A method and system for online monitoring of temperature of a cutting tool for a chipper

Abstract

The application provides a kind of temperature on-line monitoring method and system for chip removal machine cutting tool, it is related to chip removal machine cutting tool technical field.The method includes collecting the cutting process file and equipment parameter generation structured process data of cutting task;The dynamic change model of heat generation and conduction law in cutting process is constructed, and the predicted fluctuation curve of tool temperature is generated;High temperature interval or node is screened, and parallel cooling is carried out;Actual temperature data is collected and compared with the predicted fluctuation curve to judge whether the cutting tool temperature increases normally.The application accurately obtains the characteristic parameters of continuous steps by step semantic analysis and equipment parameter extraction, and improves the accuracy of temperature prediction curve.The dynamic model predicts the temperature trend, adjusts the heat conduction constraint combined with material and tool parameters, and realizes active prevention.Differentiation cooling strategy avoids resource waste and reduces energy consumption.Real-time comparison of actual and predicted temperature can timely detect abnormalities, ensure stable processing, and improve efficiency and quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cutting tool for chip removal machine, and particularly relates to a temperature online monitoring method for cutting tool of chip removal machine and a temperature online monitoring system for cutting tool of chip removal machine. BACKGROUND

[0002] In the cutting process of the chip removal machine, the temperature change of the cutting tool directly affects the tool life, machining accuracy and production safety. The traditional cutting tool temperature monitoring relies on manual inspection or simple single-point temperature sensors, which has problems such as response lag and limited monitoring range. Manual inspection is difficult to capture the temperature fluctuations in the high-speed cutting process in real time, and the single-point sensor can only reflect the local temperature and cannot cover the dynamic temperature changes of the tool in different steps and different cutting areas, which is easy to miss the key high-temperature risk points.

[0003] At the same time, the existing technology has a single cooling control strategy, usually using fixed cooling parameters, without considering the influence of cutting step differences, machined material characteristics and tool parameters, resulting in poor cooling effect or resource waste. For example, when switching between continuous steps, the fixed cooling intensity may not be able to adapt to the sudden change of cutting load, thereby causing the tool temperature to rise sharply, shortening the tool life and even causing the workpiece to be scrapped. In addition, the traditional method lacks the ability to predict the temperature change trend, and usually takes measures only when the temperature exceeds the safety threshold, which is difficult to achieve proactive prevention and increases the potential risk of production accidents. SUMMARY

[0004] The present application provides a temperature online monitoring method and system for cutting tool of chip removal machine to solve the defects in the prior art.

[0005] In one aspect, the present application provides a temperature online monitoring method for cutting tool of chip removal machine, comprising:

[0006] Collecting the cutting process file and device parameters of the cutting task, identifying the continuous steps in the cutting process file through step semantic analysis, and extracting the cutting fingerprints of each step in combination with the device parameters to generate structured process flow data.

[0007] Collecting the machined material characteristics, tool specification parameters and tool material material characteristics, combining the process flow data to construct a dynamic change model of heat generation and conduction rules in the cutting process, and generating a predicted fluctuation curve of the tool temperature.

[0008] Setting a high-temperature threshold for the cutting tool, screening the high-temperature interval or node according to the predicted fluctuation curve, formulating a cooling strategy, generating a cooling control instruction for the cutting tool according to the cooling strategy, and cooling the cutting tool according to the cooling control instruction.

[0009] In the cutting process, the actual temperature data of the cutting tool is collected in real time, the actual temperature data is dynamically compared with the predicted fluctuation curve, whether the temperature increase of the cutting tool is normal is judged according to the comparison result, otherwise an abnormal report is generated and the management personnel is notified.

[0010] According to the temperature online monitoring method for the cutting tool of the chip removal machine provided by the application, the cutting process file includes the sequence of cutting steps, the cutting time of each step, the position information of the cutting area and the step switching condition.

[0011] According to the temperature online monitoring method for the cutting tool of the chip removal machine provided by the application, the process of identifying the continuous steps in the cutting process file through step semantic analysis includes:

[0012] The cutting process file is subjected to text segmentation processing, and sentences containing keywords are extracted, the keywords including steps, start, end and switching.

[0013] The start and end positions of the steps are determined according to the time nodes and operation sequences of the sentences in the cutting process file.

[0014] The steps adjacent to each other and without interruption are classified as continuous steps, and a continuous step sequence is formed.

[0015] According to the temperature online monitoring method for the cutting tool of the chip removal machine provided by the application, the process of generating structured process flow data includes:

[0016] For each continuous step, the corresponding cutting speed and feed rate range are matched from the device parameters.

[0017] Combined with the cutting time of the step and the position information of the cutting area, the parameter combination of the step is generated as a cutting fingerprint.

[0018] The cutting fingerprints of all steps are arranged in sequence, the connection parameters between the steps are supplemented according to the step switching condition, and the structured process flow data containing the step sequence number, the cutting fingerprint, the time length and the position are formed.

