Grinding wheel production mixing process parameter adjusting system based on industrial internet of things

Abstract

The invention discloses a grinding wheel production mixing process parameter adjusting system based on the industrial internet of things, and relates to the technical field of grinding tool manufacturing and industrial automation control, and the grinding wheel production mixing process parameter adjusting system comprises a multi-dimensional sensing module, an edge calculation module and a cooperative control module; the multi-dimensional sensing module, the edge computing module and the cooperative control module are in communication connection with one another through an industrial Internet of Things bus; wherein the multi-dimensional sensing module is deployed at a material mixing equipment end and is configured to construct a multi-source heterogeneous data acquisition network and acquire equipment operation mechanical data, material rheological form image data and environment state data in a material mixing process in real time; the edge calculation module is connected with the multi-dimensional sensing module and is configured to receive the data and calculate the predicted apparent density value of the current batch of mixed materials in real time based on a preset rheology-density mapping model, and the problem that the molding weight of a grinding wheel is uneven due to the fluctuation of the apparent density of the mixed materials is solved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of abrasive tool manufacturing and industrial automation control, and particularly relates to a grinding wheel production mixing process parameter adjustment system based on an industrial Internet of Things. BACKGROUND

[0002] In the production process of resin grinding wheels or ceramic grinding wheels, the quality of the mixing process directly determines the product performance in the subsequent forming process. Existing mixing control mostly adopts a fixed time or fixed speed mode, and cannot realize real-time sensing of the rheological property changes (such as dryness, wetness and agglomeration degree) of materials caused by the influence of environmental temperature and humidity and batch differences of raw materials.

[0003] Meanwhile, the mixer and the downstream forming press independently operate. The bulk density of the mixed material often fluctuates, and the press usually adopts a fixed volume feeding method (i.e., the mold cavity depth is fixed). When the bulk density of the mixed material is low (the material is fluffy), the same feeding volume will cause the weight of the single grinding wheel to be insufficient and the porosity to be too large; on the contrary, it will cause the weight to be overweight and the hardness to be too high. Such deviations often cannot be found until the pressing is completed and the weight or detection is performed, causing batch waste and raw material waste.

[0004] Therefore, an intelligent system capable of on-line prediction of the bulk density of the mixed material, closed-loop adjustment of the mixing process based on the predicted value and guidance of the downstream press for feedforward compensation is urgently needed. SUMMARY

[0005] The application aims to provide a grinding wheel production mixing process parameter adjustment system based on an industrial Internet of Things, so as to solve the problems in the background.

[0006] In order to solve the above technical problems, the application provides the following technical scheme: a grinding wheel production mixing process parameter adjustment system based on an industrial Internet of Things, which comprises a multi-dimensional sensing module, an edge computing module and a collaborative control module; the multi-dimensional sensing module, the edge computing module and the collaborative control module are connected in communication through an industrial Internet of Things bus; wherein, The multi-dimensional sensing module is arranged at the end of the mixing equipment and is configured to construct a multi-source heterogeneous data acquisition network, and to collect device running mechanical data, material rheological form image data and environmental state data in real time during the mixing process. The edge computing module is connected with the multi-dimensional sensing module and is configured to receive the data and to calculate a predicted bulk density value of the current batch of mixed material in real time based on a preset rheological-density mapping model. The collaborative control module is bidirectionally connected to the mixing equipment controller and the downstream molding equipment controller, and is configured to execute an adaptive closed-loop adjustment strategy and a cross-process feedforward compensation strategy based on the predicted loose density value.

[0007] According to the above technical solution, the multi-dimensional perception module includes a mechanical feature acquisition unit, a visual morphology acquisition unit, and an environmental compensation acquisition unit; The mechanical feature acquisition unit is configured to acquire the instantaneous torque, speed and power consumption data of the main stirring motor at high frequency; The visual pattern acquisition unit includes a high-speed industrial camera installed in the observation window of the mixer, which is configured to capture the falling image of the material after it is lifted to the highest point by the agitator blades. The environmental compensation acquisition unit is configured to monitor the temperature, humidity, and concentration of volatile solvent gases in the mixing chamber in real time.

