnormal value processing and a preset pre-warning threshold to obtain a corresponding abnormal rate; and taking the average yield, the median yield, the standard deviation, the coefficient of variation and the abnormal rate as multi-dimensional data features.

[0010] In an implementation form of the first aspect, the multi-dimensional data analysis based on each multi-dimensional data feature, the preset time plan yield and the pre-warning threshold to obtain an abnormal analysis result comprises: performing multi-dimensional data analysis based on each multi-dimensional data feature, the preset time plan yield and the pre-warning threshold by using a decision tree algorithm to obtain path weight information; and performing weight calculation based on the path weight information to obtain abnormal probability information as an abnormal analysis result.

[0011] In an implementation form of the first aspect, the dynamic early warning processing based on the abnormal analysis result comprises: automatically triggering a corresponding early warning signal based on the abnormal analysis result; and dynamically displaying, by using a visual interface, early warning information corresponding to the early warning signal.

[0012] In an implementation form of the first aspect, the linkage processing based on the early warning information comprises: automatically matching and generating a corresponding maintenance resource scheduling signal based on the early warning information; and scheduling a corresponding maintenance resource based on the maintenance resource scheduling signal to perform corresponding early warning linkage processing.

[0013] In a second aspect, the present application provides a real-time early warning system for a production process, comprising: a data acquisition module configured to acquire running state data of a target device; a data analysis module configured to establish an early warning threshold based on the running state data, perform multi-dimensional data analysis based on the running state data and the early warning threshold, and acquire an abnormal analysis result; an early warning triggering module configured to perform dynamic early warning processing based on the abnormal analysis result and acquire early warning information; and a linkage processing module configured to perform linkage processing based on the early warning information.

[0014] In a third aspect, the present application provides an electronic device, comprising: a memory storing a computer program; and a processor communicatively connected to the memory and configured to execute the computer program to implement the real-time early warning method for a production process.

[0015] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is configured to be executed by a processor to implement the real-time early warning method for a production process.

[0016] As described above, the real-time early warning method, system, device and medium for a garment production process have the following beneficial effects:

[0017] The present application acquires running state data of a target device, establishes an early warning threshold based on the running state data, performs multi-dimensional data analysis based on the running state data and the early warning threshold, acquires an abnormal analysis result, performs dynamic early warning processing based on the abnormal analysis result, acquires early warning information, and performs linkage processing based on the early warning information. The present application intelligently analyzes and triggers early warning by monitoring production data such as production state, number of reported work, number of quality inspection, and device failure data of a production device in real time, thereby improving production efficiency, reducing production cost, and ensuring product quality. The present application solves the problem of low production efficiency and high production cost caused by incomplete and untimely early warning mechanism due to frequent device failure, production lag, quality problems and other abnormal situations in the production process. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A scene diagram showing a real-time early warning method of a garment production process according to an embodiment of the present application.

[0019] Figure 2 A flow diagram showing a real-time early warning method of a garment production process according to an embodiment of the present application.

[0020] Figure 3 A flow diagram showing a multi-dimensional data analysis according to an embodiment of the present application.

[0021] Figure 4 A flow diagram showing a multi-dimensional data feature acquisition according to an embodiment of the present application.

[0022] Figure 5 A flow diagram showing a feature extraction according to an embodiment of the present application.

[0023] Figure 6 A flow diagram showing an abnormality analysis result acquisition according to an embodiment of the present application.

[0024] Figure 7 A flow diagram showing a dynamic early warning processing according to an embodiment of the present application.

[0025] Figure 8 A flow diagram showing a linkage processing according to an embodiment of the present application.

[0026] Figure 9 A structure diagram showing a real-time early warning system of a garment production process according to an embodiment of the present application.

[0027] Figure 10 A structure diagram showing an electronic device according to an embodiment of the present application.

[0028] ELEMENT NUMBER EXPLANATION

[0029] 101 processor 3023 storage system

[0030] 102 memory 3024 utility

[0031] 103 input and output device 30241 program module

[0032] 104 display device 303 bus

[0033] 200 real-time early warning system of a production process 304 I / O interface

[0035] 201 data acquisition module 305 network adapter

[0036] 202 data analysis module S1-S4 steps 203 early warning triggering module S21-S24 steps 204 linkage processing module S221-S224 steps 300 electronic device S2241-S2246 steps 301 processing unit S241-S242 steps 302 storage unit S31-S32 steps 3021 RAM S41-S42 steps 3022 cache memory DETAILED DESCRIPTION

[0037] The advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure of the specification. The present application can also be implemented or applied in other different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0038] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner, and only show the components related to the present application in the diagrams, not the number, shape and size of the components when actually implemented. The actual implementation of each component may be a random change in type, number and proportion, and the component layout pattern may be more complex.

