Rapid sludge thin-layer drying method based on industrial image
By collecting and analyzing key image data of the thin-layer dryer in real time and adjusting the sludge feed rate and rotor speed, the problems of low sludge drying efficiency and unstable quality were solved, and efficient and stable operation of the equipment was achieved.
Patent Information
- Application Number
- CN202510749244.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-06
- Publication Date
- 2025-09-12
- Estimated Expiration
- 2045-06-06
AI Technical Summary
Existing sludge thin-layer drying devices have low drying efficiency and unstable quality when faced with changes in temperature, humidity and material properties. In addition, their reliance on predictive models leads to delayed responses and makes it impossible to respond to changes in sludge properties and operating conditions in a timely manner.
By collecting the moisture content of the thin-layer dryer's mud, steam images at the steam outlet, inner drum wall images, and blade images in real time, the steam density, grayscale value, and dry mud area are extracted. Abnormal events are determined using correlation thresholds, and the sludge feed rate and rotor speed are adjusted to form a closed-loop optimization control.
It achieves uniform sludge drying, improves drying efficiency and quality stability, avoids response lag problems caused by over-reliance on prediction models, and ensures that the equipment is always in the best operating state.
Smart Images

Figure CN120622784A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sludge treatment, and in particular to a sludge rapid thin-layer drying method based on industrial images. Background Art
[0002] With the acceleration of urbanization and the strengthening of environmental awareness, the issue of sludge treatment and disposal has gradually become a focus of attention. Sludge dryers, especially thin-layer dryers, use steam sludge drying method to achieve continuous feeding and discharging. They have the advantages of high efficiency, low energy consumption and high safety, and can be independently designed according to specific sludge treatment needs. However, in actual operation, the efficiency of thin-layer dryers is easily affected by various factors such as temperature, humidity and material properties, which in turn reduces the drying efficiency and affects the performance of the entire sludge treatment system. In addition, since thin-layer sludge drying technology mainly relies on the precise control of parameters such as feed rate and rotation speed to achieve the sludge drying goal, improper control may cause unstable quality of the dried product, such as caking or discoloration.
[0003] Patent document with publication number CN118084292A discloses a high-efficiency operation device and control method for thin-layer sludge drying, including: a feeding system, a drying system, an energy recovery system, a steam system, an exhaust gas emission system and a control system; wherein, the feeding system is used to introduce the sludge to be dried; the drying system is used to dry the sludge transported by the feeding system; the steam system is used to provide the heat energy required by the drying system; the energy recovery system is used to recover the waste heat generated in the drying system; the exhaust gas emission system is used to treat the exhaust gas generated by the drying system; the control system includes a data acquisition module, a prediction module and a parameter control module, wherein the data acquisition module is configured to collect real-time data during the sludge treatment process; the prediction module is configured to predict the moisture content of the thin-layer drying sludge, the outlet temperature of the exhaust gas heat exchanger and the amount of condensate generated based on historical data and a prediction model established by an artificial neural network; the parameter control module is configured to automatically adjust the operating parameters of the drying system according to the output results of the prediction module and real-time data.
[0004] It can be seen that the efficient operation device for sludge thin layer drying has the following problems: the accuracy of the prediction results not only depends on the accuracy of data collection, but is also closely related to the representativeness of historical data and the degree of model training; it relies on the prediction model and real-time data to automatically adjust the operating parameters of the drying system. When changes occur, it takes time to adapt to the new working conditions, resulting in a response lag of the control system. Summary of the Invention
[0005] To this end, the present invention provides a rapid thin-layer sludge drying method based on industrial images, which is used to overcome the problems of low drying efficiency and unstable drying quality caused by excessive reliance on prediction models and the inability to respond to changes in sludge characteristics and operating conditions in a timely manner through the collection of industrial images, multidimensional data analysis and dynamic adjustment mechanisms.
[0006] To achieve the above objectives, the present invention provides a method for rapid thin-layer sludge drying based on industrial images, comprising:
[0007] Real-time collection of the sludge moisture content at the discharge port, steam images at the steam discharge port, images of the inner drum wall at various detection points, and blade images during the operation of the thin-layer dryer based on a preset sludge feed rate and a preset rotor speed;
[0008] Extracting the vapor density and the grayscale value of the vapor color of each area in the vapor image, and extracting the sludge thickness in the cylinder wall image and the dry mud area of the dry mud attached to the blade surface in the blade image;
[0009] Determining the occurrence of an abnormal event based on the vapor density, the grayscale value, the dry mud area, and a preset correlation threshold, and obtaining an abnormality determination result;
[0010] determining the abnormality type according to the abnormality determination result, the sludge thickness, and the dry sludge area;
[0011] adjusting the preset sludge feed speed according to the abnormality type and the total sludge thickness to obtain an adjusted sludge feed speed, and adjusting the preset rotor speed according to the adjusted sludge feed speed and the sludge thickness to obtain an adjusted rotor speed;
[0012] Based on the adjusted sludge inlet speed and the adjusted rotor speed, the preset correlation threshold is corrected according to the sludge moisture content and the vapor density within a preset correction time to obtain a corrected correlation threshold;
[0013] The operation of the thin layer dryer is controlled based on the adjusted sludge feed rate and the adjusted rotor speed that are re-determined based on the modified correlation threshold.
[0014] Furthermore, the process of determining that an abnormal event occurs based on the vapor density, the grayscale value, the dry mud area, and a preset correlation threshold and obtaining an abnormality determination result includes:
[0015] Calculating the standard deviation of all the vapor densities to obtain density dispersion;
[0016] When the density dispersion is greater than a preset dispersion threshold, the current timestamp is recorded, and when the density dispersion is less than or equal to the preset dispersion threshold, the recording is stopped to obtain a duration;
[0017] When the duration is greater than a preset duration threshold, it is determined that an abnormal event occurs according to the gray value, the dry mud area, and a preset correlation threshold to obtain an abnormality determination result.
[0018] Furthermore, the process of determining that an abnormal event occurs based on the grayscale value, the dry mud area, and a preset correlation threshold and obtaining an abnormality determination result includes:
[0019] Calculating the standard deviation of all the grayscale values to obtain color unevenness;
[0020] Counting all the color unevenness within a preset determination time to obtain an unevenness data set;
[0021] Counting all the dry mud areas within the preset determination time to obtain an area data set;
[0022] Calculating a correlation coefficient between the unevenness dataset and the area dataset to obtain a change correlation;
[0023] When the change correlation is greater than the preset correlation threshold, it is determined that an abnormal event occurs, and an abnormality determination result is obtained.
[0024] Furthermore, the type of the abnormal event is determined to be local excessive drying according to the abnormality determination result, the sludge thickness, and the dry sludge area. The process of obtaining the abnormality determination result includes:
[0025] When an abnormality determination result is obtained, the standard deviation of the sludge thickness from the initial moment to each moment within the preset determination time period is calculated to obtain a plurality of thickness fluctuation values;
[0026] Calculating the standard deviation of the dry mud area from the initial moment to each moment within the preset determination time period in the past to obtain a plurality of area fluctuation values;
[0027] The type of the abnormal event is determined to be local excessive drying according to all the thickness fluctuation values and all the area fluctuation values, and an abnormality determination result is obtained.
