Stirring machine operation method and system based on pulse speed change and timing control

Abstract

The invention relates to the technical field of intelligent control, and discloses a stirrer operation method and system based on pulse speed change and timing control, and the method comprises the steps: carrying out the object feature recognition of a material warehousing image sequence, and obtaining a material information sequence set; performing first-stage stirring operation on the mixture according to a timing control strategy to obtain a first stirring result; acquiring material flow field information in the process of the first-stage stirring operation; performing component identification on the material information sequence set to obtain component information, and retrieving a pre-constructed stirring database according to the component information to obtain an additive set; generating a target stirring strategy by using a pre-trained adaptive stirring model according to the material flow field information and the additive set; and controlling the first stirring result and the additive set to perform second-stage stirring operation according to the target stirring strategy by using a pre-constructed pulse controller to obtain a target mixture. According to the invention, the uniformity of stirred materials can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control, and in particular to a mixer operation method and system based on pulse variable speed and timing control. BACKGROUND

[0002] Mixing is an important way to generate materials, involving various aspects such as chemical industry, food, and construction. Today's mixing methods mostly use mixers to replace manual mixing operations, improving mixing speed and efficiency, and saving manpower. However, different mixtures have different mixing rules, and the mixing rules of the mixer are subjectively configured by manpower. When the material information is incorrect, or the mixing rule is incorrectly configured, it will result in reduced mixing effect, causing hidden dangers for the use of subsequent mixed materials. SUMMARY

[0003] The present application provides a mixer operation method based on pulse variable speed and timing control, which mainly aims to improve the uniformity of the mixed material.

[0004] To achieve the above purpose, the present application provides a mixer operation method based on pulse variable speed and timing control, which comprises:

[0005] When it is detected that the user adds material to the pre-constructed mixing bin, the material bin image sequence is obtained;

[0006] The object feature recognition is performed on the material bin image sequence to obtain a material information sequence set;

[0007] The mixture in the mixing bin is obtained, the timing control strategy is obtained according to the material information sequence set, and the first-stage mixing operation is performed on the mixture according to the timing control strategy to obtain a first mixing result;

[0008] The particle image velocimetry device is used to obtain the material flow field information in the process of the first-stage mixing operation;

[0009] The component recognition is performed on the material information sequence set to obtain component information, and the pre-constructed mixing database is searched according to the component information to obtain an additive set;

[0010] The pre-trained adaptive mixing model is used to generate a target mixing strategy according to the material flow field information and the additive set;

[0011] The pulse controller is used to control the second-stage mixing operation of the first mixing result and the additive set according to the target mixing strategy to obtain a target mixture.

[0012] Optionally, the obtaining of the material-into-bin image sequence when detecting that the user adds material into the pre-constructed stirring bin comprises:

[0013] obtaining a bin mouth of the stirring bin;

[0014] performing infrared monitoring on the bin mouth by using a pre-constructed infrared sensor to obtain bin mouth infrared information;

[0015] calculating completeness of the bin mouth infrared information according to preset standard infrared information;

[0016] judging whether the completeness is a preset complete type;

[0017] when the completeness is the complete type, determining that the stirring bin is in a preset non-material-adding period;

[0018] when the completeness is not the complete type, determining that the stirring bin is in a preset material-adding period;

[0019] judging whether the stirring bin is in the material-adding period;

[0020] if the stirring bin is in the material-adding period, performing image monitoring on the bin mouth by using a pre-constructed high-vision sensor to obtain a material-into-bin image sequence.

[0021] Optionally, the object feature recognition on the material-into-bin image sequence to obtain a material information sequence set comprises:

[0022] performing feature extraction on the material-into-bin image sequence to obtain a material feature sequence set;

[0023] performing visibility recognition on the material feature sequence set to obtain a visibility value;

[0024] judging whether the visibility value is greater than a preset effective image visibility;

[0025] when the visibility value is less than or equal to the effective image visibility, generating dust-settling pulse information and sending the dust-settling pulse information to a pre-constructed dust settler in the stirring bin;

[0026] when the visibility value is greater than the effective image visibility, performing material type recognition on the material feature sequence set to obtain a material type sequence set;

[0027] performing, according to the material type sequence set, granularity change recognition on the material feature sequence set based on each material type to obtain a material information sequence set.

[0028] Optionally, after the object feature recognition of the material warehousing image sequence is performed to obtain a material information sequence set, the method further comprises:

[0029] determining whether the material type sequence set contains a preset dangerous object type;

[0030] When the material type sequence set contains the dangerous object type, generating a preset emergency stop information and sending the emergency stop information to a pre-constructed mixing bin control center.

[0031] Optionally, the obtaining of the timing control strategy according to the material information sequence set comprises:

[0032] obtaining mixture granularity information from the material information sequence set;

[0033] obtaining viscosity information of the mixture by using a pre-constructed viscosity sensor;

[0034] performing mean value calculation on the mixture granularity information and the viscosity information to obtain a material information value;

[0035] determining whether the material information value is greater than a preset rated material value;

[0036] When the material information value is greater than or equal to the rated material value, using a pre-constructed first mixing rule as the timing control strategy;

[0037] When the material information value is less than the rated material value, using a pre-constructed second mixing rule as the timing control strategy.

[0038] Optionally, before the generating of the target mixing strategy according to the material flow field information and the additive set by using the pre-trained adaptive mixing model, the method further comprises:

[0039] obtaining a pre-mixing strategy, obtaining a sample mixture and a sample additive;

[0040] pre-mixing the sample mixture according to the pre-mixing strategy to obtain a mixing sample intermediate product and obtaining sample material flow field information in the pre-mixing process;

[0041] obtaining an initial adaptive mixing model, and using the initial adaptive mixing model to predict a predicted sample mixing strategy of the mixing sample intermediate product and the sample additive according to the sample material flow field information;

[0042] using the predicted sample mixing strategy to perform a mixing operation on the mixing sample intermediate product and the sample additive to obtain a sample mixing result;

[0043] obtaining a uniformity score of the stirring result of the sample by using a pre-built ultrasonic densimeter, wherein the uniformity score comprises uniform and non-uniform;

[0044] obtaining an excitation function, wherein the excitation function is expressed as:

[0045] ,

[0046] wherein, the excitation function is represented by, the uniformity score is represented by, the energy consumption is represented by, the stirring time is represented by, 、 and the weight coefficient is represented by;

[0047] updating the initial adaptive stirring model according to the excitation function and a pre-built iteration process by using a pre-built Q-learning algorithm optimization strategy, to obtain an updated adaptive stirring model;

[0048] obtaining a stirring result output by the updated adaptive stirring model, to obtain a test stirring result;

[0049] performing a work test on the test stirring result according to a pre-set entity use test strategy, to obtain a mixture test result;

[0050] when the mixture test result is unqualified, replacing the initial adaptive stirring model with the updated adaptive stirring model, and returning to the process of using the initial adaptive stirring model to predict a predicted sample stirring strategy of the stirring sample intermediate product and the sample additive according to the sample material flow field information;

[0051] when the mixture test result is qualified, taking the updated adaptive stirring model as a trained adaptive stirring model.