[0019] According to the temperature online monitoring method for the cutting tool of the chip removal machine provided by the application, the machined material characteristics include hardness and shape. The tool specification parameters include the size, shape and edge angle of the tool. The tool material material characteristics include heat resistance and heat conduction ability.

[0020] According to the temperature online monitoring method for the cutting tool of the chip removal machine provided by the application, the process of constructing a dynamic change model of heat generation and conduction law in the cutting process includes:

[0021] Based on the cutting speed, feed rate and cutting time in the process data, the contact area and friction frequency of the tool and the material under different steps are analyzed to obtain the heat generation rate.

[0022] The heat conduction coefficient is determined in combination with the hardness of the machined material and the heat conduction ability of the tool material.

[0023] The size and shape in the tool specification parameters are taken as the constraint conditions of the heat conduction path to construct a dynamic change model reflecting the heat in the cutting process.

[0024] According to the temperature online monitoring method for the cutting tool of the chip machine provided by the application, the process of generating the predicted fluctuation curve of the tool temperature includes:

[0025] Each step parameter in the process data is input into the dynamic change model.

[0026] The rising and falling trend of the tool temperature in each step is simulated, and the temperature change slope is adjusted according to the cutting interruption when the step is switched.

[0027] The temperature change trend of all steps is connected to generate a predicted fluctuation curve of the tool temperature covering the entire cutting process, and the predicted fluctuation curve includes the predicted temperature value of the cutting tool at each time point.

[0028] According to the temperature online monitoring method for the cutting tool of the chip machine provided by the application, the process of generating the cooling control instruction of the cutting tool includes:

[0029] The safe temperature range in the historical cutting task is collected, and the high temperature threshold is set in combination with the tool material.

[0030] The interval or time node exceeding the high temperature threshold is marked in the predicted fluctuation curve.

[0031] The prolonged cooling time strategy is made for the high temperature interval, and the instantaneous enhanced cooling strength strategy is made for the high temperature node.

[0032] The cooling control parameters are generated according to the prolonged cooling time strategy and the instantaneous enhanced cooling strength strategy to obtain the cooling control instruction.

[0033] According to the temperature online monitoring method for the cutting tool of the chip machine provided by the application, the process of dynamically comparing the actual temperature data with the predicted fluctuation curve includes:

[0034] The corresponding temperature values in the actual temperature data and the predicted fluctuation curve are extracted at the same time interval.

[0035] The temperature difference value of each time point between the actual temperature data and the predicted fluctuation curve is calculated, and the difference value change trend of continuous multiple time points is counted.

[0036] If the temperature difference is within the preset allowable range, and the difference change trend does not exceed the preset fluctuation threshold, it is determined that the cutting tool temperature growth is normal.

[0037] In another aspect, the present application also provides a temperature online monitoring system for a cutting tool of a chipper, comprising:

[0038] A data acquisition module is configured to acquire a cutting process file, equipment parameters, material characteristics of a workpiece, and tool specification parameters and tool material characteristics.

[0039] A process flow acquisition module is configured to identify continuous working steps in the cutting process file through working step semantic analysis, and extract a cutting fingerprint of each working step in combination with the equipment parameters to generate structured process flow data.

[0040] A temperature prediction module is configured to construct a dynamic change model of heat generation and conduction rules in the cutting process according to the material characteristics of the workpiece, the tool specification parameters, and the tool material characteristics, in combination with the process flow data, to generate a predicted fluctuation curve of the tool temperature.

[0041] An instruction generation module is configured to set a high-temperature threshold of the cutting tool, filter a high-temperature interval or node according to the predicted fluctuation curve, develop a cooling strategy, and generate a cooling control instruction for the cutting tool according to the cooling strategy.

[0042] A cooling processing module is configured to control the start time, running time, and power adjustment parameters of the cooling system according to the cooling control instruction to cool the cutting tool.

[0043] An abnormality monitoring module is configured to acquire actual temperature data of the cutting tool in the cutting process in real time, dynamically compare the actual temperature data with the predicted fluctuation curve, determine whether the temperature growth of the cutting tool is normal according to the comparison result, otherwise generate an abnormality report and notify the management personnel.

[0044] The application provides a temperature online monitoring method and system for a cutting tool of a chip cutting machine. The application breaks through the limitation of traditional static threshold monitoring by introducing a dynamic change model, and can predict the change trend of the tool temperature in advance by analyzing the heat generation and conduction law under different working steps. The application combines the characteristics of the machined material and the tool parameters, and the model can dynamically adjust the constraint on the heat conduction path, so that the prediction curve can truly reflect the temperature fluctuation of the tool in the complex cutting process, realizes the change from passive response to active prevention, and effectively avoids the tool damage caused by sudden temperature rise. The application formulates and executes a differentiated cooling strategy, which reflects the advantages of fine control. The application adopts the strategy of prolonging the cooling time and instantaneously enhancing the cooling strength for the high temperature interval and node in the prediction fluctuation curve, avoids the resource waste problem of traditional fixed cooling parameters. At the same time, the dynamic matching of the cooling control instruction and the cutting working step ensures the timely response of the cooling system at the key node, which can not only inhibit the excessive temperature rise, but also reduce unnecessary cooling operation, and reduces the energy consumption and production cost. Through continuous comparison of the actual temperature data and the prediction curve, the abnormal temperature growth trend can be found in time, and the fault response time is shortened. The application not only ensures the stability of the machining process, but also optimizes the subsequent cutting parameters and cooling strategies through the accumulated abnormal data, and continuously improves the production efficiency and machining quality. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0046] Figure 1 is a flowchart of a temperature online monitoring method for a cutting tool of a chip cutting machine provided by an embodiment of the application;

