Shaft motion real-time monitoring method for equipment safety door

Abstract

The invention relates to the field of shaft motion state monitoring of equipment safety doors, in particular to a shaft motion real-time monitoring method for an equipment safety door, which comprises the following steps: S1, acquiring shaft motion real-time operation data of the equipment safety door; s2, establishing a shaft motion operation data classification model according to the shaft motion real-time operation data; s3, using the shaft motion operation data classification model to obtain a shaft motion real-time monitoring result, analyzing and processing various data of equipment safety door shaft motion step by step to establish a research and judgment model related to the shaft motion operation state, providing comparison data from different angles, avoiding output interference deviation caused by a single data source, and improving the accuracy of the shaft motion real-time monitoring result. Manpower is saved, and monitoring efficiency and accuracy of the equipment safety door are improved.

Description

Technical Field

[0001] The invention relates to the field of shaft motion state monitoring of equipment safety doors, and in particular to a shaft motion real-time monitoring method for equipment safety doors. Background Art

[0002] When reinforcing machines, covering film machines, PSA machines, etc. are in operation, their safety issues become the focus of protection. In order to prevent injuries caused by material splashing during machine operation, equipment safety doors are usually installed in the machine operation area. In traditional solutions, the monitoring of equipment safety doors relies on the status of the locking device to judge the opening and closing status of the door. However, the process production environment is complex, and various metals or conductors will cause the status of the locking device to be abnormal. Therefore, the status of the equipment safety door cannot be accurately grasped. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a real-time monitoring method for the axis movement of the equipment safety door. By processing and screening the related data of the equipment safety door, its axis movement state can be quickly and accurately obtained, and then the real-time opening and closing state of the equipment safety door can be obtained.

[0004] To achieve the above object, the present invention provides a method for real-time monitoring of the axis movement of a device safety door, comprising:

[0005] S1. Obtain the real-time operation data of the axis movement of the equipment safety door;

[0006] S2. establishing an axis motion operation data classification model according to the axis motion real-time operation data;

[0007] S3. Using the axis motion operation data classification model to obtain the axis motion real-time monitoring result.

[0008] Preferably, the step of obtaining the real-time operation data of the axis movement of the equipment safety door includes:

[0009] S1-1, obtaining the current time as the starting collection time t;

[0010] S1-2, obtaining the axis movement rotation angle data, axis movement straight line distance data and equipment safety door opening and closing distance data at the start collection time t;

[0011] S1-3, using the shaft movement rotation angle data, shaft movement straight distance data and equipment safety door opening and closing distance data to perform rational screening and processing to obtain the shaft movement real-time operation data.

[0012] Furthermore, the real-time operation data of the axis movement is obtained by rationally screening the axis movement rotation angle data, the axis movement linear distance data and the equipment safety door opening and closing distance data, including:

[0013] S1-3-1, respectively obtain the shaft movement rotation angle data, shaft movement straight line distance data and equipment safety door opening and closing distance data corresponding to time t-1 according to the shaft movement rotation angle data, shaft movement straight line distance data and equipment safety door opening and closing distance data;

[0014] S1-3-2, determine whether the axis movement rotation angle data at the starting acquisition time t is the same as the axis movement rotation angle data at time t-1, if so, output the axis movement rotation angle data at the starting acquisition time t, the axis movement straight-line distance data and the equipment safety door opening and closing distance data as the axis movement real-time operation data, otherwise, execute S1-3-3;

[0015] S1-3-3, determine whether the axis motion straight-line distance data at the starting acquisition time t is the same as the axis motion straight-line distance data at time t-1, if so, output the axis motion rotation angle data, axis motion straight-line distance data and equipment safety door opening and closing distance data at the starting acquisition time t as the axis motion real-time operation data, otherwise, execute S1-3-4;

[0016] S1-3-4. Determine whether the equipment safety door opening and closing distance data at the starting collection time t is the same as the equipment safety door opening and closing distance data at time t-1. If so, use the current time as the updated starting collection time t and return to S1-1. Otherwise, use the current time as the updated starting collection time t and return to S1-1.