[0028] Furthermore, the type of the abnormal event is determined to be local excessive drying according to all the thickness fluctuation values and all the area fluctuation values, and the process of obtaining the abnormality determination result includes:
[0029] Drawing a change curve of all the thickness fluctuation values to obtain a thickness fluctuation change curve;
[0030] Drawing a change curve of all the area fluctuation values to obtain an area fluctuation change curve;
[0031] Calculating the cosine similarity of the thickness fluctuation change curve and the area fluctuation change curve to obtain the change consistency;
[0032] When the change consistency is greater than the preset consistency threshold, the type of the abnormal event is determined to be local excessive drying, and an abnormality determination result is obtained.
[0033] Furthermore, the preset sludge feeding speed is adjusted according to the abnormality determination result and the total sludge thickness, and the process of adjusting the sludge feeding speed includes:
[0034] Calculating the average value of all the sludge thicknesses at each of the detection points on the cross section of the inner cylinder wall to obtain a thickness mean;
[0035] Drawing a change curve of all the thickness averages within a preset adjustment time to obtain a thickness change curve;
[0036] Calculating the slope change rate of the thickness change curve to obtain the thickness change rate;
[0037] The preset sludge feeding speed is adjusted according to the thickness change rate to obtain an adjusted sludge feeding speed.
[0038] Furthermore, the preset sludge feeding speed is adjusted according to the thickness change rate, and the process of adjusting the sludge feeding speed includes:
[0039] When the thickness change rate is greater than a preset change rate threshold, the preset sludge feeding speed is reduced according to the relative deviation between the thickness change rate and the preset change rate threshold and a preset feeding speed adjustment coefficient to obtain an adjusted sludge feeding speed.
[0040] Furthermore, the preset rotor speed is adjusted according to the sludge feed rate and the sludge thickness, and the process of adjusting the rotor speed includes:
[0041] Calculate the standard deviation of all the sludge thicknesses at each of the detection points on the vertical cross-section of the inner cylinder wall to obtain thickness dispersion;
[0042] When the thickness dispersion is greater than a preset dispersion threshold, the preset rotor speed is increased according to a relative deviation between the thickness dispersion and the preset dispersion threshold and a preset speed adjustment coefficient to obtain an adjusted rotor speed.
[0043] Furthermore, the process of correcting the preset correlation threshold according to the mud moisture content and the steam density within the preset correction time to obtain the corrected correlation threshold includes:
[0044] When the output mud moisture content is greater than a preset output mud moisture content threshold, calculating the standard deviation of the output mud moisture content within a preset correction time length to obtain a moisture content fluctuation value;
[0045] Calculate the standard deviation of all the vapor densities to obtain the corrected dispersion;
[0046] Calculating the average value of all the corrected dispersions within the preset correction time to obtain a density dispersion mean;
[0047] The preset correlation threshold is corrected according to the moisture content fluctuation value and the density dispersion mean to obtain a corrected correlation threshold.
[0048] Furthermore, the process of correcting the preset correlation threshold according to the moisture content fluctuation value and the density dispersion mean value to obtain the corrected correlation threshold includes:
[0049] Calculating a relative deviation between the moisture content fluctuation value and a preset moisture content fluctuation threshold value to obtain a fluctuation deviation;
[0050] Calculating the relative deviation between the density dispersion mean and the preset dispersion threshold to obtain a dispersion deviation;
[0051] The preset correlation threshold is reduced according to the fluctuation deviation, the dispersion deviation, the preset fluctuation deviation weight, the preset dispersion deviation weight, and the preset correction coefficient to obtain a corrected correlation threshold.
[0052] Compared with the prior art, the beneficial effects of the present invention lie in that, by collecting the moisture content of the sludge and key images of different positions in real time and extracting key data from the images, abnormal events are determined according to the vapor density, grayscale value, dry mud area and preset correlation threshold; further determining whether it is local over-drying and accurately locating the problem; adjusting the sludge feed rate and rotor speed based on the determined abnormal events and sludge thickness, optimizing the sludge drying process, and making the sludge evenly distributed and fully dried; using the moisture content of the sludge and the vapor density to correct the preset correlation threshold, so that subsequent abnormal judgments are more accurate, and the sludge feed rate and rotor speed are adjusted based on the corrected threshold to control the operation of the thin-layer dryer, forming a closed-loop optimization control, ensuring that the dryer is always in the best operating state, and effectively solving the problems of low drying efficiency and unstable drying quality caused by over-reliance on prediction models and inability to respond to changes in sludge characteristics and operating status in a timely manner.
[0053] Furthermore, the density dispersion is obtained by calculating the standard deviation of the steam density. The standard deviation of the steam density reflects the stability of the steam emission. When the density dispersion exceeds the preset dispersion threshold, it means that the fluctuation of the steam density has increased abnormally, which usually means that the drying process has become unstable, causing large fluctuations in the steam emission density. In addition, the duration of this state is greater than the preset duration threshold, indicating that it is a continuous problem rather than an accidental abnormality. It is necessary to further determine whether an abnormal event has occurred in order to accurately judge the abnormal event and take corresponding measures to adjust and optimize it to ensure the stable operation of the dryer.
[0054] Furthermore, by calculating the standard deviation of the grayscale values, we obtain color unevenness, which reflects the degree of variation in steam color across various regions. The statistical datasets are then aggregated to accumulate variations over time. The correlation coefficient between the two datasets is then calculated to obtain the variation correlation, which reveals the correlation between color variation and changes in the area of dried mud. When the variation correlation exceeds the preset correlation threshold, an abnormal event is determined, indicating a strong positive correlation between color unevenness and the area of dried mud. As color unevenness increases, the area of dried mud also increases, indicating that as the drying process progresses, sludge on the blades may fall off due to excessive drying, leading to an increase in steam impurities and, consequently, color unevenness. Simultaneously, the area of dried mud also increases as more areas are dried, indicating an abnormal drying process. At this point, an abnormal event is determined.
[0055] Furthermore, by calculating the standard deviation of sludge thickness and dry sludge area over a preset determination period, thickness fluctuation values and area fluctuation values are obtained, respectively. These fluctuation values reflect the degree of change in sludge thickness and dry sludge area over that period. Thickness fluctuation reflects the uniformity of sludge accumulation, while area fluctuation reflects the stability of the sludge adhesion range. By further analyzing the overall trend of these fluctuation values, it is possible to determine whether localized drying is excessive.
[0056] Furthermore, by drawing the thickness fluctuation change curve and the area fluctuation change curve, the changing trend of the sludge thickness and area at different positions can be intuitively observed. The cosine similarity of the two curves is calculated to obtain the change consistency, which can quantify the similarity of the change trends of the two. The calculation of cosine similarity is a prior art and will not be repeated here. When the change consistency is greater than the preset consistency threshold, it means that the thickness fluctuation and area fluctuation show a high degree of consistency in the change trend. This consistency usually indicates that the local drying is excessive, because the sludge in some areas loses water rapidly, resulting in the local thickness rapidly becoming thinner or even forming cavities, while some areas do not change much, resulting in increased thickness fluctuations. At the same time, the amount of dry mud attached to the blades will also increase as the sludge dries, causing area fluctuations. It can effectively identify abnormal events of local excessive drying and help to adjust the drying process in time.
