Sludge drying treatment method, device, equipment and storage medium

Abstract

The invention provides a sludge drying treatment method, device and equipment and a storage medium, relates to the technical field of sludge drying treatment, solves the problem that the moisture content of sludge subjected to drying treatment is unstable in related technologies, and can accurately predict the moisture content of the sludge based on sensor data acquisition and SVR model parameter prediction, so that the sludge drying treatment efficiency is improved. And the interval time of the mesh belts is correspondingly adjusted, so that the control precision of the sludge drying equipment on the water content of the sludge is improved, and the drying efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of sludge drying treatment, and in particular to a sludge drying treatment method, device, equipment and storage medium. Background Art

[0002] Sludge is a byproduct of sewage treatment. The amount of sludge generated in sewage treatment is huge, so it needs to be treated. Among them, the common sludge treatment method is to dry the sludge through drying equipment. In the sludge drying equipment, the sludge is sent to the drying room (or drying chamber) through the transmission mesh belt, and dry hot air is introduced to dry the sludge. During the drying process, the moisture content of the sludge is controlled by controlling the mesh belt interval time of the transmission mesh belt.

[0003] However, in related technologies, traditional control schemes usually rely on manual experience to adjust the transmission belt, which is time-consuming and labor-intensive, and cannot adapt to the complex changes in sludge properties and working conditions. It is difficult to accurately adjust the belt interval time, resulting in poor sludge drying effect and prone to sludge moisture content being too high or too low, which is not conducive to subsequent sludge processing. Summary of the invention

[0004] The present application provides a sludge drying method, device, equipment and storage medium, which solves the problem of unstable sludge moisture content after drying treatment in related technologies. The present solution can accurately predict the moisture content of the sludge based on sensor data acquisition and SVR model parameter prediction, and adjust the mesh belt interval time accordingly, which helps to improve the control accuracy of the sludge drying equipment on the sludge moisture content and improve the drying efficiency.

[0005] In a first aspect, the present application provides a sludge drying treatment method, which is applied to a sludge drying device, wherein the sludge drying device includes a transmission mesh belt, a temperature sensor, and a state sensor, wherein the temperature sensor is used to detect the current chamber temperature, and the state sensor is used to detect the running time and start and stop time of the transmission mesh belt, and the sludge drying treatment method includes:

[0006] Determine the average belt temperature based on the chamber temperature detected by the temperature sensor;

[0007] According to the running time and start and stop time detected by the status sensor, the belt interval time and the accumulated running time of the transmission belt are determined;

[0008] Based on the pre-built SVR model, the average belt temperature, belt interval time and cumulative running time are used as input parameters of the SVR model, and the output parameters generated by the SVR model based on the input parameters are obtained to determine the current sludge moisture content;

[0009] According to the deviation between the sludge moisture content and the target moisture content, the adjustment coefficient of the corresponding mesh belt interval time is determined, and the mesh belt interval time is updated;

[0010] According to the updated mesh belt interval time, a control instruction for controlling the mesh belt motor of the transmission mesh belt is generated to adjust the start and stop time of the mesh belt motor.

[0011] In the second aspect, the present application also provides a sludge drying treatment device, which is applied to sludge drying equipment. The sludge drying equipment includes a transmission mesh belt, a temperature sensor and a state sensor. The temperature sensor is used to detect the current chamber temperature. The state sensor is used to detect the running time and start and stop time of the transmission mesh belt. The sludge drying treatment device includes:

[0012] A first data acquisition module is configured to determine an average temperature of the web belt according to the chamber temperature detected by the temperature sensor;

[0013] A second data acquisition module is configured to determine the belt interval time and the accumulated running time of the transmission belt according to the running time and the start and stop time detected by the status sensor;

[0014] The data prediction module is configured to be based on a pre-built SVR model, using the average temperature of the mesh belt, the mesh belt interval time and the accumulated running time as input parameters of the SVR model, and obtaining output parameters generated by the SVR model based on the input parameters to determine the current sludge moisture content;

[0015] A time update module is configured to determine an adjustment coefficient of a corresponding mesh belt interval time according to a deviation value between the sludge moisture content and a target moisture content, and to update the mesh belt interval time;

[0016] The equipment control module is configured to generate a control instruction for controlling the mesh belt motor of the transmission mesh belt according to the updated mesh belt interval time, so as to adjust the start and stop time of the mesh belt motor.

[0017] In a third aspect, the present application also provides a sludge drying device, which comprises:

[0018] one or more processors;

[0019] a storage device for storing one or more programs,

[0020] When one or more programs are executed by one or more processors, the one or more processors implement the sludge drying treatment method of the present application.

[0021] In a fourth aspect, the present application also provides a storage medium storing computer executable instructions, which, when executed by a processor, are used to execute the sludge drying method of the present application.

