Visual monitoring system and method for concrete mixing main machine

Abstract

The invention relates to a concrete mixing main machine visual monitoring system and a method thereof, and belongs to the technical field of concrete production automation and intelligent quality control, and the method comprises the following steps: S1, collecting a video image sequence of movement of concrete in a mixing main machine in real time; s2, extracting a dynamic visual feature vector and a static feature vector based on the video image sequence; s3, on the basis of the dynamic visual feature vector and a preset dynamic rheological-visual feature coupling model, calculating an internal rheological state index; s4, based on the static feature vector and a preset static correlation model, calculating a predicted value of the foundation slump; s5, determining a final corrected slump through a preset correction function in combination with the intrinsic rheological state index and the predicted value of the foundation slump; s6, according to the final corrected slump, the predicted value of the foundation slump and the intrinsic rheological state index, the comprehensive risk index is calculated, and the intrinsic rheological characteristics which are caused by chemical admixtures and cannot be perceived by a traditional visual method can be deeply captured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of concrete production automation and intelligent quality control, in particular to a concrete mixing main machine visual monitoring system and method thereof. BACKGROUND

[0002] In the quality control of concrete production, the traditional mixing process monitoring method mainly relies on manual experience or conventional visual systems, which indirectly judge the working performance of concrete by observing its macroscopic apparent fluidity. However, these methods face fundamental problems when dealing with modern high-performance concrete. The widespread use of chemical admixtures causes concrete to exhibit complex non-Newtonian fluid characteristics, which seriously decouples its visual representation from its true internal working performance.

[0003] This situation leads to the fact that producers cannot accurately and timely grasp the true state of concrete, making it difficult to discover and diagnose internal rheological performance abnormalities caused by admixtures, affecting the precise regulation of the production process. In addition, the traditional method lacks the ability to quantitatively evaluate this risk of discrepancy between appearance and reality, and cannot provide scientific decision-making basis for preventing construction problems.

[0004] The above situation and deficiencies are mainly due to the limitations of monitoring and analysis technology. The analysis method that simply relies on macroscopic visual features is not sensitive enough to the microscopic structural changes and rheological property changes caused by chemical components, resulting in a single dimension of information acquisition. As a result, when concrete has potential quality risks, managers cannot quickly obtain comprehensive and accurate quantitative information, delaying the adjustment opportunity, and ultimately may lead to serious engineering accidents such as pumping pipe blockage and segregation and bleeding.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide a concrete mixing main machine visual monitoring system and method thereof to solve the problems raised in the background art.

[0007] The technical solution of the present application is as follows: S1, real-time acquisition of video image sequences of concrete moving in the mixing main machine; S2, based on the video image sequence, extracting dynamic visual feature vectors and static feature vectors; S3, based on the dynamic visual feature vectors and the preset dynamic rheological-visual feature coupling model, calculating the internal rheological state index; S4, based on the static feature vectors and the preset static correlation model, calculating the basic slump prediction value; S5, in combination with the intrinsic rheological state index and the basic slump prediction value, determining the final corrected slump through a preset correction function; S6, according to the final corrected slump, the basic slump prediction value and the intrinsic rheological state index, calculating a comprehensive risk index; S7, based on the comprehensive risk index and a preset risk threshold, outputting a control instruction.

[0008] Preferably, the dynamic visual feature vector comprises: a global shear intensity and a structural entropy rate.

[0009] Preferably, the determination of the global shear intensity comprises: calculating an optical flow field between consecutive image frames in the video image sequence; based on the optical flow field, calculating a mean value of a spatial gradient norm of the optical flow velocity field as the global shear intensity.

[0010] Preferably, the determination of the structural entropy rate comprises: calculating a gray level co-occurrence matrix of a single frame image in the video image sequence to obtain a Shannon entropy; based on the Shannon entropy, calculating a first-order derivative in the time dimension as the structural entropy rate.

[0011] Preferably, the static feature vector comprises: a surface flatness index and an average optical flow velocity amplitude.

[0012] Preferably, the intrinsic rheological state index is calculated by linear combination of the global shear intensity and the structural entropy rate.

[0013] Preferably, the output control instruction comprises: if the comprehensive risk index is higher than the risk threshold, triggering a high-risk alarm and generating a preventive control instruction; if the comprehensive risk index is not higher than the risk threshold, not generating a preventive control instruction.

