Production scheduling method, system and equipment based on industrial internet of things, and medium

Abstract

The invention discloses a production scheduling method, system and device based on the industrial Internet of Things and a medium, and relates to the technical field of the industrial Internet of Things, and the method comprises the steps: obtaining the image data of a target region, and obtaining the dust space distribution data of the target region according to the image data; dividing the target area according to the dust space distribution data to obtain at least one concentration gradient area; determining at least one calling-out area and at least one calling-in area according to the dust concentration and preset concentration; the concentration gradient region comprises the at least one callout region and the at least one callout region; determining a target callout device corresponding to the at least one callout area and a target callout area corresponding to the target callout device according to the processing rate data, the dust concentration and a preset concentration; and obtaining a production scheduling instruction according to the target callout device and the target callout area. The method has the effect of improving the safety of the production environment.

Description

Technical Field

[0001] The present application relates to the technical field of industrial Internet of Things, and in particular to a production scheduling method, system, equipment and medium based on the industrial Internet of Things. Background Art

[0002] In modern industrial production, dust is a common and non-negligible environmental problem. With the increasing degree of automation and mechanization, many factories produce a large amount of fine particles in the production process. These dusts not only affect product quality, but also pose a serious threat to the health and safety of factory employees. Dust is generated from a wide range of sources, including material processing, transportation and storage, especially in some wood processing, mining, chemical and pharmaceutical industries, where dust concentrations often exceed safety limits.

[0003] Dust has various components, including metal particles, non-metallic minerals, chemicals and biological dust. When these components are suspended in the air, they are easily inhaled by workers. Long-term exposure to dust may lead to respiratory diseases, skin diseases, and even more serious occupational diseases. In addition, some types of dust are highly flammable and explosive. Once mixed with air and reaching a certain concentration, it may cause fire or explosion, posing a huge safety hazard.

[0004] At present, although there are more and more control measures for dust, the dust concentration in many factories is still at a high level due to factors such as aging equipment, poor management, and poor ventilation in the workplace. Especially during peak hours or certain specific production links, the rapid increase in dust concentration may even exceed the monitoring range, which poses a severe challenge to the safety of the production environment. Therefore, the current dust concentration monitoring data shows that the production environment safety and the intelligent level of the production process in many factories are low, and more effective control measures are urgently needed to ensure the health of employees and work safety. Summary of the invention

[0005] In order to improve the security of the production environment, the present application provides a production scheduling method, system, device and medium based on the industrial Internet of Things.

[0006] In the first aspect, the present application provides a production scheduling method based on the industrial Internet of Things, which adopts the following technical solutions:

[0007] The production scheduling method based on the industrial Internet of Things is applied to the industrial Internet of Things system, wherein the industrial Internet of Things system includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication. The method is executed by the management platform and includes:

[0008] Acquire image data of a target area, and acquire dust spatial distribution data of the target area according to the image data;

[0009] Dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area;

[0010] Acquire the dust concentration of the at least one concentration gradient region, and determine at least one adjustment-out region and at least one adjustment-in region according to the dust concentration and a preset concentration; the concentration gradient region includes the at least one adjustment-out region and the at least one adjustment-in region;

[0011] Acquire processing rate data corresponding to the at least one call-out area, the processing rate data including processing rates of each device in the at least one call-out area, and determine a target call-out device corresponding to the at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, the dust concentration and a preset concentration;

[0012] A production scheduling instruction is acquired according to the target transfer-out equipment and the target transfer-in area, so as to transfer the target transfer-out equipment corresponding to the at least one transfer-out area into the target transfer-in area.

[0013] By adopting the above technical solution, the image data of the target area is obtained, and the dust spatial distribution data of the target area is obtained according to the image data, and then the target area is divided according to the dust spatial distribution data to obtain at least one concentration gradient area, and then the dust concentration of at least one concentration gradient area is obtained, and at least one call-out area and at least one call-in area are determined according to the dust concentration and the preset concentration. The concentration gradient area includes at least one call-out area and at least one call-in area, and then the processing rate data corresponding to the at least one call-out area is obtained, and the target call-out device corresponding to the at least one call-out area and the target call-in area corresponding to the target call-out device are determined according to the processing rate data, the dust concentration and the preset concentration, and finally the production scheduling instruction is obtained according to the target call-out device and the target call-in area, so as to call the target call-out device corresponding to the at least one call-out area into the target call-in area; through the above method, during the processing process, each processing equipment can be moved and scheduled according to the dust concentration at each location of the target area, so as to ensure that the dust concentration at each location of the target area is at a safe level, thereby improving the safety of the production environment, and improving the intelligent and automated level of production, and meeting the dust management and control requirements under a specific production environment.

[0014] Optionally, the step of acquiring dust concentration data of the target area according to the image data includes:

[0015] Performing a preprocessing operation on the image data according to the image data to obtain a corresponding preprocessed image;

[0016] Extracting features of dust particles according to the preprocessed image to obtain corresponding dust particle feature data;

[0017] Acquire historical image data, and perform data annotation on the historical image data to obtain corresponding model training data;

[0018] Dividing the model training data into a training set and a test set according to a preset ratio, and training a pre-selected deep learning model according to the model training data to obtain a trained deep learning model;

[0019] Testing and verifying the trained deep learning model according to the test set to obtain a dust particle recognition model;

[0020] The dust particle characteristic data is input into the dust particle recognition model to obtain the dust spatial distribution data of the target area.

