An energetic material 3D printing parameter adjustment system and method based on data fusion

Abstract

The present invention discloses an energy-containing material 3D printing parameter adjustment system and method based on data fusion, which relates to the technical field of additive manufacturing of energy-containing materials. In the present invention, sensors are installed on additive manufacturing equipment; sensor data is transmitted to a central database, and encryption and error correction technologies are used for data transmission; the received sensor data is preprocessed; the correlation between the operating parameter group and the corresponding performance group is analyzed; a screening database is constructed based on the operating parameter group with a correlation greater than a preset correlation threshold and the corresponding performance scores; the safety threshold corresponding to the operating parameter group corresponding to the energy-containing material charge marked as a defective product is analyzed; the operating parameters are monitored in real time, and the system gives an early warning for abnormal situations. Based on a preset parameter adjustment rule base, the operating parameters are adjusted. The dynamic transformation of the safety threshold is realized; the ability of abnormal recognition is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of additive manufacturing of energetic materials, and specifically to an energetic material 3D printing parameter adjustment system and method based on data fusion. Background Art

[0002] Due to the particularity of the material, the additive manufacturing of energetic materials has extremely high requirements for the stability and precision of the additive manufacturing process. In the traditional additive manufacturing process, the process operation parameters are usually preset fixed values. However, during the additive manufacturing of energetic materials, their physical and chemical properties may change due to various factors (such as the material's own chemical reactions, environmental temperature changes, etc.), which may affect the printing quality and even cause safety problems.

[0003] However, in the existing additive manufacturing of energetic materials, the monitoring of operation data often uses preset thresholds. However, presetting the thresholds manually is prone to deviation, which increases false alarms or misses the early warning of key events; and the preset thresholds lack flexibility, reducing the quality of decision-making.

[0004] Therefore, the present invention discloses an energetic material 3D printing parameter adjustment system and method based on data fusion to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an energetic material 3D printing parameter adjustment system and method based on data fusion to solve the problems raised in the prior art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An energetic material 3D printing parameter adjustment method based on data fusion, the method includes the following steps:

[0007] S1: Install sensors on the additive manufacturing equipment; transmit the sensor data to the central database, and the data transmission uses encryption and error correction technologies;

[0008] S2: Preprocess the received sensor data; construct an operation parameter group from the preprocessed data, and construct a performance group of the energetic material charge, and analyze the correlation between the operation parameter group and the corresponding performance group; construct a screening database based on the operation parameter group with a correlation greater than the preset correlation threshold and the corresponding performance scores;

[0009] S3: Analyze the corresponding safety threshold according to the operation parameter group corresponding to the energetic material charge marked as a defective product in the screening database;

[0010] S4: Real-time monitor the operation parameters, give a system warning for abnormal situations, and adjust the operation parameters based on the preset parameter adjustment rule library.

[0011] According to the above solution, sensors are installed on the additive manufacturing equipment; the sensors include a flow sensor installed in the material conveying pipeline, a nozzle temperature sensor and a viscosity sensor installed at the printing nozzle, a stress sensor installed on the printing platform, and an ambient temperature sensor and a humidity sensor installed in the printing chamber;

[0012] The monitoring data collected by the sensors is transmitted to the central database via Ethernet based on a high-speed data acquisition card; during the transmission of the monitoring data, the AES encryption algorithm is used to encrypt the monitoring data, and the CRC error correction code technology is adopted to detect and correct errors during the transmission of the monitoring data.

[0013] According to the above solution, in S2, it includes the following content:

[0014] S201: Filter the monitoring data using a filtering algorithm; based on the detection ranges of the respective sensors, normalize the monitoring data of each sensor; by performing differential calculation on the monitoring data of the nozzle temperature sensor and the viscosity sensor, obtain the change amounts of the nozzle temperature and viscosity per unit time, and calculate the ratio of the two to generate the nozzle temperature-viscosity change rate feature R at time t TV =△Tem÷(△Vis + ε); where, △Tem represents the change amount per unit time of the nozzle temperature at time t, and the change amount per unit time of the nozzle temperature at time t is equal to the nozzle temperature at time t minus the nozzle temperature at time t - 1; △Vis represents the change amount per unit time of the viscosity at time t, and the change amount per unit time of the viscosity at time t is equal to the viscosity at time t minus the viscosity at time t - 1; ε represents the initial value coefficient, and the initial value coefficient is a preset constant;