[0014] A concrete mixing main machine visual monitoring system, comprising: an image sequence acquisition unit configured to acquire a video image sequence of concrete moving in the mixing main machine in real time; a feature extraction unit configured to extract a dynamic visual feature vector and a static feature vector based on the video image sequence; a state identification unit configured to calculate an intrinsic rheological state index based on the dynamic visual feature vector and a preset dynamic rheological-visual feature coupling model; a basic prediction unit configured to calculate a basic slump prediction value based on the static feature vector and a preset static correlation model; The correction calculation unit is used for combining the intrinsic rheological state index and the basic slump prediction value, determining a final correction slump through a preset correction function; The risk assessment unit is used for calculating a comprehensive risk index according to the final correction slump, the basic slump prediction value and the intrinsic rheological state index. The instruction generation unit is used for outputting a control instruction based on the comprehensive risk index and a preset risk threshold.

[0015] The present application provides a concrete mixing host visual monitoring system and method, which has the following improvements and advantages compared with the prior art. 1. The present application innovatively extracts dynamic and static visual feature vectors in parallel; the static feature vector includes a surface flatness index and an average optical flow velocity amplitude, which is used to quantify the traditional macroscopic flow form that can be perceived by the naked eye, and a basic slump prediction value is calculated based on the static feature vector; the prediction value constitutes an initial benchmark evaluation of the workability of the concrete; the present application introduces a dynamic visual feature vector, which includes a global shear strength and a structural entropy rate; the global shear strength quantifies the shear deformation rate of the material as a whole from a macroscopic perspective by analyzing the spatial gradient of the optical flow velocity field; the structural entropy rate quantifies the intensity of the reorganization of the internal component structure of the material from a microscopic perspective by calculating the time derivative of the image Shannon entropy; the cooperative combination of the two features can deeply capture the intrinsic rheological characteristics triggered by chemical admixtures that cannot be perceived by traditional visual methods. 2. The present application can calculate an intrinsic rheological state index; the index quantifies the complex rheological behavior as a physical quantity that can be indirectly measured; the essence of the present application is to use the intrinsic rheological state index to nonlinearly correct the aforementioned basic slump prediction value through a preset correction function; the correction mechanism only applies effective adjustment when the intrinsic rheological state of the concrete significantly deviates from the normal benchmark, thereby achieving accurate compensation of the basic prediction deviation and obtaining a highly accurate correction slump. 4. The present application is not simply a state prediction, but establishes a quantitative risk assessment and control mechanism; a comprehensive risk index is calculated through an algorithm that comprehensively considers the abnormal degree of the rheological state and the deviation of the visual prediction; the index converts the vague construction risk into an objective and quantifiable evaluation index; when the index exceeds a preset risk threshold, the system can automatically trigger a high-risk alarm and generate a preventive control instruction; this active intervention capability changes the monitoring system from a passive state observer to an active risk manager, which can effectively prevent serious engineering accidents such as pumping pipe blockage and segregation bleeding caused by abnormal concrete performance, and greatly improves the intelligent level of concrete production and the reliability of quality control. BRIEF DESCRIPTION OF DRAWINGS

[0016] The application will be further explained in connection with the accompanying drawings and embodiments: Figure 1 is a flow chart of a concrete mixing main machine visual monitoring method of the application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the application clearer, the application will be further described in detail below with specific embodiments. Embodiment 1

