Method and system for controlling monitoring angle of 3D printing equipment based on image recognition

Abstract

The invention discloses a 3D printing equipment monitoring angle control method and system based on image recognition. The method comprises the steps that historical working data and sensing data of 3D printing equipment to be monitored are acquired; on the basis of a prediction algorithm, according to the sensing data, historical working faults corresponding to the 3D printing equipment are predicted; determining sensing accurate parameters corresponding to the sensing data according to the historical working faults and the historical working data; determining an image monitoring angle corresponding to the 3D printing equipment according to the sensing accuracy parameter and a current monitoring posture of image monitoring equipment corresponding to the 3D printing equipment; the image monitoring angle is used for indicating a view finding angle of at least one image monitoring device to the 3D printing device. Therefore, accurate image monitoring angle optimization based on fault prediction and sensing accuracy can be realized, the accuracy and efficiency of monitoring of the 3D printing equipment are improved, and the risk of missing detection of faults is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for controlling a monitoring angle of a 3D printing device based on image recognition. Background Art

[0002] With the widespread adoption of 3D printing equipment in high-precision manufacturing, companies and users are increasingly focused on reducing the risk of equipment failure through precise monitoring. Existing technologies typically collect historical operating and sensor data from 3D printing equipment, employing fixed monitoring strategies or simple image analysis methods to adjust monitoring angles to ensure controllable equipment operating status. Existing solutions lack dynamic prediction of historical operating failures and in-depth analysis of sensor data accuracy, making it difficult to effectively assess equipment status and optimize image monitoring angles. Commonly used static monitoring settings are unsuitable for complex printing scenarios, resulting in insufficient monitoring accuracy, prone to missed faults, and low monitoring efficiency, limiting the reliability and production efficiency of 3D printing equipment. Clearly, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a 3D printing equipment monitoring angle control method and system based on image recognition, which can realize precise image monitoring angle optimization based on fault prediction and sensing accuracy, improve the accuracy and efficiency of 3D printing equipment monitoring, and reduce the risk of missed fault detection.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a 3D printing equipment monitoring angle control method based on image recognition, the method comprising: Obtain historical working data and sensor data of the 3D printing equipment to be monitored; Based on the prediction algorithm, predict the historical working failures corresponding to the 3D printing device according to the sensor data; Determining accurate sensing parameters corresponding to the sensing data based on the historical working failures and the historical working data; An image monitoring angle corresponding to the 3D printing device is determined based on the accurate sensing parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device; the image monitoring angle is used to indicate a viewing angle of at least one image monitoring device relative to the 3D printing device.

[0005] As an optional embodiment, in the first aspect of the present invention, the sensing data includes at least one of light reflection data, temperature data, humidity data, image data, sound data and light intensity data.

[0006] As an optional embodiment, in the first aspect of the present invention, predicting historical operating failures corresponding to the 3D printing device based on the sensor data based on a prediction algorithm includes: Inputting the historical sensor data corresponding to each historical time point in the sensor data into a trained fault prediction neural network to obtain the fault probability and fault type corresponding to the historical sensor data corresponding to each historical time point; the fault prediction neural network is an RNN network structure, which is trained by a training data set including multiple training sensor data and corresponding fault type labels; Sort the fault probabilities corresponding to all the historical sensor data from early to late based on the historical time points to obtain a fault probability sequence; Sort the fault types corresponding to all the historical sensor data from early to late based on the historical time points to obtain a fault type sequence; According to the fault probability sequence and the fault type sequence, historical working faults corresponding to the 3D printing device are determined.

[0007] As an optional embodiment, in the first aspect of the present invention, determining the historical operating failures corresponding to the 3D printing device according to the failure probability sequence and the failure type sequence includes: Filtering out a combination of consecutive failure time points from the failure probability sequence; Filtering out a combination of associated fault time points from the fault type sequence; the associated fault time point combination includes a plurality of consecutive historical time points corresponding to the fault type that meet a preset association type rule; Calculating the intersection of the continuous fault time point combination and the associated fault time point combination to obtain at least one fault time point; All the fault time points and the corresponding fault types are determined as historical working faults corresponding to the 3D printing device.

[0008] As an optional embodiment, in the first aspect of the present invention, the continuous fault time point combination includes multiple continuous historical time points whose corresponding fault probabilities satisfy preset data change rules; the data change rules are used to limit the fault probability to be greater than a preset probability threshold and the corresponding continuous change rate to be greater than a preset change rate threshold.

