Fault warning method and system for CNC machine tools based on industrial Internet of Things

Abstract

The present invention relates to a CNC machine tool fault warning method and system based on the Industrial Internet of Things, and relates to the field of the Industrial Internet of Things. The method comprises: obtaining monitoring operation parameters of multiple key monitoring points through an Internet of Things sensor network; analyzing the monitoring operation parameters to identify potential risk points; when a potential risk point is identified, obtaining subsequent processing tasks that have not been executed by the target CNC machine tool; determining the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task; and sending a warning message if the failure probability is greater than or equal to a preset probability threshold. The present application solves the technical problem in the prior art that early warning of CNC machine tool failures cannot be achieved, which easily leads to serious failures of the machine tool. It achieves the technical effect of early identification, evaluation and timely warning of potential failures of CNC machine tools through the Internet of Things, thereby effectively preventing the occurrence of serious failures.

Description

Technical Field

[0001] The present invention relates to the field of industrial Internet of Things, and in particular to a CNC machine tool fault warning method and system based on the industrial Internet of Things. Background Art

[0002] With the rapid development of intelligent manufacturing, CNC machine tools, as core equipment in modern manufacturing, are crucial for ensuring production efficiency and product quality through stable and reliable operation. However, in actual production, CNC machine tools are prone to various faults during long-term operation, such as abnormal spindle vibration, excessive temperatures, and insufficient lubrication. If these problems are not discovered and addressed promptly, they often lead to serious machine failures. Existing CNC machine tool fault monitoring systems only issue alarms when certain parameters exceed the safe range. By this time, the failure has often already occurred or is about to occur, missing the optimal opportunity for prevention. This delayed monitoring method fails to provide early warning and can easily lead to serious machine failures. Summary of the Invention

[0003] The main purpose of this application is to provide a CNC machine tool fault warning method and system based on the Industrial Internet of Things, aiming to solve the technical problem in the existing technology that CNC machine tool failures cannot achieve early warning, which easily leads to serious failures of the machine tool.

[0004] To achieve the above-mentioned objectives, the present application provides a CNC machine tool fault warning method based on the industrial Internet of Things, which includes: obtaining monitoring and operating parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network; analyzing the monitoring and operating parameters according to the parameter safety constraint intervals of each of the key monitoring points to identify potential risk points; when potential risk points are identified, obtaining subsequent processing tasks that have not been executed by the target CNC machine tool; determining the failure probability of the target CNC machine tool based on the potential risk points and the subsequent processing tasks; and sending a warning message if the failure probability is greater than or equal to a preset probability threshold.

[0005] Optionally, the monitoring operation parameters are analyzed according to the parameter safety constraint interval of each key monitoring point to identify potential risk points, including: performing time-frequency domain conversion on the monitoring operation parameters of each key monitoring point to obtain parameter spectrum characteristics; obtaining a preset safety spectrum template for each key monitoring point; obtaining the spectrum matching degree of each key monitoring point based on the parameter spectrum characteristics of each key monitoring point and the preset safety spectrum template; and marking the key monitoring points whose spectrum matching degree is less than or equal to the matching degree threshold as potential risk points.

[0006] Optionally, obtaining the spectrum matching degree of each key monitoring point according to the parameter spectrum characteristics of each key monitoring point and a preset safe spectrum template includes: constructing a matching degree calculation formula as follows: .in, represents the parameter spectrum characteristics, T represents the preset safe spectrum template, Represents parameter spectrum characteristics The spectrum matching degree with the preset safe spectrum template T, Indicates the number of frequency points where the deviation of the parameter spectrum feature from the preset safe spectrum template is within the preset tolerance range. Indicates the total number of frequency points in the spectrum analysis, Represents parameter spectrum characteristics The main peak frequency, Indicates the main peak frequency of the preset safe spectrum template T, and Represent the spectrum matching rate weight and the main frequency similarity weight respectively and satisfy + According to the matching calculation formula, the matching degree of the parameter spectrum characteristics of each key monitoring point and the preset safety spectrum template is calculated to obtain the spectrum matching degree of each key monitoring point.

[0007] Optionally, determining the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task includes: analyzing the load characteristics of the subsequent processing task to obtain processing load parameters; obtaining the risk level and load tolerance threshold of the potential risk point; obtaining a load pressure coefficient based on the ratio of the processing load parameter to the load tolerance threshold; and determining the failure probability of the target CNC machine tool in the process of executing the subsequent processing task based on the risk level and load pressure coefficient.

[0008] Optionally, determining the failure probability of the target CNC machine tool in executing the subsequent processing task based on the risk level and the load pressure coefficient includes: constructing a failure probability calculation model as follows: ;in, represents the probability of failure, Indicates the risk level, represents the load pressure coefficient, represents a correction coefficient, which is determined according to the type and usage time of the target CNC machine tool; based on the failure probability calculation model, the risk level and the load pressure coefficient, the failure probability of the target CNC machine tool is determined.

[0009] Optionally, before obtaining the monitoring operation parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network, the method also includes: obtaining equipment characteristic information of the target CNC machine tool; obtaining a set of processing tasks to be executed by the target CNC machine tool; and determining multiple key monitoring points for the target CNC machine tool based on the equipment characteristic information and the set of processing tasks.

