Remote control system and method of numerical control machine tool and medium

Abstract

The invention relates to a remote control system and method for a numerical control machine tool and a medium. The remote control system comprises numerical control machine tool equipment, edge computing equipment, cloud equipment and remote terminal control equipment, the numerical control machine tool equipment is used for collecting field data; the edge calculation equipment is used for performing edge calculation on the field data to generate target data; the cloud equipment is used for performing data processing on the target data to obtain a data processing result; and the remote terminal control equipment is used for outputting the data processing result, responding to a control instruction received on a human-computer interaction interface, and realizing remote control interaction operation with the numerical control machine tool equipment through the cloud equipment. A remote monitoring technology is realized through a network, the equipment data of the current numerical control machine tool is remotely checked, the operation data of the numerical control machine tool is processed in combination with the computing power of the cloud equipment, remote interaction control is realized, and the problem of low control efficiency of the numerical control machine tool in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of control technology, and in particular to a remote control system, method and medium for a numerically controlled machine tool. Background Art

[0002] At present, with the rapid development of digitalization and informatization, the application of CNC systems in the industrial field is becoming more and more extensive. Among them, CNC systems are an automatic control system based on computer technology, which can convert processing requirements into mathematical models and control commands through computer programming, and then transmit them to the CNC system host, which converts them into electrical signals, and converts the electrical signals into motion signals executed by the machine tool through the servo drive system, thereby accurately controlling the movement of the machine tool.

[0003] In practice, it is found that the current control of CNC machine tools mainly relies on on-site control, which requires on-site debugging of CNC machine tools and processing of workpieces. If the developer adds a new function to the CNC system, he needs to go to the site for debugging, etc. If there is a problem during the debugging process, he even needs to return to the office for modification, etc. Repeated trips between the office and the processing site greatly reduce work efficiency. It can be seen that the current control method of CNC machine tools has the problem of low control efficiency. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a remote control system, method and medium for a CNC machine tool, so as to solve the problem of low control efficiency of CNC machine tools in the prior art.

[0005] According to a first aspect of an embodiment of the present invention, there is provided a remote control system for a numerical control machine tool, comprising: a numerical control machine tool device, an edge computing device, a cloud device, and a remote terminal control device;

[0006] The CNC machine tool equipment is used to collect field data and transmit the field data to the edge computing device or the cloud device; wherein the field data includes at least one of the following:

[0007] Machine tool sensor data, machine tool image data, machine tool positioning data;

[0008] The edge computing device is used to perform edge computing on the field data, generate target data, and upload the target data to the cloud device;

[0009] The cloud device is used to process the target data, obtain a data processing result, and transmit the data processing result to the remote terminal control device;

[0010] The remote terminal control device is used to output the data processing result and respond to the control instructions received on the human-computer interaction interface to achieve remote control interaction operations with the CNC machine tool device through the cloud device.

[0011] According to a second aspect of an embodiment of the present invention, there is provided a remote control method for a numerically controlled machine tool, comprising:

[0012] Obtain target data reported by CNC machine tools;

[0013] Processing the target data to obtain a data processing result, and transmitting the data processing result to a remote terminal control device so that the remote terminal control device outputs the data processing result;

[0014] Receive the control instructions sent back by the remote terminal control device, and implement remote control interactive operations with the CNC machine tool device.

[0015] According to a third aspect of an embodiment of the present invention, there is provided a cloud device, including:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can perform the above method.

[0019] According to a fourth aspect of an embodiment of the present invention, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above method.

[0020] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0021] Remote monitoring technology is implemented through the network, and the equipment data of the current CNC machine tool can be directly viewed remotely. Combined with the computing power of cloud devices, the operating data of the CNC machine tool is processed to achieve remote interactive control, thus solving the problem of low control efficiency of CNC machine tools in existing technologies.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0024] Figure 1 is a schematic block diagram of a remote control system for a numerically controlled machine tool according to an exemplary embodiment;

[0025] Figure 2 is a flow chart of a remote control method for a CNC machine tool according to an exemplary embodiment;

[0026] Figure 3 is a flow chart of another remote control method for a CNC machine tool according to an exemplary embodiment;

[0027] Figure 4 It is a schematic diagram showing an internal control circuit of an air conditioner according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0029] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0030] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0031] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0032] Figure 1 is a schematic block diagram of a remote control system for a numerically controlled machine tool according to an exemplary embodiment. Figure 1 As shown, it includes: CNC machine tool equipment, edge computing equipment, cloud equipment, and remote terminal control equipment;

[0033] The CNC machine tool equipment is used to collect field data and transmit the field data to the edge computing device or the cloud device; wherein the field data includes at least one of the following:

[0034] Machine tool sensor data, machine tool image data, machine tool positioning data;

[0035] The edge computing device is used to perform edge computing on the field data, generate target data, and upload the target data to the cloud device;

[0036] The cloud device is used to process the target data, obtain a data processing result, and transmit the data processing result to the remote terminal control device;

[0037] The remote terminal control device is used to output the data processing result and respond to the control instructions received on the human-computer interaction interface to achieve remote control interaction operations with the CNC machine tool device through the cloud device.