[0047] Figure 2 is a flowchart of generating a prediction fluctuation curve of tool temperature in the embodiment;

[0048] Figure 3 is a structural schematic diagram of a temperature online monitoring system for a cutting tool of a chip cutting machine provided by an embodiment of the application. DETAILED DESCRIPTION

[0049] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0050] The technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application. Figures 1-3 A temperature online monitoring method and system for a cutting tool of a chip removal machine are described.

[0051] Figure 1 A flowchart of a temperature online monitoring method for a cutting tool of a chip removal machine is provided in an embodiment of the present application.

[0052] As shown in the drawings, Figure 1 A temperature online monitoring method and system for a cutting tool of a chip removal machine are provided in an embodiment of the present application. The execution subject can be a temperature online monitoring method for a cutting tool of a chip removal machine. The method comprises the following steps.

[0053] The cutting process file and the equipment parameter of the cutting task are collected. Specifically, the unique identifier of the cutting task is searched in the corresponding task management module by connecting the manufacturing execution system or the process management platform in the enterprise through the industrial Ethernet, the digital cutting process file associated with the unique identifier is called, the digital cutting process file can include process cards, processing program lists and various formats, the real-time communication with the chip removal machine is established through the OPCUA interface of the equipment control system, the dynamic parameters during the equipment operation are read, the data real-time is ensured to be within 1 second, the continuous working steps in the cutting process file are identified through the working step semantic analysis, the cutting fingerprints of each working step are extracted in combination with the equipment parameters, and the structured process flow data are generated.

[0054] The cutting process file includes the sequence of the cutting working steps, the cutting time length of each working step, the position information of the cutting area and the working step switching condition. In addition to the spindle speed change threshold, the tool replacement signal and the cutting depth adjustment instruction, the working step switching condition further includes the workpiece positioning accuracy detection result, the cooling liquid pressure standard signal and other auxiliary trigger conditions. These conditions need to meet the combination relationship of logical "and" or "or" to trigger the working step switching. The equipment parameters include the cutting speed and the feed rate of the chip removal machine. The cutting speed includes the speed range of the spindle under different working conditions such as no load, light load and heavy load, and 3-5 typical speed values corresponding to each range are taken as references. The feed rate covers the speed parameters of longitudinal and transverse feeding, and includes the change range of the feeding acceleration and deceleration to reflect the dynamic characteristics of the feeding process.

[0055] The process of identifying continuous machining steps in the machining process file through step semantic analysis includes:

[0056] The machining process file is subjected to text segmentation processing, and a bidirectional maximum matching segmentation algorithm in natural language processing is used to disassemble the file content into independent lexical units. For professional terms such as "high-speed machining step", a self-defined dictionary is used to ensure the accuracy of segmentation, and irrelevant characters such as punctuation marks, redundant modifiers, etc. are filtered out to form a lexical sequence. The sentences containing keywords are extracted, and the keyword weight is calculated based on the TF-IDF algorithm to accurately locate the sentence fragments containing core words such as "step", "start", "end", and "switch". For cases where there are synonyms for keywords, such as "process" being equivalent to "step", a synonym dictionary is used for mapping processing, and the line number and column number of these sentences in the file are recorded as position indexes. The keywords include steps, start, end, and switch.

[0057] The start and end positions of the steps are determined according to the time nodes and operation sequences of the sentences in the machining process file. The timestamp information corresponding to each step is parsed from the extracted sentences, with a precision of microseconds. The context logic of keywords such as "start" and "end" is combined, such as "Step 2 starts at 10:05:23.123456" to determine the start time, and "Step 2 ends at 10:08:15.654321" to determine the completion time. For files without explicit timestamps, the relationship between adjacent operations is used, such as "Step 3 is executed immediately after Step 2 is completed", to calculate the start time of Step 3 as the end time of Step 2, to determine the time boundaries of the steps. Adjacent steps without interruption are classified as continuous steps, and the time interval between adjacent two steps is checked. The difference between the end time of the previous step and the start time of the next step is calculated. If the difference is within 0-100 milliseconds and no interruption instructions such as tool replacement instructions, equipment emergency stop signals, spindle overload alarms, etc. appear in between, it is determined as a continuous step, forming a continuous step sequence. The sequence contains the number of each continuous step, the time range (accurate to microseconds), the associated spindle speed, the feed rate, and other operation instructions, as well as the machining surface information corresponding to the step.

