Method and system for synergistically regulating cutting heat and micro-lubrication of nanofluid for turning tool

Abstract

The application discloses a method and system for synergistically regulating micro-lubrication of nanofluid and cutting heat, and particularly relates to the technical field of industrial automatic control system of numerical control machine tool, which is used to solve the problem that the nanofluid micro-lubrication system is difficult to synergistically process local cooling of a tool and global thermal deformation control of a workpiece in the prior art; by acquiring a workpiece material type and a machining stage feature in real time, a grade of activation tendency of phase change heat absorption of nanofluid is determined; according to the grade of the activation tendency, a dominant strength of a cutting state from a thermodynamic imbalance critical point is determined; a constraint relationship between a supply strategy adjustment and a tool thermal shock risk is analyzed; a priority of global thermal management and local thermal regulation is determined; finally, nanofluid flow and pressure parameters are adaptively adjusted accordingly; dynamic balance and synergistic optimization of local and global thermal management targets in the cutting process are realized, and the machining precision and the tool service life are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of industrial automatic control system technology for CNC machine tools, and in particular to a method and system for the coordinated control of nanofluid micro-lubrication and cutting heat of lathe tools. Background Technology

[0002] In the field of high-end CNC turning, especially in the manufacturing of difficult-to-machine materials and high-precision parts, effective management of cutting heat is crucial to ensuring machining quality and extending tool life. Nanofluid micro-lubrication technology provides an efficient compromise between traditional casting-based cooling and dry cutting by adding nanoparticles with extremely high thermal conductivity and lubricity to a base oil and then atomizing and precisely spraying them onto the cutting area using a micro-lubrication system. Existing technologies primarily focus on the preparation of nanofluids, the optimization of their physicochemical properties, and hardware improvements to the micro-lubrication system itself, such as optimizing nozzle structure or improving atomization accuracy. At the control system level, existing industrial automatic control devices typically manage the nanofluid micro-lubrication system as an auxiliary functional unit of the machine tool. Their control strategies are mostly simple open-loop control based on preset rules or local closed-loop adjustment relying only on a single feedback parameter, focusing on immediate response to local thermal effects in the cutting area.

[0003] However, the management of cutting heat essentially involves two interrelated and often conflicting objectives: first, to suppress localized instantaneous high temperatures in the tool-workpiece contact area to prevent excessive tool wear; and second, to manage the overall temperature rise of the workpiece to avoid loss of machining accuracy due to thermal expansion and deformation. Existing automatic control strategies struggle to coordinate these two different objectives because they lack intelligent judgment of machining conditions and process requirements. They are unable to make dynamic priority decisions and optimize resource allocation among conflicting objectives, which may lead to control behavior that neglects one aspect while addressing another, thus limiting the potential of nanofluid micro-lubrication technology in pursuing high-precision and high-efficiency machining. Summary of the Invention

[0004] This invention addresses the technical problems existing in the prior art by providing a method and system for the synergistic regulation of nanofluid micro-lubrication and cutting heat in lathe tools.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: A method for synergistic regulation of micro-lubrication and cutting heat in lathe tools using nanofluids includes: S1. Real-time acquisition of material type characteristic signals and current processing stage characteristic signals of the current workpiece; S2. Based on the characteristic signals of the material type and the characteristic signals of the current processing stage, determine the degree of tendency for the phase change endothermic efficiency of the nanofluid to be activated under the expected cutting environment. S3. Determine the influence of the degree of distance between the current cutting state and the thermodynamic imbalance critical point on thermal management decisions based on the tendency level. S4. The relationship between adjusting the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool, based on the assessment of the dominance intensity; S5. Determine the priority relationship between global thermal management needs and local thermal control needs based on the constraints. S6. Adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to the priority relationship.

[0006] Furthermore, the material type characteristic signal and the characteristic signal of the current processing stage of the current workpiece are acquired in real time, including: The material type code of the currently processed workpiece is read from the workpiece material database built into the CNC system to obtain the material type characteristic signal; Synchronously parse the machining program code being executed by the CNC system, identify and output the characteristic signals of the current machining stage based on the process parameter characteristics in the machining program code.

[0007] Furthermore, based on the characteristic signals of the material type and the current processing stage, the degree of tendency for the phase change endothermic efficiency of the nanofluid to be activated under the expected cutting environment is determined, including: Based on the combination of material thermophysical property parameters corresponding to material type characteristic signals and cutting parameters corresponding to characteristic signals of the current processing stage, a pre-established database of nanofluid phase change characteristic mapping relationships is queried. Output a qualitative tendency level characterizing the ease with which nanofluids undergo phase change and endothermic reaction; The qualitative tendency level includes three discriminant conclusions: high activation tendency level, medium activation tendency level, and low activation tendency level.

[0008] Furthermore, the influence of the degree to which the current cutting state is close to the thermodynamic imbalance critical point on thermal management decisions is determined based on the tendency level, including: The tendency level of nanofluid phase change endothermic efficiency to be activated was coupled with the real-time monitored cutting temperature change gradient for analysis. By comparing the current cutting state parameters with the thermodynamic imbalance critical threshold parameters pre-stored in the process database, a mapping relationship is established between the time-varying characteristics of the thermal stability of the cutting system and the urgency of thermal management decisions. Based on the dynamic evolution trend of the real-time cutting state deviating from the thermodynamic imbalance critical point, the control intensity level corresponding to different intervention urgency is output. The dominance intensity level includes three judgment conclusions: high dominance intensity level, medium dominance intensity level, and low dominance intensity level.

[0009] Furthermore, the mapping relationship between the time-varying characteristics of the cutting system's thermal stability and the urgency of thermal management decisions is established in the following way: the spindle power signal is acquired in real time and its rate of change is calculated as a time-varying characteristic parameter of thermal stability. The time-varying characteristic parameter of thermal stability is compared in real time with the thermodynamic imbalance critical threshold parameter pre-stored in the process database. Based on the comparison result and the correspondence with the preset deviation level, the dominance intensity level is output.

[0010] Furthermore, the relationship between adjusting the nanofluid supply strategy and the potential thermal shock risk to the cutting tool, based on the assessment of the dominance intensity, includes: Based on the decision urgency corresponding to the dominance intensity level, a dynamic correlation mapping between the nanofluid supply level adjustment range and the tool thermal shock sensitivity coefficient is established. By monitoring the temperature field distribution characteristics of the tool rake face in real time and the degree of deviation from the critical parameters of material thermal fatigue, a reverse constraint mechanism is constructed between the optimization direction of supply strategy and the evolution trend of thermal shock risk, forming a quantitative correspondence between the supply strategy selection space and the risk control boundary under different emergency decision states.

[0011] Furthermore, the reverse constraint mechanism between the optimization direction of the supply strategy and the evolution trend of thermal shock risk is constructed in the following way: real-time monitoring of the temperature field distribution characteristics of the tool rake face, calculation of its deviation from the critical parameter of material thermal fatigue, reverse deduction of the optimization direction of the nanofluid supply strategy based on the positive and negative trends of the deviation, and establishment of a reverse correlation model between the adjustment amount of supply parameters and the change amount of thermal shock risk.

[0012] Furthermore, the priority relationship between global thermal management needs and local thermal control needs is determined based on the constraints, including: Based on the quantitative correspondence between supply strategy selection space and risk control boundary, a dynamic trade-off mechanism is established between the workpiece thermal deformation tolerance corresponding to global thermal management needs and the tool thermal wear critical value corresponding to local thermal control needs. By analyzing the degree of matching between the evolution trend of thermal shock risk and the processing accuracy requirements, priority determination rules based on the characteristics of different processing stages are formed. The output represents the priority relationship determination result, which indicates whether global thermal management needs take precedence, local thermal control needs take precedence, or both coexist in a balanced manner.