[0038] Among them, the operation site includes two types of equipment: edge computing equipment and CNC machine tool equipment. Among them, CNC machine tool equipment can support network communication and establish communication connections with edge computing equipment or cloud equipment. In addition, CNC machine tool equipment can collect data of multiple dimensions such as its own sensor data, positioning data, video monitoring data, etc., and report them to edge computing equipment or cloud equipment for data processing, so as to realize multiple functions such as data visualization display, equipment health status management, and abnormal warning. The edge computing device can perform preliminary processing on the data and report the preliminarily processed data to the cloud for processing. It can also directly control the CNC machine tool equipment based on the preliminary data processing of the local edge computing device, and realize local control and cloud control at the same time. Through this cloud-edge collaborative computing method, latency can be reduced and network congestion in the cloud data center can be alleviated. It also supports offline local control operations to improve the flexibility and reliability of the system. Through edge computing, it can continue to operate without a network, which improves the ability to resist risks.

[0039] Specifically, edge computing devices can perform preliminary processing on data such as speed, acceleration, and rotation speed collected by sensors to generate required advanced data (such as average speed, maximum speed, etc.). Through edge computing, the data processing process is placed close to the data source to reduce latency and improve the real-time nature of data feedback. Reduce the amount of data transmission, alleviate network congestion in cloud data centers, and improve the stability and reliability of the overall system. In the absence of a network connection, edge computing devices can still process data, increasing the flexibility and reliability of the system. In edge computing devices, sorting algorithms can be used to obtain the maximum speed, statistical algorithms can be used to calculate average speed, acceleration, etc., and fault detection algorithms can be used to monitor data in real time, detect abnormal conditions, and generate early warning information.

[0040] Among them, the remote terminal control device can realize the data display interface, including numerical values, charts, etc.; optionally, it can also design common operation instructions into the interface, including parameter adjustment, troubleshooting, etc.;

[0041] Optionally, the operating data and status of the CNC machine tool can be viewed in real time; optionally, control instructions can be sent, such as adjusting parameters, changing tools, etc.; troubleshooting and remote debugging can be performed.

[0042] Among them, the cloud device can store the data uploaded from the CNC machine tool system and perform corresponding data processing; data processing includes data cleaning, statistical analysis, model building, etc.; optionally, the cloud supports AI analysis, including fault prediction, optimization of processing code, etc.; optionally, the cloud can also realize remote updates, including version management of applications and firmware. Among them, the AI ​​module in the cloud can use advanced AI algorithms to perform statistical analysis on a large amount of uploaded data and generate data models to help users view data information more clearly, identify potential faults, predict the maintenance cycle of equipment, optimize processing codes, and shorten processing time. Through the cloud platform, operators can remotely monitor the operating status and production status of CNC machine tools, and can also remotely send instructions to the CNC machine tool system through the cloud platform to adjust parameters, change tools, etc. By integrating AI modules on the cloud platform, analyzing data and creating corresponding data models, it can assist in viewing data information, discover potential faults, predict the maintenance cycle of equipment, optimize the processing process, and achieve a higher degree of intelligence. And a map interface is provided on the cloud platform to display the location information of the equipment.

[0043] Specifically, cloud-based artificial intelligence AI can obtain uploaded data from edge computing devices. The acquired source data is automatically visualized and laid out, a data visualization model is generated, and data characteristics and change trends are displayed using charts. The generated data model can help users understand the status of the equipment more intuitively and clearly, such as generating speed curves, temperature change trends, etc. At the same time, the generated visualization model can be viewed on a remote device to help dynamically grasp the status of the machine tool. When the data is abnormal, such as the temperature of the CNC machine tool exceeds the normal range, AI will issue an early warning to remind the operator to troubleshoot the problem.

[0044] As an optional implementation, the CNC machine tool equipment includes: an M2M module, a picture monitoring module, a positioning system module, and a sensor module;

[0045] The M2M module is used to implement communication with the edge computing device or the cloud device;

[0046] The image monitoring module is used to collect the machine tool image data and upload the machine tool image data to the cloud device, so that the cloud device outputs the machine tool image data to the remote terminal control device for remote image monitoring;

[0047] The positioning system module is used to collect the machine tool positioning data of the faulty equipment and report the machine tool positioning data to the edge computing device;

[0048] The sensor module is used to collect the machine tool sensor data and report the machine tool sensor data to the edge computing device, wherein the machine tool sensor data includes at least one of the following: position data, speed data, acceleration data, motor speed data, temperature data, pressure data, and load data of each axis of the CNC machine tool equipment.