[0057] Furthermore, by calculating the mean cross-sectional sludge thickness and plotting its variation curve, the dynamic changes in sludge thickness can be visually visualized; the slope change rate reflects the rate and trend of thickness change. Adjusting the sludge feed rate based on the thickness change rate ensures that the sludge feed volume matches the current drying capacity. Furthermore, adjusting the rotor speed based on the sludge thickness distribution along the vertical cross-section of the inner drum wall further optimizes the vertical sludge distribution and drying effect. This links the sludge feed rate to the rotor speed, enabling precise control of the drying process.
[0058] Furthermore, by monitoring the rate of change in sludge thickness, the accumulation rate of sludge on the inner drum wall can be promptly reflected. When the thickness change rate exceeds a preset threshold, the sludge feed rate is reduced by combining the relative deviation and adjustment coefficient to prevent excessive sludge accumulation and maintain the sludge thickness on the inner drum wall within a reasonable range. This ensures the dryer's drying efficiency and operational stability, avoids uneven drying and equipment failures caused by sludge accumulation, and enables precise dynamic control of the sludge feed rate.
[0059] Furthermore, adjusting the rotor speed based on the sludge feed rate and the sludge thickness distribution along the vertical cross-section of the inner drum wall can further optimize the vertical sludge distribution and drying effect. This links the sludge feed rate to the rotor speed, enabling refined control of the drying process. The thickness dispersion is calculated by calculating the standard deviation of the sludge thickness along the vertical cross-section, quantifying the sludge distribution uniformity. When the thickness dispersion exceeds a preset threshold, indicating uneven thickness at the top and bottom of the sludge, increasing the rotor speed based on the relative deviation and adjustment factor can enhance agitation, redistribute the sludge, and prevent localized accumulation or uneven drying.
[0060] Furthermore, by monitoring fluctuations in the mud moisture content and vapor density, the correlation threshold is dynamically adjusted. When the mud moisture content exceeds the standard, the fluctuation and the dispersed mean of the vapor density are calculated. The mud moisture content directly reflects the drying effect, while the vapor density reflects the stability of the drying process. Greater fluctuations in these two indicators indicate less stable equipment operation, requiring a lower correlation threshold to improve anomaly detection sensitivity. By combining these two indicators, the correlation threshold is adjusted to ensure stable and efficient equipment operation under different operating conditions.
[0061] Furthermore, the fluctuation deviation is calculated by calculating the relative deviation of the moisture content fluctuation value from a preset threshold, and the dispersion deviation is calculated by calculating the relative deviation of the density dispersion mean from a preset threshold. These two deviations reflect the degree of deviation in drying performance and process stability. The preset correlation threshold is then reduced based on the preset weight and correction factor to obtain the corrected threshold. Corrections based on moisture content and vapor density directly reflect the sludge drying performance and process stability, and the correlation threshold can better adapt to the actual operating conditions of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] Figure 1 This is a flow chart of the industrial image-based rapid thin-layer sludge drying method described in this embodiment;
[0063] Figure 2 This is a logic diagram for determining the occurrence of an abnormal event in this embodiment;
[0064] Figure 3 A decision logic diagram for determining an abnormality determination result in this embodiment;
[0065] Figure 4This is a decision logic diagram for adjusting the preset sludge inlet rate in this embodiment. DETAILED DESCRIPTION
[0066] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.
[0067] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.
[0068] See also Figure 1 As shown, it is a flow chart of the method for rapid thin-layer sludge drying based on industrial images described in this embodiment;
[0069] This embodiment provides a method for rapid thin-layer sludge drying based on industrial images, including:
[0070] Real-time collection of the sludge moisture content at the discharge port, steam images at the steam discharge port, images of the inner drum wall at various detection points, and blade images during the operation of the thin-layer dryer based on a preset sludge feed rate and a preset rotor speed;
[0071] Extracting the vapor density and the grayscale value of the vapor color of each area in the vapor image, and extracting the sludge thickness in the cylinder wall image and the dry mud area of the dry mud attached to the blade surface in the blade image;
[0072] Determining the occurrence of an abnormal event based on the vapor density, the grayscale value, the dry mud area, and a preset correlation threshold, and obtaining an abnormality determination result;
[0073] determining, based on the abnormality determination result, the sludge thickness, and the dry sludge area, that the type of the abnormal event is local excessive drying, and obtaining an abnormality determination result;
[0074] adjusting the preset sludge feed speed according to the abnormality determination result and the total sludge thickness to obtain an adjusted sludge feed speed, and adjusting the preset rotor speed according to the adjusted sludge feed speed and the sludge thickness to obtain an adjusted rotor speed;
[0075] Based on the adjusted sludge inlet speed and the adjusted rotor speed, the preset correlation threshold is corrected according to the sludge moisture content and the vapor density within a preset correction time to obtain a corrected correlation threshold;
[0076] The operation of the thin layer dryer is controlled based on the adjusted sludge feed rate and the adjusted rotor speed that are re-determined based on the modified correlation threshold.
[0077] The preset sludge feed rate and rotor speed described in this embodiment refer to the sludge feed rate and rotor rotation speed set before the thin-layer dryer is operational, based on factors such as equipment performance, sludge characteristics, and treatment objectives. As sludge properties change, the preset sludge feed rate and rotor speed must be adaptively adjusted to ensure drying effectiveness and efficiency.
[0078] The discharge port of the thin layer dryer is where the sludge is discharged after drying; the steam exhaust port is the channel for the discharge of water vapor and other exhaust gases generated during the drying process; the inner cylinder wall is the heat transfer part in contact with the sludge, providing the main heat exchange area and the carrier for forming a thin layer of sludge; the discharge port and steam exhaust port are located at both ends of the dryer respectively, the inner cylinder wall constitutes the internal space of the dryer, and the blades are located inside the inner cylinder wall, and the sludge is turned and renewed through rotation.
[0079] The moisture content of the sludge at the discharge port refers to the ratio of the mass of water contained in the sludge discharged from the discharge port to the total mass of the sludge, which is collected by an infrared moisture meter;
[0080] An industrial camera is set up at the steam exhaust port to collect images of the steam exhaust port and obtain a steam image to reflect the real-time status of steam emission. The "divided areas" refer to dividing the steam image into multiple grid-like areas to more accurately analyze the characteristics of the steam in each area.
[0081] Vapor density refers to the mass of vapor per unit volume. It is calculated by analyzing the grayscale histogram of the vapor image and setting a grayscale threshold to distinguish vapor from background. The grayscale value of vapor color refers to the value obtained by converting the color information in the vapor image into grayscale levels. It is used to quantify the depth of vapor color and is usually related to the particle concentration or pollutant content in the vapor. The lower the grayscale value, the darker the vapor color, which may mean that the vapor contains more pollutants or impurities. By converting the vapor image from RGB color space to grayscale color space, the grayscale value of each pixel can be directly read based on the converted grayscale image.
