An intelligent monitoring system and method for a numerically controlled machine tool

Abstract

The application discloses an intelligent monitoring system and method for a numerical control machine tool, and relates to the field of machine tool control.The system comprises a material attribute similarity acquisition module, a machining code similarity acquisition module, a historical abnormal information acquisition module, a warning prompt information generation module and an auxiliary function control module.The material attribute similarity acquisition module is used to acquire material attribute similarity information of a target machining part and historical machining parts.The machining code similarity acquisition module is used to acquire code similarity information of the target machining part and the historical machining parts.The historical abnormal information acquisition module is used to acquire abnormal pause information of the historical machining parts.The warning prompt information generation module is used to generate warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information.The auxiliary function control module is used to control the working state of the auxiliary function module according to the warning prompt information.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of machine tool control, and more particularly, an intelligent monitoring system and method for a numerical control machine tool. BACKGROUND

[0002] With the wide application of numerical control machine tools in manufacturing industry, the machining efficiency and product quality directly affect the production cost and market competitiveness of enterprises. However, due to the involvement of various complex factors (such as material properties, machining process, machine tool state and human operation, etc.) in the machining process, various abnormal situations may occur in the actual operation of numerical control machine tools. Once the tool breaks, the spindle is overloaded or the feed is abnormal, etc. Faults often lead to machine tool downtime, processing quality decline and even equipment damage, causing economic losses and production delays for enterprises.

[0003] At present, the intelligent monitoring and early warning of the machining process of numerical control machine tools, most methods only focus on the monitoring of a single dimension such as machining program or tool wear, or use artificial experience for post-troubleshooting, lacking the fusion and real-time prediction of multi-source data.

[0004] Therefore, it is necessary to propose an intelligent monitoring system and method for a numerical control machine tool to at least solve some of the above problems. SUMMARY

[0005] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiment section. The summary section of the present application does not mean to attempt to limit the key features and necessary technical features of the claimed technical solution, nor to attempt to determine the protection scope of the claimed technical solution.

[0006] In a first aspect, the present application proposes an intelligent monitoring system for a numerical control machine tool, comprising:

[0007] A material attribute similarity acquisition module is configured to acquire material attribute similarity information of a target machining part and a historical machining part.

[0008] A machining code similarity acquisition module is configured to acquire code similarity information of the target machining part and the historical machining part.

[0009] A historical abnormal information acquisition module is configured to acquire abnormal pause information of the historical machining part.

[0010] An early warning prompt information generation module is configured to generate early warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information.

[0011] An auxiliary function control module is configured to control the working state of the auxiliary function module according to the early warning prompt information.

[0012] The second aspect of the application provides an intelligent monitoring method for a numerical control machine tool, which is used for the intelligent monitoring system for a numerical control machine tool of the first aspect, comprising:

[0013] Obtain the material attribute similarity information of the target machining part and the historical machining part;

[0014] Obtain the code similarity information of the target machining part and the historical machining part;

[0015] Obtain the abnormal pause information of the historical machining part;

[0016] Generate a warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information;

[0017] Control the working state of the auxiliary function module according to the warning prompt information.

[0018] In a feasible implementation, the material attribute similarity information of the target machining part and the historical machining part is obtained, comprising:

[0019] Determine the material static similarity information according to the hardness information, the density information and the thermal conductivity of the target machining part and the historical machining part;

[0020] Determine the material dynamic similarity information according to the cutting speed, the feed amount, the tool wear amount and the surface roughness of the target machining part and the historical machining part;

[0021] Determine the material attribute similarity information according to the static similarity information and the dynamic similarity information.

[0022] In a feasible implementation, the code similarity information of the target machining part and the historical machining part is obtained, comprising:

[0023] Extract the key instructions in the G code to identify the process type;

[0024] Determine the machining stage according to the M code and the tool information;

[0025] Determine the static weight coefficient according to the process type;

[0026] Determine the stage sensitive factor according to the machining stage;

[0027] Determine the dynamic weight coefficient according to the static weight coefficient and the stage sensitive factor;

[0028] Extract the key machining features according to different process types;

[0029] According to the above target processing part and the above dynamic weight coefficient of the above historical processing part and the above key processing feature, the code similarity information is calculated.

[0030] In an embodiment, the abnormal pause information includes equipment abnormal pause information and manual emergency pause information.

[0031] The pre-warning prompt information is generated according to the material attribute similarity information, the code similarity information and the abnormal pause information, including:

[0032] The abnormal pause information is classified to obtain equipment abnormal pause information set and manual emergency pause information set.

[0033] The equipment abnormal pre-warning information is generated in the equipment abnormal pause information set according to the material attribute similarity information and the code similarity information.