[0039] The following embodiments of the present application provide a real-time early warning method, system, device and medium for a garment production process, which solves the problem of abnormal situations such as equipment failure, production progress lag, quality problems, etc. in the production process in the prior art, because the early warning mechanism is not comprehensive and timely, resulting in low production efficiency and high production cost.

[0040] The real-time early warning method, system, device and medium for a garment production process provided in the following embodiments of the present application include but are not limited to the application scene of early warning in the MES production process of a garment factory. The following will be described taking this application scene as an example.

[0041] The real-time early warning method for a garment production process provided in the embodiments of the present application can run in an electronic device. Taking an electronic device as an example, Figure 1 Figure 1 ​A hardware structure block diagram of an electronic device for running the real-time warning method of the garment production process. The electronic device includes but is not limited to a processor 101 and a memory 102. The processor 101 is connected with the memory 102 through a bus. The memory 102 is a non-transitory computer readable storage medium provided in the present application. The memory stores instructions executable by at least one processor, so that the at least one processor 101 executes the real-time warning method of the garment production process provided in the present application. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to execute the real-time warning method of the garment production process provided in the present application. The memory 102 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store image data required by the real-time warning method of the garment production process and data created by use of the electronic device according to the real-time warning method of the garment production process, etc. In addition, the memory 102 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory 102 can optionally include a memory disposed remotely with respect to the processor 101, and these remote memories can be connected to the electronic device for determining the real-time warning of the garment production process through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The electronic device further includes an input / output device 103 and a display device 104. The input / output device 103 can receive input running state data, such as running state data of a production device, which can be stored in the memory 102, so that the processor 101 performs real-time monitoring of real-time warning according to the running state data, and displays abnormal information corresponding to warning information through the display device 104. The input / output device 103 can include but is not limited to a sensor and a hardware device such as a hanger. The display device 104 can include but is not limited to a liquid crystal display (LCD), a light-emitting diode (LED) display, a plasma display, and a touch screen. The embodiments of the present application are not limited. In the embodiments of the present application, the above components of the electronic device and other components not shown in the present application can be connected with each other, such as through a bus. It should be understood that Figure 1 the above components of the electronic device and other components not shown in the present application can be connected with each other, such as through a bus. It should be understood that Figure 1The electronic device structure diagram shown is merely for the purpose of example, and is not a limitation on the scope of the present application. Those skilled in the art can add or replace other components as needed. The electronic device can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The vehicle orientation angle calculation apparatus 1 can also be a mobile or stationary server. The embodiments of the present application are not limited.

[0042] The principles and implementation manners of the real-time early warning method, system, device and medium for a garment production process of the present embodiment will be described in detail below, so that those skilled in the art can understand the real-time early warning method, system, device and medium for a garment production process of the present embodiment without creative labor.

[0043] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application.

[0044] As Figure 2 shown, the present embodiment provides a real-time early warning method for a garment production process, which comprises the following steps S1 to S4.

[0045] Step S1, obtaining running state data of a target device. The target device is a production device in a garment production process; the running state data includes but is not limited to parameter data and production data in the production process of the target device.

[0046] In some embodiments, the present application uses sensors and hardware devices such as hangers to collect abnormal states, parameter data, production data and yield data of production devices in real time, and uploads the data to the MES system after preliminary processing.

[0047] MES (Manufacturing Execution System) is a manufacturing execution system, which is a management system for workshop production. It is a core system connecting the enterprise planning layer (such as ERP) and the control layer (such as PLC, SCADA), and focuses on the management and optimization of the production process in the workshop.

[0048] In an embodiment of the present application, obtaining running state data of a target device comprises the following steps S11 to S12.

[0049] Step S11, obtaining original running state data of a target device. The original running state data is abnormal state, parameter data, production data, and yield data of a production device collected in real time by sensors and hardware devices such as hangers.

[0050] Step S12, preprocessing based on the original running state data to obtain running state data of the target device.