[0049] In this embodiment, the CNC machine tool equipment may include four modules: M2M module, sensor module, positioning system module and screen monitoring module. Among them, the M2M module enables the CNC machine tool to have networking and remote communication capabilities; through 5G communication, the data is transmitted to the edge computing device; and the M2M application system is formed to realize intelligent and interactive communication. The sensor module can collect parameters such as the position, speed, acceleration, motor speed, etc. of each axis of the CNC machine tool; and collect temperature, pressure, load and other data through temperature sensors, pressure sensors, load sensors, etc. The positioning system module can obtain the exact location of the faulty equipment; calculate the best route to help the staff quickly reach the fault site. The screen monitoring module can collect real-time images of the vicinity of the machine tool and the processing process, upload them to the cloud, and the operator can view the on-site images through the remote terminal to realize real-time and accurate control of the on-site industrial equipment. Among them, a solution based on M2M technology is adopted to collect data, and high-speed transmission is performed on the basis of 5G communication to realize data monitoring of the CNC machine tool system equipment on the cloud platform. The M2M module enables the CNC machine tool system to have the ability of networking and remote communication, and high-speed and low-latency data transmission is realized through 5G communication technology. It is also responsible for uploading the data collected by the sensor module and the positioning system module to the edge computing device. 5G transmission is preferred when uploading data, and other alternatives (such as 4G, Wi-Fi, and wired connection) can also be used. When 5G is not available or the cost is high, the 4G network can be used for data transmission. In a fixed location or a small range, Wi-Fi can be used for data transmission. In scenarios where the security and stability of data transmission are required, a wired connection can be used.

[0050] For the positioning system module, a GPS positioning device is installed on the CNC machine tool. Through this device, the specific location of the CNC machine tool can be obtained, and the current location of the device can be checked through a mobile phone. When a certain device has a problem, the specific location of the faulty device can be determined through the positioning system, so that people can be quickly sent to repair it. Positioning can be achieved by installing a GPS module and antenna in the CNC machine tool equipment.

[0051] For the image monitoring module, high-definition cameras are installed to collect on-site images, and real-time images are transmitted to the cloud through 5G communication. The remote terminal control device provides an intuitive interface for operators to view real-time images and send control commands.

[0052] Among them, through the interaction of remote terminal control equipment, cloud, and operation site, remote control of CNC machine tools can be realized, which is more convenient. Among them, the remote terminal control device is used by operators to remotely view and control the operating status of CNC machine tools, the cloud is used to store and process data, and the operation site is the actual location of the CNC machine tools. Staff can use devices such as PCs or smart phones for remote control. The location data is transmitted to the edge computing device through the M2M module and then uploaded to the cloud. And the real-time picture of the scene is collected through the camera and uploaded to the cloud. Staff can log in to the cloud platform through the remote device to view the real-time picture of the scene. Send instructions through the remote device to adjust the parameters of the CNC machine tool to achieve real-time and precise control of the on-site industrial equipment.

[0053] As an optional implementation, the cloud device is specifically used for:

[0054] Performing data analysis on the target data to extract a first target parameter value;

[0055] Generate a device health assessment result based on the pre-trained device health assessment model and the first target parameter value;

[0056] Based on the equipment health assessment result and the target parameter value, generating a visual equipment status display interface;

[0057] The visual device status display interface is transmitted to the remote terminal control device as the data processing result.

[0058] In this embodiment, the CNC machine tool collects various types of operating data in real time through the sensor module, such as: position parameters (such as the position of each axis, the position of the tool), motion parameters (such as speed, acceleration, speed, etc.), environmental parameters (such as temperature, pressure, load, etc.). The acquired raw data is preliminarily processed by the edge computing device, including screening of abnormal values, data smoothing and data completion. This can avoid erroneous analysis caused by noise and errors, and the target data is reported to the cloud device after processing. The cloud device can analyze the multi-dimensional data of the CNC machine tool (such as speed, temperature, load, etc.) and extract important features of the equipment's operating status. For example: processing process analysis, based on motion data and temperature data, analyzes the influence of factors such as heat generation and vibration in the processing process. It is also possible to predict the wear and service life of the tool by analyzing data such as temperature changes and speed changes during tool use.