[0022] The present application scheme integrates the data obtained by the sensor with the constructed SVR model to accurately predict the moisture content of the sludge, monitor the sludge status during the drying process, and adjust the belt interval time of the transmission belt based on the sludge moisture content and the target moisture content, thereby improving the control accuracy of the sludge drying equipment on the sludge moisture content, and also improving the drying efficiency of the equipment and further reducing the energy consumption of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of a sludge drying treatment method provided in one embodiment of the present application;

[0024] Figure 2 A schematic diagram of the steps for training an SVR model provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram of the output result of the trained SVR model provided in one embodiment of the present application;

[0026] Figure 4 A schematic diagram of the structure of a sludge drying treatment device provided in one embodiment of the present application;

[0027] Figure 5 A schematic diagram of the structure of a sludge drying device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present application, rather than to limit the embodiments of the present application. It should also be noted that, for ease of description, only the parts related to the embodiments of the present application rather than all structures are shown in the accompanying drawings, and those skilled in the art should be able to think of it after reading the specification of this application that as long as the technical features do not contradict each other, any combination of the technical features can constitute an optional implementation method.

[0029] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally a class, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated before and after are in an "or" relationship. In the description of the present application, "multiple" means two or more, and "several" means one or more.

[0030] In the process of sewage treatment, a huge amount of sludge is generated, and the sludge needs to be treated. The common sludge treatment method is to dry the sludge through sludge drying equipment. In the sludge drying equipment, the sludge is sent into the drying chamber (or drying chamber) through the transmission mesh belt, and dry hot air is introduced to dry the sludge, and the moisture content of the sludge is controlled by controlling the mesh belt interval time of the transmission mesh belt.

[0031] However, traditional control schemes usually rely on manual experience to control the conveyor belt. This method cannot accurately determine the sludge moisture content during the treatment process. In addition, the actual drying process has complex and changeable working conditions, and the conveyor belt needs to be controlled according to the changes in the sludge moisture content. However, traditional schemes cannot adapt to the complex changes in sludge properties and working conditions, and it is difficult to accurately adjust the belt interval time, resulting in poor sludge drying effect. Moreover, it is easy for the sludge moisture content to be too high or too low, which is not conducive to the subsequent processing of the sludge.

[0032] In this regard, an embodiment of the present application provides a sludge drying treatment method, which is applied to a sludge drying device, and the sludge drying device includes a transmission mesh belt, a temperature sensor, and a state sensor. In the sludge drying device, the sludge is sent into a drying chamber through a transmission mesh belt, and the temperature sensor can be set at one side of the transmission mesh belt, the inner wall of the drying chamber, one side of the heating source, etc., and the state sensor is set on the mesh belt motor or drive shaft corresponding to the transmission mesh belt, so as to detect the running time and start and stop time of the transmission mesh belt through the state sensor.

[0033] It is conceivable that the sludge drying equipment includes a processor and a memory. The number of processors can be one or more, so that the processor executes one or more programs stored in the memory, thereby realizing the sludge drying treatment method of the present application. Figure 1 This is a schematic diagram of the steps of a sludge drying treatment method provided in an embodiment of the present application. The sludge drying treatment method can be executed by a processor, and the specific steps are as follows:

[0034] Step S110, determining the average temperature of the mesh belt according to the chamber temperature detected by the temperature sensor.

[0035] The temperature sensor is used to detect the current chamber temperature. The processor can determine the current chamber temperature according to the parameters received from the temperature sensor, and the chamber temperature corresponds to the temperature of the drying chamber of the sludge drying equipment. In this regard, the processor can further determine the average temperature of the mesh belt. It is conceivable that when one temperature sensor is provided, the value of the average temperature of the mesh belt can adopt the detected value of the chamber temperature.

[0036] In one embodiment, there are multiple temperature sensors, and they are respectively arranged at different positions, such as distributed on one side of the transmission mesh belt, the inner wall of the drying chamber, one side of the heating source, etc. Correspondingly, corresponding weights are set for temperature sensors at different positions. It can be imagined that the weight is associated with the degree of influence of the temperature value detected by the temperature sensor at this position on the average temperature of the mesh belt. Then, after the corresponding chamber temperature is detected by each temperature sensor, the corresponding weighted average value is calculated according to the weight corresponding to each temperature sensor, so that the weighted average value is used as the average temperature of the mesh belt. Therefore, by calculating the temperatures detected by multiple temperature sensors through the corresponding weights, the processor can obtain the average temperature of the mesh belt more accurately, which helps the sludge drying equipment to better control the moisture content of the sludge.

[0037] Step S120: Determine the belt interval time and accumulated running time of the transmission belt according to the running time and start / stop time detected by the status sensor.

[0038] It can be imagined that the belt interval time is the interval time when the transmission belt switches from stopping to starting working. For this, the corresponding belt interval time can be determined by recording the start and stop time of the transmission belt. The cumulative running time is the cumulative time that the transmission belt is in working state. For this, after determining the running time of the transmission belt, the corresponding time is determined by counting the running time of each working time, and then the cumulative running time can be obtained by cumulative calculation.