[0015] Obtain the monitoring data of the stress sensor and analyze the standard deviation σ of the stress distribution corresponding to time t S 、maximum value S max and minimum value S min ; Obtain the monitoring data of the flow sensor and the printing speed monitoring data, calculate the flow-printing speed ratio at the same moment, and analyze the standard deviation σ of the flow-printing speed ratio corresponding to time t FV ; Combine the real-time ambient temperature PT and the average humidity HA to form the operation parameter group P at time t = [R TV 、σ S 、S max 、S min 、σ FV 、PT、HA];

[0016] Through the data fusion of this application, it is possible to integrate the information of a single sensor and the information provided by different types of sensors, eliminate redundancy and contradictions, improve the timeliness and reliability of information extraction, and improve the utilization efficiency of data;

[0017] S202: Use a high-precision 3D scanner to accurately measure the shape and size of the printed energetic material charge, use an electron microscope to observe the internal microstructure of the energetic material charge, and analyze the uniformity index UI and porosity index PI of the material; use an energy test device to measure the energy performance indexes of the energetic charge, and the energy performance indexes include detonation velocity DV, detonation pressure EP, and energy release amount ER; normalize the uniformity index, porosity index, and energy performance indexes; form a performance group [UI, PI, DV, EP, ER] at time t; calculate the performance score PS using the weighted average method based on the performance group; the weight coefficient in the performance score analysis is preset by the system;

[0018] S203: Analyze the correlation COR between the operation parameter group at time t and the corresponding performance score:

[0019] ;

[0020] where, P （i，j） represents the j-th data of the i-th operation parameter in the operation parameter group P from the initial time t0 to time t, i ∈ [1, 7]; j ∈ [1, J]; both i and j are positive integers; J represents the total number of monitoring data acquisitions from the initial time t0 to time t; △P （i，j） represents the average value of all data of the i-th operation parameter in the operation parameter group P from the initial time t0 to time t; PS j represents the j-th performance score from the initial time t0 to time t, and △PS j represents the average value of the performance scores from the initial time t0 to time t;

[0021] Extract the operation parameter groups and the corresponding performance scores with the correlation COR greater than the preset correlation threshold to construct a screening database.

[0022] Through the analysis of the correlation, constructing a screening database with the operation parameter groups that meet the requirements and the corresponding performance scores can effectively perform data screening, delete the data that does not meet the requirements, and improve the accuracy of subsequent data analysis;

[0023] According to the above solution, in S3, it includes the following content:

[0024] S301: Extract the operation parameter groups corresponding to the energetic material charges marked as defective products in the screening database; and construct a set of defective parameters with the i-th operation parameter data, denoted as BP i M ={BP （i，m） |i ∈ [1, 7], m ∈ [1, M]}; m is a positive integer, where BP （i，m）represents the average value of the i-th operating parameter data of the energetic material charge of the m-th defective product; M represents the total number of defective products included in the set of defective parameters, and M is greater than 2; the set of defective parameters is arranged in the production order of the defective products;

[0025] S302: Analyze the set of defective parameters BP i M of the moving average index EMA M = α × EMA M-1 + (1 - α) × BP （i，M） ; where EMA M-1 represents the moving average index of the set of defective parameters BP i M-1 ; α represents the moving average coefficient, and the moving average coefficient is a system preset constant; analyze the safety threshold THR corresponding to the i-th operating parameter data based on the moving average index M = β × EMA M + (1 - β) × BP i min ; where BP i min represents the minimum value in the set of defective parameters BP i M ; β represents the safety threshold coefficient, and the safety threshold coefficient is a system preset constant;

[0026] S303: When the (M + 1)-th energetic material charge marked as a defective product appears; if BP （i，M+1） ≤ (1 - θ) × THR M or BP （i，M+1） ≥ (1 + θ) × THR M , θ is a preset constant; expand the set of defective parameters so that BP i M+1 = {BP （i，m） | i ∈ [1, 7], m ∈ [1, M + 1]; analyze the safety threshold THR corresponding to the set of defective parameters BP i M+1 ; if (1 - θ) × THR M+1 < BP M < (1 + θ) × THR （i，M+1） < (1 + θ) × THR M , then the safety threshold THR corresponding to the set of defective parameters BP i M+1 = THR M+1 = THR M .

[0027] The present application further analyzes the operation parameter groups corresponding to the energetic material charges marked as defective products, realizes the dynamic transformation of safety thresholds, improves the ability to identify anomalies, and improves the operating efficiency of the equipment.