[0010] Optionally, the method of determining multiple key monitoring points for the target CNC machine tool based on the device characteristic information and the processing task set includes: constructing a device characteristic vector based on the device characteristic information; constructing a task characteristic vector based on the processing task set; performing case retrieval in a historical machine tool failure database based on the device characteristic vector and the task characteristic vector to obtain a set of similar machine tool failure cases; and determining the key monitoring points through the set of similar machine tool failure cases.

[0011] In addition, in order to achieve the above-mentioned purpose, the present application provides a CNC machine tool fault warning system based on the industrial Internet of Things, which is used to implement a CNC machine tool fault warning method based on the industrial Internet of Things. The system includes a data acquisition module, a risk identification module, a task acquisition module, a fault prediction module, and an early warning notification module. Among them, the data acquisition module is used to obtain the monitoring and operating parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network; the risk identification module is used to analyze the monitoring and operating parameters according to the parameter safety constraint interval of each key monitoring point to identify potential risk points; the task acquisition module is used to obtain the subsequent processing tasks that have not been executed by the target CNC machine tool when the potential risk point is identified; the fault prediction module is used to determine the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task; the early warning notification module is used to send an early warning message if the failure probability is greater than or equal to the preset probability threshold.

[0012] In addition, to achieve the above-mentioned objectives, the present application further provides an electronic device comprising a memory and a processor. The memory is used to store a computer software program; the processor is used to read and execute the computer software program, thereby implementing a CNC machine tool fault warning method based on the Industrial Internet of Things.

[0013] In addition, the present application also provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, a CNC machine tool fault warning method based on the industrial Internet of Things is implemented.

[0014] The beneficial effects that this application can achieve are as follows:

[0015] By acquiring the monitoring and operating parameters of multiple key monitoring points of the target CNC machine tool through the IoT sensor network, real-time monitoring of the machine tool's operating status is achieved, providing basic data support for fault early warning. The monitoring and operating parameters are analyzed according to the parameter safety constraint range of each key monitoring point to identify potential risk points. Potential abnormal trends can be identified before the parameters have completely exceeded the safety range, thus achieving early detection of fault signs. When potential risk points are identified, the subsequent processing tasks that have not been executed by the target CNC machine tool are obtained to evaluate them in combination with the actual work needs of the machine tool, rather than judging based on the current status. The failure probability of the target CNC machine tool is determined based on the potential risk points and subsequent processing tasks. By considering the possible evolution trend of the risk points in the future processing process, the accuracy and foresight of the early warning are improved. If the failure probability is greater than or equal to the preset probability threshold, an early warning message is sent to the management terminal through the IoT communication network to promptly remind relevant personnel to take preventive measures.

[0016] Through the above technical solution, this application realizes the early identification, evaluation and timely warning of potential faults of CNC machine tools, effectively prevents the occurrence of serious faults, ensures the safe operation of equipment and the continuity of production, and improves the reliability of CNC machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of the process of the CNC machine tool fault warning method based on the Industrial Internet of Things provided by the present invention;

[0018] Figure 2 A schematic diagram of the structure of the CNC machine tool fault warning system based on the Industrial Internet of Things provided by the present invention;

[0019] Figure 3 A schematic structural diagram of the electronic device provided by the present invention;

[0020] Figure 4 A schematic structural diagram of a computer-readable storage medium provided by the present invention.

[0021] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0022] A CNC machine tool fault warning system 100 based on the industrial Internet of Things, a management platform 101, a sensor network platform 102, an object platform 103, a data acquisition module 11, a risk identification module 12, a task acquisition module 13, a fault prediction module 14, a warning notification module 15, an electronic device 200, a memory 210, a processor 220, a computer program 211, and a computer-readable storage medium 300.

[0023] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain preset posture (as shown in the accompanying drawings). If the preset posture changes, the directional indication will also change accordingly.

[0026] In the present invention, unless otherwise specified or limited, the terms "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can mean fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two elements or interaction between two elements, unless otherwise specified. Those skilled in the art will be able to understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0027] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme in which A and B are satisfied at the same time. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0028] Example 1:

[0029] like Figure 1 As shown, an embodiment of the present invention provides a CNC machine tool fault warning method based on the industrial Internet of Things, comprising:

[0030] S1: Obtain monitoring operation parameters of multiple key monitoring points of the target CNC machine tool through the IoT sensor network;

[0031] S2: Analyze the monitoring operation parameters according to the parameter safety constraint range of each key monitoring point to identify potential risk points;

[0032] S3: When a potential risk point is identified, obtaining subsequent processing tasks that have not been executed by the target CNC machine tool;

[0033] S4: Determine the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task;

[0034] S5: If the failure probability is greater than or equal to a preset probability threshold, send an early warning message.

[0035] Specifically, first, an IoT sensor network deployed on the target CNC machine tool acquires monitoring parameters at multiple key monitoring points. The IoT sensor network includes various types of sensors, such as temperature, vibration, current, sound, and pressure sensors, installed at key monitoring points on the CNC machine tool. Key monitoring points are specific locations on the target CNC machine tool that provide a significant indicator of the machine tool's overall performance and fault status. These locations are typically prone to failure or critical locations where parameter changes can effectively reflect the machine tool's overall health. For example, the contact points between the inner and outer rings of the spindle bearings monitor bearing temperature and vibration characteristics; the contact surfaces of the screw-nut pair collect motion accuracy and friction data; key locations of the servo motor's stator and rotor monitor motor operating conditions; and the tool-workpiece contact area collects cutting parameters. The monitoring parameters collected by the IoT sensor network include, but are not limited to, temperature data, vibration frequency and amplitude, current fluctuations, noise characteristics, pressure changes, and other physical quantities. These parameters comprehensively reflect the CNC machine tool's operating status during operation, providing real-time operating parameter information for fault warning.