[0059] Furthermore, cloud devices can build equipment health assessment models based on classification algorithms and regression algorithms in advance. Generate equipment health status scores based on real-time data to help operators evaluate whether the equipment is in normal working condition and whether maintenance is required. Generate a corresponding visual interface to create a real-time status panel for the CNC machine tool. The relevant parameters may include: key parameters of the CNC machine tool (such as displacement, speed, load, temperature, etc. of each axis), equipment health score (displaying the current health score or remaining life of the equipment). Among them, the health score can be indicated by color (for example, green for normal, yellow for warning, and red for fault).

[0060] Specifically, when training the model, you can first clean and preprocess the data to ensure data quality, remove noise, fill missing values, and ensure that the model can learn from valid data. For data with less loss, linear interpolation can be used to fill in the data. Linear interpolation interpolates based on the values ​​before and after the data, and is suitable for time series data with relatively stable trends. For features with more common missing values, you can use the mean or median to fill in the data. In particular, this method is often used for sensor data such as temperature and pressure. Or fill missing values ​​based on the distance between similar data points. In multidimensional data, KNN can infer missing values ​​based on known sample data, which is suitable for scenarios with complex data. After that, outlier detection can be performed. Specifically, the Z-score method is used to detect and remove outliers. Samples with Z-score values ​​greater than 3 or less than -3 are considered abnormal. Or the IQR (interquartile range) method is used to calculate the range based on the upper and lower quartiles of the data (data outside 1.5 times the IQR is abnormal). This method is more effective for data such as machine tool vibration. Alternatively, Isolation Forest (an outlier detection algorithm based on decision trees) can be used, which is particularly suitable for high-dimensional data and can effectively remove extreme outliers in the data. After that, the data of different units (such as speed, temperature, and pressure) are converted to the same range, usually [0,1], to eliminate the impact of dimensional differences. After that, the data is converted to a mean of 0 and a standard deviation of 1, which is particularly suitable for scenarios with different data distributions. Further, after the initial data processing is completed, key information can be extracted, meaningful features can be generated, and complex raw data can be converted into a form that is easy for the model to handle. Among them, the operating data of CNC machine tools is usually time series data, including changes in parameters such as temperature, speed, and load. Data analysis can be analyzed using the following methods: Moving average (MA): Smoothes noise by calculating the average value of data within the time window to obtain the overall trend of the data. Autoregressive model (AR): Used to analyze the trend and periodicity of equipment operation. For example, predict the changing trend of equipment health status. Exponential smoothing: Suitable for short-term prediction, emphasizing recent data by weighted averaging historical data. After that, select an appropriate machine learning algorithm and train it based on the equipment data of CNC machine tools. SVR can be used to predict the operating status of CNC machine tools. It is suitable for processing high-dimensional data and complex nonlinear relationships. SVR can predict the remaining useful life (RUL) or health status score of the equipment, or make predictions by integrating multiple decision trees. It has strong robustness, can handle nonlinear data relationships, and is suitable for data analysis of multiple features. Or through linear regression, it is suitable for predicting the gradual change trend of the equipment, such as the long-term health trend of the equipment.

[0061] In addition to the visual device display interface, the remote control terminal device can also use dynamic charts to display the movement status of the machine tool, such as displaying the movement speed change trend of each axis through the speed curve, and displaying the real-time change of the load of each axis to help analyze whether there is a risk of overload operation. Display the temperature and vibration data of different parts of the machine tool through thermal maps or bar charts. Use color gradients (such as cold colors for low temperatures and warm colors for high temperatures) to clearly mark possible high-temperature areas, and warn of possible overheating problems of the equipment in advance. Through a variety of display forms, data can be quickly displayed.

[0062] As an optional implementation, the cloud device is also used for:

[0063] Performing data analysis on the target data to extract a second target parameter value;

[0064] Generate a device fault prediction result based on the pre-trained fault prediction model and the second target parameter value;

[0065] The equipment fault prediction result is added to the visual equipment status display interface as the data processing result, and transmitted to the remote terminal control device.

[0066] In this embodiment, the historical data and real-time data of the equipment can also be analyzed to generate a fault prediction model. For example, based on the temperature, pressure, load, vibration and other data of the equipment, the AI ​​system can predict whether the tool is excessively worn or whether any parts may fail (such as bearing damage, transmission system failure, etc.).

[0067] For fault prediction, SVM can be used to process high-dimensional data, which is suitable for fault prediction tasks. It divides data into normal state and fault state, and can efficiently identify fault modes. Alternatively, random forest classification can be used to achieve multi-category prediction of equipment failure. Alternatively, under small sample data, the KNN algorithm can effectively classify the state of the equipment and is suitable for real-time fault classification. In addition, for complex pattern recognition, since CNC machine tool data is mostly time series data, LSTM is very suitable for learning the state change pattern of the equipment. LSTM can capture the temporal dependencies of long time series data, which is particularly suitable for equipment fault prediction. Alternatively, CNN can be used for feature extraction of time series data in image data processing to help identify complex equipment failure modes.