[0028] According to the above solution, in S4, the operating parameters are monitored in real time. If one of the real-time operating parameters exceeds the corresponding safety threshold, a system warning is issued, and based on a preset parameter adjustment rule library, the operating parameters are adjusted.

[0029] Another aspect of the present application provides an energetic material 3D printing parameter adjustment system based on data fusion. The system is implemented by applying the above-mentioned energetic material 3D printing parameter adjustment method based on data fusion. The system includes a data acquisition and transmission module, a data screening module, a threshold analysis module, and a warning and adjustment module.

[0030] The data acquisition and transmission module is used to install sensors on the additive manufacturing equipment, and transmit the sensor data to the central database. The data transmission uses encryption and error correction technologies.

[0031] The data screening module preprocesses the received sensor data to construct an operation parameter group, constructs a performance group of the energetic material charge, and analyzes the correlation between the operation parameter group and the corresponding performance group.

[0032] The threshold analysis module analyzes the corresponding safety threshold according to the operation parameter group corresponding to the energetic material charge marked as a defective product in the screening database.

[0033] The warning and adjustment module is used to monitor the operating parameters in real time, issue a system warning for abnormal situations, and adjust the operating parameters based on a preset parameter adjustment rule library.

[0034] According to the above solution, the data acquisition and transmission module includes a data acquisition unit and a data transmission unit.

[0035] The data acquisition unit includes a flow sensor installed on the material conveying pipeline, a nozzle temperature sensor and a viscosity sensor installed at the printing nozzle, a stress sensor installed on the printing platform, and an environmental temperature sensor and a humidity sensor installed in the printing chamber.

[0036] The data transmission unit is used to transmit the monitoring data collected by the sensors to the central database through a high-speed data acquisition card based on Ethernet. During the transmission of the monitoring data, the AES encryption algorithm is used to encrypt the monitoring data, and the CRC error correction code technology is used to detect and correct errors in the transmission process of the monitoring data.

[0037] According to the above solution, the data screening module includes a data preprocessing unit and a correlation analysis unit.

[0038] The data preprocessing unit is used to analyze the monitoring data collected by the sensor and the corresponding performance data to construct an operating parameter group and a performance group;

[0039] The correlation analysis unit is used to analyze the correlation between the operating parameter group and the performance group, and construct a screening database based on the correlation analysis situation.

[0040] According to the above solution, the threshold analysis module includes a parameter screening unit and a safety threshold analysis unit;

[0041] The parameter screening unit is used to extract the operating parameter group corresponding to the energetic material charge marked as a defective product in the screening database; and arrange them in the production order of the defective products in the set of defective parameters;

[0042] The safety threshold analysis unit is used to analyze the moving average index of the set of defective parameters, and further analyze the corresponding safety threshold based on the moving average index.

[0043] According to the above solution, the warning adjustment module is used to monitor the operating parameters in real time. If any one of the real-time operating parameters exceeds the corresponding safety threshold, a system warning is issued, and the operating parameters are adjusted based on a preset parameter adjustment rule library.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the data fusion of the present application, the information of a single sensor and the information provided by different types of sensors can be integrated, redundancy and contradictions can be eliminated, the timeliness and reliability of information extraction can be improved, and the utilization efficiency of data can be increased; Through the correlation analysis, a screening database is constructed with the operating parameter groups that meet the requirements and the corresponding performance scores, which can effectively screen the data, delete the data that does not meet the requirements, and improve the accuracy of subsequent data analysis; The present application further analyzes the operating parameter group corresponding to the energetic material charge marked as a defective product, realizes the dynamic transformation of the safety threshold; improves the ability to identify anomalies and the operating efficiency of the equipment. Description of the Drawings

[0045] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0046] Figure 1 is a schematic flow chart of a method for adjusting parameters of 3D printing of energetic materials based on data fusion according to the present invention;

[0047] Figure 2 is a schematic structural diagram of a system for adjusting parameters of 3D printing of energetic materials based on data fusion according to the present invention. Detailed Embodiments

[0048] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] Please refer to Figure 1 , the present invention provides a technical solution: a method for adjusting parameters of 3D printing of energetic materials based on data fusion, the method comprising the following steps:

[0050] S1: Install sensors on the additive manufacturing equipment; transmit the sensor data to the central database, and the data transmission adopts encryption and error correction technologies;

[0051] Install sensors on the additive manufacturing equipment; the sensors include a flow sensor installed on the material conveying pipeline, a nozzle temperature sensor and a viscosity sensor installed at the printing nozzle, a stress sensor installed on the printing platform, and an ambient temperature sensor and a humidity sensor installed in the printing chamber;