[0051] In some embodiments, the application collects original running state data such as running parameters, production data, yield data, and quality inspection data of a production device through sensors and hardware devices such as hangers deployed on a target device, and obtains running state data of the target device through preprocessing of the original running state data by an edge computing device, and uploads the running state data of the target device to an MES system.

[0052] The application can discover and solve quality problems in time and avoid "manufacturing waste" by monitoring running state data of a production device in real time.

[0053] Step S2, establishing a warning threshold based on the running state data, performing multi-dimensional data analysis according to the running state data and the warning threshold to obtain an abnormal analysis result.

[0054] In some embodiments, the application analyzes collected data in combination with a decision tree algorithm to establish a warning threshold. For example, the application predicts whether the yield in production is abnormal by analyzing historical production data, and evaluates the impact of the abnormality on overall production in combination with a current production plan.

[0055] In an embodiment of the application, the running state data includes parameter data, production data, abnormal state, and yield data of a target device.

[0056] As shown in Figure 3 In an embodiment of the application, establishing a warning threshold based on the running state data and performing multi-dimensional data analysis according to the running state data and the warning threshold to obtain an abnormal analysis result includes the following steps S21 to S24.

[0057] Step S21, performing time dimension segmentation based on the production data to obtain a corresponding running parameter subset.

[0058] Step S22, performing data preprocessing based on each running parameter subset to obtain a corresponding multi-dimensional data feature.

[0059] Step S23, obtaining production plan data based on the parameter data and each multi-dimensional data feature; the production plan data includes a preset time plan yield and a warning threshold.

[0060] Step S24, performing multi-dimensional data analysis based on the multi-dimensional data features, the preset time plan yield and the early warning threshold to obtain an abnormality analysis result.

[0061] In some embodiments, the application first divides production data in a time dimension to obtain a plurality of running parameter subsets, for example, dividing production data in a time dimension by week, which can reduce the data sample capacity of a single algorithm; then, data preprocessing is performed on the plurality of running parameter subsets, for example, preprocessing raw data by an edge computing device, specifically including missing value filling, abnormal value identification and feature extraction, to obtain corresponding multi-dimensional data features, and based on the multi-dimensional data features and the parameter data, a preset time plan yield (for example, a daily plan number of production units) and an early warning threshold are obtained, and finally, multi-dimensional data analysis is performed based on the multi-dimensional data features, the preset time plan yield and the early warning threshold to obtain an abnormality analysis result.

[0062] As shown in FIG. 1, in an embodiment of the application, based on the data preprocessing of each running parameter subset, the obtaining of the corresponding multi-dimensional data features includes the following steps S221-S224. Figure 4

[0063] Step S221, receiving each running parameter subset of the target device by an edge computing device.

[0064] Step S222, performing missing value filling processing based on each running parameter subset to obtain corresponding data after missing value filling.

[0065] Step S223, performing abnormal value identification based on each data after missing value filling to obtain corresponding data after abnormal value processing.

[0066] Step S224, performing feature extraction based on each data after abnormal value processing to obtain corresponding multi-dimensional data features.

[0067] As shown in FIG. 1, in an embodiment of the application, based on the data preprocessing of each running parameter subset, the obtaining of the corresponding multi-dimensional data features includes the following steps S221-S224. Figure 5

[0068] Step S2241, performing average value calculation based on the data after abnormal value processing to obtain corresponding average yield.

[0069] Step S2242, performing sorting processing based on the data after abnormal value processing to obtain corresponding median yield.

[0070] ​​Step S2243, based on the processed data and the corresponding average yield, a standard deviation is calculated to obtain the corresponding standard deviation.

[0071] Step S2244, based on the standard deviation and the average yield, a coefficient of variation is calculated to obtain the coefficient of variation.

[0072] Step S2245, based on the processed data and a preset warning threshold, an abnormal rate is calculated to obtain the corresponding abnormal rate.

[0073] Step S2246, the average yield, the median yield, the standard deviation, the coefficient of variation and the abnormal rate are taken as multi-dimensional data features.

[0074] In some embodiments, the application obtains corresponding multi-dimensional data features by performing the above steps S2241 to S2246 of feature extraction on each of the processed data.

