Smart factory data acquisition management method

Abstract

The invention relates to a smart factory, and particularly discloses a smart factory data acquisition and management method, which comprises the following steps of S01, capturing animation data of active personnel in a factory and operation state data of production equipment in real time by using a factory monitor; s02, performing preliminary screening, cleaning and formatting processing on the acquired data to form a data packet; s03, transmitting the data packet to the terminal in a multi-transfer mode, wherein each transfer node is responsible for data delay detection and correction; and S04, after the terminal receives the data, performing deep analysis by using an artificial intelligence algorithm, judging the working state of an employee, predicting a potential dangerous case, and constructing a factory operation model based on an analysis result. According to the invention, data of active personnel and equipment in a factory can be captured in real time, a basis is provided for subsequent data processing and analysis, comprehensiveness and real-time performance of data acquisition are improved, and automatic and intelligent production of the smart factory can be realized.

Description

Technical Field

[0001] The present invention relates to a smart factory, and in particular to a data collection and management method for a smart factory. Background Art

[0002] With the rapid development of intelligent manufacturing technology, smart factories have become an important trend in the development of modern industry. In smart factories, efficient and accurate data collection and management are the key to achieving automated and intelligent production. However, existing factory data collection and management methods often have problems such as incomplete data collection, transmission delays, and low processing efficiency, which are difficult to meet the high requirements of smart factories for real-time, accuracy, and safety. In particular, in terms of employee work status monitoring and potential danger prediction, the timeliness and accuracy of data directly affect the effectiveness of management decisions and factory safety production. Summary of the invention

[0003] The purpose of the present invention is to provide a smart factory data collection and management method to solve the above problems.

[0004] In order to achieve the above object, the present invention provides the following technical solution: a smart factory data collection and management method, comprising the following steps:

[0005] S01. Use factory monitors to capture real-time animation data of people in the factory and operating status data of production equipment;

[0006] S02, preliminarily screening, cleaning and formatting the collected data to form a data package;

[0007] S03, using a multi-transfer method to transmit the data packet to the terminal, and each transfer node is responsible for data delay detection and correction;

[0008] S04. After receiving the data, the terminal uses artificial intelligence algorithms to conduct in-depth analysis to determine the work status of employees, predict potential dangerous situations, and build a factory operation model based on the analysis results.

[0009] Preferably, the step S01 captures the animation data of the active personnel in the factory and the operation status data of the production equipment, including:

[0010] S11, using an AI image recognition system, configured to be able to capture video frames in real time and convert them into animation data;

[0011] S12. Use algorithms to identify employee images in the video, extract the movement trajectory, posture changes, and operating behaviors of the identified units, and form key information data.

[0012] Preferably, the preliminary screening and cleaning of the collected data in step S02 includes:

[0013] S21, using an ant colony algorithm to quickly locate and identify valid data units in the operating status data according to a system preset project target to obtain a target unit;

[0014] S22, using a diffusion algorithm to determine the outer range of valid data, thereby determining a specific area of ​​the image to be processed;

[0015] S23, using a greedy algorithm to maximize the determination of the boundaries of a specific area, thereby aligning the specific area and completing the partitioning;

[0016] S24, screening the same specific areas in each frame of the image based on the TF-IDF similarity algorithm, retaining the data in the specific area with the highest matching degree with the target unit feature library, thereby determining the blur action of all target units in each frame.

[0017] Preferably, the step S02 of performing formatting processing on the fuzzy actions obtained after preliminary screening and cleaning includes:

[0018] S25, acquiring the blurred action of each frame and performing image denoising and sharpening respectively to obtain edge contour data sufficient for identifying the action posture;

[0019] S26, extracting spatial features from edge contour data according to a convolutional neural network model to obtain motion trajectory point data about limbs;

[0020] S27, extracting the motion trajectory point data of the limbs of the continuous frame images within the predetermined time window period by using the long short-term memory network model, thereby obtaining the motion trajectory point data connection line of each frame;

[0021] S28, comparing the motion trajectory point data connection lines in the continuous frame images with the trajectory point data connection lines map pre-stored in the system, giving the execution action of the current target unit, and judging whether it is in motion.