[0013] Furthermore, the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system are adjusted according to priority relationships, including: Based on the priority relationship of global thermal management needs, local thermal regulation needs, or a balance between the two, the corresponding nanofluid supply control mode is selected. When the priority relationship determination result is that the global thermal management needs take priority, a high flow rate and low pressure control parameter combination is used. When the priority relationship determination result is that the local thermal control demand takes priority, a combination of low flow rate and high pressure control parameters is used. When the priority relationship is determined to be balanced and coexisting, a combination of medium flow and medium pressure control parameters is used.

[0014] On the other hand, the present invention provides a nanofluid micro-lubrication and cutting heat synergistic control system for lathe tools, comprising: The signal acquisition module is used to acquire the material type characteristic signal and the characteristic signal of the current processing stage of the current workpiece in real time. The grade discrimination module is used to determine the degree of tendency of the phase change endothermic efficiency of nanofluids to be activated under the expected cutting environment, based on the characteristic signals of material type and the characteristic signals of the current processing stage. The intensity determination module is used to determine the degree of influence of the distance between the current cutting state and the thermodynamic imbalance critical point on thermal management decisions based on the tendency level. The constraint analysis module is used to assess the constraint relationship between adjusting the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool based on the dominance intensity. The relationship determination module is used to determine the priority relationship between global thermal management needs and local thermal control needs based on the constraint relationship; The parameter control module is used to adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to priority relationships.

[0015] The beneficial effects of this invention are: 1. By constructing a multi-level, adaptive intelligent decision-making chain, precise perception and coordinated control of thermal management requirements in the cutting process are achieved. First, workpiece material properties and processing stage information are obtained in real time from the processing source. Then, the activation tendency of the phase change potential of nanofluids is dynamically evaluated, and the stability of the system's thermodynamic state and the urgency of control are judged accordingly. On this basis, a constraint mapping relationship between supply strategy adjustment and thermal shock risk is established. Finally, the optimal nanofluid control parameters are output by prioritizing global and local thermal management requirements. This control mechanism based on multi-source information fusion and dynamic decision-making effectively overcomes the limitation of existing technologies that treat local and global thermal management objectives separately, and achieves coordinated optimization of conflicting thermal management objectives.

[0016] 2. It can intelligently balance and adaptively adjust between tool life protection and workpiece machining accuracy based on real-time working conditions. Through systematic state perception, risk assessment and priority decision-making, it ensures that the nanofluid micro-lubrication system always executes the control strategy that best matches the current machining requirements. This avoids the risk of tool thermal shock caused by excessive pursuit of local cooling effect, and also prevents workpiece thermal deformation caused by insufficient global thermal management. It significantly improves the thermal stability of high-end CNC turning and provides a reliable technical guarantee for achieving high-precision and high-efficiency cutting of difficult-to-machine materials. Attached Figure Description

[0017] Figure 1 This is a flowchart of the method for synergistic regulation of nanofluid micro-lubrication and cutting heat in lathe tools according to the present invention; Figure 2 This is a schematic diagram of the structure of the lathe tool nanofluid micro-lubrication and cutting heat synergistic control system of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1: Figure 1 The present invention provides a method for synergistic regulation of nanofluid micro-lubrication and cutting heat in lathe tools, comprising: S1. Real-time acquisition of material type characteristic signals and current processing stage characteristic signals of the current workpiece; S2. Based on the characteristic signals of the material type and the characteristic signals of the current processing stage, determine the degree of tendency for the phase change endothermic efficiency of the nanofluid to be activated under the expected cutting environment. S3. Determine the influence of the degree of distance between the current cutting state and the thermodynamic imbalance critical point on thermal management decisions based on the tendency level. S4. The relationship between adjusting the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool, based on the assessment of the dominance intensity; S5. Determine the priority relationship between global thermal management needs and local thermal control needs based on the constraints. S6. Adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to the priority relationship.

[0020] S1. Real-time acquisition of the material type characteristic signal and the characteristic signal of the current processing stage of the current workpiece, implemented as follows: The process of acquiring the material type characteristic signal of the current workpiece in real time is specifically implemented through the workpiece material database built into the CNC system. This workpiece material database is a structured data set pre-stored in the CNC system's memory, storing the correspondence between standard codes and material property parameters for various workpiece materials in the form of data tables. When the machining program starts executing, the control program accesses the material type code field corresponding to the current machining program in the workpiece material database by calling the application programming interface function provided by the CNC system, and reads the material classification identifier corresponding to this code as the material type characteristic signal. The material type code can adopt internationally recognized hard alloy application grouping codes, such as P01 representing high-strength steel precision machining and M20 representing general stainless steel machining, etc., standardized classification methods. By parsing these standardized codes, the material type characteristic signal of the currently machined workpiece can be accurately obtained.

[0021] The process of synchronously parsing the machining program segment code being executed by the CNC system is achieved through real-time monitoring of the program instruction stream executed by the CNC system interpreter. The control program continuously captures the machining program segment code currently being processed by the CNC system. This code segment contains complete G-code instructions and corresponding process parameters. When identifying the machining stage based on the process parameter characteristics in the machining program segment code, the cutting parameter instructions are first extracted from the program segment, including key process parameters such as spindle speed instruction S, feed rate instruction F, and depth of cut instruction. Then, by analyzing the numerical characteristics and combination patterns of these process parameters, the current machining stage is identified according to preset machining stage determination rules. For example, when a parameter combination with a depth of cut greater than 2 mm and a feed rate greater than 0.2 mm / rpm is detected, it is determined to be the roughing stage; when a parameter combination with a depth of cut less than 0.5 mm and a feed rate less than 0.1 mm / rpm is detected, it is determined to be the finishing stage. Finally, a feature signal of the current machining stage containing a machining stage type identifier is output.

[0022] The construction of the workpiece material database involves collecting standardized classification information of common engineering materials and establishing a mapping relationship between material codes and material physical property parameters. Material physical property parameters include at least key parameters affecting machinability, such as thermal conductivity, specific heat capacity, density, and elastic modulus. These parameter values ​​are derived from material standard manuals or obtained through experimental measurements and are stored in the database in a structured format. Each material code corresponds to a complete set of material property parameters, ensuring that complete material property information can be obtained when reading the material type code. The database adopts a relational data table structure, containing a material code primary key field, a material name field, a material category field, and multiple material property parameter fields. Fast query and retrieval are achieved through the establishment of index relationships.

[0023] The parsing of machining program code segments employs a regular expression-based instruction parsing algorithm, capable of accurately identifying various process parameter instructions within the G-code. The parser first performs syntactic analysis on the program code segments, separating different instruction fields, and then extracts the numerical parameters of each instruction field. Identification of process parameter characteristics is achieved by comparing the extracted numerical parameters with preset threshold ranges, which are pre-set according to the requirements of different machining processes. For example, the cutting depth threshold range for roughing is 1.0 mm to 5.0 mm, and for finishing, it is 0.1 mm to 0.8 mm. By comparing the actual parameters with these threshold ranges, the machining stage can be accurately identified. The feed rate threshold is dynamically adjusted based on the material type and tool characteristics. For instance, when machining aluminum alloys, the roughing feed rate threshold range is 0.15–0.3 mm / rpm, and the finishing feed rate threshold range is 0.05–0.12 mm / rpm.

[0024] The output of characteristic signals for the current machining stage adopts a standardized data format, including a machining stage type identifier and a corresponding set of process parameters. The machining stage type identifier uses an enumerated type definition, including basic types such as roughing, semi-finishing, and finishing, each type corresponding to a specific range of process parameter characteristics. The output signal also includes timestamp information to ensure synchronization with the timing characteristics of the machining process, providing an accurate time reference for subsequent processing. The data structure of the characteristic signal includes the following fields: machining stage code, actual spindle speed, actual feed rate, actual depth of cut, and timestamp. These field values ​​are obtained through real-time data acquisition and encapsulated according to a predetermined format.

[0025] During the acquisition of material type characteristic signals, the CNC system obtains the specific values ​​of the material's physical parameters by querying the workpiece material database. For example, when the material code is P01, the database returns a thermal conductivity of 46 W / (m·K), a specific heat capacity of 460 J / (kg·K), and a density of 7860 kg / m³. 3 These specific parameter values, as an important component of the material type characteristic signal, provide basic data support for subsequent processing. Database queries employ a parameterized query method, using the material code as the query condition to return the corresponding set of material property parameters, ensuring the accuracy and security of data queries.