[0075] In some embodiments, the application performs preprocessing on the original data by an edge computing device, including missing value filling, outlier identification and feature extraction. For example, the statistical features (such as mean, median, variance, etc.) of the yield data are extracted to quantify the stability of the production process. The statistical features are as follows:

[0076] Arithmetic mean (Mean): it is the average level of yield data in the calculation time window; the processing method of arithmetic mean: sum all yield data in the specified time period and divide by the number of data points; the use of arithmetic mean: reflects the average output level of the production equipment, which is used to judge the overall production efficiency.

[0077] Median (Median): it is the median value of yield data in the calculation time window; the processing method of median: sort the yield data by size and take the value at the middle position; the use of median: eliminate the influence of extreme values and more accurately reflect the typical output level of the production equipment.

[0078] Standard deviation (Standard Deviation): it is a measure of the volatility of yield data; the processing method of standard deviation: calculate the square root of the average of the square sum of the difference between each data point and the mean; the use of standard deviation: evaluate production stability, the smaller the standard deviation, the more stable the production.

[0079] Variance (Variance): it is a measure of the dispersion of yield data; the processing method of variance: calculate the average of the square of the difference between each data point and the mean; the use of variance: quantify the variability of the production process.

[0080] Coefficient of variation (CV): it is the ratio of standard deviation and average value; the processing method of coefficient of variation: CV = standard deviation / average value x 100%; the use of coefficient of variation: eliminate the dimension effect, compare the relative variation degree among different equipment.

[0081] It should be noted that the pre-processing of the original data by the edge computing device can be in the data analysis stage or in the data collection stage, and the application is not limited thereto.

[0082] As shown in Figure 6 In an embodiment of the present application, the multi-dimensional data analysis based on the multi-dimensional data features, the preset time plan yield and the early warning threshold value includes the following steps S241-S242.

[0083] Step S241, based on each of the multi-dimensional data features, the preset time plan yield and the early warning threshold value, using decision tree algorithm for multi-dimensional data analysis, obtaining path weight information.

[0084] Step S242, based on the path weight information, weight calculation is performed to obtain abnormal probability information as the abnormal analysis result.

[0085] In some embodiments, the present application takes the yield data in the production data as the original input of the MES system, uses the decision tree algorithm, divides the production data into multiple subsets according to the time latitude, reduces the data sample capacity of a single algorithm, and forms multi-dimensional data by statistical feature extraction for each subset. The MES system takes the yield-related statistical features as the condition attributes of the decision tree: for example, the current yield value, the yield average value, the yield median, the yield standard deviation, the coefficient of variation, etc. The present application performs data analysis according to the parameter data and statistical features of the production equipment to obtain the daily plan number of the production order and the system configuration threshold n (i.e. the preset early warning threshold value), takes the daily plan number of the production order and the system configuration threshold n (i.e. the preset early warning threshold value) as the decision attribute, and establishes the mapping relationship between the condition attribute and the decision attribute. The condition attribute, the decision attribute and the mapping relationship are input into the decision tree model, and the abnormal probability is evaluated according to the path weight set by the decision tree. The specific calculation is illustrated as follows:

[0086] First, the scene is set, assuming that the daily yield data of a certain production line in the next 7 days is as follows: day 1: 850 pieces, day 2: 920 pieces, day 3: 780 pieces, day 4: 890 pieces, day 5: 760 pieces, day 6: 910 pieces, day 7: 830 pieces. The preset early warning threshold n = 800 pieces / day.

[0087] The calculation process of the statistical features (target features) is as follows:

[0088] Mean calculation: Mean = (850 + 920 + 780 + 890 + 760 + 910 + 830) ÷ 7 = 5940 ÷ 7 = 848.57 pieces / day.

[0089] Median calculation: After sorting: 760, 780, 830, 850, 890, 910, 920; Median = 850 pieces / day (4th number).

[0090] Standard deviation calculation:

[0091] Step 1: Calculate the difference between each data point and the mean, difference sequence: 1.43, 71.43, -68.57, 41.43, -88.57, 61.43, -18.57.

[0092] Step 2: Calculate the square of the difference, square sequence: 2.04, 5102.24, 4701.84, 1716.44, 7844.64, 3773.64, 344.84.

[0093] Step 3: Calculate the variance, Variance = (2.04 + 5102.24 + 4701.84 + 1716.44 + 7844.64 + 3773.64 + 344.84) ÷ 7 = 23485.68 ÷ 7 = 3355.11.