[0009] As an optional implementation manner, in the first aspect of the present invention, determining the sensing accuracy parameter corresponding to the sensing data based on the historical working failure and the historical working data includes: Determining multiple fault error data in the historical working data based on a data identification matching algorithm; Calculating the time similarity between the data time points corresponding to all the fault error data and the fault time points in the historical working faults; Calculating the type similarity between the error types corresponding to all the fault error data and the fault types in the historical working faults; Calculate sensing accuracy parameters corresponding to the sensing data according to the time similarity and the type similarity.

[0010] As an optional implementation manner, in the first aspect of the present invention, calculating the sensing accuracy parameter corresponding to the sensing data based on the time similarity and the type similarity includes: Calculate the weighted sum average of the time similarity and the type similarity to obtain the sensing accuracy parameter corresponding to the sensing data; wherein the calculation weight corresponding to the time similarity is inversely proportional to the data concentration corresponding to all the data time points, and the calculation weight corresponding to the type similarity is inversely proportional to the type discrimination corresponding to all the error types; the type discrimination is the average value of the number of all data belonging to the same type in all the error types.

[0011] As an optional embodiment, in the first aspect of the present invention, determining the image monitoring angle corresponding to the 3D printing device based on the sensing accuracy parameter and the current monitoring posture of the image monitoring device corresponding to the 3D printing device includes: Obtaining a current monitoring posture of an image monitoring device corresponding to the 3D printing device; Based on a preset correspondence between posture and image angle, determining a current monitoring angle of the image monitoring device according to the current monitoring posture; Calculating an angle correction value inversely proportional to the sensing accuracy parameter; The angle correction value is adjusted by adjusting the current monitoring angle toward a preset optimal monitoring angle to obtain an image monitoring angle corresponding to the 3D printing device.

[0012] A second aspect of an embodiment of the present invention discloses a 3D printing equipment monitoring angle control system based on image recognition, the system comprising: An acquisition module is used to acquire historical working data and sensor data of the 3D printing equipment to be monitored; A prediction module, configured to predict historical operating failures corresponding to the 3D printing device based on the sensor data based on a prediction algorithm; A first determining module, configured to determine a sensing accuracy parameter corresponding to the sensing data based on the historical working failure and the historical working data; The second determination module is used to determine the image monitoring angle corresponding to the 3D printing device based on the accurate sensing parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device; the image monitoring angle is used to indicate the framing angle of at least one image monitoring device relative to the 3D printing device.

[0013] As an optional embodiment, in the second aspect of the present invention, the sensing data includes at least one of light reflection data, temperature data, humidity data, image data, sound data and light intensity data.

[0014] As an optional embodiment, in the second aspect of the present invention, the prediction module predicts a specific manner of historical operating failures corresponding to the 3D printing device based on the sensor data based on a prediction algorithm, including: Inputting the historical sensor data corresponding to each historical time point in the sensor data into a trained fault prediction neural network to obtain the fault probability and fault type corresponding to the historical sensor data corresponding to each historical time point; the fault prediction neural network is an RNN network structure, which is trained by a training data set including multiple training sensor data and corresponding fault type labels; Sort the fault probabilities corresponding to all the historical sensor data from early to late based on the historical time points to obtain a fault probability sequence; Sort the fault types corresponding to all the historical sensor data from early to late based on the historical time points to obtain a fault type sequence; According to the fault probability sequence and the fault type sequence, historical working faults corresponding to the 3D printing device are determined.

[0015] As an optional embodiment, in the second aspect of the present invention, the prediction module determines the specific mode of the historical working failure corresponding to the 3D printing device based on the failure probability sequence and the failure type sequence, including: Filtering out a combination of consecutive failure time points from the failure probability sequence; Filtering out a combination of associated fault time points from the fault type sequence; the associated fault time point combination includes a plurality of consecutive historical time points corresponding to the fault type that meet a preset association type rule; Calculating the intersection of the continuous fault time point combination and the associated fault time point combination to obtain at least one fault time point; All the fault time points and the corresponding fault types are determined as historical working faults corresponding to the 3D printing device.