[0018] Please refer to Figure 1 The application provides a concrete mixing main machine visual monitoring method, comprising: S1, real-time acquisition of a video image sequence of concrete movement in the mixing main machine; S2, extraction of dynamic visual feature vectors and static feature vectors based on the video image sequence; S3, calculation of an internal rheological state index based on the dynamic visual feature vectors and a preset dynamic rheological-visual feature coupling model; S4, calculation of a basic slump prediction value based on the static feature vectors and a preset static correlation model; S5, determination of a final corrected slump through a preset correction function in combination with the internal rheological state index and the basic slump prediction value; S6, calculation of a comprehensive risk index according to the final corrected slump, the basic slump prediction value and the internal rheological state index; S7, output of a control instruction based on the comprehensive risk index and a preset risk threshold value; The embodiment provides a complete method closed loop for concrete mixing main machine visual monitoring; In step S1, an image sequence acquisition unit is deployed inside or at the opening of the concrete mixing main machine, aiming to continuously capture the dynamic behavior of concrete in the mixing process; in the embodiment, the unit continuously records videos at a preset frame rate through an industrial high-speed camera, generating real-time video image sequences; the sequences provide raw data input for all subsequent analyses; In step S2, a feature extraction unit is configured to process the video image sequences acquired in the previous step; the purpose of the unit is to extract low-dimensional, quantified features that can represent different physical properties of concrete from high-dimensional pixel data; in the embodiment, the unit extracts two types of feature vectors in parallel: Dynamic visual feature vectors: this vector aims to quantify the microstructure changes and macroscopic shear behavior inside the concrete slurry, especially the strong non-Newtonian fluid effects introduced by chemical admixtures, which are difficult to distinguish by conventional visual methods; Static feature vector: This vector aims to quantify the macroscopic fluidity and surface morphology of concrete in visual presentation, which is usually the main basis for human experience to judge its workability; In step S3, the state recognition unit receives the dynamic visual feature vector and performs calculation according to a preset dynamic rheology-visual feature coupling model; the purpose of this model is to deconstruct the correlation between visual appearance and internal physical state, establish a mapping relationship between dynamic visual features and internal rheological state of concrete, and thus diagnose the real physical state; in this embodiment, the model is used to calculate an internal rheological state index; the internal rheological state index refers to a scalar for quantifying the internal rheological behavior activity or rate of concrete, and its role is to provide an indirectly measurable index for the missing rheological state dimension of the traditional visual model, which is highly sensitive to the thixotropy and shear thinning effects caused by chemical admixtures; the establishment of the preset dynamic rheology-visual feature coupling model is derived from a series of offline calibration experiments: by simultaneously performing laboratory rheometer tests and video collection in the target mixer on multiple groups of concrete samples containing different amounts of admixtures, the specific correlation between the visual feature calculation value and the rheometer measured value, such as the shear thinning index, is optimized as the optimization goal, and the model parameters are solved and fixed by regression analysis method; In step S4, the basic prediction unit receives the static feature vector and performs calculation according to a preset static correlation model; the purpose of this model is to simulate traditional human experience and establish a basic correlation between the visual apparent fluidity of concrete and its physical workability, i.e. the slump; in this embodiment, the model is used to calculate a basic slump prediction value; the basic slump prediction value refers to the slump value predicted according to the visual macroscopic fluidity without considering complex rheological effects, and its role is to provide an initial, uncorrected baseline prediction; the establishment of the preset static correlation model is derived from experiments on a large number of baseline concrete samples without high-efficiency admixtures, and the static feature values calculated from the video and the physically measured slump values are calibrated by regression analysis; In step S5, the correction calculation unit collects the internal rheological state index and the basic slump prediction value obtained in the previous steps; this unit performs operation through a preset correction function, and its purpose is to use the non-Newtonian fluid effects quantified by the internal rheological state index and ignored by the basic prediction model to correct the deviation of the basic slump prediction value; in this embodiment, the function calculates the final corrected slump; the corrected slump refers to the final prediction value of the real workability of concrete considering the visual apparent fluidity and internal rheological state; the structure and parameters of the preset correction function are carefully designed to ensure that the correction effect is significantly effective only when the internal rheological state deviates significantly from the normal baseline, thereby achieving precise compensation; In step S6, the risk assessment unit receives the final corrected slump, the base slump prediction value and the intrinsic rheological state index; the purpose of the unit is to quantify the potential construction risk caused by the disconnection between the visual representation and the true state; in this embodiment, a comprehensive risk index is calculated by a specific algorithm; the comprehensive risk index refers to a dimensionless index, which is used to comprehensively evaluate the abnormality degree of the rheological state and the deviation degree of the visual prediction caused thereby, and the higher the value is, the greater the potential risk is; In step S7, the instruction generation unit makes a decision on the comprehensive risk index calculated in the foregoing step; the purpose of the unit is to convert the quantitative risk assessment into specific and executable production intervention instructions; in this embodiment, the index is compared with a preset risk threshold; the source of the preset risk threshold is the distribution of the comprehensive risk indexes corresponding to the concrete batches that have appeared problems such as pumping pipe blockage and segregation bleeding in the history of statistical analysis, so as to determine the critical value with statistical significance; based on the comparison result, the system outputs the corresponding control instructions; The method proposed in the application forms a complete diagnostic-predictive-correction-risk control technical closed loop by extracting dynamic and static visual features in parallel and respectively used for diagnosing the intrinsic rheological state and predicting the base workability, and then using the former to correct the latter; the method solves the fundamental problem in the prior art that the visual monitoring is seriously disconnected from the true workability due to the introduction of chemical admixtures, realizes the quantitative diagnosis of the intrinsic rheological state of the concrete and the accurate prediction of the workability index, and can automatically generate preventive control instructions based on the quantitative risk assessment, thereby significantly improving the intelligent level of the concrete production and the reliability of the quality control.