[0021] By adopting the above technical scheme, in order to obtain the dust spatial distribution data of the target area, the image data is first preprocessed according to the image data to obtain the corresponding preprocessed image, and then the dust particles are feature extracted according to the preprocessed image to obtain the corresponding dust particle feature data, and then the historical image data is obtained, and the historical image data is data annotated to obtain the corresponding model training data, and then the model training data is divided into a training set and a test set according to a preset ratio, and a pre-selected deep learning model is trained according to the model training data to obtain a trained deep learning model, and then the trained deep learning model is tested and verified according to the test set to obtain a dust particle recognition model, and finally the dust particle feature data is input into the dust particle recognition model to obtain the dust spatial distribution data of the target area.

[0022] Optionally, performing a preprocessing operation on the image data according to the image data to obtain a corresponding preprocessed image includes:

[0023] Performing denoising processing on the image data according to the image data to obtain image A;

[0024] Performing image enhancement on the image A according to the image A to obtain image B;

[0025] Image segmentation is performed on image B according to image B to obtain a corresponding preprocessed image.

[0026] By adopting the above technical solution, in order to obtain appropriate preprocessing, the image data is first denoised according to the image data to obtain image A, and then image A is enhanced according to image A to obtain image B, and finally image B is segmented according to image B to obtain the corresponding preprocessed image.

[0027] Optionally, the step of dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area includes:

[0028] Extracting corresponding image features according to the image data, the image features including color features, brightness features and texture features, converting the image features into point cloud data according to the image features, and constructing a three-dimensional model of the target area according to the point cloud data;

[0029] Acquiring a preset grid division accuracy, and performing grid division on the target area according to the three-dimensional model and the grid division accuracy to obtain grid data corresponding to the three-dimensional model;

[0030] Determine dust particle data of each grid according to the dust spatial distribution data and the grid data; the dust particle data includes the number of dust particles and the size of dust particles;

[0031] Determine the dust particle density of each grid according to the dust particle data and the grid division accuracy, and perform cluster analysis on each grid according to the dust particle density to obtain a grid clustering result of each grid;

[0032] The grids are merged according to the grid clustering result to obtain at least one concentration gradient region.

[0033] By adopting the above technical solution, in order to obtain at least one concentration gradient area, firstly extract the corresponding image features according to the image data, the image features include color features, brightness features and texture features, and convert the image features into point cloud data according to the image features, and build a three-dimensional model of the target area according to the point cloud data, then obtain the preset grid division accuracy, and mesh the target area according to the three-dimensional model and the grid division accuracy to obtain the grid data corresponding to the three-dimensional model, and then determine the dust particle data of each grid according to the dust spatial distribution data and the grid data. The dust particle data includes the number of dust particles and the size of dust particles, and then determine the dust particle density of each grid according to the dust particle data and the grid division accuracy, and perform cluster analysis on each grid according to the dust particle density to obtain the grid clustering results of each grid, and finally merge each grid according to the grid clustering results to obtain at least one concentration gradient area.

[0034] Optionally, the step of determining at least one adjusted-out area and at least one adjusted-in area according to the dust concentration and a preset concentration includes:

[0035] For each of the at least one concentration gradient region, obtaining a target dust concentration of the concentration gradient region according to the dust concentration, and determining whether the target dust concentration is greater than a preset concentration according to the target dust concentration and a preset concentration;

[0036] If so, the concentration gradient region is used as a call-out region;

[0037] If not, the concentration gradient region is used as the adjustment region.

[0038] By adopting the above technical solution, in order to determine the adjustment-out area and the adjustment-in area, for each concentration gradient area in at least one concentration gradient area, the target dust concentration of the concentration gradient area is obtained according to the dust concentration, and it is judged whether the target dust concentration is greater than the preset concentration according to the target dust concentration and the preset concentration. If the target dust concentration is greater than the preset concentration, the concentration gradient area is used as the adjustment-out area. If the target dust concentration is not greater than the preset concentration, the concentration gradient area is used as the adjustment-out area.

[0039] Optionally, the step of determining a target call-out device corresponding to the at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, the dust concentration and a preset concentration includes:

[0040] For each of the at least one call-out area, determining a processing rate ratio corresponding to each of the processing equipment in the call-out area according to the processing rate data;

[0041] Determine a single dust concentration corresponding to each of the processing equipment in the transfer-out area according to the processing rate ratio and the dust concentration;

[0042] Acquire the dust concentration of the adjusted-out area corresponding to each adjusted-out area according to the dust concentration, and determine the dust concentration difference of the adjusted-out area corresponding to each adjusted-out area according to the dust concentration of the adjusted-out area and the preset concentration;

[0043] Screening each of the processing equipment in each of the transfer-out areas according to the difference between the single dust concentration and the dust concentration in the transfer-out area, and obtaining the target transfer-out equipment corresponding to each of the transfer-out areas;

[0044] A target call-in area corresponding to the target call-out device is determined according to the target call-out device, the dust concentration and a preset concentration.