[0036] Then, the monitoring operating parameters are analyzed based on the parameter safety constraint intervals of each key monitoring point to identify potential risk points. The parameter safety constraint interval refers to the safe range within which the monitoring parameters of each key monitoring point should remain under normal operation. By comparing these parameters with the pre-established safety constraint intervals, it is determined whether the current monitoring operating parameters are abnormal. Specifically, the monitoring operating parameters collected by the IoT sensor network are compared with the safety constraint intervals of the corresponding monitoring points to analyze whether the parameters exceed the safe range or exhibit abnormal trends. When the monitoring operating parameters of a key monitoring point approach or exceed the boundaries of the safety constraint interval, or when the parameter change rate is abnormal, the key monitoring point is marked as a potential risk point. For example, if the spindle bearing temperature continues to rise and approaches the preset temperature upper limit, or if the vibration spectrum of the screw-nut pair exhibits abnormal peaks, these key monitoring points will be identified as potential risk points. In this way, the most risky areas can be screened from among the many key monitoring points, providing key focus for subsequent fault warning analysis.

[0037] After identifying potential risk points, information about the target CNC machine tool's pending machining tasks is obtained to assess the impact of these potential risk points on subsequent machining tasks. Specifically, these subsequent machining tasks are stored in the target CNC machine tool's CNC system in the form of machining programs, process parameter tables, or task schedules. By interacting with the target CNC machine tool's control system, a list of remaining tasks in the current machining task plan is obtained, revealing subsequent machining tasks, including but not limited to information such as the type and quantity of workpieces to be machined, machining process requirements, and estimated machining time. This information can be used to analyze the potential failure risks that these potential risk points may cause during future machining, specifically assessing the failure probability of these potential risk points under different machining load conditions. For example, for an identified potential risk point with abnormal spindle bearing temperature, if the subsequent machining task involves a large number of high-speed cutting operations, this could further exacerbate the bearing temperature rise and increase the risk of failure. Similarly, for a potential risk point with abnormal servo system vibration, if the subsequent machining task requires high-precision contour machining, this could lead to a decrease in machining accuracy or even system failure.

[0038] After identifying potential risk points and obtaining subsequent machining tasks, the probability of a target CNC machine tool failing during the subsequent machining task is assessed. For example, a historical data-driven simulation prediction method can be used to determine the failure probability. First, a digital twin model of the CNC machine tool is constructed, which contains the machine tool's key components and their dynamic response characteristics. Then, the current state parameters of the potential risk point are input into the digital twin model, and the process parameters of the subsequent machining task are loaded to simulate the machining process. Through simulation analysis, the parameter change trends of the potential risk component during future machining are predicted and matched against a library of historical failure cases to calculate the failure probability. For example, for a potential risk point with abnormal spindle bearing temperature, parameters such as the current temperature and temperature rise rate are input into the digital twin model, and the parameters of the subsequent high-speed milling task are loaded. The simulation system predicts the bearing temperature curve and its potential peak value under these machining conditions. If the predicted temperature curve matches the temperature change pattern before the bearing overheating failure in the historical failure case at 85%, the failure probability can be determined to be 0.72. This simulation-based method can more intuitively predict the failure risk of machine tools under specific task loads, providing a reliable basis for early warning decisions.

[0039] The resulting failure probability is then compared with a preset probability threshold. When the failure probability reaches or exceeds this threshold, an early warning mechanism is triggered. The preset probability threshold can be adjusted based on the importance of the machining task, the required precision, and the acceptable risk level, and is typically set between 0.6 and 0.8. When the failure probability is determined to exceed the preset threshold, early warning information is transmitted in real time to a management terminal via an IoT communication network, such as Industrial Ethernet, 5G networks, or dedicated industrial wireless communication networks. This early warning information includes, but is not limited to, the location and type of potential risk points, current abnormal parameter values ​​and trends, predicted failure type, and failure probability. The management terminal can be a workshop management system, a mobile device used by equipment maintenance personnel, an enterprise management system, or a cloud platform. By transmitting early warning information in a timely manner, relevant personnel can take preventive maintenance measures before a failure actually occurs, such as adjusting machining plans, replacing wearing parts, and performing equipment maintenance. This prevents serious consequences such as production interruptions, workpiece scrapping, or equipment damage caused by sudden equipment failure, thereby improving production efficiency and equipment utilization.

[0040] Through real-time monitoring of key monitoring points of CNC machine tools through the Internet of Things sensor network, combined with parameter safety constraint interval analysis, potential risk points can be identified in a timely manner; subsequent processing tasks are incorporated into the early warning analysis process, and the failure probability is determined based on potential risk points and subsequent processing tasks, achieving accurate prediction of failures; when the failure probability exceeds the preset probability threshold, early warning information is sent in a timely manner through the Internet of Things communication network, enabling relevant personnel to take preventive measures before the failure actually occurs, effectively avoiding production interruptions and equipment damage caused by sudden failures, and significantly improving the reliability and production efficiency of CNC machine tools.

