A data analysis-based additive machine tool operation monitoring system and method
By designing an additive machine tool operation monitoring system based on data analysis, collecting and analyzing various parameters in the 3D printing process, calculating risk coefficients and evaluating risks, it solves the difficulty in monitoring the preheating and surface of additive machine tools in the prior art. The abnormal problems are handled and comprehensive risk monitoring of the operation process of additive machine tools is achieved.
Patent Information
- Application Number
- CN202410968799.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-07-19
AI Technical Summary
The existing selective laser melting additive machine tools monitoring methods are difficult to detect preheating before printing and surface treatment abnormalities after printing, and it is impossible to fully monitor the risks during the machine tool operation.
Design an additive machine tool operation monitoring system based on data analysis, including preheating process monitoring module, printing process monitoring module, product quality monitoring module, data analysis module, status evaluation module and abnormal warning module, through the acquisition and analysis of additive machine tools During various parameters during the 3D printing process, the preheating risk coefficient, the printing risk coefficient and the result risk coefficient are calculated, and the corresponding risk warning is issued.
It realizes comprehensive monitoring of the operation of additive machine tools, can promptly detect preheating before printing and surface treatment abnormalities after printing, monitor and evaluate risks during machine tools, and improves the comprehensiveness and accuracy of monitoring.
Smart Images

Figure CN118543858B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of equipment monitoring, and in particular to an additive machine tool operation monitoring system and method based on data analysis. Background Art
[0002] Additive manufacturing machines, commonly referred to as 3D printers, are devices specifically designed to build three-dimensional entities through additive manufacturing technology. Unlike traditional subtractive manufacturing machines (such as lathes, milling machines, etc.) that form parts by cutting materials, additive manufacturing machines build parts by adding materials layer by layer, a process usually based on digital 3D models.
[0003] Selective Laser Melting (SLM) is an advanced additive manufacturing technology mainly used for 3D printing of metal parts. It is a type of powder bed fusion (PBF).
[0004] The existing monitoring method of selective laser melting additive machine tools mainly compares the monitoring value of the main parameters involved in the 3D printing process with the set threshold. When the monitoring value of the main parameter is greater than or equal to the set threshold, it indicates that there is an abnormality in the parameter, that is, the additive machine tool is operating abnormally. This method can judge the obvious operating risks in the 3D printing molding process, but it cannot detect the preheating before printing and the surface treatment after printing in time, and it cannot detect the operating risks that occur during the operation of the machine tool, affecting the comprehensiveness of the additive machine tool monitoring. Summary of the invention
[0005] The purpose of the present invention is to provide an additive machine tool operation monitoring system and method based on data analysis to solve the above-mentioned technical problems.
[0006] An additive machine tool operation monitoring system based on data analysis, comprising a preheating process monitoring module, a printing process monitoring module, a product quality monitoring module, a data analysis module, a state evaluation module and an abnormality warning module;
[0007] The preheating process monitoring module is used to collect preheating parameters during the preheating process of the printing material before the start of 3D printing, and the preheating parameters include real-time ambient temperature, humidity and data on the change of the printing material temperature over time during the real-time preheating process;
[0008] The printing process monitoring module includes a physical parameter monitoring unit and a process parameter monitoring unit;
[0009] The physical parameter monitoring unit is used to collect real-time data of physical parameters during the 3D printing process, wherein the physical parameters include laser power and scanning speed;
[0010] The process parameter monitoring unit is used to collect real-time data of process parameters during the 3D printing process, wherein the process parameters include the time taken to complete each layer of construction during layer-by-layer construction;
[0011] The product quality monitoring module is used to collect quality parameters of products formed after 3D printing;
[0012] The data analysis module is used to obtain the printing material properties and analyze the operation process of the additive machine tool according to the printing material properties and the parameters collected by the preheating process monitoring module, the printing process monitoring module and the product quality monitoring module, and obtain the preheating risk coefficient, the printing risk coefficient and the result risk coefficient respectively;
[0013] The state assessment module is used to assess the operation risk of the additive machine tool according to the preheating risk factor, the printing risk factor and the result risk factor;
[0014] The abnormal warning module is used to issue corresponding risk warnings according to the evaluation results of the status evaluation module.
[0015] As a further description of the solution of the present invention, the working process of the data analysis module to obtain the preheating risk coefficient includes:
[0016] According to the printing material properties and the real-time ambient temperature and humidity, the standard data curve of the printing material temperature changing with time during the preheating process before 3D printing begins is obtained. ;
[0017] Get the actual data curve of the printing material temperature changing with time during the preheating process ;
[0018] The warm-up risk factor is calculated by the following formula:
[0019] ;
[0020] In the formula, is the warm-up risk factor, The warm-up start time is is the end time of preheating. = - .