[0022] Preferably, the data delay detection and correction in step S03 includes:

[0023] S31, creating multiple data storage transfer stations, and the multiple transfer stations transmit data to the monitor through at least three data transmission methods: wireless network, local area network and radio;

[0024] S32, setting a data comparison delay threshold based on the communication properties of the wireless network, local area network and radio;

[0025] S33, and compare the data received by the plurality of transfer stations within the threshold. If the data transmitted by at least two data transmission modes are consistent, there is no error; if there is no data consistency, actively generate feedback and notify the back-end personnel to conduct investigation.

[0026] Preferably, in the step S33, if there are at least two data transmission modes with consistent data transmitted, the consistent data is identified, and the co-location data given by a delayed data transmission mode is compared with the historical data of the above two types of data transmission modes, and it is determined that there is only one data in the historical data that is identical to the co-location data, and the delay factor is determined based on the time difference between the identical data and the consistent data, and correction is performed to make the data of the three data transmission modes consistent.

[0027] Preferably, judging the working status of employees, predicting potential dangers, and building a factory operation model based on the analysis results in step S04 include:

[0028] S41, obtaining the target unit in motion determined in step S02;

[0029] S42, determining which production step in the factory operation model the specific area obtained in step S02 is;

[0030] S43. Based on the motion analysis of the current target unit, the motion is compared with the preset safe execution action library in the current production step, a training set is generated from the data, and whether the target unit is safe is given based on the comparison.

[0031] Preferably, the training set obtained in step S04 is used to train the plant operation model to update the model form.

[0032] In the above technical solution, the present invention provides a smart factory data collection and management method, which has the following beneficial effects:

[0033] 1. The use of AI image recognition system can efficiently capture video frames and convert them into animation data, improving the accuracy and real-time performance of data capture.

[0034] 2. Use algorithms to identify employee images in videos and extract key information data, providing a basis for judging employee work status and predicting potential dangerous situations.

[0035] 3. The collected data is initially screened and cleaned using the ant colony algorithm, diffusion algorithm and greedy algorithm, which improves the efficiency and accuracy of data processing. The images are then screened using the TF-IDF similarity algorithm, retaining the data with the highest matching degree with the target unit feature library, which is helpful for subsequent data analysis and processing.

[0036] 4. Format the fuzzy actions after preliminary screening and cleaning, and then use the convolutional neural network and long short-term memory network model to extract motion trajectory point data, providing more detailed data support for judging the work status of employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0038] Figure 1 A flowchart provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] like Figure 1 As shown, a smart factory data collection and management method includes:

[0041] Example 1

[0042] Steps for data collection and management of smart factories:

[0043] S01. Use factory monitors to capture real-time animation data of people in the factory and operating status data of production equipment;

[0044] S02, preliminarily screening, cleaning and formatting the collected data to form a data package;

[0045] S03, using a multi-transfer method to transmit the data packet to the terminal, and each transfer node is responsible for data delay detection and correction;

[0046] S04. After receiving the data, the terminal uses artificial intelligence algorithms to conduct in-depth analysis to determine the work status of employees, predict potential dangerous situations, and build a factory operation model based on the analysis results.

[0047] The AI ​​image recognition system used in the above technology can efficiently capture video frames and convert them into animation data, improving the accuracy and real-time performance of data capture. In addition, by 2, the employee images in the video are identified through algorithms, and key information data is extracted, providing a basis for judging the working status of employees and predicting potential dangers. This provides stable data support for the factory operation model and ensures the accuracy of the data and analysis given model.

[0048] Example 2

[0049] Based on Example 1, this example aims at capturing animation data of people in the factory and operation status data of production equipment, including:

[0050] S11, using an AI image recognition system, configured to be able to capture video frames in real time and convert them into animation data;

[0051] S12. Use algorithms to identify employee images in the video, extract the movement trajectory, posture changes, and operating behaviors of the identified units, and form key information data.

[0052] The above technology uses an AI image recognition system to efficiently capture video frames and convert them into animation data, improving the accuracy and real-time performance of data capture.

