3D printer system based on artificial intelligence and control method thereof

Abstract

The invention discloses a 3D printer system based on artificial intelligence, and the 3D printer system is characterized in that the 3D printer system comprises sensors which are detachably installed on a printing head and a printing hot bed and are used for detecting data of corresponding positions; the sensor BN node is used for collecting sensor data in the 3D printing process, making a corresponding decision through a Bayesian network method, and processing the data collected by the sensor system through a K2 algorithm; the scheduler / server is used for intensively managing and scheduling the plurality of 3D printers; and the controller is used for setting the 3D printer by a user according to requirements. The sensor nodes can collect sensor data in the 3D printing process, so that inherent factors influencing the environment and a machine in the printing process can be better known, corresponding decisions are made through a Bayesian network method, the running state of the 3D printer can be effectively analyzed, and therefore the running condition of the 3D printer is predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of 3D printing, and in particular to a method for controlling a 3D printer system based on artificial intelligence. Background Art

[0002] At present, the intelligent identification and feedback functions in the control systems of 3D printers at home and abroad are basically blank. Although the various subsystems in the control system can achieve closed-loop control well, the overall control of most printers is far from being intelligent. When printing abnormalities occur, the control system cannot identify them in time, let alone dynamically adjust and solve the problem. When slight printing errors occur during the molding process, errors will continue to accumulate, resulting in the need for experienced professionals to observe its operation and make timely adjustments during the 3D printing process, which is inconvenient to operate. Summary of the invention

[0003] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a 3D printer system based on artificial intelligence and a control method thereof, so as to solve the problem that the existing 3D printing cannot be adjusted intelligently.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a 3D printer system based on artificial intelligence, characterized in that it includes: The sensor is detachably mounted on the print head and the printing bed to detect the data at the corresponding position; The sensor BN node is used to collect sensor data during the 3D printing process, and then make corresponding decisions through the Bayesian network method, and process the data collected by the sensor system through the K2 algorithm; Scheduler / server, used for intensive management and scheduling of multiple 3D printers; The controller is used for users to set up the 3D printer according to their needs.

[0005] Preferably, the size of the print head sensor node is limited to 9 x 25 x 40 mm.

[0006] Preferably, the size of the sensor nodes on the print bed is limited to 13×75×101 mm.

[0007] Preferably, the scheduler / server adopts the ESP8266-12E platform.

[0008] Preferably, the sensor node is equipped with two sensor PCBs on average, each PCB contains 1 to 4 sensors, each sensor provides 10 to 14 bits of data, and the maximum data for each measurement is 14×4×2=112 bits, in addition to a 3-bit sensor identifier, a 4-bit sensor node identifier, and 12 bits of timing information.

[0009] The present invention also relates to a control method of a 3D printer system based on artificial intelligence, comprising the following specific steps: 1) Deploy multiple sensors in 3D printers; 2) Build and maintain data from multiple sensors through sensor BN nodes; 3) Analyze the operating status of the 3D printer to predict the operating conditions of the 3D printer.

[0010] The beneficial effects of the present invention are as follows: the system of the present invention can be used for the research of FDM object additive manufacturing of consumer-grade 3D printers, and the sensor nodes can collect sensor data in the 3D printing process in order to better understand the environmental and machine-inherent factors affecting the printing process, and then make corresponding decisions through the Bayesian network method, which can effectively analyze the operating status of the 3D printer, thereby predicting the operating status of the 3D printer and realizing the intelligent recognition and feedback capabilities of the 3D printer control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 A schematic structural diagram of an artificial intelligence-based 3D printer system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0013] 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.

[0014] Embodiment 1, as Figure 1 As shown, including: Sensors, which are detachably mounted on the print head and the print bed, detect the data at the corresponding position, use existing sensors (such as thermistors, voltage sensors, A / D converters, stepper drive signals, etc.), and add some new other sensors (such as Hall effect current sensors, voltage, temperature, etc.) to generate some data sets and use learning algorithms for useful Bayesian networks; The sensor BN node is used to collect sensor data during the 3D printing process, and then make corresponding decisions through the Bayesian network method, and process the data collected by the sensor system through the K2 algorithm; Scheduler / server, used for intensive management and scheduling of multiple 3D printers; The controller is used for users to set up the 3D printer according to their needs.

[0015] Furthermore, the size of the print head sensor node is limited to 9×25×40 mm.

[0016] Furthermore, the size of the sensor node on the print bed is limited to 13×75×101mm.

[0017] The attachment of sensor nodes on the printer is limited by the sensor's ability to detect valid sensory inputs. The placement of the sensor requires rigidity and stability to ensure that the sensor node does not fall off during operation. The installation of the sensor node must also be detachable to ensure that the entire system has high flexibility.

[0018] Furthermore, the scheduler / server uses the ESP8266-12E platform, which is low-cost and available in large quantities from various vendors at very low prices, thus enabling each application or machine to have a large number of sensor nodes.

[0019] Furthermore, the sensor node is equipped with two sensor PCBs on average, each containing 1 to 4 sensors. Each sensor provides 10 to 14 bits of data, and the maximum data for each measurement is 14×4×2=112 bits. In addition, there are 3 bits of sensor identifier, 4 bits of sensor node identifier, and 12 bits of timing information. Therefore, the total data for each measurement is estimated to be up to 112+3+4+12=131 bits at a speed of 200Hz, that is, 26200 bits / second or 3.198KiB / s. ESP8266 provides 80kib of dynamic RAM (DRAM), which can save about 5850 sensor samples or 29.2 seconds of sensor data at a collection rate of 200Hz. The system can effectively collect real-time data generated by the 3D printer during the printing process for use in the Bayesian network algorithm.

[0020] The present invention also relates to a control method of a 3D printer system based on artificial intelligence, comprising the following specific steps: 1) Deploy multiple sensors in 3D printers; 2) Build and maintain data from multiple sensors through sensor BN nodes; 3) Analyze the operating status of the 3D printer to predict the operating conditions of the 3D printer.

[0021] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A 3D printer system based on artificial intelligence, characterized in that: include: The sensor is detachably mounted on the print head and the printing bed to detect the data at the corresponding position; The sensor BN node is used to collect sensor data during the 3D printing process, and then make corresponding decisions through the Bayesian network method, and process the data collected by the sensor system through the K2 algorithm; Scheduler / server, used for intensive management and scheduling of multiple 3D printers; The controller is used for users to set up the 3D printer according to their needs.

2. The artificial intelligence-based 3D printer system according to claim 1, characterized in that: The size of the print head sensor node is limited to 9×25×40mm.

3. The artificial intelligence-based 3D printer system according to claim 1, characterized in that: The size of the sensor node on the print bed is limited to 13×75×101mm.

4. The artificial intelligence-based 3D printer system according to claim 1, characterized in that: The scheduler / server uses the ESP8266-12E platform.

5. The artificial intelligence-based 3D printer system according to claim 1, characterized in that: The sensor node is equipped with two sensor PCBs on average. Each PCB contains 1 to 4 sensors. Each sensor provides 10 to 14 bits of data. The maximum data for each measurement is 14×4×2=112 bits. There are also 3 bits of sensor identifier, 4 bits of sensor node identifier, and 12 bits of timing information.

6. A control method for a 3D printer system based on artificial intelligence, characterized in that: Including the specific steps: 1) Deploy multiple sensors in 3D printers; 2) Build and maintain data from multiple sensors through sensor BN nodes; 3) Analyze the operating status of the 3D printer to predict the operating conditions of the 3D printer.

Images