[0021] As a further description of the solution of the present invention, the working process of the data analysis module to obtain the printing risk coefficient includes:
[0022] First, the physical risk coefficient is calculated based on the parameters obtained by the physical parameter monitoring unit;
[0023] Then, the processing risk coefficient is calculated based on the parameters obtained by the process parameter monitoring unit;
[0024] Finally, the printing risk factor is calculated based on the physical risk factor and the processing risk factor.
[0025] As a further description of the scheme of the present invention, the working process of calculating the physical risk coefficient includes:
[0026] Obtain the standard data curve of laser power variation over time during 3D printing based on the printing material properties and the layer thickness set during layer-by-layer construction Standard data curve of scanning speed changing with time ;
[0027] Get the actual data curve of laser power changing with time during 3D printing The actual data curve of scanning speed changing with time ;
[0028] The physical risk factor is calculated by the following formula:
[0029] = ;
[0030] in, ;
[0031] In the formula, is the physical risk factor, is the printing start time, is the printing end time, = - , is the laser power scanning speed corresponding difference function, , and is the weight coefficient, is the laser power versus scanning speed function, is the standard reference value;
[0032] As a further description of the solution of the present invention, the working process of calculating the processing risk coefficient includes:
[0033] The processing risk factor is calculated by the following formula:
[0034] ;
[0035] In the formula, is the processing risk coefficient, n is the number of layers set when slicing the printed 3D model, i belongs to n, is the time it takes to complete the i-th layer during 3D printing, It is the preset time to complete the 3D model construction.
[0036] As a further description of the solution of the present invention, the working process of calculating the printing risk coefficient includes:
[0037] Substitute the physical risk factor and processing risk factor into the following formula to calculate the printing risk factor:
[0038] ;
[0039] In the formula, is the printing risk factor, yes The corresponding standard value is yes The corresponding standard value.
[0040] As a further description of the solution of the present invention, the working process of the data analysis module to obtain the result risk coefficient includes:
[0041] Get the actual parameter values of the model after 3D printing, and then calculate the risk factor of the result by the following formula:
[0042] ;
[0043] in, is the result risk coefficient, m is the number of parameters that need to be tested, j∈[1,m]; is the detection value of the jth parameter, is the standard value of the jth parameter, is the reference value of the jth parameter, is the correlation coefficient of the jth parameter.
[0044] As a further description of the solution of the present invention, the working process of the state assessment module includes:
[0045] The preheating risk factor, the printing risk factor and the result risk factor are respectively compared with the corresponding set threshold intervals. If there is a risk factor that does not meet the set threshold interval, it is determined that the additive machine tool is operating abnormally;
[0046] Otherwise, the operating risk factor of the additive machine tool is calculated by the following formula: :
[0047] ;
[0048] Will The set additive machine operation coefficient threshold Compare, if Greater than or equal to , then the additive machine tool operation risk is judged to be high, otherwise, the additive machine tool operation risk is judged to be low.
[0049] A data analysis-based additive machine tool operation monitoring method, wherein the method is applicable to the data analysis-based additive machine tool operation monitoring system.
[0050] Beneficial effects of the present invention:
[0051] The present invention collects preheating parameters of the additive machine tool during the preheating process of printing materials before 3D printing, physical parameters and process parameters of the additive machine tool during the 3D printing process, and product quality parameters of the product formed by the additive machine tool after 3D printing through a preheating process monitoring module, a printing process monitoring module, and a product quality monitoring module, and comprehensively monitors the operation of the additive machine tool. Then, the data analysis module analyzes the operation process of the additive machine tool according to the collected parameters, and obtains the preheating risk coefficient, the printing risk coefficient, and the result risk coefficient respectively. Finally, the state evaluation module evaluates the operation risk of the additive machine tool according to the preheating risk coefficient, the printing risk coefficient, and the result risk coefficient, so as to realize not only the monitoring of abnormal operation of the additive machine tool, but also the monitoring of the risks in the operation process of the additive machine tool. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] The present invention will be further described below in conjunction with the accompanying drawings.