[0052] Embodiment 1: Select high-precision turbine flow sensors and install one at each of the inlet and outlet of the material conveying pipeline. The flow sensor at the inlet is used to monitor the initial flow rate of the energetic material entering the conveying pipeline from the storage container, and the flow sensor at the outlet ensures the flow stability of the material before entering the nozzle. The installation position of the sensor ensures its close fit with the inner wall of the pipeline to reduce measurement errors. After installation, calibrate the flow sensor to make its measurement accuracy reach ±0.1 ml / min, which can meet the requirements of high-precision conveying flow monitoring of energetic materials.

[0053] Install a micro-thermocouple temperature sensor and a vibration-based viscosity sensor at key positions inside the printing nozzle. The probe of the temperature sensor extends deep into the nozzle and is close to the flow path of the energetic material to accurately measure the actual temperature of the material inside the nozzle. The viscosity sensor is installed near the discharge port of the nozzle and can sense the viscosity change of the energetic material in real time when it is about to be extruded. The measurement range of the temperature sensor is set from -20°C to 200°C, and the resolution is 0.1°C; the measurement range of the viscosity sensor is 1 - 10000 mPa・s, and the accuracy is ±2% of the measured value, which can effectively cover the possible viscosity range of the energetic material during the printing process.

[0054] A plurality of piezoelectric stress sensors are installed below the printing platform according to the principle of uniform distribution. The sensors are firmly connected to the bottom surface of the platform through special adhesives to ensure accurate measurement of the vertical and horizontal stresses borne by the platform during the printing process. The stress measurement range is set to 0 - 500N, and the sensitivity is 0.1N, which can accurately capture the minute changes in stress.

[0055] Temperature and humidity integrated sensors are installed at the four corners and the center of the printing chamber respectively. The installation height of the sensors is appropriate to avoid being affected by the self - heating of the printing equipment or local air flow. The measurement accuracy of the ambient temperature sensor is ±0.2°C, and the measurement accuracy of the humidity sensor is ±3%RH. The measurement ranges are - 10°C to 50°C and 10% - 90%RH respectively, which are sufficient to monitor the temperature and humidity changes in the printing chamber.

[0056] The monitoring data collected by the sensors is transmitted to the central database via a high - speed data acquisition card based on Ethernet; during the transmission of the monitoring data, the AES encryption algorithm is used to encrypt the monitoring data, and the CRC error - correction code technology is adopted to detect and correct the errors in the transmission process of the monitoring data.

[0057] S2: Pre - process the received sensor data; construct an operating parameter group and a performance group of the energetic material charge from the pre - processed data, and analyze the correlation between the operating parameter group and the corresponding performance group; construct a screening database based on the operating parameter group with a correlation greater than the preset correlation threshold and the corresponding performance scores;

[0058] In S2, it includes the following content:

[0059] S201: Filter the monitoring data using a filtering algorithm; perform normalization processing on the monitoring data of each sensor based on the detection range of each sensor;

[0060] Example 2: The present invention uses the linear normalization method to normalize the data of all sensors. Taking the data of the flow sensor as an example, assuming its measurement range is 0 - 10ml / min and the actual flow value collected is x, then the normalized flow value y=(x - 0) / (10 - 0).

[0061] By performing differential calculation on the monitoring data of the nozzle temperature sensor and the viscosity sensor, the change amounts of the nozzle temperature and viscosity per unit time are obtained, and the ratio of the two is calculated to generate the nozzle temperature - viscosity change rate feature R corresponding to the t - moment TV=△Tem÷(△Vis+ε); where, △Tem represents the change in the nozzle temperature per unit time at time t, and the change in the nozzle temperature per unit time at time t is equal to the nozzle temperature at time t minus the nozzle temperature at time t-1; △Vis represents the change in viscosity per unit time at time t, and the change in viscosity per unit time at time t is equal to the viscosity at time t minus the viscosity at time t-1; ε represents the initial value coefficient, and the initial value coefficient is a preset constant;

[0062] Obtain the monitoring data of the stress sensor and analyze the standard deviation σ of the stress distribution corresponding to time t S and the maximum value S max and the minimum value S min ; Obtain the monitoring data of the flow sensor and the printing speed monitoring data, calculate the flow printing speed ratio at the same moment, and analyze the standard deviation σ of the flow printing speed ratio corresponding to time t FV ; Combine the real-time environmental temperature PT and the average humidity HA to form the operation parameter group P at time t = [R TV , σ S , S max , S min , σ FV , PT, HA];