[0045] By adopting the above technical scheme, in order to determine the target call-in area corresponding to the target call-out equipment, for each call-out area in at least one call-out area, the processing rate ratio corresponding to each processing equipment in the call-out area is determined according to the processing rate data, and then the single dust concentration corresponding to each processing equipment in the call-out area is determined according to the processing rate ratio and the dust concentration, and then the call-out area dust concentration corresponding to each call-out area is obtained according to the dust concentration, and the call-out area dust concentration difference corresponding to each call-out area is determined according to the call-out area dust concentration and the preset concentration, and then the various processing equipment in each call-out area is screened according to the single dust concentration and the call-out area dust concentration difference to obtain the target call-out equipment corresponding to each call-out area, and finally the target call-in area corresponding to the target call-out equipment is determined according to the target call-out equipment, the dust concentration and the preset concentration.

[0046] Optionally, the step of determining the target call-in area corresponding to the target call-out device according to the target call-out device, the dust concentration and a preset concentration includes:

[0047] For each of the at least one transferred-in area, obtaining a transferred-in area dust concentration corresponding to the transferred-in area according to the dust concentration, and determining a transferred-in area dust concentration difference corresponding to the transferred-in area according to the transferred-in area dust concentration and the preset concentration;

[0048] The target dust concentration corresponding to each target call-out device is obtained according to the single dust concentration, and the target call-in area corresponding to each target call-out device is determined from the at least one to-be-called area according to the target dust concentration and the dust concentration difference of the call-in area.

[0049] By adopting the above technical scheme, in order to determine the target call-in area corresponding to the target call-out device, for each call-in area in at least one call-in area, the call-in area dust concentration corresponding to the call-in area is obtained according to the dust concentration, and the call-in area dust concentration difference corresponding to the call-in area is determined according to the call-in area dust concentration and the preset concentration, and then the target dust concentration corresponding to each target call-out device is obtained according to the single dust concentration, and the target call-in area corresponding to each target call-out device is determined from at least one area to be called in according to the target dust concentration and the call-in area dust concentration difference.

[0050] In the second aspect, the present application also provides a production scheduling system based on the industrial Internet of Things, which adopts the following technical solutions:

[0051] The production scheduling system based on the industrial Internet of Things includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication, and the management platform is configured with:

[0052] An image data processing module, used to obtain image data of a target area, and obtain dust spatial distribution data of the target area according to the image data;

[0053] A target area division module, used for dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area;

[0054] a scheduling area determination module, configured to obtain the dust concentration of the at least one concentration gradient area, and determine at least one outgoing area and at least one incoming area according to the dust concentration and a preset concentration; the concentration gradient area includes the at least one outgoing area and the at least one incoming area;

[0055] a call-out device determination module, configured to obtain processing rate data corresponding to the at least one call-out area, and determine a target call-out device corresponding to the at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, the dust concentration and a preset concentration;

[0056] The production scheduling module is used to obtain a production scheduling instruction according to the target outgoing device and the target incoming area, so as to transfer the at least one outgoing area into the target incoming area corresponding to the target outgoing device.

[0057] In a third aspect, the present application also provides a computer device, which adopts the following technical solution:

[0058] A computer device comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method described in the first aspect when executing the computer program.

[0059] In a fourth aspect, the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0060] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the method described in the first aspect.

[0061] In summary, the present application includes at least the following beneficial technical effects: acquiring image data of a target area, and acquiring dust spatial distribution data of the target area according to the image data, and then dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area, and then acquiring the dust concentration of at least one concentration gradient area, and determining at least one call-out area and at least one call-in area according to the dust concentration and the preset concentration. The concentration gradient area includes at least one call-out area and at least one call-in area, and then acquiring processing rate data corresponding to at least one call-out area, and determining a target call-out device corresponding to at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, the dust concentration and the preset concentration, and finally acquiring a production scheduling instruction according to the target call-out device and the target call-in area, so as to call at least one call-out area corresponding to the target call-out device into the target call-in area; through the above method, during the processing process, each processing equipment can be moved and scheduled according to the dust concentration at each location of the target area, so as to ensure that the dust concentration at each location of the target area is at a safe level, thereby improving the safety of the production environment, and improving the intelligent and automated level of production, and meeting the dust management and control requirements under a specific production environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic diagram of the overall process of an embodiment of the present application.

[0063] Figure 2 It is a structural diagram of one application scenario of the system of an embodiment of the present application.

[0064] Figure 3 It is a structural diagram of another application scenario of the system of an embodiment of the present application.

[0065] Figure 4 It is a structural block diagram of the computer device of the present application. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-4 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0067] The embodiment of the present application discloses a production scheduling method based on industrial Internet of Things.

[0068] Reference Figure 1 The production scheduling method based on industrial Internet of Things is applied to the industrial Internet of Things system. The industrial Internet of Things system includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication. The method is executed by the management platform and includes:

[0069] Step S11, acquiring image data of the target area, and acquiring dust spatial distribution data of the target area according to the image data.