[0094] Step 4: Calculate the standard deviation, Standard Deviation = √3355.11 = 57.93 pieces / day.

[0095] Coefficient of variation calculation: CV = (57.93 ÷ 848.57) × 100% = 6.83%.

[0096] Threshold judgment logic, state judgment as follows:

[0097] Day 1: 850 ≥ 800, normal state.

[0098] Day 2: 920 ≥ 800, normal state.

[0099] Day 3: 780 < 800, abnormal state.

[0100] Day 4: 890 ≥ 800, normal state.

[0101] Day 5: 760 < 800, abnormal state.

[0102] Day 6: 910 ≥ 800, normal state.

[0103] Day 7: 830 ≥ 800, normal state.

[0104] Abnormal days: 2 days; Abnormal rate: 2 / 7 = 28.57%.

[0105] The decision tree feature input example is as follows:

[0106] The conditional attribute matrix includes the current yield, 7-day average yield, 7-day median yield, 7-day standard deviation, coefficient of variation, and proportion of abnormal days, as follows:

[0107] Current yield: 830 pieces;

[0108] 7-day average yield: 848.57 pieces;

[0109] 7-day median yield: 850 pieces;

[0110] 7-day standard deviation: 57.93 pieces;

[0111] Coefficient of variation: 6.83%;

[0112] Proportion of abnormal days: 28.57%.

[0113] The decision attribute includes the daily planned yield and the system preset warning threshold n, as follows:

[0114] Daily planned yield: 900 pieces;

[0115] System preset warning threshold n: 800 pieces.

[0116] The decision tree output is as follows:

[0117] According to the path weight calculation, the abnormal probability is calculated;

[0118] The abnormal probability is calculated by accumulating the weights of each node in the decision tree:

[0119] Abnormal probability = Σ (path i weight × path i probability).

[0120] Example calculation:

[0121] Path 1 (yield < threshold): weight 0.4 × probability 0.6 = 0.24;

[0122] Path 2 (coefficient of variation > 10%): weight 0.3 × probability 0.2 = 0.06;

[0123] Path 3 (trend downward): weight 0.2 × probability 0.3 = 0.06;

[0124] Path 4 (abnormal rate > 20%): weight 0.1 × probability 0.9 = 0.09;

[0125] Total abnormal probability = 0.24 + 0.06 + 0.06 + 0.09 = 0.45 = 45%.

[0126] The application can discover and solve quality problems in time and avoid "manufacturing waste" by monitoring the running state data of the production equipment in real time and timely analyzing the running state data.

[0127] Step S3: performing dynamic early warning processing based on the abnormality analysis result to obtain early warning information.

[0128] In some embodiments, the MES system automatically triggers an early warning signal according to the abnormality analysis result, and displays abnormal information corresponding to the early warning signal through a visual interface. For example, when the production yield is abnormal, the MES system will immediately display the abnormal information (such as color change and warning information) corresponding to the early warning signal on a large display screen and notify relevant personnel to handle it.

[0129] As shown in the embodiment of the application, the step of performing dynamic early warning processing based on the abnormality analysis result to obtain early warning information includes steps S31 and S32. Figure 7

[0130] Step S31: automatically triggering a corresponding early warning signal based on the abnormality analysis result.

[0131] Step S32: dynamically displaying early warning information corresponding to the early warning signal through a visual interface.

[0132] The application reduces downtime or prolongs production delivery time caused by production equipment failure or production abnormality through early warning and rapid response, reduces maintenance cost and defective product rate, optimizes resource allocation, and reduces production cost. In addition, the application displays production state and abnormal information in real time through a visual interface, which facilitates managers to make quick decisions and enhances management transparency.

[0133] Step S4: performing linkage processing based on the early warning information.

[0134] In some embodiments, the application performs linkage processing according to the early warning information, schedules maintenance resources (such as maintenance personnel and production planners) in time, and generates optimization suggestions (such as adjusting workstation arrangement or replacing equipment). At the same time, the MES system supports recording the abnormality handling process and forms a closed-loop management.

[0135] As shown in the embodiment of the application, the step of performing linkage processing based on the early warning information includes steps S41 and S42. Figure 8

[0136] Step S41: automatically matching and generating a corresponding maintenance resource scheduling signal based on the early warning information.

