A monitoring instrument, method, and electronic equipment for quality inspection of bolt tightening operations.

Abstract

This invention discloses a monitoring instrument, method, and electronic device for quality inspection of bolt tightening operations. The monitoring instrument includes: a recording unit for acquiring tightening data of bolt tightening tools during bolt tightening operations; the tightening data includes pressure time-series data; an analysis unit for inputting the pressure time-series data into a built-in processing model for analysis and processing to obtain quality inspection data; the processing model is pre-trained using a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing bolt tightening quality; and an interaction unit for providing real-time prompts and / or alarms at the work site based on the quality inspection data. Its advantages are: the invention is timely and efficient, eliminating the need for secondary manual quality inspection; it inspects each bolt to avoid omissions; and the entire system operates automatically, overcoming the drawbacks of large human error and improving accuracy.

Description

Technical Field

[0001] This invention relates to the field of bolt fastening technology, and more specifically to a monitoring instrument, method, and electronic device for quality inspection of bolt fastening operations. Background Technology

[0002] In the assembly of large equipment such as wind power and petrochemical plants, the requirements for bolt tightening are extremely high, necessitating the installation of bolts with a constant torque. For some large bolts, such as those with a specification of M36 or larger, commonly used torque-setting tools include hydraulic wrenches and hydraulic tensioners. Hydraulic wrenches convert pressure into torque to tighten bolts with a constant torque. First, the output pressure value of the hydraulic wrench pump is set, and this set pressure value determines the torque value output by the hydraulic wrench. When the hydraulic wrench applies the rated torque value to the bolt, and the bolt stops rotating, the preload is considered to have reached the set value. Hydraulic tensioners tighten bolts using a stretching method. Hydraulic force elongates the bolt rod, causing elastic deformation and thus applying preload to the bolt.

[0003] After on-site construction is completed, quality inspectors need to conduct random checks on the bolt tightness. The current standard method is the scribing method. For example, if 100 bolts are tightened on-site using a hydraulic wrench with a set torque of 5000 Nm, the quality inspectors will conduct random checks using the scribing method. First, a straight line is drawn on the bolt and nut. Then, using 95% of the set torque (4750 Nm), the hydraulic wrench is used to tighten the bolt to this torque value. If the bolt and nut do not move relative to each other (i.e., the straight line does not become two segments), it proves that the bolt's preload is not less than 95% of the set value. Then, using 105% of the set torque (5250 Nm), the hydraulic wrench is used to tighten the bolt to this torque value. If the bolt and nut move relative to each other (i.e., the straight line becomes two segments), it proves that the bolt's preload is not greater than 105% of the set value, meaning the bolt tightening meets the requirements. If the bolt and nut move relative to each other at 95% torque, it indicates that the actual torque value of the bolt in the construction operation is too small. If the bolt and nut do not move relative to each other at 105% torque, it indicates that the actual torque value of the bolt in the construction operation is too large.

[0004] If the torque is too small or too large, it does not comply with the construction process specifications and requires rectification.

[0005] Therefore, the current quality inspection methods have the following problems:

[0006] 1. There is a lag, and a second quality inspection is required after the bolts are tightened on site, which is inefficient and has poor timeliness;

[0007] 2. Using a sampling inspection method cannot achieve 100% quality inspection, and there are omissions.

[0008] 3. Human error is significant, easily affected by ambient light, and the lines themselves may not be perfectly standardized. Even slight movements are not easily detected by the human eye, resulting in low accuracy.

[0009] 4. Currently, the on-site data is recorded via video and photos, but the data cannot be archived and cannot be traced. Summary of the Invention

[0010] In view of the technical defects mentioned in the background art, the purpose of the embodiments of the present invention is to provide a monitoring instrument, method and electronic device for quality inspection of bolt tightening operations, which aims to at least solve one of the technical problems in the related art to a certain extent.