[0070] Step S12, dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area.

[0071] Step S13, obtaining the dust concentration of at least one concentration gradient area, and determining at least one adjusted-out area and at least one adjusted-in area according to the dust concentration and a preset concentration.

[0072] The concentration gradient region includes at least one outgoing region and at least one incoming region.

[0073] It can be understood that the dust concentration at various locations in the concentration gradient area can be considered to be the same or similar, that is, for each concentration gradient area, the dust concentration in the concentration gradient area varies within a certain concentration range; the transfer-out area is a concentration gradient area where the processing equipment needs to be transferred out, and the transfer-in area is a concentration gradient area where the processing equipment can be transferred in.

[0074] Step S14, obtaining processing rate data corresponding to at least one call-out area, and determining a target call-out device corresponding to at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, dust concentration and preset concentration.

[0075] The processing rate data includes at least one processing rate of each device in the calling area.

[0076] Step S15, obtaining a production scheduling instruction according to the target transfer-out equipment and the target transfer-in area, so as to transfer the target transfer-out equipment corresponding to at least one transfer-out area into the target transfer-in area.

[0077] In the above embodiment, image data of the target area is obtained, and dust spatial distribution data of the target area is obtained according to the image data, and then the target area is divided according to the dust spatial distribution data to obtain at least one concentration gradient area, and then the dust concentration of at least one concentration gradient area is obtained, and at least one call-out area and at least one call-in area are determined according to the dust concentration and the preset concentration. The concentration gradient area includes at least one call-out area and at least one call-in area, and then the processing rate data corresponding to the at least one call-out area is obtained, and the target call-out device corresponding to the at least one call-out area and the target call-in area corresponding to the target call-out device are determined according to the processing rate data, the dust concentration and the preset concentration, and finally the production scheduling instruction is obtained according to the target call-out device and the target call-in area, so as to call the target call-out device corresponding to the at least one call-out area into the target call-in area; in the above manner, during the processing process, each processing equipment can be moved and scheduled according to the dust concentration at each location of the target area, so as to ensure that the dust concentration at each location of the target area is at a safe level, thereby improving the safety of the production environment, and improving the intelligent and automated level of production, and meeting the dust management and control requirements under a specific production environment.

[0078] As a further implementation of the production scheduling method, the step of acquiring dust concentration data of the target area according to the image data includes:

[0079] Step S21, performing a preprocessing operation on the image data according to the image data to obtain a corresponding preprocessed image.

[0080] It should be noted that the preprocessing operation is an image processing technology. Image preprocessing includes image scaling, image normalization, image enhancement, edge detection, and denoising. Through the preprocessing operation, the original image can be effectively preprocessed to obtain a processed image that is more suitable for subsequent analysis or training. Different application scenarios usually require different preprocessing combinations. The specific selection and parameter settings should be adjusted according to actual needs.

[0081] Step S22: extracting features of dust particles according to the preprocessed image to obtain corresponding dust particle feature data.

[0082] Step S23, acquiring historical image data, and annotating the historical image data to obtain corresponding model training data.

[0083] It should be noted that the historical image data is an image containing dust in the air, the data annotation object is the dust in the image, and the annotation type is the attribute of the dust, such as the attribute of the dust particles (size, density, etc. of the dust particles).

[0084] Step S24, divide the model training data into a training set and a test set according to a preset ratio, and train a pre-selected deep learning model according to the model training data to obtain a trained deep learning model.

[0085] It should be noted that the preset ratio is usually set according to actual needs, for example, the preset ratio is set to 7:3 or 8:2.

[0086] Step S25, testing and verifying the trained deep learning model according to the test set to obtain a dust particle recognition model.

[0087] Step S26, inputting the dust particle characteristic data into the dust particle recognition model to obtain the dust spatial distribution data of the target area.

[0088] In the above embodiment, in order to obtain the dust spatial distribution data of the target area, the image data is first preprocessed according to the image data to obtain the corresponding preprocessed image, and then the dust particles are feature extracted according to the preprocessed image to obtain the corresponding dust particle feature data, and then the historical image data is obtained, and the historical image data is data annotated to obtain the corresponding model training data, and then the model training data is divided into a training set and a test set according to a preset ratio, and a pre-selected deep learning model is trained according to the model training data to obtain a trained deep learning model, and then the trained deep learning model is tested and verified according to the test set to obtain a dust particle recognition model, and finally the dust particle feature data is input into the dust particle recognition model to obtain the dust spatial distribution data of the target area.

[0089] As a further implementation of the production scheduling method, performing a preprocessing operation on the image data according to the image data to obtain a corresponding preprocessed image includes:

[0090] Step S31, performing denoising processing on the image data according to the image data to obtain image A;

[0091] Step S32, performing image enhancement on image A according to image A to obtain image B;

[0092] Step S33, performing image segmentation on image B according to image B to obtain a corresponding preprocessed image.

[0093] In the above embodiment, in order to obtain appropriate preprocessing, the image data is first denoised according to the image data to obtain image A, and then image A is enhanced according to image A to obtain image B, and finally image B is segmented according to image B to obtain the corresponding preprocessed image.