[0034] The manual pause prompt information is generated in the manual emergency pause information set according to the material attribute similarity information and the code similarity information.

[0035] In an embodiment, the equipment abnormal pre-warning information is generated in the equipment abnormal pause information set according to the material attribute similarity information and the code similarity information, including:

[0036] The first processing condition similarity information is calculated in the equipment abnormal pause information set according to the material attribute similarity information and the code similarity information.

[0037] In the case that the first processing condition similarity information greater than the first preset threshold exists in the equipment abnormal pause information set, the first abnormal statistical information of all the equipment possible abnormal information is obtained.

[0038] The equipment abnormal pre-warning information is generated according to the first abnormal statistical information.

[0039] In an embodiment, the abnormal statistical information includes abnormal occurrence frequency, abnormal severity and abnormal category statistical information.

[0040] The equipment abnormal pre-warning information is generated according to the abnormal statistical information, including:

[0041] The abnormal risk score is calculated according to the abnormal occurrence frequency, the abnormal severity and the abnormal category statistical information.

[0042] The equipment abnormal pre-warning information is generated according to the abnormal risk score.

[0043] In an embodiment, the method for controlling the working state of the auxiliary function module according to the early warning prompt information comprises:

[0044] obtaining device abnormality risk level information of the device abnormality early warning information;

[0045] adjusting the sampling frequency of the data monitoring module in the case of low risk of the abnormality risk level information; and / or,

[0046] determining a high-probability abnormality category based on the abnormality category statistical information in the case of medium risk of the abnormality risk level information;

[0047] adjusting the processing parameters based on the high-probability abnormality category and the abnormality risk level information; and / or,

[0048] starting the machine tool emergency stop program in the case of high risk of the abnormality risk level information.

[0049] In an embodiment, the manual emergency pause information in the manual emergency pause information set comprises:

[0050] calculating second processing condition similarity information according to the material attribute similarity information and the code similarity information in the manual emergency pause information set;

[0051] obtaining second abnormality statistical information of all the manual pause prompt information in the case of existence of manual pause prompt information with second processing condition similarity information greater than a second preset threshold in the device abnormality pause information set;

[0052] generating the manual pause prompt information according to the second abnormality statistical information.

[0053] In an embodiment, the method for controlling the working state of the auxiliary function module according to the early warning prompt information comprises:

[0054] controlling the cooling liquid flow information and the light prompt information according to the manual pause prompt information.

[0055] In summary, the present application considers the similarity of material properties and the similarity of processing codes, and combines historical abnormal pause information to comprehensively compare the target machining part and the historical machining part in different dimensions. Compared with the traditional monitoring method which only depends on a single factor such as process code or tool wear, the present application can more accurately capture potential abnormalities in complex machining environments, identify high-risk parts and failure modes, and thus significantly improve the accuracy of abnormal early warning. Through the mining and analysis of high-similarity historical abnormal cases, the system can predict and output "early warning information" on the possible abnormalities of the target part at the beginning or during the machining. Compared with the traditional manual experience or post-mortem mode, the method of the present application can discover potential failure signs earlier, reduce economic losses caused by unexpected machine tool downtime and tool scrapping, and improve the machine tool opening rate and production efficiency. After the method of the present application generates "early warning information", it will link to the auxiliary function module to control and adjust the cooling flow, feed speed, alarm signal and the like according to the early warning information. Compared with the traditional manual operation mode, the present application can automatically adjust the process parameters and prompt the operator to check the key links during the operation of the machine tool, greatly reducing the dependence on manual experience and enhancing the safety and automation level of the machine tool. Therefore, the present application constructs a more perfect early warning and auxiliary function linkage mechanism through multi-dimensional comprehensive analysis of the similarity of material properties, the similarity of processing codes and historical abnormal information, which can improve the accuracy and timeliness of prediction. BRIEF DESCRIPTION OF DRAWINGS

[0056] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not intended to limit the scope of the present application. Moreover, like reference numerals designate like parts throughout the several views in the drawings. In the drawings:

[0057] Figure 1 A structural schematic diagram of an intelligent monitoring system for a numerical control machine tool provided by an embodiment of the present application;

[0058] Figure 2 A flowchart of an intelligent monitoring method for a numerical control machine tool of an intelligent monitoring system for a numerical control machine tool provided by an embodiment of the present application. DETAILED DESCRIPTION

[0059] The terms "first", "second", "third", "fourth" and the like in the description and in the claims of the present application and above-mentioned drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a specific sequential or chronological order. It is to be understood that the use of the terms so construed herein is merely for convenience and only to aid in understanding the application and in no way define the scope of the application. It is also to be understood that the description and the examples, while indicating certain embodiments of the application, are given by way of example and are not intended to limit the scope of the application unless otherwise specifically indicated. Thereafter, the application is described and exemplified through the use of the accompanying drawings.