[0063] S202: Use a high-precision 3D scanner to accurately measure the shape and size of the printed energetic material charge, use an electron microscope to observe the internal microstructure of the energetic material charge, and analyze the uniformity index UI and porosity index PI of the material; use an energy testing device to measure the energy performance indicators of the energetic charge, and the energy performance indicators include detonation velocity DV, detonation pressure EP, and energy release amount ER; normalize the uniformity index, porosity index, and energy performance indicators; form the performance group at time t = [UI, PI, DV, EP, ER]; calculate the performance score PS using the weighted average method based on the performance group; the weight coefficient in the performance score analysis is preset by the system;

[0064] S203: Analyze the correlation COR between the operation parameter group at time t and the corresponding performance score:

[0065] ;

[0066] where, P （i，j） represents the jth data between the initial time t0 and time t of the ith operation parameter in the operation parameter group P, i ∈ [1, 7]; j ∈ [1, J]; both i and j are positive integers; J represents the total number of monitoring data acquisitions between the initial time t0 and time t; △P （i，j） represents the average value of all data of the ith operation parameter in the operation parameter group P between the initial time t0 and time t; PS j represents the jth performance score between the initial time t0 and time t, △PSj represents the average value of the performance scores between the initial time t0 and time t;

[0067] Extract the operating parameter groups with a correlation COR greater than the preset correlation threshold and the corresponding performance scores to construct a screening database.

[0068] S3: Analyze the corresponding safety threshold according to the operating parameter group corresponding to the energetic material charge marked as a defective product in the screening database;

[0069] In S3, it includes the following content:

[0070] S301: Extract the operating parameter group corresponding to the energetic material charge marked as a defective product in the screening database; and construct a set of bad parameters from the i-th operating parameter data among them, denoted as BP i M ={BP （i，m） |i ∈ [1, 7], m ∈ [1, M]}; m is a positive integer, where BP （i，m） represents the average value of the i-th operating parameter data of the energetic material charge of the m-th defective product; M represents the total number of defective products included in the set of bad parameters, M > 2; the defective products are arranged in the production order in the set of bad parameters;

[0071] S302: Analyze the moving average index EMA of the set of bad parameters BP i M of M = α × EMA M-1 + (1 - α) × BP （i，M） ; where EMA M-1 represents the moving average index of the set of bad parameters BP i M-1 ; α represents the moving average coefficient, and the moving average coefficient is a system preset constant; analyze the corresponding safety threshold THR of the i-th operating parameter data based on the moving average index M = β × EMA M + (1 - β) × BP i min ; where BP i min represents the minimum value in the set of bad parameters BP i M ; β represents the safety threshold coefficient, and the safety threshold coefficient is a system preset constant;

[0072] S303: When the (M + 1)-th energetic material charge marked as a defective product appears; if BP （i，M+1） ≤ (1 - θ) × THR M or BP （i，M+1） ≥ (1 + θ) × THRM , θ is a preset constant; expand the set of bad parameters to make BP i M+1 ={BP （i，m） | i ∈ [1, 7], m ∈ [1, M + 1]; analyze the set of bad parameters BP according to S302 i M+1 corresponding safety threshold THR M+1 ; if (1 - θ) × THR M < BP （i，M+1） < (1 + θ) × THR M , then the safety threshold THR corresponding to the set of bad parameters BP i M+1 corresponding safety threshold THR M+1 = THR M .

[0073] Example 3: In this example, BP1 5 ={5, 5, 5, 5, 6}; α = 0.2; thus EMA4 = 5;

[0074] Moving average index EMA5 = α × EMA4 + (1 - α) × BP （1，5） = 0.2 × 5 + 0.8 × 6 = 5.8;

[0075] In this example, β is 0.5;

[0076] Thus THR5 = β × EMA5 + (1 - β) × BP1 min = 0.5 × 5.8 + 0.5 × 5 = 5.4;

[0077] If the 6th energetic material pellet marked as a defective product appears, and BP （1，6） = 7, in this example, θ is 0.2;

[0078] Then (1 + θ) × THR5 = (1 + 0.2) × 5.4 = 6.48 < 7 = BP （1，6） ;

[0079] Therefore, BP1 6 ={5, 5, 5, 5, 6, 7}; Analyze the corresponding THR6 according to BP1 6 ;

[0080] S4: Monitor the operating parameters in real time, give a system warning for abnormal situations, and adjust the operating parameters based on a preset parameter adjustment rule library.