[0052] Optionally, the using a pre-trained adaptive stirring model to generate a target stirring strategy according to the material flow field information and an additive set comprises:

[0053] performing feature extraction on the material flow field information by using the pre-trained adaptive stirring model, to obtain a flow field feature set;

[0054] performing feature extraction on the timing control strategy, to obtain a stirring action feature set;

[0055] obtaining stirring characteristics based on the mixture according to the flow field feature set and the stirring action feature set;

[0056] According to the stirring characteristics, a stirring strategy generation operation based on the excitation function is performed on the mixture to obtain a target stirring strategy.

[0057] Optionally, after the pre-trained adaptive stirring model is used to generate the target stirring strategy according to the material flow field information and the additive set, the method further includes:

[0058] Obtaining a stirring flowchart based on the target stirring strategy;

[0059] Visualizing the stirring flowchart on a display device pre-built outside the stirring bin;

[0060] Obtaining a current stirring progress and visualizing the current stirring progress on the stirring flowchart.

[0061] Optionally, the pre-built pulse controller is used to control the first stirring result and the additive set to perform a second-stage stirring operation according to the target stirring strategy, to obtain a target mixture, including:

[0062] Obtaining a real-time stirring speed of the second-stage stirring operation;

[0063] Obtaining a configuration speed at a current time point in the target stirring strategy, calculating a difference between the real-time stirring speed and the configuration speed to obtain a speed difference;

[0064] According to a pre-built speed-pulse conversion formula, a pulse difference of the speed difference is calculated, and the pulse difference is fed back to the pulse controller, wherein the speed-pulse conversion formula is expressed as:

[0065] ,

[0066] In the formula, represents a pulse frequency, represents a rotating speed, represents a number of motor encoder lines, represents a reduction ratio, represents a pulse frequency multiplication coefficient;

[0067] The pulse controller is used to stir the first stirring result and the additive set according to the target stirring strategy and the pulse difference, to obtain a target mixture.

[0068] To achieve the above object, the application further provides a stirring machine operation system based on pulse variable speed and timing control, including:

[0069] An information acquisition module is configured to acquire a material entering bin image sequence when detecting that a user adds material into a pre-built stirring bin, and perform object feature recognition on the material entering bin image sequence to obtain a material information sequence set;

[0070] A preliminary stirring module is configured to acquire a mixture in the stirring bin, acquire a timing control strategy according to the material information sequence set, and perform a first-stage stirring operation on the mixture according to the timing control strategy to obtain a first stirring result;

[0071] An adaptive stirring scheme acquisition module is configured to acquire material flow field information in the process of the first-stage stirring operation by using a pre-built particle image velocimetry device, perform component recognition on the material information sequence set to obtain component information, retrieve a pre-built stirring database according to the component information to obtain an additive set, and generate a target stirring strategy according to the material flow field information and the additive set by using a pre-trained adaptive stirring model;

[0072] An adaptive stirring module is configured to control the first stirring result and the additive set to perform a second-stage stirring operation according to the target stirring strategy by using a pre-built pulse controller to obtain a target mixture.

[0073] To solve the above problems, the present application further provides an electronic device, which comprises:

[0074] A memory is configured to store at least one instruction;

[0075] A processor is configured to execute the instruction stored in the memory to implement the above-mentioned stirring machine operation method based on pulse variable speed and timing control.

[0076] To solve the above problems, the present application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned stirring machine operation method based on pulse variable speed and timing control.

[0077] The present application is to solve the problems described in the background art, first to obtain the mixture of the information, the present application through the material into the warehouse image sequence feature recognition, can get material information sequence set, then according to the material information sequence set, select the appropriate timing control strategy as the first stage of the mixing process mixer operation steps, can get the first mixing result, and get in the process of the first stage of the mixing operation of material flow field information, wherein, the material flow field information can describe the mixture in the mixing, conveying or reaction process, its speed, pressure, concentration and other physical quantities in space and time distribution state, therefore, when the timing control strategy of mixing step is known, then can understand the relationship between the mixing step of the mixture and the flow field, thereby generating the mixing step corresponding to the better flow field through the adaptive mixing model, get the target mixing strategy, and then through the pulse controller, the target mixing strategy is implemented to the mixing process, get the target mixture. Therefore, the present application can improve the uniformity of the mixing material. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 The flowchart of the mixer operation method based on pulse variable speed and timing control provided by an embodiment of the present application is shown in the figure.

[0079] Figure 2 The function module diagram of the mixer operation system based on pulse variable speed and timing control provided by an embodiment of the present application is shown in the figure.

[0080] Figure 3 The structure diagram of the electronic device for implementing the mixer operation method based on pulse variable speed and timing control provided by an embodiment of the present application is shown in the figure.

[0081] Explanation of reference signs:

[0082] 1, electronic device; 10, processor; 11, memory; 12, bus.

[0083] The implementation of the present application, functional characteristics and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0084] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0085] The embodiment of the present application provides a mixer operation method based on pulse variable speed and timing control. The execution subject of the mixer operation method based on pulse variable speed and timing control includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the mixer operation method based on pulse variable speed and timing control can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like.

[0086] Referring to Figure 1 Fig. 1 shows a flowchart of the mixer operation method based on pulse variable speed and timing control provided by an embodiment of the present application. In the embodiment, the mixer operation method based on pulse variable speed and timing control includes the following steps.

[0087] S1, when detecting that a user adds material into a pre-constructed mixing bin, acquiring a material binning image sequence.

[0088] Wherein, the mixing bin refers to a bin body for mixing, which has stirring blades and various types of sensors inside.

[0089] Wherein, the material binning image sequence refers to a collection of images of the material taken during binning.