[0017] Furthermore, establishing an axis motion operation data classification model according to the axis motion real-time operation data includes:

[0018] S2-1, acquiring corresponding historical real-time operation data of the axis movement according to the real-time operation data of the axis movement;

[0019] S2-2, using the historical axis motion real-time operation data to establish an axis motion operation status analysis model;

[0020] S2-3. Obtain an axis motion operation data classification model according to the axis motion operation state analysis model.

[0021] Furthermore, using the historical real-time operation data of the axis movement to establish an axis movement operation state analysis model includes:

[0022] S2-2-1, using the real-time operation data of the historical axis movement to establish a historical data set as a training set;

[0023] S2-2-2, using the training set as input, the axis motion operation state of the equipment safety door corresponding to the training set as output, using the number of operation state adjustment moments corresponding to the historical axis motion real-time operation data to establish a hidden layer, and training based on a deep learning multi-layer neural network to obtain an initial state analysis model;

[0024] S2-2-3, determine whether the number of training times corresponding to the current initial state analysis model is n-1, if so, output the current initial state analysis model as the axis motion operation state analysis model, otherwise, return to S2-2-2;

[0025] The operating state includes a normal state and an abnormal state, and n is the number of subsets in the training set.

[0026] Furthermore, obtaining an axis motion operation data classification model according to the axis motion operation state analysis model includes:

[0027] According to the axis motion operation state analysis model, a training set corresponding to an abnormal state is obtained as an abnormal node training set;

[0028] Using the abnormal node training set as input, the historical axis motion real-time operation data corresponding to the abnormal state of the abnormal node training set as output, and training based on the single-layer perceptron algorithm to obtain an axis motion operation state abnormality analysis model;

[0029] The shaft motion operation state analysis model is used as a primary model, and the shaft motion operation state abnormality analysis model is used as a secondary model to establish a shaft motion operation data classification model.

[0030] Furthermore, the real-time monitoring results of the axis motion obtained by using the axis motion operation data classification model include:

[0031] S3-1, using the real-time operation data of the axis movement to adjust the operation state to establish a real-time monitoring node for the axis movement;

[0032] S3-2. Utilize the axis motion real-time monitoring node to obtain the axis motion real-time monitoring result according to the axis motion operation data classification model.

[0033] Further, using the real-time operation data of the axis movement to adjust the operation state at the time to establish a real-time monitoring node for the axis movement includes:

[0034] The first node, the second node, the third node, the fourth node and the fifth node are established in sequence using the axis movement rotation angle data, the axis movement straight line distance data and the equipment safety door opening and closing distance data of the axis movement real-time operation data;

[0035] Establishing a first time range threshold, a second time range threshold, a third time range threshold, a fourth time range threshold and a fifth time range threshold respectively according to the first node, the second node, the third node, the fourth node and the fifth node;

[0036] Using the first node, the second node, the third node, the fourth node, and the fifth node to respectively establish an independent bidirectional mapping node with the first time range threshold, the second time range threshold, the third time range threshold, the fourth time range threshold, and the fifth time range threshold;

[0037] Using the independent bidirectional mapping node as a real-time monitoring node for axis motion;

[0038] The time range threshold is the operating state adjustment time corresponding to the axis movement of the equipment safety door.

[0039] Furthermore, the real-time monitoring result of the axis motion is obtained by using the axis motion real-time monitoring node according to the axis motion operation data classification model, including:

[0040] S3-2-1, determine whether the real-time operation data of the axis motion do not exceed the corresponding time range threshold of the corresponding axis motion real-time monitoring node in sequence, if so, the real-time monitoring result of the axis motion is normal, use the current time as the starting collection time t for update, and return to S1-1, otherwise, execute S3-2-2;

[0041] S3-2-2, using the real-time operation data of the axis motion to obtain an axis motion operation data classification result according to an axis motion operation data classification model;

[0042] S3-2-3. Determine whether the classification result of the axis motion operation data is in a normal state. If so, the real-time monitoring result of the axis motion is normal. Use the current time as the updated starting acquisition time t and return to S1-1. Otherwise, the real-time monitoring result of the axis motion is abnormal. Use the secondary model output corresponding to the axis motion operation data classification model as abnormal data.