[0008] According to the above technical solution, the edge computing module includes a feature extraction unit, a density soft measurement unit, and a model correction unit; The feature extraction unit is used to extract energy consumption integral features from the mechanical data. And extract fluid topological features, namely the flowability index, from the collapse scene. ; The density soft measurement unit is used to input the extracted features into the rheology-density mapping model to calculate the initial predicted density. The model correction unit is used to generate an environmental correction factor based on the temperature and humidity data acquired by the environmental compensation acquisition unit, to compensate and correct the initial predicted density, and to output the final predicted loose density value. .

[0009] According to the above technical solution, the feature extraction unit calculates the energy consumption integral feature. The calculation formula is: ; in, to This refers to the time window for the mixing and refining stage. The stirring torque is collected in real time. For real-time stirring angular velocity, The power loss due to mechanical losses during no-load operation of the equipment; the energy consumption integral characteristic It represents the net shear energy absorbed by boredom to reach its current dense state during the mixing process.

[0010] According to the above technical solution, the feature extraction unit extracts the flowability index. The specific steps are as follows: The velocity vector field of the falling particles in the collapse picture is extracted by an optical flow method algorithm; An angle between a main direction of the velocity vector field and a direction of gravity is calculated, and is defined as a collapse flow angle; The dispersion of the pixel points in the collapse picture is calculated; The flowability index is generated based on the collapse flow angle and the pixel point dispersion ; when the flowability index is lower than a preset threshold value, it is determined that the material is in a high-viscosity agglomeration state.

[0011] According to the above technical solution, the calculation formula of the density soft measurement unit for predicting the bulk density value is as follows: ; wherein, is a theoretical limit bulk density of the formula material in an ideal state, is a preset constant, is a natural initial bulk density of the material, is an energy consumption integral feature representing a densification power, is a flowability index representing a densification resistance, is an environmental correction factor, is a process sensitivity coefficient, is a residual correction term; the formula shows that the predicted bulk density value approaches the theoretical limit bulk density at an exponential rate with the increase of the energy consumption integral feature, and is constrained by the flowability index and the environmental correction factor.

[0012] According to the above technical solution, the calculation formula of the environmental correction factor is as follows: ; wherein, are a current environmental relative humidity and a standard working condition relative humidity respectively, are a current environmental temperature and a standard working condition temperature respectively, is a humidity influence coefficient; is a temperature sensitivity reference constant; the formula is used to represent the nonlinear amplification or inhibition effect of the change of the environmental temperature on the humidity-induced moisture absorption activity of the binder.

[0013] According to the above technical solution, the specific logic of the collaborative control module for executing the cross-process feedforward compensation strategy is as follows: The target bulk density corresponding to the standard process formula and the standard feeding depth of the molding equipment are obtained; The final predicted bulk density is locked before discharging at the end of mixing; Computing the forming filler depth compensation coefficient ; Generating new feeding depth instructions ; Sending the feeding depth instructions to the downstream forming equipment, instructing the forming equipment to automatically adjust the mold cavity depth to when performing the batch material pressing, so as to keep the single piece grinding wheel feeding weight constant.

[0014] According to the above technical scheme, the specific logic of the cooperative control module executing the adaptive closed-loop adjustment strategy is: Setting a target density lower limit threshold; During the mixing process, if the real-time calculated predicted bulk density value is lower than the lower limit threshold, it is determined that the material is not sufficiently exhausted or there are false particles; Control the mixing equipment to enter the densification mode: automatically reduce the spindle stirring speed to increase the material extrusion residence time, and at the same time, start the pulse type auxiliary crushing device for depolymerization until the predicted bulk density value rises back to the target range.

[0015] According to the above technical scheme, the sand wheel production mixing process parameter adjustment method based on industrial internet of things includes the following steps: Step S1: Real-time acquisition of stirring torque data, material collapse image data and environmental temperature and humidity data during the mixing process by using a multi-dimensional perception module; Step S2: The edge computing module extracts features from the collected data, calculates energy consumption integral features and fluid topology features; Step S3: Based on the pre-branch rheological-density mapping model and the environmental correction factor, the predicted bulk density value of the current batch of materials is calculated in real time; Step S4: Compare the predicted bulk density value with the target value, and if there is a deviation, perform adaptive closed-loop adjustment on the mixing equipment; Step S5: At the end of the mixing, generate a cross-process feedforward compensation instruction according to the final predicted bulk density value to adjust the mold feeding depth of the downstream forming equipment.