[0041] As an optional implementation manner, analyzing the monitoring operation parameters according to the parameter safety constraint interval of each key monitoring point to identify potential risk points includes:

[0042] S21: performing time-frequency domain conversion on the monitoring operation parameters of each key monitoring point to obtain parameter spectrum characteristics;

[0043] S22: Obtaining a preset safe spectrum template for each of the key monitoring points;

[0044] S23: Obtaining a spectrum matching degree of each key monitoring point according to the parameter spectrum characteristics of each key monitoring point and a preset safe spectrum template;

[0045] S24: Mark key monitoring points where the spectrum matching degree is less than or equal to the matching degree threshold as potential risk points.

[0046] Specifically, first, the monitoring parameters at each key monitoring point are transformed into the time-frequency domain to obtain the parameter spectral characteristics. For example, time-frequency analysis methods such as the Fast Fourier Transform (FFT), wavelet transform, or Hilbert-Huang transform are used to convert the time-domain signal into the frequency domain and extract the spectral characteristics. This transformation enables more effective identification of abnormal characteristics that are difficult to detect in the time domain. For example, performing a Fast Fourier Transform on the spindle vibration signal can produce a vibration spectrum containing information such as frequency distribution, amplitude, and phase characteristics. This spectrum can reflect the health status of components such as bearings and gears in the spindle system. Next, a preset safe spectrum template is obtained for each key monitoring point. The preset safe spectrum template is a standard pattern of the parameter spectral characteristics of each key monitoring point under normal operating conditions of the target CNC machine tool. These templates can be obtained through statistical analysis of historical normal operating data, expert knowledge rules, standard parameters provided by the equipment manufacturer, or self-learning during the machine tool's initial operation. The preset safe spectrum template contains key information such as the main peak frequency of the spectrum, the frequency distribution range, and the amplitude characteristics.

[0047] Next, the spectrum matching degree of each key monitoring point is obtained based on the parameter spectrum characteristics of each key monitoring point and the preset safety spectrum template. The spectrum matching degree is an indicator to measure the similarity between the current spectrum characteristics and the preset safety spectrum template. By calculating the consistency between the current spectrum and the safety template in terms of frequency distribution, energy distribution, peak position, etc., a matching value between 0 and 1 is obtained, where 1 indicates a perfect match and 0 indicates a complete mismatch. Afterwards, the key monitoring points with a spectrum matching degree less than or equal to the matching degree threshold are marked as potential risk points. The matching degree threshold is a preset judgment standard, which is determined by an expert group based on the machine tool type, processing accuracy requirements and safety level, and is generally set between 0.7 and 0.9. When the spectrum matching degree of a key monitoring point is lower than the set threshold, it indicates that the parameter spectrum characteristics of the point have significantly deviated from the normal mode and there is a potential fault risk. Therefore, it is marked as a potential risk point for subsequent fault warning analysis.

[0048] Through the spectrum analysis-based method, potential risk points in CNC machine tools can be identified more accurately, providing a reliable basis for fault warning.

[0049] As an optional implementation manner, obtaining the spectrum matching degree of each key monitoring point according to the parameter spectrum characteristics of each key monitoring point and a preset safe spectrum template includes:

[0050] S231: Construct the following matching degree calculation formula:

[0051]

[0052] in, represents the parameter spectrum characteristics, T represents the preset safe spectrum template, Represents parameter spectrum characteristics The spectrum matching degree with the preset safe spectrum template T, Indicates the number of frequency points where the deviation of the parameter spectrum feature from the preset safe spectrum template is within the preset tolerance range. Indicates the total number of frequency points in the spectrum analysis, Represents parameter spectrum characteristics The main peak frequency, Indicates the main peak frequency of the preset safe spectrum template T, and Represent the spectrum matching rate weight and the main frequency similarity weight respectively and satisfy + ;

[0053] S232: According to the matching degree calculation formula, a matching degree is calculated for the parameter spectrum characteristics of each key monitoring point and a preset safe spectrum template to obtain a spectrum matching degree of each key monitoring point.

[0054] Specifically, first, a spectrum matching calculation formula is constructed. This formula comprehensively considers the similarity of spectrum distribution and the similarity of main frequency. The calculation formula is as follows:

[0055]

[0056] in, represents the parameter spectrum characteristics, T represents the preset safe spectrum template, Represents parameter spectrum characteristics The spectrum matching degree with the preset safe spectrum template T, Indicates the number of frequency points where the deviation of the parameter spectrum feature from the preset safe spectrum template is within the preset tolerance range. Indicates the total number of frequency points in the spectrum analysis, Represents parameter spectrum characteristics The main peak frequency, Indicates the main peak frequency of the preset safe spectrum template T, and Represent the spectrum matching rate weight and the main frequency similarity weight respectively and satisfy + The first part of the formula Indicates the overall spectrum matching rate, reflecting the similarity between the current spectrum and the template spectrum in overall distribution; the second part Calculate the similarity of the main peak frequency. The value is 1 when the main frequencies are exactly the same, and the greater the difference in main frequencies, the smaller the value. and Adjustment can flexibly adjust the importance of overall spectrum matching and main frequency matching in matching according to different types of machine tools and monitoring parameters.