[0058] The process of generating structured process data includes:

[0059] For each continuous step, the corresponding cutting speed and feed rate range are matched from the device parameters. According to the machining type of the step (such as rough machining, finishing machining, semi-finishing machining), the appropriate cutting speed range and feed rate range are selected from the device parameter library. For rough machining, the cutting speed range is usually low and wide, and the feed rate range is high. For finishing machining, it is the opposite. The step number and corresponding speed and feed rate range are bound through a parameter mapping algorithm based on BP neural network.

[0060] The cutting duration is accurately calculated by the difference between the start and end times, which is accurate to the millisecond level, and the deviation range of the duration, such as ±5 milliseconds, is recorded to reflect the fluctuations in actual processing. The position information of the cutting area is converted into three-dimensional coordinate values (X, Y, Z) through the machine tool coordinate system (such as G54-G59 coordinate system), and each coordinate value is kept to four decimal places. The specific coordinate range of the machining area on the workpiece corresponding to the process step is determined, including the starting point, end point and boundary contour of the area. The parameter combination of the process step is generated as the cutting fingerprint. The cutting speed range, feed rate range, cutting duration and area coordinates are integrated into a set of characteristic parameters. A unique cutting fingerprint of the process step is generated through the SHA-256 hash algorithm. The fingerprint length is 256 bits, ensuring the uniqueness of the fingerprints of different process steps.

[0061] The cutting fingerprints of all process steps are arranged in order, and the cutting fingerprints are sorted according to the time sequence of the continuous process step sequence. If there is a timestamp duplication during the sorting process, the size of the process step number is used to determine the sequence to ensure consistency with the actual processing sequence. The connection parameters between the process steps are supplemented according to the process switching conditions. The connection parameters include the transition time during process switching, the spindle speed adjustment gradient (such as increasing / decreasing 500 revolutions per second), the feed rate change rate (such as increasing / decreasing 0.1 mm / r per second), etc. These parameters are extracted from the process switching conditions. For multi-condition triggered switching, the average value of the parameters corresponding to each condition is taken. The structured process flow data containing the process step number, cutting fingerprint, duration and position is formed. The final data is presented in a standardized table in JSON format. Each field contains not only the specific parameter value but also metadata such as data collection time and credibility, which can be directly called by the subsequent heat model construction module through the API interface.

[0062] The material being processed characteristics, tool specification parameters and tool material material characteristics are collected. The material being processed characteristics are retrieved from the material detection database, covering the material hardness level, such as Brinell hardness and Rockwell hardness specific value; three-dimensional shape parameters, including length, width, height and surface curvature radius, etc.; tool specification parameters are obtained from the tool management system, including the specific size of the tool, such as diameter, length, handle size; geometry, such as straight handle, taper handle, spiral groove structure; the exact angle value of the blade angle, such as rake angle, relief angle, blade inclination angle; tool material material characteristics are extracted from the tool material manual, involving heat resistance performance index (such as maximum heat resistance temperature, hardness retention rate at high temperature) and thermal conductivity parameter (such as specific value range of thermal conductivity coefficient). Combined with the process flow data, a dynamic change model of heat generation and conduction law in the cutting process is constructed to generate a predicted fluctuation curve of tool temperature.

[0063] The material properties include hardness and shape, where the hardness is detected by the actual value of the hardness meter, and the shape includes the overall profile, surface features and internal structure of the material; the tool specification parameters include the size, shape and edge angle of the tool, the size parameter is accurate to the micron level, the shape is described by the model file generated by the three-dimensional modeling software, and the edge angle is accurate to the minute; the tool material quality characteristics include heat resistance and heat conduction capacity, the heat resistance is reflected in the hardness decay rate of the tool in different temperature intervals, and the heat conduction capacity is represented by the heat conduction amount per unit area per unit time.

[0064] The process of constructing a dynamic change model of heat generation and conduction rules in the cutting process includes:

[0065] Based on the cutting speed, feed rate and cutting time in the process flow data, the specific value of cutting speed, the actual rate of feed rate and the accurate time of cutting time of each step are extracted from the structured process flow data, and these parameters are arranged into parameter sequences in the order of steps. The contact area and friction frequency of the tool and the material under different steps are analyzed, and the actual contact area of the tool and the material in each step is calculated through three-dimensional contact simulation according to the shape and size of the tool and the shape of the machined material. The friction frequency in unit time, i.e. the friction frequency, is calculated by combining the cutting speed and the feed rate, the heat generation rate is obtained, and the heat value generated per second is calculated through the energy conversion formula according to the contact area, friction frequency, cutting force and friction coefficient of the material, which is the heat generation rate. The formula is expressed as:

[0066]

[0067] In the formula, Q represents the heat generation rate, A represents the contact area of the tool and the material, f represents the friction frequency, F represents the cutting force, represents the friction coefficient of the material.