[0043] Compared with the closest prior art, the present invention has the following beneficial effects:

[0044] Through the various data of the equipment safety door axis movement, we analyze and process them step by step to establish a research and judgment model for the operation status of the axis movement, provide comparison data from different angles, avoid output interference deviation caused by a single data source, save manpower and improve the monitoring efficiency and accuracy of the equipment safety door. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The present invention provides a flow chart of a method for real-time monitoring of the axis movement of a device safety door. DETAILED DESCRIPTION

[0046] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0048] Embodiment 1:

[0049] The present invention provides a method for real-time monitoring of the axis movement of a device safety door, such as Figure 1 As shown, including:

[0050] S1. Obtain the real-time operation data of the axis movement of the equipment safety door;

[0051] S2. establishing an axis motion operation data classification model according to the axis motion real-time operation data;

[0052] S3. Using the axis motion operation data classification model to obtain the axis motion real-time monitoring result.

[0053] S1 specifically includes:

[0054] S1-1, obtaining the current time as the starting collection time t;

[0055] S1-2, obtaining the axis movement rotation angle data, axis movement straight line distance data and equipment safety door opening and closing distance data at the start collection time t;

[0056] S1-3, using the shaft movement rotation angle data, shaft movement straight distance data and equipment safety door opening and closing distance data to perform rational screening and processing to obtain the shaft movement real-time operation data.

[0057] S1-3 specifically includes:

[0058] S1-3-1, respectively obtain the shaft movement rotation angle data, shaft movement straight line distance data and equipment safety door opening and closing distance data corresponding to time t-1 according to the shaft movement rotation angle data, shaft movement straight line distance data and equipment safety door opening and closing distance data;

[0059] S1-3-2, determine whether the axis movement rotation angle data at the starting acquisition time t is the same as the axis movement rotation angle data at time t-1, if so, output the axis movement rotation angle data at the starting acquisition time t, the axis movement straight-line distance data and the equipment safety door opening and closing distance data as the axis movement real-time operation data, otherwise, execute S1-3-3;

[0060] S1-3-3, determine whether the axis motion straight-line distance data at the starting acquisition time t is the same as the axis motion straight-line distance data at time t-1, if so, output the axis motion rotation angle data, axis motion straight-line distance data and equipment safety door opening and closing distance data at the starting acquisition time t as the axis motion real-time operation data, otherwise, execute S1-3-4;

[0061] S1-3-4. Determine whether the equipment safety door opening and closing distance data at the starting collection time t is the same as the equipment safety door opening and closing distance data at time t-1. If so, use the current time as the updated starting collection time t and return to S1-1. Otherwise, use the current time as the updated starting collection time t and return to S1-1.

[0062] S2 specifically includes:

[0063] S2-1, acquiring corresponding historical real-time operation data of the axis movement according to the real-time operation data of the axis movement;

[0064] S2-2, using the historical axis motion real-time operation data to establish an axis motion operation status analysis model;

[0065] S2-3. Obtain an axis motion operation data classification model according to the axis motion operation state analysis model.

[0066] S2-2 specifically includes:

[0067] S2-2-1, using the real-time operation data of the historical axis movement to establish a historical data set as a training set;

[0068] S2-2-2, using the training set as input, the axis motion operation state of the equipment safety door corresponding to the training set as output, using the number of operation state adjustment moments corresponding to the historical axis motion real-time operation data to establish a hidden layer, and training based on a deep learning multi-layer neural network to obtain an initial state analysis model;

[0069] S2-2-3, determine whether the number of training times corresponding to the current initial state analysis model is n-1, if so, output the current initial state analysis model as the axis motion operation state analysis model, otherwise, return to S2-2-2;

[0070] The operating state includes a normal state and an abnormal state, and n is the number of subsets in the training set.

[0071] S2-3 specifically includes:

[0072] S2-3-1. Obtaining a training set corresponding to an abnormal state as an abnormal node training set according to the axis motion operation state analysis model;

[0073] S2-3-2, using the abnormal node training set as input, the historical axis motion real-time operation data corresponding to the abnormal state of the abnormal node training set as output, and training based on the single-layer perceptron algorithm to obtain an axis motion operation state abnormality analysis model;

[0074] S2-3-3. Use the axis motion operation status analysis model as the primary model and the axis motion operation status abnormality analysis model as the secondary model to establish an axis motion operation data classification model.