[0090] In detail, in the embodiment of the present application, when detecting that a user adds material into a pre-constructed mixing bin, acquiring a material binning image sequence includes:

[0091] Acquiring a bin opening of the mixing bin;

[0092] Performing infrared monitoring operation on the bin opening by using a pre-constructed infrared sensor to obtain bin opening infrared information;

[0093] According to preset standard infrared information, calculating the integrity of the bin opening infrared information;

[0094] Judging whether the integrity is a preset complete type;

[0095] When the integrity is the complete type, it is determined that the mixing bin is in a preset non-material feeding period;

[0096] When the integrity is not the complete type, it is determined that the mixing bin is in a preset material feeding period;

[0097] Judging whether the mixing bin is in the material feeding period;

[0098] If the stirring bin is in the feeding period, the high-vision sensor is used to monitor the bin opening to obtain a material entering bin image sequence.

[0099] The bin opening refers to the entrance of the material into the stirring bin.

[0100] The infrared sensor refers to a device capable of emitting and receiving infrared light.

[0101] The infrared monitoring operation refers to the process of determining whether there is an object at the bin opening through the infrared sensor. The bin opening infrared information refers to the result of the infrared monitoring operation.

[0102] The standard infrared information refers to the fact that the infrared at the bin opening is not blocked and can be irradiated from one end of the bin opening to the other end, similar to the line on a tennis racket.

[0103] The integrity refers to the proportion of the number of infrared that can be irradiated from one end of the bin opening to the other end of the bin opening to the total number of pre-arranged infrared.

[0104] The complete type refers to the fact that the number of infrared that can be irradiated from one end of the bin opening to the other end of the bin opening is the same as the total number of pre-arranged infrared.

[0105] The non-feeding period refers to a period when the user does not add material, and the feeding period refers to a period when the user adds material to the stirring bin.

[0106] The high-vision sensor refers to a camera device that can take 100 frames in one second. The image monitoring refers to the shooting process of the high-vision sensor.

[0107] Specifically, in the embodiment of the present application, first attention is paid to the bin opening of the stirring bin. The present application adds an infrared sensor at the bin opening to cover the bin opening with infrared. When material is added to the stirring bin, the material will block the infrared, causing the integrity of the bin opening infrared information to be lost. Therefore, when the integrity is the complete type, it is determined that the stirring bin is in the preset non-feeding period, and when the integrity is not the complete type, it is determined that the stirring bin is in the preset feeding period. Once the present application detects that the stirring bin is in the feeding period, the shooting function of the high-vision sensor is started to obtain a material entering bin image sequence.

[0108] S2, object feature recognition is performed on the material entering bin image sequence to obtain a material information sequence set.

[0109] The object feature recognition refers to the process of convolution, pooling, and flattening of images in a neural network. The material information sequence set refers to a collection of results of object feature recognition of each material entering bin image in the material entering bin image sequence.

[0110] In detail, in the embodiment of the present application, the object feature recognition on the material warehousing image sequence is performed to obtain a material information sequence set, which comprises:

[0111] The feature extraction is performed on the material warehousing image sequence to obtain a material feature sequence set;

[0112] The visibility recognition operation is performed on the material feature sequence set to obtain a visibility value;

[0113] It is judged whether the visibility value is greater than a preset effective image visibility;

[0114] When the visibility value is less than or equal to the effective image visibility, dust fall pulse information is generated and sent to a pre-constructed dust fall device in the stirring bin;

[0115] When the visibility value is greater than the effective image visibility, the material type recognition is performed on the material feature sequence set to obtain a material type sequence set;

[0116] According to the material type sequence set, the particle size change recognition operation based on each material type is performed on the material feature sequence set to obtain a material information sequence set.

[0117] The feature extraction refers to the process of dimension reduction extraction of information in the material warehousing image sequence by each convolution kernel in the neural network. The material feature sequence set is the feature extraction result of the material warehousing image sequence.

[0118] The visibility recognition operation refers to the operation of recognizing the concentration of dust at the bin mouth. The visibility value refers to the recognition result of judging the concentration of dust at the bin mouth.

[0119] The effective image visibility refers to the visibility value when the dust at the bin mouth makes the image recognition accuracy of the material warehousing image sequence decrease by 50%.

[0120] The dust fall pulse information refers to the electrical information for controlling the dust fall device to perform the dust fall operation. The dust fall device refers to the device for spraying water mist to realize dust fall at the bin mouth.

[0121] The material type recognition refers to the operation of recognizing the type of material. The material type sequence set refers to the result of material type recognition of the mixture, such as large particles, powder, liquid, etc.

[0122] The granularity change identification operation refers to a process of identifying the granularity of the material of each material type at different times and then sorting the granularity of the material of each material type at different times in chronological order. The material information sequence set refers to the identification result of the granularity change identification operation of the material feature sequence set.

[0123] Specifically, in the embodiment of the present application, a large amount of dust may be generated during the material entering the warehouse process. When a large number of noise points appear in the material feature sequence set, the image contrast decreases, the image recognition accuracy decreases, and the like, it indicates that the dust concentration at the warehouse opening is high, and dust reduction treatment is needed. The present application obtains the visibility value through the visibility identification operation. When the visibility value is greater than the preset effective image visibility, a dust reduction pulse information is generated to control the dust reducer to sprinkle water for dust reduction.

[0124] Specifically, in the embodiment of the present application, the material type needs to be identified to obtain a material type sequence set, and then the granularity change identification operation is performed on the material of each material type in the material type sequence set to obtain a material information sequence set.

[0125] In detail, after the object feature identification of the material entering warehouse image sequence is performed to obtain the material information sequence set, the method further comprises:

[0126] determining whether the material type sequence set contains a preset dangerous object type;

[0127] When the material type sequence set contains the dangerous object type, a preset emergency stop information is generated, and the emergency stop information is sent to a pre-constructed mixing bin control center.

[0128] The dangerous object type refers to an object type that may cause hidden troubles to safety production, such as human body parts, cloth, and the like.

[0129] The emergency stop information refers to an electric signal for controlling the mixing blade in the mixing bin to perform emergency braking.

[0130] The mixing bin control center refers to a terminal device for controlling the mixing bin.

[0131] Specifically, in the embodiment of the present application, the dangerous object types such as hands, gloves, shoes, cloth, and the like are configured, and then it is determined whether the material type sequence set contains a preset dangerous object type, which is beneficial to prevent the operating personnel from being involved in the mixer to cause a safety accident. Once the dangerous object type is detected, the emergency stop information is directly sent to the mixing bin control center to close the mixing blade in the mixing bin with the highest priority.

