Method and system for filament extrusion control based on sensory feedback

Abstract

The application discloses a kind of based on sensing feedback's silk extrusion control method and system, the method includes: when target silk extrusion equipment works, the multiple regional sensing information of the target silk extrusion equipment is obtained by sensor;According to the multiple regional sensing information, the link sensing information corresponding to the multiple work links of the target silk extrusion equipment is calculated;According to the link sensing information, and the corresponding relationship of preset sensing information and defect, the corresponding work defect condition of the target silk extrusion equipment is determined;According to the work defect condition, and the corresponding relationship of preset condition and control parameter strategy, the control instruction of at least one equipment component of the target silk extrusion equipment is determined;The control instruction is used to control corresponding equipment component to reduce or solve the work defect condition. Visible, the application can be based on sensing information real-time and comprehensively monitor the work condition of silk extrusion equipment and promptly correct defect, to improve the utilization rate of silk extrusion equipment to consumable and extrusion quality, realize more green and environmental protection's waste recovery work.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a filament extrusion control method and system based on sensor feedback. BACKGROUND

[0002] With the popularization of the concept of green economy, more and more technical research and development work has begun to focus on how to improve the reutilization rate of waste materials. Among them, 3D printing technology has begun to think about how to reheat the recycled materials to realize the new printing work, for example, some enterprises or institutions have launched a filament extrusion technology using 3D printing to process a large amount of waste plastic or nylon printing consumables to realize reutilization. However, the existing filament extrusion printing equipment generally only mechanically and simply processes waste materials according to the designed mechanical structure and processing flow, without effectively utilizing the sensor information obtained by the sensor to judge the working condition in the filament extrusion process in real time, and adjusting the working parameters accordingly. Therefore, the existing filament extrusion technology cannot realize more efficient and stable filament extrusion, and the processing efficiency of waste materials is also limited, which cannot meet the more green and environmentally friendly work requirements. It can be seen that the existing technology has defects and needs to be solved. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a filament extrusion control method and system based on sensor feedback, which can monitor the working condition of the filament extrusion equipment in real time and comprehensively based on sensor information and correct defects in time, so as to improve the utilization rate and extrusion quality of the filament extrusion equipment for consumables, and realize more green and environmentally friendly waste recycling work.

[0004] In order to solve the above technical problems, the present application discloses a filament extrusion control method based on sensor feedback, which comprises:

[0005] When the target filament extrusion equipment is working, acquiring a plurality of regional sensor information of the target filament extrusion equipment through a sensor;

[0006] According to the plurality of regional sensor information, calculating a plurality of link sensor information corresponding to a plurality of working links of the target filament extrusion equipment;

[0007] According to the link sensor information, and the corresponding relationship between the preset sensor information and defects, determining the working defect condition corresponding to the target filament extrusion equipment;

[0008] According to the working defect condition, and the corresponding relationship between the preset condition and the control parameter strategy, determining the control instruction of at least one equipment component of the target filament extrusion equipment; the control instruction is used to control the corresponding equipment component to reduce or solve the working defect condition.

[0009] As an optional implementation, in the first aspect of the present application, the area sensing information is sensing information obtained by a sensor device arranged in a component area of the target filament extrusion device; the component area is a driving motor area, a hopper area, a discharge port area, a gear cycloid area, or a wire material winding area; and the sensing information includes one or more combinations of image information, sound information, temperature information, and infrared distance measuring information.

[0010] As an optional implementation, in the first aspect of the present application, the calculation of the link sensing information corresponding to each working link of the target filament extrusion device according to the plurality of area sensing information includes:

[0011] For each area sensing information, the component area and the information type corresponding to the area sensing information are determined; the information type is image information, sound information, temperature information, or infrared distance measuring information;

[0012] According to the component area and the information type, a link prediction model corresponding to the area sensing information is determined from a plurality of candidate prediction models;

[0013] The area sensing information is input into the link prediction model to obtain the working link corresponding to the area sensing information.

[0014] All the area sensing information corresponding to each working link of the target filament extrusion device is determined as the link sensing information corresponding to the working link.

[0015] As an optional implementation, in the first aspect of the present application, the determination of the link prediction model corresponding to the area sensing information from a plurality of candidate prediction models according to the component area and the information type includes:

[0016] For each candidate prediction model, all component area labels in a training data set corresponding to the prediction model are determined to obtain a training component label set;

[0017] A first similarity parameter between the training component label set and the component area is calculated;

[0018] The data types of all input data in a historical prediction record corresponding to the prediction model are determined to obtain a historical data type set;

[0019] A second similarity parameter between the historical data type set and the information type is calculated;

[0020] The product of the first similarity parameter and the second similarity parameter is calculated to obtain a model priority parameter corresponding to the prediction model;

[0021] The prediction model with the highest model priority parameter is determined as a link prediction model corresponding to the region sensor information, and the link prediction model is obtained by training a training data set including region sensor information of multiple training components and corresponding working link labels.

[0022] As an optional implementation form, in the first aspect of the present application, the working link is a heating consumable link, an extrusion consumable link, an extrusion molding link, a gear disc wire link, or a wire winding link.

[0023] As an optional implementation form, in the first aspect of the present application, determining the working defect condition corresponding to the target filament extrusion device according to the link sensor information and a preset correspondence between sensor information and defects comprises:

[0024] For each working link, the link sensor information corresponding to the working link is input into a defect prediction neural network corresponding to the working link to obtain a plurality of predicted defects corresponding to the working link, and the defect prediction neural network is obtained by training a training data set including training link sensor information of a plurality of the working link and corresponding working defect labels;

[0025] For any two working links in a preset working link sequence and located at adjacent positions, the intersection between all the predicted defects corresponding to the two working links is calculated to obtain an intersection defect set corresponding to the two working links, and the working link sequence is in turn a heating consumable link, an extrusion consumable link, an extrusion molding link, a gear disc wire link, and a wire winding link.