[0011] To achieve the above objectives, in a first aspect, embodiments of the present invention provide a monitoring instrument for quality inspection of bolt tightening operations, comprising:

[0012] A recording unit is used to acquire tightening data of bolt tightening tools during bolt tightening operations; wherein, the tightening data includes pressure timing data;

[0013] The analysis unit is used to input the pressure time series data into the built-in processing model for analysis and processing to obtain quality inspection data; wherein, the processing model is pre-trained by a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing the bolt fastening quality.

[0014] An interactive unit is used to provide real-time prompts and / or alarms at the work site based on the quality inspection data.

[0015] In a preferred implementation of this application, the analysis unit is further configured to:

[0016] The fastening data and the analyzed quality inspection data are uploaded to the cloud server;

[0017] If there is no network, cache it locally first, and then send it to the cloud server after the network is restored.

[0018] As a specific implementation of this application, before analysis and processing, the real-time collected pressure time series data is segmented through a fixed-length window; then the segmented fixed-length data is input into the processing model for forward calculation.

[0019] As one specific implementation of this application, the processing model includes convolutional layers, LSTM layers, and fully connected layers;

[0020] The convolutional layer uses convolutional kernels of different scales to perform convolution, and extracts features of different granularities through local feature extraction and hierarchical learning;

[0021] The LSTM layer captures long-term dependencies in the pressure time-series data;

[0022] The fully connected layer integrates local features and long-term dependencies and maps them to the final output space to complete the corresponding task branch.

[0023] As a specific implementation of this application, the specific evaluation process for bolt fastening quality assessment includes:

[0024] The pressure timing data corresponding to each bolt tightening process is fitted into a pressure curve, and then the curve is divided according to the tightening stroke of the bolt tightening tool to obtain the corresponding multi-segment stroke curves, which are denoted as stroke curve 1, stroke curve 2 to stroke curve x.

[0025] Each stroke curve is then segmented and coded to obtain each change segment, and it is determined whether the continuity of the corresponding change segment in each stroke curve conforms to a preset rule; wherein, the segmentation is performed according to a set pressure change trend threshold.

[0026] If the pattern is consistent, it indicates that the bolt is tightened well; otherwise, it indicates that an abnormality occurred during the tightening process.

[0027] As a specific implementation of this application, the step of segmenting and encoding each travel curve segment to obtain each change segment, and determining whether the continuity of the corresponding change segment in each travel curve segment conforms to a preset rule, specifically includes:

[0028] Each travel curve is segmented and coded to obtain at least the corresponding Class A and Class B change segments. The change segments obtained from travel curve 1 are coded as 1A and 1B, the change segments obtained from travel curve 2 are coded as 2A and 2B, the change segments obtained from travel curve 3 are coded as 3A and 3B, and so on.

[0029] Analyze the pressure values ​​of type A and type B change segments in each stroke curve to see if the continuity between adjacent segments conforms to a preset rule; wherein, the preset rule is that 1B and 2A have the same height, 2B and 3A have the same height, and so on.

[0030] Secondly, embodiments of the present invention also provide a method for quality inspection of bolt tightening operations, applied to a monitoring instrument for quality inspection of bolt tightening operations as described in the first aspect, the method comprising:

[0031] Acquire tightening data of bolt tightening tools during bolt tightening operations; wherein, the tightening data includes pressure timing data;

[0032] The pressure time series data is fed into the deployed processing model for analysis and processing to obtain quality inspection data; wherein, the processing model is pre-trained by a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing the bolt fastening quality.

[0033] Based on the quality inspection data, real-time prompts and / or alarms will be provided at the work site.

[0034] Thirdly, embodiments of the present invention also provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for quality inspection of bolt tightening operations as described in the second aspect.