[0019] The dynamic visual feature vector includes: global shear strength and structural entropy rate; In this embodiment, the composition of the dynamic visual feature vector is limited; the vector at least contains two core components: global shear strength and structural entropy rate; The global shear strength is defined as a scalar obtained by calculating the optical flow field between consecutive image frames and calculating the spatial gradient norm of the optical flow velocity field; the index aims to quantize the average shear deformation rate of the concrete material under the driving of the stirring blade from a macroscopic perspective; higher global shear strength usually means that the overall macroscopic fluidity of the material is stronger, or that the material is experiencing a severe shear thinning process; The structural entropy rate is defined as a scalar obtained by first calculating the gray level co-occurrence matrix of a single frame image to obtain the Shannon entropy representing the texture complexity, and then calculating the first-order derivative of the Shannon entropy of consecutive frames in the time dimension; the index aims to quantize the degree of reorganization of the relative position relationship between the internal aggregates, mortar and other components of the concrete from a microscopic perspective; higher structural entropy rate usually means that the internal structure of the material is accelerating the deconstruction and reorganization, which is highly related to the rheological behavior such as thixotropy. By combining the macroscopic global shear strength with the microscopic structural entropy rate, the dynamic visual feature vector of the embodiment can more comprehensively and profoundly capture the complex rheological phenomena caused by chemical additives; the global shear strength focuses on the macroscopic result of the shear rate, while the structural entropy rate focuses on the microscopic process of structural reorganization, and the two complement each other to provide more dimensionally rich and more reliable input for subsequent accurate identification of the internal rheological state, thereby improving the accuracy of the index diagnosis of the internal rheological state.

[0020] The determination of the global shear strength includes: calculating the optical flow field between consecutive image frames in the video image sequence; based on the optical flow field, calculating the mean value of the spatial gradient norm of the optical flow velocity field as the global shear strength; In the embodiment, the calculation steps of the global shear strength are described in detail; The calculation process includes: calculating the optical flow field between consecutive image frames in the video image sequence; the optical flow field refers to a two-dimensional vector field, where each vector represents the motion displacement of a point on the image between two consecutive frames, i.e. a very short time interval In this embodiment, a mature optical flow estimation algorithm is used to process every two consecutive image frames in the collected video sequence to obtain a velocity vector field covering the entire image area ; Based on the above optical flow field, the mean value of the spatial gradient norm of the optical flow velocity field is calculated; the spatial gradient of the optical flow velocity field refers to the rate of change of the velocity vector field in the spatial coordinates , which reflects the velocity difference between adjacent material points and is directly related to the strength of shear deformation; in this embodiment, the Jacobian matrix of the calculated velocity field is calculated, and the norm of the matrix is further calculated, which is the shear strength of each point; the shear strength values of all pixel points in the image are spatially averaged, and the mean value is defined as the global shear strength ; This method of determining the global shear strength directly maps the concept of shear rate in the physical world to a calculable image feature through optical flow analysis technology; instead of simply measuring the average velocity, it accurately captures the relative deformation strength caused by the velocity difference within the material by calculating the spatial gradient of the velocity field; this method is more sensitive and direct in response to rheological effects such as shear thinning, thereby providing a more explicit physical meaning and more accurate quantification of the macroscopic feature for identifying the internal rheological state.

