A material type identification system and method applied to the automated operation of a sand mill

Abstract

The present invention provides a material type identification system and method applied to the automated operation of a sand mill. Among them, the system includes: a material type identification subsystem for obtaining the material type identification result of the material to be ground on the automated operation production line of the sand mill; a grinding strategy retrieval subsystem for retrieving a grinding strategy library according to the material type identification result and determining the grinding strategy for the identified material; an automated grinding subsystem for controlling the sand mill to perform automated grinding on the identified material based on the grinding strategy. The material type identification system and method applied to the automated operation of a sand mill according to the present invention obtain the material type identification result of the material to be ground, retrieve the grinding strategy library according to the material type identification result, determine the grinding strategy for the identified material, and automatically control the grinding of the sand mill based on the grinding strategy, realizing the corresponding transportation and coordinated grinding control of the identified material to different types of sand mills, and greatly improving the working efficiency of the sand mill.

Description

Technical Field

[0001] The present invention relates to the technical field of sand mills, and particularly to a material type identification system and method applied to the automated operation of sand mills. Background Art

[0002] A sand mill is a high-efficiency wet ultra-fine grinding and dispersing device. During the grinding process, different types of materials have different physical and chemical properties. Traditional sand mills often rely on manual adjustment of control parameters according to the material type (for example: materials with higher hardness require greater grinding force and longer time, while softer materials can be processed quickly). However, manual operation has the risk of misoperation, and the workload of operators is also heavy, resulting in low work efficiency.

[0003] In view of this, there is an urgent need for a material type identification system and method applied to the automated operation of sand mills to at least solve the above deficiencies. Summary of the Invention

[0004] One of the objectives of the present invention is to provide a material type identification system and method applied to the automated operation of sand mills, obtain the material type identification result of the material to be ground, retrieve the grinding strategy library according to the material type identification result, determine the grinding strategy for the identified material, and automatically control the grinding of the sand mill based on the grinding strategy, realizing the corresponding transportation and collaborative grinding control of the identified material to different types of sand mills, and greatly improving the work efficiency of the sand mill.

[0005] A material type identification system applied to the automated operation of a sand mill provided by an embodiment of the present invention includes:

[0006] A material type identification subsystem for obtaining the material type identification result of the material to be ground on the automated operation production line of the sand mill;

[0007] A grinding strategy retrieval subsystem for retrieving the grinding strategy library according to the material type identification result and determining the grinding strategy for the identified material;

[0008] An automated grinding subsystem for automatically controlling the sand mill to grind the identified material based on the grinding strategy.

[0009] Preferably, the material type identification subsystem obtains the material type identification result of the material to be ground on the automated operation production line of the sand mill and performs the following operations:

[0010] Based on machine vision technology, obtain the captured image of the material to be ground and extract the image features, and determine the material type identification result according to the image features;

[0011] And / or,

[0012] Based on spectral analysis technology, analyze the spectral characteristic information of the material to be ground, and then determine the material type recognition result according to the spectral characteristic information;

[0013] And / or,

[0014] Based on machine learning algorithms and combined with historical data, train a material type recognition model, and then determine the material type recognition result based on real-time sensor data and the material type recognition model.

[0015] Preferably, the grinding strategy retrieval subsystem retrieves the grinding strategy library according to the material type recognition result, determines the grinding strategy for the recognized material, and performs the following operations:

[0016] According to the material type recognition result, determine the type of sand mill suitable for grinding the recognized material;

[0017] Obtain the grinding strategy library of the sand mill of the sand mill type;

[0018] Characterize the material type recognition result to obtain a set of recognition result characteristic values;

[0019] According to the set of recognition result characteristic values and the grinding strategy library, determine the grinding strategy.