[0039] It is understandable that the processor can detect the working state of the mesh belt motor of the transmission mesh belt through the state sensor to complete the detection of the running time and start and stop time of the transmission mesh belt, such as recording the time corresponding to the mesh belt motor starting and stopping to determine the running time and start and stop time. This solution detects the operation of the transmission mesh belt through the state sensor, which can achieve more accurate detection of parameters (such as the above-mentioned running time and start and stop time), thereby improving the accuracy of the sludge moisture content output by the model.

[0040] It should be noted that in some embodiments, speed sensors, Hall sensors, photoelectric sensors, encoders, etc. can be used as status sensors to detect the operating status of the transmission belt, so as to determine the corresponding operating time and start and stop times.

[0041] Step S130: Based on the pre-built SVR model, the average belt temperature, the belt interval time and the accumulated running time are used as input parameters of the SVR model, and the output parameters generated by the SVR model based on the input parameters are obtained to determine the current sludge moisture content.

[0042] The SVR (Support Vector Regression) model is used to determine a function that can accurately predict the target value. In the present application scheme, the average temperature of the mesh belt, the mesh belt interval time and the cumulative running time are used as the input parameters of the SVR model, and the sludge moisture content change value is used as the output parameter of the SVR model to construct the corresponding training set data, so as to train the SVR model. The SVR model obtained after training is used to output accurate sludge moisture content change values ​​according to the corresponding input parameters, and the SVR model obtained after training is used as a pre-built model. The processor can call the SVR model to determine the current sludge moisture content when the input parameters are determined, such as determining the current sludge moisture content by the initial sludge moisture content and the corresponding sludge moisture content change value.

[0043] It is understandable that in the process of sludge drying, simply detecting the sludge moisture content through a humidity sensor is difficult to accurately reflect the changes in the moisture content of the entire sludge. However, constructing a corresponding SVR model, a mathematical model that is trained to better fit the actual moisture content changes of the sludge, can more accurately predict the current sludge moisture content based on the SVR model.

[0044] Step S140: Determine the adjustment coefficient of the corresponding mesh belt interval time according to the deviation value between the sludge moisture content and the target moisture content, and update the mesh belt interval time.

[0045] The target moisture content is used as a preset threshold. After determining the sludge moisture content, the processor compares the sludge moisture content with the target moisture content to determine the deviation between the sludge moisture content and the target moisture content. Corresponding to different deviation values, the sludge drying equipment adopts different control strategies to control the transmission mesh belt. For example, different adjustment coefficients corresponding to the mesh belt interval time are set for different deviation values, and the mesh belt interval time is updated according to the adjustment coefficient, so as to achieve the effect of adjusting the moisture content of the sludge during the drying process.

[0046] Optionally, in one embodiment, when the deviation between the sludge moisture content and the target moisture content is greater than the preset value, and the sludge moisture content is greater than the target moisture content, the adjustment coefficient is determined to be the first coefficient, the product of the first coefficient and the deviation value is used as the duration increase ratio, and the mesh belt interval time is extended according to the duration increase ratio. That is, when the sludge moisture content is greater than the target moisture content and the corresponding deviation value is also greater than the preset value, it means that the current sludge moisture content is high. In this regard, the processor further increases the drying time by extending the mesh belt interval time to reduce the moisture content of the sludge.

[0047] When the deviation between the sludge moisture content and the target moisture content is greater than the preset value, and the sludge moisture content is less than the target moisture content, the adjustment coefficient is determined to be the second coefficient, and the product of the second coefficient and the deviation value is used as the duration reduction ratio, and the mesh belt interval time is shortened according to the duration reduction ratio. That is, when the sludge moisture content is less than the target moisture content and the corresponding deviation value is still greater than the preset value, it means that the current sludge moisture content is low. In this regard, the processor further reduces the drying time by shortening the mesh belt interval time to avoid the sludge moisture content being too low.

[0048] For example, H p represents the sludge moisture content determined based on the SVR model, H t Indicates the target moisture content, and the set deviation value is 5%. p -H t When it is >5%, it indicates that the moisture content is too high and the drying needs to be accelerated, thereby increasing the mesh belt interval time. The corresponding increase in time ΔT = k1×(H p -H t ), where k1 is the first coefficient, which can be set according to actual operation needs. t -H p When it is >5%, it indicates that the moisture content is too low, and the mesh belt interval time is reduced, and the corresponding reduction time ΔT=k2×(H t -H p ), wherein k2 is the second coefficient, and the second coefficient can also be set according to actual operation needs.

[0049] Step S150: Generate a control instruction for controlling the mesh belt motor of the transmission mesh belt according to the updated mesh belt interval time, so as to adjust the start and stop time of the mesh belt motor.

