Intelligent integrated control system and method for angle grinder

Abstract

The invention relates to the field of intelligent integrated control, and particularly discloses an angle grinder intelligent integrated control system and method.The angle grinder intelligent integrated control method comprises the steps that firstly, angle grinder machining data collected by a database, temperature data, collected by a sensor, of an angle grinder working area at multiple preset time points and rotating speed data, collected by a sensor, of the angle grinder at the multiple preset time points are obtained; and then feature extraction and correlation analysis are performed on the two by using a deep learning technology, and finally a classification result is obtained through a classifier to judge whether the water supply flow of the angle grinder needs to be adjusted, so that the waste of water and energy is reduced, the production efficiency is improved, and more efficient and more accurate water supply adjustment is provided.

Description

Technical Field

[0001] This application relates to the field of intelligent integrated control, and more specifically, to an intelligent integrated control system and method for a angle grinder. Background Art

[0002] With the development of electric technology, cutting tools have emerged, and the cutting tools mainly include angle grinders and cutting machines. An angle grinder uses a high-speed rotating thin grinding wheel, a rubber grinding wheel, a wire wheel, etc. to grind, cut, remove rust, and polish metal components.

[0003] In the stone processing industry, considering that stone is a material with relatively high hardness, in order to ensure the precision and smoothness of stone processing, workers often need to cooperate with a certain amount of water flow for cooling and lubrication when using an angle grinder. However, in the traditional stone processing process, a large amount of continuous large-flow water supply is often used. Although this method can effectively reduce the heat generated by friction and avoid tool damage due to overheating, the continuous large-flow water supply will not only waste a large amount of water resources, but also, during the operation process, excessive water flow may affect the working state of the angle grinder, especially in the stone polishing process.

[0004] Therefore, an intelligent integrated control system and method for an angle grinder are desired. Summary of the Invention

[0005] To solve the above technical problems, this application is proposed. Embodiments of this application provide an intelligent integrated control system and method for an angle grinder, which first obtain the angle grinder processing data collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points, then use deep learning technology to perform feature extraction and correlation analysis on the two, and finally obtain a classification result through a classifier to determine whether the water supply flow of the angle grinder needs to be adjusted, so as to reduce the waste of water and energy, improve production efficiency, and provide more efficient and more accurate water supply regulation.

[0006] According to one aspect of this application, an intelligent integrated control system for an angle grinder is provided, which includes:

[0007] An angle grinder water supply data acquisition module, configured to obtain the angle grinder processing data collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points;

[0008] An angle grinder water supply data extraction module, configured to extract an angle grinder processing data semantic global feature vector and an angle grinder multi-modal correlation feature vector from the angle grinder processing data collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points;

[0009] An angle grinder water supply flow adjustment judgment module, configured to judge whether the water supply flow of the angle grinder needs to be adjusted based on the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder.

[0010] According to another aspect of the present application, there is provided an intelligent integrated control method for an angle grinder, which includes:

[0011] Obtain the angle grinder processing data collected by the database, the temperature data of multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points;

[0012] Extract the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder from the angle grinder processing data collected by the database, the temperature data of multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points;

[0013] Based on the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder, judge whether the water supply flow of the angle grinder needs to be adjusted.

[0014] Compared with the prior art, an intelligent integrated control system and method for an angle grinder provided by the present application first obtains the angle grinder processing data collected by the database, the temperature data of multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points, and then uses deep learning technology to perform feature extraction and correlation analysis on the two, and finally obtains a classification result through a classifier to judge whether the water supply flow of the angle grinder needs to be adjusted, thereby reducing waste of water and energy, improving production efficiency, and providing more efficient and accurate water supply adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 It is a block diagram schematic diagram of an intelligent integrated control system for an angle grinder according to an embodiment of the present application.

[0017] Figure 2 It is a block diagram schematic diagram of an angle grinder water supply data extraction module in an intelligent integrated control system for an angle grinder according to an embodiment of the present application.

[0018] Figure 3 It is a schematic block diagram of the water supply flow adjustment and judgment module in the intelligent integrated control system of a angle grinder according to an embodiment of the present application.

[0019] Figure 4 It is a flowchart of the intelligent integrated control method of the angle grinder according to an embodiment of the present application. Detailed implementation manners

[0020] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0021] The special term "exemplary" herein means "serving as an example, embodiment or illustration". Any embodiment described as "exemplary" herein is not necessarily to be construed as superior or better than other embodiments.

[0022] In addition, in order to better illustrate the present application, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present application can also be implemented without some specific details. In some instances, methods, means, elements and circuits well known to those skilled in the art are not described in detail so as to highlight the gist of the present application.

[0023] Furthermore, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality of" means two or more unless otherwise specifically defined.

[0024] Figure 1 It is a schematic block diagram of the intelligent integrated control system of the angle grinder according to an embodiment of the present application. As Figure 1As shown in the figure, the intelligent integrated control system 100 of a angle grinder according to an embodiment of the present application includes: an angle grinder water supply data acquisition module 110, configured to acquire the angle grinder processing data collected by a database, the temperature data of multiple predetermined time points in the working area of the angle grinder collected by a sensor, and the rotation speed data of the angle grinder at multiple predetermined time points; an angle grinder water supply data extraction module 120, configured to extract a semantic global feature vector of the angle grinder processing data and a multi-modal association feature vector of the angle grinder from the angle grinder processing data collected by the database, the temperature data of multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points; an angle grinder water supply flow adjustment judgment module 130, configured to judge whether the water supply flow of the angle grinder needs to be adjusted based on the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder.