[0060] Referring now to the drawings Figure 1 The intelligent monitoring system 10 for a numerical control machine tool provided by the embodiments of the present application is shown in a structural schematic diagram, and can specifically include:

[0061] The material attribute similarity acquisition module 101 is configured to acquire material attribute similarity information of the target machining part and the historical machining part.

[0062] The machining code similarity acquisition module 102 is configured to acquire code similarity information of the target machining part and the historical machining part.

[0063] The historical abnormal information acquisition module 103 is configured to acquire abnormal pause information of the historical machining part.

[0064] The early warning prompt information generation module 104 is configured to generate early warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information.

[0065] The auxiliary function control module 105 is configured to control the working state of the auxiliary function module according to the early warning prompt information.

[0066] For example, the material attribute similarity acquisition module 101 acquires the material characteristic parameters (such as hardness, density, thermal conductivity, etc.) of the target machining part and the historical machining part respectively, and performs comparison operation, so as to obtain the "material attribute similarity information" reflecting the similarity degree of the two in the material aspect. When performing abnormal prediction or process optimization, the material characteristics often directly affect the key factors such as tool wear and cutting parameter selection.

[0067] The processing code similarity acquisition module 102 extracts the corresponding process feature information (such as process type, processing stage, feed speed, tool path, etc.) by analyzing the numerical control programs (such as G code, M code, tool call, etc.) of the target machining part and the historical machining part respectively, and then calculates the similarity of these information to obtain the "code similarity information". This can help the system evaluate the similarity of the target part and the historical part in terms of processing strategy and processing sequence.

[0068] The historical abnormal information acquisition module 103 collects and organizes "abnormal pause information" from historical machining data, including automatic alarm triggered shutdown (such as spindle overload, tool breakage alarm, etc.) and manual emergency stop. Through these abnormal records, we can understand the faults or abnormal conditions that have occurred under similar working conditions.

[0069] The early warning information generation module 104 integrates "material attribute similarity information", "code similarity information" and "abnormal pause information", evaluates the possible abnormalities or risks of the target machining part under the current working condition, and then outputs the corresponding "early warning information". If the system judges that the target part and a certain historical part are highly similar in material and process, and the historical part has frequently appeared downtime, a high-risk prompt will be issued to remind preventive measures.

[0070] The auxiliary function control module 105 controls the auxiliary functions of the numerical control machine tool (such as cooling and lubrication system, feed adjustment, alarm device, etc.) according to the early warning information. The system may actively increase the flow of coolant, reduce the feed speed, or turn on the prompt light and display information, in order to reduce tool or machine tool failure, and ensure the safety and stability of processing.

[0071] In summary, the application considers the similarity of material properties and the similarity of machining codes, and combines historical abnormal pause information to comprehensively compare the target machining part and the historical machining part in different dimensions. Compared with the traditional monitoring method which only depends on a single factor such as process code or tool wear, the application can more accurately capture potential abnormalities in complex machining environments, identify high-risk parts and failure modes, and significantly improve the accuracy of abnormal early warning. Through the mining and analysis of high-similarity historical abnormal cases, the system can predict and output "early warning information" for the possible abnormalities of the target part at the beginning or during the machining. Compared with the traditional manual experience or post-mortem mode, the method of the application can discover potential failure signs earlier, reduce economic losses caused by unexpected machine tool downtime and tool scrap, and improve the machine tool opening rate and production efficiency. After the method of the application generates "early warning information", it will link to the auxiliary function module and make corresponding control and adjustment to the cooling flow, feed speed, alarm signal, etc. Compared with the traditional manual operation mode, the method can automatically adjust the process parameters and prompt the operator to check the key links during the operation of the machine tool, greatly reducing the dependence on manual experience and enhancing the safety and automation level of the machine tool. Therefore, the application improves the accuracy and timeliness of prediction by multi-dimensional comprehensive analysis of the similarity of material properties, the similarity of machining codes, and historical abnormal information, and constructs a more perfect early warning and auxiliary function linkage mechanism.

[0072] In a second aspect, the application provides an intelligent monitoring method for a numerical control machine tool, which is used in the intelligent monitoring system 10 for a numerical control machine tool of the first aspect, and includes the following steps:

[0073] S110, obtaining material property similarity information of the target machining part and the historical machining part;

[0074] For example, the system mainly collects the material physical characteristics (such as hardness, density, thermal conductivity, etc.) of the target part and the historical part respectively, and compares these material properties to obtain the material property similarity information. This similarity is used to judge the matching degree of the target part and the historical part in terms of material characteristics, and provides a basis for subsequent fault risk judgment.