[0050] Furthermore, after determining the corresponding mesh belt interval time, the processor generates a control instruction accordingly according to the updated mesh belt interval time. The control instruction is used to control the mesh belt motor of the transmission mesh belt to adjust the start and stop time of the mesh belt motor, thereby controlling the transmission mesh belt. For example, according to the determined mesh belt interval time, after the mesh belt motor stops running, the mesh belt motor is restarted after the timing reaches the mesh belt interval time, so as to bring the sludge out of the drying chamber through the transmission mesh belt.

[0051] In the actual application scenario, 30 batches of sludge are continuously processed, and the corresponding target moisture content is 30%. The comparison of the effects (final moisture content, drying time, and monthly energy consumption) between the traditional solution and this solution is shown in the following table:

[0052] Final moisture content Drying time Monthly energy consumption Traditional Solution 33±7％ 12h 7000kW·h This program 30.5±2％ 8.5h 5000kW·h

[0053] It can be seen from the above scheme that this scheme accurately predicts the moisture content of the sludge by fusing the data obtained by the sensor with the constructed SVR model, realizes the monitoring of the sludge state during the drying process, and adjusts the belt interval time of the transmission belt based on the sludge moisture content and the target moisture content, thereby achieving the improvement of the control accuracy of the sludge drying equipment on the sludge moisture content, and also improves the drying efficiency of the equipment and further reduces the energy consumption of the equipment.

[0054] In some embodiments, the SVR model is constructed with a radial basis function (RBF) as a kernel function, and the SVR model is used to determine the decision function by minimizing the objective function. Correspondingly, the radial basis function is expressed as:

[0055]

[0056] Wherein, γ is a kernel function parameter. The use of the kernel function enables the SVR model to find the optimal regression plane in the high-dimensional space, thereby processing complex nonlinear relationships. It should be noted that, in one embodiment, the kernel function used by the SVR model may also be a linear kernel function, a polynomial kernel function or a Sigmoid kernel function.

[0057] It can be understood that the above-mentioned decision function is a function used to express the mapping relationship between output parameters and input parameters, wherein the output parameter is the change value of sludge moisture content, and the input parameters include the average temperature of the mesh belt, the mesh belt interval time and the cumulative running time. Moreover, the objective function is a function associated with weights, penalty parameters, first slack variables and second slack variables, wherein the weights are the weights of the corresponding regression plane (corresponding to the decision function), the first slack variables and the second slack variables are used to represent the amount of allowable error, and the penalty coefficient is used to control the complexity of the model, and the above-mentioned parameters (weights, penalty parameters, first slack variables and second slack variables) all meet the preset constraints. Exemplarily, in one embodiment, the specific representation of the objective function is:

[0058]

[0059] Among them, w is the weight (which can be expressed in vector form), C is the penalty parameter, ξ i is the first slack variable, is the second slack variable. It can be imagined that the constraints can be the constraints on the parameter values, the constraints on the association between any parameters, etc. The corresponding constraints are:

[0060]

[0061] Among them, b is the bias term, which is used to represent the offset of the regression plane, Φ(x i) is a nonlinear mapping function. In this regard, this solution constructs an SVR model based on the radial basis function, so that the SVR model can find the optimal regression plane in the high-dimensional space, thereby processing complex nonlinear relationships, and by minimizing the objective function to achieve the construction of the decision function, so that the output parameters calculated by the SVR model can accurately fit the actual sludge moisture content.

[0062] Figure 2 A schematic diagram of the steps of model training for an SVR model provided in one embodiment of the present application. In one embodiment, model training generally includes the steps of training and verification. For the training and verification of the SVR model, the acquired historical data is classified to divide the two data sets of training set and verification set, and then the SVR model is trained and verified. The specific steps are as follows:

[0063] Step S210, dividing the historical data into a training set and a validation set according to a preset ratio, each set of parameters in the historical data includes the average temperature of the mesh belt, the mesh belt interval time, the cumulative running time and the change value of the sludge moisture content.

[0064] Step S220: According to the Lagrange multiplier method, a training set is selected as input data and the constraint condition is used as a conditional function to optimize the objective function to generate a decision function.

[0065] Step S230: Based on the verification set, parameter verification is performed on the decision function.

[0066] It is understandable that the historical data is divided into corresponding groups according to the input parameters and output parameters, that is, each group of parameters includes the average temperature of the mesh belt, the mesh belt interval time, the cumulative running time and the sludge moisture content change value, wherein the input parameters include the average temperature of the mesh belt, the mesh belt interval time and the cumulative running time, and the output parameter is the sludge moisture content change value, and the corresponding sludge moisture content data can be obtained by detecting the humidity sensor. When dividing the data set of historical data, it can be divided according to a preset ratio, such as using 70% of the historical data as a training set and the remaining part (i.e. 30%) as a verification set.

[0067] Then, using the data of the training set, the optimization goal (i.e., the above-mentioned objective function) in the SVR model is solved by the Lagrange multiplier method, that is, the training set is selected as the input data and the constraint condition is used as the conditional function to optimize the objective function, thereby determining the corresponding decision function. The specific expression of the decision function is:

[0068]

[0069] Among them, a i , are all Lagrange multipliers, K(x i,x) is the kernel function and b is the bias term.