[0068] As an optional implementation, the cloud device is also used for:

[0069] Early warning data is generated according to the equipment fault prediction result, the equipment health assessment result, the first target parameter value, and / or the second target parameter value, and the early warning data is transmitted to the remote terminal control device as the data processing result.

[0070] In this embodiment, various data can also be monitored in real time. If the equipment parameters are abnormal (such as temperature exceeding the standard, load being too high, etc.), the system will trigger an alarm and automatically notify the operator. At this time, the system will feedback the warning information in real time on the interface through color changes, icon flashing, etc., to remind the operator to make corresponding adjustments or inspections. By detecting equipment anomalies in real time and issuing fault warnings, equipment downtime can be avoided in advance. When performing anomaly detection, by reconstructing the input data, the autoencoder can detect data that is inconsistent with the normal behavior pattern. For example, if the operating data of the equipment, such as temperature, vibration, etc., fluctuates greatly, the model will detect the anomaly. Or based on Isolation Forest (a tree-based anomaly detection algorithm), abnormal data can be found by randomly dividing the feature space of the data set. In industrial data, any data that does not conform to the normal pattern will be marked as abnormal.

[0071] In addition, fault prediction can be performed based on machine learning or deep learning, using regression algorithms (such as SVR and random forest regression) to predict the health status score of the equipment, or using classification methods (such as SVM and random forest classification) to predict whether the equipment will fail. LSTM can be used for long-term trend prediction to help predict the probability of equipment failure within a certain period of time in the future.

[0072] As an optional implementation, the cloud device is also used for:

[0073] Determine the type of fault according to the equipment fault prediction result;

[0074] Based on the fault type, a fault handling suggestion is generated, and the fault handling suggestion is transmitted to the remote terminal control device as the data processing result.

[0075] As an optional implementation, the cloud device is also used for:

[0076] A data statistical report is generated based on the equipment fault prediction result, the equipment health assessment result, the first target parameter value, the second target parameter value, and / or the target data, and the data statistical report is transmitted to the remote terminal control device as the data processing result.

[0077] In this implementation, the cloud can store all data, including sensor data, processed advanced data, historical data, etc. Advanced AI algorithms are used for data processing and analysis, including data cleaning, statistical analysis, anomaly detection, model building, etc.

[0078] As an optional implementation manner, the remote terminal control device is specifically used for:

[0079] Outputting the data processing result; wherein the data processing result includes a visual device status display interface;

[0080] If the control instruction received on the human-computer interaction interface is a display control instruction, adjusting the display view in the visualization device status display interface;

[0081] If the control instruction received on the human-computer interaction interface is a device control instruction, the device control instruction is sent to the CNC machine tool device through the cloud device to realize remote control interactive operation.

[0082] In this embodiment, the remote terminal control device can provide a remote control interface, through which the operator can adjust the parameters of the CNC machine tool in real time, such as adjusting the cutting speed and tool change control. Specifically, the cutting speed can be adjusted according to the real-time monitored cutting temperature and load conditions without affecting the work to avoid overheating or excessive tool wear. And when AI predicts that the tool is severely worn, the operator can send a tool replacement instruction through the remote control interface to avoid reduced processing accuracy or production downtime due to tool damage.

[0083] The interface design adopts a graphical approach, allowing operators to view key parameters and data through simple clicks. For example, by clicking the "Temperature" module, operators can view the temperature changes of different parts of the machine tool; by clicking the "Vibration" module, operators can view the current vibration frequency and amplitude of the machine tool.

[0084] Users can customize different views according to the needs of operators. For example, process engineers can choose to view the machining process parameters of machine tools, while maintenance personnel can view fault prediction data and historical maintenance records to optimize maintenance plans.

[0085] In addition, the machine tool working environment is monitored in real time through high-definition cameras, and videos are uploaded to the cloud. Operators view the on-site images through remote terminals to provide operation guidance or problem diagnosis. Through video monitoring combined with data visualization, operators can adjust the equipment on the remote terminal, and even quickly troubleshoot with the assistance of AI. For example, when the remote terminal displays the equipment temperature and vibration data, the staff can view the on-site video at the same time and make timely adjustments based on the visual feedback.