[0132] S3, obtaining the mixture in the stirring bin, obtaining a timing control strategy according to the material information sequence set, and performing a first-stage stirring operation on the mixture according to the timing control strategy to obtain a first stirring result.

[0133] The mixture refers to all materials in the stirring bin.

[0134] The timing control strategy refers to a control strategy of configuring the stirring speed and direction of each time period by timing.

[0135] The first-stage stirring operation refers to a stirring process of executing the timing control strategy. The first stirring result refers to the mixture after the first-stage stirring operation.

[0136] In detail, in the embodiment of the present application, the timing control strategy is obtained according to the material information sequence set, including:

[0137] The mixture granularity information is obtained from the material information sequence set.

[0138] The viscosity information of the mixture is obtained by using a pre-constructed viscosity sensor.

[0139] The material information value is obtained by performing mean value calculation on the mixture granularity information and the viscosity information.

[0140] It is judged whether the material information value is greater than a preset rated material value.

[0141] When the material information value is greater than or equal to the rated material value, the pre-constructed first stirring rule is used as the timing control strategy.

[0142] When the material information value is less than the rated material value, the pre-constructed second stirring rule is used as the timing control strategy.

[0143] The mixture granularity information refers to the set of granularity size and distribution relationship of the material of each material type.

[0144] The viscosity sensor refers to a device that can obtain the viscosity of the mixture. The viscosity information refers to the data result obtained by the viscosity sensor in the mixture.

[0145] The mean value calculation refers to the process of summing the mixture granularity information and the viscosity information and dividing by 2. In the present application, the mixture granularity information and the viscosity information are calculated by using normalized values. The material information value refers to half of the sum of the mixture granularity information and the viscosity information.

[0146] The rated material value is a material information value capable of distinguishing materials, and the material is configured as two kinds, one is a large-particle low-viscosity material such as concrete, and the other is a small-particle high-viscosity material such as a sauce material, and the rated material value can be used as a demarcation line of the two materials.

[0147] The first stirring rule is configured as low-speed pre-stirring (30 rpm, 10 seconds)→ pulse breaking (500 rpm instantaneous impact, 3 times)→ medium-speed homogenization (150 rpm, continuous stirring).

[0148] Specifically, in the embodiment of the present application, considering that different particle sizes and viscosities of the mixture need to adopt different stirring modes, therefore, the present application configures a rated material value, and the viscosity and particle size are considered in combination. When the average calculation result of the particle size information and the viscosity information of the mixture, that is, the material information value, is greater than the rated material value, the mixture is determined as a large-particle low-viscosity material. When the material information value is less than the rated material value, the mixture is determined as a small-particle high-viscosity material.

[0149] Specifically, in the embodiment of the present application, according to the stirring experience, the first stirring rule is used as a timing control strategy to stir the mixture with the material information value greater than or equal to the rated material value. The second stirring rule is used as a timing strategy to stir the mixture with the material information value less than the rated material value.

[0150] S4, using a pre-constructed particle image velocimetry device, obtaining material flow field information in the process of the first stage stirring operation.

[0151] The particle image velocimetry device refers to a device for visualizing a flow field. The material flow field information refers to the recognition result of the first stage stirring operation by the particle image velocimetry device.

[0152] The material flow field refers to the distribution state of the velocity, pressure, concentration and other physical quantities of the stirred material in the material in the stirring process in space and time.

[0153] Specifically, in the embodiment of the present application, the tracer particles are injected into the flow field by the particle image velocimetry device, the particle motion trajectory is photographed by a high-speed camera, and the visualized material flow field information is obtained.

[0154] S5, performing component recognition on the material information sequence set to obtain component information, and searching a pre-constructed stirring database according to the component information to obtain an additive set.

[0155] The component identification refers to the process of understanding the components of each material according to the shape of the material of each material type in the material information sequence set and the time-varying granularity. The component information refers to the component identification result, such as gravel, a certain type of cement, etc.

[0156] The stirring database refers to a database for storing the stirring experience of various mixtures in each stirring scene of the stirrer, which can be obtained by big data collection.

[0157] The additive set refers to the additives required by each mixture during mixing. Most of the time, the additive set only contains pure water, and in special cases, it can contain catalysts, targeting agents, thickening agents, etc.

[0158] Specifically, in the embodiment of the present application, the pre-trained neural network model can be used to analyze the material information sequence set to obtain accurate information of each material and obtain component information. Then, the present application also needs to construct the additive set under each stirring material and stirring scene through big data technology to obtain the stirring database, thereby providing data support for the generation of subsequent stirring steps.

[0159] S6, using a pre-trained adaptive stirring model, generating a target stirring strategy according to the material flow field information and the additive set.

[0160] The adaptive stirring model refers to a model that adjusts the stirring process adaptively according to different mixtures.

[0161] The target stirring strategy refers to the stirring strategy prediction result of the adaptive stirring model for the mixture, which is a stirring strategy that tries to save stirring energy consumption and stirring time under the premise of uniformity of the mixture.

[0162] In detail, in the embodiment of the present application, the pre-trained adaptive stirring model is used to generate a target stirring strategy according to the material flow field information and the additive set, which includes:

[0163] Using a pre-trained adaptive stirring model, the material flow field information is feature extracted to obtain a flow field feature set;

[0164] The timing control strategy is feature extracted to obtain a stirring action feature set;

[0165] According to the flow field feature set and the stirring action feature set, the stirring characteristics based on the mixture are obtained;

[0166] According to the stirring characteristics, the mixture is subjected to a stirring strategy generation operation based on the excitation function to obtain a target stirring strategy.

[0167] The feature extraction refers to the process of extracting information from the material flow information through a neural network using dimensionality reduction. The flow field feature set refers to the feature extraction results of the material flow field information. Similarly, the stirring characteristics refer to the feature extraction results of the mixer's mechanical characteristics and the stirring steps.

[0168] The stirring characteristics refer to the relationship between the stirring steps and the flow field characteristics when the mixture and the stirring equipment are fixed. The present invention can construct the mapping relationship between the flow field characteristic set and the stirring action characteristic set to construct the stirring characteristics.

[0169] The step of generating a stirring strategy for the mixture based on the excitation function refers to first generating a set of stirring steps that can keep the mixture uniform, and then further filtering the set of stirring steps through the excitation function.

[0170] The excitation function is a function that results in a higher score for more uniform stirring effect, lower stirring energy consumption, and shorter stirring time.

[0171] The target mixing strategy refers to a mixing method that ensures the mixture is mixed evenly while consuming less energy and requiring less mixing time.