[0075] S120, obtaining code similarity information of the target machining part and the historical machining part;

[0076] For example, by analyzing the numerical control program (G code, M code, etc.), the similarity of the target part and the historical part in terms of machining process, process path, machining stage, etc. is compared, and the code similarity information is calculated. This information reflects the closeness of their machining strategies and can provide a reference for fault prediction or process optimization.

[0077] S130, obtaining abnormal pause information of the historical machining part;

[0078] For example, the system retrieves "abnormal pause" related records from the historical database, including equipment abnormality (machine tool automatically alarms and stops) and manual emergency pause (operator manually stops). Through sorting and classifying, these data are used to locate possible faults or problems under similar working conditions.

[0079] S140, generating early warning prompt information according to the above material attribute similarity information, the above code similarity information and the above abnormal pause information;

[0080] For example, the system comprehensively considers the material similarity, code similarity and abnormal pause records in historical processing, evaluates the possible risks of the target processing part, and outputs corresponding "early warning prompt information". For example, if the target part is highly similar to a historical part in terms of material and process, and the historical part has appeared abnormality such as tool fracture and spindle overload for many times, the system will prompt a higher potential risk.

[0081] S150, controlling the working state of the auxiliary function module according to the above early warning prompt information.

[0082] For example, if the system determines that there is an abnormal risk, the auxiliary function module (such as the cooling system, the tool management module, the light warning, etc.) of the numerical control machine tool will be controlled to take corresponding measures to prevent or reduce possible faults. For example, actively increasing the flow of cooling liquid, reducing the feed amount, prompting the operator to check the tool condition, etc., so as to reduce the possibility of shutdown and damage.

[0083] In summary, the present application considers the similarity of material properties and the similarity of machining codes, and combines historical abnormal pause information to comprehensively compare the target machining part and the historical machining part in different dimensions. Compared with the traditional monitoring method which only depends on a single factor such as process code or tool wear, the present application can more accurately capture potential abnormalities in complex machining environments, identify high-risk parts and failure modes, and thus significantly improve the accuracy of abnormal early warning. Through the mining and analysis of high-similarity historical abnormal cases, the system can predict and output "early warning information" for the possible abnormalities of the target part at the beginning or during the machining. Compared with the traditional manual experience or post-mortem mode, the method of the present application can discover potential failure signs earlier, reduce economic losses caused by unexpected machine downtime and tool scrap, and improve the machine opening rate and production efficiency of the numerical control machine tool. After the method of the present application generates "early warning information", it will link to the auxiliary function module to control and adjust the cooling flow, feed speed, alarm signal and the like according to the early warning information. Compared with the traditional manual operation mode, the present application can automatically adjust the process parameters and prompt the operator to check the key links during the operation of the machine tool, which greatly reduces the dependence on manual experience and enhances the safety and automation level of the machine tool. Therefore, the present application constructs a more perfect early warning and auxiliary function linkage mechanism through multi-dimensional comprehensive analysis of the similarity of material properties, the similarity of machining codes and historical abnormal information, which can improve the accuracy and timeliness of prediction.

[0084] In a feasible implementation, the above-mentioned obtaining of the material property similarity information of the target machining part and the historical machining part includes:

[0085] According to the hardness information, density information and thermal conductivity of the target machining part and the historical machining part, the material static similarity information is determined;

[0086] According to the cutting speed, feed amount, tool wear and surface roughness of the target machining part and the historical machining part, the material dynamic similarity information is determined;

[0087] According to the static similarity information and the dynamic similarity information, the material property similarity information is determined.

[0088] For example, the material static similarity measures the closeness of the target part and the historical part in physical properties, mainly including hardness (H), density (D) and thermal conductivity (K).

[0089] The normalized Euclidean distance or weighted cosine similarity is used to calculate the similarity of a single material property:

[0090]

[0091] H target ,Dtarget ,K target Hardness, density and thermal conductivity of target part, H history ,D history ,K history Corresponding attribute values of historical parts, H max ,D max ,K max Maximum value in the material category, respectively.

[0092] Calculate the comprehensive static similarity S static :

[0093] S static = a H × S H + a D × S D + a K × S K

[0094] Wherein: a H , a D , a K are weight coefficients, a H + a D + a K = 1

[0095] The weights can be optimized according to process experience or data training, for example: if the material hardness has greater influence on processing, set a H = 0.5, a D = 0.3, a K = 0.2.