[0081] In S4, monitor the operating parameters in real time. If one of the real-time operating parameters exceeds the corresponding safety threshold, give a system warning and adjust the operating parameters based on a preset parameter adjustment rule library.

[0082] Example 4: Parameter adjustment rules are formulated based on the physical and chemical properties of energetic materials, the basic principles of additive manufacturing, and the results of a large number of experimental studies. For the relationship between the temperature-viscosity change rate of energetic materials and the adjustment of the nozzle temperature, it is determined through thermodynamics analysis and rheology experiments that when the temperature-viscosity change rate exceeds a certain threshold (0.1 °C / (mPa·s)), the nozzle temperature is adjusted within a certain range according to the magnitude of the change rate. If the change rate is between 0.1 and 0.2 °C / (mPa·s), the nozzle temperature is reduced by 1 - 5 °C; if the change rate is greater than 0.2 °C / (mPa·s), the nozzle temperature is reduced by 5 - 10 °C. For the relationship between the degree of stress concentration and the printing speed, according to the principles of material mechanics and the stability analysis of the printed structure, when the standard deviation of the stress distribution exceeds a certain threshold (10 N), the printing speed is appropriately reduced. The specific reduction amplitude is determined according to factors such as the magnitude of the standard deviation and the current height of the propellant column, generally reducing the printing speed by 5 - 15 mm / s each time.

[0083] Please refer to Figure 2 , the present invention provides a technical solution: an energetic material 3D printing parameter adjustment system based on data fusion, which includes a data acquisition and transmission module, a data screening module, a threshold analysis module, and an early warning and adjustment module;

[0084] The data acquisition and transmission module is used to install sensors on the additive manufacturing equipment; transmit the sensor data to the central database, and the data transmission adopts encryption and error correction technologies;

[0085] The data screening module preprocesses the received sensor data to construct an operating parameter group, constructs a performance group of the energetic material propellant column, and analyzes the correlation between the operating parameter group and the corresponding performance group;

[0086] The threshold analysis module analyzes the corresponding safety threshold according to the operating parameter group corresponding to the energetic material propellant column marked as a defective product in the screening database;

[0087] The early warning and adjustment module is used to monitor the operating parameters in real time, give a system warning for abnormal situations, and adjust the operating parameters based on a preset parameter adjustment rule library.

[0088] The data acquisition and transmission module includes a data acquisition unit and a data transmission unit;

[0089] The data acquisition unit includes a flow sensor installed on the material conveying pipeline, a nozzle temperature sensor and a viscosity sensor installed at the printing nozzle, a stress sensor installed on the printing platform, and an environmental temperature sensor and a humidity sensor installed in the printing chamber;

[0090] The data transmission unit is used to transmit the monitoring data collected by the sensors to the central database via a high-speed data acquisition card based on Ethernet. During the transmission of the monitoring data, the AES encryption algorithm is used to encrypt the monitoring data, and the CRC error correction code technology is adopted to detect and correct the errors in the transmission process of the monitoring data.

[0091] The data screening module includes a data preprocessing unit and a correlation analysis unit;

[0092] The data preprocessing unit is used to analyze the monitoring data collected by the sensors and the corresponding performance data to construct an operating parameter group and a performance group;

[0093] The correlation analysis unit is used to analyze the correlation between the operating parameter group and the performance group, and construct a screening database based on the correlation analysis results.

[0094] The threshold analysis module includes a parameter screening unit and a safety threshold analysis unit;

[0095] The parameter screening unit is used to extract the operating parameter group corresponding to the energetic material charge marked as a defective product from the screening database, and arrange them in the production order of the defective products in the set of defective parameters;

[0096] The safety threshold analysis unit is used to analyze the moving average index of the set of defective parameters, and further analyze the corresponding safety threshold based on the moving average index.

[0097] The warning adjustment module is used to monitor the operating parameters in real time. If any of the real-time operating parameters exceeds the corresponding safety threshold, a system warning is issued, and the operating parameters are adjusted based on the preset parameter adjustment rule library.