[0094] As a further implementation of the production scheduling method, the step of dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area includes:

[0095] Step S41 , extracting corresponding image features according to the image data, converting the image features into point cloud data according to the image features, and constructing a three-dimensional model of the target area according to the point cloud data.

[0096] Among them, image features include color features, brightness features and texture features.

[0097] Step S42, obtaining a preset mesh division accuracy, and meshing the target area according to the three-dimensional model and the mesh division accuracy to obtain mesh data corresponding to the three-dimensional model.

[0098] It is understandable that meshing accuracy usually depends on the 3D model detail requirements and computing resources.

[0099] Step S43, determining dust particle data of each grid according to the dust spatial distribution data and the grid data.

[0100] The dust particle data includes the number of dust particles and the size of dust particles.

[0101] Step S44, determining the dust particle density of each grid according to the dust particle data and the grid division accuracy, and performing cluster analysis on each grid according to the dust particle density to obtain a grid clustering result of each grid.

[0102] It should be noted that in step S44, when performing cluster analysis, it is necessary to select a suitable clustering algorithm according to the characteristics of the data (i.e., dust particle density). Common clustering methods include K-means clustering, hierarchical clustering, DBSCAN, etc. K-means clustering is suitable for data with relatively uniform distribution and approximately spherical shape, hierarchical clustering is suitable for cluster analysis that requires a hierarchical structure, and DBSCAN is suitable for data with more noise or irregular shape; then the dust particle density data is standardized. If the density value ranges of different grids vary greatly, the clustering effect can be improved by standardization (such as Z-score standardization or Min-Max scaling), and then the number of clusters is determined (if necessary). For K-means clustering, the number of clusters (K) needs to be determined in advance. The K value can be assisted by methods such as the Elbow Method or Silhouette Score, and then cluster analysis is performed, that is, the dust particle density data is input into the selected clustering algorithm to perform cluster analysis. The clustering algorithm will automatically classify grids with the same or similar dust particle density into the same category, and then evaluate the clustering results by analyzing the clustering results, such as the center of each cluster, the number of grids in each category, the distribution, etc. At the same time, use evaluation indicators (such as silhouette coefficient) to evaluate the clustering effect, and then visualize the clustering results. For example, use visualization tools (such as scatter plots, cluster diagrams, etc.) to display the clustering results to help understand the distribution of dust particle density in different grids. Finally, output the clustering results, that is, record the cluster category to which each grid belongs, and organize it into a clustering result file so that the grids can be merged later in step S35.

[0103] Step S45, merging each grid according to the grid clustering result to obtain at least one concentration gradient region.

[0104] It can be understood that from step S44, the clustering result can be used to obtain the clustering category to which each grid belongs, and each category represents a group of grids with similar or similar dust particle density; then the grids are merged according to the preset merging criteria, for example: grids of the same clustering category are selected for merging, or a merging threshold is set, such as the average dust particle density difference between adjacent clustering grids is less than a certain value, thereby obtaining at least one concentration gradient region. After the merging is completed, these regions can be described by the average dust particle density of each region or the spatial range and shape of the region.

[0105] In the above embodiment, in order to obtain at least one concentration gradient region, the corresponding image features are first extracted according to the image data, and the image features include color features, brightness features and texture features, and the image features are converted into point cloud data according to the image features, and a three-dimensional model of the target area is constructed according to the point cloud data, and then the preset grid division accuracy is obtained, and the target area is grid-divided according to the three-dimensional model and the grid division accuracy to obtain the grid data corresponding to the three-dimensional model, and then the dust particle data of each grid is determined according to the dust spatial distribution data and the grid data. The dust particle data includes the number of dust particles and the size of dust particles, and then the dust particle density of each grid is determined according to the dust particle data and the grid division accuracy, and each grid is clustered according to the dust particle density. The grid clustering results of each grid are obtained, and finally the grids are merged according to the grid clustering results to obtain at least one concentration gradient region.

[0106] As a further implementation of the production scheduling method, the step of determining at least one transfer-out area and at least one transfer-in area according to the dust concentration and the preset concentration includes:

[0107] Step S51, for each concentration gradient area in at least one concentration gradient area, obtaining a target dust concentration of the concentration gradient area according to the dust concentration, and judging whether the target dust concentration is greater than the preset concentration according to the target dust concentration and the preset concentration.

[0108] Step S52: If yes, the concentration gradient area is used as the call-out area.

[0109] Specifically, if the target dust concentration is greater than a preset concentration, the concentration gradient area is used as an adjustment-out area.

[0110] Step S53: if not, the concentration gradient region is used as the input region.

[0111] Specifically, if the target dust concentration is not greater than a preset concentration, the concentration gradient area is used as an adjustment-out area.

[0112] It should be noted that, in this embodiment, when the target dust concentration is equal to the preset concentration, it is conceivable that the target dust concentration in a certain concentration gradient area may exceed the preset concentration at the next moment, and therefore also needs to be included in the scope of the adjustment area.