[0026] According to a preset correspondence between continuous links and influence defects, a set of influenceable defects corresponding to the two working links is determined.

[0027] The intersection between the intersection defect set and the set of influenceable defects is calculated to obtain screened defects corresponding to the two working links.

[0028] All the screened defects corresponding to the working links are determined as the working defect condition corresponding to the target filament extrusion device.

[0029] As an optional implementation form, in the first aspect of the present application, the working defect condition comprises one or more combinations of motor defects, heating temperature defects, insufficient extrusion of consumables defects, excessive impurities of consumables defects, consumable blockage defects, gear failure defects, gear disc wire speed defects, and wire winding speed defects.

[0030] As an optional implementation, in the first aspect of the application, the determining of the control instruction of at least one device component of the target filament extrusion device according to the working defect condition and the corresponding relationship between the preset working defect condition and the control parameter strategy comprises:

[0031] determining at least one defective device component corresponding to the working defect condition and a corresponding working adjustment parameter according to the preset corresponding relationship between the working defect condition and the device component;

[0032] generating the control instruction corresponding to the defective device component and comprising the working adjustment parameter;

[0033] and / or,

[0034] for each defect in the working defect condition, determining the associated device component corresponding to the defect according to the preset corresponding relationship between the working defect condition and the device component;

[0035] setting the objective function as the number of control instructions in the control instruction combination reaching the minimum;

[0036] setting the constraint condition comprising:

[0037] all the associated device components corresponding to the working defect condition are included in the union set of possible influence device components corresponding to all the control instructions in the control instruction combination, which are predicted by inputting the control instructions into the trained component influence prediction neural network;

[0038] the working defect condition is included in the union set of defect resolution effects corresponding to all the control instructions in the control instruction combination, which is obtained according to the corresponding relationship between the preset control effect and the defect resolution effect, and the control effect is obtained by inputting the control instructions into the trained control effect prediction algorithm model;

[0039] based on the dynamic programming algorithm, iteratively calculating according to the objective function and the constraint condition to obtain the optimal control instruction combination; the control instruction combination comprises the control instruction of at least one device component of the target filament extrusion device; the control instruction comprises one or more of the motor restart instruction, the motor acceleration instruction, the extrusion head control instruction, the heating control instruction, the extrusion component control instruction, the gear control instruction and the winding motor control instruction.

[0040] The second aspect of the embodiment of the application discloses a filament extrusion control system based on sensing feedback, which comprises:

[0041] an acquisition module, configured to acquire sensing information of multiple regions of the target filament extrusion device through a sensor when the target filament extrusion device is working;

[0042] a calculation module, configured to calculate, according to the plurality of region sensing information, a plurality of working link sensing information corresponding to a plurality of working links of the target filament extrusion device;

[0043] a determination module, configured to determine, according to the working link sensing information and a preset corresponding relationship between sensing information and defects, a working defect situation corresponding to the target filament extrusion device;

[0044] a control module, configured to determine, according to the working defect situation and a preset corresponding relationship between situations and control parameter strategies, a control instruction of at least one device component of the target filament extrusion device; the control instruction is used to control the corresponding device component to reduce or solve the working defect situation.

[0045] As an optional implementation, in the second aspect of the present application, the region sensing information is sensing information obtained by a sensor device arranged in a different component region of the target filament extrusion device; the component region is a driving motor region, a hopper region, a discharge port region, a gear and cycloid region, or a wire material winding region; and the sensing information includes one or more combinations of image information, sound information, temperature information, and infrared distance measuring information.

[0046] As an optional implementation, in the second aspect of the present application, the specific manner in which the calculation module calculates the working link sensing information corresponding to a plurality of working links of the target filament extrusion device according to the plurality of region sensing information includes:

[0047] for each region sensing information, determining the component region and the information type corresponding to the region sensing information; the information type is image information, sound information, temperature information, or infrared distance measuring information;

[0048] determining, according to the component region and the information type, a link prediction model corresponding to the region sensing information from a plurality of candidate prediction models;

[0049] inputting the region sensing information into the link prediction model to obtain the working link corresponding to the region sensing information;

[0050] determining all the region sensing information corresponding to each working link of the target filament extrusion device as the working link sensing information corresponding to the working link.

[0051] As an optional implementation, in the second aspect of the present application, the specific manner in which the calculation module determines, according to the component region and the information type, a link prediction model corresponding to the region sensing information from a plurality of candidate prediction models includes:

[0052] For each prediction model of the candidate, determine all component region labels in the training data set corresponding to the prediction model, to obtain a training component label set;

[0053] Calculate a first similarity parameter between the training component label set and the component region;

[0054] Determine the data types of all input data in the historical prediction record corresponding to the prediction model, to obtain a historical data type set;

[0055] Calculate a second similarity parameter between the historical data type set and the information type;

[0056] Calculate the product of the first similarity parameter and the second similarity parameter, to obtain a model priority parameter corresponding to the prediction model;

[0057] Determine the prediction model with the highest model priority parameter as the link prediction model corresponding to the region sensor information; the link prediction model is obtained by training a training data set including a plurality of training component region sensor information and corresponding work link labels.