[0172] Specifically, in this embodiment of the invention, features are first extracted from the material flow field information to obtain a flow field feature set, and then features are extracted from the timing control strategy to obtain a stirring action feature set. With the stirring equipment fixed, the correspondence between the flow field feature set and the stirring action feature set is related to the stirring characteristics of the mixture. Therefore, by constructing a mapping relationship between the flow field feature set and the stirring action feature set, the stirring characteristics of the mixture can be obtained.

[0173] Specifically, this invention can adaptively modify the material flow field information to ensure that the material flow field information leaves no dead zones, driving the mixture throughout the entire chamber to be stirred, thus achieving the "uniformity" requirement in the excitation function. Then, based on the stirring characteristics, a stirring strategy is derived, resulting in a set of stirring strategies that can stir the mixture uniformly. Finally, based on the requirements of stirring energy consumption and stirring time in the excitation function, the set of stirring strategies is filtered to obtain the target stirring strategy with relatively low energy consumption and short stirring time.

[0174] In detail, in this embodiment of the invention, before generating the target mixing strategy based on the material flow field information and the additive set using the pre-trained adaptive mixing model, the method further includes:

[0175] Obtain the pre-stirring strategy, and obtain the sample mixture and sample additives;

[0176] According to the pre-stirring strategy, the sample mixture is pre-stirred to obtain a stirred sample intermediate product, and sample material flow field information in the pre-stirring process is acquired;

[0177] An initialized adaptive stirring model is acquired, and the initialized adaptive stirring model is used to predict a predicted sample stirring strategy of the stirred sample intermediate product and the sample additive according to the sample material flow field information;

[0178] The stirred sample intermediate product and the sample additive are stirred according to the predicted sample stirring strategy to obtain a sample stirring result;

[0179] A uniformity score of the sample stirring result is acquired by using a pre-constructed ultrasonic densitometer, wherein the uniformity score includes uniformity and non-uniformity;

[0180] An excitation function is acquired, wherein the excitation function is expressed as:

[0181] ,

[0182] In the formula, The excitation function is represented by, The uniformity score is represented by, The energy consumption is represented by, The stirring time is represented by, 、 and The weight coefficient is represented by;

[0183] An initialized adaptive stirring model is acquired, and the initialized adaptive stirring model is used to predict a predicted sample stirring strategy of the stirred sample intermediate product and the sample additive according to the sample material flow field information;

[0184] An initialized adaptive stirring model is acquired, and the initialized adaptive stirring model is used to predict a predicted sample stirring strategy of the stirred sample intermediate product and the sample additive according to the sample material flow field information;

[0185] According to a preset entity use test strategy, the test stirring result is tested to obtain a mixture test result;

[0186] When the mixture test result is unqualified, the initialized adaptive stirring model is replaced by the updated adaptive stirring model, and the process of using the initialized adaptive stirring model to predict the predicted sample stirring strategy of the stirred sample intermediate product and the sample additive according to the sample material flow field information is returned;

[0187] When the mixture test result is qualified, the updated adaptive stirring model is used as a trained adaptive stirring model.

[0188] The pre-mixing strategy refers to the timing control strategy used for training. The sample mixture refers to the mixture used as the training sample. The sample additive refers to the additive set used as the training sample.

[0189] The pre-mixing is equivalent to the first-stage mixing operation described above. The mixed sample intermediate product is equivalent to the first mixing result described above. The sample material flow field information refers to the material flow field information during pre-mixing.

[0190] The initialized adaptive mixing model refers to an adaptive mixing model with untrained parameters. The predicted sample mixing strategy refers to the prediction result of the initialized adaptive mixing model for the sample mixture.

[0191] The predicted sample mixing strategy is equivalent to a timing control strategy. The sample mixing result refers to the mixing result of the mixed sample intermediate product and the sample additive under the predicted sample mixing strategy.

[0192] The ultrasonic densitometer refers to an instrument that detects the interior of an object through ultrasonic waves.

[0193] The uniformity score refers to the binary classification result of the ultrasonic densitometer detection result.

[0194] The higher the score of the excitation function, the better the effect of the predicted sample mixing strategy. The energy consumption refers to the amount of electricity consumed by the motor during mixing. The mixing time refers to the length of time the predicted sample mixing strategy is executed.

[0195] The Q-learning algorithm optimization strategy refers to a strategy that realizes dynamic decision-making through value iteration mechanism in the mixing system strategy optimization, and finally generates an optimal control strategy.

[0196] The iteration process refers to: after completing 100 mixings, automatically update the network parameters of "pulse frequency-viscosity-uniformity" in the initialized adaptive mixing model, so that the initialized adaptive mixing model evolves towards "low energy consumption, short time, and high uniformity".

[0197] The updated adaptive mixing model refers to an initialized adaptive mixing model with changed internal parameters.

[0198] The test mixing result refers to the target mixing strategy predicted by the updated adaptive mixing model for the sample mixture.

[0199] The entity uses the test strategy, which refers to a strategy that actually operates the test mixing result and tests the performance of the resulting mixture.

[0200] The mixture test result refers to a test result of a stirring product of a test stirring result in an actual application test scene.

[0201] Specifically, in the embodiment of the present application, firstly, an initial adaptive stirring model is obtained, and then a pre-stirring strategy, a sample mixture and a sample additive are obtained. Then, the initial adaptive stirring model is trained by using the pre-stirring strategy, the sample mixture and the sample additive.

[0202] In the training process, firstly, the sample mixture is pre-stirred according to the pre-stirring strategy to obtain a stirring sample intermediate product, and sample material flow field information in the pre-stirring process is obtained. Then, the initial adaptive stirring model is used to predict a predicted sample stirring strategy of the stirring sample intermediate product and the sample additive according to the sample material flow field information, and then the predicted sample stirring strategy is executed to obtain a sample stirring result. The uniformity of the sample stirring result is scored by using an ultrasonic densitometer to obtain a uniformity score, wherein the uniformity score includes uniformity and non-uniformity. The predicted sample stirring strategy with a uniformity score of uniformity is retained, and the predicted sample stirring strategy with a uniformity score of non-uniformity is deleted.

[0203] Specifically, the present application not only considers the stirring effect, but also pays attention to stirring energy consumption and stirring time. Therefore, the stirring energy consumption and the stirring time are added to the stirring effect to obtain an excitation function. The predicted sample stirring strategy can have constraints on uniformity, energy consumption and time.