[0021] The determination of the structural entropy rate includes: calculating the gray level co-occurrence matrix of a single frame of image in the video image sequence to obtain the Shannon entropy; Based on the Shannon entropy, the first derivative in time dimension is calculated as the structural entropy rate; In this embodiment, the calculation steps of the structural entropy rate are described in detail; The calculation process includes: calculating the gray level co-occurrence matrix (GLCM) of a single frame of image in the video image sequence to obtain the Shannon entropy; the GLCM is a matrix describing the distribution of pixel pairs with a specific gray level in the image, which is a classic method for analyzing image texture; in this embodiment, the GLCM of each frame of image in the video sequence is calculated; then, the Shannon entropy is calculated based on the matrix ; the Shannon entropy Herein, it refers to a scalar for quantifying the texture complexity and disorder degree of the image, which serves to evaluate the randomness of the visual texture of the concrete surface formed by the aggregate and mortar; a high entropy value usually corresponds to a rough and complex texture surface; Based on the above-mentioned Shannon entropy, the first derivative in time dimension is calculated; since the instantaneous Shannon entropy has been calculated for each frame of image in the video sequence , the time series of the entropy value with respect to time is obtained; in this embodiment, the first derivative of time is approximately calculated by using numerical methods such as finite difference method on the time series, and the result is defined as the structural entropy rate ; This method of determining the structural entropy rate ingeniously uses the entropy in information theory to quantify the visual representation of the concrete microstructure; by further calculating the time variation rate of the entropy, the method can capture the dynamic process from order to disorder or vice versa rather than a static snapshot; this is particularly effective for representing the rheological properties such as thixotropy which are directly related to the structural reorganization rate, and provides a microscopic dynamic perspective that the traditional visual methods cannot achieve for identifying the internal rheological state. Embodiment 2

[0022] The static feature vector includes: a surface flatness index and an average optical flow velocity amplitude; In this embodiment, the composition of the static feature vector is limited; the vector at least contains two core components: a surface flatness index and an average optical flow velocity amplitude; The surface flatness index is defined as a dimensionless scalar for quantifying the degree of the surface tending to be flat during the mixing process of the concrete; the purpose is to capture the ability of the concrete to resist plastic deformation under the action of gravity, which is closely related to the yield stress; in this embodiment, it can be calculated by analyzing the edge gradient distribution or frequency energy distribution of the image; Calculation method based on image edge gradient statistics The physical intuition of this method is that the more uneven and rough the concrete surface is, the richer and sharper the texture edges it presents in the image are, and thus the higher the overall gradient strength is.

[0023] For a single gray-scale image Apply a standard edge detection operator, such as Sobel or Canny operator, to calculate the gradient magnitude of each pixel in the image, and obtain the gradient map ; Calculate the spatial average of the gradient magnitudes of all pixels in the entire image, or in a pre-defined region of interest (ROI) The calculation formula is: where, is the total number of pixels involved in the calculation; is the gradient magnitude of the i-th pixel in the image; is the spatial coordinate of the pixel; Since the surface flatness index should be positively correlated with the flatness, while the average gradient should be negatively correlated with the flatness, a reciprocal function relationship can be used to construct ; For example, the following formula can be used for calculation:

[0024] where, is a normal constant calibrated through experiments, and its dimension is the inverse of the dimension of the average gradient to ensure that is a dimensionless quantity; this formula ensures that when the surface tends to be absolutely flat ; the rougher the surface is , the lower the value of ; The surface of concrete with poor fluidity and high plasticity will be rougher and more uneven, corresponding to a lower value of ; before calculation, this index will be normalized; The average optical flow velocity magnitude , defined as a scalar obtained by spatially averaging the magnitudes of all velocity vectors in the aforementioned calculated optical flow field; the purpose is to macroscopically evaluate the overall movement speed of the concrete material, which is the most intuitive visual representation of fluidity; a higher value of usually corresponds to better fluidity of the concrete; By combining the surface flatness index reflecting the static state with the average optical flow velocity amplitude reflecting the dynamic trend, the static feature vector of the embodiment can more robustly evaluate the macroscopic apparent fluidity of the concrete; the surface flatness focuses on the plastic behavior of the material after it is left for a short period of time, while the average optical flow velocity focuses on the overall rate of the material in motion; the combination of the two can provide more comprehensive visual information for the basic slump flow prediction model, thereby improving the accuracy and robustness of the basic prediction value A more accurate benchmark value is a prerequisite for achieving final high-precision prediction.