[0058] As an optional implementation, in the second aspect of the application, the work link is a heating consumable link, an extrusion consumable link, an extrusion molding link, a gear disc wire link, or a wire material winding link.

[0059] As an optional implementation, in the second aspect of the application, the determining module determines the specific manner of the target filament extrusion device corresponding to the work defect condition according to the link sensor information and a preset correspondence between sensor information and defects, comprising:

[0060] For each work link, input the link sensor information corresponding to the work link into a defect prediction neural network corresponding to the work link, to obtain a plurality of predicted defects corresponding to the work link; the defect prediction neural network is obtained by training a training data set including a plurality of training link sensor information of the work link and corresponding work defect labels;

[0061] For any two work links in a preset work link sequence and located at adjacent positions, calculate the intersection between all predicted defects corresponding to the two work links, to obtain an intersection defect set corresponding to the two work links; the work link sequence is in turn a heating consumable link, an extrusion consumable link, an extrusion molding link, a gear disc wire link, and a wire material winding link;

[0062] According to a preset correspondence between continuous links and influence defects, determine a set of influenceable defects corresponding to the two work links;

[0063] An intersection of the intersection defect set and the influenceable defect set is calculated to obtain a screened defect corresponding to the two work links;

[0064] All the screened defects corresponding to the work links are determined as a work defect condition corresponding to the target wire extrusion device.

[0065] As an optional implementation, in the second aspect of the present application, the work defect condition includes one or more of a combination of motor defect, heating temperature defect, insufficient consumption material extrusion defect, excessive consumption material impurity defect, consumption material blockage defect, gear failure defect, gear disc linear speed defect, and wire winding speed defect.

[0066] As an optional implementation, in the second aspect of the present application, the control module determines a specific manner of a control instruction of at least one device component of the target wire extrusion device according to the work defect condition and a preset corresponding relationship between a condition and a control parameter strategy, including:

[0067] According to a preset corresponding relationship between a work defect condition and a device component, at least one defective device component corresponding to the work defect condition and a corresponding work adjustment parameter are determined;

[0068] A control instruction corresponding to the defective device component and including the work adjustment parameter is generated;

[0069] And / or,

[0070] For each defect in the work defect condition, an associated device component corresponding to the defect is determined according to a preset corresponding relationship between a work defect condition and a device component;

[0071] A target function is set to minimize the number of control instructions in the control instruction combination;

[0072] The constraint condition includes:

[0073] All the associated device components corresponding to the work defect condition are included in the union set of possible influence device components corresponding to all the control instructions in the control instruction combination, which are obtained by inputting the control instructions into a trained component influence prediction neural network;

[0074] The work defect condition is included in the union set of defect resolution effects corresponding to all the control instructions in the control instruction combination, which is obtained according to a preset corresponding relationship between a control effect and a defect resolution effect corresponding to the control instruction, and the control effect is obtained by inputting the control instruction into a trained control effect prediction algorithm model;

[0075] The dynamic programming algorithm is used to iteratively calculate according to the target function and the constraint condition to obtain an optimal control instruction combination; the control instruction combination includes control instructions of at least one device component of the target filament extrusion device; the control instructions include one or more of a motor restart instruction, a motor acceleration instruction, an extrusion head control instruction, a heating control instruction, an extrusion component control instruction, a gear control instruction, and a spool motor control instruction.

[0076] The third aspect of the present application discloses another filament extrusion control system based on sensing feedback, which comprises:

[0077] a memory storing executable program codes;

[0078] a processor coupled with the memory;

[0079] The processor invokes the executable program codes stored in the memory to execute part or all of the steps of the filament extrusion control method based on sensing feedback disclosed in the first aspect of the present application.

[0080] The fourth aspect of the present application discloses a computer storage medium storing computer instructions, which are invoked to execute part or all of the steps of the filament extrusion control method based on sensing feedback disclosed in the first aspect of the present application.

[0081] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0082] The present application can calculate the link sensing information corresponding to multiple work links based on the multiple area sensing information of the target filament extrusion device, determine the working defect condition of the target filament extrusion device according to the link sensing information and the preset corresponding relationship between sensing information and defects, and determine the control instructions of at least one device component of the target filament extrusion device based on this to reduce or solve the working defect condition, so as to monitor the working condition of the filament extrusion device in real time and comprehensively based on the sensing information and correct defects in time, improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work. BRIEF DESCRIPTION OF DRAWINGS

[0083] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0084] Figure 1 is a flowchart of a filament extrusion control method based on sensing feedback disclosed by the embodiments of the present application.

[0085] Figure 2 is a structural schematic view of a filament extrusion control system based on sensing feedback disclosed by an embodiment of the present application.

[0086] Figure 3 is a structural schematic view of another filament extrusion control system based on sensing feedback disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0087] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0088] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or apparatus.

[0089] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0090] The present application discloses a filament extrusion control method and system based on sensing feedback, which can calculate a plurality of work link sensing information corresponding to a plurality of regions of a target filament extrusion device based on a plurality of region sensing information of the target filament extrusion device, and determine a work defect condition corresponding to the target filament extrusion device according to the link sensing information and a preset corresponding relationship between sensing information and defects, and determine a control instruction of at least one device component of the target filament extrusion device based on this to reduce or solve the work defect condition, so as to be able to monitor the working condition of the filament extrusion device in real time and comprehensively based on the sensing information and correct defects in time, so as to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work. The following will be described in detail respectively.