[0025] In the above intelligent integrated control system 100 of the angle grinder, the angle grinder water supply data acquisition module 110 is configured to acquire the angle grinder processing data collected by a database, the temperature data of multiple predetermined time points in the working area of the angle grinder collected by a sensor, and the rotation speed data of the angle grinder at multiple predetermined time points. It should be understood that the processing data of the angle grinder usually includes the number of water ink sheets and the material roughness, and these data help to analyze the performance of the angle grinder under different working conditions. The temperature data is used to collect the temperature of the working area of the angle grinder in real time through a sensor, and the temperature change directly reflects the friction condition of the tool. Excessive temperature may cause tool damage or a decline in processing quality. The rotation speed data is used to understand the rotation speed change of the angle grinder, and the fluctuation of the rotation speed may mean that the angle grinder has a fault or abnormal operation. Therefore, it is necessary to monitor at multiple time points. These data can be collected in real time through sensors connected to the angle grinder control system and stored in the database. Through these data, strong data support can be provided for subsequent processing process adjustment, fault warning and optimization decision-making, so as to improve the processing accuracy, reduce the risk of resource waste and equipment damage.

[0026] Specifically, with the continuous progress of electric technology, cutting tools have emerged, among which angle grinders and cutting machines are relatively common types. Angle grinders use high-speed rotating thin grinding wheels, rubber grinding wheels, wire wheels, etc. to perform grinding, cutting, rust removal, and polishing operations on metal components. In the field of stone processing, due to the high hardness of stone, in order to ensure processing accuracy and surface finish, workers usually need to use water flow for cooling and lubrication when using an angle grinder. However, in traditional stone processing methods, continuous large-flow water supply is often adopted. Although this method can effectively reduce the heat generated by friction and prevent the tool from being damaged due to overheating, the long-term large-flow water supply will not only cause a large waste of water resources, but also in actual operation, too much water flow may interfere with the normal working state of the angle grinder, especially in the stone polishing stage, affecting the processing effect. Therefore, in the technical solution of this application, by obtaining the angle grinder processing data collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points, and combining deep learning technology, it is determined whether the water flow needs to be adjusted, so as to reduce the waste of water and energy, improve production efficiency at the same time, and achieve more efficient and accurate water supply control.

[0027] In the above-mentioned angle grinder intelligent integrated control system 100, the angle grinder water supply data extraction module 120 is used to extract the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder from the angle grinder processing data collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points. It should be understood that the semantic global feature vector and multi-modal association feature vector of the angle grinder processing data include key operation parameters (such as the number of mesh of the water grinding sheet, material roughness), temperature, rotation speed, etc. during the processing process. They can reflect the performance of the angle grinder under different working conditions. By extracting the global features and multi-modal features of these data, more efficient data analysis and processing can be achieved, so as to realize in-depth analysis of the working state of the angle grinder, optimize the processing process, and improve the intelligent monitoring and early warning capabilities.

[0028] Figure 2 Schematic block diagram of the angle grinder water supply data extraction module in the angle grinder intelligent integrated control system according to an embodiment of the present application. As Figure 2As shown, in a specific embodiment of the present application, the angle grinder water supply data extraction module 120 includes: an angle grinder processing data feature extraction unit 121, configured to extract features from the angle grinder processing data collected by the database to obtain the semantic global feature vector of the angle grinder processing data; an angle grinder working area temperature feature extraction unit 122, configured to extract features from the temperature data at multiple predetermined time points in the angle grinder working area to obtain the angle grinder temperature feature vector; an angle grinder rotation speed feature extraction unit 123, configured to extract features from the rotation speed data of the angle grinder at multiple predetermined time points to obtain the angle grinder rotation speed feature vector; and an angle grinder multi-modal feature fusion unit 124, configured to fuse the angle grinder temperature feature vector and the angle grinder rotation speed feature vector to obtain the angle grinder multi-modal association feature vector.

[0029] It should be understood that the purpose of extracting features from the angle grinder processing data collected by the database is to extract key information from the original data that can accurately describe the processing process and reveal potential laws in the processing process. Among them, the angle grinder processing data usually includes information in multiple dimensions such as feed speed, grinding depth, working load, processing time, number of water mill sheets, and material roughness. These data record the changes in various parameters of the angle grinder during the processing process. In order to convert these multi-dimensional data into a meaningful representation, it is necessary to extract features from the data, that is, to extract key information from the original data that can reveal the processing state and process effect. Through the feature extraction of the angle grinder processing data, the obtained semantic global feature vector can effectively summarize the important information in the processing process and reflect the overall performance of the angle grinder under different working conditions.

[0030] Furthermore, the temperature data can reflect the heat changes of the angle grinder during operation. Excessive temperature may lead to rapid tool wear, reduced processing quality, or equipment damage. Feature extraction of the temperature data helps to detect abnormalities in a timely manner and prevent potential failures or problems. Also, considering that the original temperature data is usually time series data, containing a large amount of noise and redundant information. Through feature extraction, the data dimension can be reduced while retaining the key change patterns, helping to achieve more efficient and accurate analysis.

[0031] Furthermore, the rotational speed is a key parameter for measuring the working efficiency and stability of the angle grinder. Fluctuations in the rotational speed may indicate faults or abnormalities in the angle grinder. Especially during the machining process, the instability of the rotational speed may directly affect the machining accuracy, surface quality, and equipment safety. By extracting the characteristics of the rotational speed data, it is possible to help identify problems in a timely manner, optimize the process, and achieve fault prediction and maintenance of the equipment. Moreover, the original rotational speed data is usually time-series data collected by sensors at multiple time points. These data may be affected by factors such as noise and interference and contain a large amount of redundant information. Through feature extraction, key rotational speed features can be refined from these data to help reveal the laws, trends, and abnormalities of rotational speed changes.