[0086] Specifically, the data statistical report can be generated by collecting data from different modules (such as sensor modules, positioning systems, screen monitoring modules, etc.) and different sensors, and merging these data into a unified format for subsequent processing. For example, the temperature, speed, pressure and other parameters collected by the sensor need to be unified to a timestamp to ensure the consistency and comparability of the data. Remove noise data and fill in missing values ​​to ensure the quality of the data and avoid inaccurate data affecting the statistical results. Calculate the conventional statistical indicators of the equipment operation parameters, such as mean, standard deviation, maximum value, minimum value, quartile, skewness and kurtosis. These indicators can help analyze the distribution of various parameters of the machine tool and find the normal range of the equipment. For example, the data of the temperature sensor can generate the following statistical reports: average temperature, temperature fluctuation range, maximum temperature and minimum temperature, reflecting whether the equipment is within the normal working range. For time series data (such as the speed and temperature of the machine tool), trend lines, seasonal changes, fluctuation ranges, etc. can be calculated, and the changes of various parameters in different time periods can be displayed. For example, through time series analysis, the daily average temperature change trend or weekly periodic vibration mode of the machine tool is generated to help analyze the working status of the equipment. The linear relationship between multiple variables is then quantified using the Pearson correlation coefficient. By calculating the correlation between the sensor data of the machine tool (such as speed, temperature, pressure, etc.), we can identify whether they have commonalities or correlations. For example, there is a positive correlation between temperature and speed. Under certain conditions, an increase in speed may lead to an increase in temperature, which is crucial to the control decision of the machine tool operator.

[0087] In addition, when performing anomaly detection and fault prediction, statistical analysis will be used to find data points that differ greatly from historical data, such as when temperature fluctuations exceed the set threshold. The statistical report will automatically mark the abnormal point. In addition, the report will provide some prediction results based on historical data, such as equipment failure probability, remaining service life, etc.

[0088] Among them, the specific content of the data statistics report can include key parameter statistics, such as equipment operating parameters: list the key operating parameters of CNC machine tools (such as speed, temperature, pressure, etc.) and their statistical results, including average, maximum, minimum, standard deviation, deviation, etc. For example, speed: average speed: 1500RPM, maximum speed: 2000RPM, minimum speed: 1200RPM temperature: average temperature: 45°C, maximum temperature: 65°C, minimum temperature: 30°C. By generating a fluctuation chart of equipment operation data, it can be shown whether the machine is operating within an acceptable range. For example, a temperature fluctuation chart is generated to show the changes in machine tool temperature in different time periods.

[0089] The report can also include equipment health status analysis, which calculates the health status of the equipment by setting a health score model. The score is derived from a combination of multiple sensor data, using a score range of 0-100, with larger values ​​indicating healthier equipment. For example, a device health status score of 80 / 100 means that the equipment is operating normally, but there may be a few anomalies that require attention. Based on the historical operating data and current working status of the equipment, a probability prediction of equipment failure in the next few days or weeks is generated. For example: "The probability of equipment A failing in the next 7 days is 12%", which helps make maintenance decisions.

[0090] The report can also include abnormal event records and warnings, listing all abnormal situations that occurred during the reporting period, including situations where equipment parameters exceeded the preset range (such as too high speed, too much vibration, etc.). It also marks the time of occurrence, type of abnormality, impact range, and other information of each abnormal event. Based on the abnormalities detected by the algorithm, warning information is automatically generated, for example: "The speed of equipment A exceeds the set threshold, and it is recommended to shut down for inspection."

[0091] The report can also include trends and forecasts, showing the operating trends of the equipment within a certain time range and analyzing the performance changes of the equipment. For example, a gradual increase in temperature or pressure may indicate that the equipment is about to fail. Use predictive algorithms to generate future operating trends of the equipment, such as the remaining service life of the equipment, health scores, etc.

[0092] In addition, the display interface can also generate intuitive charts to help operators quickly understand the statistical results. For example, a line chart shows the trend of equipment parameters over time, and a bar chart shows the comparison of different equipment or parameters. A pie chart shows the distribution of equipment operating status (such as the proportion of equipment health status). A heat map shows the correlation between different equipment parameters to help operators understand the relationship between various equipment parameters.

[0093] In addition, control instructions can be used to instruct adjustment of parameters, replacement of tools, etc.

[0094] Through this application, the remote control system has significantly improved the production efficiency of modern workshops. The intelligent remote control system can save a lot of manpower and material resources for the factory and improve production efficiency. The remote control system performs well in data monitoring. The CNC system equipped with the remote control system can realize real-time monitoring, obtain equipment data, and facilitate statistics of data information for the day or a certain stage. At the same time, it can automatically make adjustments through AI and make reasonable plans to facilitate the next step. And it can grasp the on-site information more quickly, optimize the working environment, concentrate human resources, and avoid wasting human resources. And realize a series of functions such as remote upgrade and download of firmware / applications, remote monitoring, debugging, troubleshooting, etc.