[0070] Accordingly, after completing the training using the training set, it is also necessary to perform parameter verification on the decision function generated by the model through the verification set to verify the accuracy of the generated decision function. Figure 3 A schematic diagram of the output results of the trained SVR model provided in one embodiment of the present application, wherein the horizontal axis is the predicted sample, and the vertical axis is the predicted result (including the predicted value output by the model and the true value in the sample). As shown in the figure, the predicted value and the true value in the prediction result are consistent, and the RSME (root mean square error) of the two is 0.36.

[0071] In this regard, the constructed SVR model can fit the actual moisture content of the sludge, so that the sludge moisture content obtained based on the SVR model can be accurately reflected in the sludge moisture content in the actual drying process, which in turn helps to improve the control accuracy of the sludge drying equipment on the sludge moisture content and improve the drying efficiency.

[0072] In one embodiment, in the process of constructing the SVR model, the SVR parameters can also be optimized based on the firefly algorithm. It can be imagined that the SVR parameters are the parameters required for the SVR model to generate a decision function. A set of SVR parameters includes multiple parameter items, such as the penalty parameter, kernel function parameter, first slack variable, second slack variable, weight and bias item shown in the above embodiment. The SVR parameters with different values ​​will affect the complexity of the SVR model and its ability to fit the data, that is, the constructed SVR models are different, and the values ​​output based on the SVR model will also be different.

[0073] As you can imagine, the core idea of ​​the firefly algorithm as an optimization algorithm is to simulate the behavioral characteristics of fireflies in nature. It has at least the following key points: First, brightness (or attraction). In the algorithm, the brightness of each firefly represents its optimization objective function value. In the optimization problem, it can be the maximum or minimum value of the function, and the higher the brightness, the better the solution. The second is attraction and movement. In the algorithm, fireflies will be attracted by brighter fireflies around them and move towards brighter fireflies, that is, adjust their positions according to the "best" solutions around them, which corresponds to the process of moving in the parameter space during the optimization process.

[0074] In the process of parameter optimization, based on the parameter values ​​corresponding to the randomly generated multiple SVR parameters, the SVR model is iteratively optimized according to the preset position update formula within the preset number of iterations according to the firefly algorithm. It can be understood that the parameter values ​​corresponding to the randomly generated multiple SVR parameters can be used to represent the fireflies in the initialized firefly group, that is, in the parameter space, the specific parameter value of each SVR parameter corresponds to a firefly position. In addition, the brightness of the fireflies is represented by a fitness value in the parameter space, and the fitness value is used to represent the performance of the SVR model corresponding to the parameter values ​​of this group of SVR parameters. Optionally, the mean square error between the actual value corresponding to the sludge moisture content in the validation set and the predicted value determined by the SVR model constructed according to the parameter value corresponding to the SVR parameter is calculated, and then the mean square error is used as the firefly brightness corresponding to the parameter position of the parameter value in the parameter space corresponding to the firefly algorithm, that is, as the specific value of the above-mentioned fitness value. It can be understood that when the mean square error is smaller, the prediction accuracy of the model corresponding to the group of SVR parameters is higher, that is, the firefly brightness is higher.

[0075] Then, the parameters are optimized according to the preset number of iterations. In each iteration, the fitness value corresponding to the SVR model obtained after training is compared with the fitness value corresponding to the SVR model corresponding to the specific parameters of the initialized multiple sets of SVR parameters. When the latter is more optimized, the parameter position corresponding to the parameters of the SVR model obtained after training is moved in the parameter space according to the preset position update formula, that is, the position of the firefly is moved to update the parameters of the SVR model, thereby terminating this iteration and entering the next iteration.

[0076] Exemplarily, in one embodiment, in the position update formula used, the moving distance depends on the brightness difference and the distance. The formula is associated with the current position, the target position, the attraction coefficient of the corresponding attraction, the light absorption coefficient, the random walk coefficient and the random vector. The specific position update formula is:

[0077]

[0078] in, is the position of the firefly at iteration t+1, is the position of the firefly at the tth iteration, β0 is the maximum absorption coefficient, γ is the light absorption coefficient, r ij is the firefly spacing, a is the random walk coefficient, is a random vector. Specifically, the maximum absorption coefficient and the light absorption coefficient can take the value of 1, while the random walk coefficient can take the value of 0.2, and the random vector is a vector uniformly distributed within [-0.5, 0.5].

[0079] Therefore, by optimizing the parameters of the SVR model, the sludge drying equipment can optimize the SVR model, thereby further improving the prediction accuracy of the model, which not only improves the accuracy of the model prediction, but also helps to improve the effectiveness of the control strategy for the transmission belt.