[0026] During the identification of characteristic signals at each machining stage, the system monitors changes in the machining program segment in real time. When a program segment switch is detected, a new round of process parameter analysis is immediately initiated. This analysis employs multi-condition judgment logic, comprehensively considering the characteristics of multiple process parameters to determine the machining stage. For example, if the three conditions of depth of cut > 1.5 mm, feed rate > 0.18 mm / rev, and spindle speed < 2000 rpm are simultaneously met, it is determined to be the roughing stage; if the three conditions of depth of cut < 0.6 mm, feed rate < 0.15 mm / rev, and spindle speed > 2500 rpm are simultaneously met, it is determined to be the finishing stage. This multi-parameter comprehensive judgment method improves the accuracy and reliability of machining stage identification.

[0027] During real-time data acquisition, the system obtains the actual values ​​of current machining parameters through the data interface provided by the CNC system. These actual values ​​include the actual values ​​of spindle speed, feed rate, and depth of cut, which are acquired in real time by the sensors of the CNC system. The acquired data is filtered and used for machining stage identification. The filtering algorithm uses the moving average method, and the window size is set to 10 sampling points to ensure the stability and reliability of the data. The data acquisition frequency is set to 100Hz, which meets the requirements of real-time monitoring.

[0028] The output format of the characteristic signals adopts JSON data format, containing all necessary process parameter information. For example, the output data packet includes the following fields: timestamp (data acquisition timestamp), material_code (material type code), processing_stage (processing stage identifier), spindle_speed (actual spindle speed), feed_rate (actual feed rate), and cutting_depth (actual cutting depth), etc. This standardized data format facilitates subsequent processing, parsing, and use, ensuring the accuracy and consistency of data transmission. The output data is transmitted to subsequent processing via the CNC system's data bus, providing a reliable input data source for the entire control system.

[0029] S2. Based on the characteristic signals of the material type and the current processing stage, determine the degree of tendency for the phase change endothermic efficiency of the nanofluid to be activated under the expected cutting environment, and implement it as follows: The process of determining the activation tendency level of nanofluid phase change endothermic efficiency based on material type characteristic signals and current processing stage characteristic signals first involves querying a pre-established nanofluid phase change characteristic mapping database based on the combination of material thermophysical property parameters corresponding to the material type characteristic signals and cutting parameters corresponding to the current processing stage characteristic signals. The material thermophysical property parameters include values ​​such as thermal conductivity, specific heat capacity, and density obtained from the workpiece material database. These parameter values ​​are in units of W / (m·K), J / (kg·K), and kg / m³, respectively. 3 The cutting parameter combination includes process parameters such as spindle speed, feed rate, and depth of cut extracted from the characteristic signals of the machining stage, with units of revolutions per minute (RPM), millimeters per revolution (MM), and millimeters, respectively. The query process uses the current material thermophysical property parameters and cutting parameter values ​​as joint input conditions, and performs a matching search in the mapping relation database to find the record with the closest working condition.

[0030] The pre-established database of nanofluid phase transition characteristics was constructed as follows: Nanofluid jetting experiments were conducted on different workpiece materials using various combinations of cutting parameters. Critical point data of the phase transition endothermic phenomenon of the nanofluid were recorded, forming a dataset of mapping relationships with material thermophysical properties and cutting parameter combinations as inputs and phase transition tendency as output. The construction process involved a series of cutting experiments on different types of workpiece materials, covering various cutting parameter combinations. For example, on typical materials such as 45 steel, 304 stainless steel, and titanium alloys, nanofluid micro-lubrication cutting experiments were conducted using different spindle speed ranges (e.g., 500–3000 rpm), feed rate ranges (e.g., 0.05–0.3 mm / rpm), and depth of cut ranges (e.g., 0.1–3 mm). The phase transition behavior of the nanofluid was monitored in each experiment, and critical temperature, critical pressure, and other operating condition parameters at the time of phase transition were recorded, forming a large number of experimental data points. The experiments were conducted under standard test conditions, maintaining an ambient temperature of 20±2℃ and a relative humidity of 50±5%.

[0031] The determination of the phase transition characteristics of nanofluids is achieved through a combination of direct observation and indirect measurement. Direct observation uses a high-speed camera system to record the atomization state and phase transition process of the nanofluid in the cutting area, with a frame rate of no less than 1000 frames per second to ensure that the instantaneous phase transition can be captured. Indirect measurement uses thermocouples to measure the cutting temperature change curve, with a measurement accuracy of ±1℃ and a sampling frequency of 1000Hz. The timing of the phase transition is determined by analyzing the characteristic points of the temperature curve. When a clear plateau phase is detected in the temperature curve, it is determined that the nanofluid has undergone endothermic phase transition, and the cutting parameter combination and material parameters at this time are recorded as critical operating conditions. The criteria for determining the plateau phase are a temperature change rate of less than 0.5℃ / second and a duration of more than 0.1 seconds.

[0032] The mapping relational database uses a multidimensional data table structure to store these experimental data. Each row in the table represents a specific experimental condition, and the column fields include material thermophysical property parameters, cutting parameter combinations, and phase transformation tendency indicators. The material thermophysical property parameter field includes numerical data such as thermal conductivity, specific heat capacity, and density; the cutting parameter combination field includes process parameters such as spindle speed, feed rate, and depth of cut; the phase transformation tendency indicator field uses numerical representation, with values ​​between 0 and 1 indicating the ease of phase transformation, with larger values ​​indicating a higher likelihood of phase transformation. The database is managed using a relational database management system to ensure data integrity and consistency.

[0033] When querying the database, a nearest neighbor matching algorithm is used to calculate the Euclidean distance between the current operating parameters and each record stored in the database, selecting the record with the smallest distance as the matching result. During distance calculation, each parameter is normalized to eliminate the influence of dimensional differences. For example, thermal conductivity and spindle speed are normalized to the range of 0-1 to ensure that each parameter has a relatively equal weight in the distance calculation. The normalization formula is: Normalized value = (Actual value - Minimum value) / (Maximum value - Minimum value), where the minimum and maximum values ​​are taken from the historical extreme values ​​of each parameter in the database. A similarity threshold is set during the matching process. When the minimum distance is less than the threshold (e.g., 0.1), the phase transition tendency index of that record is directly used; when the minimum distance is greater than the threshold, interpolation is used to calculate the phase transition tendency index.

[0034] When outputting a qualitative tendency level characterizing the ease with which nanofluids undergo phase transition and endothermic reaction, the retrieved phase transition tendency numerical index is converted into a three-level qualitative description. The conversion process employs a two-level threshold division method, setting two thresholds to divide the numerical range into three intervals. For example, a phase transition tendency value less than 0.3 is classified as a low activation tendency level; a value between 0.3 and 0.7 is classified as a medium activation tendency level; and a value greater than 0.7 is classified as a high activation tendency level. These thresholds are determined through statistical analysis of a large amount of experimental data, ensuring the scientific validity and rationality of the level division. The threshold determination method uses cluster analysis; by performing cluster analysis on historical experimental data, natural dividing points are found as the thresholds for level division.

[0035] The qualitative assessment of the tendency level also considers the interaction between material properties and cutting parameters. For example, for materials with low thermal conductivity (e.g., below 20 W / (m·K)), nanofluids are more prone to phase transitions under the same cutting parameters, thus increasing the tendency value for phase transition. For roughing operations with large depths of cut (e.g., greater than 2 mm), the generated cutting heat is greater, making it easier to induce phase transitions in nanofluids. These influencing factors are fully considered during database queries through multi-parameter joint matching, ensuring the accuracy of the assessment results. The quantification of the interaction effect is achieved by establishing a multi-parameter regression model that considers the interaction terms between material thermophysical parameters and cutting parameters, thereby improving prediction accuracy.