[0095] Remote monitoring technology is implemented through the network, and the equipment data of the current CNC machine tool can be directly viewed remotely. Combined with the computing power of cloud devices, the operating data of the CNC machine tool is processed to achieve remote interactive control, thus solving the problem of low control efficiency of CNC machine tools in existing technologies.

[0096] Based on the same inventive concept, Figure 2 is a flow chart of a remote control method for a numerical control machine tool according to an exemplary embodiment. Figure 2 As shown, the method is applicable to a cloud device, including:

[0097] Step S21, obtaining target data reported by the CNC machine tool equipment;

[0098] Step S22: performing data processing on the target data to obtain a data processing result, and transmitting the data processing result to a remote terminal control device so that the remote terminal control device outputs the data processing result;

[0099] Step S23: receiving the control command sent back by the remote terminal control device, and implementing remote control interactive operation with the CNC machine tool device.

[0100] Please also read Figure 3 , Figure 3This is a flowchart of another remote control method for a CNC machine tool according to an exemplary embodiment. When the equipment fails, the fault information is reported to the cloud through the M2M module. The cloud AI performs fault analysis and generates processing suggestions. The operator performs fault diagnosis through the remote terminal and dispatches field service personnel when necessary. The field service personnel quickly reach the location of the faulty equipment according to the best route provided by the cloud. After the data is uploaded to the cloud, the AI ​​module will diagnose and analyze the equipment operation data, and conduct real-time monitoring by setting reasonable thresholds, rules or using statistical methods (such as Z-score, standard deviation, etc.) to determine whether the equipment is abnormal. For example, an alarm is triggered when the temperature exceeds 70°C, a warning is issued when the speed deviates from the predetermined range, and abnormal pressure values ​​are generated. By learning from historical data, AI can identify the "normal" operating mode of the equipment and detect deviations from this mode (such as vibration data, temperature data, etc. of the equipment). For example, the temperature of a CNC machine tool has been fluctuating around 60°C in the past week. If the temperature suddenly soars to 80°C at a certain moment, it will be regarded as abnormal data by AI. Alternatively, machine learning models (such as decision trees, support vector machines (SVM), etc.) can be used for anomaly detection, and model training can be performed based on the historical operating data and fault records of the equipment to identify potential abnormal patterns. Through the trained prediction model, AI can predict potential equipment failures. For example, AI can predict whether the equipment may fail in the next few hours based on the current operating status of the equipment (such as temperature, speed, pressure, etc.) and historical data. Based on the above fault analysis, AI will generate specific processing suggestions and transmit them to the operator or maintenance team in the form of a report. For example, based on the type of fault, AI will automatically generate a set of processing solutions or suggestions to ensure that the equipment can be quickly repaired and resume production. For example:

[0101] Cooling problem: If AI detects that the device temperature is continuously high, it is recommended to check the cooling system and adjust the cooling parameters or clean the cooling device.

[0102] Mechanical failure: If the AI ​​identifies an abnormal speed and it is correlated with the vibration data, it may be a sign of mechanical failure. It is recommended to check the motor and transmission system.

[0103] Equipment overload: If AI detects that the load of the equipment is close to the maximum value, it is recommended to stop operation and perform load balancing and pressure adjustment.

[0104] In addition to handling faults, AI can also provide some preventive maintenance suggestions to reduce the possibility of failure and extend the service life of equipment. For example:

[0105] Regular inspection: It is recommended that operators check the key components of the machine tool (such as motor, cooling system, transmission system, etc.) every month.

[0106] Parts replacement: Depending on the operating conditions of the equipment, AI can recommend replacement of certain vulnerable parts (such as tools, bearings, etc.) based on usage time or failure frequency.

[0107] Optimizing parameters: AI can recommend adjustments to the operating parameters of the equipment based on the analysis results to improve efficiency or reduce energy consumption.

[0108] In addition, the generated processing suggestions will not only be displayed in the cloud control platform, but also can send notifications through the automation system to remind operators or maintenance teams, such as notifying relevant personnel of the processing suggestions and machine tool location in real time through email, SMS or APP push. According to the severity of the fault, AI can give priorities and guide operators to deal with the most urgent faults first. After implementing the processing suggestions, the operator will monitor the equipment in real time through the cloud platform, and AI will track the processing results to confirm whether the fault has been repaired. If the problem still exists, AI will continue to optimize the processing suggestions and feedback the current fault status to the operator in real time.

[0109] Remote monitoring technology is implemented through the network, and the equipment data of the current CNC machine tool can be directly viewed remotely. Combined with the computing power of cloud devices, the operating data of the CNC machine tool is processed to achieve remote interactive control, thus solving the problem of low control efficiency of CNC machine tools in existing technologies.