[0082] Endoscopes are evenly spaced along the inner cylinder wall to capture images of the dryer interior, producing images of the cylinder wall and blades. "Inspection points" refer to the specific locations of the endoscopes, evenly spaced along the inner cylinder wall, used to measure sludge thickness and the area of dry sludge adhered to the blade surfaces. In this embodiment, the endoscopes are evenly spaced vertically and horizontally along the inner cylinder wall, forming a grid of inspection points:
[0083] Vertical (height direction): Several rows of endoscopes are arranged at equal distances on the height of the cylinder wall, evenly distributed from the top to the bottom of the cylinder wall, to ensure that the changes in sludge thickness and dry mud adhesion at different height sections can be captured.
[0084] Transverse (circumferential / annular): Several rows of endoscopes are evenly spaced along the circumference of the cylinder wall, so that each row corresponds to an adjacent angular area to achieve full-circle monitoring without blind spots.
[0085] The intersections of vertical and horizontal rows are designated as specific inspection points. Endoscopes at each inspection point collect images of sludge thickness on the cylinder wall and dry sludge area on the blade surface. This vertical and horizontal grid layout simultaneously captures multi-point image data in both elevation and circumferential directions, providing comprehensive and balanced data support for the calculation of metrics such as dispersion and correlation.
[0086] Sludge thickness refers to the straight-line distance from the inner cylinder wall surface to the outer surface of the sludge layer. The cylinder wall image collected by the endoscope is grayscaled, and then the outer boundary of the sludge layer and the boundary of the inner cylinder wall are determined through the edge detection algorithm. The vertical distance between these two boundaries is measured to obtain the sludge thickness.
[0087] The dry mud area refers to the area occupied by the dry mud formed after the sludge attached to the leaf surface dries up. The leaf image is grayscaled, and then the sludge area is separated from the leaf surface. The number of pixels in the segmented sludge area is counted and then converted into the actual area according to the image resolution to obtain the dry mud area.
[0088] The preset correlation threshold is a critical value used to determine the degree of correlation between color unevenness and dry sludge area change. It depends on the nature of the sludge, the drying process requirements, historical equipment operation data, and the type and severity of the abnormal event, and is typically set between 0.6 and 0.9. In this embodiment, it is set to 0.8, which can more accurately screen data combinations with significant correlations, thereby improving the accuracy of abnormal event determination and reducing the possibility of misjudgment and omission.
[0089] The preset correction time is the length of time used to correct the preset relevance threshold. It depends on the operating characteristics of the thin-layer dryer, the sludge drying rate, and the required response speed, and is typically set between 5 and 30 minutes. In this embodiment, it is set to 10 minutes to ensure timely and effective correction of the relevance threshold, allowing the device to quickly respond to changes in operating conditions.
[0090] By collecting the moisture content of the sludge and key images of different positions in real time, and extracting the steam density, grayscale value of the steam color, sludge thickness and dry mud area attached to the blades from the images; then judging whether an abnormal event has occurred based on the collected steam density, grayscale value, dry mud area and preset correlation threshold, thereby obtaining an abnormal judgment result; then combining the abnormal judgment result, sludge thickness and dry mud area to determine whether it is local excessive drying; then, based on the determination of the abnormal event, adjusting the preset sludge feed speed and the preset rotor speed according to all sludge thicknesses to obtain adjusted sludge feed speed and rotor speed; then, within the preset correction time, correcting the preset correlation threshold according to the moisture content of the sludge and the steam density to obtain a corrected correlation threshold; finally, based on the corrected correlation threshold, re-determining the adjusted sludge feed speed and the adjusted rotor speed, and controlling the operation of the thin layer dryer according to these two adjusted parameters.
[0091] The underlying logical relationships between the various parameters follow the basic principles of conservation of mass and energy: the preset sludge feed rate and rotor speed determine the sludge residence time and mechanical shear strength within the dryer, affecting heat transfer efficiency. The solid content (or residual moisture content) at the discharge port reflects the overall degree of water evaporation and is positively correlated with the vapor density and grayscale value measured at the steam outlet—the more moisture, the denser the vapor, and the darker the grayscale. Simultaneously, the sludge thickness and dry sludge attachment area measured in the inner drum wall and blade images correspond to the local water removal rate and dry solid accumulation, respectively. Changes in their standard deviations and correlation coefficients reveal the unevenness of the drying process. Based on the dynamic feedback of these parameters, when the vapor density or grayscale fluctuations exceed a threshold, or when the consistency of changes in thickness and dry sludge area reaches a preset standard, it is judged as local overdrying. By adjusting the feed rate and rotation speed to change the residence time and shear effect, heat and mass transfer are rebalanced, thereby achieving optimal coupling between energy input and water removal efficiency, ensuring stable and efficient system operation.
[0092] By collecting the moisture content of the sludge and key images at different positions in real time and extracting key data from the images, abnormal events are determined based on the vapor density, grayscale value, dry mud area and preset correlation thresholds; further determining whether it is local over-drying and accurately locating the problem; adjusting the sludge feed rate and rotor speed based on the determined abnormal events and sludge thickness, optimizing the sludge drying process, and making the sludge evenly distributed and fully dried; using the moisture content of the sludge and the vapor density to correct the preset correlation threshold, making subsequent abnormality judgments more accurate, and controlling the operation of the thin-layer dryer based on the adjusted sludge feed rate and rotor speed determined based on the corrected thresholds, forming a closed-loop optimization control to ensure that the dryer is always in the best operating state, effectively solving the problems of low drying efficiency and unstable drying quality caused by over-reliance on prediction models and the inability to respond to changes in sludge characteristics and operating conditions in a timely manner.
[0093] Specifically, the process of determining the occurrence of an abnormal event based on the vapor density, the grayscale value, the dry mud area, and a preset correlation threshold and obtaining the abnormality determination result includes:
[0094] Calculating the standard deviation of all the vapor densities to obtain density dispersion;
[0095] When the density dispersion is greater than a preset dispersion threshold, the current timestamp is recorded, and when the density dispersion is less than or equal to the preset dispersion threshold, the recording is stopped to obtain a duration;
[0096] When the duration is greater than a preset duration threshold, it is determined that an abnormal event occurs according to the gray value, the dry mud area, and a preset correlation threshold to obtain an abnormality determination result.
[0097] The preset dispersion threshold is a critical value used to measure the degree of dispersion of vapor density changes. It depends on the specific model and specifications of the thin-layer dryer, the type of sludge being processed, and the operating requirements, and is typically set between 0.5 and 2.0. In this embodiment, it is set to 1.2, which effectively distinguishes normal operation from possible abnormal conditions. It is neither too sensitive to cause frequent false alarms nor too insensitive to miss important abnormal changes.