[0053] Figure 1 It is a partial structural schematic diagram of the additive machine tool operation monitoring system based on data analysis provided by the present invention. DETAILED DESCRIPTION
[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0055] See also Figure 1 As shown, the present invention is an additive machine tool operation monitoring system based on data analysis, including a preheating process monitoring module, a printing process monitoring module, a product quality monitoring module, a data analysis module, a state evaluation module and an abnormal warning module;
[0056] The preheating process monitoring module is used to collect preheating parameters during the preheating process of the printing material before the start of 3D printing, and the preheating parameters include real-time ambient temperature, humidity and data on the change of the printing material temperature over time during the real-time preheating process;
[0057] The printing process monitoring module includes a physical parameter monitoring unit and a process parameter monitoring unit;
[0058] The physical parameter monitoring unit is used to collect real-time data of physical parameters during the 3D printing process, wherein the physical parameters include laser power and scanning speed;
[0059] The process parameter monitoring unit is used to collect real-time data of process parameters during the 3D printing process, wherein the process parameters include the time taken to complete each layer of construction during layer-by-layer construction;
[0060] The product quality monitoring module is used to collect quality parameters of products formed after 3D printing;
[0061] The data analysis module is used to obtain the printing material properties and analyze the operation process of the additive machine tool according to the printing material properties and the parameters collected by the preheating process monitoring module, the printing process monitoring module and the product quality monitoring module, and obtain the preheating risk coefficient, the printing risk coefficient and the result risk coefficient respectively;
[0062] The state assessment module is used to assess the operation risk of the additive machine tool according to the preheating risk factor, the printing risk factor and the result risk factor;
[0063] The abnormal warning module is used to issue corresponding risk warnings according to the evaluation results of the status evaluation module.
[0064] Through the above technical scheme, the present invention collects the preheating parameters of the additive machine tool during the preheating process of the printing material before the start of 3D printing, the physical parameters and process parameters of the additive machine tool during the 3D printing process, and the product quality parameters of the additive machine tool after the 3D printing is completed through the preheating process monitoring module, the printing process monitoring module, and the product quality monitoring module, and comprehensively monitors the operation of the additive machine tool. Then, the data analysis module analyzes the operation process of the additive machine tool according to the collected parameters, and obtains the preheating risk coefficient, the printing risk coefficient and the result risk coefficient respectively. Finally, the state evaluation module evaluates the operation risk of the additive machine tool according to the preheating risk coefficient, the printing risk coefficient and the result risk coefficient.
[0065] As a further description of the solution of the present invention, the working process of the data analysis module to obtain the preheating risk coefficient includes:
[0066] According to the printing material properties and the real-time ambient temperature and humidity, the standard data curve of the printing material temperature changing with time during the preheating process before 3D printing begins is obtained. ;
[0067] Get the actual data curve of the printing material temperature changing with time during the preheating process ;
[0068] The warm-up risk factor is calculated by the following formula:
[0069] ;
[0070] In the formula, is the warm-up risk factor, The warm-up start time is is the end time of preheating. = - .
[0071] Through the above technical solution, this implementation first obtains the standard data curve of the change of printing material temperature over time during the preheating process before 3D printing according to the printing material properties and the real-time ambient temperature and humidity. , and then combined with the actual data curve of the change of printing material temperature over time during the preheating process Based on the formula The preheating risk coefficient is calculated, where the preheating risk coefficient is obtained by analyzing the difference between the cumulative amount of actual data of the temperature change of the printing material over time during the preheating process and the standard amount.
[0072] It should be noted that the standard data curve of the printing material temperature changing with time during the preheating process is These are empirical data and are selectively set based on actual conditions, so there is no need to elaborate on them.
[0073] As a further description of the solution of the present invention, the working process of the data analysis module to obtain the printing risk coefficient includes:
[0074] First, the physical risk coefficient is calculated based on the parameters obtained by the physical parameter monitoring unit;
[0075] Then, the processing risk coefficient is calculated based on the parameters obtained by the process parameter monitoring unit;
[0076] Finally, the printing risk factor is calculated based on the physical risk factor and the processing risk factor.
[0077] As a further description of the scheme of the present invention, the working process of calculating the physical risk coefficient includes:
[0078] Obtain the standard data curve of laser power variation over time during 3D printing based on the printing material properties and the layer thickness set during layer-by-layer construction Standard data curve of scanning speed changing with time ;
[0079] Get the actual data curve of laser power changing with time during 3D printing The actual data curve of scanning speed changing with time ;
[0080] The physical risk factor is calculated by the following formula:
[0081] = ;
[0082] in, ;
[0083] In the formula, is the physical risk factor, is the printing start time, is the printing end time, = - , is the laser power scanning speed corresponding difference function, , and is the weight coefficient, is the laser power versus scanning speed function, is the standard reference value;
[0084] As a further description of the solution of the present invention, the working process of calculating the processing risk coefficient includes:
[0085] The processing risk factor is calculated by the following formula:
[0086] ;
[0087] In the formula, is the processing risk coefficient, n is the number of layers set when slicing the printed 3D model, i belongs to n, is the time it takes to complete the i-th layer during 3D printing, It is the preset time to complete the 3D model construction.