[0098] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0099] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A parameter adjustment method for energetic material 3D printing based on data fusion, characterized in that: The method comprises the following steps: S1: Install sensors on the additive manufacturing equipment; transmit sensor data to the central database, using encryption and error correction technology; S2: preprocessing the received sensor data; constructing an operation parameter group from the preprocessed data, constructing a performance group of the energetic material column, and analyzing the correlation between the operation parameter group and the corresponding performance group; Building a screening database based on the operating parameter groups with correlations greater than a preset correlation threshold and the corresponding performance scores; S3: Analyze the corresponding safety threshold according to the operation parameter group corresponding to the energetic material column marked as a bad product in the screening database; S4: Monitor the operating parameters in real time, issue system warnings for abnormal situations, and adjust the operating parameters based on the preset parameter adjustment rule library.

2. According to claim 1, a method for adjusting parameters of energetic material 3D printing based on data fusion, characterized in that: Installing sensors on the additive manufacturing equipment; the sensors include a flow sensor installed on the material delivery pipeline, a nozzle temperature sensor and a viscosity sensor installed at the print nozzle, a stress sensor installed on the printing platform, and an ambient temperature sensor and a humidity sensor installed in the printing chamber; The monitoring data collected by the sensor is transmitted to the central database through a high-speed data acquisition card based on Ethernet; during the monitoring data transmission process, the monitoring data is encrypted using the AES encryption algorithm, and the CRC error correction code technology is used to detect and correct errors in the monitoring data transmission process.

3. According to claim 2, a method for adjusting parameters of energetic material 3D printing based on data fusion, characterized in that: In S2, the following contents are included: S201: Filter the monitoring data using a filtering algorithm; normalize the monitoring data of each sensor based on the detection range of each sensor; obtain the change of the nozzle temperature and viscosity per unit time by performing differential calculation on the monitoring data of the nozzle temperature sensor and the monitoring data of the viscosity sensor, and calculate the ratio of the two to generate the nozzle temperature viscosity change rate characteristic R corresponding to time t TV =△Tem÷(△Vis+ε);wherein, △Tem represents the change of nozzle temperature per unit time at time t, which is equal to the nozzle temperature at time t minus the nozzle temperature at time t-1; △Vis represents the change of viscosity per unit time at time t, which is equal to the viscosity at time t minus the viscosity at time t-1; ε represents the initial value coefficient, which is a preset constant; Obtain stress sensor monitoring data and analyze the standard deviation σ of the stress distribution corresponding to time t S , maximum value S max and the minimum value S min ; Obtain flow sensor monitoring data and printing speed monitoring data, calculate the flow printing speed ratio at the same time, and analyze the standard deviation σ of the flow printing speed ratio corresponding to time t FV ; Combine the real-time ambient temperature PT and the average humidity HA to form the operating parameter group P at time t = [R TV , σ S , S max , S min , σ FV , PT, HA]; S202: Use a high-precision three-dimensional scanner to accurately measure the shape and size of the energetic material grain after printing, use an electron microscope to observe the internal microstructure of the energetic material grain, and analyze the uniformity index UI and porosity index PI of the material; use energy testing equipment to measure the energy performance index of the energetic material grain, the energy performance index includes detonation velocity DV, detonation pressure EP and energy release ER; normalize the uniformity index, porosity index and energy performance index; form a performance group [UI, PI, DV, EP, ER] at time t; calculate the performance score PS based on the performance group using the weighted average method; the weight coefficient in the performance score analysis is preset by the system; S203: Analyze the correlation COR between the operating parameter group at time t and the corresponding performance score: ； Among them, P （i，j） represents the jth data between the initial time t0 and the time t of the i-th operating parameter in the operating parameter group P, i∈[1,7]; j∈[1,J]; i and j are both positive integers; J represents the total number of monitoring data collection between the initial time t0 and the time t; △P （i，j） represents the average value of all data of the i-th operating parameter in the operating parameter group P from the initial time t0 to the time t; PS j represents the jth performance score between the initial time t0 and time t, △PS j Represents the average value of the performance score between the initial time t0 and time t; The operating parameter groups with correlation COR greater than the preset correlation threshold and the corresponding performance scores are extracted to build a screening database.