[0053] Example 3

[0054] Based on Example 1, this example performs preliminary screening, cleaning and formatting of the collected data, including:

[0055] S21, using the ant colony algorithm to quickly locate and identify the valid data units in the running status data according to the project objectives preset by the system to obtain the target unit;

[0056] S22, using a diffusion algorithm to determine the outer range of valid data, thereby determining a specific area of ​​the image to be processed;

[0057] S23, using a greedy algorithm to maximize the determination of the boundaries of a specific area, thereby aligning the specific area and completing the partitioning;

[0058] S24, screening the same specific area in each frame of the image based on the TF-IDF similarity algorithm, retaining the data in the specific area with the highest matching degree with the target unit feature library, thereby determining the blur action of all target units in each frame;

[0059] S25, acquiring the blurred action of each frame and performing image denoising and sharpening respectively to obtain edge contour data sufficient for identifying the action posture;

[0060] S26, extracting spatial features from edge contour data according to a convolutional neural network model to obtain motion trajectory point data about limbs;

[0061] S27, extracting the motion trajectory point data of the limbs of the continuous frame images within the predetermined time window period by using the long short-term memory network model, thereby obtaining the motion trajectory point data connection line of each frame;

[0062] S28, comparing the motion trajectory point data connection lines in the continuous frame images with the trajectory point data connection lines map pre-stored in the system, giving the execution action of the current target unit, and judging whether it is in motion.

[0063] The above technology uses ant colony algorithm, diffusion algorithm and greedy algorithm to initially screen and clean the collected data, improving the efficiency and accuracy of data processing. The TF-IDF similarity algorithm is then used to continue screening the images, retaining the data with the highest matching degree with the target unit feature library, which is helpful for subsequent data analysis and processing.

[0064] Example 4

[0065] Based on Example 1, this example detects and corrects data delay, including:

[0066] S31, creating multiple data storage transfer stations, and the multiple transfer stations transmit data to the monitor through at least three data transmission methods: wireless network, local area network and radio;

[0067] S32, setting a data comparison delay threshold based on the communication properties of the wireless network, the local area network and the radio;

[0068] S33, and compare the data received by multiple transfer stations within the threshold. If the data transmitted by at least two data transmission methods are consistent, there is no error; if there is no data consistency, actively generate feedback to notify the back-end personnel to conduct investigation.

[0069] Furthermore, in the above step S33, if there are at least two data transmission modes whose transmitted data are consistent, the consistent data is marked, and the co-location data given by a delayed data transmission mode is compared with the historical data of the above two types of data transmission modes, and it is determined that there is only one data in the historical data that is the same as the co-location data, and the delay factor is determined according to the time difference between the identical data and the consistent data, and correction is performed to make the data of the three data transmission modes consistent.

[0070] In the above technology, multiple data storage transfer stations are created, and data is transmitted to the monitor through multiple data transmission methods, thereby improving the reliability and stability of data transmission. In addition, by setting a data comparison delay threshold and comparing data in multiple transmission methods, data delay problems can be discovered and corrected in a timely manner, ensuring the real-time and accuracy of data.

[0071] Example 5

[0072] Based on Example 1, this example aims to judge the working status of employees, predict potential dangers, and build a factory operation model based on the analysis results, including:

[0073] S41, obtaining the target unit in motion determined in step S02;

[0074] S42, determining which production step in the factory operation model the specific area obtained in step S02 is;

[0075] S43. Based on the motion analysis of the current target unit, the target unit is compared with the preset safe execution action library in the current production step, a training set is generated from the data, and whether the target unit is safe is given based on the comparison.

[0076] Furthermore, the training set obtained in step S04 is used to train the plant operation model to update the model form.

[0077] In the above technology, based on the determined target units and specific areas in motion, the data can be accurately mapped to the production steps in the factory operation model.

[0078] By comparing with the preset safe execution action library, it is possible to determine whether the target unit is safe, providing a basis for predicting potential dangerous situations. The obtained training set is used for training the factory operation model, which can continuously update the model form and improve the accuracy and adaptability of the model.

[0079] Through continuous model training and optimization, it can better meet the high requirements of smart factories for data collection and management, and improve factory production efficiency and safety.