[0016] Compared with the prior art, the beneficial effects achieved by the present application are: the present application uses a multi-dimensional perception module to fuse energy consumption and visual features, combines a nonlinear saturation model and a temperature and humidity coupling correction, realizes accurate prediction of the mixing bulk density and environmental disturbance resistance, and overcomes the problems of distortion of traditional models and poor environmental adaptability. On this basis, the system constructs a cross-process feedforward mechanism through industrial internet of things, automatically adjusts the downstream press feeding depth according to the predicted density, effectively solves the problem of uneven finished product weight caused by material fluctuations, significantly reduces the scrap rate, and improves the intelligent level of sand wheel manufacturing and product consistency. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and are meant to explain the application without limiting the application to the embodiments shown. In the drawings: Figure 1 is a schematic diagram of the system module composition of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0019] Please refer to Figure 1 The present application provides a technical solution: a grinding wheel production mixing process parameter adjustment system based on an industrial Internet of Things, which comprises a multi-dimensional perception module, an edge computing module and a collaborative control module; the multi-dimensional perception module, the edge computing module and the collaborative control module are connected in communication with each other through an industrial Internet of Things bus; wherein, The multi-dimensional perception module is deployed at the end of a mixing device and is configured to construct a multi-source heterogeneous data acquisition network, and to collect device running mechanical data, material flow deformation image data and environmental state data in real time during the mixing process. The edge computing module is connected with the multi-dimensional perception module and is configured to receive the data and to calculate a predicted bulk density value of the current batch of mixed materials in real time based on a preset rheological-density mapping model. The collaborative control module is bidirectionally connected in communication with a mixing device controller and a downstream forming device controller, and is configured to execute an adaptive closed-loop adjustment strategy and a cross-process feedforward compensation strategy according to the predicted bulk density value.

[0020] The multi-dimensional perception module comprises a mechanical characteristic acquisition unit, a visual morphology acquisition unit and an environmental compensation acquisition unit. The mechanical characteristic acquisition unit is configured to collect high-frequency instantaneous torque, rotational speed and power consumption data of a main stirring motor. The visual morphology acquisition unit comprises a high-speed industrial camera arranged at an observation window of a mixer and is configured to capture a collapse picture of material falling after being lifted to the highest point by a stirring paddle blade. The environmental compensation acquisition unit is configured to monitor the temperature, humidity and concentration of volatile solvent gas in the mixing cavity in real time.

[0021] The edge computing module comprises a feature extraction unit, a density soft measurement unit and a model correction unit. The feature extraction unit is configured to extract an energy consumption integral feature from the mechanical data , and extract a fluid topological feature, i.e., a flowability index, from the caving picture . The density soft measurement unit is configured to input the extracted features into the rheological-density mapping model to calculate an initial predicted density. The model correction unit is configured to generate an environmental correction factor according to the temperature and humidity data acquired by the environment compensation acquisition unit, compensate and correct the initial predicted density, and output a final predicted bulk density value .

[0022] The feature extraction unit calculates the energy consumption integral feature , and the calculation formula is as follows: ; wherein, to is a time window of the mixing and fine mixing stage, is a real-time acquired stirring torque, is a real-time stirring angular velocity, is a mechanical loss power when the device is running empty; the energy consumption integral feature characterizes the net shear energy absorbed by the material to reach the current dense state in the mixing process.

[0023] The feature extraction unit extracts the flowability index , and the specific steps are as follows: The velocity vector field of the particle group falling in the caving picture is extracted by using the optical flow method algorithm; the Farneback dense optical flow algorithm in the OpenCV library is called to process the caving images ; the velocity vector of a pixel point in the image at moment is , wherein is a horizontal component, is a vertical component; the system only calculates the pixels in the ROI region, i.e., the preset falling area below the stirring paddle, and outputs the dense velocity field; The included angle between the main direction of the velocity vector field and the direction of gravity is calculated, and is defined as the caving flowability angle; the caving angle reflects the internal friction angle of the material; the more loose (low density) the material is, the more divergent the falling trajectory is; the more heavy (high density) the material is, the more vertical and clustered the falling trajectory is; the average direction angle of the velocity vectors of all effective moving pixel points in the ROI region is calculated as follows: ; The caving flowability angle is defined as is the absolute value of the angle between the main direction of velocity and the direction of gravity, if is smaller, it means that the material is in a "heavy block" vertical drop (too wet or too sticky); on the contrary, if is larger, it means that the material is in a "parabolic spray" scattered (good flow, relatively loose); Calculate the dispersion of the pixel points in the collapse picture ; this index is used to measure whether the material is "fog-like scattering" or "block-like falling"; the adaptive threshold binaryzation is performed on the difference image to extract the moving foreground particle target, and the simplified centroid distance variance algorithm is used: ; Among them, is the total number of current pixel points, is the coordinate of the th pixel point, is the geometric centroid of all foreground pixel points; when is larger, it means that the material is scattered (good atomization, loose material), and when is smaller, it means that the material is gathered together (grouping, solid material); The flow index is generated based on the collapse flow angle and the pixel point dispersion ; when the flow index is lower than the preset threshold, it is determined that the material is in a high-viscosity agglomeration state; In order to obtain a normalized and monotonic control variable, the system constructs the flow index based on the above two physical quantities; considering that anti-grouping is the core in the sand wheel mixing process, therefore, the higher represents the better flowability (looser), and the calculation formula is as follows: .