[0020] Preferably, the grinding strategy retrieval subsystem obtains the grinding strategy library of the sand mill of the sand mill type and performs the following operations:

[0021] Obtain the operation records of the operators of the sand mill of the sand mill type;

[0022] Analyze the operation records, obtain the manual recognition result and grinding parameters of the manipulated material, characterize the manual recognition result, obtain the first set of manipulated material recognition result characteristic values, and associate them with the grinding parameters to obtain the first associated item;

[0023] Perform machine learning on the manual recognition result and grinding parameters of the same manipulated material to obtain a grinding parameter determination model;

[0024] According to the manual recognition result, determine the missing recognition result;

[0025] Input the missing recognition result into the grinding parameter determination model, obtain the missing grinding parameters output by the grinding parameter determination model, characterize the missing recognition result, obtain the second set of manipulated material recognition result characteristic values, and associate them with the missing grinding parameters to obtain the second associated item;

[0026] Integrate the first and second associated items of all manipulated materials to obtain the grinding strategy library of the sand mill of the sand mill type.

[0027] An application of the material type recognition system for sand mill automated operation provided by an embodiment of the present invention further includes:

[0028] A parity check subsystem is used to obtain the sampled material after the identified material is ground, perform a grinding precision check on the sampled material, and perform a grinding medium detection when the grinding precision check fails.

[0029] Preferably, when the grinding precision check fails, the parity check subsystem performs a grinding medium detection and executes the following operations:

[0030] Obtain the real-time triboelectric signal between the friction pairs;

[0031] Obtain the initial triboelectric signal of the friction pairs;

[0032] Calculate the change in the friction coefficient based on the difference in the triboelectric signals between the real-time triboelectric signal and the initial triboelectric signal;

[0033] If the change in the friction coefficient reaches a preset degree of change, use the corresponding grinding medium as the determined grinding medium and obtain the usage duration of the determined grinding medium;

[0034] Judge the rationality of the usage duration of the determined grinding medium. If it is unreasonable, reset the cleaning time setting parameter;

[0035] Among them, judging the rationality of the usage duration of the determined grinding medium. If it is unreasonable, resetting the cleaning time setting parameter includes:

[0036] Obtain the standard usage duration of the determined grinding medium;

[0037] If the difference in duration between the standard usage duration and the usage duration is greater than or equal to a preset duration difference threshold, obtain the cleaning time setting parameter;

[0038] Obtain the comparison table of the reduction values of the cleaning time setting parameters;

[0039] Determine the target cleaning time setting parameter after reduction according to the duration difference and the comparison table of the reduction values of the cleaning time setting parameters;

[0040] After notifying the staff to replace the determined grinding medium, apply the target cleaning time setting parameter.

[0041] A method for identifying the type of material applied to the automatic operation of a sand mill provided by an embodiment of the present invention includes:

[0042] Step 1: Obtain the identification result of the type of material of the material to be ground on the automatic operation pipeline of the sand mill;

[0043] Step 2: Retrieve the grinding strategy library according to the material type identification result to determine the grinding strategy of the identified material;

[0044] Step 3: Based on the grinding strategy, control the sand mill to automatically grind the identified material.

[0045] Preferably, obtaining the material type recognition result of the material to be ground on the automated operation pipeline of the sand mill includes:

[0046] Based on machine vision technology, obtaining the captured image of the material to be ground and extracting the image features, and determining the material type recognition result according to the image features;

[0047] And / or,

[0048] Based on spectral analysis technology, analyzing the spectral characteristic information of the material to be ground, and then determining the material type recognition result according to the spectral characteristic information;

[0049] And / or,

[0050] Based on machine learning algorithms, training a material type recognition model in combination with historical data, and then determining the material type recognition result based on real-time sensor data and the material type recognition model.

[0051] Preferably, according to the material type recognition result, retrieving the grinding strategy library to determine the grinding strategy for the recognized material, including:

[0052] According to the material type recognition result, determining the type of sand mill suitable for grinding the recognized material;

[0053] Obtaining the grinding strategy library of the sand mill of the sand mill type;

[0054] Characterizing the material type recognition result to obtain a set of recognition result feature values;

[0055] Determining the grinding strategy according to the set of recognition result feature values and the grinding strategy library.