[0032] In particular, temperature and rotational speed respectively provide different information about the operation of the equipment. Among them, temperature reflects the thermal state of the equipment, while rotational speed shows its operating efficiency and load changes. Analyzing only one of these features may not accurately identify the overall operating condition of the equipment because there may be a correlation between the two. For example, fluctuations in rotational speed under high load may cause the temperature to rise, and vice versa. By fusing these two features, the comprehensive performance and potential faults of the equipment can be captured more accurately. Among them, the fusion method can be achieved through simple splicing, weighted combination, or a multi-modal model based on deep learning. These methods can effectively combine the correlation between temperature and rotational speed to form a more discriminative feature vector, thereby improving the accuracy and efficiency of fault diagnosis, performance prediction, and equipment maintenance.

[0033] In a specific embodiment of the present application, the angle grinder machining data feature extraction unit 121 includes: passing the angle grinder machining data collected by the database through an angle grinder machining data semantic feature encoder to obtain a plurality of angle grinder machining data semantic feature vectors; splicing the plurality of angle grinder machining data semantic feature vectors into the angle grinder machining data semantic global feature vector.

[0034] It should be understood that the original processing data often contains a large amount of noise and redundant information, and directly using this data for analysis or training a model may reduce efficiency and accuracy. Through a semantic feature encoder, the data can be mapped to a new feature space, extracting high-dimensional and abstract features related to the processing process. These features can better reflect the core characteristics of the processing process, such as processing quality, equipment load, and potential failure modes. Specifically, the semantic feature encoder for angle grinder processing data performs feature extraction based on deep learning. Through training on a large amount of data, it automatically learns effective features that can characterize the operating state of the angle grinder, thereby reducing the dimension and noise of the data, enhancing the model's learning ability for complex data patterns, and finally generating multiple semantic feature vectors of angle grinder processing data. Specifically, passing the angle grinder processing data collected by the database through the semantic feature encoder for angle grinder processing data to obtain multiple semantic feature vectors of angle grinder processing data includes: performing word segmentation on the angle grinder processing data collected by the database to obtain an angle grinder processing word sequence; using the embedding layer of the semantic feature encoder for angle grinder processing data to map each angle grinder processing word in the angle grinder processing word sequence to an angle grinder processing word embedding vector to obtain a sequence of angle grinder processing word embedding vectors; using the Transformer-based Bert model of the semantic feature encoder for angle grinder processing data to perform global context semantic encoding on the sequence of angle grinder processing word embedding vectors to obtain multiple semantic feature vectors of angle grinder processing data.

[0035] Furthermore, splicing multiple semantic feature vectors of angle grinder processing data into a semantic global feature vector of angle grinder processing data can comprehensively utilize feature information from different sources to construct a more comprehensive and discriminative feature representation. Among them, multiple semantic feature vectors of angle grinder processing data represent various aspects in the angle grinder processing process, such as processing quality, equipment status, and load changes. Each feature vector extracts different detailed information, but a single feature vector may not be able to comprehensively reflect the overall operating state of the equipment. By splicing these feature vectors, different feature information can be integrated into a unified feature space to form a more complete and higher-dimensional global feature vector. This splicing operation can retain the unique information of each feature vector and also capture the correlations between them, helping to improve the accuracy of data analysis and the generalization ability of the model. Specifically, the splicing operation usually connects multiple semantic feature vectors in sequence into a longer vector to cover more dimensional information.

[0036] In a specific embodiment of the present application, the temperature feature extraction unit 122 of the angle grinder working area includes: constructing the temperature data at multiple predetermined time points in the angle grinder working area into an angle grinder temperature input vector; passing the angle grinder temperature input vector through the angle grinder temperature time series encoder to obtain the angle grinder temperature feature vector.

[0037] It should be understood that the temperature data of the angle grinder is an important indicator of the equipment operation status, which can reflect the working load, wear condition, and potential failure risks. However, the temperature value at a single moment cannot comprehensively display the overall status of the equipment because the temperature of the equipment usually changes over time and is affected by various factors such as working load and environmental changes. Integrating the temperature data at multiple time points into an input vector enables the model to capture the changing trend of temperature over time, thereby providing a more accurate status assessment and prediction. Specifically, first, the working area of the angle grinder regularly collects temperature data at predetermined time intervals, and these data points are arranged in chronological order to form a time series. Then, in order to make the temperature data suitable for model input, it is usually necessary to preprocess these data, such as removing noise, smoothing, and normalizing, to ensure data quality and comparability. Finally, the temperature data at multiple time points are concatenated into a feature vector in chronological order, and this vector reflects the changing trend of temperature over time. In this way, the temperature input vector can better represent the thermal state of the equipment over a certain period of time, enabling the model to more accurately analyze the equipment operation status, predict potential failure risks, and optimize maintenance and operation decisions.