[0024] Among them, is a normalization function that maps the value to the interval; , is the weight coefficient; The system presets a "high-viscosity agglomeration threshold" ; when the real-time calculated , it is determined that the material is in a high-viscosity agglomeration state, indicating that the binder is not uniformly dispersed or there are too many pseudo-particles; at this time, the system will automatically trigger the densification mode reverse operation.

[0025] The density soft-sensing unit calculates the predicted loose bulk density value The calculation formula is: ; Among them, is the theoretical limit loose bulk density of the material in the ideal state, and is a preset constant, is the initial density of the natural accumulation of the material, is the energy consumption integral characteristic, representing the densification power, is the flowability index, representing the densification resistance, is the environmental correction factor, is the process sensitivity coefficient, is the residual correction term; the formula shows that the predicted bulk density value approaches the theoretical limit bulk density at an exponential rate as the energy consumption integral characteristic increases, with the flowability index and the environmental correction factor as constraints; In actual industrial production, the compaction process of the grinding wheel mixture is not a simple linear superposition process. The applicant found through in-depth research that, with the continuous input of mixing energy, the increase rate of the bulk density of the material will gradually slow down and tend to a physical limit; at the same time, the micro-rheological structure of the material (represented by the flowability index ) will significantly affect the efficiency of energy conversion into density. In order to accurately describe this complex physical process, the embodiment discards the traditional linear regression algorithm and innovatively constructs an energy-structure coupled exponential saturation prediction model, in which represents the potential compressible space of the material. With the decay of the exponential term, the predicted density will infinitely approach the theoretical limit density, avoiding the fallacy of the linear model that the predicted value exceeds the physical limit under long-time mixing; The in the exponential term is defined as the effective densification potential energy, and the flowability index as the denominator, which means that when the value is larger, the densification effect produced by the same energy input will be weakened. This mathematical structure skillfully simulates the nonlinear constraint of the material structure on energy transfer.

[0026] The calculation formula of the environmental correction factor is: ; wherein, are the current relative humidity and the standard working condition relative humidity, respectively, are the current ambient temperature and the standard working condition temperature, respectively, is the humidity influence coefficient; is the temperature sensitivity reference constant; this formula is used to represent the nonlinear amplification or inhibition of the moisture absorption activity of the binder caused by the change of the environmental temperature; considering that the moisture absorption characteristics of the resin binder (such as phenolic resin) are significantly affected by temperature (usually the higher the temperature, the more intense the molecular motion, and the more obvious the agglomeration effect caused by moisture absorption), the embodiment calculates the environmental correction factor in a temperature and humidity coupled manner, in which, when the environmental temperature deviates from the standard temperature When it does, it will amplify or reduce the impact of humidity difference on the final density in a nonlinear way, thus accurately compensating for the different physical and chemical effects of the same humidity on the quality of the grinding wheel mixture in different seasons (such as high temperature and humidity in summer and low temperature and humidity in winter), greatly improving the robustness of the system in all-weather environments.

[0027] The specific logic of the collaborative control module executing the cross-process feedforward compensation strategy is: Obtain the target bulk density corresponding to the standard process recipe and the standard feeding depth of the molding equipment ; Lock the final predicted bulk density before discharging at the end of mixing ; Calculate the molding filler depth compensation coefficient ; Generate a new feeding depth instruction ; Send the feeding depth instruction to the downstream molding equipment, instructing the molding equipment to automatically adjust the mold cavity depth to when executing the batch of material pressing, to keep the single piece of grinding wheel feeding weight constant; the system locks the predicted bulk density of the material before the end of mixing, and automatically calculates the corresponding molding filler depth compensation coefficient. Whether the upstream material is loose or solid, the system can automatically adjust the mold cavity depth by instructing the downstream press, realize more filling for loose material and less filling for solid material, and ensure the constant feeding weight of each piece of grinding wheel. Thus, the batch waste caused by raw material or process fluctuation is fundamentally eliminated, and the molding qualification rate is significantly improved.