[0056] The material type recognition method applied to the automated operation of the sand mill provided by the embodiment of the present invention further includes:

[0057] Obtaining the sampled material after grinding the recognized material, performing a grinding accuracy check on the sampled material, and when the grinding accuracy check fails, performing a grinding medium detection.

[0058] Preferably, when the grinding accuracy check fails, performing a grinding medium detection includes:

[0059] Obtaining the real-time triboelectric signal between the friction pairs;

[0060] Obtaining the initial triboelectric signal of the friction pair;

[0061] Calculating the change in the friction coefficient according to the electrical signal difference between the real-time triboelectric signal and the initial triboelectric signal;

[0062] If the change in the friction coefficient reaches a preset degree of change, regarding the corresponding grinding medium as the determined grinding medium and obtaining the usage duration of the determined grinding medium;

[0063] Judge the rationality of the service life of the grinding medium. If it is unreasonable, reset the cleaning time setting parameter;

[0064] Among them, judging the rationality of the service life of the grinding medium. If it is unreasonable, reset the cleaning time setting parameter, including:

[0065] Obtain the standard service life of the judgment grinding medium;

[0066] If the time difference between the standard service life and the service life is greater than or equal to the preset time difference threshold, obtain the cleaning time setting parameter;

[0067] Obtain the cleaning time setting parameter downward adjustment value comparison table;

[0068] According to the time difference and the cleaning time setting parameter downward adjustment value comparison table, determine the target cleaning time setting parameter after downward adjustment;

[0069] After notifying the staff to replace the fixed grinding medium, apply the target cleaning time setting parameter.

[0070] The beneficial effects of the present invention are:

[0071] The present invention obtains the material type recognition result of the material to be ground, retrieves the grinding strategy library according to the material type recognition result, determines the grinding strategy of the recognized material, and automatically controls the grinding of the sand mill based on the grinding strategy, realizing the corresponding transportation and collaborative grinding control of the recognized material to different types of sand mills, greatly improving the working efficiency of the sand mill.

[0072] Other features and advantages of the present invention will be described in the following description, and in part will be obvious from the description, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0073] The following through the drawings and embodiments, the technical solutions of the present invention will be further described in detail. Description of the Drawings

[0074] The drawings are used to provide a further understanding of the present invention, and constitute a part of the description, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0075] Figure 1 It is a schematic diagram of a material type recognition system applied to the automated operation of a sand mill in an embodiment of the present invention;

[0076] Figure 2 It is a schematic diagram of a material type recognition method applied to the automated operation of a sand mill in an embodiment of the present invention. Specific Embodiment

[0077] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0078] An embodiment of the present invention provides a material type recognition system applied to the automated operation of a sand mill, as Figure 1 shown, including:

[0079] A material type recognition subsystem 1, which is used to obtain the material type recognition result of the material to be ground on the automated operation pipeline of the sand mill; among them, the automated operation pipeline of the sand mill includes sand mills of various types, such as: basket sand mills, horizontal disk sand mills, and ultra-fine rod pin sand mills, etc.; the material to be ground is: the material that needs to be ground, such as: coatings, inks, and pigments, etc.; the material type recognition result is: the material type and material characteristic information of the material to be ground (such as: chemical composition, physical characteristics (such as particle size, density, viscosity, etc.), color, etc.);

[0080] A grinding strategy retrieval subsystem 2, which is used to retrieve the grinding strategy library according to the material type recognition result and determine the grinding strategy of the recognized material; among them, retrieving the grinding strategy library is: a database storing the grinding control parameters of various material types, and each material type has a corresponding grinding strategy, such as: the type of grinding machine used, the control parameters of the grinding machine (such as: grinding force and grinding duration), etc., and the grinding strategy library is constructed by workers with local grinding machine control experience based on experience;

[0081] An automated grinding subsystem 3, which is used to control the sand mill to automatically grind the recognized material based on the grinding strategy.

[0082] The working principle and beneficial effects of the above technical solution are:

[0083] The present invention obtains the material type recognition result of the material to be ground, retrieves the grinding strategy library according to the material type recognition result, determines the grinding strategy of the recognized material, and automatically controls the sand mill to grind based on the grinding strategy, realizing the corresponding transportation and coordinated grinding control of the recognized material to different types of sand mills, and greatly improving the working efficiency of the sand mill.