[0035] The technical solution provided by this invention analyzes and processes bolt tightening data from a built-in processing model to obtain quality inspection data. Based on this data, real-time prompts and / or alarms are provided at the work site. The processing model is pre-trained using a deep learning algorithm and outputs at least a regression branch for determining the number of bolts and a classification branch for assessing bolt tightening quality. This results in a time-efficient and effective solution, eliminating the need for manual secondary quality inspection after bolt tightening. Each bolt is inspected to prevent omissions, and the bolt tightening process is effectively recorded and analyzed. For bolts missed or with poor tightening quality, the tightening process and results are promptly and efficiently fed back to relevant personnel for intelligent quality inspection analysis. Furthermore, the entire solution operates automatically, overcoming the limitations of human error and improving accuracy. Attached Figure Description

[0036] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below.

[0037] Figure 1 This is a schematic diagram of a monitoring instrument for quality inspection of bolt tightening operations provided in an embodiment of the present invention;

[0038] Figure 2 This is a schematic diagram of the network structure of a processing model provided in an embodiment of the present invention;

[0039] Figure 3 This is a schematic diagram of a multi-segment stroke curve provided in an embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of segmenting and encoding each segment of a travel curve according to an embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of a continuity determination provided by an embodiment of the present invention;

[0042] Figure 6 This is a flowchart of a method for quality inspection of bolt tightening operations provided in an embodiment of the present invention;

[0043] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0046] Throughout this specification, references to "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination.

[0047] It should be noted that, unless otherwise specified, the technical terms used in this embodiment have the common meaning understood in the relevant technical field; and the examples given are related to the enterprise's applications, but are not intended to limit the scope of the application.

[0048] Please refer to Figure 1 The present invention provides a monitoring instrument for quality inspection of bolt tightening operations, comprising:

[0049] A recording unit is used to acquire tightening data of bolt tightening tools during bolt tightening operations; wherein, the tightening data includes pressure timing data;

[0050] The analysis unit is used to input the pressure time series data into the built-in processing model for analysis and processing to obtain quality inspection data; wherein, the processing model is pre-trained by a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing the bolt fastening quality.

[0051] An interactive unit is used to provide real-time prompts and / or alarms at the work site based on the quality inspection data.

[0052] The bolt tightening tool is illustrated by using a hydraulic wrench or a hydraulic tensioner as an example; the recording unit obtains the pressure data in the hydraulic circuit of the hydraulic wrench or hydraulic tensioner, forms a change curve, and obtains the corresponding pressure time sequence data; the analysis unit and the recording unit are wirelessly connected; the interaction unit uses a display screen.

[0053] Furthermore, the analysis unit is also used for:

[0054] The fastening data and the analyzed quality inspection data are uploaded to the cloud server;

[0055] If there is no network, cache it locally first, and then send it to the cloud server after the network is restored.

[0056] When applied, the monitoring device includes:

[0057] (1) A display screen that is interactive;

[0058] (2) Communication module. The communication module consists of two parts: a Bluetooth module and a 5G module. The Bluetooth module is used to communicate with the recording unit via Bluetooth to obtain real-time pressure data. The 5G module is used to upload the data recorded on site and the quality inspection data analyzed to the cloud server.

[0059] (3) Intelligent chip, deploy the processing model to perform analysis and processing, so that the monitoring instrument has edge computing capabilities;

[0060] (4) Power supply module, used for power supply;

[0061] (5) Storage module, which can cache the data on site locally when there is no network, and send it to the cloud server when there is network.

[0062] It should be noted that during bolt tightening operations, information such as the number of bolts to be tightened and the corresponding torque value can be obtained by scanning the bolt tightening point and the code (such as QR code) of the bolt tool. This information is familiar to those skilled in the art and will not be elaborated here.

[0063] In this embodiment, before analysis and processing, the real-time pressure time series data is segmented through a fixed-length window; then the segmented fixed-length data is input into the processing model for forward calculation.

[0064] Furthermore, the processing model includes convolutional layers, LSTM layers, and fully connected layers;

[0065] The convolutional layer uses convolutional kernels of different scales to perform convolution, and extracts features of different granularities through local feature extraction and hierarchical learning;

[0066] The LSTM layer captures long-term dependencies in the pressure time-series data;

[0067] The fully connected layer integrates local features and long-term dependencies and maps them to the final output space to complete the corresponding task branch.