[0036] The output of the propensity level uses a standardized data structure, including a level code and a confidence index. The level code is represented by numbers; for example, 1 represents a low activation propensity level, 2 represents a medium activation propensity level, and 3 represents a high activation propensity level. The confidence index indicates the reliability of the judgment result, calculated based on the matching distance; the smaller the matching distance, the higher the confidence. The confidence calculation formula is: Confidence = 1 - Matching Distance / Maximum Possible Distance, where the maximum possible distance is the maximum Euclidean distance in the normalized parameter space. The output data also includes timestamp information to ensure consistency with the time series of the processing process, providing a time series reference for subsequent processing. The data output frequency is consistent with the update frequency of the feature signals in the processing stage, typically outputting a judgment result every 0.1 seconds.

[0037] The database's update and maintenance mechanism includes regularly adding new experimental data to continuously enrich its coverage. When a new material type or a new combination of cutting parameters is encountered, a supplementary experimental procedure is initiated to obtain phase transformation characteristic data under that condition and add it to the database. The database also has a data verification mechanism that periodically verifies the accuracy of existing data to ensure the reliability of query results. Verification methods include cross-validation, randomly selecting a subset of data as a test set to verify the accuracy of database query results. The entire discrimination process achieves an accurate mapping from material and process parameters to the tendency level of nanofluid phase transformation characteristics, providing an important basis for subsequent thermal management decisions.

[0038] S3. Determine the influence of the degree of proximity of the current cutting state to the thermodynamic imbalance critical point on thermal management decisions based on the tendency level, and implement it as follows: The process of determining the degree to which the current cutting state is close to the thermodynamic imbalance critical point, and its influence on thermal management decisions, is based on the tendency level. First, a coupling correlation analysis is performed between the tendency level of activation of the nanofluid phase change endothermic efficiency and the real-time monitored cutting temperature gradient. The tendency level of activation of the nanofluid phase change endothermic efficiency includes three categories: high activation tendency, medium activation tendency, and low activation tendency, which are obtained from the preprocessing stage. The real-time monitored cutting temperature gradient is collected by thermocouple sensors mounted on the tool body. K-type thermocouples are used, with a measurement range of 0–1000℃, a sampling frequency of 1000Hz, and a temperature measurement accuracy of ±1℃. The coupling correlation analysis employs a weighted comprehensive evaluation method, converting the tendency level into numerical weights. For example, a high activation tendency level corresponds to a weight of 0.8, a medium activation tendency level to a weight of 0.5, and a low activation tendency level to a weight of 0.2. These weight values ​​are determined through statistical analysis of a large amount of experimental data. During the weighted calculation, the weight value is multiplied by the real-time cutting temperature change gradient value to obtain the comprehensive thermal risk assessment value. The unit of the temperature change gradient is ℃ / s, and the calculated comprehensive thermal risk assessment value is a dimensionless value.

[0039] By comparing the current cutting state parameters with the thermodynamic imbalance critical threshold parameters pre-stored in the process database, a mapping relationship is established between the time-varying characteristics of the cutting system's thermal stability and the urgency of thermal management decisions. The current cutting state parameters include a comprehensive set of multiple parameters such as spindle power, cutting temperature, and feed force. These parameters are acquired in real-time by sensors in the CNC system, with a sampling interval of 0.1 seconds. The thermodynamic imbalance critical threshold parameters are determined through prior process experiments, such as conducting cutting experiments under different materials and cutting parameters to monitor the critical conditions for thermodynamic imbalance and recording the corresponding process parameters as threshold parameters. The mapping relationship is established using a multi-parameter fitting method, comparing the current cutting state parameters with the critical threshold parameters item by item, calculating the relative deviation, and then obtaining the overall deviation index through a weighted average. The weighting coefficients are determined based on the influence of each parameter on the thermodynamic imbalance; for example, spindle power has a weight of 0.4, cutting temperature has a weight of 0.3, and feed force has a weight of 0.3.

[0040] The mapping relationship between the time-varying characteristics of the cutting system's thermal stability and the urgency of thermal management decisions is established by real-time acquisition of the spindle power signal and calculation of its rate of change as a time-varying characteristic parameter of thermal stability. The spindle power signal is acquired through the spindle drive module of the CNC system, with a power measurement range of 0–30 kW, a sampling interval of 0.1 seconds, and a power measurement accuracy of ±0.5 kW. The spindle power change rate is calculated using the first-order difference method, that is, the difference between the current power value and the power value at the previous sampling point is divided by the sampling time interval. The calculation formula is: Power change rate = (Current power - Power at the previous moment) / 0.1, with units of kW / s. The calculated time-varying characteristic parameter of thermal stability is compared in real time with the thermodynamic imbalance critical threshold parameters pre-stored in the process database. The thermodynamic imbalance critical threshold parameters include a set of multiple parameter thresholds such as the power change rate threshold and the temperature change rate threshold. These thresholds vary depending on the material type and processing stage.

[0041] The dominance level is output based on the comparison results and the preset correspondence between deviation levels. This correspondence is established through statistical analysis of extensive historical data. For example, a deviation of less than 10% from the critical threshold corresponds to a low dominance level, a deviation between 10% and 30% corresponds to a medium dominance level, and a deviation exceeding 30% corresponds to a high dominance level. A confidence level is also output along with the dominance level. The confidence level is determined comprehensively based on the parameter measurement accuracy and calculation error. For example, a confidence level of 0.9 is given when the measurement error is less than 1%, 0.7 when the measurement error is between 1% and 3%, and 0.5 when the measurement error is greater than 3%. The dominance level output uses a standardized data format, including fields such as level code, timestamp, and confidence level. The level code is represented by numbers; for example, 1 represents a low dominance level, 2 represents a medium dominance level, and 3 represents a high dominance level.

[0042] Based on the dynamic evolution trend of the real-time cutting state deviating from the thermodynamic imbalance critical point, the system outputs a dominance intensity level corresponding to different intervention urgency levels. Dynamic evolution trend analysis is achieved through time series analysis, fitting the trend of thermal stability parameters over a continuous period and using the least squares method to calculate the slope of change to determine the development direction of the system state. For example, selecting data from the most recent 10 sampling points, the linear regression slope is calculated; a positive slope with a large value indicates that the system state is deteriorating. The determination of intervention urgency comprehensively considers the current state value and the changing trend, using fuzzy inference to convert numerical parameters into urgency levels. The output includes the dominance intensity level and the expected evolution time. The expected evolution time represents the estimated time required to develop to the critical state according to the current trend, calculated by dividing the difference between the current state value and the critical value by the slope of change.

[0043] The critical threshold parameters for thermodynamic imbalance in the process database were determined through systematic experimental studies. Experiments were conducted under different materials and cutting parameters, monitoring the thermodynamic behavior of the cutting system and recording the critical parameter values ​​before system instability. For example, in 45 steel, when the cutting temperature reaches 800℃ and the temperature change rate exceeds 50℃ / s, the system enters a state of thermodynamic imbalance, and these parameter values ​​are recorded as critical threshold parameters. The database employs a hierarchical storage structure, storing corresponding threshold parameter sets according to different material types and processing stages to ensure accurate parameter matching. The database is regularly updated and maintained, with new experimental data added to improve the threshold parameter system; the update cycle is every 6 months.

[0044] The real-time monitoring of the cutting temperature gradient is calculated using the moving window difference method. Ten consecutive temperature sampling points are selected as a calculation window, and the slope of the linear fit of the temperature values ​​within the window is taken as the temperature gradient. The window size is determined based on the sampling frequency and response speed requirements, and the window duration is one second. The unit of the temperature gradient is °C / s, representing the rate of temperature change. A Kalman filter algorithm is used during the calculation to eliminate noise interference and ensure the accuracy of the gradient values. The filter parameters are adjusted according to sensor characteristics and environmental conditions; for example, the process noise covariance is set to 0.1, and the measurement noise covariance is set to 0.5.