[0084] In one embodiment, the material type recognition subsystem obtains the material type recognition result of the material to be ground on the automated operation pipeline of the sand mill and performs the following operations:

[0085] Based on machine vision technology, capture the captured image of the material to be ground and extract the image features, and determine the material type recognition result according to the image features; wherein, the image features are: the color, texture, shape and edge of the material to be ground;

[0086] and / or,

[0087] Based on spectral analysis technology, analyze the spectral characteristic information of the material to be ground, and then determine the material type recognition result according to the spectral characteristic information; wherein, the spectral characteristic information is: the spectral absorption or emission characteristics of the material to be ground within a specific wavelength range;

[0088] and / or,

[0089] Based on machine learning algorithms, combine historical data to train a material type recognition model, and then determine the material type recognition result based on real-time sensor data and the material type recognition model. When training the material type recognition model by combining historical data, the historical data includes: sensor historical sensing data and corresponding historical material type recognition results. Use the sensor historical sensing data as the input of machine learning and the historical material type recognition results as the output of machine learning. After learning all the historical data, obtain the learned material type recognition model, and input the real-time sensor data into the material type recognition model to obtain the material type recognition result.

[0090] The working principle and beneficial effects of the above technical solutions are:

[0091] The present invention introduces three methods, namely machine vision technology, spectral analysis technology and machine learning, to determine the material type recognition result, improving the comprehensiveness and recognition accuracy of material type recognition.

[0092] In one embodiment, the grinding strategy retrieval subsystem retrieves the grinding strategy library according to the material type recognition result, determines the grinding strategy for the recognized material, and performs the following operations:

[0093] According to the material type recognition result, determine the type of sand mill suitable for grinding the recognized material;

[0094] Obtain the grinding strategy library of the sand mill of the sand mill type; wherein, the grinding strategy library stores a set of preselected recognition result feature values corresponding one by one and the control parameters of the sand mill of the sand mill type;

[0095] Characterize the material type recognition result to obtain a set of recognition result feature values;

[0096] According to the set of recognition result feature values and the grinding strategy library, determine the grinding strategy.

[0097] The working principle and beneficial effects of the above technical solutions are:

[0098] Different types of sand mills are suitable for grinding different types of materials (for example: basket sand mills are suitable for grinding medium- and low-viscosity materials, and horizontal sand mills are suitable for products with high viscosity and fine particle size requirements). Therefore, first, roughly determine the type of sand mill to be used based on the material type recognition result, and then determine the specific control parameters of the sand mill for subsequent operations to improve the efficiency of obtaining the subsequent grinding strategy. After determining the type of sand mill, retrieve the grinding strategy library corresponding to the type of sand mill. The grinding strategy library stores the control parameters of the sand mill with a one-to-one corresponding set of preselected recognition result feature values and the type of sand mill. Characterize the material type recognition result to obtain a set of recognition result feature values, and perform feature matching with the preselected recognition result feature value set. When the matching is successful, the control parameters of the corresponding sand mill are the grinding strategy.

[0099] In one embodiment, the grinding strategy retrieval subsystem retrieves the grinding strategy library of the sand mill of the type of sand mill and performs the following operations:

[0100] Obtain the operation records of the operator of the sand mill of the type of sand mill; wherein, the operation record is the record generated by the sand mill operator during the actual operation process, including: material information (the recognition result of the material manipulated by the operator, including the type of material, chemical and physical states) and grinding parameter settings. The operation record can be automatically recorded by the control system of the sand mill or manually recorded by the operator.

[0101] Analyze the operation record, obtain the manual recognition result of the manipulated material and the grinding parameters, characterize the manual recognition result, obtain the first set of recognition result feature values of the manipulated material, and associate them with the grinding parameters to obtain the first association item; wherein, the process of characterizing the manual recognition result is the same as the process of characterizing the material type recognition result.