[0038] Furthermore, considering that temperature data not only contains static information but also exhibits dynamic characteristics that change over time. The original temperature input vector only contains temperature values at multiple time points, which can reflect the temperature status of the device but lacks a deep understanding of how these data change over time. By using the angle grinder temperature time series encoder, it is possible to effectively capture the time series patterns, change trends, and potential regularities in the temperature data. Specifically, the angle grinder temperature time series encoder typically uses time series models such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or gated recurrent units (GRUs) in deep learning, which can handle and model long-term dependencies in time series data. During this process, the angle grinder temperature input vector is input into the time series encoder, and the time series encoder processes the temperature data at each time point and incorporates past temperature information into the current prediction and feature representation using the memory mechanism within the network. In this way, the encoder can learn the dynamic patterns of temperature changes, such as temperature fluctuations, rising or falling trends, and the relationships between these changes and factors such as device status and load changes. Finally, after being processed by the angle grinder temperature time series encoder, the resulting angle grinder temperature feature vector will contain higher-level abstract features. It is not just a collection of original temperature values but a high-dimensional vector that can accurately reflect the temperature change pattern and its relationship with device performance. Specifically, obtaining the angle grinder temperature feature vector by passing the angle grinder temperature input vector through the angle grinder temperature time series encoder includes: using the fully connected layer of the angle grinder temperature time series encoder to perform fully connected encoding on the angle grinder temperature input vector to extract high-dimensional hidden features of the feature values at each position in the angle grinder temperature input vector; and using the one-dimensional convolutional layer of the angle grinder temperature time series encoder to perform one-dimensional encoding on the angle grinder temperature input vector to extract high-dimensional hidden correlation features of the correlations between the feature values at each position in the angle grinder temperature input vector.

[0039] In a specific embodiment of the present application, the angle grinder rotation speed feature extraction unit 123 includes: constructing the rotation speed data of the angle grinder at multiple predetermined time points into an angle grinder rotation speed input vector; passing the angle grinder rotation speed input vector through the angle grinder rotation speed feature encoder based on a convolutional neural network to obtain the angle grinder rotation speed feature vector.

[0040] It should be understood that constructing the rotational speed data of a grinder at multiple predetermined time points into a rotational speed input vector of the grinder is to better capture the operating state and performance changes of the device. During the operation of the grinder, the rotational speed is a key parameter, which directly reflects the load, wear degree of the device, and possible fault omens. The rotational speed value at a single moment cannot comprehensively present the dynamic changes of the device, while the rotational speed data at multiple time points can show the working performance of the device in different time periods, revealing key information such as the change trend and fluctuation range of the rotational speed. By constructing the rotational speed data at multiple time points into an input vector, the subsequent model can more comprehensively understand the operating characteristics of the device, help the model better understand the time-dependent relationship in the device operation, and identify potential problems or trends behind the rotational speed changes.

[0041] Furthermore, the original rotational speed input vector of the grinder usually contains the rotational speed data at multiple time points. Although it can reflect the working state of the device, it lacks an in-depth understanding of the potential patterns and local changes in these data. Through the convolutional neural network encoder, important features in the rotational speed data can be extracted to generate a more refined and expressive feature vector. Among them, when dealing with time series data, the convolutional neural network can effectively capture local features and patterns, especially suitable for identifying key trends and changes in the data, thereby helping to analyze the dynamic behavior of the rotational speed data. Specifically, the convolutional layer filters the input data through multiple convolutional kernels to extract valuable local features in the rotational speed data. The convolutional neural network can identify local patterns and trends in the data, such as sudden changes, fluctuations, and periodic changes in the rotational speed, which may be related to device failures, load changes, or performance degradation. After several layers of convolution and pooling operations, the convolutional neural network can compress the original rotational speed input vector into a more compact rotational speed feature vector, which contains the key feature information of the data and removes noise and redundant information. In this way, the convolutional neural network can automatically learn valuable features in the data, reduce the complexity of manual feature engineering, and improve the depth of the model's understanding of the rotational speed data. Specifically, obtaining the rotational speed feature vector of the grinder by passing the rotational speed input vector of the grinder through the rotational speed feature encoder of the convolutional neural network includes: using each layer of the rotational speed feature encoder of the convolutional neural network to perform convolution processing, mean pooling processing based on the local feature matrix, and non-linear activation processing on the input data respectively during the forward pass of the layer, so as to output the rotational speed feature vector by the last layer of the rotational speed feature encoder of the convolutional neural network, where the input of the rotational speed feature encoder of the convolutional neural network is the rotational speed input vector of the grinder.

[0042] In the above-mentioned intelligent integrated control system 100 of the angle grinder, the water supply flow adjustment judgment module 130 of the angle grinder is used to judge whether the water supply flow of the angle grinder needs to be adjusted based on the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder. It should be understood that considering that the water supply system of the angle grinder directly affects its grinding efficiency and equipment temperature management. Too much or too little water supply flow may affect the normal operation of the equipment, resulting in overheating or overcooling, thereby reducing the processing quality and even causing equipment failures. Therefore, accurately judging whether the water supply flow needs to be adjusted is crucial for ensuring the stable operation of the equipment and improving production efficiency. By inputting the semantic global feature vector of the processing data and the multi-modal association feature vector into the intelligent prediction model for analysis. Through training on historical data, this model can identify whether the water supply flow is insufficient or excessive under certain working conditions of the equipment and judge whether it will have an adverse impact on the equipment at this time. By evaluating the relationship between the current feature vector and historical data and combining machine learning algorithms, the model makes a prediction decision on whether to adjust the water supply flow, so as to achieve more accurate water supply adjustment, ensure the equipment operates in an efficient and stable working state, avoid potential failures caused by water supply problems, and improve production efficiency and processing quality.