[0113] In the above embodiment, in order to determine the adjustment-out area and the adjustment-in area, for each concentration gradient area in at least one concentration gradient area, the target dust concentration of the concentration gradient area is obtained according to the dust concentration, and it is judged whether the target dust concentration is greater than the preset concentration according to the target dust concentration and the preset concentration. If the target dust concentration is greater than the preset concentration, the concentration gradient area is used as the adjustment-out area. If the target dust concentration is not greater than the preset concentration, the concentration gradient area is used as the adjustment-out area.

[0114] As a further implementation of the production scheduling method, the step of determining a target outgoing device corresponding to at least one outgoing area and a target incoming area corresponding to the target outgoing device according to the processing rate data, the dust concentration and the preset concentration includes:

[0115] Step S61: for each of the at least one call-out area, determining the processing rate ratio corresponding to each processing equipment in the call-out area according to the processing rate data.

[0116] Step S62, determining a single dust concentration corresponding to each processing equipment in the call-out area according to the processing rate ratio and the dust concentration.

[0117] Step S63, obtaining the dust concentration of the call-out area corresponding to each call-out area according to the dust concentration, and determining the dust concentration difference of the call-out area corresponding to each call-out area according to the dust concentration of the call-out area and the preset concentration.

[0118] Step S64, screening each processing equipment in each transfer-out area according to the difference between the single dust concentration and the dust concentration of the transfer-out area, and obtaining the target transfer-out equipment corresponding to each transfer-out area.

[0119] According to the difference between the single dust concentration and the dust concentration of the transfer-out area, each processing equipment in each transfer-out area is screened to obtain the target transfer-out equipment corresponding to each transfer-out area.

[0120] It should be noted that in step S54, screening is required according to pre-set screening criteria. For example, the outbound area includes areas A and B, and the inbound area includes area C. The equipment in the outbound area A includes a1 (corresponding to a single dust concentration of 20) and a2 (corresponding to a single dust concentration of 20). The equipment in the inbound area B includes b1 (corresponding to a single dust concentration of 10), b2 (corresponding to a single dust concentration of 20), and b3 (corresponding to a single dust concentration of 35). The equipment in the inbound area C includes c1 (corresponding to a single dust concentration of 35), c2 (corresponding to a single dust concentration of 25), and c3 (corresponding to a single dust concentration of 25). The dust concentration difference in the outbound areas is 30. Then when screening, for the call-out area A, any device between a1 and a2 can be used as the target call-out device; for the call-out area B, only b3 can be used as the target call-out device; for the call-in area C, c1 and c2 can be used as the target call-out devices, or c1 and c3 can be used as the target call-out devices. For the call-in area C, which method to choose can be set according to the actual situation.

[0121] Step S55, determining the target call-in area corresponding to the target call-out device according to the target call-out device, the dust concentration and the preset concentration.

[0122] In the above embodiment, in order to determine the target call-in area corresponding to the target call-out equipment, for each call-out area in at least one call-out area, the processing rate ratio corresponding to each processing equipment in the call-out area is determined according to the processing rate data, and then the single dust concentration corresponding to each processing equipment in the call-out area is determined according to the processing rate ratio and the dust concentration, and then the call-out area dust concentration corresponding to each call-out area is obtained according to the dust concentration, and the call-out area dust concentration difference corresponding to each call-out area is determined according to the call-out area dust concentration and the preset concentration, and then the various processing equipment in each call-out area is screened according to the single dust concentration and the call-out area dust concentration difference to obtain the target call-out equipment corresponding to each call-out area, and finally the target call-in area corresponding to the target call-out equipment is determined according to the target call-out equipment, dust concentration and preset concentration.

[0123] As a further implementation of the production scheduling method, the step of determining the target input area corresponding to the target output device according to the target output device, the dust concentration and the preset concentration includes:

[0124] Step S71, for each of the at least one transferred-in area, obtain the transferred-in area dust concentration corresponding to the transferred-in area according to the dust concentration, and determine the transferred-in area dust concentration difference corresponding to the transferred-in area according to the transferred-in area dust concentration and a preset concentration.

[0125] Step S72, obtaining the target dust concentration corresponding to each target call-out device according to the single dust concentration, and determining the target call-in area corresponding to each target call-out device from at least one to-be-called area according to the target dust concentration and the difference between the dust concentration in the call-in area.

[0126] It should be noted that, assuming that the input area includes E and F areas, the dust concentration difference between the output areas corresponding to A and B is 30 and 50 respectively, assuming that the target output devices include x1, x2 and x3, and the target dust concentrations corresponding to x1, x2 and x3 are 10, 17 and 35. Then Scheme 1: The target input area corresponding to x1 and x2 is E, and the target input area corresponding to x3 is F, that is, x1 and x2 are transferred to the E area, and x3 is transferred to the F area; then Scheme 2: The target input area corresponding to x1 and x3 is F, and the target input area corresponding to x2 is E, that is, x1 and x3 are transferred to the F area, and x2 is transferred to the E area. Which scheme to use is usually set according to actual needs, such as randomly selecting one, or selecting the one that takes the least time to call.