[0091] Embodiment one

[0092] Please refer to Figure 1 , Figure 1 is a flowchart of a sensing feedback based filament extrusion control method according to an embodiment of the present disclosure. Wherein, Figure 1 The sensing feedback based filament extrusion control method described can be applied in a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 1 shown, the sensing feedback based filament extrusion control method can include the following operations:

[0093] 101. When the target filament extrusion device is working, acquire multiple region sensing information of the target filament extrusion device through a sensor.

[0094] 102. According to the multiple region sensing information, calculate link sensing information corresponding to multiple working links of the target filament extrusion device.

[0095] 103. According to the link sensing information, and a preset corresponding relationship between sensing information and defects, determine a working defect situation corresponding to the target filament extrusion device.

[0096] 104. According to the working defect situation, and a preset corresponding relationship between situations and control parameter strategies, determine a control instruction of at least one device component of the target filament extrusion device.

[0097] Optionally, the control instruction is used to control the corresponding device component to reduce or solve the working defect situation.

[0098] In one specific embodiment, the control scheme of the present disclosure can be applied in a 3D printing device with filament extrusion printing function, such as a FDM printing device, the structure of which can be referred to the Chinese invention patent document with publication number CN108790174A, or the structure of the original desktop filament extruder with model MK2.5 sold by ARTME 3D company. The control scheme of the present disclosure should be considered as an improvement to this kind of filament extrusion device, and other devices with similar structure should also be considered as included in the protection scope of the present disclosure.

[0099] It can be seen that the above embodiments of the application can calculate the link sensor information corresponding to a plurality of working links based on the plurality of region sensor information of the target filament extrusion device, determine the working defect condition corresponding to the target filament extrusion device according to the link sensor information and the preset corresponding relationship between the sensor information and the defect, determine the control instruction of at least one device component of the target filament extrusion device based on this to reduce or solve the working defect condition, thereby being able to monitor the working condition of the filament extrusion device in real time and comprehensively based on the sensor information and correct the defect in time, improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0100] As an optional embodiment, in the above step, the region sensor information is sensor information obtained by a sensor device arranged in a different component region of the target filament extrusion device.

[0101] Specifically, the component region is a driving motor region, a hopper region, a discharge port region, a gear cycloid region, or a wire material winding region.

[0102] Optionally, the sensor information includes one or a combination of more of image information, sound information, temperature information, and infrared distance measurement information.

[0103] It can be seen that through the above optional embodiments, the content of the region sensor information is limited to comprehensively represent the working condition characteristics of the device component region, facilitate subsequent defect prediction and instruction determination, and assist in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensor information and correcting defects in time to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0104] As an optional embodiment, in the above step, the link sensor information corresponding to a plurality of working links of the target filament extrusion device is calculated based on a plurality of region sensor information, including:

[0105] For each region sensor information, determine the component region and information type corresponding to the region sensor information; optionally, the information type is image information, sound information, temperature information, or infrared distance measurement information;

[0106] According to the component region and the information type, determine the link prediction model corresponding to the region sensor information from a plurality of candidate prediction models;

[0107] Input the region sensor information into the link prediction model to obtain the working link corresponding to the region sensor information.

[0108] Determine all region sensor information corresponding to each working link of the target filament extrusion device as the link sensor information corresponding to the working link.

[0109] It can be seen that through the above optional embodiments, the appropriate prediction model can be screened based on the area and type of the sensing information to accurately predict the working link corresponding to the area sensing information, so as to facilitate subsequent defect determination, assist in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects, improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0110] As an optional embodiment, in the above step, the link prediction model corresponding to the area sensing information is determined from the plurality of candidate prediction models according to the component area and the information type, including:

[0111] For each prediction model, determine all component area labels in the training data set corresponding to the prediction model to obtain a training component label set;

[0112] Calculate the first similarity parameter between the training component label set and the component area;

[0113] Determine the data type of all input data in the historical prediction record corresponding to the prediction model to obtain a historical data type set;

[0114] Calculate the second similarity parameter between the historical data type set and the information type;

[0115] Calculate the product of the first similarity parameter and the second similarity parameter to obtain a model priority parameter corresponding to the prediction model;

[0116] The prediction model with the highest model priority parameter is determined as the link prediction model corresponding to the area sensing information; the link prediction model is trained by a training data set including a plurality of training component area sensing information and corresponding working link labels.

[0117] It can be seen that through the above optional embodiments, the most reasonable and accurate link prediction model corresponding to the area sensing information can be determined based on the similarity calculation of the training data and the historical prediction record of the model, facilitating subsequent link determination and defect prediction, assisting in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects, improving the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realizing more green and environmentally friendly waste recycling work.

[0118] As an optional embodiment, in the above step, the working link is a heating consumable link, an extruding consumable link, an extruding forming link, a gear disc wire link, or a wire winding link.

[0119] It can be seen that through the above optional embodiments, the type of work link is limited to accurately characterize the division of work flow and facilitate subsequent defect prediction and instruction determination, thereby assisting in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realizing more green and environmentally friendly waste recycling work.

[0120] As an optional embodiment, in the above step, determining the working defect condition corresponding to the target filament extrusion device according to the link sensing information and the preset corresponding relationship between sensing information and defects comprises:

[0121] For each work link, the link sensing information corresponding to the work link is input into the defect prediction neural network corresponding to the work link to obtain a plurality of predicted defects corresponding to the work link; optionally, the defect prediction neural network is trained by a training data set comprising a plurality of training link sensing information and corresponding work defect labels of the work link;

[0122] For any two work links in a preset work link sequence, the intersection between all predicted defects corresponding to the two work links is calculated to obtain an intersection defect set corresponding to the two work links; optionally, the work link sequence is in turn a heating consumable link, an extruding consumable link, an extruding forming link, a gear disc wire link, and a wire material winding link;

[0123] According to a preset corresponding relationship between continuous links and influencing defects, a set of influenceable defects corresponding to the two work links is determined;

[0124] The intersection of the intersection defect set and the set of influenceable defects is calculated to obtain the screened defects corresponding to the two work links;

[0125] The screened defects corresponding to all work links are determined as the working defect condition corresponding to the target filament extrusion device.