[0102] Perform machine learning on the manual recognition result and the grinding parameters of the same manipulated material to obtain a grinding parameter determination model; wherein, when training the grinding parameter determination model, the input is the manual recognition result and the output is the grinding parameter.

[0103] Determine the missing recognition result based on the manual recognition result; wherein, when determining the missing recognition result in the manual recognition result, obtain the historical material recognition result of the manipulated material based on big data, compare the historical material recognition result with the manual recognition result, and determine the missing recognition result that does not exist in the manual recognition result.

[0104] Input the missing recognition result into the grinding parameter determination model, obtain the missing grinding parameters output by the grinding parameter determination model, characterize the missing recognition result, obtain the second set of recognition result feature values of the manipulated material, and associate them with the missing grinding parameters to obtain the second association item.

[0105] Integrate the first association item and the second association item of all controlled materials to obtain a grinding strategy library for sand mills of the sand mill type.

[0106] The working principle and beneficial effects of the above technical solution are as follows:

[0107] The present invention introduces the operation records of the operators of sand mills of the sand mill type, obtains the manual recognition results and grinding parameters in the operation records, performs machine learning on the manual recognition results and grinding parameters of the same controlled material to obtain a grinding parameter determination model; obtains the missing recognition results in the manual recognition results, inputs the missing recognition results into the grinding parameter determination model, and obtains the missing grinding parameters output by the grinding parameter determination model; characterizes the manual recognition results to obtain a first set of controlled material recognition result eigenvalue sets and associates them with the grinding parameters to obtain a first association item; characterizes the missing recognition results to obtain a second set of controlled material recognition result eigenvalue sets and associates them with the missing grinding parameters to obtain a second association item; integrates the first association item and the second association item of all controlled materials to obtain a grinding strategy library for the sand mill type. In addition to directly obtaining the data items of the grinding strategy library from the known operation records, machine learning is also performed using the known data to supplement the missing grinding parameters of the missing recognition results, improving the comprehensiveness and construction efficiency of the construction of the grinding strategy library.

[0108] An embodiment of the present invention provides a material type recognition system applied to the automated operation of a sand mill, which further includes:

[0109] A verification subsystem for obtaining the sampled material after the identified material is ground, performing a grinding accuracy verification on the sampled material, and performing a grinding medium detection when the grinding accuracy verification fails. Among them, the sampled material is: a part of the material taken out after the identified material is ground for grinding accuracy detection.

[0110] The working principle and beneficial effects of the above technical solution are as follows:

[0111] The present invention samples the identified material after grinding, and when the grinding accuracy verification of the sampled material fails, the grinding medium detection is performed in a timely manner, improving the timeliness of grinding medium replacement.

[0112] In one embodiment, when the grinding accuracy verification fails, the verification subsystem performs a grinding medium detection and performs the following operations:

[0113] Obtain the real-time triboelectric signal between the friction pairs; among them, the friction pair is: the components that rub against each other during the relative movement of two contact surfaces in the sand mill, such as: the dynamic ring and the static ring of the mechanical seal;

[0114] The triboelectric signal is read by connecting one end of a wire to any object constituting the friction pair and the other end of the wire to a detector (such as an oscilloscope), and the real-time triboelectric signal is read by the detector when the grinding accuracy verification fails;

[0115] Obtain the initial triboelectric signal of the friction pair; wherein, the initial triboelectric signal is the electrical signal read by the detector just after the grinding medium is replaced;

[0116] Calculate the change in friction coefficient according to the electrical signal difference between the real-time triboelectric signal and the initial triboelectric signal; wherein, the change in friction coefficient can be characterized by the electrical signal difference, and the corresponding relationship between the electrical signal and the friction coefficient is obtained according to historical test data;

[0117] If the change in friction coefficient reaches a preset degree of change, take the corresponding grinding medium as the judged grinding medium and obtain the service life of the judged grinding medium; wherein, the preset degree of change is preset manually and is the difference between the friction coefficient when the grinding requirement is not met and the friction coefficient when the grinding requirement is met; the service life is: the time when the judged grinding medium is put into the sand mill for use;