[0110] The implementation methods and beneficial effects of each method step of this embodiment can refer to the introduction of the corresponding cloud device module in the above embodiment, and will not be repeated in this embodiment.

[0111] Based on the same inventive concept, Figure 4 is a schematic diagram of an internal control circuit of a cloud device according to an exemplary embodiment. Figure 4 As shown, the cloud device includes:

[0112] At least one processor 401, a communication interface 402; and

[0113] A memory 403 communicatively connected to the at least one processor 401;

[0114] Among them, the processor 401, communication interface 402 and memory 403 communicate with each other through a communication bus 404; the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0115] According to an exemplary embodiment, a non-transitory computer-readable storage medium storing computer instructions is shown, where the computer instructions are used to enable a computer to execute the above method.

[0116] The computer-readable storage medium disclosed in this embodiment includes, but is not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device.

[0117] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0118] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A remote control system for a CNC machine tool, characterized in that: include: CNC machine tool equipment, edge computing equipment, cloud equipment, and remote terminal control equipment; The CNC machine tool equipment is used to collect field data and transmit the field data to the edge computing device or the cloud device; wherein the field data includes at least one of the following: machine tool sensor data, machine tool image data, and machine tool positioning data; The edge computing device is used to perform edge computing on the field data, generate target data, and upload the target data to the cloud device; The cloud device is used to process the target data, obtain a data processing result, and transmit the data processing result to the remote terminal control device; The remote terminal control device is used to output the data processing result and respond to the control instructions received on the human-computer interaction interface to achieve remote control interaction operations with the CNC machine tool device through the cloud device.

2. The system according to claim 1, characterized in that The CNC machine tool equipment includes: an M2M module, a picture monitoring module, a positioning system module, and a sensor module; The M2M module is used to implement communication with the edge computing device or the cloud device; The image monitoring module is used to collect the machine tool image data and upload the machine tool image data to the cloud device, so that the cloud device outputs the machine tool image data to the remote terminal control device for remote image monitoring; The positioning system module is used to collect the machine tool positioning data of the faulty equipment and report the machine tool positioning data to the edge computing device; The sensor module is used to collect the machine tool sensor data and report the machine tool sensor data to the edge computing device, wherein the machine tool sensor data includes at least one of the following: position data, speed data, acceleration data, motor speed data, temperature data, pressure data, and load data of each axis of the CNC machine tool equipment.

3. The system according to claim 1, characterized in that The cloud device is specifically used for: Performing data analysis on the target data to extract a first target parameter value; Generate a device health assessment result based on the pre-trained device health assessment model and the first target parameter value; Based on the equipment health assessment result and the target parameter value, generating a visual equipment status display interface; The visual device status display interface is transmitted to the remote terminal control device as the data processing result.

4. The system according to claim 3, characterized in that The cloud device is also used for: Performing data analysis on the target data to extract a second target parameter value; Generate a device fault prediction result based on the pre-trained fault prediction model and the second target parameter value; The equipment fault prediction result is added to the visual equipment status display interface as the data processing result, and transmitted to the remote terminal control device.

5. The system according to claim 4, characterized in that The cloud device is also used for: Early warning data is generated according to the equipment fault prediction result, the equipment health assessment result, the first target parameter value, and / or the second target parameter value, and the early warning data is transmitted to the remote terminal control device as the data processing result.

6. The system according to claim 4, characterized in that The cloud device is also used for: Determine the type of fault according to the equipment fault prediction result; Based on the fault type, a fault handling suggestion is generated, and the fault handling suggestion is transmitted to the remote terminal control device as the data processing result.

7. The system according to claim 4, characterized in that The cloud device is also used for: A data statistical report is generated based on the equipment fault prediction result, the equipment health assessment result, the first target parameter value, the second target parameter value, and / or the target data, and the data statistical report is transmitted to the remote terminal control device as the data processing result.

8. The system according to any one of claims 1 to 7, characterized in that: The remote terminal control device is specifically used for: Outputting the data processing result; wherein the data processing result includes a visual device status display interface; If the control instruction received on the human-computer interaction interface is a display control instruction, adjusting the display view in the visualization device status display interface; If the control instruction received on the human-computer interaction interface is a device control instruction, the device control instruction is sent to the CNC machine tool device through the cloud device to realize remote control interactive operation.

9. A remote control method for a CNC machine tool, characterized in that: include: Obtain target data reported by CNC machine tools; Processing the target data to obtain a data processing result, and transmitting the data processing result to a remote terminal control device so that the remote terminal control device outputs the data processing result; Receive the control instructions sent back by the remote terminal control device, and implement remote control interactive operations with the CNC machine tool device.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method of claim 9.

Images