[0080] In one embodiment, the abnormal data may be further processed and then input into the SVR model as input parameters. Specifically, when abnormal data exists, multiple adjacent point data are selected and weighted average values ​​are calculated according to corresponding weights to replace the abnormal data, that is, the abnormal parameters are processed according to the adjacent point data to eliminate the abnormality, wherein the adjacent point data are data detected at adjacent sampling moments or adjacent sampling points.

[0081] It is understandable that adjacent point data can be selected in the time domain, that is, for a sensor with a numerical anomaly, the sampling data of the sensor before and after the time point (corresponding to the sampling time of the abnormal data) is used as the adjacent point data. Of course, the selected sampling moments before and after can be the sampling moments included in a sampling cycle before and after or multiple sampling cycles before and after, so as to obtain multiple adjacent point data. Similarly, when there are multiple sensors of the same type, the data collected by sensors with adjacent positions in the spatial range can also be used as the adjacent point data.

[0082] Moreover, different weights are configured for each adjacent point data. Specifically, the weight corresponding to the adjacent point data is negatively correlated with the sampling time interval or spatial distance of the adjacent point data relative to the abnormal data. It can be understood that in the time domain, in the same sensor, the sampling time interval of the adjacent point data relative to the abnormal data can be understood as: the time interval between the sampling time of the adjacent point data and the sampling time of the abnormal data. Based on this, the smaller the sampling time interval of the adjacent point data corresponding to the abnormal data, the greater the corresponding weight; the larger the sampling time interval of the adjacent point data corresponding to the abnormal data, the smaller the corresponding weight.

[0083] In space, in different sensors, the spatial distance between adjacent point data and abnormal data can be understood as: the spatial interval between the sensor that collects adjacent point data and the sensor that collects abnormal data. Based on this, the smaller the spatial interval between the location of the sensor that collects adjacent point data and the location of the sensor that collects abnormal data, the greater the corresponding weight; the larger the spatial interval between the location of the sensor that collects adjacent point data and the location of the sensor that collects abnormal data, the smaller the corresponding weight.

[0084] For example, take the temperature parameter as an example. For example, the temperature collected at a certain moment is abnormal data. For example, the specific value of the abnormal data is 65°C, while the temperatures at the first two sampling moments are 45°C and 46°C, and the weights associated with the first two sampling moments are 0.3 (corresponding to the sampling moment of the data at 45°C) and 0.7 (corresponding to the sampling moment of the data at 46°C). Therefore, the weighted average value obtained by calculating the adjacent point data according to the corresponding weights is 45×0.3+46×0.7=45.7 (°C), and the abnormal data is replaced with this value (45.7°C).

[0085] In this regard, this solution can eliminate the impact of abnormal data on the final predicted sludge moisture content by processing abnormal data, which helps to ensure the accuracy of the data and makes the sludge moisture content determined based on the SVR model more in line with the actual moisture content, so as to control the transmission belt according to the sludge moisture content, which helps to improve the control accuracy of the sludge drying equipment over the sludge moisture content.

[0086] Figure 4 This is a schematic diagram of the structure of a sludge drying treatment device provided in one embodiment of the present application. The device is used to execute the sludge drying treatment method provided in the above embodiment, and has functional modules and beneficial effects corresponding to the execution method. The sludge drying treatment device is applied to sludge drying equipment, and the sludge drying equipment includes a transmission mesh belt, a temperature sensor and a state sensor. The temperature sensor is used to detect the current chamber temperature, and the state sensor is used to detect the running time and start and stop time of the transmission mesh belt. As shown in the figure, the sludge drying treatment device includes a first data acquisition module 401, a second data acquisition module 402, a data prediction module 403, a time update module 404 and an equipment control module 405.

[0087] The first data acquisition module 401 is configured to determine the average temperature of the web belt according to the chamber temperature detected by the temperature sensor;

[0088] The second data acquisition module 402 is configured to determine the belt interval time and the accumulated running time of the transmission belt according to the running time and the start and stop time detected by the state sensor;

[0089] The data prediction module 403 is configured to obtain output parameters generated by the SVR model based on the input parameters based on the pre-built SVR model, taking the average temperature of the mesh belt, the mesh belt interval time and the accumulated running time as input parameters of the SVR model, so as to determine the current sludge moisture content;

[0090] The time updating module 404 is configured to determine the adjustment coefficient of the corresponding mesh belt interval time according to the deviation value between the sludge moisture content and the target moisture content, and update the mesh belt interval time;

[0091] The equipment control module 405 is configured to generate a control instruction for controlling the mesh belt motor of the transmission mesh belt according to the updated mesh belt interval time, so as to adjust the start and stop time of the mesh belt motor.

[0092] Based on the above embodiment, the first data acquisition module 401 is specifically configured as follows:

[0093] When multiple temperature sensors are provided, a corresponding weighted average value is calculated for the chamber temperature detected by each temperature sensor according to a preset weight corresponding to each temperature sensor, and the weighted average value is used as the average temperature of the web belt.