[0098] The preset duration threshold is the length of time that the density dispersion exceeds the threshold. This threshold depends on the operating characteristics of the dryer and the dynamics of the sludge drying process, and is typically set between 30 seconds and 5 minutes. In this embodiment, it is set to 1 minute to strike a balance between quickly responding to anomalies and avoiding false positives, thereby improving system stability and reliability.
[0099] The density dispersion is calculated by calculating the standard deviation of the steam density in each zone of the steam outlet. If the density dispersion exceeds the preset dispersion threshold, the current timestamp is recorded. Otherwise, recording stops and the duration is calculated. Finally, if the duration exceeds the preset duration threshold, the grayscale value of the steam color, the area of sludge attached to the blade surface, and the preset correlation threshold are further combined to comprehensively analyze and determine whether an abnormal event has occurred, thereby obtaining an abnormality determination result.
[0100] The density dispersion is obtained by calculating the standard deviation of the vapor density. The standard deviation of the vapor density reflects the stability of the vapor emission. When the density dispersion exceeds the preset dispersion threshold, it means that the fluctuation of the vapor density has increased abnormally, which usually means that the drying process has become unstable, causing large fluctuations in the vapor emission density. Moreover, the duration of this state is greater than the preset duration threshold, indicating that it is a continuous problem rather than an accidental abnormality. Further determination is needed to determine whether an abnormal event has occurred in order to accurately judge the abnormal event and take corresponding measures to adjust and optimize it to ensure the stable operation of the dryer.
[0101] Please continue reading Figure 2 As shown, it is a decision logic diagram for determining the occurrence of an abnormal event in this embodiment;
[0102] The process of determining the occurrence of an abnormal event based on the grayscale value, the dry mud area, and a preset correlation threshold and obtaining an abnormality determination result includes:
[0103] Calculating the standard deviation of all the grayscale values to obtain color unevenness;
[0104] Counting all the color unevenness within a preset determination time to obtain an unevenness data set;
[0105] Counting all the dry mud areas within the preset determination time to obtain an area data set;
[0106] Calculating a correlation coefficient between the unevenness dataset and the area dataset to obtain a change correlation;
[0107] When the change correlation is greater than the preset correlation threshold, it is determined that an abnormal event occurs, and an abnormality determination result is obtained.
[0108] The preset determination time is the length of time used to identify abnormal events based on data changes. It depends on the thin-layer dryer's operating cycle, the sludge drying rate, and the representativeness of the required data, and is typically set between 1 and 5 minutes. In this embodiment, it is set to 3 minutes to ensure data sufficiency while promptly reflecting changes in the dryer's operating status and ensuring timely identification of abnormal events.
[0109] The color unevenness is obtained by calculating the standard deviation of all grayscale values. Then, all color unevenness within the preset judgment time is counted to form an unevenness data set, and all dry mud areas within the preset judgment time are counted to form an area data set. Then, the correlation coefficient of the unevenness data set and the area data set is calculated to obtain the change correlation. Finally, when the change correlation is greater than the preset correlation threshold, it is determined that an abnormal event has occurred and an abnormal judgment result is obtained.
[0110] Color unevenness is calculated by calculating the standard deviation of the grayscale values, reflecting the degree of steam color variation across regions. A statistical dataset is then compiled to accumulate these variations over time. The correlation coefficient between the two datasets is then calculated to obtain the variation correlation, revealing the correlation between color variation and dry mud area. When the variation correlation exceeds the preset correlation threshold, it indicates a strong positive correlation between color unevenness and dry mud area. Increased color unevenness is associated with increased dry mud area, indicating that as the drying process progresses, sludge on the blades may fall off due to excessive drying, leading to increased steam impurities and, consequently, increased color unevenness. Simultaneously, the dry mud area increases as more areas are dried, indicating an abnormality in the drying process. This is when an abnormal event is determined to have occurred.
[0111] Specifically, the type of the abnormal event is determined to be local excessive drying according to the abnormality determination result, the sludge thickness, and the dry sludge area. The process of obtaining the abnormality determination result includes:
[0112] When an abnormality determination result is obtained, the standard deviation of the sludge thickness from the initial moment to each moment within the preset determination time period is calculated to obtain a plurality of thickness fluctuation values;
[0113] Calculating the standard deviation of the dry mud area from the initial moment to each moment within the preset determination time period in the past to obtain a plurality of area fluctuation values;
[0114] The type of the abnormal event is determined to be local excessive drying according to all the thickness fluctuation values and all the area fluctuation values, and an abnormality determination result is obtained.
[0115] By calculating the standard deviation of the sludge thickness from the initial moment to each moment within the preset judgment time period in the past, multiple thickness fluctuation values are obtained; then the standard deviation of the dry mud area at each moment within the same preset judgment time period is calculated to obtain multiple area fluctuation values; finally, the characteristics of all thickness fluctuation values and area fluctuation values are combined to determine whether it is local excessive drying.
[0116] By calculating the standard deviation of sludge thickness and dry sludge area over a preset determination period, we can determine thickness fluctuation and area fluctuation, respectively. These fluctuations reflect the degree of change in sludge thickness and dry sludge area over that period. Thickness fluctuation reflects the uniformity of sludge accumulation, while area fluctuation reflects the stability of sludge adhesion. Further analysis of the overall trend of these fluctuations can determine whether localized drying is excessive.
[0117] Please continue reading Figure 3 As shown, it is a decision logic diagram for determining an abnormality determination result in this embodiment;
[0118] The process of determining the type of the abnormal event as local excessive drying according to all the thickness fluctuation values and all the area fluctuation values, and obtaining the abnormality determination result includes:
[0119] Drawing a change curve of all the thickness fluctuation values to obtain a thickness fluctuation change curve;
[0120] Drawing a change curve of all the area fluctuation values to obtain an area fluctuation change curve;
[0121] Calculating the cosine similarity of the thickness fluctuation change curve and the area fluctuation change curve to obtain the change consistency;
[0122] When the change consistency is greater than the preset consistency threshold, the type of the abnormal event is determined to be local excessive drying, and an abnormality determination result is obtained.
[0123] The preset consistency threshold is used to determine the degree of similarity between the thickness fluctuation curve and the area fluctuation curve. It depends on the characteristics of the sludge processed by the thin-layer dryer, the fluctuation characteristics during normal operation of the equipment, and historical data on abnormal events. It is usually set between 0.7 and 0.95. In this embodiment, it is set to 0.85, which can accurately distinguish normal fluctuations from abnormal conditions, effectively avoiding misjudgments and missed judgments, and ensuring stable operation of the equipment.
[0124] The thickness fluctuation change curve is formed by plotting the change curves of all thickness fluctuation values, and the area fluctuation change curve is formed by plotting the change curves of all area fluctuation values. The cosine similarity of the two curves is then calculated to obtain the change consistency. Finally, if the change consistency is greater than the preset consistency threshold, the abnormal event is determined to be local excessive drying, and an abnormal determination result is obtained.