[0016] As an optional embodiment, in the second aspect of the present invention, the continuous fault time point combination includes multiple continuous historical time points whose corresponding fault probabilities satisfy preset data change rules; the data change rules are used to limit the fault probability to be greater than a preset probability threshold and the corresponding continuous change rate to be greater than a preset change rate threshold.

[0017] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the first determination module determines the sensing accuracy parameter corresponding to the sensing data based on the historical working failure and the historical working data includes: Determining multiple fault error data in the historical working data based on a data identification matching algorithm; Calculating the time similarity between the data time points corresponding to all the fault error data and the fault time points in the historical working faults; Calculating the type similarity between the error types corresponding to all the fault error data and the fault types in the historical working faults; Calculate sensing accuracy parameters corresponding to the sensing data according to the time similarity and the type similarity.

[0018] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the first determination module calculates the sensing accuracy parameter corresponding to the sensing data based on the time similarity and the type similarity includes: Calculate the weighted sum average of the time similarity and the type similarity to obtain the sensing accuracy parameter corresponding to the sensing data; wherein the calculation weight corresponding to the time similarity is inversely proportional to the data concentration corresponding to all the data time points, and the calculation weight corresponding to the type similarity is inversely proportional to the type discrimination corresponding to all the error types; the type discrimination is the average value of the number of all data belonging to the same type in all the error types.

[0019] As an optional embodiment, in the second aspect of the present invention, the second determination module determines the specific manner of the image monitoring angle corresponding to the 3D printing device based on the sensing accuracy parameter and the current monitoring posture of the image monitoring device corresponding to the 3D printing device, including: Obtaining a current monitoring posture of an image monitoring device corresponding to the 3D printing device; Based on a preset correspondence between posture and image angle, determining a current monitoring angle of the image monitoring device according to the current monitoring posture; Calculating an angle correction value inversely proportional to the sensing accuracy parameter; The angle correction value is adjusted by adjusting the current monitoring angle toward a preset optimal monitoring angle to obtain an image monitoring angle corresponding to the 3D printing device.

[0020] A third aspect of the present invention discloses another 3D printing equipment monitoring angle control system based on image recognition, the system comprising: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the 3D printing device monitoring angle control method based on image recognition disclosed in the first aspect of the present invention.

[0021] A fourth aspect of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the image recognition-based 3D printing device monitoring angle control method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention obtains historical working data and sensor data of the 3D printing equipment to be monitored, predicts historical working failures based on a prediction algorithm, determines accurate sensing parameters in combination with the historical working failures and historical working data, and determines the image monitoring angle according to the accurate sensing parameters and the current monitoring posture of the image monitoring equipment. This can achieve precise image monitoring angle optimization based on fault prediction and sensor accuracy, improve the accuracy and efficiency of 3D printing equipment monitoring, and reduce the risk of missed fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0024] Figure 1 This is a flow chart of a method for controlling a monitoring angle of a 3D printing device based on image recognition disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a structural diagram of a 3D printing equipment monitoring angle control system based on image recognition disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a structural diagram of another 3D printing equipment monitoring angle control system based on image recognition disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0029] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a method and system for controlling the monitoring angle of 3D printing equipment based on image recognition. By acquiring historical operating data and sensor data of the 3D printing equipment to be monitored, the system predicts historical operating failures based on a prediction algorithm, determines accurate sensing parameters based on these historical failures and operating data, and then determines the image monitoring angle based on these accurate sensing parameters and the current monitoring posture of the image monitoring equipment. This system enables precise optimization of the image monitoring angle based on fault prediction and sensor accuracy, improving the accuracy and efficiency of 3D printing equipment monitoring and reducing the risk of missed fault detection. These are described in detail below.

[0031] Example 1 See also Figure 1 , Figure 1 This is a flow chart of a method for controlling the monitoring angle of a 3D printing device based on image recognition disclosed in an embodiment of the present invention. Figure 1The described method for controlling the monitoring angle of a 3D printing device based on image recognition can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the 3D printing device monitoring angle control method based on image recognition may include the following operations: 101. Obtain historical working data and sensor data of the 3D printing equipment to be monitored.

[0032] 102. Based on the prediction algorithm and sensor data, predict the historical working failures of 3D printing equipment. 103. Determine accurate sensing parameters corresponding to the sensing data based on historical working failures and historical working data. 104. Determine an image monitoring angle corresponding to the 3D printing device based on the accurate sensing parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device.