[0080] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0085] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0086] Processor, memory, communications interface and bus;

[0087] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0088] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0089] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0090] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Although the embodiment of this specification provides the method operation steps described in the embodiment or flow chart, more or less operation steps can be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same one or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the process and / or box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0092] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. A smart factory data collection and management method, characterized in that: The following steps are involved: S01. Use factory monitors to capture real-time animation data of people in the factory and operating status data of production equipment; S02, preliminarily screening, cleaning and formatting the collected data to form a data package; S03, using a multi-transfer method to transmit the data packet to the terminal, and each transfer node is responsible for data delay detection and correction; S04. After receiving the data, the terminal uses artificial intelligence algorithms to conduct in-depth analysis to determine the work status of employees, predict potential dangerous situations, and build a factory operation model based on the analysis results.

2. A smart factory data collection and management method according to claim 1, characterized in that: The step S01 captures the animation data of the active personnel in the factory and the operation status data of the production equipment, including: S11, using an AI image recognition system, configured to be able to capture video frames in real time and convert them into animation data; S12. Use algorithms to identify employee images in the video, extract the movement trajectory, posture changes, and operating behaviors of the identified units, and form key information data.

3. The method for data collection and management of a smart factory according to claim 1, characterized in that: The preliminary screening and cleaning of the collected data in step S02 includes: S21, using an ant colony algorithm to quickly locate and identify valid data units in the operating status data according to a system preset project target to obtain a target unit; S22, using a diffusion algorithm to determine the outer range of valid data, thereby determining a specific area of ​​the image to be processed; S23, using a greedy algorithm to maximize the determination of the boundaries of a specific area, thereby aligning the specific area and completing the partitioning; S24, screening the same specific areas in each frame of the image based on the TF-IDF similarity algorithm, retaining the data in the specific area with the highest matching degree with the target unit feature library, thereby determining the blur action of all target units in each frame.

4. The method for data collection and management of a smart factory according to claim 1, characterized in that: The step S02 of formatting the fuzzy actions obtained after preliminary screening and cleaning includes: S25, acquiring the blurred action of each frame and performing image denoising and sharpening respectively to obtain edge contour data sufficient for identifying the action posture; S26, extracting spatial features from edge contour data according to a convolutional neural network model to obtain motion trajectory point data about limbs; S27, extracting the motion trajectory point data of the limbs of the continuous frame images within the predetermined time window period by using the long short-term memory network model, thereby obtaining the motion trajectory point data connection line of each frame; S28, comparing the motion trajectory point data connection lines in the continuous frame images with the trajectory point data connection lines map pre-stored in the system, giving the execution action of the current target unit, and judging whether it is in motion.

5. The method for data collection and management of a smart factory according to claim 1, characterized in that: The data delay detection and correction in step S03 includes: S31, creating multiple data storage transfer stations, and the multiple transfer stations transmit data to the monitor through at least three data transmission methods: wireless network, local area network and radio; S32, setting a data comparison delay threshold based on the communication properties of the wireless network, local area network and radio; S33, and compare the data received by the plurality of transfer stations within the threshold. If the data transmitted by at least two data transmission modes are consistent, there is no error; if there is no data consistency, actively generate feedback and notify the back-end personnel to conduct investigation.

6. A smart factory data collection and management method according to claim 5, characterized in that: In the step S33, if there are at least two data transmission modes with consistent data, the consistent data will be marked, and the co-location data given by a delayed data transmission mode will be compared with the historical data of the above two types of data transmission modes, and it will be determined that there is only one data in the historical data that is the same as the co-location data. The delay factor is determined based on the time difference between the identical data and the consistent data, and correction is made to make the data of the three data transmission modes consistent.

7. The method for data collection and management of a smart factory according to claim 1, characterized in that: The step S04 of judging the working status of employees, predicting potential dangers, and building a factory operation model based on the analysis results includes: S41, obtaining the target unit in motion determined in step S02; S42, determining which production step in the factory operation model the specific area obtained in step S02 is; S43. Based on the motion analysis of the current target unit, the motion is compared with the preset safe execution action library in the current production step, a training set is generated from the data, and whether the target unit is safe is given based on the comparison.

8. A smart factory data collection and management method according to claim 7, characterized in that: The training set obtained in step S04 is used to train the plant operation model to update the model form.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the smart factory data collection and management method described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart factory data collection and management method described in any one of claims 1 to 8 are implemented.

Images