[0043] Figure 3 Schematic block diagram of the water supply flow adjustment judgment module of the angle grinder in the intelligent integrated control system of the angle grinder according to an embodiment of the present application. As Figure 3 shown, in a specific embodiment of the present application, the water supply flow adjustment judgment module 130 of the angle grinder includes: a water supply flow feature association unit 131 for associating the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder to obtain a water supply flow adjustment judgment feature vector; a water supply flow feature optimization unit 132 for capturing boundary performance information based on eigen-decomposition space mapping for the water supply flow adjustment judgment feature vector to obtain an optimized water supply flow adjustment judgment feature vector; a water supply flow adjustment judgment classification unit 133 for passing the optimized water supply flow adjustment judgment feature vector through a classifier to obtain a classification result, and the classification result is used to judge whether the water supply flow of the angle grinder needs to be adjusted.

[0044] It should be understood that the semantic global feature vector of the angle grinder processing data contains the global information of the equipment during the processing process and reflects the overall operating state of the equipment. On the other hand, the multi-modal correlation feature vector of the angle grinder forms a feature vector that can reflect the performance of the equipment under the action of multiple factors by integrating data from multiple sensors and data sources (such as temperature sensors, pressure sensors, vibration sensors, etc.). These two feature vectors capture information on different aspects of the equipment operation from the global state and multi-modal data levels. However, using these features alone may not fully reflect the complex relationship between the water supply flow and the equipment state. Therefore, by correlating these two feature vectors, a more accurate feature vector for judging the water supply flow adjustment can be obtained. The correlation process usually includes fusing these two feature vectors, which can be combined into a comprehensive feature vector through weighted average, concatenation or other deep learning methods, such as multi-layer perceptron (MLP) or convolutional neural network (CNN). The feature vector obtained in this way can not only comprehensively consider the global state of the equipment, but also fuse multi-dimensional data to capture potential problems in the equipment operation. Finally, the obtained feature vector for judging the water supply flow adjustment can be input into the decision-making model to help the system judge whether it is necessary to adjust the water supply flow rate according to the real-time operating conditions and historical data of the equipment. This fusion method based on multi-source data can significantly improve the accuracy and reliability of the water supply regulation decision-making, ensure that the angle grinder operates under the best working conditions, improve production efficiency and reduce the risk of failure.

[0045] In particular, considering that the processing data is usually discrete data collected through a database, which may contain different indicators related to the process, usually exists in the form of structured data, and is high-dimensional and time-independent; while the temperature and rotational speed data are time-series data collected in real time by sensors, fluctuating with time and having significant continuity in the time dimension. This difference makes the data characteristics from multiple sources very different in terms of distribution, dimension, and impact on the model in the feature space. Among them, the temperature and rotational speed characteristics pay more attention to capturing dynamic changes, while the processing data may focus more on extracting global patterns. Moreover, in traditional feature fusion methods, a common practice is to directly splice features from different sources or perform weighted averaging on the features. Such a simple splicing method may not be able to effectively handle the distribution differences between features. For example, directly splicing time-series data (such as temperature and rotational speed) with non-time-series data (such as processing data) may cause the model to ignore the importance of time dynamic information and instead be biased towards the influence of a certain type of data, resulting in incomplete model training. The vector after feature splicing may generate high-dimensional sparsity, thereby increasing the computational complexity and affecting the training efficiency and accuracy of the model. These fusion methods ignore the distribution differences of different features in the representation space and do not fully consider how to adaptively adjust the feature weights and importance during the model training process, resulting in over-reliance on certain features or failure to effectively capture the dynamic changes of time-series data, and thus leading to a decline in generalization performance. Therefore, in the technical solution of this application, boundary performance information capture based on eigen-decomposition space mapping is performed on the water supply flow adjustment judgment feature vector to obtain an optimized water supply flow adjustment judgment feature vector.

[0046] In the technical solution of this application, boundary performance information capture based on eigen-decomposition space mapping is performed on the water supply flow adjustment judgment feature vector to obtain an optimized water supply flow adjustment judgment feature vector, including: mapping the water supply flow adjustment judgment feature vector to the eigen-decomposition space to obtain a first water supply flow adjustment eigen-decomposition feature vector; extracting the maximum water supply flow adjustment eigenvalue and the minimum water supply flow adjustment eigenvalue of the first water supply flow adjustment eigen-decomposition feature vector; calculating the difference between the maximum water supply flow adjustment eigenvalue and the minimum water supply flow adjustment eigenvalue as the water supply flow adjustment target domain edge anchoring description operator; extracting the mean and standard deviation of the first water supply flow adjustment eigen-decomposition feature vector, and dividing the mean by the standard deviation to obtain the water supply flow adjustment optimization direction description operator; based on the water supply flow adjustment target domain edge anchoring description operator and the water supply flow adjustment optimization direction description operator, performing matching optimization on the water supply flow adjustment judgment feature vector to obtain the optimized water supply flow adjustment judgment feature vector.

[0047] Among them, the water supply flow adjustment judgment eigenvector is mapped to the eigen - decomposition space to obtain the first water supply flow adjustment eigen - decomposition feature vector, which is represented by the following mapping formula:

[0048]

[0049] Among them, V 1 represents the water supply flow adjustment judgment eigenvector, PCA(V 1 ) represents mapping V 1 into the eigen - decomposition space, U 1 is a sequence of the first eigen - decomposition vectors, Λ 1 is the first diagonal matrix, U 1 T is the transpose of U 1 , v 11 , v 12 , v 1m are the first, second, and m - th eigenvectors of the sequence of the first eigen - decomposition vectors, λ i1 , λ im are the eigenvalues at the first position and the m - th position of the first diagonal matrix respectively, and V represents the first water supply flow adjustment eigen - decomposition feature vector.