[0045] The urgency of thermal management decisions is quantified through a multi-parameter comprehensive evaluation. Evaluation parameters include time-varying thermal stability characteristics, temperature change gradients, and tendency level weights, each assigned a different weight coefficient based on its importance. These weight coefficients are determined through a combination of expert scoring and historical data statistical analysis; for example, thermal stability parameters have a weight of 0.4, temperature change gradients have a weight of 0.3, and tendency level weights have a weight of 0.3. The comprehensive evaluation value is calculated as a weighted sum of all parameters, and different urgency levels are assigned based on the range of the evaluation value. An evaluation value less than 0.3 indicates low urgency, between 0.3 and 0.7 indicates medium urgency, and greater than 0.7 indicates high urgency. The evaluation process is conducted in real-time, with the evaluation frequency consistent with the data acquisition frequency to ensure timely reflection of changes in system status.

[0046] The output interface for the dominance intensity level adopts a standardized protocol. The output data contains complete status information, including current parameter values, historical trends, and prediction results. Data transmission uses a real-time data stream method and the TCP / IP protocol to ensure the timeliness and integrity of the information. The rationality and consistency of the output data are checked periodically; when abnormal data is detected, a recalculation or alarm mechanism is initiated to ensure system reliability. The self-check cycle is set to once every 10 minutes, and a recalculation process is immediately triggered when an anomaly is detected. The entire judgment process achieves accurate conversion from multi-source sensor data to the dominance intensity for thermal management decisions, providing a quantitative basis for subsequent thermal management strategy formulation.

[0047] S4. Based on the assessment of the dominance intensity, adjust the constraint relationship between the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool, and implement it as follows: The process of adjusting the nanofluid supply strategy based on the dominance intensity assessment and the constraint relationship between this strategy and the potential thermal shock risk to the cutting tool first establishes a dynamic correlation mapping between the nanofluid supply adjustment range and the cutting tool thermal shock sensitivity coefficient, based on the decision urgency corresponding to the dominance intensity level. The dominance intensity level includes three assessment conclusions: high-intensity dominance, medium-intensity dominance, and low-intensity dominance, which are obtained from the preliminary processing. The decision urgency is obtained through conversion from the dominance intensity level; for example, a high-intensity dominance level corresponds to a decision urgency value of 0.8, a medium-intensity dominance level corresponds to a decision urgency value of 0.5, and a low-intensity dominance level corresponds to a decision urgency value of 0.2. The nanofluid supply adjustment range is determined according to the decision urgency; for example, when the decision urgency value is 0.8, the supply adjustment range is 80% to 120% of the standard supply; when the decision urgency value is 0.5, the supply adjustment range is 90% to 110% of the standard supply. The thermal shock sensitivity coefficient of the cutting tool is calculated using the physical property parameters of the cutting tool material, including parameters such as the coefficient of thermal expansion, thermal conductivity, and specific heat capacity. The calculation formula is a weighted sum of the parameters, and the weighting coefficients are determined through material property tests. For example, the coefficient of thermal expansion has a weight of 0.4, the thermal conductivity has a weight of 0.3, and the specific heat capacity has a weight of 0.3.

[0048] By monitoring the deviation between the temperature field distribution characteristics of the tool rake face and the critical parameters of material thermal fatigue in real time, a reverse constraint mechanism is constructed between the optimization direction of the supply strategy and the evolution trend of thermal shock risk. The temperature field distribution characteristics of the tool rake face are obtained through infrared thermal imager monitoring, covering the main cutting area of ​​the tool rake face. The temperature measurement accuracy reaches ±2℃, the spatial resolution is 0.1 mm, and the sampling frequency is 100 Hz. The critical parameters of material thermal fatigue are obtained from a material performance database, including parameters such as the material's fatigue strength limit and thermal fatigue life, which are determined using standard material testing methods. The deviation is calculated using the relative difference method, i.e., the difference between the real-time temperature value and the critical temperature value is divided by the critical temperature value to obtain a dimensionless deviation index. A positive deviation indicates that the current temperature exceeds the critical value, while a negative deviation indicates that it is below the critical value. Moving average filtering is used during the calculation process, with a window size of 10 sampling points to eliminate random errors.

[0049] A reverse constraint mechanism is constructed between the optimization direction of the supply strategy and the evolution trend of thermal shock risk. This is achieved by real-time monitoring of the temperature field distribution characteristics of the tool rake face and calculating its deviation from the critical parameter of material thermal fatigue. The monitoring process employs non-contact infrared thermography, with an infrared thermal imager installed 200 mm from the tool rake face at a 30-degree viewing angle to ensure complete coverage of the cutting area. The temperature field data undergoes emissivity correction and ambient temperature compensation. The emissivity parameter is set to 0.8 based on the tool surface condition, and the ambient temperature is monitored in real-time by an additional temperature sensor. When calculating the deviation, the temperature values ​​of nine characteristic points on the tool rake face are selected, and the deviation at each point is calculated, then the arithmetic mean is taken as the overall deviation index. The positive and negative trends of the deviation are used to deduce the optimization direction of the nanofluid supply strategy. A positive deviation indicates that the supply should be reduced to decrease the risk of thermal shock, while a negative deviation indicates that the supply can be increased to improve the cooling effect.

[0050] A reverse correlation model was established between the adjustment of supply parameters and the change in thermal shock risk. This model was built based on regression analysis of a large amount of experimental data. Experiments were conducted under different cutting parameters to record the correspondence between changes in nanofluid supply and tool thermal shock risk. The model adopted a linear regression form; for example, a 10% increase in supply resulted in a 15% increase in thermal shock risk, while a 10% decrease resulted in a 12% decrease. The model parameters varied depending on the tool type and the material being machined. For example, the risk variation coefficient was 1.2 for carbide tools and 1.5 for high-speed steel tools. The model was updated regularly with new experimental data every three months to ensure its accuracy.

[0051] A quantitative correspondence is established between the supply strategy selection space and the risk control boundary under different decision-making emergency states. The decision-making emergency state is determined comprehensively based on the dominance intensity level and the degree of deviation, and a fuzzy inference method is used to convert numerical parameters into an emergency state level. For example, when the dominance intensity level is high and the deviation degree is greater than 0.3, the decision-making emergency state is at the highest level. The supply strategy selection space is determined through a multi-parameter optimization algorithm, considering different combinations of parameters such as nanofluid supply quantity, supply pressure, and supply time. The optimization objectives include multiple objective functions such as minimizing thermal shock risk, maximizing processing efficiency, and minimizing nanofluid consumption. The risk control boundary is determined based on the tolerance of the tool material and the processing quality requirements; for example, the maximum allowable temperature fluctuation range is set to ±10℃, and the minimum allowable supply quantity is set to 50% of the standard supply quantity.

[0052] The real-time monitoring of the temperature field distribution characteristics of the tool rake face utilizes a high-precision infrared thermal imager with a temperature measurement range of 0–1000℃ and a thermal sensitivity of 0.03℃. Monitoring data is transmitted to the processing system via Ethernet using the TCP / IP protocol at a data transmission rate of 100Mbps. Temperature field data processing includes steps such as defective pixel removal, noise filtering, and temperature compensation. Defective pixel removal employs a neighborhood comparison method; when the temperature value of a pixel differs from the average temperature of its eight surrounding pixels by more than 10℃, it is identified as a defective pixel and replaced with the neighborhood average value. Noise filtering uses a median filtering algorithm with a filtering window size of 3×3 pixels. Temperature compensation is based on the ambient temperature and measurement distance, using the following formula: Actual temperature = Measured temperature + 0.01 × (Ambient temperature - 20) + 0.001 × (Measurement distance - 200).

[0053] The critical parameters for thermal fatigue of the material were obtained using standard material testing methods. An electro-hydraulic servo fatigue testing machine was used, with a loading frequency of 10 Hz, a stress ratio R = 0.1, and a test temperature range of 20–800 °C. At least 10 sets of tests were performed at each temperature point, and the average value was taken as the fatigue strength limit at that temperature. Thermal fatigue life parameters were determined through thermal shock testing, where the specimens were alternately placed in high and low temperature environments, and the number of cycles leading to crack initiation was recorded. All test data was stored in a material property database managed by SQL Server, supporting rapid querying and updating.