[0137] Step S42: scheduling corresponding maintenance resources based on the maintenance resource scheduling signal to perform corresponding early warning linkage processing.​​

[0138] In some embodiments, the application utilizes the MES system to automatically schedule maintenance resources (e.g., maintenance personnel) according to the warning level and generate optimization suggestions (e.g., adjust the process or replace the equipment). At the same time, the application utilizes the MES system to record the exception handling process and form a closed-loop management. When encountering such warning information and warning level next time, the application can directly automatically schedule the corresponding recorded maintenance resources and optimization suggestions through the MES system, timely respond to the warning information, so as to timely discover and solve quality problems, reduce downtime or extend production delivery time caused by equipment failure or production exception through early warning and rapid response.

[0139] In some embodiments, in the production process, each hanging production line has an edge agent, the edge agent sends a heartbeat packet to the cloud to detect the online state of the production line. When the production line fails, such as motor failure, card reader exception, etc., the fault electrical signal is sent to the hardware control program, and the hardware control program processes and sends the production line position, fault position, fault code, etc. information to the edge agent. The edge agent reports the fault information to the cloud, and the cloud service matches the fault code dictionary (for example, fault code: 1-1-1, fault equipment: air cylinder, equipment position: channel 1, fault name: low air pressure, fault description: please check whether the air cylinder is damaged or the air pressure source is abnormal; fault code: 2-1-1, fault equipment: push rod, equipment position: channel 1, fault name: push rod spacing abnormal, fault description: please check the push rod installation spacing or whether the push rod is damaged;), converts the fault information into readable information according to the fault code, and pushes it to the mobile phone notification of the service personnel (such as maintenance workers). The relevant service personnel such as maintenance workers will confirm the exception after receiving the notification and take the next maintenance operation. The cloud records the fault and generates corresponding statistical report. Through analysis, the hot fault reason can be obtained, so as to carry out parts stocking, equipment replacement, adjustment of station arrangement, etc.

[0140] The application intelligently analyzes and triggers early warning by real-time monitoring of production data such as production state, work quantity, quality inspection quantity, and equipment failure data, thereby improving production efficiency, reducing production cost and ensuring product quality, comprehensively improving the intelligent level and exception handling efficiency of the production process, significantly improving the production efficiency and management level of the garment factory, and having important social and economic benefits.

[0141] The application can discover and solve quality problems in time, avoid "manufacturing waste", and ensure product quality by monitoring the running state data of the production equipment in real time and timely analyzing the running state data; the application reduces downtime or extends production delivery time caused by equipment failure or production abnormalities through early warning and rapid response, improves production efficiency, reduces maintenance costs and defective product rates, optimizes resource allocation, and reduces production costs; and the application displays production status and abnormal information in real time through a visual interface, facilitates managers to make quick decisions, and enhances management transparency.

[0142] The protection scope of the real-time warning method for the garment production process described in the embodiments of the application is not limited to the execution order of the steps listed in the embodiments, and any scheme realized by adding, replacing or changing steps of the prior art according to the principles of the application is included in the protection scope of the application.

[0143] The embodiments of the application also provide a real-time warning system for a garment production process, which can implement the real-time warning method for the garment production process described in the application, but the implementation device of the real-time warning method for the garment production process described in the application includes but is not limited to the structure of the real-time warning system for the garment production process listed in the embodiments, and any structure deformation and replacement of the prior art according to the principles of the application is included in the protection scope of the application.

[0144] As shown in Figure 9 The embodiments provide a real-time warning system for a garment production process, and the system 200 includes a data acquisition module 201, a data analysis module 202, a warning triggering module 203, and a linkage processing module 204.

[0145] The data acquisition module 201 is configured to acquire running state data of a target device.

[0146] The data analysis module 202 is configured to establish a warning threshold based on the running state data, perform multi-dimensional data analysis based on the running state data and the warning threshold, and acquire an abnormal analysis result.

[0147] The warning triggering module 203 is configured to perform dynamic warning processing based on the abnormal analysis result and acquire warning information.

[0148] The linkage processing module 204 is configured to perform linkage processing based on the warning information.

[0149] It should be noted that the functions or operations of the data acquisition module 201, the data analysis module 202, the warning triggering module 203, and the linkage processing module 204 described in the embodiments of the application correspond one-to-one to the steps in the real-time warning method for the garment production process described above, and therefore will not be described again here.