[0127] In the above embodiment, in order to determine the target call-in area corresponding to the target call-out device, for each call-in area of ​​at least one call-in area, the call-in area dust concentration corresponding to the call-in area is obtained according to the dust concentration, and the call-in area dust concentration difference corresponding to the call-in area is determined according to the call-in area dust concentration and the preset concentration, and then the target dust concentration corresponding to each target call-out device is obtained according to the single dust concentration, and the target call-in area corresponding to each target call-out device is determined from at least one area to be called in according to the target dust concentration and the call-in area dust concentration difference.

[0128] The embodiment of the present application also discloses a production scheduling system based on the industrial Internet of Things.

[0129] refer to Figure 2 The production scheduling system based on the industrial Internet of Things includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication. The management platform is configured with:

[0130] An image data processing module is used to obtain image data of a target area, and obtain dust spatial distribution data of the target area according to the image data;

[0131] A target area division module is used to divide the target area according to the dust spatial distribution data to obtain at least one concentration gradient area;

[0132] A scheduling area determination module, used to obtain the dust concentration of at least one concentration gradient area, and determine at least one outgoing area and at least one incoming area according to the dust concentration and a preset concentration; the concentration gradient area includes at least one outgoing area and at least one incoming area;

[0133] A call-out device determination module, used to obtain processing rate data corresponding to at least one call-out area, and determine a target call-out device corresponding to at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, dust concentration and a preset concentration;

[0134] The production scheduling module is used to obtain a production scheduling instruction according to a target outgoing device and a target incoming area, so as to transfer the target outgoing device corresponding to at least one outgoing area into the target incoming area.

[0135] The overall framework of another application scenario of the production scheduling system based on industrial Internet of Things of this application is as follows Figure 3 As shown, it may include a user platform, a service platform, a management platform, a sensor network platform and an object platform that interact in sequence, forming a five-platform architecture based on the industrial Internet of Things. Among them, the management platform includes an image data processing module, a target area division module, a scheduling area determination module, a call-out equipment determination module and a production scheduling module; the service platform includes a service total database, n service sub-platforms and n service sub-databases, each service sub-platform can communicate with the corresponding service sub-database, and each service sub-database can communicate with the service total database; the sensor network platform includes a sensor total database and n sensor network sub-platforms, each sensor network sub-platform is provided with a sensor sub-database, and each sensor network sub-platform can communicate with the sensor total database.

[0136] Specifically, in another application scenario mentioned above, the production scheduling system based on the industrial Internet of Things includes a management platform, which is configured to: obtain image data of the target area, and obtain dust spatial distribution data of the target area based on the image data; divide the target area according to the dust spatial distribution data to obtain at least one concentration gradient area; obtain the dust concentration of the at least one concentration gradient area, and determine at least one call-out area and at least one call-in area based on the dust concentration and a preset concentration; the concentration gradient area includes the at least one call-out area and the at least one call-in area; obtain processing rate data corresponding to the at least one call-out area, and determine the target call-out device corresponding to the at least one call-out area and the target call-in area corresponding to the target call-out device based on the processing rate data, the dust concentration and the preset concentration; obtain production scheduling instructions based on the target call-out device and the target call-in area to call the target call-out device corresponding to the at least one call-out area into the target call-in area.

[0137] Through the interaction between the various functional platforms of the industrial Internet of Things-based production scheduling system based on the above three platforms or five platforms, a complete closed-loop information operation logic is established, ensuring the orderly operation of perception information and control information and realizing intelligent equipment management.

[0138] The production scheduling system based on industrial Internet of Things of the present invention can implement any one of the production scheduling methods based on industrial Internet of Things, and the specific working process of the production scheduling system based on industrial Internet of Things of the present invention can refer to the corresponding process in the above-mentioned production scheduling method based on industrial Internet of Things.

[0139] The embodiment of the present application also discloses a computer device.

[0140] refer to Figure 4 A computer device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, any of the above-mentioned production scheduling methods based on the industrial Internet of Things is implemented.

[0141] The embodiment of the present application also discloses a computer-readable storage medium.

[0142] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned production scheduling methods based on the industrial Internet of Things.

[0143] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0144] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A production scheduling method based on industrial Internet of Things, characterized in that: Applied to an industrial Internet of Things system, the industrial Internet of Things system includes a management platform, a sensor network platform and an object platform that are sequentially communicatively connected, and the method is executed by the management platform, including: Acquire image data of a target area, and acquire dust spatial distribution data of the target area according to the image data; Dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area; Acquire the dust concentration of the at least one concentration gradient region, and determine at least one adjustment-out region and at least one adjustment-in region according to the dust concentration and a preset concentration; the concentration gradient region includes the at least one adjustment-out region and the at least one adjustment-in region; Acquire processing rate data corresponding to the at least one call-out area, the processing rate data including processing rates of each processing equipment in the at least one call-out area, and determine a target call-out equipment corresponding to the at least one call-out area and a target call-in area corresponding to the target call-out equipment according to the processing rate data, the dust concentration and a preset concentration; A production scheduling instruction is acquired according to the target transfer-out equipment and the target transfer-in area, so as to transfer the target transfer-out equipment corresponding to the at least one transfer-out area into the target transfer-in area.