[0033] Optionally, the image monitoring angle is used to indicate a viewing angle of at least one image monitoring device relative to the 3D printing device.

[0034] It can be seen that the above-mentioned embodiment of the invention obtains the historical working data and sensor data of the 3D printing equipment to be monitored, predicts historical working failures based on the prediction algorithm, determines the sensing accuracy parameters in combination with the historical working failures and historical working data, and determines the image monitoring angle according to the sensing accuracy parameters and the current monitoring posture of the image monitoring equipment, thereby realizing accurate image monitoring angle optimization based on fault prediction and sensor accuracy, improving the accuracy and efficiency of 3D printing equipment monitoring, and reducing the risk of missed fault detection.

[0035] As an optional embodiment, in the above steps, the sensing data includes at least one of light reflection data, temperature data, humidity data, image data, sound data and light intensity data.

[0036] It can be seen that through the above optional embodiments, the content of the sensor data is limited to comprehensively characterize the relevant characteristics of the printing equipment's sensing, so as to facilitate subsequent accurate fault prediction and accurate sensing judgment, and assist in realizing precise image monitoring angle optimization based on fault prediction and sensing accuracy, thereby improving the accuracy and efficiency of 3D printing equipment monitoring and reducing the risk of missed fault detection.

[0037] As an optional embodiment, in the above steps, predicting historical operating failures corresponding to the 3D printing device based on the prediction algorithm and sensor data includes: Inputting the historical sensor data corresponding to each historical time point in the sensor data into a trained fault prediction neural network to obtain the fault probability and fault type corresponding to the historical sensor data corresponding to each historical time point; optionally, the fault prediction neural network is an RNN network structure, which is trained by a training data set including multiple training sensor data and corresponding fault type labels; Sort the fault probabilities corresponding to all historical sensor data from early to late based on historical time points to obtain a fault probability sequence; Sort the fault types corresponding to all historical sensor data from early to late based on historical time points to obtain a fault type sequence; According to the fault probability sequence and fault type sequence, the historical working faults corresponding to the 3D printing equipment are determined.

[0038] It can be seen that through the above optional embodiments, by inputting the historical sensor data of the 3D printing equipment into the trained RNN fault prediction neural network according to the historical time points, the fault probability and fault type corresponding to each time point are obtained and sorted from early to late in time to form a fault probability sequence and a fault type sequence, and the two are combined to determine the historical working failures, thereby realizing accurate fault analysis based on time series fault prediction, improving the accuracy and reliability of 3D printing equipment monitoring, and reducing the risk of fault misjudgment.

[0039] As an optional embodiment, in the above step, determining the historical working failures corresponding to the 3D printing device according to the failure probability sequence and the failure type sequence includes: Filter out the combination of consecutive failure time points from the failure probability sequence; Filtering out a combination of associated fault time points from the fault type sequence; optionally, the associated fault time point combination includes a plurality of consecutive historical time points whose corresponding fault types satisfy a preset association type rule; Calculate the intersection of the combination of consecutive fault time points and the combination of associated fault time points to obtain at least one fault time point; All fault time points and corresponding fault types are determined as historical working faults corresponding to the 3D printing equipment.

[0040] It can be seen that through the above optional embodiments, by screening continuous fault time point combinations from the fault probability sequence, and screening continuous historical time points that meet the preset association type rules from the fault type sequence to form an associated fault time point combination, the intersection of the two is calculated to obtain the fault time point and its corresponding fault type, which is determined to be a historical working fault of the 3D printing device, thereby realizing accurate fault identification based on time series and type association, improving the accuracy of equipment monitoring and fault diagnosis efficiency, and reducing the risk of missed detection.

[0041] As an optional embodiment, in the above steps, the continuous fault time point combination includes multiple continuous historical time points whose corresponding fault probabilities meet the preset data change rules; the data change rules are used to limit the fault probability to be greater than the preset probability threshold and the corresponding continuous change rate to be greater than the preset change rate threshold.

[0042] It can be seen that through the above optional embodiments, it is limited to screen out continuous historical time points from the fault probability sequence that meet the fault probability exceeding the probability threshold and the continuous change rate exceeding the change rate threshold to form a continuous fault time point combination, so as to facilitate the subsequent realization of accurate fault identification based on probability changes and type associations, improve equipment monitoring accuracy and fault diagnosis efficiency, and reduce the risk of missed fault detection.