[0096] The material dynamic similarity measures the similarity between the target part and the historical part in the processing process, mainly considering the cutting speed (V), the feed amount (F), the tool wear (W) and the surface roughness (R a )

[0097] The weighted cosine similarity or Euclidean distance is used to calculate the dynamic similarity:

[0098]

[0099] Wherein: V target , F target , W target , R a,target are the cutting speed, feed amount, tool wear and surface roughness of the target part, V history , F history , W history , R a,history are the corresponding cutting speed, feed amount, tool wear and surface roughness of the historical part, V max , F maxW max ,R a,max is a normalization coefficient.

[0100] The comprehensive dynamic similarity S dynamic is calculated.

[0101] S dynamic = β V × S V + β F × S F + β W × S W + β R × S R

[0102] wherein β V , β F , β W , β R are weight coefficients, β V + β F + β W + β R = 1, for example, if the tool wear has a greater impact on the abnormality, β W = 0.4, β V = 0.3, β F = 0.2, β R = 0.1

[0103] The final material property similarity S mat is calculated by the static similarity and the dynamic similarity:

[0104] S mat = γ static × S static + γ dynamic× S dynamic

[0105] wherein γ static and γ dynamic are fusion weights, γ static + γ dynamic = 1. If the material physical properties are more important than the machining parameters, γ static = 0.6, γ dynamic = 0.4, and if the machining parameters have a greater impact on the performance, γ static = 0.4, γ dynamic = 0.6.

[0106] In summary, the embodiment simultaneously considers the characteristics of the material itself and the key parameters in the processing process to ensure that the similarity calculation is closer to the actual processing situation. The influence weight of physical properties and processing parameters can be adjusted according to the process requirements to improve the adaptability. In combination with historical abnormal data, equipment failures or processing problems that may occur in the target part are predicted to improve production stability.

[0107] In a feasible implementation, the code similarity information of the target machining part and the historical machining part is obtained, including:

[0108] Extracting key instructions in the G code to identify the process type;

[0109] Determining the processing stage according to the M code and the tool information;

[0110] Determining a static weight coefficient according to the process type;

[0111] Determining a stage sensitive factor according to the processing stage;

[0112] Determining a dynamic weight coefficient according to the static weight coefficient and the stage sensitive factor;

[0113] Extracting key machining features according to different process types;

[0114] Calculating the code similarity information according to the dynamic weight coefficient and the key machining features of the target machining part and the historical machining part.

[0115] For example, a numerical control machining program contains multiple G codes, which determine the specific operation of machining, such as: G01: linear interpolation (commonly used for milling and turning); G02 / G03: circular interpolation (suitable for curve machining); G81-G89: drilling, tapping and other cycle machining; G71 / G72: rough turning, fine turning cycle.

[0116] Scan the G code line by line, extract the key instructions, and identify the process type, such as: G01 represents linear milling, G02 / GO3 represents circular machining, G81 represents drilling, and G84 represents tapping.

[0117] The processing process is represented as a process vector:

[0118] V op =[x1,x2,…,x n ]

[0119] Where x i represents the i-th process (such as linear milling, drilling, etc.).

[0120] M code is used to control the state of the machine tool (such as spindle start-stop, coolant control), which can help determine the processing stage, for example: M03 (spindle forward), M08 (cooling liquid open) → rough machining; M05 (spindle stop), M09 (cooling liquid closed) → non-processing stage; M06 (tool change) → tool change information; T01, T02. (Tool number) → Identify the tool used.

[0121] For example: rough machining has a large feed amount, high cutting depth, and code features: M03 + G71 / G72 (rough turning), G01 (fast feed). Fine machining has small feed amount, high precision, and code features: G01 low feed speed, M08 open cooling.

[0122] Construct the processing stage vector, set the processing stage vector V stage :

[0123] V stage = [s1, s2, …, s n ]

[0124] Where s i represents each stage (such as rough machining, fine machining).

[0125] Different processing procedures have different effects on overall similarity, so set the static weight coefficient W static : drilling W drill = 0.4, milling W mill = 0.3, turning W turn = 0.2, tapping W tap = 0.1.

[0126] Integrate the static weight coefficient W static :

[0127]

[0128] Where: is the proportion of the process in the machining program, is the static weight of the process

[0129] Define the stage sensitivity factor S stage :

[0130]

[0131] Where: is the proportion of the stage, is the sensitivity of the stage (rough machining = 1.5, fine machining = 1.2)

[0132] Determine the dynamic weight coefficient W dynamic according to the above static weight coefficient and the above stage sensitivity factor:

[0133] W dynamic =W static ×S stage

[0134] Key machining features include: path complexity (coordinate point density, tool path change rate), cutting parameters (feed rate, spindle speed, etc.) and machining time (the proportion of total time occupied by different processes)

[0135] Construct feature vector:

[0136] V feature =[f1,f2,…,f n ]

[0137] Where: f1 is the path complexity, f2 is the cutting parameter, f3 is the machining time.