[0118] Judge the rationality of the service life of the judged grinding medium. If it is unreasonable, reset the cleaning time setting parameter;

[0119] Among them, judging the rationality of the service life of the judged grinding medium. If it is unreasonable, reset the cleaning time setting parameter, including:

[0120] Obtain the standard service life of the judged grinding medium; wherein, the standard service life is: the expected service life determined by the operator of the judged grinding medium according to experience;

[0121] If the time difference between the standard service life and the service life is greater than or equal to a preset time difference threshold, obtain the cleaning time setting parameter; wherein, the time difference is: the result obtained by subtracting the service life from the standard service life; the preset time difference threshold is preset manually; the cleaning time setting parameter is: the cleaning time of the sand mill after each grinding of a material;

[0122] Obtain the cleaning time setting parameter downward adjustment value comparison table; wherein, the cleaning time setting parameter downward adjustment value comparison table includes: multiple corresponding waiting-to-match time differences and cleaning time setting parameter downward adjustment values. The longer the waiting-to-match time difference, the larger the corresponding downward adjustment value, and the cleaning time setting parameter after being adjusted downward based on the largest cleaning time setting parameter downward adjustment value needs to be greater than the preset cleaning time threshold;

[0123] Determine the target cleaning time setting parameter after downward adjustment according to the time difference and the cleaning time setting parameter downward adjustment value comparison table;

[0124] After notifying the staff to replace the judged grinding medium, set the parameters with the target cleaning time.

[0125] The working principle and beneficial effects of the above technical solution are as follows:

[0126] The present invention obtains the electrical signal difference between the real-time triboelectric signal and the initial triboelectric signal. The change of the electrical signal characterizes the change of the friction coefficient. When the change of the friction coefficient reaches the point where the friction coefficient does not meet the preset expectation, the corresponding grinding medium is used as the judged grinding medium, and the usage duration of the judged grinding medium is obtained; the standard usage duration and the usage duration are compared, and the difference is obtained to get the duration difference. When the duration difference is greater than the duration difference threshold, it indicates that the wear rate of the judged grinding medium is too fast. During the interval when the sand mill grinds different materials alternately, the equipment needs to be cleaned. From the perspective of force, when the dispersion disk transfers energy to the grinding medium, if the liquid viscosity is very low, the medium may contact the dispersion disk and break. Therefore, it is necessary to minimize the cleaning duration. Obtain the cleaning time setting parameter, and in addition, obtain the cleaning time setting parameter reduction value comparison table; determine the cleaning time setting parameter reduction value corresponding to the cleaning time setting parameter according to the duration difference, and lower the set cleaning time. At the same time, a threshold is preset for the shortest cleaning time to ensure the cleaning effect. After notifying the staff to replace the judged grinding medium, apply the adjusted target cleaning time setting parameter. When the cleaning time setting is unreasonable and causes excessive wear of the grinding medium, notify the staff to replace the grinding medium in time and reasonably reset the cleaning time setting parameter, avoiding frequent replacement of the grinding medium and being more suitable.

[0127] An embodiment of the present invention provides a method for identifying the material type applied to the automatic operation of a sand mill, as Figure 2 shown, including:

[0128] Step 1: Obtain the material type identification result of the material to be ground on the automatic operation production line of the sand mill;

[0129] Step 2: Retrieve the grinding strategy library according to the material type identification result to determine the grinding strategy for the identified material;

[0130] Step 3: Based on the grinding strategy, control the sand mill to automatically grind the identified material.

[0131] In one embodiment, obtaining the material type identification result of the material to be ground on the automatic operation production line of the sand mill includes:

[0132] Based on machine vision technology, obtain the captured image of the material to be ground and extract the image features, and determine the material type identification result according to the image features;

[0133] and / or,

[0134] Based on spectral analysis technology, analyze the spectral characteristic information of the material to be ground, and then determine the material type recognition result according to the spectral characteristic information;

[0135] And / or,

[0136] Based on machine learning algorithms and combined with historical data, train a material type recognition model, and then determine the material type recognition result based on real-time sensor data and the material type recognition model.