[0125] By drawing the thickness fluctuation change curve and the area fluctuation change curve, the changing trend of the sludge thickness and area at different positions can be intuitively observed. The cosine similarity of the two curves is calculated to obtain the change consistency, which can quantify the similarity of the change trends of the two. The calculation of cosine similarity is an existing technology and will not be repeated here. When the change consistency is greater than the preset consistency threshold, it means that the thickness fluctuation and area fluctuation show a high degree of consistency in the change trend. This consistency usually indicates that the local drying is excessive, because the sludge in some areas loses water rapidly, resulting in the local thickness rapidly becoming thinner or even forming cavities, while some areas do not change much, resulting in increased thickness fluctuations. At the same time, the amount of dry mud attached to the blades will also increase as the sludge dries, causing area fluctuations. It can effectively identify abnormal events of local excessive drying and help to adjust the drying process in time.
[0126] Specifically, the preset sludge feeding speed is adjusted according to the abnormality determination result and the total sludge thickness, and the process of adjusting the sludge feeding speed includes:
[0127] Calculating the average value of all the sludge thicknesses at each of the detection points on the cross section of the inner cylinder wall to obtain a thickness mean;
[0128] Drawing a change curve of all the thickness averages within a preset adjustment time to obtain a thickness change curve;
[0129] Calculating the slope change rate of the thickness change curve to obtain the thickness change rate;
[0130] The preset sludge feeding speed is adjusted according to the thickness change rate to obtain an adjusted sludge feeding speed.
[0131] The preset adjustment time is the period used to calculate and analyze changes in sludge thickness. It depends on the operating characteristics of the thin-layer dryer, the sludge drying rate, and the required adjustment response speed, and is typically set between 5 and 30 minutes. In this example, it is set to 10 minutes to ensure timely and effective adjustments to the sludge feed rate and rotor speed, allowing the equipment to quickly respond to changes in operating conditions and optimize drying results.
[0132] The cross section of the inner cylinder wall refers to the cross section formed by cutting along the horizontal direction of the inner cylinder wall (i.e., parallel to the ground), which shows the sludge thickness distribution in the horizontal direction of the inner cylinder. It can be used to analyze whether the sludge thickness distribution in the circumferential direction of the inner cylinder wall (horizontally surrounding the cylinder wall) is uniform, and whether there is local accumulation or missing.
[0133] The thickness mean is obtained by calculating the average value of all sludge thicknesses in the cross section; then a thickness change curve is drawn of the change of all thickness means within the preset adjustment time; then the thickness change rate is calculated by calculating the slope change rate of the thickness change curve; the preset sludge feed speed is adjusted according to the thickness change rate to obtain the adjusted sludge feed speed; finally, based on the adjusted sludge feed speed, the preset rotor speed is adjusted according to the total sludge thickness of the vertical section of the inner cylinder wall to obtain the adjusted rotor speed.
[0134] By calculating the average cross-sectional sludge thickness and plotting its variation curve, the dynamic changes in sludge thickness can be visually visualized; the slope change rate reflects the rate and trend of thickness change. Adjusting the sludge feed rate based on the thickness change rate ensures that the sludge feed volume matches the current drying capacity.
[0135] Please continue reading Figure 4 As shown, it is a decision logic diagram for adjusting the preset sludge feeding speed in this embodiment;
[0136] The process of adjusting the preset sludge feeding speed according to the thickness change rate to adjust the sludge feeding speed includes:
[0137] When the thickness change rate is greater than a preset change rate threshold, the preset sludge feed rate is reduced based on the relative deviation between the thickness change rate and the preset change rate threshold and the preset feed rate adjustment coefficient to obtain an adjusted sludge feed rate. Here, Q' = Q × [1 - k × (S - S0) / S0], where Q' is the adjusted sludge feed rate, Q is the preset sludge feed rate, k is the preset feed rate adjustment coefficient, S is the thickness change rate, and S0 is the preset change rate threshold.
[0138] The preset change rate threshold is used to determine whether the sludge thickness is changing too rapidly. It depends on the thin-layer dryer's processing capacity, sludge characteristics, and equipment stability, and is typically set between 0.1 and 0.5. In this embodiment, it is set to 0.3, which effectively detects excessively rapid sludge thickness changes and allows for timely adjustment of the sludge feed rate to prevent sludge accumulation or uneven distribution on the inner drum wall.
[0139] The preset feed rate adjustment coefficient is a factor used to control the adjustment range of the sludge feed rate. It depends on the response speed of the equipment, the fluidity of the sludge, and the required sensitivity of the adjustment. It is usually set between 0.5 and 0.9. In this embodiment, it is set to 0.7 to avoid excessive feed rate adjustment that may cause system instability and ensure that the sludge feed rate adjustment is timely and stable.
[0140] When the thickness change rate exceeds the preset change rate threshold, the relative deviation between the thickness change rate and the preset change rate threshold is calculated, and then the preset sludge feed rate is reduced according to the relative deviation and the preset feed rate adjustment coefficient to obtain the adjusted sludge feed rate.
[0141] By monitoring the sludge thickness change rate, the accumulation rate of sludge on the inner drum wall can be promptly reflected. When the thickness change rate exceeds the preset threshold, the sludge feed rate is reduced by combining the relative deviation and adjustment coefficient to prevent excessive sludge accumulation and maintain the sludge thickness on the inner drum wall within a reasonable range. This ensures the dryer's drying efficiency and operational stability, avoids uneven drying and equipment failure caused by sludge accumulation, and achieves precise dynamic control of the sludge feed rate.
[0142] Specifically, the process of adjusting the preset rotor speed according to the sludge feed rate and the sludge thickness to adjust the rotor speed includes:
[0143] Calculate the standard deviation of all the sludge thicknesses at each of the detection points on the vertical cross-section of the inner cylinder wall to obtain thickness dispersion;
[0144] When the thickness dispersion is greater than a preset dispersion threshold, the preset rotor speed is increased based on the relative deviation between the thickness dispersion and the preset dispersion threshold and the preset speed adjustment coefficient to obtain an adjusted rotor speed. Here, R' = R × [1 + a × (M - M0) / M0], where R' is the adjusted rotor speed, R is the preset rotor speed, a is the preset speed adjustment coefficient, M is the thickness dispersion, and M0 is the preset dispersion threshold.
[0145] The vertical cross-section of the inner cylinder wall refers to the cross-section formed by cutting along the vertical direction of the inner cylinder wall (i.e. perpendicular to the ground), which shows the distribution of sludge thickness in the vertical direction of the inner cylinder. It can be used to analyze the accumulation thickness of sludge at different height positions in the vertical direction of the inner cylinder wall, and whether there is uneven thickness in the upper and lower parts.
[0146] The preset dispersion threshold is a standard value used to determine the uniformity of sludge thickness distribution in a vertical cross-section. It depends on the designed sludge carrying capacity of the equipment and historical operating data statistics, and is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.2, which accurately identifies uneven sludge thickness at the top and bottom of the sludge, while being sensitive and not triggering adjustments too frequently.
[0147] The preset speed adjustment factor is a factor used to control the rotor speed adjustment range. It is typically set between 0.2 and 0.5, depending on the maximum speed limit of the rotor and the required response speed of the device. In this embodiment, it is set to 0.3 to achieve smooth speed adjustment and avoid impact on the device due to excessive adjustment range.