[0043] As an optional embodiment, in the above step, determining the accurate sensing parameters corresponding to the sensing data based on historical working failures and historical working data includes: Based on the data identification matching algorithm, multiple fault error data in the historical working data are determined; Calculate the time similarity between the data time points corresponding to all fault error data and the fault time points in historical work faults; Calculate the type similarity between the error types corresponding to all fault error data and the fault types in historical work faults; According to the time similarity and type similarity, the sensing accuracy parameters corresponding to the sensing data are calculated.

[0044] It can be seen that through the above optional embodiments, by identifying the fault error data in the historical work data based on the data identification matching algorithm, calculating the time similarity between its data time point and the historical work fault time point and the type similarity between the error type and the fault type, and combining the two to determine the sensing accuracy parameters of the sensing data, thereby realizing accurate sensing accuracy evaluation based on time and type matching, improving the reliability of 3D printing equipment monitoring, and reducing the risk of misjudgment of faults.

[0045] As an optional embodiment, in the above step, calculating the sensing accuracy parameter corresponding to the sensing data based on the time similarity and the type similarity includes: Calculate the weighted sum average of time similarity and type similarity to obtain the sensing accuracy parameter corresponding to the sensing data; optionally, the calculation weight corresponding to time similarity is inversely proportional to the data concentration corresponding to all data time points, and the calculation weight corresponding to type similarity is inversely proportional to the type discrimination corresponding to all error types; type discrimination is the average value of the number of all data belonging to the same type in all error types.

[0046] It can be seen that through the above optional embodiments, by calculating the time similarity between the fault error data time point and the historical working fault time point and the type similarity between the error type and the fault type, and using the weighted sum average value related to the data concentration and type discrimination to determine the sensing accuracy parameters of the sensing data, accurate sensing accuracy evaluation based on weighted analysis of time and type features is achieved, thereby improving the reliability of 3D printing equipment monitoring and fault diagnosis accuracy, and reducing the risk of misjudgment.

[0047] As an optional embodiment, in the above step, determining the image monitoring angle corresponding to the 3D printing device based on the sensing accuracy parameter and the current monitoring posture of the image monitoring device corresponding to the 3D printing device includes: Obtain the current monitoring posture of the image monitoring device corresponding to the 3D printing device; Based on the corresponding relationship between the preset posture and the image angle, the current monitoring angle of the image monitoring device is determined according to the current monitoring posture; Calculate the angle correction value which is inversely proportional to the sensing accuracy parameter; Adjust the current monitoring angle toward the preset optimal monitoring angle by an angle correction value to obtain the image monitoring angle corresponding to the 3D printing device.

[0048] It can be seen that through the above optional embodiments, by obtaining the current monitoring posture of the 3D printing device image monitoring device and determining the current monitoring angle based on the correspondence between the preset posture and the image angle, calculating the angle correction value inversely proportional to the sensing accuracy parameter, adjusting the current monitoring angle toward the optimal monitoring angle to obtain the final image monitoring angle, thereby realizing precise monitoring angle optimization based on sensing accuracy and posture analysis, improving the accuracy and efficiency of 3D printing device monitoring, and reducing the risk of missed fault detection.

[0049] Example 2 See also Figure 2 , Figure 2 This is a schematic diagram of a 3D printing equipment monitoring angle control system based on image recognition disclosed in an embodiment of the present invention. Figure 2 The described 3D printing device monitoring angle control system based on image recognition can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the 3D printing equipment monitoring angle control system based on image recognition may include: The acquisition module 201 is used to acquire historical working data and sensor data of the 3D printing device to be monitored.

[0050] The prediction module 202 is configured to predict historical operating failures of the 3D printing device based on a prediction algorithm and sensor data. The first determination module 203 is configured to determine accurate sensing parameters corresponding to the sensing data based on historical operating failures and historical operating data. The second determining module 204 is configured to determine the image monitoring angle corresponding to the 3D printing device according to the sensing accuracy parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device.

[0051] Optionally, the image monitoring angle is used to indicate a viewing angle of at least one image monitoring device relative to the 3D printing device.