[0126] It can be seen that through the above optional embodiments, the working defect condition corresponding to the target filament extrusion device can be determined more accurately based on the defect intersection between continuous links and the screening of the preset corresponding relationship between links and influencing defects, facilitating subsequent instruction generation and control, thereby assisting in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realizing more green and environmentally friendly waste recycling work.

[0127] As an optional embodiment, in the above step, the working defect condition includes one or more of a combination of motor defects, heating temperature defects, insufficient material extrusion defects, excessive material impurity defects, material blockage defects, gear failure defects, gear disc linear speed defects, and wire winding speed defects.

[0128] It can be seen that, through the above optional embodiment, the content of the working defect condition is defined to comprehensively and accurately characterize the possible defects of the wire extrusion device, so as to facilitate subsequent accurate determination of the control instruction to access the correction, and to assist in realizing real-time and comprehensive monitoring of the working condition of the wire extrusion device based on sensing information and timely correction of defects, so as to improve the utilization rate of the wire extrusion device for consumables and the extrusion quality, and to realize more green and environmentally friendly waste recycling work.

[0129] As an optional embodiment, in the above step, according to the working defect condition, and the corresponding relationship between the preset condition and the control parameter strategy, the control instruction of at least one device component of the target wire extrusion device is determined, including:

[0130] According to the preset corresponding relationship between the working defect condition and the device component, at least one defective device component corresponding to the working defect condition and the corresponding working adjustment parameter are determined;

[0131] The control instruction corresponding to the defective device component is generated, including the working adjustment parameter;

[0132] And / or,

[0133] For each defect in the working defect condition, according to the preset corresponding relationship between the working defect condition and the device component, the associated device component corresponding to the defect is determined;

[0134] The objective function is set to be the minimum number of control instructions in the control instruction combination;

[0135] The constraint condition includes:

[0136] The possible influence device components corresponding to all control instructions in the control instruction combination are included in the union of all associated device components corresponding to the working defect condition; optionally, the possible influence device components are obtained by inputting the control instruction into the trained component influence prediction neural network;

[0137] The working defect condition is included in the union of defect resolution effects corresponding to all control instructions in the control instruction combination; optionally, the defect resolution effect is obtained according to the corresponding relationship between the control effect and the defect resolution effect of the preset control effect; the control effect is obtained by inputting the control instruction into the trained control effect prediction algorithm model;

[0138] The dynamic programming algorithm is used to iteratively calculate according to the objective function and the constraint condition to obtain an optimal control instruction combination. Optionally, the control instruction combination includes a control instruction of at least one device component of the target filament extrusion device. The control instruction includes one or more of a motor restart instruction, a motor acceleration instruction, an extrusion head control instruction, a heating control instruction, an extrusion component control instruction, a gear control instruction, and a spool motor control instruction.

[0139] It can be seen that, through the above optional embodiments, the specific scheme of the control instruction determination is limited, wherein the scheme determined according to the corresponding relationship can directly generate the corresponding control instruction in the case of less defects, and the scheme based on the dynamic programming algorithm can obviously achieve the effect of the least instruction control while ensuring the defect correction, so as to improve the control efficiency, realize real-time and comprehensive monitoring of the working condition of the filament extrusion device based on the sensing information, and timely correct the defects, so as to improve the utilization rate of the consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0140] Embodiment two

[0141] Please refer to Figure 2 , Figure 2 is a structural schematic diagram of a filament extrusion control system based on sensing feedback disclosed by the embodiments of the present application. Among them, Figure 2 The filament extrusion control system based on sensing feedback described above can be applied in a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 2 indicated, the filament extrusion control system based on sensing feedback can include:

[0142] The acquisition module 201 is configured to acquire, by a sensor, sensing information of multiple regions of a target filament extrusion device when the target filament extrusion device is working.

[0143] The calculation module 202 is configured to calculate, according to the sensing information of the multiple regions, link sensing information corresponding to multiple working links of the target filament extrusion device.

[0144] The determination module 203 is configured to determine, according to the link sensing information and a preset corresponding relationship between sensing information and defects, a working defect condition corresponding to the target filament extrusion device.

[0145] The control module 204 is configured to determine, according to the working defect condition and a preset corresponding relationship between conditions and control parameter strategies, a control instruction of at least one device component of the target filament extrusion device.

[0146] Optionally, the control instruction is used to control the corresponding device component to reduce or solve the working defect condition.

[0147] It can be seen that the above embodiments of the application can calculate the link sensor information corresponding to a plurality of working links based on the plurality of regional sensor information of the target filament extrusion device, determine the working defect condition corresponding to the target filament extrusion device according to the link sensor information and the preset corresponding relationship between the sensor information and the defect, determine the control instruction of at least one device component of the target filament extrusion device based on this to reduce or solve the working defect condition, thereby being able to monitor the working condition of the filament extrusion device in real time and comprehensively based on the sensor information and correct the defect in time, improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0148] As an optional embodiment, the regional sensor information is sensor information obtained by a sensor device arranged in a different component region of the target filament extrusion device; the component region is a driving motor region, a hopper region, a discharge port region, a gear cycloid region, or a wire material winding region; and the sensor information includes one or a combination of multiple kinds of image information, sound information, temperature information, and infrared distance measurement information.