[0204] Further, in order to improve the optimization efficiency of the algorithm, the Q-learning algorithm optimization strategy is used, the activation function and the iteration process of automatically updating the mapping relationship of "pulse frequency- viscosity-uniformity" every 100 times of stirring are used, the update of the initial adaptive stirring model is realized, and an updated adaptive stirring model is obtained.

[0205] After obtaining the updated adaptive stirring model, the present application can perform a test process based on an entity use test strategy on a test stirring result of the updated adaptive stirring model to obtain a mixture test result. When the hardness, wear resistance or supportability, coefficient performance in the mixture test result meet the requirements in the actual application scene, it is determined that the mixture test result is qualified. Otherwise, it is determined that the mixture test result is unqualified, and the updated adaptive stirring model needs to be updated according to the Q-learning algorithm optimization strategy.

[0206] In detail, after the pre-trained adaptive stirring model is used to generate the target stirring strategy according to the material flow field information and the additive set, the method further includes:

[0207] acquiring a stirring flowchart based on the target stirring strategy;

[0208] visualizing the stirring flowchart to a display device pre-built outside the stirring bin;

[0209] acquiring a current stirring progress and visualizing the current stirring progress to the stirring flowchart.

[0210] The visualizing refers to the step of displaying a time flowchart. The display device refers to a device capable of data display through a screen.

[0211] The current stirring progress refers to a node of the stirring process corresponding to a current timestamp.

[0212] Specifically, in the embodiment of the present application, to ensure that the staff outside the stirring bin can understand the material composition, stirring plan and stirring progress inside the stirring bin, and verify whether the information inside and outside the stirring bin corresponds in time, the present application visualizes the stirring flowchart and the current stirring progress by using a display device pre-built outside the stirring bin.

[0213] S7, using a pre-built pulse controller, controlling the first stirring result and the additive set to perform a second-stage stirring operation according to the target stirring strategy, to obtain a target mixture.

[0214] The pulse controller refers to a device for controlling the stirring work of a motor through a pulse signal.

[0215] The second-stage stirring operation refers to the execution process of the target stirring strategy. The target mixture refers to the stirring result of the first stirring result and the additive set under the target stirring strategy.

[0216] In detail, in the embodiment of the present application, the use of a pre-built pulse controller to control the first stirring result and the additive set to perform a second-stage stirring operation according to the target stirring strategy to obtain a target mixture comprises:

[0217] acquiring a real-time stirring speed of the second-stage stirring operation;

[0218] acquiring a configuration speed at a current time point in the target stirring strategy, calculating a difference between the real-time stirring speed and the configuration speed to obtain a speed difference;

[0219] calculating a pulse difference of the speed difference according to a pre-built speed-pulse conversion formula, and feeding back the pulse difference to the pulse controller, wherein the speed-pulse conversion formula is expressed as:

[0220] ,

[0221] In the formula, represents the pulse frequency, represents the rotation speed, represents the number of motor encoder lines, represents the reduction ratio, represents the pulse frequency multiplication coefficient;

[0222] The pulse controller is used to stir the first stirring result and the additive set according to the target stirring strategy and the pulse difference, so as to obtain a target mixture.

[0223] The real-time stirring speed refers to the speed of the stirring blade.

[0224] The configuration speed refers to the stirring speed corresponding to the current time point in the target stirring strategy.

[0225] The speed difference refers to the difference between the real-time stirring speed and the configuration speed, and has a direction and a size.

[0226] The speed-pulse conversion formula refers to a formula representing the relationship between the rotation speed of the stirring blade and the pulse frequency of the pulse controller. The number of motor encoder lines refers to the number of physical lines on the encoder disc, representing the number of original pulses output by the encoder per revolution. The reduction ratio refers to the ratio of the input rotation speed of the motor of the stirring blade to the output rotation speed. The pulse frequency multiplication coefficient refers to the multiple of the subdivision processing of the original pulse by the encoder signal processing circuit (such as PLC or driver), realizing the amplification of “physical line number → actual pulse number”.

[0227] Specifically, in the embodiment of the present application, in order to avoid the target stirring strategy predicted not being achieved in actual work, the real-time stirring speed of the second stage stirring operation is monitored, and the difference between the real-time stirring speed and the configuration speed in the target stirring strategy at the current time point is calculated to obtain a speed difference, which is then converted into a pulse difference and fed back to the pulse controller, so as to realize the fine adjustment of the pulse controller and ensure that the target stirring strategy can be accurately implemented, so as to obtain the desired target mixture.

[0228] The present application is to solve the problems described in the background art, first to obtain the information of the mixture, the present application can obtain the material information sequence set by feature recognition on the material warehouse image sequence, then according to the material information sequence set, select the appropriate timing control strategy as the mixer operation step of the first stage stirring process, can obtain the first stirring result, and obtain the material flow field information in the process of the first stage stirring operation, wherein the material flow field information can describe the distribution state of the velocity, pressure, concentration and other physical quantities of the mixture in the stirring, conveying or reaction process in space and time, therefore, when the stirring step of the timing control strategy is known, the relationship between the stirring step and the flow field of the mixture can be understood, so as to automatically generate the stirring step corresponding to the better flow field through the adaptive stirring model, obtain the target stirring strategy, and then implement the target stirring strategy into the stirring process through the pulse controller, obtain the target mixture. Therefore, the present application can improve the uniformity of the stirred material.

[0229] As Figure 2 shown, it is the functional module diagram of the mixer operation system based on pulse variable speed and timing control provided by an embodiment of the present application.

[0230] The mixer operation system based on pulse variable speed and timing control 100 can be installed in an electronic device. According to the realized function, the mixer operation system based on pulse variable speed and timing control 100 can include an information acquisition module 101, a preliminary stirring module 102, an adaptive stirring scheme acquisition module 103 and an adaptive stirring module 104. The modules of the present application can also be called units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0231] The information acquisition module 101 is used to acquire the material warehouse image sequence when detecting that the user adds material to the pre-constructed stirring warehouse, and to perform object feature recognition on the material warehouse image sequence to obtain a material information sequence set;

[0232] The preliminary stirring module 102 is used to acquire the mixture in the stirring warehouse, acquire a timing control strategy according to the material information sequence set, and perform a first stage stirring operation on the mixture according to the timing control strategy to obtain a first stirring result;

[0233] The adaptive stirring scheme acquisition module 103 is configured to acquire material flow field information in the first-stage stirring operation by using a pre-built particle image velocimetry device, to perform component identification on the material information sequence set to obtain component information, to search a pre-built stirring database according to the component information to obtain an additive set, and to generate a target stirring strategy according to the material flow field information and the additive set by using a pre-trained adaptive stirring model.