[0050] Among them, boundary performance information capture based on eigen - decomposition space mapping is performed on the water supply flow adjustment judgment eigenvector to obtain an optimized water supply flow adjustment judgment eigenvector, which is represented by the following optimization formula:

[0051]

[0052] α = v max - v min

[0053]

[0054] Among them, v max and v min represent the maximum water supply flow adjustment eigenvalue and the minimum water supply flow adjustment eigenvalue of the first water supply flow adjustment eigen - decomposition feature vector respectively, α represents the water supply flow adjustment target domain edge anchoring description operator, μ and σ represent the mean and standard deviation of the first water supply flow adjustment eigen - decomposition feature vector respectively, τ represents the water supply flow adjustment optimization direction description operator, ⊙ and represent point - by - point addition, point - by - point multiplication, and point - by - point subtraction respectively, exp represents the natural exponential function with the natural constant e as the base, V 1 ⊙-1 represents calculating the reciprocal of each eigenvalue of the water supply flow adjustment judgment eigenvector, V 1Let \(V\) represent the first water supply flow adjustment eigen - decomposition feature vector, and \(V'\) represent the optimized water supply flow adjustment judgment feature vector.

[0055] In the technical solution of this application, boundary performance information capture based on eigen - decomposition space mapping is performed on the water supply flow adjustment judgment feature vector. This process first maps the water supply flow adjustment judgment feature vector into the eigen - decomposition space. By means of eigen - decomposition (such as classical numerical algebraic methods like eigenvalue decomposition, singular value decomposition, etc.), the original high - dimensional feature vector is projected onto a low - dimensional space composed of orthogonal bases. The directions in this low - dimensional space are defined by eigen - vectors, and the corresponding eigenvalues characterize the variance or intensity distribution of the data in different directions. The process of projecting into the eigen - decomposition space not only removes the redundant noise in the original features through dimensionality reduction but also maps the original vector with complex distribution onto a physically more intuitive decomposition dimension, making the structured information of the features clearer.

[0056] After the mapping is completed, it is necessary to further extract the maximum water supply flow adjustment eigenvalue and the minimum water supply flow adjustment eigenvalue of the first water supply flow adjustment eigen - decomposition feature vector. These two values respectively reflect the data characteristics of the feature vector in the most significant direction and the least significant direction. The maximum water supply flow adjustment eigenvalue represents the proportion of data information in the main direction and is the core explanatory factor of the feature distribution, while the minimum water supply flow adjustment eigenvalue is usually related to noise or data error and represents the weakest change in the direction. The maximum and minimum water supply flow adjustment eigenvalues are important representations of the data space form. In the analysis and optimization process, they provide a mathematical description of the global distribution characteristics of the features. At the same time, the distribution pattern of eigenvalues also implies the complexity of the data in the target domain. For example, when the maximum water supply flow adjustment eigenvalue is much larger than other eigenvalues, the feature has an obvious main axis direction in this space; if the eigenvalue distribution is relatively uniform, there may be higher complexity or diversity.

[0057] To construct a further feature optimization index, it is necessary to calculate the difference between the maximum water supply flow adjustment eigenvalue and the minimum water supply flow adjustment eigenvalue and define it as the water supply flow adjustment target domain edge anchoring description operator. The eigenvalue difference clearly defines the distribution range and span of the feature in the target domain from a geometric perspective. It corresponds to the difference between the major axis and the minor axis in the eigen - decomposition dimension and can be regarded as an anchoring index of the feature distribution, reflecting the boundary characteristics that the feature may exhibit in the target domain. The theoretical significance of the edge anchoring description operator is not limited to describing the data distribution difference. It also provides a measurement method for capturing the information specific points that establish the boundary performance in the feature space and supports the subsequent division and adjustment process of the target domain features. Through deep association with the target domain, this operator can further guide the subsequent optimization steps, making the optimized feature vector closely adhere to the domain edge attributes and enhancing its adaptability within the domain.

[0058] Meanwhile, it is also necessary to extract the mean and standard deviation from the first water supply flow adjustment eigen - decomposition eigen - vector, and calculate their ratio to obtain the water supply flow adjustment optimization direction description operator. The mean depicts the central tendency of the eigenvalues in a specific direction, while the standard deviation describes their discrete characteristics within the overall range. By normalizing the ratio of the mean to the standard deviation, this water supply flow adjustment optimization direction description operator provides a normalization mechanism, enabling the feature optimization process to better cope with the imbalance of different data scales while ensuring the robustness of the model. In the high - dimensional feature space, the ratio of the mean to the standard deviation further provides a stable basis for direction optimization, ensuring that the optimization process will not be overly interfered by extreme values or outliers. At the same time, this operator can also be understood as an adaptive adjustment rule for direction selection, making the optimization result more conform to the inherent characteristics of the target domain, especially achieving a balance between direction alignment and noise suppression.

[0059] After the construction of the above - mentioned key operator, the operation of finally matching and optimizing the water supply flow adjustment judgment eigen - vector comprehensively uses the water supply flow adjustment target domain edge anchoring description operator and the water supply flow adjustment optimization direction description operator to improve the discrimination ability of the eigen - vector and obtain an optimized representation. Matching optimization is a multi - objective optimization strategy that requires balancing the edge property and the directional property of the feature distribution simultaneously, avoiding over - fitting or deviation caused by preferring a certain objective. The edge anchoring description operator ensures that the distribution of the eigen - vector can better reflect the global and local distribution patterns of the target domain by capturing the significance of the edge characteristics; the water supply flow adjustment optimization direction description operator further provides a direction adjustment reference in this process, thus ensuring that the optimization can proceed in a more effective gradient direction.