[0057] The obtained parameter spectrum characteristics and the obtained preset safe spectrum template are then substituted into the spectrum matching formula to calculate the spectrum matching degree. The closer the matching degree is to 1, the more similar the current spectrum characteristics are to the safe template, and the more normal the key monitoring point is. Conversely, the closer the matching degree is to 0, the greater the difference between the current spectrum characteristics and the safe template, and the higher the possibility that the key monitoring point is a potential risk point.

[0058] By comprehensively considering the matching degree of the overall spectrum distribution and the main frequency characteristics, the status of key monitoring points can be evaluated more comprehensively and accurately, and the accuracy of identifying potential risk points can be improved.

[0059] As an optional implementation manner, determining the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task includes:

[0060] S41: Analyze the load characteristics of the subsequent processing task and obtain processing load parameters;

[0061] S42: Obtaining the risk level and load tolerance threshold of the potential risk point;

[0062] S43: Obtaining a load pressure coefficient according to a ratio of the processing load parameter to the load tolerance threshold;

[0063] S44: Based on the risk level and the load pressure coefficient, determining the failure probability of the target CNC machine tool during execution of the subsequent processing task.

[0064] Specifically, when determining the failure probability of a target CNC machine tool based on potential risk points and subsequent processing tasks, the process begins by analyzing the machining program for the target CNC machine tool's subsequent processing tasks and extracting process parameters such as cutting parameters, feed rate, and spindle speed. Combined with the characteristics of the material being processed and the processing requirements, various load parameters during the machining process are derived. These parameters include, but are not limited to, cutting force, cutting power, machining duration, feed load, and spindle load rate, comprehensively reflecting the load intensity of the subsequent machining tasks on the machine tool's various systems. Next, the risk level and load tolerance threshold of the potential risk point are determined. The risk level is determined based on the degree of parameter deviation of the identified potential risk point. For example, it is categorized into low, medium, and high, corresponding to minor, significant, and severe anomalies, respectively. The load tolerance threshold represents the maximum workload that the system at the potential risk point can withstand under the current risk state. This threshold decreases as the risk level increases. For example, for a risk point with abnormal spindle bearing temperature, the load tolerance threshold is the maximum allowable spindle speed or cutting power; for a risk point with abnormal servo system vibration, the load tolerance threshold is the maximum allowable feed rate or acceleration.

[0065] Next, the load pressure coefficient is calculated based on the ratio of the machining load parameter to the load tolerance threshold. The load pressure coefficient is a dimensionless indicator that measures the degree of pressure that subsequent machining tasks place on a potential risk point. When this coefficient approaches or exceeds 1, it indicates that the subsequent machining task will exert a load pressure on the potential risk point that approaches or exceeds its tolerance, increasing the likelihood of a failure. Next, based on the risk level and the load pressure coefficient, the failure probability of the target CNC machine tool during the execution of the subsequent machining task is determined. By comprehensively considering the current state of the potential risk point (reflected by the risk level) and the impact of the subsequent machining task (reflected by the load pressure coefficient), a relationship model between the two is established, and the failure probability is calculated. This failure probability reflects the likelihood of failure when executing a specific machining task under the current machine tool state, providing a quantitative basis for fault warning decisions.

[0066] By determining the failure probability based on risk level and load pressure coefficient, the failure risk can be dynamically assessed for different processing tasks, thereby improving the pertinence and accuracy of fault warning.

[0067] As an optional implementation manner, determining the failure probability of the target CNC machine tool in executing the subsequent processing task based on the risk level and the load pressure coefficient includes:

[0068] S441: Construct a failure probability calculation model as follows:

[0069]

[0070] in, represents the probability of failure, Indicates the risk level, represents the load pressure coefficient, represents a correction coefficient, wherein the correction coefficient is determined according to the type and usage time of the target CNC machine tool;

[0071] S442: Determine the failure probability of the target CNC machine tool based on the failure probability calculation model, the risk level, and the load pressure coefficient.

[0072] Specifically, first, a failure probability calculation model is constructed. Specifically, a failure probability calculation model based on an exponential function is adopted, and its expression is as follows:

[0073]

[0074] P represents the probability of failure, ranging from 0 to 1, with larger values ​​indicating a higher likelihood of failure. R represents the risk level, a quantitative value between 0 and 1 that reflects the severity of the potential risk point's current state. For example, a minor anomaly can be quantified as 0.3, a significant anomaly as 0.6, and a severe anomaly as 0.9. L represents the load pressure coefficient, which is the ratio of the machining load parameter to the load tolerance threshold and reflects the degree of pressure that subsequent machining tasks will place on the potential risk point. k represents the correction factor, which is determined based on the type and age of the target CNC machine tool. This model considers the combined effects of risk level and load pressure. As the risk level or load pressure coefficient increases, the probability of failure also increases. The correction factor k reflects the differences in failure sensitivity between different machine types and at different stages of use. For example, older machine tools typically have larger correction factors, reflecting the greater sensitivity of older equipment to failure risk.