[0088] As a further description of the solution of the present invention, the working process of calculating the printing risk coefficient includes:
[0089] Substitute the physical risk factor and processing risk factor into the following formula to calculate the printing risk factor:
[0090] ;
[0091] In the formula, is the printing risk factor, yes The corresponding standard value is yes The corresponding standard value.
[0092] Through the above technical solution, this embodiment obtains the actual data curve of laser power changing with time during 3D printing. The actual data curve of scanning speed changing with time , through the formula = Calculate the physical risk factor, where Indicates the difference between the overall accumulated laser power during 3D printing and the standard laser power. It indicates the difference between the overall accumulated scanning speed and the standard scanning speed during 3D printing, eliminating the misjudgment caused by instantaneous changes. Indicates the influence of the relationship between laser power and scanning speed on the physical risk factor;
[0093] At the same time, this embodiment not only monitors physical parameters, but also monitors processing parameters, and substitutes the time taken to complete the i-th layer construction in the 3D printing process into the formula Calculate the processing risk factor;
[0094] Finally, this embodiment combines the physical parameters and processing parameters of the 3D printing process, and uses the formula Calculate the printing risk factor.
[0095] It should be noted that , and , and , and , These are all empirical data, which are selectively set according to actual conditions and need not be elaborated in detail.
[0096] As a further description of the solution of the present invention, the working process of the data analysis module to obtain the result risk coefficient includes:
[0097] Get the actual parameter values of the model after 3D printing, and then calculate the risk factor of the result by the following formula:
[0098] ;
[0099] in, is the result risk coefficient, m is the number of parameters that need to be tested, j∈[1,m]; is the detection value of the jth parameter, is the standard value of the jth parameter, is the reference value of the jth parameter, is the correlation coefficient of the jth parameter.
[0100] Through the above technical solution, this embodiment sequentially obtains the test values and standard values of the number of parameter items that need to be tested after 3D printing, and uses the formula Calculate the resulting risk factor.
[0101] As a further description of the solution of the present invention, the working process of the state assessment module includes:
[0102] The preheating risk factor, the printing risk factor and the result risk factor are respectively compared with the corresponding set threshold intervals. If there is a risk factor that does not meet the set threshold interval, it is determined that the additive machine tool is operating abnormally;
[0103] Otherwise, the operating risk factor of the additive machine tool is calculated by the following formula: :
[0104] ;
[0105] Will The set additive machine operation coefficient threshold Compare, if Greater than or equal to , then the additive machine tool operation risk is judged to be high, otherwise, the additive machine tool operation risk is judged to be low.
[0106] Through the above technical solution, this embodiment compares the preheating risk coefficient, the printing risk coefficient and the result risk coefficient with the corresponding set threshold intervals respectively. If there is a risk coefficient that does not meet the set threshold interval, it is judged that the additive machine tool is operating abnormally. If they all meet the set threshold interval, the formula Calculating the operational risk factor for additive machines ,Will The set additive machine operation coefficient threshold Compare, if Greater than or equal to , then the additive machine tool operation risk is judged to be high, otherwise, the additive machine tool operation risk is judged to be low.
[0107] It should be noted that , , and , and the set threshold ranges are all empirical data, which are selectively set according to actual conditions and need not be elaborated in detail.
[0108] A data analysis-based additive machine tool operation monitoring method, wherein the method is applicable to the data analysis-based additive machine tool operation monitoring system.
[0109] All parameter calculations in the present invention are simple numerical calculations, and there is no need to consider the dimension.