[0068] In this embodiment, refer to Figure 2 As shown, a network structure combining 1DCNN and LSTM was constructed. This network structure sequentially performs feature extraction, target localization, and state classification through convolutional layers, bidirectional LSTM layers, and fully connected layers.

[0069] During training, Dropout is used to prevent overfitting; the LSTM layer solves the problem of vanishing or exploding gradients in RNNs through a gating mechanism, and can also capture long-term dependencies in time series data; 1DCNN is responsible for extracting local features, and LSTM is responsible for modeling the global context. The combination of the two can utilize both local and global information to form a more robust model.

[0070] The model output has two branches:

[0071] Branch 1 is a regression task that obtains the start and end range, category, and confidence level of a single bolt tightening.

[0072] Branch 2 is a classification task that assesses the quality level of trend changes.

[0073] The algorithm determines the start and end points of pressure on each bolt. Within this range, the pressure change trend is categorized to assess whether the bolt experiences normal stress and a good tightening condition during the tightening process. Furthermore, the pressure change trend is segmented according to its speed (gradual, rapid, etc.), and each segment is analyzed in more detail. This allows for a more thorough and detailed analysis of the bolt's stress changes, leading to a more accurate final quality assessment. For specific details, please refer to [link / reference]. Figures 3 to 5 And subsequent detailed descriptions.

[0074] The specific evaluation process for assessing the bolt fastening quality includes:

[0075] The pressure timing data corresponding to each bolt tightening process is fitted into a pressure curve, and then the curve is divided according to the tightening stroke of the bolt tightening tool to obtain the corresponding multi-segment stroke curves, which are denoted as stroke curve 1, stroke curve 2 to stroke curve x.

[0076] That is, during the operation of a hydraulic wrench, the tightening process of a bolt consists of several tightening strokes. By analyzing the process data of each stroke in detail, the process is first divided into 6 curve segments, numbered 1-6, as follows: Figure 3 As shown, X represents the last trip, X=6;

[0077] Each stroke curve is then segmented and encoded to obtain each change segment, and it is determined whether the continuity of the corresponding change segment in each stroke curve conforms to a preset rule; wherein, the segmentation is performed according to a set pressure change trend threshold; that is, each stroke is then segmented.

[0078] If the pattern is consistent, it indicates that the bolt is tightened well; otherwise, it indicates that an abnormality occurred during the tightening process.

[0079] The process of segmenting and encoding each travel curve segment to obtain each change segment, and determining whether the continuity of the corresponding change segment in each travel curve segment conforms to a preset rule, specifically includes:

[0080] Each travel curve segment is divided and coded to obtain at least two corresponding type A and type B change segments. The change segments obtained from travel curve 1 are coded as 1A and 1B, those from travel curve 2 as 2A and 2B, those from travel curve 3 as 3A and 3B, and so on. Figure 4 ;

[0081] For ease of understanding, the meaning of each variation section is shown in Table 1.

[0082] Table 1 Explanation of the meaning of each change segment.

[0083] coding meaning A The hydraulic wrench started working, applying torque to the nut, but it did not turn the nut. B With continued pressure applied, the nut rotates along with the hydraulic wrench. C The hydraulic wrench can only rotate about 30 degrees at a time. If pressure is applied to the hydraulic wrench further, it will stop rotating. D The hydraulic wrench can still rotate, but the maximum torque output is no longer sufficient to turn the nut. At this point, the bolt is considered to be properly tightened. E The pressure drops from maximum to zero, and then another cycle begins.

[0084] It should be noted that during the initial tightening stage, the characteristic values ​​of B / C / D are not particularly obvious, so no further division is required at this time.

[0085] The logic of the curves follows these rules:

[0086] The stroke curve image has 1-B, 2-B, 3-B, ... (X-1)B, XD. If it conforms to the above pattern, it means that the bolt is fastened well.