[0137] In one embodiment, according to the material type recognition result, retrieve the grinding strategy library to determine the grinding strategy for the identified material, including:

[0138] According to the material type recognition result, determine the type of sand mill suitable for grinding the identified material;

[0139] Obtain the grinding strategy library of the sand mill of the sand mill type;

[0140] Characterize the material type recognition result to obtain a set of recognition result characteristic values;

[0141] According to the set of recognition result characteristic values and the grinding strategy library, determine the grinding strategy.

[0142] An embodiment of the present invention provides a method for identifying the type of material applied to the automated operation of a sand mill, further including:

[0143] Obtain the sampled material after grinding the identified material, perform a grinding accuracy verification on the sampled material, and when the grinding accuracy verification fails, perform a grinding medium detection.

[0144] In one embodiment, when the grinding accuracy verification fails, perform a grinding medium detection, including:

[0145] Obtain the real-time frictional electrical signal between the friction pairs;

[0146] Obtain the initial frictional electrical signal of the friction pairs;

[0147] According to the electrical signal difference between the real-time frictional electrical signal and the initial frictional electrical signal, calculate the change in the friction coefficient;

[0148] If the change in the friction coefficient reaches a preset degree of change, use the corresponding grinding medium as the determined grinding medium, and obtain the usage duration of the determined grinding medium;

[0149] Judge the rationality of the usage duration of the determined grinding medium. If it is unreasonable, reset the cleaning time setting parameter;

[0150] Among them, judging the rationality of the usage duration of the determined grinding medium. If it is unreasonable, reset the cleaning time setting parameter, including:

[0151] Obtain the standard service life of the grinding medium for determination;

[0152] If the time difference between the standard service life and the service life is greater than or equal to the preset time difference threshold, obtain the cleaning time setting parameter;

[0153] Obtain the comparison table of the downward adjustment values of the cleaning time setting parameters;

[0154] Determine the target cleaning time setting parameter after downward adjustment according to the time difference and the comparison table of the downward adjustment values of the cleaning time setting parameters;

[0155] After notifying the staff to replace the fixed grinding medium, apply the target cleaning time setting parameter.

[0156] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A material type recognition system applied to the automated operation of a sand mill, characterized in that including: a material type identification subsystem, configured to obtain the identification result of the material type of the material to be ground on the automated operation pipeline of the sand mill; a grinding strategy retrieval subsystem, configured to retrieve the grinding strategy library according to the material type identification result and determine the grinding strategy for the identified material; an automated grinding subsystem, configured to control the sand mill to perform automated grinding on the identified material based on the grinding strategy; the material type identification system applied to the automated operation of the sand mill further performs the following operations: a calibration subsystem, configured to obtain the sampled material after grinding the identified material, perform grinding precision calibration on the sampled material, and perform grinding medium detection when the grinding precision calibration fails; wherein, when the grinding precision calibration fails, the calibration subsystem performs grinding medium detection and executes the following operations: obtain the real-time frictional electrical signal between the friction pairs; wherein, the friction pairs are the moving ring and the static ring of the mechanical seal in the sand mill; obtain the initial frictional electrical signal of the friction pairs; calculate the change in the friction coefficient according to the electrical signal difference between the real-time frictional electrical signal and the initial frictional electrical signal; if the change in the friction coefficient reaches the preset change degree, regard the corresponding grinding medium as the determined grinding medium and obtain the usage duration of the determined grinding medium; judge the rationality of the usage duration of the determined grinding medium, and if it is unreasonable, reset the cleaning time setting parameter; wherein, judging the rationality of the usage duration of the determined grinding medium, and if it is unreasonable, resetting the cleaning time setting parameter includes: obtain the standard usage duration of the determined grinding medium; if the duration difference between the standard usage duration and the usage duration is greater than or equal to the preset duration difference threshold, obtain the cleaning time setting parameter; obtain the cleaning time setting parameter downward adjustment value comparison table; determine the target cleaning time setting parameter after downward adjustment according to the duration difference and the cleaning time setting parameter downward adjustment value comparison table; after notifying the staff to replace the determined grinding medium, apply the target cleaning time setting parameter.