[0068] The heat conduction coefficient is determined by combining the hardness of the machined material and the heat conduction capacity of the tool material. The higher the hardness of the machined material, the greater the friction resistance of the tool, and the higher the corresponding correction coefficient. The stronger the heat conduction capacity of the tool material, the greater the basic heat conduction coefficient value. The two are integrated through a weighting algorithm to obtain a comprehensive heat conduction coefficient. The coefficient will be dynamically adjusted with the change of the cutting conditions in the steps. The formula is expressed as:

[0069]

[0070] In the formula, K represents the comprehensive heat conduction coefficient, and respectively represent the weight of the hardness correction coefficient of the machined material and the basic heat conduction coefficient of the tool material, represents the hardness correction coefficient of the machined material, This indicates the basic thermal conductivity of the tool material.

[0071] The dimensions and shape of the tool specifications are used as constraints on the heat conduction path. The dimensions of the tool determine the cross-sectional area for heat conduction, and the shape determines the direction and path of heat conduction (e.g., the heat conduction path of a spiral groove tool is along the spiral direction). These parameters are transformed into boundary conditions for heat conduction using finite element analysis software to construct a model that reflects the dynamic changes in heat during the cutting process. The model takes the heat generation rate as input, the heat conduction coefficient as the conduction characteristic parameter, and the tool dimensions and shape as constraints. Numerical simulation algorithms are used to calculate the heat distribution and temperature changes of various parts of the tool at different times in real time.

[0072] Figure 2 This is a schematic diagram of the process for generating the predicted fluctuation curve of the tool temperature in this embodiment.

[0073] like Figure 2 As shown, the process of generating the predicted fluctuation curve of tool temperature includes:

[0074] Each step parameter in the process flow data is input into the dynamic change model. The cutting speed, feed rate, cutting time and other parameters are imported into the model one by one in the order of the steps. At the same time, the heat generation rate and heat conduction coefficient corresponding to each step are associated to ensure that the model can identify the parameter differences between different steps.

[0075] The simulation model simulates the rise and fall of tool temperature within each machining step. At the initial stage of the step, based on the heat generation rate and the initial tool temperature, the simulation model shows the temperature rise over time, with the rise slope positively correlated with the heat generation rate. When the cutting parameters are stable within the step, the temperature tends to rise gradually or remain stable. Near the end of the step, if the heat generation rate decreases, the simulation model shows the temperature fall trend. The temperature change slope is adjusted based on the cutting interruption during step switching. If cutting is interrupted during step switching, heat generation stops, and the temperature change slope becomes negative, with the magnitude of the drop related to the interruption time and the tool's heat dissipation capacity. If steps are switched continuously, the temperature change slope is adjusted for a smooth transition based on the difference in heat generation rates between preceding and following steps.

[0076] The temperature change trend of all steps is connected, the temperature change curve simulated by each step is spliced in time sequence, the temperature value is ensured to be continuous at the connection point to avoid mutation, the slope change of the connection point is processed by the curve smoothing algorithm, the tool temperature prediction fluctuation curve covering the entire cutting process is generated, the horizontal axis of the curve is the cutting time, the vertical axis is the tool temperature value, the starting and ending time points of each step are marked in the curve, the prediction temperature value corresponding to each time point of the cutting tool is included in the prediction fluctuation curve, the temperature value of each time point is calculated by the model and stored as a temperature-time data table, which can be directly used for subsequent cooling control and temperature comparison.

[0077] A high temperature threshold of the cutting tool is set, the temperature records of the tool without overheating damage are screened out by calling the historical database of the same type of cutting task in recent years, the upper limit value of the safe temperature interval is counted, and the heat resistance limit of the tool material quality (such as the heat resistance limit of high-speed steel tool about 600℃, and the heat resistance limit of hard alloy tool about 800℃) is combined, the smaller value of the upper limit value of the safe temperature interval and 80% of the heat resistance limit is taken as the high temperature threshold reference, and the threshold is adjusted according to the hardness of the machined material, the threshold is adjusted down by 5-8℃ for every 10HRC increase in hardness, according to the prediction fluctuation curve, the high temperature interval or node is screened, the prediction fluctuation curve is imported into the data analysis software, all temperature values exceeding the high temperature threshold in the curve are automatically scanned by the threshold comparison algorithm, the continuous section of three or more continuous time points exceeding the threshold is marked as the high temperature interval, and the single or discontinuous time point exceeding the threshold is marked as the high temperature node, and the start and end time of the interval, the specific time and corresponding temperature value of the node are recorded, the cooling strategy is developed, the cutting parameters in the high temperature interval are analyzed, such as continuous high feed rate, and the proportion of cooling time to be extended is calculated, the instantaneous enhanced cooling intensity is developed according to the amplitude of the node temperature exceeding the threshold, such as 20% for every 10℃, the specific length of the extended cooling time, the pressure increase of the instantaneous enhanced cooling intensity and other parameters are converted into digital signals recognizable by the cooling system, and the cutting tool is cooled according to the cooling control instruction, after receiving the instruction, the cooling system changes the flow by adjusting the speed of the cooling liquid pump, and adjusts the jet angle by controlling the opening of the electromagnetic valve, to ensure that the cooling time is continuously extended in the high temperature interval and the cooling intensity is instantaneously enhanced in the high temperature node.