[0087] The preset rules, during the bolt tightening process with a hydraulic wrench, will involve the following stages:

[0088] (1) Initial preload stage (A): In this stage, a very small force is required to rotate the bolt. The initial preload stage may involve several pressure curve strokes; such as Figure 3 The first and second journeys in the middle;

[0089] (2) Tightening stress stage (abbreviated as B): In this stage, there is a clear inflection point of slope change. Since the small output force cannot overcome the friction of the bolt, the output force also increases with the increase of pressure. When the output force increases to a certain extent, the bolt and the hydraulic wrench move together. During this process, it will experience several pressure curve strokes; such as Figure 3 The third and fourth steps in the sequence;

[0090] (3) Near completion of tightening: In this stage, the pressure rises relatively slowly as it approaches the target pressure value; for example... Figure 3 The 5th journey;

[0091] (4) Tightening completion stage: In this stage, the pressure is a relatively standard trapezoid, and at this point, the bolt no longer rotates under the maximum torque (corresponding to the maximum pressure); Figure 3 The 6th step in the process.

[0092] Analyze the pressure values ​​of type A and type B change segments in each stroke curve to see if the continuity between adjacent segments conforms to a preset rule; wherein, the preset rule is that 1B and 2A have the same height, 2B and 3A have the same height, and so on.

[0093] Reference Figure 5 In practical applications, the focus is on analyzing the continuity of the B-type change segment curve and the trend change of the D-type change segment curve for each stroke; D-type indicates that the bolt has been tightened and is no longer rotating, reaching the set target torque value.

[0094] For example, the starting pressure of the 1-B curve is 80 bar, the ending pressure of the 1-B curve is 100 bar, and the starting pressure of the 2-A curve is generally close to the ending pressure of the 1-B curve.

[0095] The above solution analyzes bolt tightening data from a built-in processing model to obtain quality inspection data. Based on this data, real-time prompts and / or alarms are provided at the work site. The processing model, pre-trained using deep learning algorithms, outputs at least a regression branch for determining the number of bolts and a classification branch for assessing bolt tightening quality. This results in a time-efficient and effective solution, eliminating the need for manual secondary quality inspection after bolt tightening. Each bolt is inspected to prevent omissions, effectively recording and analyzing the bolt tightening process. For missed bolts or poor tightening quality, 5G transmission technology allows for timely and efficient feedback of the tightening process and results to relevant personnel, facilitating intelligent quality inspection analysis. Furthermore, the automated operation of the entire solution overcomes the limitations of human error, improving accuracy.

[0096] Reference Figure 6 Based on the same inventive concept, this invention also provides a method for quality inspection of bolt tightening operations, applied to the aforementioned monitoring instrument for quality inspection of bolt tightening operations, the method comprising:

[0097] S101, acquire the tightening data of the bolt tightening tool during bolt tightening operation; wherein, the tightening data includes pressure timing data;

[0098] S102, The pressure time series data is input into the deployed processing model for analysis and processing to obtain quality inspection data; wherein, the processing model is pre-trained by a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing the bolt fastening quality.

[0099] S103, provide real-time prompts and / or alarms at the work site based on the quality inspection data.

[0100] Before analysis and processing, the real-time pressure time series data is segmented through a fixed-length window; then the segmented fixed-length data is input into the processing model for forward calculation.

[0101] Furthermore, the specific evaluation process for assessing the bolt fastening quality includes:

[0102] The pressure timing data corresponding to each bolt tightening process is fitted into a pressure curve, and then the curve is divided according to the tightening stroke of the bolt tightening tool to obtain the corresponding multi-segment stroke curves, which are denoted as stroke curve 1, stroke curve 2 to stroke curve x.

[0103] Each stroke curve is then segmented and coded to obtain each change segment, and it is determined whether the continuity of the corresponding change segment in each stroke curve conforms to a preset rule; wherein, the segmentation is performed according to a set pressure change trend threshold.

[0104] If the pattern is consistent, it indicates that the bolt is tightened well; otherwise, it indicates that an abnormality occurred during the tightening process.