[0149] It can be seen that through the above optional embodiments, the content of the regional sensor information is limited to comprehensively represent the working condition characteristics of the device component region, facilitate subsequent defect prediction and instruction determination, and assist in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensor information and correcting defects in time to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0150] As an optional embodiment, the specific manner in which the computing module calculates the link sensor information corresponding to a plurality of working links of the target filament extrusion device based on the plurality of regional sensor information includes:

[0151] For each regional sensor information, determine the component region and the information type corresponding to the regional sensor information; optionally, the information type is image information, sound information, temperature information, or infrared distance measurement information;

[0152] According to the component region and the information type, determine the link prediction model corresponding to the regional sensor information from a plurality of candidate prediction models;

[0153] Input the regional sensor information into the link prediction model to obtain the working link corresponding to the regional sensor information.

[0154] Determine all regional sensor information corresponding to each working link of the target filament extrusion device as the link sensor information corresponding to the working link.

[0155] It can be seen that through the above optional embodiments, the suitable prediction model can be screened based on the area and type of the sensing information to accurately predict the working link corresponding to the area sensing information, so as to facilitate subsequent defect determination, assist in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects, improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0156] As an optional embodiment, the specific manner in which the computing module determines the link prediction model corresponding to the area sensing information from the candidate plurality of prediction models according to the component area and the information type comprises:

[0157] For each prediction model in the candidate, determine all component area labels in the training data set corresponding to the prediction model to obtain a training component label set;

[0158] Calculate a first similarity parameter between the training component label set and the component area;

[0159] Determine the data type of all input data in the historical prediction record corresponding to the prediction model to obtain a historical data type set;

[0160] Calculate a second similarity parameter between the historical data type set and the information type;

[0161] Calculate the product of the first similarity parameter and the second similarity parameter to obtain a model priority parameter corresponding to the prediction model;

[0162] Determine the prediction model with the highest model priority parameter as the link prediction model corresponding to the area sensing information; the link prediction model is trained through a training data set comprising a plurality of training component area sensing information and corresponding working link labels.

[0163] It can be seen that through the above optional embodiments, the most reasonable and accurate link prediction model corresponding to the area sensing information can be determined based on the similarity calculation of the training data and the historical prediction record of the model, facilitating subsequent link determination and defect prediction, assisting in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects, improving the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realizing more green and environmentally friendly waste recycling work.

[0164] As an optional embodiment, the working link is a heating consumable link, an extruding consumable link, an extruding forming link, a gear disc wire link, or a wire winding link.

[0165] It can be seen that through the above optional embodiments, the types of work links are defined to accurately characterize the division of work flow and facilitate subsequent defect prediction and instruction determination, thereby assisting in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realizing more green and environmentally friendly waste recycling work.

[0166] As an optional embodiment, the determining module determines the specific manner of the working defect condition corresponding to the target filament extrusion device according to the link sensing information and the preset correspondence between sensing information and defects, which includes:

[0167] For each work link, the link sensing information corresponding to the work link is input into the defect prediction neural network corresponding to the work link to obtain a plurality of predicted defects corresponding to the work link. Optionally, the defect prediction neural network is trained by a training data set including a plurality of training link sensing information and corresponding working defect labels of the work link;

[0168] For any two work links in adjacent positions in the preset work link sequence, the intersection between all predicted defects corresponding to the two work links is calculated to obtain an intersection defect set corresponding to the two work links. Optionally, the work link sequence is in turn a heating consumable link, an extruding consumable link, an extruding forming link, a gear disc wire link, and a wire material winding link.

[0169] According to the preset correspondence between continuous links and influencing defects, the set of influencing defects corresponding to the two work links is determined.

[0170] The intersection of the intersection defect set and the set of influencing defects is calculated to obtain the screened defects corresponding to the two work links.

[0171] The screened defects corresponding to all work links are determined as the working defect condition corresponding to the target filament extrusion device.

[0172] It can be seen that through the above optional embodiments, more accurate working defect conditions corresponding to the target filament extrusion device can be determined based on the defect intersection between continuous links and the screening of the preset correspondence between links and influencing defects, which facilitates subsequent instruction generation and control, thereby assisting in realizing real-time and comprehensive monitoring of the working condition of the filament extrusion device based on sensing information and timely correcting defects to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realizing more green and environmentally friendly waste recycling work.

[0173] As an optional embodiment, the working defect condition comprises one or more of a combination of a motor defect, a heating temperature defect, a consumable extrusion deficiency defect, a consumable impurity excess defect, a consumable blockage defect, a gear failure defect, a gear disc linear speed defect, and a wire winding speed defect.

[0174] As can be seen, through the above optional embodiments, the content of the working defect condition is defined to comprehensively and accurately characterize the possible defects of the wire extrusion device, so as to facilitate subsequent accurate determination of the control instruction to access the correction, and to assist in realizing real-time and comprehensive monitoring of the working condition of the wire extrusion device based on sensing information and timely correction of defects, so as to improve the utilization rate of consumables and the extrusion quality of the wire extrusion device, and to realize more green and environmentally friendly waste recycling work.