[0138] Calculate the code similarity S between the target part and the historical part based on the cosine similarity code :

[0139]

[0140] Where, V feature,i is the key feature vector of the target part, is the corresponding feature vector of the historical part, W dynamic,i is the calculated dynamic weight.

[0141] In summary, the method proposed in this embodiment combines G code, M code and tool information, which can accurately determine the machining stage and improve the accuracy of similarity calculation. Through the process type and machining stage sensitive factor, the influence of different machining steps is adjusted, and the matching degree of complex machining program is improved. Combined with tool path, feed speed, spindle speed and other process parameters, the code similarity calculation is more in line with the actual machining situation. It can improve the intelligence of machine tool monitoring, find possible machining abnormalities in advance, and improve the safety and production efficiency of machine tools.

[0142] In a feasible implementation manner, the abnormal pause information includes equipment abnormal pause information and manual emergency pause information,

[0143] The above generates warning prompt information according to the above material attribute similarity information, the above code similarity information and the above abnormal pause information, including:

[0144] Classify the above abnormal pause information to obtain an equipment abnormal pause information set and a manual emergency pause information set;

[0145] Generate equipment abnormal warning information in the above equipment abnormal pause information set according to the above material attribute similarity information and the above code similarity information;

[0146] The manual emergency pause information is generated according to the material attribute similarity information and the code similarity information in the device abnormal pause information set.

[0147] For example, the historical machining database stores multiple abnormal pause records, and the records include:

[0148] 1. Device abnormal pause (R eqp ): System automatically detected abnormalities, such as spindle overload, tool breakage, etc.

[0149] 2. Manual emergency pause (R man ): Manually triggered emergency stop, such as operator finding tool abnormality or vibration abnormality, etc.

[0150] In order to determine whether the target part is likely to have a historical abnormality, the machining condition similarity S cond (first machining condition similarity information and second machining condition similarity information are determined by this formula) needs to be calculated first:

[0151] S cond = αS mat + (1-α)S code

[0152] Where: S mat is the material attribute similarity, which measures the closeness of the target part and the historical part in terms of material hardness, density, thermal conductivity, etc. S code is the code similarity, which measures the similarity of the target part and the historical part in terms of machining process, process, cutting parameter, etc.

[0153] In one possible implementation, the device abnormal warning information is generated according to the material attribute similarity information and the code similarity information in the device abnormal pause information set, including:

[0154] The first machining condition similarity information is calculated according to the material attribute similarity information and the code similarity information in the device abnormal pause information set.

[0155] In the case where the first machining condition similarity information in the device abnormal pause information set is greater than the first preset threshold, the first abnormal statistical information of all the device possible abnormal information is obtained.

[0156] The device abnormal warning information is generated according to the first abnormal statistical information.

[0157] For example, when the machining condition similarity S cond is greater than the first preset threshold τ1, it means that the machining condition of the target part is highly similar to the historical machining record, and it is necessary to check whether there is an abnormal pause record in the historical data.

[0158] If S cond >τ1, then enter the first abnormal statistics, τ1 is the first preset threshold of the machining condition similarity (such as 0.7).

[0159] For the screened historical abnormal machining cases, the abnormal data is counted, including:

[0160] 1. Abnormal frequency R eqp :

[0161]

[0162] Wherein, M is the number of cases of device abnormality in similar working condition historical data, and N is the total number of machining times of similar working condition.

[0163] 2. Abnormal severity R sev :

[0164]

[0165] For example, tool wear (weight = 1), tool fracture (weight = 3), spindle overload (weight = 5).

[0166] 3. Abnormal category statistics

[0167]

[0168] Comprehensive abnormal statistics, calculate the device abnormal risk score R risk :

[0169] In one possible implementation, the above abnormal statistics include abnormal frequency, abnormal severity and abnormal category statistics,

[0170] The above device abnormal warning information is generated according to the above abnormal statistics, including:

[0171] According to the above abnormal frequency, abnormal severity and the above abnormal category statistics, the abnormal risk score is calculated;

[0172] According to the above abnormal risk score, the device abnormal warning information is generated.

[0173] For example, the abnormal risk score R risk :

[0174]

[0175] Wherein: λ1, λ2, λ3 are adjustable weight parameters (such as λ1 = 0.5, λ2 = 0.3, λ3 = 0.2). Tool fracture W 刀具 = 3.0, spindle overload W主轴 = 5.0, servo alarm W 伺服 = 4.0.