[0148] The thickness dispersion is obtained by calculating the standard deviation of the thickness of all sludge in the vertical section of the inner drum wall; if the thickness dispersion is greater than the preset dispersion threshold, the preset rotor speed is increased based on the relative deviation between the thickness dispersion and the preset dispersion threshold and the preset speed adjustment coefficient, and finally the adjusted rotor speed is obtained.
[0149] By adjusting the rotor speed based on the sludge feed rate and the sludge thickness distribution along the vertical cross-section of the inner drum wall, the vertical sludge distribution and drying effect can be further optimized. This links the sludge feed rate to the rotor speed, enabling refined control of the drying process. Calculating the standard deviation of the sludge thickness along the vertical cross-section yields the thickness dispersion, which quantifies the uniformity of the sludge distribution. When the thickness dispersion exceeds a preset threshold, indicating uneven thickness at the top and bottom of the sludge, increasing the rotor speed based on the relative deviation and adjustment factor enhances agitation, redistributes the sludge, and prevents localized accumulation or uneven drying.
[0150] Specifically, the process of correcting the preset correlation threshold according to the mud moisture content and the steam density within the preset correction time to obtain the corrected correlation threshold includes:
[0151] When the output mud moisture content is greater than a preset output mud moisture content threshold, calculating the standard deviation of the output mud moisture content within a preset correction time length to obtain a moisture content fluctuation value;
[0152] Calculate the standard deviation of all the vapor densities to obtain the corrected dispersion;
[0153] Calculating the average value of all the corrected dispersions within the preset correction time to obtain a density dispersion mean;
[0154] The preset correlation threshold is corrected according to the moisture content fluctuation value and the density dispersion mean to obtain a corrected correlation threshold.
[0155] The preset sludge moisture content threshold is used to determine whether the sludge moisture content exceeds the allowable range. It depends on the sludge treatment process requirements, subsequent treatment or disposal needs, and environmental protection standards, and is typically set between 30% and 60%. In this embodiment, it is set to 33% to ensure that the sludge moisture content is within a reasonable range and meets the requirements of subsequent treatment or disposal.
[0156] When the moisture content of the mud exceeds the preset threshold, the standard deviation of the moisture content of the mud within the preset correction time is calculated to obtain the moisture content fluctuation value; then the standard deviation of all steam densities is calculated to obtain the corrected dispersion; then the average value of all corrected dispersions within the preset correction time is calculated to obtain the density dispersion mean; finally, the preset correlation threshold is corrected according to the moisture content fluctuation value and the density dispersion mean, thereby obtaining the corrected correlation threshold.
[0157] By monitoring fluctuations in the mud moisture content and vapor density, the correlation threshold is dynamically adjusted. When the mud moisture content exceeds the standard, the fluctuation and the dispersed mean of the vapor density are calculated. The mud moisture content directly reflects the drying effect, while the vapor density reflects the stability of the drying process. Greater fluctuations in these two indicators indicate less stable equipment operation, requiring a lower correlation threshold to improve anomaly detection sensitivity. By combining these two indicators, the correlation threshold is adjusted to ensure stable and efficient equipment operation under different operating conditions.
[0158] Specifically, the process of correcting the preset correlation threshold according to the moisture content fluctuation value and the density dispersion mean value to obtain the corrected correlation threshold includes:
[0159] Calculating a relative deviation between the moisture content fluctuation value and a preset moisture content fluctuation threshold value to obtain a fluctuation deviation;
[0160] Calculating the relative deviation between the density dispersion mean and the preset dispersion threshold to obtain a dispersion deviation;
[0161] The preset correlation threshold is reduced according to the fluctuation deviation, the dispersion deviation, the preset fluctuation deviation weight, the preset dispersion deviation weight, and the preset correction coefficient to obtain a corrected correlation threshold. Here, T'=T×[1+b×(W1×B1+W2×B2]), T' is the corrected correlation threshold, T is the preset correlation threshold, b is the preset correction coefficient, W1 is the preset fluctuation deviation weight, B1 is the fluctuation deviation, W2 is the preset dispersion deviation weight, and B2 is the dispersion deviation.
[0162] The preset moisture content fluctuation threshold is a key indicator for assessing the stability of sludge moisture content. It depends on sludge characteristics, drying equipment performance, and process requirements, and is typically set between 2% and 5%. In this embodiment, it is set to 3%. This allows for timely monitoring of abnormal fluctuations in the drying process, allowing for timely adjustment of process parameters to ensure stable and consistent sludge drying results.
[0163] The preset fluctuation deviation weight and the preset dispersion deviation weight are coefficients used to measure the impact of moisture content fluctuation and density dispersion mean on the revised correlation threshold. They are determined by the importance and sensitivity of the impact of mud moisture content and vapor density dispersion on the equipment's operating status. They are typically set between 0 and 1, with the sum of the two being 1. In this embodiment, the preset fluctuation deviation weight is set to 0.6, and the preset dispersion deviation weight is set to 0.4. This balances the impact of moisture content fluctuation and density dispersion on the correlation threshold correction, ensuring that the correction result more accurately reflects the equipment's operating status.
[0164] The preset correction factor is a factor used to control the magnitude of the threshold correction. It depends on the sensitivity and stability of the correlation threshold correction and is typically set between 0.1 and 0.5. In this embodiment, it is set to 0.2, which is a moderate correction amplitude to avoid excessive or insufficient corrections, ensuring stable device operation and accurate anomaly detection.
[0165] The fluctuation deviation is obtained by calculating the relative deviation between the moisture content fluctuation value and the preset moisture content fluctuation threshold, and then the dispersion deviation is obtained by calculating the relative deviation between the density dispersion mean and the preset dispersion threshold. Finally, the fluctuation deviation, dispersion deviation, and the preset fluctuation deviation weight, dispersion deviation weight and correction coefficient are combined to reduce and adjust the preset correlation threshold to obtain the corrected correlation threshold.
[0166] The fluctuation deviation is calculated by calculating the relative deviation of the moisture content fluctuation value from a preset threshold, and the dispersion deviation is calculated by calculating the relative deviation of the density dispersion mean from a preset threshold. These two deviations reflect the degree of deviation in drying performance and process stability. The preset correlation threshold is then reduced based on the preset weight and correction factor to obtain the corrected threshold. Corrections based on moisture content and vapor density directly reflect the sludge drying performance and process stability, and the correlation threshold can better adapt to the actual operating conditions of the equipment.
[0167] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.
