Iron and steel enterprise field auditing method and system

Abstract

The invention relates to an iron and steel enterprise site auditing method and system. The method comprises the following steps: acquiring a monitoring image of an iron and steel enterprise site; performing denoising on the monitoring image to obtain a denoised monitoring image; performing image enhancement on the denoised monitoring image to obtain an enhanced monitoring image; marking unqualified behaviors in the enhanced monitoring image to form a training sample; inputting the marked training sample into a deep learning network for training to obtain an auditing model; and completing identification of the on-site unqualified behavior of the iron and steel enterprise by using the auditing model. According to the invention, by using the deep learning technology, the on-site unqualified behavior of the iron and steel enterprise can be automatically identified without human intervention, and the early warning information can be timely sent out. Therefore, the field management efficiency of iron and steel enterprises is improved, and omissions caused by manual auditing are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of on-site audit of steel enterprises, and in particular to an on-site audit method and system for steel enterprises. Background Art

[0002] On-site audits of steel enterprises mainly refer to the audits of the steel plant's product development, process control, process equipment, testing capabilities, production environment, employee quality, supply capabilities, service capabilities, costs and other system contents. It is an evaluation to ensure stable production conditions for product quality. On-site audits are a systematic work. The audit process includes but is not limited to on-site visits, announcement of audit results, rectification of non-conformities and other links. The audit content also varies according to different technical requirements of users and has personalized characteristics. Therefore, in order to achieve efficient advancement of the audit process and quickly gain user recognition, it is necessary to maximize the efficiency of the audit work. Summary of the invention

[0003] In order to solve the above problems, the purpose of the embodiments of the present invention is to provide a steel enterprise on-site audit method and system.

[0004] A method for on-site audit of a steel enterprise, comprising:

[0005] Step 1: Obtain monitoring images of the steel enterprise site;

[0006] Step 2: De-noising the surveillance image to obtain a denoised surveillance image;

[0007] Step 3: Perform image enhancement on the denoised surveillance image to obtain an enhanced surveillance image;

[0008] Step 4: marking unqualified behaviors in the enhanced monitoring image to form training samples;

[0009] Step 5: Input the labeled training samples into the deep learning network for training to obtain the audit model;

[0010] Step 6: Use the audit model to identify non-conforming behaviors on site of the steel enterprise.

[0011] Preferably, the step 2: denoising the surveillance image to obtain a denoised surveillance image comprises:

[0012] The surveillance image is denoised based on a Gaussian function to obtain a denoised surveillance image; wherein the denoising formula is:

[0013]

[0014] Where I′(i,j) is the denoised surveillance image, H(i,j,σ) is the Gaussian kernel function, I(i,j) is the original surveillance image, σ is the standard deviation of the Gaussian kernel function, and the size of the Gaussian kernel is (2p+1)(2p+1).

[0015] Preferably, the step 3: performing image enhancement on the denoised surveillance image to obtain an enhanced surveillance image comprises:

[0016] Converting the denoised surveillance image into a grayscale image;

[0017] The grayscale image is subjected to histogram equalization processing to obtain an enhanced monitoring image.

[0018] Preferably, step 5: inputting the labeled training samples into the deep learning network for training to obtain the audit model includes:

[0019] The training samples are input into the deep learning network for training to obtain the audit model; wherein the loss function used in the process of training the deep learning network is:

[0020]

[0021] Among them, Loss is the value of the loss function, n is the number of samples, y i is the actual label of the i-th sample, The labels predicted by the deep learning network.

[0022] The present invention also provides a steel enterprise on-site audit system, comprising:

[0023] Monitoring image acquisition module, used to acquire monitoring images of steel enterprise sites;

[0024] A denoising module, used for denoising the surveillance image to obtain a denoised surveillance image;

[0025] An enhancement module, used for performing image enhancement on the denoised surveillance image to obtain an enhanced surveillance image;

[0026] A labeling module, used for labeling unqualified behaviors in the enhanced monitoring image to form training samples;

[0027] The training module is used to input the labeled training samples into the deep learning network for training to obtain the audit model;

[0028] The audit module is used to use the audit model to complete the identification of unqualified behaviors on site of the steel enterprise.

[0029] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned on-site audit method for a steel enterprise.

[0030] The present invention also provides a computer-readable storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned on-site audit method for a steel enterprise are implemented.

[0031] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] The present invention relates to a steel enterprise on-site audit method and system. Compared with the prior art, the present invention can automatically identify unqualified behaviors on-site in steel enterprises without human intervention by using deep learning technology, and issue early warning information in a timely manner. This improves the efficiency of on-site management of steel enterprises and reduces omissions in human audits.

[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 This is a flow chart of an on-site audit method for a steel enterprise in an embodiment provided by the present invention. DETAILED DESCRIPTION

[0036] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0037] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0038] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] See also Figure 1 , a steel enterprise on-site audit method, comprising:

[0040] Step 1: Obtain monitoring images of the steel enterprise site;

[0041] Step 2: De-noising the surveillance image to obtain a denoised surveillance image;

[0042] Furthermore, step 2 includes:

[0043] The surveillance image is denoised based on a Gaussian function to obtain a denoised surveillance image; wherein the denoising formula is:

[0044]

[0045] Where I′(i,j) is the denoised surveillance image, H(i,j,σ) is the Gaussian kernel function, I(i,j) is the original surveillance image, σ is the standard deviation of the Gaussian kernel function, and the size of the Gaussian kernel is (2p+1)(2p+1).