[0075] Then, the obtained risk level, load pressure coefficient, and correction coefficient determined according to the machine tool characteristics are substituted into the above-mentioned failure probability calculation model to obtain the failure probability of the target CNC machine tool during the execution of subsequent processing tasks, providing a quantitative basis for subsequent early warning decisions.

[0076] By taking into account the risk status, processing load and equipment characteristics of the failure probability calculation method, it is possible to more accurately assess the failure risk of CNC machine tools under specific working conditions, and improve the scientific nature and reliability of fault warning.

[0077] As an optional implementation manner, before acquiring the monitoring operation parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network, the method further includes:

[0078] S61: Acquire equipment characteristic information of the target CNC machine tool;

[0079] S62: Acquire a set of processing tasks to be executed by the target CNC machine tool;

[0080] S63: Determine a plurality of key monitoring points for the target CNC machine tool according to the equipment characteristic information and the processing task set.

[0081] Specifically, first, obtain the target CNC machine tool's equipment characteristic information. Equipment characteristic information refers to a set of parameters that comprehensively reflect the basic characteristics of the CNC machine tool, including but not limited to the machine model, manufacturer, machining accuracy grade, maximum spindle speed, maximum cutting power, control system type, number of axes, production date, cumulative operating time, and historical fault records. This information can be obtained by querying the machine tool's nameplate, equipment archive, maintenance records, or directly reading it from the machine tool's control system. Equipment characteristic information is an important basis for identifying key monitoring points, as CNC machine tools of different types and at different stages of use may have significantly different fault-prone locations and failure modes. Simultaneously, obtain the target CNC machine tool's pending machining task set. A machining task set refers to all machining tasks scheduled for the machine tool within a specific time period, including information such as the workpiece material, machining process, cutting parameters, machining accuracy requirements, and estimated machining time for each task. The characteristics of the machining tasks are equally important in identifying key monitoring points, as different machining tasks impose varying degrees of load and wear on different machine tool components, thus affecting the location of potential faults. Afterwards, by comprehensively analyzing the machine tool's own equipment characteristic information and the set of processing tasks to be performed, the key parts that are most likely to fail or have the most significant impact on processing quality are identified and determined as key monitoring points.

[0082] By determining key monitoring points based on equipment characteristics and task characteristics, it is possible to customize monitoring plans for different machine tools and different processing tasks, improve the pertinence and efficiency of monitoring, avoid the limitations of fixed monitoring points in traditional methods, achieve optimal allocation of monitoring resources, and lay the foundation for subsequent fault warnings.

[0083] As an optional implementation, determining multiple key monitoring points for the target CNC machine tool based on the device characteristic information and the processing task set includes:

[0084] S631: Constructing a device characteristic vector based on the device characteristic information;

[0085] S632: Constructing a task characteristic vector based on the processing task set;

[0086] S633: Perform case search in a historical machine tool failure database based on the device characteristic vector and the task characteristic vector to obtain a set of similar machine tool failure cases;

[0087] S634: Determine the key monitoring points through the similar machine tool failure case set.

[0088] Specifically, the target CNC machine tool's device characteristic information is first quantified and standardized to form a device characteristic vector. This vector includes characteristic values ​​for multiple dimensions, including basic machine tool parameters (such as the number of axes, table size, and maximum travel), performance parameters (such as maximum spindle speed, maximum cutting power, and positioning accuracy), and usage parameters (such as age, accumulated operating hours, and maintenance frequency). This vectorized representation transforms the target CNC machine tool's device characteristic information into a standardized form suitable for mathematical calculations and similarity analysis. Simultaneously, the set of machining tasks to be performed by the CNC machine tool is feature extracted and quantified to construct a task characteristic vector. This vector reflects the key characteristics of the machining task, including factors such as the type of material being machined, machining complexity, required precision, average spindle speed, and machining duration.

[0089] Next, based on the device characteristic vector and task characteristic vector, a case search is performed in the historical machine tool failure database to obtain a set of similar machine tool failure cases. The historical machine tool failure database contains a large number of historical failure cases. Each case records information such as the characteristic vector of the faulty machine tool, the task characteristic vector before the failure, the fault location, and the fault type. By calculating the similarity between the device characteristic vector and task characteristic vector of the current machine tool and the historical cases, N similar failure cases are retrieved to form a set of similar machine tool failure cases. The similarity calculation can be performed using methods such as Euclidean distance and cosine similarity. Afterwards, a statistical analysis of the set of similar machine tool failure cases is performed to identify the locations with the highest fault frequency in these cases and the monitoring locations that have a significant predictive effect on failures. These locations are then identified as key monitoring points for the current CNC machine tool.

[0090] Through the key monitoring point determination method based on case retrieval, we can make full use of historical failure experience, optimize the configuration of monitoring resources, and improve the pertinence and effectiveness of fault warning.