[0150] In several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other manners. For example, the division of the above-described device embodiment is only a logical function division, and there can be another division manner for the actual implementation, for example, multiple physical devices or multiple physical modules can be combined or integrated into another system, or some characteristics can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different parts can be indirect couplings or communication connections through some interfaces, devices or modules, and can be electrical, mechanical or in other forms.

[0151] The modules / units described as separated components can or can not be physically separated, and the components displayed as modules / units can or can not be physical modules, i.e., can be located in one place or distributed on multiple network units. Some or all of the modules / units can be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in each embodiment of the present application can be integrated into one processing module, or each module / unit can be physically separated, or two or more modules / units can be integrated into one module / unit.

[0152] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0153] In an embodiment of the present application, the embodiment provides an electronic device, the electronic device comprising: a memory and a processor.

[0154] The memory stores a computer program.

[0155] The processor, in communication connection with the memory, invokes the computer program to execute the real-time early warning method of the production process described above.

[0156] As Figure 10As shown, the electronic device 300 of this application is embodied in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors or processing units 301, a storage unit 302, and a bus 303 connecting different system components (including the storage unit 302 and the processing unit 301).

[0157] Bus 303 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0158] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0159] Storage unit 302 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 3021 and / or cache memory 3022. The terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 3023 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 10 Not shown; usually referred to as a "hard drive"). Although Figure 10 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 303 via one or more data media interfaces. Storage unit 302 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0160] A program / utility 3024 having a set (at least one) of program modules 30241 may be stored, for example, in storage unit 302. Such program modules 30241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 30241 typically perform the functions and / or methods described in the embodiments of this application.

[0161] The electronic device can also be in communication with one or more external devices such as a keyboard or a pointing and / or selection device, a display, etc.; one or more devices that enable a user to interact with the terminal; and / or one or more devices (e.g., network cards, modems, etc.) that enable the terminal to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface 304. Still yet, such terminal can communicate with one or more networks such as a local area network (LAN), a general wide area network (WAN), and / or a public network (e.g., the Internet) via network adapter 305. As Figure 10 illustrated, network adapter 305 is in communication with the other components of the terminal through bus 303. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with the terminal. These components, which would be well known in the art, include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0162] The embodiments of the present application also provide a computer readable storage medium. Those skilled in the art can understand that all or part of the steps of the methods described above can be completed by a program instructing a processor, and the program can be stored in a computer readable storage medium. The storage medium is a non-transitory medium, such as a random access memory, a read only memory, a flash memory, a hard disk, a solid state disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0163] The embodiments of the present application can also provide a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in the embodiments of the present application are generated. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer or data center to another website, computer or data center through a wired (such as a coaxial cable, an optical fiber, a digital subscriber line (DSL)) or a wireless (such as infrared, wireless, microwave, etc.) manner.

[0164] The computer program product is executed by a computer, and the computer executes the method of the foregoing method embodiments. The computer program product can be a software installation package, and in the case of needing to use the foregoing method, the computer program product can be downloaded and executed on the computer.

[0165] In summary, the real-time early warning method, system, device and medium for a garment production process have the following beneficial effects:

[0166] The application obtains running state data of a target device, establishes a warning threshold based on the running state data, performs multi-dimensional data analysis based on the running state data and the warning threshold, obtains an abnormal analysis result, performs dynamic warning processing based on the abnormal analysis result, obtains warning information, and performs linkage processing based on the warning information. The application intelligently analyzes and triggers early warning by monitoring production data such as the production state, the number of reported work, the number of quality inspection, and device fault data of the production device in real time, thereby improving production efficiency, reducing production cost, and ensuring product quality. The application solves the problems of frequent device failure, lagging production progress, quality problems, and other abnormal situations in the production process in the prior art, and the problems of incomplete and untimely early warning mechanism, thereby leading to low production efficiency and high production cost.

[0167] The descriptions of the processes or structures corresponding to the above respective figures each have a focus, and parts not described in detail in a certain process or structure can be referred to the related descriptions of other processes or structures.

[0168] The above embodiments only exemplarily illustrate the principles and effects of the application, and are not used to limit the application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the application. Therefore, all equivalent modifications or changes completed by those skilled in the art without departing from the spirit and technical thought of the application should be covered by the claims of the application.