2. The material type recognition system for the automated operation of a sand mill according to claim 1, characterized in that, The material type identification subsystem obtains the identification result of the material type of the material to be ground on the automated operation pipeline of the sand mill and executes the following operations: Based on machine vision technology, obtain the captured image of the material to be ground and extract the image features, and determine the material type identification result according to the image features; and / or Based on spectral analysis technology, analyze the spectral characteristic information of the material to be ground, and then determine the material type identification result according to the spectral characteristic information; and / or Based on machine learning algorithms, train the material type identification model in combination with historical data, and then determine the material type identification result based on the real-time sensor data and the material type identification model.

3. The material type recognition system for the automated operation of a sand mill according to claim 1, wherein, The grinding strategy retrieval subsystem retrieves the grinding strategy library according to the material type identification result and determines the grinding strategy for the identified material, and executes the following operations: According to the material type identification result, determine the type of sand mill suitable for grinding the identified material; obtain the grinding strategy library of the sand mill of the sand mill type; characterize the material type identification result to obtain the identification result feature value set; Determine the grinding strategy according to the identification result feature value set and the grinding strategy library.

4. A method for identifying the type of material applied to the automated operation of a sand mill, characterized in that, including: obtain the identification result of the material type of the material to be ground on the automated operation pipeline of the sand mill; Retrieve the grinding strategy library according to the material type recognition result, and determine the grinding strategy for the recognized material; Based on the grinding strategy, control the sand mill to automatically grind the recognized material; Obtain the sampled material after grinding the recognized material, and conduct a grinding accuracy verification on the sampled material. When the grinding accuracy verification fails, conduct a grinding medium detection; Among them, when the grinding accuracy verification fails, conducting a grinding medium detection includes: Obtain the real-time triboelectric signal between the friction pairs; Obtain the initial triboelectric signal of the friction pairs; Calculate the change in friction coefficient according to the signal difference between the real-time triboelectric signal and the initial triboelectric signal; If the change in friction coefficient reaches the preset change degree, regard the corresponding grinding medium as the judged grinding medium, and obtain the service life of the judged grinding medium; Judge the rationality of the service life of the judged grinding medium. If it is unreasonable, reset the cleaning time setting parameter; Among them, judging the rationality of the service life of the judged grinding medium. If it is unreasonable, resetting the cleaning time setting parameter includes: Obtain the standard service life of the judged grinding medium; If the time difference between the standard service life and the service life is greater than or equal to the preset time difference threshold, obtain the cleaning time setting parameter; Obtain the cleaning time setting parameter down-regulation value comparison table; According to the time difference and the cleaning time setting parameter down-regulation value comparison table, determine the target cleaning time setting parameter after down-regulation; After notifying the staff to replace the determined grinding medium, apply the target cleaning time setting parameter.

5. The material type recognition method applied to the automated operation of a sand mill according to claim 4, wherein, Obtain the material type recognition result of the material to be ground on the automatic operation pipeline of the sand mill, including: Based on machine vision technology, obtain the captured image of the material to be ground and extract the image features. According to the image features, determine the material type recognition result; and / or Based on spectral analysis technology, analyze the spectral characteristic information of the material to be ground, and then determine the material type recognition result according to the spectral characteristic information; and / or Based on machine learning algorithms, combine historical data to train the material type recognition model, and then determine the material type recognition result based on real-time sensor data and the material type recognition model.

6. The material type recognition method applied to the automated operation of a sand mill according to claim 4, characterized in that Retrieve the grinding strategy library according to the material type recognition result, and determine the grinding strategy for the recognized material, including: According to the material type recognition result, determine the type of sand mill suitable for grinding the recognized material; Obtain the grinding strategy library of the sand mill of the sand mill type; Characterize the material type recognition result to obtain the recognition result feature value set; According to the recognition result feature value set and the grinding strategy library, determine the grinding strategy.

Images