[0175] As an optional embodiment, the control module determines the specific manner of the control instruction of at least one device component of the target wire extrusion device according to the working defect condition and the corresponding relationship between the preset condition and the control parameter strategy, comprising:

[0176] According to the preset corresponding relationship between the working defect condition and the device component, at least one defective device component corresponding to the working defect condition and the corresponding working adjustment parameter are determined;

[0177] A control instruction corresponding to the defective device component is generated, which includes the working adjustment parameter;

[0178] And / or,

[0179] For each defect in the working defect condition, the corresponding associated device component of the defect is determined according to the preset corresponding relationship between the working defect condition and the device component;

[0180] The objective function is set to be the minimum number of control instructions in the control instruction combination;

[0181] The constraint condition comprises:

[0182] The possible influence device components corresponding to all control instructions in the control instruction combination are included in the union set of all associated device components corresponding to the working defect condition; optionally, the possible influence device components are obtained by inputting the control instruction into the trained component influence prediction neural network;

[0183] The working defect condition is included in the union set of defect solution effects corresponding to all control instructions in the control instruction combination; optionally, the defect solution effect is obtained according to the corresponding relationship between the control effect and the preset control effect and defect solution effect; the control effect is obtained by inputting the control instruction into the trained control effect prediction algorithm model;

[0184] Based on a dynamic programming algorithm, iteration calculation is performed according to a target function and a constraint condition to obtain an optimal control instruction combination; optionally, the control instruction combination includes a control instruction of at least one device component of the target filament extrusion device; the control instruction includes one or more of a motor restart instruction, a motor acceleration instruction, an extrusion head control instruction, a heating control instruction, an extrusion component control instruction, a gear control instruction, and a spool motor control instruction.

[0185] It can be seen that through the above optional embodiments, the specific scheme of the control instruction determination is limited, wherein the scheme determined directly according to the corresponding relationship can directly generate the corresponding control instruction in the case of less defects, and the scheme based on the dynamic programming algorithm can obviously realize the effect of the least instruction control while ensuring the defect correction, so as to improve the control efficiency, realize real-time and comprehensive monitoring of the working condition of the filament extrusion device based on the sensing information, and timely correct defects, so as to improve the utilization rate of consumables and the extrusion quality of the filament extrusion device, and realize more green and environmentally friendly waste recycling work.

[0186] Embodiment three

[0187] Please refer to Figure 3 , Figure 3 It is another kind of filament extrusion control system based on sensing feedback disclosed by the embodiments of the present application. Figure 3 The described filament extrusion control system based on sensing feedback is applied in a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 3 shown, the filament extrusion control system based on sensing feedback can include:

[0188] a memory 301 storing executable program codes;

[0189] a processor 302 coupled with the memory 301;

[0190] The processor 302 calls the executable program codes stored in the memory 301, and is used for executing the steps of the filament extrusion control method based on sensing feedback described in embodiment one.

[0191] Embodiment four

[0192] The embodiments of the present application disclose a computer readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the filament extrusion control method based on sensing feedback described in embodiment one.

[0193] Embodiment five

[0194] The computer program product includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the method for controlling the filament extrusion based on the sensing feedback described in Embodiment I.

[0195] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in which they are recited in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily have to be performed in the specific order described or in sequential order, but can be performed in other orders or concurrently.

[0196] The systems, apparatuses, modules or units illustrated by the above embodiments can be specifically implemented by a computer chip or entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer may, for example, be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0197] For the convenience of description, the above apparatus is described as various units divided by functions when described. Of course, the functions of each unit can be implemented in the same or more software and / or hardware when implementing the present specification.

[0198] Those skilled in the art will understand that the embodiments of the present specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0199] The present specification is described with reference to flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a machine that implements the functions described in the flowcharts and / or block diagrams.Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the function specified in the flow or flows and / or blocks.

[0200] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow or flows and / or blocks. Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the function specified in the flow or flows and / or blocks.

[0201] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow or flows and / or blocks. Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the function specified in the flow or flows and / or blocks.

[0202] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0203] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, and / or non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory. The memory is an example of computer-readable media.

[0204] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0205] It should also be noted that the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without further constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0206] The specification can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. The specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0207] The various embodiments in the specification are described in progressive manner, and the same or similar parts between the various embodiments can be mutually referred to, and each embodiment focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.

[0208] Finally, it should be noted that the disclosed method and system for controlling the extrusion of filaments based on sensing feedback are only the preferred embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones. Such modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of filament extrusion control based on sensory feedback, characterized in that, The method comprises: acquiring, by a sensor, a plurality of region sensing information of a target filament extrusion device while the target filament extrusion device is working; the region sensing information is sensing information acquired by a sensor device arranged in different component regions of the target filament extrusion device; the component regions are a driving motor region, a hopper region, a discharge port region, a gear and cycloid region, or a wire material winding region; the sensing information comprises one or a combination of multiple types of information including image information, sound information, temperature information, and infrared distance measuring information; calculating, according to the plurality of region sensing information, a plurality of link sensing information corresponding to a plurality of working links of the target filament extrusion device, comprising: for each region sensing information, determining the component region and the information type corresponding to the region sensing information; the information type is image information, sound information, temperature information, or infrared distance measuring information; determining, according to the component region and the information type, a link prediction model corresponding to the region sensing information from a plurality of candidate prediction models; inputting the region sensing information into the link prediction model to obtain a working link corresponding to the region sensing information; determining, for each working link of the target filament extrusion device, all the region sensing information corresponding to the working link as link sensing information corresponding to the working link; determining, according to the link sensing information and a preset correspondence between sensing information and defects, a working defect condition corresponding to the target filament extrusion device; determining, according to the working defect condition and a preset correspondence between conditions and control parameter strategies, a control instruction for at least one device component of the target filament extrusion device; the control instruction is used to control the corresponding device component to reduce or solve the working defect condition.