[0094] Based on the above embodiment, the time update module 404 is specifically configured as follows:

[0095] When the deviation between the sludge moisture content and the target moisture content is greater than the preset value, and the sludge moisture content is greater than the target moisture content, the adjustment coefficient is determined to be the first coefficient, the product of the first coefficient and the deviation value is used as the duration increase ratio, and the mesh belt interval time is extended according to the duration increase ratio;

[0096] When the deviation between the sludge moisture content and the target moisture content is greater than the preset value and the sludge moisture content is less than the target moisture content, the adjustment coefficient is determined to be the second coefficient, the product of the second coefficient and the deviation value is used as the duration reduction ratio, and the belt interval time is shortened according to the duration reduction ratio.

[0097] On the basis of the above embodiment, the SVR model uses the radial basis function as the kernel function. The SVR model is used to determine the decision function by minimizing the objective function. The decision function is used to represent the mapping relationship between the output parameters and the input parameters. The objective function is a function associated with the weight, the penalty parameter, the first slack variable and the second slack variable, and the weight, the penalty parameter, the first slack variable and the second slack variable in the objective function all satisfy the preset constraints.

[0098] On the basis of the above embodiment, the sludge drying treatment device further includes a model training module, and the model training module is configured as follows:

[0099] The historical data are divided into a training set and a validation set according to a preset ratio. Each set of parameters in the historical data includes the average temperature of the mesh belt, the mesh belt interval time, the cumulative running time and the change value of the sludge moisture content;

[0100] According to the Lagrange multiplier method, the training set is selected as input data and the constraint condition is used as the conditional function to optimize the objective function to generate a decision function;

[0101] Based on the validation set, the decision function parameters are validated.

[0102] Based on the above embodiment, the model training module is further configured as follows:

[0103] Based on parameter values ​​corresponding to a plurality of randomly generated SVR parameters, the SVR model is iteratively optimized according to a preset position update formula within a preset number of iterations according to the firefly algorithm, and the SVR parameters are parameters required for the SVR model to generate a decision function;

[0104] Among them, the mean square error between the actual value corresponding to the sludge moisture content in the verification set and the predicted value determined by the SVR model constructed according to the parameter value corresponding to the SVR parameter is taken as the firefly brightness corresponding to the parameter position of the parameter value in the parameter space corresponding to the firefly algorithm.

[0105] On the basis of the above embodiment, the sludge drying treatment device further includes a data anomaly processing module, and the data anomaly processing module is configured as follows:

[0106] In the presence of abnormal data, multiple adjacent point data are selected and the weighted average is calculated according to the corresponding weights to replace the abnormal data. The adjacent point data are the data detected at adjacent sampling moments or adjacent sampling points. The weights corresponding to the adjacent point data are negatively correlated with the sampling moment spacing or spatial distance of the adjacent point data relative to the abnormal data.

[0107] It is worth noting that in the embodiment of the above-mentioned device, the modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present application.

[0108] Figure 5 The structural diagram of the sludge drying equipment provided in one embodiment of the present application is used to execute the sludge drying treatment method provided in the above embodiment, and has the functional modules and beneficial effects corresponding to the execution method. As shown in the figure, the sludge drying equipment includes a processor 501, a memory 502, an input device 503 and an output device 504. The number of processors 501 can be one or more, and one processor 501 is taken as an example in the figure; the processor 501, the memory 502, the input device 503 and the output device 504 can be connected by a bus or other means, and the figure takes the bus connection as an example. The memory 502, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the sludge drying treatment method in the embodiment of the present application. The processor 501 executes the corresponding various functional applications and data processing by running the software programs, instructions and modules stored in the memory 502, that is, realizing the above-mentioned sludge drying treatment method.

[0109] The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data recorded or created during use, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 502 may further include a memory remotely arranged relative to the processor 501, and these remotely arranged memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0110] The input device 503 can be used to input corresponding digital or character information to the processor 501, and to generate key signal input related to the user settings and function control of the device; the output device 504 can be used to send or display key signal output related to the user settings and function control of the device.

[0111] An embodiment of the present application also provides a storage medium storing computer executable instructions, which, when executed by a processor, are used to perform relevant operations in the sludge drying treatment method provided in any embodiment of the present application.

[0112] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0113] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0114] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A sludge drying method, characterized in that: Applied to sludge drying equipment, the sludge drying equipment includes a transmission mesh belt, a temperature sensor and a state sensor, the temperature sensor is used to detect the current chamber temperature, the state sensor is used to detect the running time and start and stop time of the transmission mesh belt, and the sludge drying treatment method includes: Determining the average temperature of the mesh belt according to the chamber temperature detected by the temperature sensor; Determine the belt interval time and the accumulated running time of the transmission belt according to the running time and the start and stop time detected by the status sensor; Based on the pre-built SVR model, the average temperature of the mesh belt, the mesh belt interval time and the accumulated running time are used as input parameters of the SVR model, and the output parameters generated by the SVR model based on the input parameters are obtained to determine the current sludge moisture content; Determine the adjustment coefficient corresponding to the mesh belt interval time according to the deviation value between the sludge moisture content and the target moisture content, and update the mesh belt interval time; According to the updated mesh belt interval time, a control instruction for controlling the mesh belt motor of the transmission mesh belt is generated to adjust the start and stop time of the mesh belt motor.