[0078] The process of generating the cooling control instruction of the cutting tool includes:

[0079] Collect the safe temperature range in historical cutting tasks, extract the cutting task data of the same tool type and the same machined material from the enterprise production management system in the past five years, eliminate abnormal temperature records caused by equipment failure and operation errors, calculate the safe temperature range of the confidence interval through normal distribution analysis, record the upper limit value and the lower limit value of the range, set the high temperature threshold value combined with the tool material quality, query the thermal stability parameter according to the chemical composition of the tool material, and calculate the final high temperature threshold value by weighting the upper limit value of the safe temperature range and the 90% of the thermal stability parameter, which is expressed as:

[0080]

[0081] In the formula, represents the final high temperature threshold value, and respectively represent the weight of the upper limit value of the safe temperature range and the 90% of the thermal stability parameter, represents the upper limit value of the safe temperature range, represents the thermal stability parameter of the tool material.

[0082] Mark the interval or time node that exceeds the high temperature threshold value in the predicted fluctuation curve, use the curve segmentation scanning method, compare the curve temperature value with the high temperature threshold value at intervals of 0.1 seconds, integrate the time points that continuously exceed the threshold value into a high temperature interval, mark the start time, end time and average threshold value amplitude of the interval, mark the isolated threshold value time point as a high temperature node (mark the node time and instantaneous threshold value amplitude), and mark the interval with red shadow and the node with red dot in the curve chart.

[0083] Develop an extended cooling time strategy for the high temperature interval, calculate the basic cooling time according to the duration of the interval, and adjust the cooling time by 10% for every 5℃ increase in the threshold value amplitude, while ensuring that the total cooling time after extension does not exceed 1.2 times the duration of the interval to avoid affecting the processing efficiency, which is expressed as:

[0084]

[0085] In the formula, represents the extended cooling time, represents the basic cooling time, represents the average threshold value amplitude of the interval.

[0086] Develop an instantaneous enhanced cooling intensity strategy for the high temperature node, determine the intensity increment according to the value of the node temperature exceeding the threshold value, such as 30% for exceeding 10℃, 50% for exceeding 20℃, and set the duration of the enhancement.

[0087] The temperature control parameters are generated according to the prolonged cooling time strategy and the instant enhanced cooling intensity strategy, the prolonged cooling time strategy is converted into a running time parameter and a start delay time of the cooling system, and the instant enhanced cooling intensity strategy is converted into a cooling liquid pressure parameter, a flow parameter and a jet direction angle, so that a temperature control instruction is obtained, all the control parameters are packaged into a standardized instruction package according to a communication protocol of the cooling system, and the standardized instruction package includes an instruction number, an execution time, a parameter value and a check code.

[0088] Real-time acquisition of actual temperature data of the cutting tool in the cutting process, continuous acquisition of temperature values by an infrared temperature measuring instrument installed near the tool, data transmission to a data processing terminal after filtering processing, storage as a temperature sequence with a time stamp, dynamic comparison of the actual temperature data and the predicted fluctuation curve, complete alignment of the time axis of the actual temperature data and the predicted curve through a data synchronization algorithm, analysis of the degree of coincidence of the two in sections by a sliding window comparison method, judgment of whether the temperature increase of the cutting tool is normal according to the comparison result, if the comparison results of 10 consecutive time points all meet the normal standard, it is determined that the temperature increase is normal, if 3 or more time points do not meet the standard or the single time point exceeds the tolerance by ≥15℃, it is determined to be abnormal, otherwise an abnormal report is generated, the report includes the abnormal start time, the current actual temperature, the predicted temperature, the tolerance amplitude, the current working step and the corresponding cutting parameters, and the comparison chart of the actual temperature and the predicted curve is attached, and the management personnel are notified, the warning information is sent to the terminal equipment of the management personnel through the message push function of the production management system, including the abnormal level (general, serious, urgent) and the recommended treatment measures, and the sound and light alarm of the equipment is triggered synchronously in an emergency.

[0089] The process of dynamically comparing the actual temperature data with the predicted fluctuation curve includes:

[0090] The corresponding temperature values in the actual temperature data and the predicted fluctuation curve are extracted at the same time interval, the temperature values are extracted one by one from the actual temperature sequence and the predicted curve data according to the time stamp, two groups of comparison data pairs with the same length are formed, and it is ensured that there are corresponding actual values and predicted values at each time point.