[0110] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. An additive machine tool operation monitoring system based on data analysis, characterized in that: It includes preheating process monitoring module, printing process monitoring module, product quality monitoring module, data analysis module, status assessment module and abnormal warning module; The preheating process monitoring module is used to collect preheating parameters during the preheating process of the printing material before the start of 3D printing, and the preheating parameters include real-time ambient temperature, humidity and data on the change of the printing material temperature over time during the real-time preheating process; The printing process monitoring module includes a physical parameter monitoring unit and a process parameter monitoring unit; The physical parameter monitoring unit is used to collect real-time data of physical parameters during the 3D printing process, wherein the physical parameters include laser power and scanning speed; The process parameter monitoring unit is used to collect real-time data of process parameters during the 3D printing process, wherein the process parameters include the time taken to complete each layer of construction during layer-by-layer construction; The product quality monitoring module is used to collect quality parameters of products formed after 3D printing; The data analysis module is used to obtain the printing material properties and analyze the operation process of the additive machine tool according to the printing material properties and the parameters collected by the preheating process monitoring module, the printing process monitoring module and the product quality monitoring module, and obtain the preheating risk coefficient, the printing risk coefficient and the result risk coefficient respectively; The state assessment module is used to assess the operation risk of the additive machine tool according to the preheating risk factor, the printing risk factor and the result risk factor; The abnormal warning module is used to issue corresponding risk warnings according to the evaluation results of the status evaluation module; The working process of the data analysis module to obtain the preheating risk coefficient includes: According to the printing material properties and the real-time ambient temperature and humidity, the standard data curve T0(t) of the printing material temperature change over time during the preheating process before 3D printing begins is obtained; Obtain the actual data curve T(t) of the temperature change of the printing material over time during the preheating process; The warm-up risk factor is calculated by the following formula: In the formula, σ T is the preheating risk coefficient, t0 is the preheating start time, t1 is the preheating end time, ΔT1=t1-t0; The working process of calculating the printing risk coefficient includes: Substitute the physical risk factor and processing risk factor into the following formula to calculate the printing risk factor: In the formula, σ P is the printing risk factor, σ Nth is N The corresponding standard value, σ mth is m The corresponding standard value; The working process of the data analysis module to obtain the result risk coefficient includes: Get the actual parameter values of the model after 3D printing, and then calculate the risk factor of the result by the following formula: Among them, σ R is the result risk coefficient, m is the number of parameters that need to be tested, j∈[1,m]; δ j is the detected value of the jth parameter, δ j0 is the standard value of the jth parameter, d k is the reference value of the jth parameter, ω j is the correlation coefficient of the jth parameter; The working process of the status assessment module includes: The preheating risk factor, the printing risk factor and the result risk factor are respectively compared with the corresponding set threshold intervals. If there is a risk factor that does not meet the set threshold interval, it is determined that the additive machine tool is operating abnormally; Otherwise, the additive machine operation risk factor σ is calculated by the following formula: s : σ s Compared with the set additive machine tool operation coefficient threshold σ0, if σ s If it is greater than or equal to σ0, the operating risk of the additive machine tool is judged to be high; otherwise, the operating risk of the additive machine tool is judged to be low.
2. The additive machine tool operation monitoring system based on data analysis according to claim 1, characterized in that: The working process of the data analysis module obtaining the printing risk coefficient includes: First, the physical risk coefficient is calculated based on the parameters obtained by the physical parameter monitoring unit; Then, the processing risk coefficient is calculated based on the parameters obtained by the process parameter monitoring unit; Finally, the printing risk factor is calculated based on the physical risk factor and the processing risk factor.
3. The additive machine tool operation monitoring system based on data analysis according to claim 2, characterized in that: The working process of calculating the physical risk coefficient includes: According to the printing material properties and the layer thickness set during layer-by-layer construction, the standard data curve P0(t) of the laser power changing with time and the standard data curve V0(t) of the scanning speed changing with time during the 3D printing process are obtained; Obtain the actual data curve P(t) of laser power changing with time and the actual data curve V(t) of scanning speed changing with time during 3D printing; The physical risk factor is calculated by the following formula: in, In the formula, σ N is the physical risk coefficient, t2 is the printing start time, t3 is the printing end time, ΔT2 = t3-t2, f(P(t), V(t)) is the laser power scanning speed corresponding difference function, k1, k2 and k3 are weight coefficients, g is the laser power scanning speed function, f th It is the standard reference value.
4. The additive machine tool operation monitoring system based on data analysis according to claim 3, characterized in that: The working process of calculating the processing risk coefficient includes: The processing risk factor is calculated by the following formula: In the formula, σ m is the processing risk coefficient, n is the number of layers set when slicing the printed 3D model, i belongs to n, T i It is the time taken to complete the construction of the i-th layer in the 3D printing process, and T0 is the preset time to complete the construction of the 3D model.
5. A method for monitoring the operation of an additive machine tool based on data analysis, characterized in that: The method is applicable to the additive machine tool operation monitoring system based on data analysis as described in any one of claims 1 to 4.
Citation Information
Patent Citations
Profile processing risk assessment system for porous extrusion of solar frame
CN115780555A
Metal material processing control optimization method based on 3D printing
CN117399647A