[0025] The intrinsic rheological state index is calculated by linear combination of the global shear strength and the structural entropy rate; In the embodiment, the calculation paradigm of the intrinsic rheological state index is clarified, that is, a linear combination model is used; the model is based on the physical hypothesis that strong shear thinning or thixotropic effect must be manifested in the macroscopic increase of shear rate, which is characterized, while in the microcosmic aspect, it is accompanied by accelerated deconstruction and recombination of internal structure, which is characterized; The calculation formula of the intrinsic rheological state index is as follows: Wherein, : intrinsic rheological state index, physical dimension of reciprocal time , used to represent the activity or rate of rheological behavior; : global shear strength, dimension of ; : structural entropy rate, dimension of ; : dimensionless weight coefficient; the value is not arbitrarily set, but is obtained through a series of offline calibration experiments; in the calibration process, the Pearson correlation coefficient between the calculated value and the true value of the rheological performance measured by the laboratory rheometer is maximized as the optimization objective, and the optimal coefficient pair is solved by least squares regression analysis; Relatedly, the calculation of the basic slump flow prediction value and the final corrected slump flow also involves specific models; The calculation formula of the basic slump flow is as follows:

[0026] Wherein, : basic slump flow, physical dimension of length ; : surface flatness index, dimensionless; : average optical flow velocity amplitude, dimension of length ; : weight coefficient and bias constant, both dimension of length ; : weight coefficient, dimension of time T to ensure dimension of length ; The above parameters are calibrated by multiple linear regression analysis of the video calculated characteristic values and the physical measured slump values of a large number of reference concrete samples without high-performance admixtures; The final corrected slump is calculated according to the following formula:

[0027] : final corrected slump, physical dimension of length mm; : basic slump prediction value, calculated by the previous formula; : intrinsic rheological state index, calculated by the previous formula; : reference rheological state index, a reference value representing normal rheological state, dimension of ; determined by a large number of experiments on concrete batches without or with conventional dosage of admixtures and with qualified performance, and the average level of values is determined; : refers to the base of natural logarithm, which is a mathematical constant; : sensitivity coefficient of correction function, physical dimension of time to ensure that the exponential term is dimensionless; the calibration target of the value is to minimize the error between the corrected and the measured slump value of the sample containing admixtures; The intrinsic rheological state index is constructed as a linear combination of and , providing a calculation framework that can effectively integrate macro and micro rheological information; through offline calibration, the The model is highly sensitive to the strong non-Newtonian effect introduced by chemical admixtures, but not sensitive to the viscosity change caused by simply adding water, thus successfully decoupling the rheological state from the traditional visual features; the subsequent S-shaped correction function uses this decoupled exponent to achieve a nonlinear adjustment mechanism that only effectively corrects when the rheological state deviates significantly from the baseline, greatly improving the accuracy of the final slump prediction, especially when dealing with modern high-performance concrete containing various high-efficiency admixtures.

[0028] Output control instructions, including: If the comprehensive risk index is higher than the risk threshold, trigger a high-risk alarm and generate preventive control instructions; If the comprehensive risk index is not higher than the risk threshold, do not generate preventive control instructions; In this embodiment, the decision-making logic and instruction generation mechanism based on the comprehensive risk index are elaborated in detail; The calculation formula is as follows:

[0029] Wherein, : Comprehensive risk index, dimensionless; : Intrinsic rheological state index, value calculated from the previous step; : Baseline rheological state index, value is a preset parameter; : Basic slump prediction value, value calculated from the previous step; : Final corrected slump, value calculated from the previous step; : Dimensionless risk coefficient, a constant obtained by analyzing historical data and used to adjust the overall magnitude of the risk index; The decision-making process is as follows: Risk calculation: The risk assessment unit calculates the value of the comprehensive risk index in real time; In the calculation, to prevent the denominator from being zero, when the basic slump prediction value is less than a preset minimum positive number , special processing should be performed, such as setting the risk index to a preset maximum value or triggering a specific alarm; Threshold comparison: Compare the calculated with the preset risk threshold ; is a critical value, and its source is the corresponding value distribution, thereby determining the limit that can effectively distinguish high risk from normal state; instruction generation: If , it is determined that the current batch of concrete has high construction risk; the system automatically triggers a high-risk alarm and displays warning information on the control interface; at the same time, the instruction generation unit queries the preset rule library, for example, generates specific and preventive control instructions, such as rheological state abnormality, suggests extending the mixing time by 20 seconds, rechecks the homogeneity or the serious decoupling between the visual and the rheological state, the high risk of pumping, suggests suspending pumping and sampling for rechecking; If , it is determined that the current batch of concrete state is within the acceptable range, and no preventive control instruction is generated, and the production process continues normally. This method converts the fuzzy and qualitative risk concept into quantifiable and comparable indicators through a mathematical model that comprehensively considers the rheological state abnormality degree and the visual prediction deviation degree, which has a clear physical meaning. Based on the threshold value determined based on the indicators and statistics , decisions are made, which changes the risk control from relying on artificial experience to an automated and standardized process; this approach not only greatly improves the timeliness and accuracy of risk identification, but also provides clear disposal suggestions for operators through the generation of specific preventive instructions, thereby effectively avoiding serious engineering accidents such as pumping pipe blockage and segregation and bleeding caused by abnormal concrete rheological properties.

[0030] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. 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 equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A visual monitoring method for a concrete mixing plant, characterized in that, include: S1, real-time acquisition of video image sequences of concrete moving inside the mixing host; S2, based on video image sequences, extracts dynamic visual feature vectors and static feature vectors; S3, based on the dynamic visual feature vector and the preset dynamic rheology-visual feature coupling model, calculates the intrinsic rheological state index; S4, based on the static feature vector and the preset static correlation model, calculates the predicted value of the basic slump. S5, combining the intrinsic rheological state index and the predicted basic slump, determines the final corrected slump using a preset correction function; S6. Calculate the comprehensive risk index based on the final corrected slump, the predicted basic slump, and the intrinsic rheological state index. S7 outputs control commands based on the comprehensive risk index and preset risk thresholds.

2. The visual monitoring method for a concrete mixing host according to claim 1, characterized in that, The dynamic visual feature vector includes: global shear strength and structural entropy change rate.

3. The visual monitoring method for a concrete mixing host according to claim 2, characterized in that, The determination of the global shear strength includes: Calculate the optical flow field between consecutive image frames in a video image sequence; Based on the optical flow field, the mean value of the spatial gradient norm of the optical flow velocity field is obtained as the global shear strength.

4. The visual monitoring method for a concrete mixing host according to claim 2, characterized in that, The determination of the structural entropy change rate includes: Calculate the gray-level co-occurrence matrix of a single frame in a video image sequence to obtain the Shannon entropy; Based on Shannon entropy, the first derivative is calculated in the time dimension to serve as the rate of change of structural entropy.

5. The visual monitoring method for a concrete mixing host according to claim 1, characterized in that, The static feature vector includes: surface smoothness index and average optical flow velocity amplitude.

6. The visual monitoring method for a concrete mixing host according to claim 2, characterized in that, The intrinsic rheological state index is calculated by a linear combination of global shear strength and structural entropy change rate.

7. The visual monitoring method for a concrete mixing host according to claim 1, characterized in that, The output control commands include: If the overall risk index is higher than the risk threshold, a high-risk alert will be triggered, and preventative control instructions will be generated. If the overall risk index is not higher than the risk threshold, no preventative control instructions will be generated.

8. A visual monitoring system for a concrete mixing plant, based on the visual monitoring method for a concrete mixing plant according to any one of claims 1-7, characterized in that, include: The image sequence acquisition unit is used to acquire video image sequences of concrete moving inside the mixing host in real time. The feature extraction unit is used to extract dynamic visual feature vectors and static feature vectors based on video image sequences; The state identification unit is used to calculate the intrinsic rheological state index based on the dynamic visual feature vector and the preset dynamic rheological-visual feature coupling model. The basic prediction unit is used to calculate the basic collapse prediction value based on the static feature vector and the preset static correlation model. The correction calculation unit is used to combine the intrinsic rheological state index and the basic slump prediction value, and determine the final corrected slump through a preset correction function. The risk assessment unit is used to calculate the comprehensive risk index based on the final corrected slump, the predicted base slump, and the intrinsic rheological state index. The instruction generation unit is used to output control instructions based on the comprehensive risk index and preset risk thresholds.

Images