[0054] The deviation was calculated using a standardized method, including data normalization, weighted averaging, and trend analysis. Data normalization converted temperature values ​​to the range of 0-1, using the formula: Normalized value = (Actual value - Minimum value) / (Maximum value - Minimum value). Weighted averaging assigned weights based on the importance of the measurement point location: points near the cutting edge received a weight of 0.2, points in the tool tip area received a weight of 0.3, and points in other areas received a weight of 0.1. Trend analysis used linear regression to calculate the slope of the deviation change over the most recent 10 sampling points; a positive slope indicated increasing risk, while a negative slope indicated decreasing risk.

[0055] The inverse correlation model is established based on parameter estimation using the least squares method. Historical data, including supply adjustment records and corresponding thermal shock risk changes, are collected, and model parameters are solved using linear regression. Model validation employs k-fold cross-validation, dividing the data into 10 subsets. Nine subsets are used for training in rotation, and one subset is used for testing, repeated 10 times, with the average error taken. Incremental learning is used for model updates; when the deviation between the new data and the old model's predictions exceeds 15%, the model parameter update procedure is initiated. During the update process, some historical data is retained to ensure model stability.

[0056] The supply strategy selection space is determined using a multi-objective genetic algorithm for optimization. Algorithm parameters are set as follows: population size 100, number of iterations 500, crossover probability 0.8, and mutation probability 0.1. The optimization results output a Pareto optimal solution set, where each solution contains a set of supply parameter combinations and the corresponding objective function value. Decision-makers can select a suitable solution from the solution set based on actual needs. The risk control boundary is set based on the technical specifications provided by the tool manufacturer and actual machining experience, and is periodically adjusted according to tool wear, with adjustments generally not exceeding 20% ​​of the initial value. The entire constraint relationship assessment process achieves a complete transformation from theoretical analysis to practical application, ensuring the reliability and practicality of the system.

[0057] S5. Determine the priority relationship between global thermal management needs and local thermal control needs based on the constraints, and implement it as follows: The process of determining the priority relationship between global thermal management needs and local thermal control needs based on constraints first establishes a dynamic trade-off mechanism between the workpiece thermal deformation tolerance corresponding to global thermal management needs and the tool thermal wear critical value corresponding to local thermal control needs, based on the quantitative correspondence between the supply strategy selection space and the risk control boundary. The supply strategy selection space includes multiple feasible combinations of nanofluid supply parameters determined by a multi-objective optimization algorithm. Each parameter combination is labeled with the expected thermal shock risk level and processing effect indicators. These parameter combinations include different combinations of parameters such as nanofluid supply quantity, supply pressure, and injection angle. The risk control boundary is determined based on the tool material's tolerance and processing quality requirements. For example, the maximum allowable temperature fluctuation range is set to ±10℃, and the minimum allowable supply quantity is set to 50% of the standard supply quantity. These boundary values ​​are verified and determined through material testing and processing testing. The workpiece's thermal deformation tolerance is calculated using the physical properties of the workpiece material, including its coefficient of thermal expansion, modulus of elasticity, and yield strength. These parameters are obtained from a material property database. The calculation formula is a weighted sum of the parameters, with weighting coefficients determined through material property tests. For example, the coefficient of thermal expansion has a weight of 0.4, the modulus of elasticity has a weight of 0.3, and the yield strength has a weight of 0.3, with a total weighting coefficient of 1. The critical value for tool thermal wear is determined through tool life tests. Wear tests are conducted under different temperature conditions, and the critical temperature at which the tool reaches the predetermined wear standard is recorded. The test temperature range covers 200℃ to 800℃, with a test point set every 50℃. The dynamic trade-off mechanism employs a multi-objective decision-making method, simultaneously considering both the workpiece's thermal deformation tolerance and the critical value for tool thermal wear. Different weighting coefficients are set to reflect the relative importance of the two. These weighting coefficients are dynamically adjusted according to the machining stage and requirements. For example, in the roughing stage, the tool life weight is set to 0.6, and the workpiece deformation weight is set to 0.4; in the finishing stage, the workpiece deformation weight is set to 0.7, and the tool life weight is set to 0.3.

[0058] By analyzing the degree of matching between the evolution trend of thermal shock risk and machining accuracy requirements, priority judgment rules based on the characteristics of different machining stages are formed. The evolution trend of thermal shock risk is obtained through time series analysis. The trend of thermal shock risk indicators over a continuous period is fitted, and the slope of change is calculated using the least squares method to determine the direction of risk development. The analysis time window length is 10 sampling points, and the sampling interval is 1 second. Machining accuracy requirements are obtained from the process specifications, including accuracy indicators such as dimensional tolerances, shape tolerances, and positional tolerances. These indicators are determined according to workpiece drawings and technical requirements, such as diameter tolerance ±0.01mm, roundness tolerance 0.005mm, and parallelism tolerance 0.01mm. The matching degree analysis uses the deviation comparison method to calculate the relative deviation between the predicted value of thermal shock risk and the maximum allowable risk value of machining accuracy. The matching level is determined according to the magnitude of the deviation; for example, a deviation of less than 10% is high matching, 10% to 20% is medium matching, and greater than 20% is low matching. Priority determination rules are formulated based on the characteristics of each machining stage. For example, in the roughing stage, tool life and machining efficiency are prioritized, while local thermal management requirements have a higher weight. In the finishing stage, workpiece quality and machining accuracy are prioritized, while global thermal management requirements have a higher weight. The determination rules adopt an if-then form of production rules. For example, if the machining stage is finishing and the matching degree is less than 0.7, the result is that global thermal management requirements take priority; if the machining stage is roughing and the matching degree is greater than 0.8, the result is that local thermal management requirements take priority.

[0059] The output determines the priority relationship between global thermal management needs, local thermal control needs, or a balanced coexistence of both. The determination is made through a comprehensive scoring mechanism. First, the scores for global thermal management needs and local thermal control needs are calculated separately, and then the two scores are compared. The global thermal management need score is calculated based on the deviation between the workpiece's thermal deformation tolerance and its current thermal state; the greater the deviation, the higher the score. The formula is: Global Score = 100 × (Current Thermal Deformation / Thermal Deformation Tolerance). The local thermal control need score is calculated based on the proximity of the tool's thermal wear threshold value to the current tool temperature; the closer to the threshold value, the higher the score. The formula is: Local Score = 100 × (Current Tool Temperature / Thermal Wear Threshold Value). The scoring calculation uses a standardized processing method, converting the original parameters to a range of 0-100 points for easier comparison and decision-making. When the difference between the two scores exceeds 20 points, the higher score is prioritized; when the difference is between 10 and 20 points, a balanced coexistence of both is determined; when the difference is less than 10 points, a comprehensive judgment considering other factors is required. The judgment results are output in a standardized data format, including priority code, score details, confidence level and other information. The priority code is represented by numbers, where 1 represents priority for global thermal management needs, 2 represents priority for local thermal control needs, and 3 represents a balance between the two.

[0060] The tolerance for thermal deformation of a workpiece is determined through material thermal deformation testing. The test utilizes a thermo-coupled testing machine to apply mechanical loads to workpiece material samples under different temperature conditions, measuring the amount of thermal deformation. The test temperature range covers the temperature range that may occur during processing, for example, from room temperature to 600℃, with a test point set every 50℃. At least five repeated tests are performed at each temperature point, and the average value is taken as the amount of thermal deformation at that temperature. The tolerance threshold is determined based on the workpiece's precision requirements; for example, for precision machining, the thermal deformation tolerance is set to 0.01 mm; for ordinary machining, the tolerance can be relaxed to 0.05 mm. All test data is stored in a material property database using a relational database management system, supporting rapid querying and updates, with an update cycle of every six months.