[0091] The temperature difference value of each time point between the actual temperature data and the predicted fluctuation curve is calculated, the difference value is obtained by subtracting the predicted temperature value from the actual temperature value (a positive value indicates that the actual temperature is too high, and a negative value indicates that the actual temperature is too low), the absolute value of the difference value is recorded, and the difference value change trend of consecutive multiple time points is counted, the average value and the standard deviation of the difference value of consecutive 5 time points are calculated, the change slope of the difference value is obtained through linear fitting, and the slope is positive, indicating that the amplitude of the actual temperature deviating from the predicted value is increasing, and the slope is negative, indicating that the amplitude is decreasing.

[0092] If the temperature difference is within the preset allowable range, and the difference change trend does not exceed the preset fluctuation threshold, it is determined that the cutting tool temperature growth is normal, and the normal determination result is fed back to the control system in real time, and the current cooling strategy is maintained unchanged; if it is determined to be abnormal, the system will automatically trigger an abnormal processing procedure.

[0093] In summary, the embodiment provides an online temperature monitoring method for cutting tools of chip removal machines. Through the generation of structured process flow data, combined with step semantic analysis and equipment parameter extraction, a fine description of the cutting process is achieved. Compared with traditional extensive data collection, this method can accurately identify the characteristic parameters of continuous steps, providing more realistic cutting scene input data for temperature prediction, making the construction of the heat model more targeted, and greatly improving the accuracy of the temperature prediction fluctuation curve, laying a reliable foundation for subsequent cooling control. The introduction of the dynamic change model breaks through the limitations of traditional static threshold monitoring, and by analyzing the heat generation and conduction rules under different steps, the trend of tool temperature change can be predicted in advance. Combined with the characteristics of the machined material and the tool parameters, the model can dynamically adjust the constraints on the heat conduction path, so that the prediction curve can truly reflect the temperature fluctuations of the tool in the complex cutting process, realizing the transition from passive response to active prevention, and effectively avoiding tool damage caused by sudden temperature rise. The formulation and execution of differentiated cooling strategies demonstrate the advantages of fine control. For the high temperature interval and nodes in the prediction fluctuation curve, strategies such as extending the cooling time and instantaneously enhancing the cooling intensity are used, avoiding the resource waste problem of traditional fixed cooling parameters. At the same time, the dynamic matching of cooling control instructions and cutting steps ensures the timely response of the cooling system at key nodes, both suppressing excessive temperature rise and reducing unnecessary cooling operations, reducing energy consumption and production costs. Real-time monitoring and dynamic comparison mechanism form a closed-loop control system. By continuously comparing actual temperature data with prediction curves, abnormal temperature growth trends can be detected in time, and when the fluctuation range exceeds the allowable range, an abnormal report is generated and the manager is notified, shortening the fault response time. This dynamic feedback capability not only ensures the stability of the machining process, but also optimizes subsequent cutting parameters and cooling strategies through accumulated abnormal data, continuously improving production efficiency and machining quality.

[0094] The scheme has good adaptability and expandability. By integrating various information such as machined material characteristics and tool specification parameters, it can flexibly respond to monitoring needs of different materials and different cutting tasks without the need for large-scale modification of the hardware system. This versatility enables it to be widely applied to various chip removal machining scenarios, providing practical technical support for the intelligent upgrading of the manufacturing industry.

[0095] Based on the same general inventive concept, the present application also protects an online temperature monitoring system for a cutting tool of a chip removal machine. The following describes an online temperature monitoring system for a cutting tool of a chip removal machine provided by the present application. The online temperature monitoring system for a cutting tool of a chip removal machine described below can be mutually corresponding with reference to the online temperature monitoring method for a cutting tool of a chip removal machine described above.

[0096] Figure 3 FIG. 1 is a structural schematic diagram of an online temperature monitoring system for a cutting tool of a chip removal machine provided by an embodiment of the present application.

[0097] As shown in FIG. 1, an online temperature monitoring system for a cutting tool of a chip removal machine includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor includes a data acquisition module, a process flow acquisition module, a temperature prediction module, an instruction generation module, a cooling processing module, and an abnormality monitoring module. Figure 3

[0098] The data acquisition module is configured to acquire a cutting process file of a cutting task, equipment parameters, material properties of a workpiece, and tool specification parameters and tool material properties.

[0099] The process flow acquisition module is configured to identify continuous steps in the cutting process file through step semantic analysis, and extract a cutting fingerprint of each step in combination with the equipment parameters to generate structured process flow data.

[0100] The temperature prediction module is configured to construct a dynamic change model of heat generation and conduction rules in a cutting process according to the material properties of the workpiece, the tool specification parameters, and the tool material properties in combination with the process flow data to generate a predicted fluctuation curve of the tool temperature.

[0101] The instruction generation module is configured to set a high-temperature threshold of the cutting tool, filter a high-temperature interval or node according to the predicted fluctuation curve, formulate a cooling strategy, and generate a cooling control instruction of the cutting tool according to the cooling strategy.

[0102] The cooling processing module is configured to control a start time, a running time, and a power adjustment parameter of a cooling system according to the cooling control instruction to cool the cutting tool.