[0028] The specific logic of the collaborative control module executing the adaptive closed-loop regulation strategy is: Set the lower limit threshold of the target density During the mixing process, if the predicted bulk density value calculated in real time is lower than the lower limit threshold, it is determined that the material is not sufficiently deaerated or there are false particles Control the mixing equipment to enter the densification mode: automatically reduce the spindle stirring speed to increase the material extrusion residence time, and at the same time, turn on the pulse type auxiliary crushing device for depolymerization until the predicted bulk density value rises back to the target range.

[0029] A grinding wheel production mixing process parameter adjustment method based on industrial Internet of Things, the grinding wheel production mixing process parameter adjustment method comprises the following steps: Step S1: Use a multi-dimensional perception module to collect stirring torque data, material collapse image data, and environmental temperature and humidity data in real time during the mixing process Step S2: The edge computing module extracts features from the collected data, calculates energy consumption integral features and fluid topology features; Step S3: Based on the pre-branching rheological-density mapping model and the environmental correction factor, the predicted bulk density value of the current batch of materials is calculated in real time; Step S4: Compare the predicted bulk density value with the target value, and if there is a deviation, the mixing equipment is subjected to adaptive closed-loop adjustment; Step S5: At the end of mixing, a cross-process feedforward compensation instruction is generated according to the final predicted bulk density value to adjust the mold feeding depth of the downstream forming equipment.

[0030] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0031] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0032] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0033] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are only illustrative and not limiting. Those skilled in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these are all within the protection of the present application.

Claims

1. An industrial internet of things based grinding wheel production mix process parameter adjustment system, characterized in that, The grinding wheel production mixing process parameter adjustment system comprises a multi-dimensional perception module, an edge calculation module and a collaborative control module; the multi-dimensional perception module, the edge calculation module and the collaborative control module are connected in communication through an industrial Internet of Things bus; wherein, The multi-dimensional perception module is deployed at the mixing equipment end and is configured to construct a multi-source heterogeneous data acquisition network, and to collect device running mechanical data, material flow deformation image data and environmental state data in real time during the mixing process; The edge calculation module is connected with the multi-dimensional perception module and is configured to receive the data and to calculate the predicted bulk density value of the current batch of mixed materials in real time based on a pre-set rheological-density mapping model; The collaborative control module is connected in bidirectional communication with the mixing equipment controller and the downstream forming equipment controller, and is configured to execute an adaptive closed-loop adjustment strategy and a cross-process feedforward compensation strategy according to the predicted bulk density value.

2. The grinding wheel production mixture process parameter adjusting system based on industrial internet of things according to claim 1, characterized in that: The multi-dimensional perception module comprises a mechanical characteristic acquisition unit, a visual morphology acquisition unit and an environmental compensation acquisition unit; The mechanical characteristic acquisition unit is configured to collect high-frequency instantaneous torque, rotating speed and power consumption data of the main stirring motor; The visual morphology acquisition unit comprises a high-speed industrial camera arranged at the observation window of the mixer and is configured to capture the collapse picture of the material lifted to the highest point by the stirring paddle blade and then thrown down; The environmental compensation acquisition unit is configured to monitor the temperature, humidity and concentration of volatile solvent gas in the mixing cavity in real time. 3.The industrial Internet of Things based grinding wheel production mixture process parameter adjusting system according to claim 2, characterized in that: The edge calculation module comprises a feature extraction unit, a density soft measurement unit and a model correction unit; The feature extraction unit is configured to extract an energy consumption integral feature from the mechanical data , and extract a fluid topological feature, i.e., a flowability index, from the collapse picture ; The density soft measurement unit is used to input the extracted features into the rheological-density mapping model to calculate the initial predicted density; The model correction unit is configured to generate an environment correction factor according to the temperature and humidity data acquired by the environment compensation acquisition unit, compensate and correct the initial predicted bulk density, and output a final predicted bulk density value .