[0052] It can be seen that the above-mentioned embodiment of the invention obtains the historical working data and sensor data of the 3D printing equipment to be monitored, predicts historical working failures based on the prediction algorithm, determines the sensing accuracy parameters in combination with the historical working failures and historical working data, and determines the image monitoring angle according to the sensing accuracy parameters and the current monitoring posture of the image monitoring equipment, thereby realizing accurate image monitoring angle optimization based on fault prediction and sensor accuracy, improving the accuracy and efficiency of 3D printing equipment monitoring, and reducing the risk of missed fault detection.

[0053] As an optional embodiment, the sensing data includes at least one of light reflection data, temperature data, humidity data, image data, sound data and light intensity data.

[0054] It can be seen that through the above optional embodiments, the content of the sensor data is limited to comprehensively characterize the relevant characteristics of the printing equipment's sensing, so as to facilitate subsequent accurate fault prediction and accurate sensing judgment, and assist in realizing precise image monitoring angle optimization based on fault prediction and sensing accuracy, thereby improving the accuracy and efficiency of 3D printing equipment monitoring and reducing the risk of missed fault detection.

[0055] As an optional embodiment, the prediction module predicts the specific manner in which the historical working failure of the 3D printing device corresponds to the sensor data based on the prediction algorithm, including: Inputting the historical sensor data corresponding to each historical time point in the sensor data into a trained fault prediction neural network to obtain the fault probability and fault type corresponding to the historical sensor data corresponding to each historical time point; optionally, the fault prediction neural network is an RNN network structure, which is trained by a training data set including multiple training sensor data and corresponding fault type labels; Sort the fault probabilities corresponding to all historical sensor data from early to late based on historical time points to obtain a fault probability sequence; Sort the fault types corresponding to all historical sensor data from early to late based on historical time points to obtain a fault type sequence; According to the fault probability sequence and fault type sequence, the historical working faults corresponding to the 3D printing equipment are determined.

[0056] It can be seen that through the above optional embodiments, by inputting the historical sensor data of the 3D printing equipment into the trained RNN fault prediction neural network according to the historical time points, the fault probability and fault type corresponding to each time point are obtained and sorted from early to late in time to form a fault probability sequence and a fault type sequence, and the two are combined to determine the historical working failures, thereby realizing accurate fault analysis based on time series fault prediction, improving the accuracy and reliability of 3D printing equipment monitoring, and reducing the risk of fault misjudgment.

[0057] As an optional embodiment, the prediction module determines the specific mode of historical working failure corresponding to the 3D printing device based on the failure probability sequence and the failure type sequence, including: Filter out the combination of consecutive failure time points from the failure probability sequence; Filtering out a combination of associated fault time points from the fault type sequence; optionally, the associated fault time point combination includes a plurality of consecutive historical time points whose corresponding fault types satisfy a preset association type rule; Calculate the intersection of the combination of consecutive fault time points and the combination of associated fault time points to obtain at least one fault time point; All fault time points and corresponding fault types are determined as historical working faults corresponding to the 3D printing equipment.

[0058] It can be seen that through the above optional embodiments, by screening continuous fault time point combinations from the fault probability sequence, and screening continuous historical time points that meet the preset association type rules from the fault type sequence to form an associated fault time point combination, the intersection of the two is calculated to obtain the fault time point and its corresponding fault type, which is determined to be a historical working fault of the 3D printing device, thereby realizing accurate fault identification based on time series and type association, improving the accuracy of equipment monitoring and fault diagnosis efficiency, and reducing the risk of missed detection.

[0059] As an optional embodiment, the continuous fault time point combination includes multiple continuous historical time points whose corresponding fault probabilities meet the preset data change rules; the data change rules are used to limit the fault probability to be greater than the preset probability threshold and the corresponding continuous change rate to be greater than the preset change rate threshold.

[0060] It can be seen that through the above optional embodiments, it is limited to screen out continuous historical time points from the fault probability sequence that meet the fault probability exceeding the probability threshold and the continuous change rate exceeding the change rate threshold to form a continuous fault time point combination, so as to facilitate the subsequent realization of accurate fault identification based on probability changes and type associations, improve equipment monitoring accuracy and fault diagnosis efficiency, and reduce the risk of missed fault detection.

[0061] As an optional embodiment, the first determining module determines the specific manner of the sensing accuracy parameter corresponding to the sensing data based on the historical working failure and the historical working data, including: Based on the data identification matching algorithm, multiple fault error data in the historical working data are determined; Calculate the time similarity between the data time points corresponding to all fault error data and the fault time points in historical work faults; Calculate the type similarity between the error types corresponding to all fault error data and the fault types in historical work faults; According to the time similarity and type similarity, the sensing accuracy parameters corresponding to the sensing data are calculated.