[0234] The adaptive stirring module 104 is configured to control the first stirring result to perform a second-stage stirring operation with the additive set according to the target stirring strategy by using a pre-built pulse controller to obtain a target mixture.

[0235] In detail, the modules in the stirring machine operation system 100 based on pulse variable speed and timing control in the embodiments of the present application adopt the same technical means as the stirring machine operation method based on pulse variable speed and timing control in the above Figure 1 , and can produce the same technical effects, which will not be described here again.

[0236] As shown in Figure 3 , it is a structural schematic diagram of an electronic device for implementing the stirring machine operation method based on pulse variable speed and timing control according to an embodiment of the present application.

[0237] The electronic device 1 can include a processor 10, a memory 11 and a bus 12, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as a stirring machine operation method program based on pulse variable speed and timing control.

[0238] The memory 11 includes at least one type of readable storage medium, such as a flash memory, a mobile hard disk, a multimedia card, a card-type memory (such as an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 includes an internal storage unit of the electronic device 1 and also includes an external storage device. The memory 11 can be used not only to store application software and various data installed in the electronic device 1, such as the code of the stirring machine operation method program based on pulse variable speed and timing control, but also to temporarily store data that has been output or will be output.

[0239] The processor 10 can be composed of integrated circuits in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor 10 is the control core of the electronic device, connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as a stirring machine operation method program based on pulse variable speed and timing control, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0240] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11, the at least one processor 10, etc.

[0241] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0242] For example, although not shown, the electronic device 1 can also include a power supply (such as a battery) for powering various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so as to realize functions such as charge management, discharge management, and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0243] Further, the electronic device 1 can further comprise a network interface, which can optionally comprise a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0244] Optionally, the electronic device 1 can further comprise a user interface, which can be a display, an input unit (such as a keyboard), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 1 and to display a visualized user interface.

[0245] The pulse variable speed and timing control based blender operation method program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which, when running in the processor 10, can achieve:

[0246] When it is detected that a user adds material to a pre-constructed mixing bin, a material binning image sequence is obtained;

[0247] Object feature recognition is performed on the material binning image sequence to obtain a material information sequence set;

[0248] The mixture in the mixing bin is obtained, a timing control strategy is obtained according to the material information sequence set, and a first-stage mixing operation is performed on the mixture according to the timing control strategy to obtain a first mixing result;

[0249] A pre-constructed particle image velocimetry device is used to obtain material flow field information in the process of the first-stage mixing operation;

[0250] Component recognition is performed on the material information sequence set to obtain component information, and a pre-constructed mixing database is searched according to the component information to obtain an additive set;

[0251] A pre-trained adaptive mixing model is used to generate a target mixing strategy according to the material flow field information and the additive set;

[0252] A pre-constructed pulse controller is used to control a second-stage mixing operation of the first mixing result and the additive set according to the target mixing strategy to obtain a target mixture.

[0253] Specifically, the processor 10 can refer to the specific implementation method of the above instructions Figures 1 to 3 The description of the related steps in the corresponding embodiments will not be repeated here.

[0254] Further, the modules / units integrated in the electronic device 1, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0255] The application also provides a computer readable storage medium, the readable storage medium stores a computer program, the computer program can realize the following when being executed by the processor of the electronic device:

[0256] When it is detected that the user adds material into the pre-constructed mixing bin, an image sequence of material entering the bin is acquired;

[0257] Object feature recognition is performed on the image sequence of material entering the bin to obtain a material information sequence set;

[0258] The mixture in the mixing bin is acquired, a timing control strategy is acquired according to the material information sequence set, and a first-stage mixing operation is performed on the mixture according to the timing control strategy to obtain a first mixing result;

[0259] A particle image velocimetry device pre-constructed is used to acquire material flow field information in the process of the first-stage mixing operation;

[0260] Composition recognition is performed on the material information sequence set to obtain composition information, and a pre-constructed mixing database is searched according to the composition information to obtain an additive set;

[0261] A pre-trained adaptive mixing model is used to generate a target mixing strategy according to the material flow field information and the additive set;

[0262] A pre-constructed pulse controller is used to control the first mixing result and the additive set to perform a second-stage mixing operation according to the target mixing strategy to obtain a target mixture.

[0263] In the several embodiments provided in the application, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. Actual implementation can have another division way.

[0264] The modules described as separate components can or can not be physically separate, and the components shown as modules can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0265] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0266] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0267] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method of operating a mixer based on pulse speed variation and timing control, characterized by, The method comprises: When detecting that a user adds material into a pre-constructed mixing bin, an image sequence of the material entering the bin is acquired; Object feature recognition is performed on the image sequence of the material entering the bin to obtain a material information sequence set; The mixture in the mixing bin is acquired, a timing control strategy is acquired according to the material information sequence set, and a first-stage mixing operation is performed on the mixture according to the timing control strategy to obtain a first mixing result; A particle image velocimetry device is used to acquire material flow field information in the process of the first-stage mixing operation; Composition recognition is performed on the material information sequence set to obtain composition information, and a pre-constructed mixing database is searched according to the composition information to obtain an additive set; A pre-trained adaptive mixing model is used to generate a target mixing strategy according to the material flow field information and the additive set; A pre-constructed pulse controller is used to control the first mixing result and the additive set to perform a second-stage mixing operation according to the target mixing strategy to obtain a target mixture.

2. The impulsive speed variation and timing control based blender operation method as claimed in claim 1, wherein, When detecting that a user adds material into a pre-constructed mixing bin, an image sequence of the material entering the bin is acquired, comprising: Acquiring a bin opening of the mixing bin; Performing infrared monitoring on the bin opening using a pre-constructed infrared sensor to obtain bin opening infrared information; According to a preset standard infrared information, the integrity of the bin opening infrared information is calculated; Determine whether the integrity is a preset complete type; When the integrity is the complete type, it is determined that the mixing bin is in a preset non-material feeding period; When the integrity is not the complete type, it is determined that the mixing bin is in a preset material feeding period; Determine whether the mixing bin is in the material feeding period; If the mixing bin is in the material feeding period, a pre-constructed high-vision sensor is used to monitor the bin opening to obtain an image sequence of the material entering the bin.