[0105] The process of segmenting and encoding each travel curve segment to obtain each change segment, and determining whether the continuity of the corresponding change segment in each travel curve segment conforms to a preset rule, specifically includes:

[0106] Each travel curve is segmented and coded to obtain at least the corresponding Class A and Class B change segments. The change segments obtained from travel curve 1 are coded as 1A and 1B, the change segments obtained from travel curve 2 are coded as 2A and 2B, the change segments obtained from travel curve 3 are coded as 3A and 3B, and so on. This is just an example; please refer to the attached figure for details.

[0107] Analyze the pressure values ​​of type A and type B change segments in each stroke curve to see if the continuity between adjacent segments conforms to a preset rule; wherein, the preset rule is that 1B and 2A have the same height, 2B and 3A have the same height, and so on.

[0108] It should be noted that for a more detailed description of the workflow of the method embodiments, please refer to the aforementioned device embodiments section, which will not be repeated here.

[0109] The entire solution analyzes and processes bolt tightening data from a built-in processing model to obtain quality inspection data. Based on this data, real-time prompts and / or alarms are provided at the work site. The processing model, pre-trained using deep learning algorithms, outputs at least a regression branch for determining the number of bolts and a classification branch for assessing bolt tightening quality. This results in a time-efficient and effective solution, eliminating the need for manual secondary quality inspection after bolt tightening. Each bolt is inspected to prevent omissions, and the bolt tightening process is effectively recorded and analyzed. For bolts missed or with poor tightening quality, the tightening process and results are promptly and efficiently fed back to relevant personnel for intelligent quality inspection analysis. Furthermore, the automated operation of the entire solution overcomes the limitations of human error, improving accuracy.

[0110] In another embodiment of the present invention, an electronic device is also provided, with reference to... Figure 7The system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for quality inspection of bolt tightening operations as described above.

[0111] In the embodiments provided in this application, it should be understood that the disclosed methods can also be implemented in other ways. The system embodiments described above are merely illustrative. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or using a combination of dedicated hardware and computer instructions.

[0112] In addition, the functional units in the various embodiments of the present invention can be integrated together to form an independent part, or each unit can exist independently, or two or more units can be integrated to form an independent part. When each module is used, information is collected and stored only with the full authorization of the relevant user or organization and in compliance with relevant laws and regulations, and the security and privacy of the data are protected. Unauthorized access is strictly prohibited.

[0113] Data processing will be conducted within the scope of the law and will not exceed the authorized purpose and scope; at the same time, the authorizing party has the right to access, correct, delete, restrict processing, refuse, and so on of its personal data; and strictly comply with applicable laws and regulations and conduct compliance reviews.

[0114] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. It should be noted that, in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0115] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A monitoring instrument for quality inspection of bolt tightening operations, characterized in that, include: A recording unit is used to acquire tightening data of bolt tightening tools during bolt tightening operations; wherein, the tightening data includes pressure timing data; The analysis unit is used to input the pressure time series data into the built-in processing model for analysis and processing to obtain quality inspection data; wherein, the processing model is pre-trained by a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing the bolt fastening quality. An interactive unit is used to provide real-time prompts and / or alarms at the work site based on the quality inspection data.

2. The monitoring instrument for quality inspection of bolt tightening operations as described in claim 1, characterized in that, The analysis unit is also used for: The fastening data and the analyzed quality inspection data are uploaded to the cloud server; If there is no network, cache it locally first, and then send it to the cloud server after the network is restored.

3. The monitoring instrument for quality inspection of bolt tightening operations as described in claim 2, characterized in that, Before analysis and processing, the real-time pressure time series data is segmented through a fixed-length window; then the segmented fixed-length data is input into the processing model for forward calculation.

4. A monitoring instrument for quality inspection of bolt tightening operations as described in claim 3, characterized in that, The processing model includes convolutional layers, LSTM layers, and fully connected layers; The convolutional layer uses convolutional kernels of different scales to perform convolution, and extracts features of different granularities through local feature extraction and hierarchical learning; The LSTM layer captures long-term dependencies in the pressure time-series data; The fully connected layer integrates local features and long-term dependencies and maps them to the final output space to complete the corresponding task branch.