[0046] The present invention is based on the Gaussian function, and by sequentially traversing each pixel of the image, the neighboring pixels are weighted averaged, so that each pixel value of the image is replaced by the weighted average value of itself and the surrounding pixels, and the weight of the pixel farther from the center pixel is smaller. In this way, the main features of the image can be retained while weakening the influence of noise.

[0047] Step 3: Perform image enhancement on the denoised surveillance image to obtain an enhanced surveillance image;

[0048] Furthermore, step 3 includes:

[0049] Converting the denoised surveillance image into a grayscale image;

[0050] The grayscale image is subjected to histogram equalization processing to obtain an enhanced monitoring image.

[0051] Step 4: marking unqualified behaviors in the enhanced monitoring image to form training samples;

[0052] Step 5: Input the labeled training samples into the deep learning network for training to obtain the audit model;

[0053] In step 5, the training samples are input into the deep learning network for training to obtain the audit model; wherein the loss function used in the process of training the deep learning network is:

[0054]

[0055] Among them, Loss is the value of the loss function, n is the number of samples, y i is the actual label of the i-th sample, The labels predicted by the deep learning network.

[0056] Step 6: Use the audit model to identify non-conforming behaviors on site of the steel enterprise.

[0057] It should be noted that when marking samples, the present invention needs to divide the on-site marking work of steel enterprise users into levels according to their responsibilities, among which product R&D personnel, sales personnel, financial personnel, management personnel, skilled operators, etc. are the first level, and they each need to mark unqualified behaviors during the work process.

[0058] The team leaders and group leaders of each work section, audit group, product group, sales group, and financial group are the second level. Their main responsibilities are: completing the preparation of audit materials in the area they are responsible for and summarizing them, supervising, inspecting and confirming the content of the materials; organizing rectification in the area they are responsible for for audit non-conformities, and submitting rectification plans and rectification results.

[0059] By using deep learning technology, the present invention can automatically identify unqualified behaviors on the site of steel enterprises without human intervention and issue early warning information in a timely manner. This improves the efficiency of on-site management of steel enterprises and reduces omissions in human audits.

[0060] The present invention also provides a steel enterprise on-site audit system, comprising:

[0061] Monitoring image acquisition module, used to acquire monitoring images of steel enterprise sites;

[0062] A denoising module, used for denoising the surveillance image to obtain a denoised surveillance image;

[0063] An enhancement module, used for performing image enhancement on the denoised surveillance image to obtain an enhanced surveillance image;

[0064] A labeling module, used for labeling unqualified behaviors in the enhanced monitoring image to form training samples;

[0065] The training module is used to input the labeled training samples into the deep learning network for training to obtain the audit model;

[0066] The audit module is used to use the audit model to complete the identification of unqualified behaviors on site of the steel enterprise.

[0067] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and is characterized in that when the computer program is executed by the processor, the steps in the above-mentioned on-site audit method for a steel enterprise are implemented. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the on-site audit method for a steel enterprise described in the above-mentioned technical solution, and are not elaborated herein.

[0068] The present invention also provides 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 in the above-mentioned on-site audit method for a steel enterprise are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the on-site audit method for a steel enterprise described in the above-mentioned technical solution, which will not be repeated here.

[0069] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A steel enterprise on-site audit method, characterized in that: include: Step 1: Obtain monitoring images of the steel enterprise site; Step 2: De-noising the surveillance image to obtain a denoised surveillance image; Step 3: Perform image enhancement on the denoised surveillance image to obtain an enhanced surveillance image; Step 4: marking unqualified behaviors in the enhanced monitoring image to form training samples; Step 5: Input the labeled training samples into the deep learning network for training to obtain the audit model; Step 6: Use the audit model to identify non-conforming behaviors on site of the steel enterprise.

2. A steel enterprise on-site audit method according to claim 1, characterized in that: The step 2: denoising the surveillance image to obtain a denoised surveillance image, comprising: The surveillance image is denoised based on a Gaussian function to obtain a denoised surveillance image; wherein the denoising formula is: Where I′(i,j) is the denoised surveillance image, H(i,j,σ) is the Gaussian kernel function, I(i,j) is the original surveillance image, σ is the standard deviation of the Gaussian kernel function, and the size of the Gaussian kernel is (2p+1)(2p+1).

3. A steel enterprise on-site audit method according to claim 2, characterized in that: The step 3: performing image enhancement on the denoised surveillance image to obtain an enhanced surveillance image, comprises: Converting the denoised surveillance image into a grayscale image; The grayscale image is subjected to histogram equalization processing to obtain an enhanced monitoring image.

4. A steel enterprise on-site audit method according to claim 3, characterized in that: Step 5: Input the labeled training samples into the deep learning network for training to obtain the audit model, including: The training samples are input into the deep learning network for training to obtain the audit model; wherein the loss function used in the process of training the deep learning network is: Among them, Loss is the value of the loss function, n is the number of samples, y i is the actual label of the i-th sample, The labels predicted by the deep learning network.

5. A steel enterprise on-site audit system, characterized in that: include: Monitoring image acquisition module, used to acquire monitoring images of steel enterprise sites; A denoising module, used for denoising the surveillance image to obtain a denoised surveillance image; An enhancement module, used for performing image enhancement on the denoised surveillance image to obtain an enhanced surveillance image; A labeling module, used for labeling unqualified behaviors in the enhanced monitoring image to form training samples; The training module is used to input the labeled training samples into the deep learning network for training to obtain the audit model; The audit module is used to use the audit model to complete the identification of unqualified behaviors on site of the steel enterprise.

6. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of the on-site audit method for a steel enterprise according to any one of claims 1 to 4 are implemented.

7. 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 on-site audit method for a steel enterprise as claimed in any one of claims 1 to 4 are implemented.

Images