2. The sensor feedback based filament extrusion control method of claim 1, wherein, The method comprises: for each candidate prediction model, determining all component region labels in a training data set corresponding to the prediction model to obtain a training component label set; calculating a first similarity parameter between the training component label set and the component region; determining data types of all input data in a historical prediction record corresponding to the prediction model to obtain a historical data type set; calculating a second similarity parameter between the historical data type set and the information type; calculating a product of the first similarity parameter and the second similarity parameter to obtain a model priority parameter corresponding to the prediction model; determining, as the link prediction model corresponding to the region sensing information, the prediction model with the highest model priority parameter; the link prediction model is obtained by training a training data set comprising a plurality of training component region sensing information and corresponding working link labels.

3. The sensor feedback based filament extrusion control method of claim 1, wherein, The working link is a heating consumable link, an extruding consumable link, an extrusion molding link, a gear and disc wire link, or a wire material winding link.

4. The sensor feedback based filament extrusion control method of claim 3, wherein, The method comprises: For each of the work links, input the link sensor information corresponding to the work link into the defect prediction neural network corresponding to the work link to obtain a plurality of predicted defects corresponding to the work link; the defect prediction neural network is trained by a training data set including training link sensor information and corresponding work defect labels of a plurality of the work links; For any two of the work links in adjacent positions in the preset work link sequence, calculate the intersection between all the predicted defects corresponding to the two work links to obtain an intersection defect set corresponding to the two work links; the work link sequence is in turn a heating consumable link, an extrusion consumable link, an extrusion molding link, a gear disc wire link, and a wire material winding link; According to the preset continuous link and the corresponding relationship between the influence defects, determine the influenceable defect set corresponding to the two work links; Calculate the intersection of the intersection defect set and the influenceable defect set to obtain the screened defects corresponding to the two work links; Determine the screened defects corresponding to all the work links as the work defect situation corresponding to the target wire extrusion equipment.

5. The sensor feedback based filament extrusion control method of claim 1, wherein, The work defect situation includes one or more combinations of motor defects, heating temperature defects, insufficient consumable extrusion defects, excessive consumable impurity defects, consumable blockage defects, gear failure defects, gear disc wire speed defects, and wire material winding speed defects.

6. The sensor feedback based filament extrusion control method of claim 5, wherein, The control instructions of at least one device component of the target wire extrusion equipment according to the work defect situation and the corresponding relationship between the preset situation and the control parameter strategy include: According to the preset corresponding relationship between the work defect situation and the device component, determine at least one defective device component corresponding to the work defect situation and the corresponding work adjustment parameter; Generate the control instructions corresponding to the defective device component, which include the work adjustment parameter; And / or, For each defect in the work defect situation, determine the associated device component corresponding to the defect according to the preset corresponding relationship between the work defect situation and the device component; Set the target function to be the minimum number of control instructions in the control instruction combination; The restriction conditions include: The union of all possible influence device components corresponding to all control instructions in the control instruction combination includes all associated device components corresponding to the work defect situation; the possible influence device components are obtained by inputting the control instructions into the trained component influence prediction neural network; The union of all defect solution effects corresponding to all control instructions in the control instruction combination includes the work defect situation; the defect solution effect is obtained according to the corresponding relationship between the control effect and the defect solution effect; the control effect is obtained by inputting the control instructions into the trained control effect prediction algorithm model; Based on a dynamic programming algorithm, iterative calculation is performed according to the target function and the constraint condition to obtain an optimal control instruction combination; the control instruction combination includes control instructions of at least one device component of the target filament extrusion device; the control instructions include one or more of a motor restart instruction, a motor acceleration instruction, an extrusion head control instruction, a heating control instruction, an extrusion component control instruction, a gear control instruction, and a wire motor control instruction.

7. A sensor feedback based filament extrusion control system, characterized by, The system comprises: An acquisition module is configured to acquire, when the target filament extrusion device is working, a plurality of region sensing information of the target filament extrusion device through a sensor; the region sensing information is sensing information acquired by a sensor device arranged in a different component region of the target filament extrusion device; the component region is a driving motor region, a hopper region, a discharge port region, a gear and cycloid region, or a wire material winding region; the sensing information includes one or more combinations of image information, sound information, temperature information, and infrared distance measuring information; A calculation module is configured to calculate, according to the plurality of region sensing information, a plurality of link sensing information corresponding to a plurality of working links of the target filament extrusion device, including: For each region sensing information, determine the component region and the information type corresponding to the region sensing information; the information type is image information, sound information, temperature information, or infrared distance measuring information; According to the component region and the information type, determine a link prediction model corresponding to the region sensing information from a plurality of candidate prediction models; Input the region sensing information into the link prediction model to obtain a working link corresponding to the region sensing information; Determine all the region sensing information corresponding to each working link of the target filament extrusion device as the link sensing information corresponding to the working link; A determination module is configured to determine, according to the link sensing information and a preset correspondence between sensing information and defects, a working defect condition corresponding to the target filament extrusion device; A control module is configured to determine, according to the working defect condition and a preset correspondence between conditions and control parameter strategies, a control instruction of at least one device component of the target filament extrusion device; the control instruction is used to control the corresponding device component to reduce or solve the working defect condition.

8. A sensor feedback based filament extrusion control system, characterized by, The system comprises: A memory storing executable program code; A processor coupled to the memory; The processor invokes the executable program code stored in the memory to execute the filament extrusion control method based on sensing feedback according to any one of claims 1-6.

Images