[0176] In an embodiment, the working state of the auxiliary function module is controlled according to the early warning prompt information, including:

[0177] obtaining device abnormality risk level information of the device abnormality early warning information;

[0178] in the case of low risk of the abnormality risk level information, adjusting the sampling frequency of the data monitoring module; and / or,

[0179] in the case of medium risk of the abnormality risk level, determining a high-probability abnormality category based on the abnormality category statistical information;

[0180] adjusting the processing parameters based on the high-probability abnormality category and the abnormality risk level information; and / or,

[0181] in the case of high risk of the abnormality risk level, starting the machine tool emergency stop program.

[0182] For example, a threshold τ of different risk levels is set, in the case of low risk of the abnormality risk level information (R risk <1.0), mild early warning, adjusting the sampling frequency of the data monitoring module, and closely monitoring the working state of the machine tool. In the case of medium risk of the abnormality risk level (1.0≤R risk <2.0), determining a high-probability abnormality category based on the abnormality category statistical information. In the case of high risk of the abnormality risk level (R risk ≥2.0), starting the machine tool emergency stop program.

[0183] Specifically, 1. When the high-probability abnormality category is tool fracture early warning and the spindle load is too high, the feed rate F is reduced:

[0184] F ′ = F x (1-ΔF)

[0185] where ΔF is the adjustment amplitude, usually 5% to 15%.

[0186] The spindle speed N is reduced:

[0187] N ′ = N x (1-ΔN)

[0188] If the early warning prompt is spindle overload, the spindle speed can be reduced to reduce the load.

[0189] 2. In the case of high-probability abnormality category of optimizing the cooling / lubrication system, the cooling liquid flow is increased:

[0190] Q c ′ oolant =Q coolant ×(1+ΔQ)

[0191] Where ΔQ is the adjustment amplitude.

[0192] The nozzle direction can also be adjusted to improve cooling efficiency. If the system has controllable nozzles, the cooling liquid flow direction can be dynamically optimized. The cutting oil concentration is increased

[0193] In an embodiment, the manual emergency pause information set includes manual pause prompt information according to the material attribute similarity information and the code similarity information.

[0194] The second machining condition similarity information is calculated according to the material attribute similarity information and the code similarity information in the manual emergency pause information set.

[0195] In the case where the second machining condition similarity information of the manual pause prompt information in the device abnormal pause information set is greater than the second preset threshold, the second abnormal statistical information of all the manual pause prompt information is obtained.

[0196] The manual pause prompt information is generated according to the second abnormal statistical information.

[0197] For example, when the machining condition similarity S cond is greater than the second preset threshold τ2, it means that the machining condition of the target part is highly similar to the historical machining record, and it is necessary to check whether the manual pause prompt information exists in the historical data.

[0198] If S cond >τ2, the second abnormal statistical information is entered, and τ2 is the second preset threshold of the machining condition similarity (e.g., 0.9).

[0199] The second abnormal statistical information includes the number R man of manual pause prompt information, the time distribution information of the manual pause prompt information, and the parameter modification information after manual pause.

[0200] The time distribution information of the manual pause prompt information is counted, such as: the machining start stage (e.g., 0% to 10% of the machining time): it may be caused by initial setting error. The machining middle stage (e.g., 30% to 70% of the machining time): it may be caused by excessive feed amount or rapid tool wear. The machining late stage (e.g., more than 80%): it may be caused by cutting quality decline or tool failure.

[0201] The parameter modification information after manual pause ΔP=Pafter-Pbefore, wherein Pafter and P before are the adjusted machining parameters before and after the pause, respectively.

[0202] In one possible implementation, the above-mentioned controlling the working state of the auxiliary function module according to the above-mentioned early warning prompt information comprises:

[0203] controlling the coolant flow information and the light prompt information according to the above-mentioned manual pause prompt information.

[0204] For example, the system adopts the hierarchical control strategy shown in Table 1 in combination with the number R of manual pause prompt information, pause time distribution information and parameter adjustment ΔP: man

[0205]

[0206] Table 1

[0207] This embodiment reduces abnormal downtime and improves the stability of the numerical control machine tool through data-driven coolant adjustment and light prompts. The coolant adjustment strategy is optimized to reduce the machining temperature and improve the tool life and machining precision. The yellow / red light warning is adopted to improve the abnormal response speed of the operator and reduce the risk of misadjustment. The machining parameters are automatically adjusted to improve the automation level of the numerical control machine tool and are suitable for large-scale production scenarios.