Claims
1. A method for rapid thin-layer sludge drying based on industrial images, characterized in that: include: Real-time collection of the sludge moisture content at the discharge port, steam images at the steam discharge port, images of the inner drum wall at various detection points, and blade images during the operation of the thin-layer dryer based on a preset sludge feed rate and a preset rotor speed; Extracting the vapor density and the grayscale value of the vapor color of each area in the vapor image, and extracting the sludge thickness in the cylinder wall image and the dry mud area of the dry mud attached to the blade surface in the blade image; Determining the occurrence of an abnormal event based on the vapor density, the grayscale value, the dry mud area, and a preset correlation threshold, and obtaining an abnormality determination result; determining, based on the abnormality determination result, the sludge thickness, and the dry sludge area, that the type of the abnormal event is local excessive drying, and obtaining an abnormality determination result; adjusting the preset sludge feed speed according to the abnormality determination result and the total sludge thickness to obtain an adjusted sludge feed speed, and adjusting the preset rotor speed according to the adjusted sludge feed speed and the sludge thickness to obtain an adjusted rotor speed; Based on the adjusted sludge inlet speed and the adjusted rotor speed, the preset correlation threshold is corrected according to the sludge moisture content and the vapor density within a preset correction time to obtain a corrected correlation threshold; The operation of the thin layer dryer is controlled based on the adjusted sludge feed rate and the adjusted rotor speed that are re-determined based on the modified correlation threshold.
2. The method for rapid thin-layer sludge drying based on industrial images according to claim 1, characterized in that: The process of determining the occurrence of an abnormal event based on the vapor density, the grayscale value, the dry mud area, and a preset correlation threshold and obtaining an abnormality determination result includes: Calculating the standard deviation of all the vapor densities to obtain density dispersion; When the density dispersion is greater than a preset dispersion threshold, the current timestamp is recorded, and when the density dispersion is less than or equal to the preset dispersion threshold, the recording is stopped to obtain a duration; When the duration is greater than a preset duration threshold, it is determined that an abnormal event occurs according to the gray value, the dry mud area, and a preset correlation threshold to obtain an abnormality determination result.
3. The method for rapid thin-layer sludge drying based on industrial images according to claim 2, characterized in that: The process of determining the occurrence of an abnormal event based on the grayscale value, the dry mud area, and a preset correlation threshold and obtaining an abnormality determination result includes: Calculating the standard deviation of all the grayscale values to obtain color unevenness; Counting all the color unevenness within a preset determination time to obtain an unevenness data set; Counting all the dry mud areas within the preset determination time to obtain an area data set; Calculating a correlation coefficient between the unevenness dataset and the area dataset to obtain a change correlation; When the change correlation is greater than the preset correlation threshold, it is determined that an abnormal event occurs, and an abnormality determination result is obtained.
4. The method for rapid thin-layer sludge drying based on industrial images according to claim 3, characterized in that: The process of determining the type of the abnormal event as local excessive drying according to the abnormality determination result, the sludge thickness, and the dry sludge area, and obtaining the abnormality determination result includes: When an abnormality determination result is obtained, the standard deviation of the sludge thickness from the initial moment to each moment within the preset determination time period is calculated to obtain a plurality of thickness fluctuation values; Calculating the standard deviation of the dry mud area from the initial moment to each moment within the preset determination time period in the past to obtain a plurality of area fluctuation values; The type of the abnormal event is determined to be local excessive drying according to all the thickness fluctuation values and all the area fluctuation values, and an abnormality determination result is obtained.
5. The method for rapid thin-layer sludge drying based on industrial images according to claim 4 is characterized in that: The process of determining the type of the abnormal event as local excessive drying according to all the thickness fluctuation values and all the area fluctuation values, and obtaining the abnormality determination result includes: Drawing a change curve of all the thickness fluctuation values to obtain a thickness fluctuation change curve; Drawing a change curve of all the area fluctuation values to obtain an area fluctuation change curve; Calculating the cosine similarity of the thickness fluctuation change curve and the area fluctuation change curve to obtain the change consistency; When the change consistency is greater than the preset consistency threshold, the type of the abnormal event is determined to be local excessive drying, and an abnormality determination result is obtained.
6. The method for rapid thin-layer sludge drying based on industrial images according to claim 5, characterized in that: The process of adjusting the preset sludge feeding speed according to the abnormality determination result and the total sludge thickness includes: Calculating the average value of all the sludge thicknesses at each of the detection points on the cross section of the inner cylinder wall to obtain a thickness mean; Drawing a change curve of all the thickness averages within a preset adjustment time to obtain a thickness change curve; Calculating the slope change rate of the thickness change curve to obtain the thickness change rate; The preset sludge feeding speed is adjusted according to the thickness change rate to obtain an adjusted sludge feeding speed.
7. The method for rapid thin-layer sludge drying based on industrial images according to claim 6, characterized in that: The process of adjusting the preset sludge feeding speed according to the thickness change rate to adjust the sludge feeding speed includes: When the thickness change rate is greater than a preset change rate threshold, the preset sludge feeding speed is reduced according to the relative deviation between the thickness change rate and the preset change rate threshold and a preset feeding speed adjustment coefficient to obtain an adjusted sludge feeding speed.
8. The method for rapid thin-layer sludge drying based on industrial images according to claim 7, characterized in that: The process of adjusting the preset rotor speed according to the sludge feed rate and the sludge thickness to adjust the rotor speed includes: Calculate the standard deviation of all the sludge thicknesses at each of the detection points on the vertical cross-section of the inner cylinder wall to obtain thickness dispersion; When the thickness dispersion is greater than a preset dispersion threshold, the preset rotor speed is increased according to a relative deviation between the thickness dispersion and the preset dispersion threshold and a preset speed adjustment coefficient to obtain an adjusted rotor speed.
9. The method for rapid thin-layer sludge drying based on industrial images according to claim 8, characterized in that: The process of correcting the preset correlation threshold according to the mud moisture content and the steam density within the preset correction time to obtain the corrected correlation threshold includes: When the output mud moisture content is greater than a preset output mud moisture content threshold, calculating the standard deviation of the output mud moisture content within a preset correction time length to obtain a moisture content fluctuation value; Calculate the standard deviation of all the vapor densities to obtain the corrected dispersion; Calculating the average value of all the corrected dispersions within the preset correction time to obtain a density dispersion mean; The preset correlation threshold is corrected according to the moisture content fluctuation value and the density dispersion mean to obtain a corrected correlation threshold.
10. The method for rapid thin-layer sludge drying based on industrial images according to claim 9, characterized in that: The process of correcting the preset correlation threshold according to the moisture content fluctuation value and the density dispersion mean value to obtain the corrected correlation threshold includes: Calculating a relative deviation between the moisture content fluctuation value and a preset moisture content fluctuation threshold value to obtain a fluctuation deviation; Calculating the relative deviation between the density dispersion mean and the preset dispersion threshold to obtain a dispersion deviation; The preset correlation threshold is reduced according to the fluctuation deviation, the dispersion deviation, the preset fluctuation deviation weight, the preset dispersion deviation weight, and the preset correction coefficient to obtain a corrected correlation threshold.
Citation Information
Patent Citations
Sludge thin-layer drying efficient operation device and control method
CN118084292A
Sludge drying system and debugging method thereof and computer equipment
CN111410400A
Sludge micro-negative pressure drying treatment system and process
CN117819796A
Moisture content controllable thin-layer sludge drying treatment system and moisture content controllable thin-layer sludge drying treatment method
CN118005253A
Sludge drying control method and device and electronic equipment
CN118529909A