[0060] Furthermore, the optimized judgment feature vector of the water supply flow is usually obtained by correlating the semantic global feature vector of the processing data of the angle grinder and the multi-modal correlation feature vector. These feature vectors contain multi-dimensional information during the operation of the equipment, such as rotational speed, temperature, load, vibration, and water supply status. After processing these data, a comprehensive vector that can accurately reflect the equipment status is formed. Through the optimization process, redundant data and noise are removed, while the important features required for judging the water supply flow adjustment are strengthened. At this time, the feature vector already has sufficient discriminative ability. Next, the optimized feature vector will be input into the classifier. The classifier is usually trained through supervised learning, and the training data includes known equipment status and corresponding water supply adjustment requirements. By using these historical data, the classifier learns how to identify patterns indicating the need for water supply flow adjustment from the feature vector. Common classifiers include decision trees, support vector machines (SVMs), neural networks, etc. Selecting an appropriate classifier can improve the classification accuracy. After training, the classifier can give a classification result based on the new input feature vector, usually "needs adjustment" or "does not need adjustment". For example, if the rotational speed of the angle grinder increases abnormally and the temperature is high, the classifier may determine that the water supply flow is insufficient at this time and then give a classification result of "needs adjustment". On the contrary, if all indicators of the equipment are normal, the classifier may judge that "the water supply flow does not need to be adjusted". Finally, the classification result is used to automatically judge whether the water supply flow needs to be adjusted. This judgment can play a key role in the real-time monitoring system, timely detect potential problems, optimize the working efficiency of the angle grinder, reduce the occurrence of faults, and ensure the long-term stable operation of the equipment. By combining the optimized feature vector with the classifier, the intelligent level of the system can be improved, and the dynamic adjustment of the equipment operation status can be realized.

[0061] In summary, in the embodiment of the present application, first, the processing data of the angle grinder collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotational speed data of the angle grinder at multiple predetermined time points are obtained. Then, using deep learning technology, feature extraction and correlation analysis are performed on the two. Finally, a classification result is obtained through a classifier to judge whether the water supply flow of the angle grinder needs to be adjusted, so as to reduce the waste of water and energy, improve production efficiency, and provide more efficient and accurate water supply regulation.

[0062] As described above, the angle grinder intelligent integrated control system 100 according to the embodiments of the present application can be implemented in various terminal devices. In one example, the angle grinder intelligent integrated control system 100 can be integrated into the terminal device as a software module and / or a hardware module. For example, the angle grinder intelligent integrated control system 100 can be a software module in the operating system of the terminal device, or can be an application program developed for the terminal device; of course, the angle grinder intelligent integrated control system 100 can also be one of the many hardware modules of the terminal device.

[0063] Alternatively, in another example, the angle grinder intelligent integrated control system 100 and the terminal device can also be separate devices, and the angle grinder intelligent integrated control system 100 can be connected to the terminal device through a wired and / or wireless network, and transmit interaction information according to a predefined data format.

[0064] Figure 4 FIG. is a flowchart of the angle grinder intelligent integrated control method according to the embodiments of the present application. As Figure 4 shown, the angle grinder intelligent integrated control method according to the embodiments of the present application includes: S110, obtaining angle grinder processing data collected by a database, temperature data at multiple predetermined time points in the working area of the angle grinder collected by a sensor, and rotation speed data of the angle grinder at multiple predetermined time points; S120, extracting a semantic global feature vector of the angle grinder processing data and a multi-modal association feature vector of the angle grinder from the angle grinder processing data collected by the database, the temperature data at multiple predetermined time points in the working area of the angle grinder collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points; S130, based on the semantic global feature vector of the angle grinder processing data and the multi-modal association feature vector of the angle grinder, determining whether the water supply flow of the angle grinder needs to be adjusted.

[0065] Here, those skilled in the art can understand that the specific operations of each step in the above angle grinder intelligent integrated control method have been described in detail in the description of the angle grinder intelligent integrated control system above with reference to Figures 1 to 3 and thus, the repeated description thereof will be omitted.

[0066] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation.

[0067] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical unit, that is, it may be located in one place or distributed over multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0068] In addition, in each embodiment of the present invention, each functional module can be integrated in a processing unit, can also exist separately as individual physical units, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

[0069] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0070] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be construed as limiting the claimed invention.

[0071] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The terms such as "second" are used to denote names and do not denote any particular order.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit of the technical solutions of the present invention.

Claims

1. An intelligent integrated control system for an angle grinder, characterized in that: include: An angle grinder water supply data acquisition module, used to acquire angle grinder processing data collected by a database, temperature data of a plurality of predetermined time points in the angle grinder working area collected by a sensor, and rotation speed data of a plurality of predetermined time points in the angle grinder; An angle grinder water supply data extraction module is used to extract the angle grinder processing data semantic global feature vector and the angle grinder multimodal association feature vector from the angle grinder processing data collected by the database, the temperature data of the angle grinder working area at multiple predetermined time points collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points; The angle grinder water supply flow adjustment judgment module is used to judge whether the angle grinder water supply flow needs to be adjusted based on the angle grinder processing data semantic global feature vector and the angle grinder multimodal association feature vector.