[0075] S3 specifically includes:

[0076] S3-1, using the real-time operation data of the axis movement to adjust the operation state to establish a real-time monitoring node for the axis movement;

[0077] S3-2. Utilize the axis motion real-time monitoring node to obtain the axis motion real-time monitoring result according to the axis motion operation data classification model.

[0078] S3-1 specifically includes:

[0079] S3-1-1, using the axis movement rotation angle data, axis movement straight distance data and equipment safety door opening and closing distance data of the axis movement real-time operation data to sequentially establish a first node, a second node, a third node, a fourth node and a fifth node;

[0080] S3-1-2, respectively establish a first time range threshold, a second time range threshold, a third time range threshold, a fourth time range threshold and a fifth time range threshold according to the first node, the second node, the third node, the fourth node and the fifth node;

[0081] S3-1-3, using the first node, the second node, the third node, the fourth node, and the fifth node to respectively establish an independent bidirectional mapping node with the first time range threshold, the second time range threshold, the third time range threshold, the fourth time range threshold, and the fifth time range threshold;

[0082] S3-1-4, using the independent bidirectional mapping node as a real-time monitoring node for axis motion;

[0083] The time range threshold is the operating state adjustment time corresponding to the axis movement of the equipment safety door.

[0084] S3-2 specifically includes:

[0085] S3-2-1, determine whether the real-time operation data of the axis motion do not exceed the corresponding time range threshold of the corresponding axis motion real-time monitoring node in sequence, if so, the real-time monitoring result of the axis motion is normal, use the current time as the starting collection time t for update, and return to S1-1, otherwise, execute S3-2-2;

[0086] S3-2-2, using the real-time operation data of the axis motion to obtain an axis motion operation data classification result according to an axis motion operation data classification model;

[0087] S3-2-3. Determine whether the classification result of the axis motion operation data is in a normal state. If so, the real-time monitoring result of the axis motion is normal. Use the current time as the updated starting acquisition time t and return to S1-1. Otherwise, the real-time monitoring result of the axis motion is abnormal. Use the secondary model output corresponding to the axis motion operation data classification model as abnormal data.

[0088] 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.

[0089] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the 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 generate 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.

[0090] 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.

[0091] 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.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A real-time monitoring method for the axis movement of a device safety door, It is characterized in that include: S1. Obtain the real-time operation data of the axis movement of the equipment safety door; S2. establishing an axis motion operation data classification model according to the axis motion real-time operation data; S3. Using the axis motion operation data classification model to obtain the axis motion real-time monitoring result.

2. A method for real-time monitoring of the axis movement of a device safety door according to claim 1, It is characterized in that The acquisition of real-time operation data of the axis movement of the equipment safety door includes: S1-1, obtaining the current time as the starting collection time t; S1-2, obtaining the axis movement rotation angle data, axis movement straight line distance data and equipment safety door opening and closing distance data at the start collection time t; S1-3, using the shaft movement rotation angle data, shaft movement straight distance data and equipment safety door opening and closing distance data to perform rational screening and processing to obtain the shaft movement real-time operation data.

3. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 2, It is characterized in that The real-time operation data of the axis movement obtained by rational screening and processing using the axis movement rotation angle data, the axis movement linear distance data and the equipment safety door opening and closing distance data include: S1-3-1, respectively obtain the shaft movement rotation angle data, shaft movement straight line distance data and equipment safety door opening and closing distance data corresponding to time t-1 according to the shaft movement rotation angle data, shaft movement straight line distance data and equipment safety door opening and closing distance data; S1-3-2, determine whether the axis movement rotation angle data at the starting acquisition time t is the same as the axis movement rotation angle data at time t-1, if so, output the axis movement rotation angle data at the starting acquisition time t, the axis movement straight-line distance data and the equipment safety door opening and closing distance data as the axis movement real-time operation data, otherwise, execute S1-3-3; S1-3-3, determine whether the axis motion straight-line distance data at the starting acquisition time t is the same as the axis motion straight-line distance data at time t-1, if so, output the axis motion rotation angle data, axis motion straight-line distance data and equipment safety door opening and closing distance data at the starting acquisition time t as the axis motion real-time operation data, otherwise, execute S1-3-4; S1-3-4. Determine whether the equipment safety door opening and closing distance data at the starting collection time t is the same as the equipment safety door opening and closing distance data at time t-1. If so, use the current time as the updated starting collection time t and return to S1-1. Otherwise, use the current time as the updated starting collection time t and return to S1-1.

4. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 2, It is characterized in that Establishing an axis motion operation data classification model according to the axis motion real-time operation data includes: S2-1, acquiring corresponding historical real-time operation data of the axis movement according to the real-time operation data of the axis movement; S2-2, using the historical axis motion real-time operation data to establish an axis motion operation status analysis model; S2-3. Obtain an axis motion operation data classification model according to the axis motion operation state analysis model.

5. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 4, It is characterized in that Using the historical axis motion real-time operation data to establish an axis motion operation state analysis model includes: S2-2-1, using the real-time operation data of the historical axis movement to establish a historical data set as a training set; S2-2-2, using the training set as input, the axis motion operation state of the equipment safety door corresponding to the training set as output, using the number of operation state adjustment moments corresponding to the historical axis motion real-time operation data to establish a hidden layer, and training based on a deep learning multi-layer neural network to obtain an initial state analysis model; S2-2-3, determine whether the number of training times corresponding to the current initial state analysis model is n-1, if so, output the current initial state analysis model as the axis motion operation state analysis model, otherwise, return to S2-2-2; The operating state includes a normal state and an abnormal state, and n is the number of subsets in the training set.

6. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 5, It is characterized in that The axis motion operation data classification model obtained according to the axis motion operation state analysis model includes: According to the axis motion operation state analysis model, a training set corresponding to an abnormal state is obtained as an abnormal node training set; Using the abnormal node training set as input, the historical axis motion real-time operation data corresponding to the abnormal state of the abnormal node training set as output, and training based on the single-layer perceptron algorithm to obtain an axis motion operation state abnormality analysis model; The shaft motion operation state analysis model is used as a primary model, and the shaft motion operation state abnormality analysis model is used as a secondary model to establish a shaft motion operation data classification model.

7. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 4, It is characterized in that The real-time monitoring results of the axis motion obtained by using the axis motion operation data classification model include: S3-1, using the real-time operation data of the axis movement to adjust the operation state to establish a real-time monitoring node for the axis movement; S3-2. Utilize the axis motion real-time monitoring node to obtain the axis motion real-time monitoring result according to the axis motion operation data classification model.

8. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 7, It is characterized in that Establishing a real-time monitoring node for axis motion by using the axis motion real-time operation data corresponding to the operation state adjustment time includes: The first node, the second node, the third node, the fourth node and the fifth node are established in sequence using the axis movement rotation angle data, the axis movement straight line distance data and the equipment safety door opening and closing distance data of the axis movement real-time operation data; Establishing a first time range threshold, a second time range threshold, a third time range threshold, a fourth time range threshold and a fifth time range threshold respectively according to the first node, the second node, the third node, the fourth node and the fifth node; Using the first node, the second node, the third node, the fourth node, and the fifth node to respectively establish an independent bidirectional mapping node with the first time range threshold, the second time range threshold, the third time range threshold, the fourth time range threshold, and the fifth time range threshold; Using the independent bidirectional mapping node as a real-time monitoring node for axis motion; The time range threshold is the operating state adjustment time corresponding to the axis movement of the equipment safety door.

9. A method for real-time monitoring of the axis movement of a device safety door as claimed in claim 8, It is characterized in that The real-time monitoring result of the axis motion is obtained by using the axis motion real-time monitoring node according to the axis motion operation data classification model, including: S3-2-1, determine whether the real-time operation data of the axis motion do not exceed the corresponding time range threshold of the corresponding axis motion real-time monitoring node in sequence, if so, the real-time monitoring result of the axis motion is normal, use the current time as the starting collection time t for update, and return to S1-1, otherwise, execute S3-2-2; S3-2-2, using the real-time operation data of the axis motion to obtain an axis motion operation data classification result according to an axis motion operation data classification model; S3-2-3. Determine whether the classification result of the axis motion operation data is in a normal state. If so, the real-time monitoring result of the axis motion is normal. Use the current time as the updated starting acquisition time t and return to S1-1. Otherwise, the real-time monitoring result of the axis motion is abnormal. Use the secondary model output corresponding to the axis motion operation data classification model as abnormal data.

Images