[0062] It can be seen that through the above optional embodiments, by identifying the fault error data in the historical work data based on the data identification matching algorithm, calculating the time similarity between its data time point and the historical work fault time point and the type similarity between the error type and the fault type, and combining the two to determine the sensing accuracy parameters of the sensing data, thereby realizing accurate sensing accuracy evaluation based on time and type matching, improving the reliability of 3D printing equipment monitoring, and reducing the risk of misjudgment of faults.

[0063] As an optional embodiment, the specific manner in which the first determination module calculates the sensing accuracy parameter corresponding to the sensing data based on the time similarity and the type similarity includes: Calculate the weighted sum average of time similarity and type similarity to obtain the sensing accuracy parameter corresponding to the sensing data; optionally, the calculation weight corresponding to time similarity is inversely proportional to the data concentration corresponding to all data time points, and the calculation weight corresponding to type similarity is inversely proportional to the type discrimination corresponding to all error types; type discrimination is the average value of the number of all data belonging to the same type in all error types.

[0064] It can be seen that through the above optional embodiments, by calculating the time similarity between the fault error data time point and the historical working fault time point and the type similarity between the error type and the fault type, and using the weighted sum average value related to the data concentration and type discrimination to determine the sensing accuracy parameters of the sensing data, accurate sensing accuracy evaluation based on weighted analysis of time and type features is achieved, thereby improving the reliability of 3D printing equipment monitoring and fault diagnosis accuracy, and reducing the risk of misjudgment.

[0065] As an optional embodiment, the second determination module determines the specific manner of the image monitoring angle corresponding to the 3D printing device based on the sensing accuracy parameter and the current monitoring posture of the image monitoring device corresponding to the 3D printing device, including: Obtain the current monitoring posture of the image monitoring device corresponding to the 3D printing device; Based on the corresponding relationship between the preset posture and the image angle, the current monitoring angle of the image monitoring device is determined according to the current monitoring posture; Calculate the angle correction value which is inversely proportional to the sensing accuracy parameter; Adjust the current monitoring angle toward the preset optimal monitoring angle by an angle correction value to obtain the image monitoring angle corresponding to the 3D printing device.

[0066] It can be seen that through the above optional embodiments, by obtaining the current monitoring posture of the 3D printing device image monitoring device and determining the current monitoring angle based on the correspondence between the preset posture and the image angle, calculating the angle correction value inversely proportional to the sensing accuracy parameter, adjusting the current monitoring angle toward the optimal monitoring angle to obtain the final image monitoring angle, thereby realizing precise monitoring angle optimization based on sensing accuracy and posture analysis, improving the accuracy and efficiency of 3D printing device monitoring, and reducing the risk of missed fault detection.

[0067] Example 3 See also Figure 3 , Figure 3 This is another 3D printing equipment monitoring angle control system based on image recognition disclosed in an embodiment of the present invention. Figure 3 The described 3D printing equipment monitoring angle control system based on image recognition is applied to a data processing system / data processing equipment / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the 3D printing equipment monitoring angle control system based on image recognition may include: A memory 301 storing executable program code; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the 3D printing device monitoring angle control method based on image recognition described in the first embodiment.

[0068] Example 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for controlling the monitoring angle of a 3D printing device based on image recognition described in the first embodiment.

[0069] Example 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the image recognition-based 3D printing device monitoring angle control method described in Example 1.

[0070] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0072] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0073] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This specification 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 this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0078] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0079] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0081] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0082] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0083] Finally, it should be noted that the image recognition-based 3D printing equipment monitoring angle control method and system disclosed in the embodiments of the present invention are only preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A 3D printing equipment monitoring angle control method based on image recognition, characterized in that: The method comprises: Obtain historical working data and sensor data of the 3D printing equipment to be monitored; Based on the prediction algorithm, predict the historical working failures corresponding to the 3D printing device according to the sensor data; Determining accurate sensing parameters corresponding to the sensing data based on the historical working failures and the historical working data; An image monitoring angle corresponding to the 3D printing device is determined based on the accurate sensing parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device; the image monitoring angle is used to indicate a viewing angle of at least one image monitoring device relative to the 3D printing device.

2. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 1, wherein: The sensing data includes at least one of light reflection data, temperature data, humidity data, image data, sound data, and light intensity data.

3. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 1, wherein: The predicting of historical operating failures corresponding to the 3D printing device based on the sensor data based on a prediction algorithm includes: Inputting the historical sensor data corresponding to each historical time point in the sensor data into a trained fault prediction neural network to obtain the fault probability and fault type corresponding to the historical sensor data corresponding to each historical time point; the fault prediction neural network is an RNN network structure, which is trained by a training data set including multiple training sensor data and corresponding fault type labels; Sort the fault probabilities corresponding to all the historical sensor data from early to late based on the historical time points to obtain a fault probability sequence; Sort the fault types corresponding to all the historical sensor data from early to late based on the historical time points to obtain a fault type sequence; According to the fault probability sequence and the fault type sequence, historical working faults corresponding to the 3D printing device are determined.

4. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 3, wherein: The determining, based on the fault probability sequence and the fault type sequence, the historical working faults corresponding to the 3D printing device includes: Filtering out a combination of consecutive failure time points from the failure probability sequence; Filtering out a combination of associated fault time points from the fault type sequence; the associated fault time point combination includes a plurality of consecutive historical time points corresponding to the fault type that meet a preset association type rule; Calculating the intersection of the continuous fault time point combination and the associated fault time point combination to obtain at least one fault time point; All the fault time points and the corresponding fault types are determined as historical working faults corresponding to the 3D printing device.

5. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 4, wherein: The continuous fault time point combination includes multiple continuous historical time points whose corresponding fault probabilities meet preset data change rules; the data change rules are used to limit the fault probability to be greater than a preset probability threshold and the corresponding continuous change rate to be greater than a preset change rate threshold.

6. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 1, wherein: The determining, based on the historical working failure and the historical working data, the sensing accuracy parameter corresponding to the sensing data includes: Determining multiple fault error data in the historical working data based on a data identification matching algorithm; Calculating the time similarity between the data time points corresponding to all the fault error data and the fault time points in the historical working faults; Calculating the type similarity between the error types corresponding to all the fault error data and the fault types in the historical working faults; Calculate sensing accuracy parameters corresponding to the sensing data according to the time similarity and the type similarity.

7. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 6, wherein: The calculating, based on the time similarity and the type similarity, a sensing accuracy parameter corresponding to the sensing data includes: Calculate the weighted sum average of the time similarity and the type similarity to obtain the sensing accuracy parameter corresponding to the sensing data; wherein the calculation weight corresponding to the time similarity is inversely proportional to the data concentration corresponding to all the data time points, and the calculation weight corresponding to the type similarity is inversely proportional to the type discrimination corresponding to all the error types; the type discrimination is the average value of the number of all data belonging to the same type in all the error types.

8. The method for controlling the monitoring angle of a 3D printing device based on image recognition according to claim 1, wherein: The determining, based on the accurate sensing parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device, an image monitoring angle corresponding to the 3D printing device includes: Obtaining a current monitoring posture of an image monitoring device corresponding to the 3D printing device; Based on a preset correspondence between posture and image angle, determining a current monitoring angle of the image monitoring device according to the current monitoring posture; Calculating an angle correction value inversely proportional to the sensing accuracy parameter; The angle correction value is adjusted by adjusting the current monitoring angle toward a preset optimal monitoring angle to obtain an image monitoring angle corresponding to the 3D printing device.

9. A 3D printing equipment monitoring angle control system based on image recognition, characterized in that: The system comprises: An acquisition module is used to acquire historical working data and sensor data of the 3D printing equipment to be monitored; A prediction module, configured to predict historical operating failures corresponding to the 3D printing device based on the sensor data based on a prediction algorithm; A first determining module, configured to determine a sensing accuracy parameter corresponding to the sensing data based on the historical working failure and the historical working data; The second determination module is used to determine the image monitoring angle corresponding to the 3D printing device based on the accurate sensing parameters and the current monitoring posture of the image monitoring device corresponding to the 3D printing device; the image monitoring angle is used to indicate the framing angle of at least one image monitoring device relative to the 3D printing device.

10. A 3D printing equipment monitoring angle control system based on image recognition, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the 3D printing device monitoring angle control method based on image recognition according to any one of claims 1 to 8.

Images