2. The intelligent integrated control system for angle grinder according to claim 1 is characterized in that: The angle grinder water supply data extraction module comprises: An angle grinder processing data feature extraction unit, used for performing feature extraction on the angle grinder processing data collected from the database to obtain a semantic global feature vector of the angle grinder processing data; An angle grinder working area temperature feature extraction unit, used for extracting features from the temperature data of the angle grinder working area at a plurality of predetermined time points to obtain an angle grinder temperature feature vector; An angle grinder speed feature extraction unit, used for extracting features from the speed data of the angle grinder at a plurality of predetermined time points to obtain a speed feature vector of the angle grinder; The angle grinder multi-modal feature fusion unit is used to fuse the angle grinder temperature feature vector and the angle grinder speed feature vector to obtain the angle grinder multi-modal correlation feature vector.

3. The intelligent integrated control system for angle grinder according to claim 2 is characterized in that: The angle grinder processing data feature extraction unit comprises: Passing the angle grinder processing data collected from the database through an angle grinder processing data semantic feature encoder to obtain a plurality of angle grinder processing data semantic feature vectors; The multiple angle grinder processing data semantic feature vectors are concatenated into the angle grinder processing data semantic global feature vector.

4. The intelligent integrated control system for angle grinder according to claim 3 is characterized in that: The angle grinder working area temperature feature extraction unit comprises: constructing the temperature data of a plurality of predetermined time points in the working area of ​​the angle grinder into an angle grinder temperature input vector; The angle grinder temperature input vector is passed through an angle grinder temperature timing encoder to obtain the angle grinder temperature characteristic vector.

5. The intelligent integrated control system for angle grinder according to claim 4, characterized in that: The angle grinder speed feature extraction unit comprises: constructing the rotation speed data of the angle grinder at a plurality of predetermined time points into an angle grinder rotation speed input vector; The angle grinder speed input vector is passed through an angle grinder speed feature encoder based on a convolutional neural network to obtain the angle grinder speed feature vector.

6. The intelligent integrated control system for angle grinder according to claim 5, characterized in that: The angle grinder speed input vector is passed through an angle grinder speed feature encoder based on a convolutional neural network to obtain the angle grinder speed feature vector, including: Each layer of the angle grinder speed feature encoder based on the convolutional neural network performs convolution processing, mean pooling processing based on the local feature matrix and nonlinear activation processing on the input data in the forward transfer of the layer, so that the last layer of the angle grinder speed feature encoder based on the convolutional neural network outputs the angle grinder speed feature vector, wherein the input of the angle grinder speed feature encoder based on the convolutional neural network is the angle grinder speed input vector.

7. The intelligent integrated control system for angle grinder according to claim 6, characterized in that: The angle grinder water supply flow adjustment judgment module comprises: An angle grinder water supply flow feature association unit, used to associate the angle grinder processing data semantic global feature vector with the angle grinder multimodal association feature vector to obtain a water supply flow adjustment judgment feature vector; An angle grinder water supply flow characteristic optimization unit is used to capture the boundary performance information of the water supply flow adjustment judgment feature vector based on the intrinsic decomposition space mapping to obtain an optimized water supply flow adjustment judgment feature vector; The water supply flow adjustment judgment classification unit is used to pass the optimized water supply flow adjustment judgment feature vector through a classifier to obtain a classification result, and the classification result is used to judge whether the water supply flow of the angle grinder needs to be adjusted.

8. The intelligent integrated control system for angle grinder according to claim 7, characterized in that: The angle grinder water supply flow characteristic optimization unit comprises: Mapping the water supply flow adjustment judgment feature vector to an eigendecomposition space to obtain a first water supply flow adjustment eigendecomposition feature vector; Extracting the maximum water supply flow adjustment eigenvalue and the minimum water supply flow adjustment eigenvalue of the first water supply flow adjustment eigendecomposition eigenvector; Calculate the difference between the maximum water supply flow adjustment characteristic value and the minimum water supply flow adjustment characteristic value as the edge anchoring description operator of the water supply flow adjustment target domain; Extracting the mean and standard deviation of the first water supply flow adjustment intrinsic decomposition eigenvector, and dividing the mean by the standard deviation to obtain a water supply flow adjustment optimization direction description operator; Based on the water supply flow adjustment target domain edge anchoring description operator and the water supply flow adjustment optimization direction description operator, the water supply flow adjustment judgment feature vector is matched and optimized to obtain the optimized water supply flow adjustment judgment feature vector.

9. An intelligent integrated control method for an angle grinder, characterized in that: include: Acquire the processing data of the angle grinder collected by the database, the temperature data of the working area of ​​the angle grinder at multiple predetermined time points collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points; Extracting a semantic global feature vector of the angle grinder processing data and a multimodal association feature vector of the angle grinder from the angle grinder processing data collected by the database, the temperature data of the angle grinder working area at multiple predetermined time points collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points; Based on the semantic global feature vector of the angle grinder processing data and the multimodal association feature vector of the angle grinder, it is determined whether the water supply flow of the angle grinder needs to be adjusted.

10. The intelligent integrated control method for angle grinder according to claim 9, characterized in that: Extracting the angle grinder processing data semantic global feature vector and the angle grinder multimodal association feature vector from the angle grinder processing data collected by the database, the temperature data of the angle grinder working area at multiple predetermined time points collected by the sensor, and the rotation speed data of the angle grinder at multiple predetermined time points, including: Performing feature extraction on the angle grinder processing data collected from the database to obtain a semantic global feature vector of the angle grinder processing data; Extracting features from the temperature data of a plurality of predetermined time points in the working area of ​​the angle grinder to obtain a temperature feature vector of the angle grinder; Extracting features from the rotation speed data of the angle grinder at a plurality of predetermined time points to obtain a rotation speed feature vector of the angle grinder; The angle grinder temperature feature vector and the angle grinder speed feature vector are fused to obtain the angle grinder multi-modal association feature vector.

Images