Claims

1. A real-time alert method for a garment production process, characterized in that, The method comprises the following steps: acquiring running state data of a target device; establishing a pre-warning threshold based on the running state data, performing multi-dimensional data analysis based on the running state data and the pre-warning threshold, and obtaining an abnormality analysis result; performing dynamic pre-warning processing based on the abnormality analysis result, and obtaining pre-warning information; performing linkage processing based on the pre-warning information.

2. The real-time alert method for apparel production process according to claim 1, wherein, The running state data comprises parameter data and production data of the target device, the pre-warning threshold is established based on the running state data, the multi-dimensional data analysis is performed based on the running state data and the pre-warning threshold, and the abnormality analysis result is obtained, which comprises the following steps: performing time dimension segmentation based on the production data, and obtaining a corresponding running parameter subset; performing data preprocessing based on each running parameter subset, and obtaining a corresponding multi-dimensional data feature; obtaining production plan data based on the parameter data and each multi-dimensional data feature; the production plan data comprises a preset time plan yield and a pre-warning threshold; performing multi-dimensional data analysis based on each multi-dimensional data feature, the preset time plan yield and the pre-warning threshold, and obtaining an abnormality analysis result.

3. The real-time alert method for apparel production process according to claim 2, wherein, The data preprocessing based on each running parameter subset and the obtaining of the corresponding multi-dimensional data feature comprise the following steps: receiving each running parameter subset of the target device by using an edge computing device; performing missing value filling processing based on each running parameter subset, and obtaining corresponding data after missing value filling; performing abnormal value identification based on each data after missing value filling, and obtaining corresponding data after abnormal value processing; performing feature extraction based on each data after abnormal value processing, and obtaining a corresponding multi-dimensional data feature.

4. The real-time alert method for garment production process according to claim 3, wherein, The feature extraction based on each data after abnormal value processing and the obtaining of the corresponding multi-dimensional data feature comprise the following steps: performing average value calculation based on the data after abnormal value processing, and obtaining a corresponding average yield; performing sorting processing based on the data after abnormal value processing, and obtaining a corresponding median yield; performing standard deviation calculation based on the data after abnormal value processing and the corresponding average yield, and obtaining a corresponding standard deviation; performing coefficient of variation calculation based on the standard deviation and the average yield, and obtaining a coefficient of variation; performing abnormal rate calculation based on the data after abnormal value processing and a preset pre-warning threshold, and obtaining a corresponding abnormal rate; taking the average yield, the median yield, the standard deviation, the coefficient of variation and the abnormal rate as multi-dimensional data features.

5. The real-time alert method for apparel production process according to claim 2, wherein, The multi-dimensional data analysis based on each multi-dimensional data feature, the preset time plan yield and the pre-warning threshold, and the obtaining of the abnormality analysis result comprise the following steps: performing multi-dimensional data analysis based on each multi-dimensional data feature, the preset time plan yield and the pre-warning threshold by using a decision tree algorithm, and obtaining path weight information; performing weight calculation based on the path weight information, and obtaining abnormal probability information as the abnormality analysis result.

6. The real-time alert method of garment production process according to claim 1, wherein, The dynamic pre-warning processing based on the abnormality analysis result, and the obtaining of the pre-warning information comprise the following steps: automatically triggering a corresponding pre-warning signal based on the abnormality analysis result; dynamically displaying pre-warning information corresponding to the pre-warning signal by using a visual interface.

7. The real-time early warning method for the garment production process according to claim 1, characterized in that, The linkage processing based on the early warning information comprises: The early warning information is matched and a corresponding maintenance resource scheduling signal is generated automatically; The corresponding maintenance resource is scheduled based on the maintenance resource scheduling signal to perform corresponding early warning linkage processing.

8. A real-time alert system for a garment production process, characterized in that, It comprises: An acquisition module configured to acquire running state data of a target device; A data analysis module configured to establish an early warning threshold based on the running state data, perform multi-dimensional data analysis according to the running state data and the early warning threshold, and acquire an abnormal analysis result; An early warning triggering module configured to perform dynamic early warning processing based on the abnormal analysis result and acquire early warning information; A linkage processing module configured to perform linkage processing based on the early warning information.

9. An electronic device, comprising: It comprises: A memory storing a computer program; A processor connected in communication with the memory, which invokes the computer program to execute the real-time early warning method of the garment production process according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by the processor to implement the real-time early warning method of the garment production process according to any one of claims 1 to 7.

Images