[0103] The abnormality monitoring module is configured to acquire actual temperature data of the cutting tool in real time, dynamically compare the actual temperature data with the predicted fluctuation curve, determine whether the temperature increase of the cutting tool is normal according to a comparison result, generate an abnormality report if not, and notify a manager.

[0104] ​Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0105] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for on-line temperature monitoring of a cutting tool for a chip removal machine, characterized in that, The method comprises the following steps: Collecting the cutting process file and equipment parameters of the cutting task, identifying the continuous working steps in the cutting process file through working step semantic analysis, and extracting the cutting fingerprints of each working step in combination with the equipment parameters to generate structured process flow data; Collecting the material properties and tool specification parameters and tool material quality characteristics, combining the process flow data to build a dynamic change model of heat generation and conduction rules in the cutting process, and generating a predicted fluctuation curve of tool temperature; Setting a high-temperature threshold for the cutting tool, screening the high-temperature interval or node according to the predicted fluctuation curve, formulating a cooling strategy, generating a cooling control instruction for the cutting tool according to the cooling strategy, and cooling the cutting tool according to the cooling control instruction; Real-time collection of actual temperature data of the cutting tool during the cutting process, dynamic comparison of the actual temperature data with the predicted fluctuation curve, and judgment of whether the temperature increase of the cutting tool is normal according to the comparison result, otherwise an abnormal report is generated and the management personnel is notified.

2. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The cutting process file includes the sequence of cutting steps, the cutting time of each step, the position information of the cutting area, and the working step switching condition; the equipment parameters include the cutting speed and feed rate of the cutting machine.

3. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The process of identifying the continuous working steps in the cutting process file through working step semantic analysis comprises: Text segmentation processing of the cutting process file, extracting sentences containing keywords, the keywords including working steps, start, end and switching; Determining the starting and ending positions of the working steps according to the time nodes and operation sequence of the sentences in the cutting process file, Classifying the working steps that are adjacent and have no interruption operation as continuous working steps to form a continuous working step sequence.

4. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 2, characterized in that, The process of generating structured process flow data comprises: For each continuous working step, matching the corresponding cutting speed and feed rate range from the equipment parameters; Combining the cutting time of the working step and the position information of the cutting area, generating the parameter combination of the working step as the cutting fingerprint; Arranging the cutting fingerprints of all working steps in order, supplementing the connection parameters between working steps according to the working step switching condition, and forming the structured process flow data containing the working step number, cutting fingerprint, time and position.

5. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The material properties include hardness and shape; the tool specification parameters include the size, shape and edge angle of the tool; the tool material quality characteristics include heat resistance and heat conduction ability.

6. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The process of building a dynamic change model of heat generation and conduction rules in the cutting process comprises: Based on the cutting speed, feed rate and cutting time in the process flow data, analyzing the contact area and friction frequency of the tool and the material under different working steps to obtain the heat generation rate; Determine the heat conduction coefficient in combination with the hardness of the processed material and the heat conduction ability of the tool material; Taking the size and shape in the tool specification parameters as the constraint conditions of the heat conduction path, build a dynamic change model reflecting the heat in the cutting process.

7. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The process of generating a predicted fluctuation curve of tool temperature comprises: Inputting each working step parameter in the process flow data into the dynamic change model; Simulate the rising and falling trend of the tool temperature in each working step, and adjust the temperature change slope according to the cutting interruption condition when the working step switches; The temperature change trends of all working steps are connected to generate a tool temperature prediction fluctuation curve covering the entire cutting process, and the prediction fluctuation curve contains the corresponding predicted temperature value of the cutting tool at each time point.

8. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The process of generating the cooling control instruction of the cutting tool includes: Collecting the safe temperature range in the historical cutting task, and setting a high temperature threshold combined with the material quality of the tool; Marking the interval or time node exceeding the high temperature threshold in the prediction fluctuation curve; Developing a prolonged cooling time strategy for the high temperature interval and an instantaneous enhanced cooling intensity strategy for the high temperature node; Generating cooling control parameters according to the prolonged cooling time strategy and the instantaneous enhanced cooling intensity strategy to obtain the cooling control instruction.

9. A method for on-line temperature monitoring of a cutting tool for a chipper according to claim 1, characterized in that, The process of dynamically comparing the actual temperature data with the prediction fluctuation curve includes: Extracting the corresponding temperature values in the actual temperature data and the prediction fluctuation curve according to the same time interval; Calculating the temperature difference value of each time point between the actual temperature data and the prediction fluctuation curve, and counting the difference value change trend of continuous multiple time points; If the temperature difference value is within the preset allowable range, and the difference value change trend does not exceed the preset fluctuation threshold, it is determined that the cutting tool temperature growth is normal.

10. An on-line temperature monitoring system for a cutting tool of a chipper comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the temperature online monitoring method for the cutting tool of the chip machine according to any one of claims 1-9 when executing the program.

Images