[0091] The second embodiment of the present application provides a CNC machine tool fault warning system based on the industrial Internet of Things, such as Figure 2 As shown, the system 100 may include: a management platform 101, a sensor network platform 102 and an object platform 103 that are communicatively connected in sequence, the object platform 103 is used to obtain and store monitoring operation parameters of multiple key monitoring points of the target CNC machine tool, the sensor network platform 102 is used to transmit the monitoring operation parameters to the management platform 101, and the management platform may include: a data acquisition module 11, a risk identification module 12, a task acquisition module 13, a fault prediction module 14 and an early warning notification module 15. Among them, the data acquisition module 11 is used to obtain the monitoring and operating parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network; the risk identification module 12 is used to analyze the monitoring and operating parameters according to the parameter safety constraint interval of each key monitoring point to identify potential risk points; the task acquisition module 13 is used to obtain the subsequent processing tasks that have not been executed by the target CNC machine tool when the potential risk point is identified; the fault prediction module 14 is used to determine the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task; the early warning notification module 14 is used to send an early warning message if the failure probability is greater than or equal to a preset probability threshold; the sensor network platform 102 is also used to receive the early warning message and transmit the early warning message to the object platform 103; the object platform 103 is also used to control the target CNC machine tool based on the early warning information.

[0092] As an optional embodiment, the risk identification module 12 includes a time-frequency conversion unit, a template acquisition unit, a matching degree calculation unit, and a risk marking unit. The time-frequency conversion unit is used to perform time-frequency domain conversion on the monitoring operation parameters of each key monitoring point to obtain parameter spectrum characteristics; the template acquisition unit is used to obtain the preset safety spectrum template of each key monitoring point; the matching degree calculation unit is used to obtain the spectrum matching degree of each key monitoring point based on the parameter spectrum characteristics of each key monitoring point and the preset safety spectrum template; and the risk marking unit is used to mark key monitoring points with a spectrum matching degree less than or equal to a matching degree threshold as potential risk points.

[0093] As an optional implementation, the matching degree calculation unit includes a formula subunit and a calculation subunit. The formula subunit is used to construct the following matching degree calculation formula:

[0094]

[0095] in, represents the parameter spectrum characteristics, T represents the preset safe spectrum template, Represents parameter spectrum characteristics The spectrum matching degree with the preset safe spectrum template T, Indicates the number of frequency points where the deviation of the parameter spectrum feature from the preset safe spectrum template is within the preset tolerance range. Indicates the total number of frequency points in the spectrum analysis, Represents parameter spectrum characteristics The main peak frequency, Indicates the main peak frequency of the preset safe spectrum template T, and Represent the spectrum matching rate weight and the main frequency similarity weight respectively and satisfy + .

[0096] The calculation subunit is used to perform matching calculation on the parameter spectrum characteristics of each key monitoring point and the preset safe spectrum template according to the matching calculation formula to obtain the spectrum matching degree of each key monitoring point.

[0097] As an optional embodiment, the fault prediction module 14 includes a load analysis unit, a risk assessment unit, a pressure coefficient unit, and a fault prediction unit. The load analysis unit is configured to analyze the load characteristics of the subsequent processing task and obtain processing load parameters; the risk assessment unit is configured to obtain the risk level and load tolerance threshold of the potential risk point; the pressure coefficient unit is configured to obtain the load pressure coefficient based on the ratio of the processing load parameter to the load tolerance threshold; and the fault prediction unit is configured to determine the failure probability of the target CNC machine tool during the execution of the subsequent processing task based on the risk level and load pressure coefficient.

[0098] As an optional implementation, the fault prediction unit includes a model building subunit and a probability calculation subunit. The model building subunit is used to build a fault probability calculation model as follows:

[0099]

[0100] in, represents the probability of failure, Indicates the risk level, represents the load pressure coefficient, represents a correction coefficient, which is determined according to the type and usage time of the target CNC machine tool.

[0101] The probability calculation subunit is used to determine the failure probability of the target CNC machine tool based on the failure probability calculation model, the risk level and the load pressure coefficient.

[0102] As an optional embodiment, the system further includes a monitoring point determination module, which includes a device information unit, a task set unit, and a monitoring point determination unit. The device information unit is used to obtain device characteristic information of the target CNC machine tool; the task set unit is used to obtain a set of processing tasks to be executed by the target CNC machine tool; and the monitoring point unit is used to determine multiple key monitoring points for the target CNC machine tool based on the device characteristic information and the processing task set.

[0103] As an optional embodiment, the monitoring point unit further includes a device vector subunit, a task vector subunit, a case retrieval subunit, and a key point determination subunit. The device vector subunit is configured to construct a device characteristic vector based on the device characteristic information; the task vector subunit is configured to construct a task characteristic vector based on the processing task set; the case retrieval subunit is configured to perform case retrieval in a historical machine tool failure database based on the device characteristic vector and the task characteristic vector to obtain a set of similar machine tool failure cases; and the key point determination subunit is configured to determine the key monitoring points based on the set of similar machine tool failure cases.

[0104] A third embodiment of the present application provides an electronic device, such as Figure 3 As shown, the electronic device includes a memory 210, a processor 220, and a computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, a CNC machine tool fault warning method based on the industrial Internet of Things is implemented.

[0105] The fourth embodiment of the present application provides a computer-readable storage medium, such as Figure 4 As shown, a computer program 211 is stored on the computer-readable storage medium 300. When the computer program 211 is executed by the processor, a fault warning method for a CNC machine tool based on the industrial Internet of Things is implemented.