3. The impulsive speed variation and timing control based blender operation method as claimed in claim 2, wherein, The object feature recognition on the image sequence of the material entering the bin to obtain a material information sequence set comprises: Feature extraction is performed on the image sequence of the material entering the bin to obtain a material feature sequence set; Visibility recognition is performed on the material feature sequence set to obtain a visibility value; Determine whether the visibility value is greater than a preset effective image visibility; When the visibility value is less than or equal to the effective image visibility, dust reduction pulse information is generated and sent to a pre-constructed dust reducer in the mixing bin; When the visibility value is greater than the effective image visibility, material type recognition is performed on the material feature sequence set to obtain a material type sequence set; According to the material type sequence set, a particle size change recognition operation based on each material type is performed on the material feature sequence set to obtain a material information sequence set.

4. The impulsive speed varying and timing control based blender operation method as claimed in claim 3, wherein, After the object feature recognition on the image sequence of the material entering the bin to obtain a material information sequence set, the method further comprises: Determine whether the material type sequence set contains a preset dangerous object type; When the dangerous object type is contained in the material type sequence set, a preset emergency stop information is generated, and the emergency stop information is sent to a pre-constructed mixing bin control center.

5. The impulsive speed variation and timing control based blender operation method as claimed in claim 4, wherein, The obtaining of the timing control strategy according to the material information sequence set comprises: acquiring mixture granularity information from the material information sequence set; acquiring viscosity information of the mixture by using a pre-constructed viscosity sensor; performing mean value calculation on the mixture granularity information and the viscosity information to obtain a material information value; judging whether the material information value is greater than a preset rated material value; when the material information value is greater than or equal to the rated material value, using a pre-constructed first mixing rule as the timing control strategy; when the material information value is less than the rated material value, using a pre-constructed second mixing rule as the timing control strategy.

6. The impulsive speed varying and timing control based blender operation method as claimed in claim 5, wherein, Before the generating of the target mixing strategy according to the material flow field information and the additive set by using the pre-trained adaptive mixing model, the method further comprises: acquiring a pre-mixing strategy, and acquiring a sample mixture and a sample additive; pre-mixing the sample mixture according to the pre-mixing strategy to obtain a mixing sample intermediate product, and acquiring sample material flow field information in a pre-mixing process; acquiring an initial adaptive mixing model, and predicting a predicted sample mixing strategy of the mixing sample intermediate product and the sample additive according to the sample material flow field information by using the initial adaptive mixing model; performing a mixing operation on the mixing sample intermediate product and the sample additive by using the predicted sample mixing strategy to obtain a sample mixing result; acquiring a uniformity score of the sample mixing result by using a pre-constructed ultrasonic density meter, wherein the uniformity score includes uniformity and non-uniformity; acquiring an excitation function, wherein the excitation function is expressed as: ， wherein denotes the excitation function, denotes the homogeneity score, denotes the energy consumption, denotes the stirring time, , and denotes the weight coefficient; updating the initial adaptive mixing model according to the excitation function and a pre-constructed iteration process by using a pre-constructed Q-learning algorithm optimization strategy to obtain an updated adaptive mixing model; acquiring a mixing result output by the updated adaptive mixing model to obtain a test mixing result; performing a work test on the test mixing result according to a preset entity use test strategy to obtain a mixture test result; when the mixture test result is unqualified, replacing the initial adaptive mixing model with the updated adaptive mixing model, and returning to the process of predicting the predicted sample mixing strategy of the mixing sample intermediate product and the sample additive according to the sample material flow field information by using the initial adaptive mixing model; when the mixture test result is qualified, taking the updated adaptive mixing model as a trained adaptive mixing model.

7. The impulsive speed variation and timing control based blender operation method as claimed in claim 6, wherein, The generating of the target mixing strategy according to the material flow field information and the additive set by using the pre-trained adaptive mixing model comprises: performing feature extraction on the material flow field information by using the pre-trained adaptive mixing model to obtain a flow field feature set; performing feature extraction on the timing control strategy to obtain a mixing action feature set; According to the flow field feature set and the stirring action feature set, a stirring characteristic based on the mixture is obtained; According to the stirring characteristic, a stirring strategy generation operation based on the excitation function is performed on the mixture to obtain a target stirring strategy.

8. The impulsive speed variation and timing control based blender operation method as claimed in claim 7, wherein, After the pre-trained adaptive stirring model is used to generate the target stirring strategy according to the material flow field information and the additive set, the method further comprises: obtaining a stirring flowchart based on the target stirring strategy; visualizing the stirring flowchart to a display device pre-built outside the stirring bin; obtaining a current stirring progress and visualizing the current stirring progress to the stirring flowchart.

9. The impulsive speed variation and timing control based blender operation method as claimed in claim 8, wherein, According to the target stirring strategy, the pre-built pulse controller is used to control the first stirring result and the additive set to perform a second-stage stirring operation to obtain a target mixture, comprising: obtaining a real-time stirring speed of the second-stage stirring operation; obtaining a configuration speed at a current time point in the target stirring strategy, calculating a difference between the real-time stirring speed and the configuration speed to obtain a speed difference; According to a pre-built speed-pulse conversion formula, a pulse difference of the speed difference is calculated, and the pulse difference is fed back to the pulse controller, wherein the speed-pulse conversion formula is expressed as: ， wherein, represents the pulse frequency, represents the rotational speed, represents the number of motor encoder lines, represents the reduction ratio, represents the pulse multiplication factor; Using the pulse controller, the first stirring result and the additive set are stirred according to the target stirring strategy and the pulse difference to obtain a target mixture.

10. A mixer operating system based on pulse speed variation and timing control, characterized by, The system comprises: An information acquisition module is configured to acquire a material entering bin image sequence when detecting that a user adds material to a pre-built stirring bin, and perform object feature recognition on the material entering bin image sequence to obtain a material information sequence set; A preliminary stirring module is configured to acquire a mixture in the stirring bin, acquire a timing control strategy according to the material information sequence set, and perform a first-stage stirring operation on the mixture according to the timing control strategy to obtain a first stirring result; An adaptive stirring scheme acquisition module is configured to acquire material flow field information in the process of the first-stage stirring operation by using a pre-built particle image velocimetry device, perform component recognition on the material information sequence set to obtain component information, retrieve a pre-built stirring database according to the component information to obtain an additive set, and generate a target stirring strategy according to the material flow field information and the additive set by using a pre-trained adaptive stirring model; An adaptive stirring module is configured to control the first stirring result and the additive set to perform a second-stage stirring operation according to the target stirring strategy by using a pre-built pulse controller to obtain a target mixture.

Images