[0061] The critical value for tool thermal wear is obtained through tool life testing. Tests are conducted under different cutting parameters and cooling conditions, with periodic measurement of the tool's flank wear and recording the cumulative machining time until the tool reaches a predetermined wear standard. The wear standard is determined based on the tool type and machining requirements; for example, the standard flank wear for carbide tools is 0.3 mm, and for high-speed steel tools, it is 0.5 mm. Tool temperature is monitored during the test, and a correlation between temperature and tool wear rate is established. By fitting the wear rate curve, the critical temperature point where tool wear increases sharply is found; this temperature point is the critical value for tool thermal wear. The test data includes critical values ​​under the influence of multiple factors such as tool material, coating type, and cutting parameters, forming a complete tool thermal wear database. The database contains at least 1000 sets of test data, covering common tool materials and machining conditions.

[0062] The analysis of the evolution trend of thermal shock risk employs a time series forecasting method. Historical thermal shock risk data is collected, and trend prediction is performed using exponential smoothing. The forecasting model parameters are estimated using the least squares method, and the smoothing coefficient is dynamically adjusted based on data fluctuations; for example, a smaller smoothing coefficient (0.1–0.3) is used when data fluctuations are large, and a larger smoothing coefficient (0.7–0.9) is used when fluctuations are small. The forecast results include point forecast values ​​and forecast intervals, where the forecast interval represents the possible range of future risk values, with a confidence level set at 95%. The trend analysis period is determined based on the characteristics of the processing procedure; for example, for continuous processing, the analysis period is set to 5 minutes; for intermittent processing, the analysis period is synchronized with the processing cycle. The analysis results are stored in a process database for priority determination.

[0063] The quantification of machining accuracy requirements is achieved through tolerance analysis. Based on the dimensional tolerances, form tolerances, and positional tolerances indicated on the workpiece drawings, the overall accuracy requirement index is calculated. Dimensional tolerances are directly adopted from the drawing values, while form and positional tolerances are combined into a comprehensive accuracy index using the tolerance superposition principle. When converting the accuracy requirement index into thermal management requirements, the influence coefficient of thermal deformation on accuracy needs to be considered, such as the deformation caused by each 1°C increase in temperature. This influence coefficient is determined through thermal deformation tests; different materials have different influence coefficients, for example, the thermal deformation coefficient of steel is approximately 12 × 10⁻⁶ / °C, and that of aluminum alloys is approximately 24 × 10⁻⁶ / °C. These coefficients are stored in a material property database, and the corresponding parameter values ​​are retrieved based on the workpiece material type. The database is periodically validated to ensure data accuracy.

[0064] Priority determination rules are formulated using a combination of expert systems and machine learning. First, the experiential knowledge of processing experts is collected to form an initial rule base containing at least 50 rules. Then, historical processing data is analyzed using machine learning algorithms to optimize rule parameters and weight settings, with a training dataset of at least 1000 sets. The rule base uses a production rule representation, with each rule consisting of a condition and a conclusion. The condition consists of multiple logical conditions, and the conclusion outputs the priority determination result. Rule matching employs a forward reasoning mechanism, checking each rule condition one by one until a matching rule is found. The rule base is updated regularly, adjusting the rules based on new processing data and expert feedback, with an update cycle of every three months to ensure the accuracy and adaptability of the determination results.

[0065] The output of the judgment results adopts a standardized data protocol, containing complete decision-making basis information. The data format adopts a JSON structure, including a priority_level field to indicate the priority level (1 for global priority, 2 for local priority, 3 for balanced coexistence), a global_score field to indicate the global demand score, a local_score field to indicate the local demand score, a confidence field to indicate the confidence level, and a timestamp field to indicate the timestamp. The output frequency is dynamically adjusted according to the processing process. When the processing state is stable, the output frequency is lower (e.g., once per minute), and when the processing state changes drastically, the output frequency is higher (e.g., once every 10 seconds). The output data is transmitted to subsequent processing via a real-time data bus. Data transmission uses the TCP / IP protocol at a transmission rate of 100Mbps to ensure the real-time performance and reliability of the data. The entire priority relationship determination process realizes a complete transformation from multi-source information to decision output, ensuring the intelligence and adaptive capability of the thermal management system.

[0066] S6. Adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to the priority relationship, as follows: The process of adjusting the fluid flow and air pressure control parameters of the nanofluid micro-lubrication system based on priority relationships first selects the corresponding nanofluid supply control mode based on the priority relationship determination results: priority of global thermal management needs, priority of local thermal regulation needs, or a balance between the two. The priority relationship determination results are obtained from the previous processing and include information such as priority code, score details, and confidence level. The priority code is represented by numbers: 1 represents priority of global thermal management needs, 2 represents priority of local thermal regulation needs, and 3 represents a balance between the two. When selecting a control mode, the system queries a pre-stored control mode mapping table. This mapping table, established through extensive process experiments, records the optimal control mode parameters corresponding to different priority codes. For example, when the priority code is 1, a high flow rate and low air pressure control mode is selected; when the priority code is 2, a low flow rate and high air pressure control mode is selected; and when the priority code is 3, a medium flow rate and medium air pressure control mode is selected. The control mode mapping table varies depending on the tool type, workpiece material, and processing conditions, and is periodically updated and optimized based on process experiment data, with an update cycle of once every three months.

[0067] When the priority relationship determination result indicates that global thermal management needs take precedence, a high-flow-rate, low-pressure control parameter combination is adopted. The specific values ​​of the high-flow-rate, low-pressure control parameter combination are determined through process experiments. These experiments test the control effect of different flow rate and pressure combinations on workpiece thermal deformation under different cutting parameters. For example, for machining 45 steel, the high flow rate range is 100–150 ml / h, and the low pressure range is 0.3–0.5 MPa; for machining 304 stainless steel, the high flow rate range is 120–180 ml / h, and the low pressure range is 0.4–0.6 MPa. The parameter adjustment process adopts a gradual adjustment method, with a flow rate adjustment step of 5 ml / h and a pressure adjustment step of 0.05 MPa. After each adjustment, a 10-second wait is allowed to observe the effect, ensuring system stability. Workpiece temperature changes are monitored in real time during the adjustment process. When the temperature change rate exceeds 5℃ / second, the adjustment is paused and resumed after the system stabilizes. The monitoring data sampling frequency is 10Hz, and the temperature measurement accuracy is ±1℃.

[0068] When the priority determination result prioritizes local thermal control needs, a low-flow-rate, high-pressure control parameter combination is adopted. The determination of this combination is based on the principle of tool thermal protection, finding a parameter range that effectively cools without causing overcooling damage through tool life testing. For example, for cemented carbide tools, the low-flow-rate range is 30–50 ml / h, and the high-pressure range is 0.8–1.2 MPa; for ceramic tools, the low-flow-rate range is 20–40 ml / h, and the high-pressure range is 0.6–1.0 MPa. Parameter adjustment employs a rapid response mode. When the tool temperature approaches the critical value, it immediately switches to high-pressure mode, with the pressure rising from the reference value to the target value within 2 seconds, and the flow rate adjusting to the target value within 5 seconds. Tool stress changes are monitored during adjustment; when the stress change rate exceeds 10 MPa / s, adjustment is automatically paused to prevent tool damage. Stress monitoring uses strain gauge sensors with a sampling frequency of 1000 Hz.

[0069] When the priority relationship determination result indicates that both factors coexist in a balanced manner, a medium flow rate and medium pressure control parameter combination is adopted. This combination is determined through a multi-objective optimization algorithm to balance the needs of workpiece thermal deformation control and tool thermal protection. For example, for most steel machining, the medium flow rate range is 60–90 ml / h, and the medium pressure range is 0.5–0.7 MPa; for cast iron machining, the medium flow rate range is 50–80 ml / h, and the medium pressure range is 0.4–0.6 MPa. Parameter adjustment employs a smooth transition method, with flow rate and pressure adjusted synchronously at adjustment rates of 3 ml / h / s and 0.03 MPa / s, ensuring a smooth machining process. During adjustment, both workpiece and tool temperatures are monitored simultaneously. When the temperature difference exceeds 50°C, parameters are automatically fine-tuned to achieve a more balanced temperature distribution. Temperature monitoring uses a dual-channel infrared thermometer with a measurement accuracy of ±2°C.