2. The sludge drying method according to claim 1, characterized in that: The step of determining the average temperature of the web belt according to the chamber temperature detected by the temperature sensor comprises: When there are multiple temperature sensors, a corresponding weighted average value is calculated for the chamber temperatures detected by each temperature sensor according to a preset weight corresponding to each temperature sensor, and the weighted average value is used as the average temperature of the web belt.

3. The sludge drying method according to claim 1, characterized in that: The step of determining the adjustment coefficient corresponding to the mesh belt interval time according to the deviation value between the sludge moisture content and the target moisture content, and updating the mesh belt interval time, comprises: When the deviation between the sludge moisture content and the target moisture content is greater than a preset value, and the sludge moisture content is greater than the target moisture content, the adjustment coefficient is determined to be a first coefficient, the product of the first coefficient and the deviation value is used as a duration increase ratio, and the mesh belt interval time is extended according to the duration increase ratio; When the deviation value between the sludge moisture content and the target moisture content is greater than the preset value, and the sludge moisture content is less than the target moisture content, the adjustment coefficient is determined to be the second coefficient, the product of the second coefficient and the deviation value is used as the duration reduction ratio, and the belt interval time is shortened according to the duration reduction ratio.

4. The sludge drying method according to any one of claims 1 to 3, characterized in that: The SVR model uses a radial basis function as a kernel function. The SVR model is used to determine a decision function by minimizing an objective function. The decision function is used to represent a mapping relationship between the output parameter and the input parameter. The objective function is a function associated with a weight, a penalty parameter, a first slack variable, and a second slack variable. The weight, penalty parameter, first slack variable, and second slack variable in the objective function all satisfy preset constraints.

5. The sludge drying method according to claim 4, characterized in that: The training process of the SVR model includes: Dividing the historical data into a training set and a validation set according to a preset ratio, wherein each set of parameters in the historical data includes the average temperature of the mesh belt, the mesh belt interval time, the cumulative running time and the change value of the sludge moisture content; According to the Lagrange multiplier method, the training set is selected as input data and the constraint condition is used as a conditional function to optimize the objective function to generate the decision function; Based on the verification set, parameter verification is performed on the decision function.

6. The sludge drying method according to claim 5, characterized in that: After performing parameter verification on the decision function based on the verification set, the method further includes: Based on parameter values ​​corresponding to a plurality of randomly generated SVR parameters, iteratively optimizing the parameters of the SVR model according to a preset position update formula within a preset number of iterations according to the firefly algorithm, the SVR parameters being the parameters required for the SVR model to generate the decision function; Among them, the mean square error between the actual value corresponding to the sludge moisture content in the verification set and the predicted value determined by the SVR model constructed according to the parameter value corresponding to the SVR parameter is used as the firefly brightness corresponding to the parameter position of the parameter value in the parameter space corresponding to the firefly algorithm.

7. The sludge drying method according to claim 4, characterized in that: The sludge drying treatment method also includes: In the presence of abnormal data, multiple adjacent point data are selected and a weighted average is calculated according to the corresponding weights to replace the abnormal data. The adjacent point data are data detected at adjacent sampling moments or adjacent sampling points, and the weights corresponding to the adjacent point data are negatively correlated with the sampling moment spacing or spatial distance of the adjacent point data relative to the abnormal data.

8. A sludge drying treatment device, characterized in that: Applied to sludge drying equipment, the sludge drying equipment includes a transmission mesh belt, a temperature sensor and a state sensor, the temperature sensor is used to detect the current chamber temperature, the state sensor is used to detect the running time and start and stop time of the transmission mesh belt, the sludge drying treatment device includes: A first data acquisition module is configured to determine an average temperature of the web belt according to the chamber temperature detected by the temperature sensor; A second data acquisition module is configured to determine the belt interval time and the accumulated running time of the transmission belt according to the running time and the start and stop time detected by the status sensor; A data prediction module is configured to obtain output parameters generated by the SVR model based on the input parameters based on the pre-built SVR model, taking the average temperature of the mesh belt, the mesh belt interval time and the accumulated running time as input parameters of the SVR model, so as to determine the current sludge moisture content; A time updating module is configured to determine an adjustment coefficient corresponding to the mesh belt interval time according to a deviation value between the sludge moisture content and a target moisture content, and to update the mesh belt interval time; The equipment control module is configured to generate a control instruction for controlling the mesh belt motor of the transmission mesh belt according to the updated mesh belt interval time, so as to adjust the start and stop time of the mesh belt motor.

9. A sludge drying device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the sludge drying treatment method as described in any one of claims 1-7.

10. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a processor, they are used to perform the sludge drying method according to any one of claims 1 to 7.

Images