[0106] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A CNC machine tool fault warning method based on industrial Internet of Things, characterized in that: The method comprises: Obtain monitoring and operating parameters of multiple key monitoring points of the target CNC machine tool through the IoT sensor network; Analyze the monitoring operation parameters according to the parameter safety constraint range of each key monitoring point to identify potential risk points; When a potential risk point is identified, obtaining subsequent processing tasks that have not been executed by the target CNC machine tool; Determining a failure probability of the target CNC machine tool based on the potential risk points and the subsequent processing tasks; If the failure probability is greater than or equal to a preset probability threshold, send an early warning message; Determining the failure probability of the target CNC machine tool based on the potential risk point and the subsequent processing task includes: Analyzing the load characteristics of the subsequent processing task to obtain processing load parameters; Obtaining the risk level and load tolerance threshold of the potential risk point; Obtaining a load pressure coefficient according to a ratio of the processing load parameter to the load tolerance threshold; determining, based on the risk level and the load pressure coefficient, a failure probability of the target CNC machine tool during execution of the subsequent processing task; The determining, based on the risk level and the load pressure coefficient, of a failure probability of the target CNC machine tool during execution of the subsequent processing task includes: Construct the following failure probability calculation model: in, represents the probability of failure, Indicates the risk level, which is a quantitative value between 0 and 1. The higher the risk level, the larger the value of R; represents the load pressure coefficient, represents a correction coefficient, wherein the correction coefficient is determined according to the type and usage time of the target CNC machine tool; The failure probability of the target CNC machine tool is determined based on the failure probability calculation model, the risk level, and the load pressure coefficient.

2. The method according to claim 1, characterized in that Analyzing the monitoring operation parameters according to the parameter safety constraint intervals of each key monitoring point to identify potential risk points includes: Performing time-frequency conversion on the monitoring operation parameters of each of the key monitoring points to obtain parameter spectrum characteristics; Obtaining a preset safety spectrum template for each of the key monitoring points; Obtaining a spectrum matching degree of each of the key monitoring points according to the parameter spectrum characteristics of each of the key monitoring points and a preset safe spectrum template; Key monitoring points where the spectrum matching degree is less than or equal to the matching degree threshold are marked as potential risk points.

3. The method according to claim 2, characterized in that The obtaining of the spectrum matching degree of each key monitoring point according to the parameter spectrum characteristics of each key monitoring point and a preset safe spectrum template includes: Construct the following matching calculation formula: in, represents the parameter spectrum characteristics, T represents the preset safe spectrum template, Represents parameter spectrum characteristics The spectrum matching degree with the preset safe spectrum template T, Indicates the number of frequency points where the deviation of the parameter spectrum feature from the preset safe spectrum template is within the preset tolerance range. Indicates the total number of frequency points in the spectrum analysis, Represents parameter spectrum characteristics The main peak frequency, Indicates the main peak frequency of the preset safe spectrum template T, and Represent the spectrum matching rate weight and the main frequency similarity weight respectively and satisfy + ; According to the matching degree calculation formula, a matching degree calculation is performed on the parameter spectrum characteristics of each key monitoring point and a preset safe spectrum template to obtain the spectrum matching degree of each key monitoring point.

4. The method according to claim 1, wherein Before acquiring the monitoring operation parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network, the method further includes: Acquiring equipment characteristic information of the target CNC machine tool; Obtaining a set of processing tasks to be executed by the target CNC machine tool; A plurality of key monitoring points for the target CNC machine tool are determined based on the equipment characteristic information and the processing task set.

5. The method according to claim 4, characterized in that Determining a plurality of key monitoring points for the target CNC machine tool based on the equipment characteristic information and the processing task set includes: constructing a device characteristic vector based on the device characteristic information; Constructing a task characteristic vector based on the processing task set; Perform case retrieval in a historical machine tool failure database based on the device characteristic vector and the task characteristic vector to obtain a set of similar machine tool failure cases; The key monitoring points are determined through the similar machine tool failure case set.

6. The CNC machine tool fault warning system based on industrial Internet of Things is characterized by: For implementing the method according to any one of claims 1 to 5, the system comprises a management platform, a sensor network platform, and an object platform that are communicatively connected in sequence, the object platform being used to collect monitoring operation parameters of multiple key monitoring points of a target CNC machine tool, the sensor network platform being used to obtain the monitoring operation parameters and transmit the monitoring operation parameters to the management platform, the management platform comprising: A data acquisition module is used to obtain monitoring and operating parameters of multiple key monitoring points of the target CNC machine tool through the Internet of Things sensor network; A risk identification module is used to analyze the monitoring operation parameters according to the parameter safety constraint range of each key monitoring point to identify potential risk points; A task acquisition module is used to acquire subsequent processing tasks that have not been executed by the target CNC machine tool when a potential risk point is identified; A fault prediction module, configured to determine a failure probability of the target CNC machine tool based on the potential risk points and the subsequent processing tasks; An early warning notification module is used to send an early warning message if the failure probability is greater than or equal to a preset probability threshold; The sensor network platform is further configured to receive the warning information and transmit the warning information to the target platform; The object platform is further used to control the target CNC machine tool based on the warning information; The fault prediction module is also used to: analyze the load characteristics of the subsequent processing task to obtain the processing load parameters; obtain the risk level and load tolerance threshold of the potential risk point; obtain the load pressure coefficient based on the ratio of the processing load parameter to the load tolerance threshold; and determine the failure probability of the target CNC machine tool during the execution of the subsequent processing task based on the risk level and load pressure coefficient.

Images