5. A monitoring instrument for quality inspection of bolt tightening operations as described in claim 4, characterized in that, The specific evaluation process for assessing the bolt fastening quality includes: The pressure timing data corresponding to each bolt tightening process is fitted into a pressure curve, and then the curve is divided according to the tightening stroke of the bolt tightening tool to obtain the corresponding multi-segment stroke curves, which are denoted as stroke curve 1, stroke curve 2 to stroke curve x. Each stroke curve is then segmented and coded to obtain each change segment, and it is determined whether the continuity of the corresponding change segment in each stroke curve conforms to a preset rule; wherein, the segmentation is performed according to a set pressure change trend threshold. If the pattern is consistent, it indicates that the bolt is tightened well; otherwise, it indicates that an abnormality occurred during the tightening process.

6. A monitoring instrument for quality inspection of bolt tightening operations as described in claim 5, characterized in that, The process of segmenting and encoding each travel curve segment to obtain each change segment, and determining whether the continuity of the corresponding change segment in each travel curve segment conforms to a preset rule, specifically includes: Each travel curve is segmented and coded to obtain at least the corresponding Class A and Class B change segments. The change segments obtained from travel curve 1 are coded as 1A and 1B, the change segments obtained from travel curve 2 are coded as 2A and 2B, the change segments obtained from travel curve 3 are coded as 3A and 3B, and so on. Analyze the pressure values ​​of type A and type B change segments in each stroke curve to see if the continuity between adjacent segments conforms to a preset rule; wherein, the preset rule is that 1B and 2A have the same height, 2B and 3A have the same height, and so on.

7. A method for quality inspection of bolt tightening operations, characterized in that, The method applied to the monitoring instrument for quality inspection of bolt tightening operations as described in claim 1 includes: Acquire tightening data of bolt tightening tools during bolt tightening operations; wherein, the tightening data includes pressure timing data; The pressure time series data is fed into the deployed processing model for analysis and processing to obtain quality inspection data; wherein, the processing model is pre-trained by a deep learning algorithm and outputs at least a regression task branch for determining the number of bolts and a classification task branch for assessing the bolt fastening quality. Based on the quality inspection data, real-time prompts and / or alarms will be provided at the work site.

8. The method as described in claim 7, characterized in that, The specific evaluation process for assessing the bolt fastening quality includes: The pressure timing data corresponding to each bolt tightening process is fitted into a pressure curve, and then the curve is divided according to the tightening stroke of the bolt tightening tool to obtain the corresponding multi-segment stroke curves, which are denoted as stroke curve 1, stroke curve 2 to stroke curve x. Each stroke curve is then segmented and coded to obtain each change segment, and it is determined whether the continuity of the corresponding change segment in each stroke curve conforms to a preset rule; wherein, the segmentation is performed according to a set pressure change trend threshold. If the pattern is consistent, it indicates that the bolt is tightened well; otherwise, it indicates that an abnormality occurred during the tightening process.

9. The method as described in claim 8, characterized in that, The process of segmenting and encoding each travel curve segment to obtain each change segment, and determining whether the continuity of the corresponding change segment in each travel curve segment conforms to a preset rule, specifically includes: Each travel curve is segmented and coded to obtain at least the corresponding Class A and Class B change segments. The change segments obtained from travel curve 1 are coded as 1A and 1B, the change segments obtained from travel curve 2 are coded as 2A and 2B, the change segments obtained from travel curve 3 are coded as 3A and 3B, and so on. Analyze the pressure values ​​of type A and type B change segments in each stroke curve to see if the continuity between adjacent segments conforms to a preset rule; wherein, the preset rule is that 1B and 2A have the same height, 2B and 3A have the same height, and so on.

10. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement a method for quality inspection of bolt tightening operations as described in any one of claims 7-9.

Images