4. The method for adjusting parameters of energetic material 3D printing based on data fusion according to claim 3 is characterized in that: In S3, the following are included: S301: Extract the operating parameter group corresponding to the energetic material column marked as a bad product in the screening database; and construct a bad parameter set from the i-th operating parameter data, denoted as BP i M ={BP （i，m） |i∈[1,7],m∈[1,M]}; m is a positive integer, where BP （i，m） The average value of the i-th operating parameter data of the energetic material column of the m-th defective product; M represents the total number of defective products included in the defective parameter set, and M is greater than 2; the defective products are arranged in the production order in the defective parameter set; S302: Analyze bad parameter set BP i M Moving Average EMA M =α×EMA M-1 + (1-α) × BP （i，M） ; Among them, EMA M-1 Denotes the bad parameter set BP i M-1 The moving average index; α represents the moving average coefficient, and the moving average coefficient is a system preset constant; Analyze the safety threshold THR corresponding to the i-th operating parameter data based on the moving average index M =β×EMA M + (1-β) × BP i min ; BP i min Denotes the bad parameter set BP i M The minimum value in , β represents the safety threshold coefficient, and the safety threshold coefficient is a system preset constant; S303: When the M+1th energetic material column marked as a defective product appears; if BP （i，M+1） ≤(1-θ)×THR M or BP （i，M+1） ≥(1+θ)×THR M , θ is a preset constant; the bad parameter set is expanded to make BP i M+1 ={BP （i，m） |i∈[1,7],m∈[1,M+1]; Analyze the bad parameter set BP according to S302 i M+1 Corresponding safety threshold THR M+1 ; If (1-θ)×THR M <BP （i，M+1） < (1 + θ) × THR M , then the bad parameter set BP i M+1 Corresponding safety threshold THR M+1 =THR M .

5. The method for adjusting parameters of energetic material 3D printing based on data fusion according to claim 4, characterized in that: In S4, the operating parameters are monitored in real time. If one of the real-time operating parameters exceeds the corresponding safety threshold, a system warning is issued, and the operating parameters are adjusted based on a preset parameter adjustment rule library.

6. A parameter adjustment system for 3D printing of energetic materials based on data fusion, the system being used to implement a parameter adjustment method for 3D printing of energetic materials based on data fusion as described in any one of claims 1 to 5, characterized in that: The system includes a data acquisition and transmission module, a data screening module, a threshold analysis module and an early warning adjustment module; The data acquisition and transmission module is used to install sensors on the additive manufacturing equipment; the sensor data is transmitted to the central database, and the data transmission adopts encryption and error correction technology; The data screening module pre-processes the received sensor data to construct an operating parameter group, constructs a performance group of the energetic material column, and analyzes the correlation between the operating parameter group and the corresponding performance group; The threshold analysis module analyzes the corresponding safety threshold according to the operation parameter group corresponding to the energetic material column marked as a bad product in the screening database; The early warning adjustment module is used to monitor the operating parameters in real time, issue a system early warning for abnormal situations, and adjust the operating parameters based on a preset parameter adjustment rule base.

7. The parameter adjustment system for 3D printing of energetic materials based on data fusion according to claim 6, characterized in that: The data acquisition and transmission module includes a data acquisition unit and a data transmission unit; The data acquisition unit includes a flow sensor installed on the material delivery pipeline, a nozzle temperature sensor and a viscosity sensor installed at the print nozzle, a stress sensor installed on the printing platform, and an ambient temperature sensor and a humidity sensor installed in the printing chamber; The data transmission unit is used to transmit the monitoring data collected by the sensor to the central database based on Ethernet through a high-speed data acquisition card; during the monitoring data transmission process, the monitoring data is encrypted using the AES encryption algorithm, and the CRC error correction code technology is used to detect and correct errors in the monitoring data transmission process.

8. The parameter adjustment system for 3D printing of energetic materials based on data fusion according to claim 6, characterized in that: The data screening module includes a data preprocessing unit and a correlation analysis unit; The data preprocessing unit is used to analyze the monitoring data collected by the sensor and the corresponding performance data to construct an operating parameter group and a performance group; The correlation analysis unit is used to analyze the correlation between the operating parameter group and the performance group, and to construct a screening database based on the correlation analysis results.

9. The parameter adjustment system for 3D printing of energetic materials based on data fusion according to claim 6, characterized in that: The threshold analysis module includes a parameter screening unit and a safety threshold analysis unit; The parameter screening unit is used to extract the operating parameter group corresponding to the energetic material column marked as a defective product in the screening database; and arrange the defective product in the defective parameter set according to the production order of the defective product; The safety threshold analysis unit is used to analyze the moving average index of the bad parameter set, and further analyze the corresponding safety threshold based on the moving average index.

10. The parameter adjustment system for 3D printing of energetic materials based on data fusion according to claim 6, characterized in that: The early warning adjustment module is used to monitor the operating parameters in real time. If any of the real-time operating parameters exceeds the corresponding safety threshold, a system early warning is issued, and the operating parameters are adjusted based on a preset parameter adjustment rule library.

Images