2. The production scheduling method based on industrial Internet of Things according to claim 1 is characterized in that: The step of acquiring dust concentration data of the target area according to the image data comprises: Performing a preprocessing operation on the image data according to the image data to obtain a corresponding preprocessed image; Extracting features of dust particles according to the preprocessed image to obtain corresponding dust particle feature data; Acquire historical image data, and annotate the historical image data to obtain corresponding model training data; Dividing the model training data into a training set and a test set according to a preset ratio, and training a pre-selected deep learning model according to the model training data to obtain a trained deep learning model; Testing and verifying the trained deep learning model according to the test set to obtain a dust particle recognition model; The dust particle characteristic data is input into the dust particle recognition model to obtain the dust spatial distribution data of the target area.

3. The production scheduling method based on industrial Internet of Things according to claim 2 is characterized in that: Performing a preprocessing operation on the image data according to the image data to obtain a corresponding preprocessed image includes: Performing denoising processing on the image data according to the image data to obtain image A; Performing image enhancement on the image A according to the image A to obtain image B; Image segmentation is performed on the image B according to the image B to obtain a corresponding preprocessed image.

4. The production scheduling method based on industrial Internet of Things according to claim 1 is characterized in that: The step of dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area includes: Extracting corresponding image features according to the image data, the image features including color features, brightness features and texture features, converting the image features into point cloud data according to the image features, and constructing a three-dimensional model of the target area according to the point cloud data; Acquiring a preset grid division accuracy, and performing grid division on the target area according to the three-dimensional model and the grid division accuracy to obtain grid data corresponding to the three-dimensional model; Determine dust particle data of each grid according to the dust spatial distribution data and the grid data; the dust particle data includes the number of dust particles and the size of dust particles; Determine the dust particle density of each grid according to the dust particle data and the grid division accuracy, and perform cluster analysis on each grid according to the dust particle density to obtain a grid clustering result of each grid; The grids are merged according to the grid clustering result to obtain at least one concentration gradient region.

5. The production scheduling method based on industrial Internet of Things according to claim 1 is characterized in that: The step of determining at least one transfer-out area and at least one transfer-in area according to the dust concentration and the preset concentration comprises: For each concentration gradient region of the at least one concentration gradient region, obtaining a target dust concentration of the concentration gradient region according to the dust concentration, and determining whether the target dust concentration is greater than a preset concentration according to the target dust concentration and a preset concentration; If so, the concentration gradient region is used as a call-out region; If not, the concentration gradient region is used as the adjustment region.

6. The production scheduling method based on industrial Internet of Things according to claim 1 is characterized in that: The step of determining the target call-out device corresponding to the at least one call-out area and the target call-in area corresponding to the target call-out device according to the processing rate data, the dust concentration and the preset concentration comprises: For each of the at least one call-out area, determining a processing rate ratio corresponding to each of the processing equipment in the call-out area according to the processing rate data; Determine a single dust concentration corresponding to each of the processing equipment in the transfer-out area according to the processing rate ratio and the dust concentration; Acquire the dust concentration of the adjusted-out area corresponding to each adjusted-out area according to the dust concentration, and determine the dust concentration difference of the adjusted-out area corresponding to each adjusted-out area according to the dust concentration of the adjusted-out area and the preset concentration; Screening each of the processing equipment in each of the transfer-out areas according to the difference between the single dust concentration and the dust concentration in the transfer-out area, and obtaining the target transfer-out equipment corresponding to each of the transfer-out areas; A target call-in area corresponding to the target call-out device is determined according to the target call-out device, the dust concentration and a preset concentration.

7. The production scheduling method based on industrial Internet of Things according to claim 6 is characterized in that: The step of determining the target call-in area corresponding to the target call-out device according to the target call-out device, the dust concentration and the preset concentration includes: For each of the at least one transferred-in area, obtaining a transferred-in area dust concentration corresponding to the transferred-in area according to the dust concentration, and determining a transferred-in area dust concentration difference corresponding to the transferred-in area according to the transferred-in area dust concentration and the preset concentration; The target dust concentration corresponding to each target call-out device is obtained according to the single dust concentration, and the target call-in area corresponding to each target call-out device is determined from the at least one to-be-called area according to the target dust concentration and the dust concentration difference of the call-in area.

8. The production scheduling system based on industrial Internet of Things is characterized by: It includes a management platform, a sensor network platform and an object platform which are connected in sequence, and the management platform is configured with: An image data processing module, used to obtain image data of a target area, and obtain dust spatial distribution data of the target area according to the image data; A target area division module, used for dividing the target area according to the dust spatial distribution data to obtain at least one concentration gradient area; a scheduling area determination module, configured to obtain the dust concentration of the at least one concentration gradient area, and determine at least one outgoing area and at least one incoming area according to the dust concentration and a preset concentration; the concentration gradient area includes the at least one outgoing area and the at least one incoming area; a call-out device determination module, configured to obtain processing rate data corresponding to the at least one call-out area, and determine a target call-out device corresponding to the at least one call-out area and a target call-in area corresponding to the target call-out device according to the processing rate data, the dust concentration and a preset concentration; The production scheduling module is used to obtain a production scheduling instruction according to the target outgoing device and the target incoming area, so as to transfer the at least one outgoing area into the target incoming area corresponding to the target outgoing device.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images