[0208] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.​

Claims

1. An intelligent monitoring method for a numerical control machine tool, an intelligent monitoring system for a numerical control machine tool, characterized by, The intelligent monitoring system of the numerical control machine tool comprises: A material attribute similarity acquisition module is configured to acquire material attribute similarity information of a target machining part and a historical machining part; A machining code similarity acquisition module is configured to acquire code similarity information of the target machining part and the historical machining part; A historical abnormal information acquisition module is configured to acquire abnormal pause information of the historical machining part; An early warning prompt information generation module is configured to generate early warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information; An auxiliary function control module is configured to control a working state of the auxiliary function module according to the early warning prompt information; The method comprises: acquiring material attribute similarity information of a target machining part and a historical machining part; acquiring code similarity information of the target machining part and the historical machining part; acquiring abnormal pause information of the historical machining part; generating early warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information; controlling a working state of an auxiliary function module according to the early warning prompt information; The acquiring of the material attribute similarity information of the target machining part and the historical machining part comprises: determining material static similarity information according to hardness information, density information and thermal conductivity of the target machining part and the historical machining part; determining material dynamic similarity information according to cutting speed, feed rate, tool wear and surface roughness of the target machining part and the historical machining part; determining the material attribute similarity information according to the static similarity information and the dynamic similarity information; The acquiring of the code similarity information of the target machining part and the historical machining part comprises: extracting key instructions in G code to identify process types; judging machining stages according to M code and tool information; determining static weight coefficients according to the process types; determining stage sensitive factors according to the machining stages; determining dynamic weight coefficients according to the static weight coefficients and the stage sensitive factors; extracting key machining features according to different process types; calculating the code similarity information according to the dynamic weight coefficients and the key machining features of the target machining part and the historical machining part.

2. The intelligent monitoring method for a CNC machine tool according to claim 1, characterized in that, The abnormal pause information comprises device abnormal pause information and manual emergency pause information, The generating of the early warning prompt information according to the material attribute similarity information, the code similarity information and the abnormal pause information comprises: classifying the abnormal pause information to acquire a device abnormal pause information set and a manual emergency pause information set; generating device abnormal early warning information according to the material attribute similarity information and the code similarity information in the device abnormal pause information set; generating manual pause prompt information according to the material attribute similarity information and the code similarity information in the manual emergency pause information set.

3. The intelligent monitoring method for a CNC machine tool according to claim 2, characterized in that, The generating of the device abnormal early warning information according to the material attribute similarity information and the code similarity information in the device abnormal pause information set comprises: In the device abnormal suspension information set, first processing condition similarity information is calculated according to the material attribute similarity information and the code similarity information; In the case where there is device possible abnormal information with first processing condition similarity information greater than a first preset threshold in the device abnormal suspension information set, first abnormal statistical information of all the device possible abnormal information is obtained; Device abnormal early warning information is generated according to the first abnormal statistical information.

4. The intelligent monitoring method for a CNC machine tool according to claim 3, characterized in that, The abnormal statistical information includes abnormal occurrence frequency, abnormal severity and abnormal category statistical information, The device abnormal early warning information is generated according to the abnormal statistical information, including: An abnormal risk score is calculated according to the abnormal occurrence frequency, the abnormal severity and the abnormal category statistical information; Device abnormal early warning information is generated according to the abnormal risk score.

5. The intelligent monitoring method for a CNC machine tool according to claim 4, characterized in that, The working state of the auxiliary function module is controlled according to the early warning prompt information, including: Device abnormal risk level information of the device abnormal early warning information is obtained; In the case where the abnormal risk level information is low risk, the sampling frequency of the data monitoring module is adjusted; and / or, In the case where the abnormal risk level is medium risk, a high-probability abnormal category is determined based on the abnormal category statistical information; Processing parameters are adjusted based on the high-probability abnormal category and the abnormal risk level information; and / or, In the case where the abnormal risk level is high risk, a machine tool emergency stop program is started.

6. The intelligent monitoring method for CNC machine tools as claimed in claim 2 wherein, The manual suspension prompt information in the manual emergency suspension information set includes: Second processing condition similarity information is calculated in the manual emergency suspension information set according to the material attribute similarity information and the code similarity information; Second abnormal statistical information of all the manual suspension prompt information is obtained in the case where there is manual suspension prompt information with second processing condition similarity information greater than a second preset threshold in the device abnormal suspension information set; Manual suspension prompt information is generated according to the second abnormal statistical information.

7. The intelligent monitoring method for a CNC machine tool according to claim 6, characterized in that, The working state of the auxiliary function module is controlled according to the early warning prompt information, including: Cooling liquid flow information and light prompt information are controlled according to the manual suspension prompt information.

Images