4. The grinding wheel production mixture process parameter adjusting system based on industrial internet of things according to claim 3, characterized in that: The feature extraction unit calculates the energy consumption integral feature The calculation formula is: ； wherein, to is the time window for the refining phase of the mixing, is the real-time collected mixing torque, is the real-time mixing angular velocity, is the mechanical loss power of the equipment when running empty; said energy consumption integral feature characterizes the net shear energy absorbed by boredom in reaching the current consistency state in the mixing process.

5. The grinding wheel production mixture process parameter adjustment system based on industrial internet of things according to claim 3, characterized in that: The feature extraction unit extracts a flow index The specific steps are as follows: The velocity vector field of the particle group falling in the collapse picture is extracted by an optical flow algorithm; The included angle between the main direction of the velocity vector field and the direction of gravity is calculated, which is defined as the collapse flow angle; The dispersion of the material pixel points in the collapse picture is calculated; generating the flowability index based on a flow angle of collapse and a pixel point dispersion ; when the flowability index is lower than a preset threshold value, determining that the material is in a high-viscosity agglomeration state.

6. The grinding wheel production mixture process parameter adjustment system based on industrial internet of things according to claim 3, characterized in that: The density soft sensor unit calculates a predicted bulk density value The calculation formula is: ； wherein, is the theoretical limit bulk density of the formulation material in ideal state, is a pre-set constant, is the initial bulk density of the material in natural state, is the energy consumption integral characteristic, representing the densification power, is the flowability index, representing the densification resistance, is the environmental correction factor, is the process sensitivity coefficient, is the residual correction term; the formula shows that the predicted bulk density value approaches the theoretical limit bulk density at an exponential rate as the energy consumption integral characteristic increases, with the flowability index and the environmental correction factor as constraints. 7.The industrial Internet of Things based grinding wheel production mixture process parameter adjusting system according to claim 6, characterized in that: The environmental correction factor The calculation formula is: ； wherein, respectively the current ambient relative humidity and the standard operating relative humidity, respectively the current ambient temperature and the standard operating temperature, is the humidity influence coefficient; is the temperature sensitivity reference constant; this formula is used to characterize the nonlinear amplification or inhibition effect of the change of ambient temperature on the moisture-induced moisture activity of the binder. 8.The industrial Internet of Things based grinding wheel production mixture process parameter adjusting system according to claim 1, characterized in that: The specific logic of the collaborative control module executing the cross-process feedforward compensation strategy is as follows: obtaining a target bulk density corresponding to a standard process recipe and a standard charge depth of the forming apparatus ; Lock final predicted bulk density before discharging at the end of mixing ; Computing a shaped filler depth compensation factor ; Generating new dosing depth instructions ; The feeding depth instruction is sent to a downstream forming device, instructing the forming device to automatically adjust the mold cavity depth to to keep the feeding weight of the single piece grinding wheel constant. 9.The industrial Internet of Things based grinding wheel production mixture process parameter adjusting system according to claim 1, characterized in that: The specific logic of the collaborative control module executing the adaptive closed-loop adjustment strategy is as follows: A target density lower threshold is set; During the mixing process, if the real-time calculated predicted bulk density value is lower than the lower threshold value, it is determined that the material is not sufficiently degassed or that there are false particles. The mixing equipment is controlled to enter the densification mode: the main shaft stirring speed is automatically reduced to increase the material extrusion residence time, and at the same time, the pulse type auxiliary crushing device is started to perform depolymerization until the predicted bulk density value rises back to the target range.

10. A method for adjusting the parameters of a mixture process for grinding wheel production based on an industrial internet of things, characterized in that: The grinding wheel production mixing process parameter adjustment method comprises the following steps: Step S1: real-time collection of stirring torque data, material collapse image data and environmental temperature and humidity data during the mixing process by using the multi-dimensional perception module; Step S2: feature extraction of the collected data by the edge calculation module, calculation of energy consumption integral features and fluid topology features; Step S3: real-time calculation of the predicted bulk density value of the current batch of materials based on the pre-set rheological-density mapping model and the environmental correction factor; Step S4: comparison of the predicted bulk density value with the target value, and adaptive closed-loop adjustment of the mixing equipment if there is a deviation. Step S5: At the end of the mixing, cross-process feedforward compensation instructions are generated based on the final predicted bulk density value to adjust the mould charge depth of the downstream forming equipment.

Images