[0070] The nanofluid supply control mode is implemented through a PLC controller in a numerical control system. After receiving the priority determination result, the controller outputs corresponding control signals according to the preset control logic. Flow control is achieved by adjusting the speed of the metering pump; the speed is linearly related to the control signal. For example, a 4–20 mA control signal corresponds to a flow range of 0–200 mL / h, with a linearity error of less than 1%. Pressure control is achieved by adjusting the opening of the pressure regulating valve; the opening is proportional to the control signal. For example, a 0–10 V control signal corresponds to a pressure range of 0–1.5 MPa, with a repeatability of 0.5%. The control signal is filtered before output using a first-order low-pass filter with a cutoff frequency of 10 Hz to eliminate jitter and interference, ensuring smooth actuator operation.

[0071] Parameter optimization is achieved through a real-time feedback mechanism. The system continuously monitors machining status parameters, including workpiece temperature, tool temperature, and cutting force, and fine-tunes control parameters based on the monitoring results. For example, when the workpiece temperature is detected to be rising too rapidly, the flow rate is appropriately increased; when the tool temperature is detected to be too high, the pressure is appropriately increased. The adjustment amount is determined based on the magnitude of the deviation, and a PID control algorithm is used to calculate the adjustment amount. The proportional gain, integral time, and derivative time are obtained through experimental tuning; for example, the proportional gain is 0.8, the integral time is 2 seconds, and the derivative time is 0.5 seconds. During the adjustment process, safety boundaries are set to ensure that the parameters do not exceed the allowable range; for example, the flow rate does not exceed 120% of the maximum allowable flow rate, and the pressure does not exceed 110% of the maximum allowable pressure. The safety boundary values ​​are stored in the system parameter table and can be adjusted according to actual conditions.

[0072] The storage and management of control parameters are achieved through a parameter database. The database stores optimal parameter combinations under different machining conditions, including index fields such as workpiece material, tool type, cutting parameters, and priority codes. The database uses a relational structure and contains multiple data tables, including parameter tables, material tables, and tool tables, linked by foreign keys. When the machining program starts, the system queries the database based on the current machining conditions to obtain baseline parameter values, and then fine-tunes them based on real-time monitoring data. Queries use parameterized SQL statements to prevent SQL injection attacks. The database is updated regularly, adding new optimized parameter combinations and deleting ineffective ones; the update cycle is every three months. The database employs a redundant storage design, with data backed up in real-time to two independent storage devices to ensure data security and reliability.

[0073] The system also features a parameter self-learning function, which automatically optimizes control parameters based on historical data. The self-learning algorithm employs reinforcement learning, using multiple objectives such as machining quality, tool life, and production efficiency as reward functions, and continuously searches for the optimal parameter combination through trial and error. The learning process takes place in a simulation environment to avoid impacting actual machining. The simulation environment uses a finite element analysis model with a simulation accuracy exceeding 95%. The learning results are updated to the parameter database after verification. The verification method involves testing the effect of the new parameter combination in actual machining and comparing it with the old parameter combination, ensuring a performance improvement of at least 5% before updating the database. The self-learning cycle is determined based on the machining volume; for example, the learning process is initiated every 100 workpieces machined to ensure continuous parameter optimization.

[0074] The entire parameter adjustment process achieves complete closed-loop control from priority determination to specific parameter execution, ensuring that the nanofluid micro-lubrication system can provide optimal thermal management based on actual machining requirements. The system features high reliability, adaptability, and scalability, capable of adapting to different machining conditions and requirements, providing effective thermal control assurance for precision machining. All control and algorithm parameters are stored in non-volatile memory, ensuring they are not lost after power failure and automatically restoring the previous operating state upon system restart. The system also provides a manual adjustment interface, allowing operators to fine-tune parameters according to special circumstances, ensuring the system's flexibility and practicality.

[0075] Example 2: Figure 2 A schematic diagram of the lathe tool nanofluid micro-lubrication and cutting heat synergistic regulation system of the present invention is given. The lathe tool nanofluid micro-lubrication and cutting heat synergistic regulation system includes: The signal acquisition module is used to acquire the material type characteristic signal and the characteristic signal of the current processing stage of the current workpiece in real time. The grade discrimination module is used to determine the degree of tendency of the phase change endothermic efficiency of nanofluids to be activated under the expected cutting environment, based on the characteristic signals of material type and the characteristic signals of the current processing stage. The intensity determination module is used to determine the degree of influence of the distance between the current cutting state and the thermodynamic imbalance critical point on thermal management decisions based on the tendency level. The constraint analysis module is used to assess the constraint relationship between adjusting the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool based on the dominance intensity. The relationship determination module is used to determine the priority relationship between global thermal management needs and local thermal control needs based on the constraint relationship; The parameter control module is used to adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to priority relationships.

[0076] All calculations involved in the embodiments are dimensionless numerical calculations, and the preset parameters and thresholds in the calculations are set by those skilled in the art according to the actual situation.

[0077] It should be noted that this invention can be deployed on the device itself to realize embedded applications, or it can run on a PC or other terminal with a user interface, thereby meeting various hardware environments and usage requirements.

[0078] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wireless or wired transmission; wired transmission methods include optical fiber, twisted pair, coaxial cable, etc.; wireless transmission includes infrared, microwave, etc. Computer-readable storage media can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0079] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0081] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0082] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0083] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0084] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0085] In conclusion, the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for synergistic regulation of micro-lubrication and cutting heat of lathe tools using nanofluids, characterized in that, include: S1. Real-time acquisition of material type characteristic signals and current processing stage characteristic signals of the current workpiece; S2. Based on the characteristic signals of the material type and the current processing stage, determine the degree of tendency for the phase change endothermic efficiency of the nanofluid to be activated under the expected cutting environment; including: Based on the combination of material thermophysical property parameters corresponding to material type characteristic signals and cutting parameters corresponding to characteristic signals of the current processing stage, a pre-established database of nanofluid phase change characteristic mapping relationships is queried. Output a qualitative tendency level characterizing the ease with which nanofluids undergo phase change and endothermic reaction; The qualitative tendency level includes three discriminant conclusions: high activation tendency level, medium activation tendency level, and low activation tendency level. S3. Determine the influence of the degree of distance between the current cutting state and the thermodynamic imbalance critical point on thermal management decisions based on the tendency level. S4. The relationship between adjusting the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool, based on the assessment of the dominance intensity; S5. Determine the priority relationship between global thermal management needs and local thermal control needs based on the constraints. S6. Adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to the priority relationship.

2. The method for synergistic control of nanofluid micro-lubrication and cutting heat in lathe tools according to claim 1, characterized in that, Real-time acquisition of material type characteristic signals and current processing stage characteristic signals of the current workpiece, including: The material type code of the currently processed workpiece is read from the workpiece material database built into the CNC system to obtain the material type characteristic signal; Synchronously parse the machining program code being executed by the CNC system, identify and output the characteristic signals of the current machining stage based on the process parameter characteristics in the machining program code.

3. A lathe tool nanofluid micro-lubrication and cutting heat synergistic control system, used to implement the lathe tool nanofluid micro-lubrication and cutting heat synergistic control method according to any one of claims 1-2, characterized in that, include: The signal acquisition module is used to acquire the material type characteristic signal and the characteristic signal of the current processing stage of the current workpiece in real time. The grade discrimination module is used to determine the degree of tendency of the phase change endothermic efficiency of nanofluids to be activated under the expected cutting environment, based on the characteristic signals of material type and the characteristic signals of the current processing stage. The intensity determination module is used to determine the degree of influence of the distance between the current cutting state and the thermodynamic imbalance critical point on thermal management decisions based on the tendency level. The constraint analysis module is used to assess the constraint relationship between adjusting the nanofluid supply strategy and the potential risk of thermal shock to the cutting tool based on the dominance intensity. The relationship determination module is used to determine the priority relationship between global thermal management needs and local thermal control needs based on the constraint relationship; The parameter control module is used to adjust the fluid flow control parameters and air pressure control parameters of the nanofluid micro-lubrication system according to priority relationships.

Images