High-pressure fan power frequency control method and system based on data processing

Abstract

The invention relates to the technical field of power frequency control, in particular to a high-pressure fan power frequency control method and system based on data processing. The method comprises the following steps: acquiring data of each dimension of each data point in environmental data of a granary; obtaining the anomaly degree of each data point through an iterative self-organizing clustering algorithm, and taking the mean value of the anomaly degrees of all the data points as the anomaly degree of the environmental data of the granary so as to realize high-pressure fan power frequency control based on data processing; wherein each round of iteration process of the iteration self-organizing clustering algorithm comprises the steps of sequentially calculating the similarity between data points, the importance degree of each dimension, the weighted Euclidean distance from each data to each clustering center and the possibility of distributing each data point to each clustering cluster, distributing each data point to the clustering cluster with the maximum possibility, and completing the clustering. According to the method, the error accumulation in the clustering process is reduced, so that the clustering result is more accurate, and the accuracy of power frequency control of the high-pressure fan is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power frequency control, and particularly to a power frequency control method and system for a high-pressure blower based on data processing. Background Art

[0002] In modern agricultural production and grain storage processes, ensuring the safety and quality of grain is of utmost importance. With the growth of the global population and the impact of climate change, grain storage technology faces more and more challenges. Traditional grain storage methods often rely on mechanical ventilation and natural drying, but these methods are easily affected by changes in the external environment and it is difficult to achieve precise control of the grain environment, resulting in problems such as grain mildew, pests, and rot.

[0003] Due to advantages such as large air volume, high air pressure, and low energy consumption, high-pressure blowers are widely used in the ventilation systems of grain storage. By effectively controlling the operation of the blower, precise adjustment of the storage environment can be achieved, thereby improving the storage safety and quality of grain. However, existing high-pressure blower control technologies mainly rely on power frequency power supply methods with fixed frequencies, lacking intelligent and automated control means, and it is difficult to adjust the operating state of the blower according to real-time data, unable to meet the dynamically changing grain storage requirements. The iterative self-organizing clustering algorithm is an algorithm for analyzing multi-dimensional data. In the field of grain storage, by monitoring and analyzing parameters such as temperature, humidity, and oxygen concentration in the granary, and achieving precise control of the high-pressure blower according to the analysis results, the best state of the grain storage environment can be maintained.

[0004] The patent document with the publication number CN117762106B discloses a monitoring method for the processing process of livestock and poultry blood products based on the Internet of Things. This method obtains the time series distribution sequence of division points by analyzing the local fluctuations and time differences between inflection points in multiple processing cycles, and divides all processing cycles according to the distribution of the division points to obtain the divided segments of the processing cycles; performs iterative self-organizing clustering on each divided segment to obtain the initial clustering clusters, and obtains the corrected weight to adjust the corrected clustering center based on the fluctuation deviation of the data points in the processing cycle and the initial clustering cluster they belong to, to obtain the final clustering center; monitors the processing state based on the deviation of the temperature data at the current moment from the corresponding final clustering center.

[0005] However, the above patent documents do not target the grain storage process, and do not solve the problem that for the environmental data in the granary, due to different environmental characteristics and aggregation patterns in different dimensions, when the environmental data of each dimension in the granary changes, it will change gradually. Therefore, there will be some data points that are relatively close to some clustering clusters during the clustering process, and the iterative self-organizing algorithm will directly assign this data point to the clustering cluster with the closest distance during the clustering process, ignoring other clustering clusters with close distances, resulting in the continuous accumulation of errors in the clustering result, reducing the accuracy of the clustering result, and further making the industrial frequency control result of the high-pressure fan inaccurate. Summary of the Invention

[0006] In order to solve the problem that the iterative self-organizing algorithm will directly assign this data point to the clustering cluster with the closest distance during the clustering process, ignoring other clustering clusters with close distances, resulting in the continuous accumulation of errors in the clustering result, reducing the accuracy of the clustering result, and further making the industrial frequency control result of the high-pressure fan inaccurate, the present invention provides a method and system for industrial frequency control of a high-pressure fan based on data processing.

[0007] In a first aspect, the present invention provides a method for industrial frequency control of a high-pressure fan based on data processing, adopting the following technical solution: A method for industrial frequency control of a high-pressure fan based on data processing includes: obtaining the data of each dimension of each data point in the environmental data of the granary; obtaining the anomaly degree of each data point through the iterative self-organizing clustering algorithm, and taking the mean value of the anomaly degrees of all data points as the anomaly degree of the environmental data of the granary to achieve industrial frequency control of the high-pressure fan based on data processing; in each round of iteration of the iterative self-organizing clustering algorithm, in response to the clustering clusters to which each data point belongs no longer changing, the clustering ends and enters the next round of iteration, including: for each clustering in each round of iteration, calculating the similarity between data points based on the difference in the values of any two data points in each dimension and the Euclidean distance between the clustering centers of the clustering clusters to which these two data points belong up to this clustering; for any one dimension, calculating the importance degree of this dimension based on the difference between the value of each data point in this dimension and the mean value of the data points in this dimension; using the importance degree as a weight to weight the Euclidean distance from each data point to each clustering center to obtain the weighted Euclidean distance from each data point to each clustering center; pre-assigning each data to the clustering cluster with the smallest weighted Euclidean distance according to the weighted Euclidean distance; calculating the possibility of each data point being assigned to each clustering cluster based on the ratio of the similarity mean value of each data point and all data points in each clustering cluster and the weighted Euclidean distance; and assigning each data point to the clustering cluster with the greatest possibility according to the possibility to complete this clustering.

[0008] The beneficial effects are as follows: By using the iterative self-organizing clustering algorithm to obtain the outlier degrees of each data point and taking the mean of the outlier degrees of all data points as the outlier degree of the granary environmental data, it is possible to more accurately identify the outlier points in the environmental data, thereby improving the accuracy of outlier detection; Through cluster analysis, a large number of environmental data points can be effectively classified, reducing redundant information and improving data processing efficiency; The evaluation of importance enables the control system to focus on the most relevant dimensions and optimize the decision-making process; By quantifying the similarity between each data point and any other data point, the similarity between data points can be measured more accurately, thereby improving the robustness of data processing; The calculation of similarity and weighted Euclidean distance enables data points to be assigned to the most suitable clusters, thereby improving the accuracy of clustering and avoiding classification errors that may exist in traditional methods.

[0009] Further, the data of each dimension includes: temperature dimension data, humidity dimension data, and oxygen concentration dimension data.

[0010] Further, the similarity satisfies the following relational expression: ; In the formula, is the similarity between the th data point and the th data point, is the number of dimensions, is the value of the th data point in the th dimension, is the value of the th data point in the th dimension, is the number of clustering times up to this clustering, is the th clustering, and is the Euclidean distance between the clustering centers of the clusters to which the th and th data points belong, is a hyperparameter, is the natural exponential function.

[0011] The beneficial effects are as follows: By comprehensively considering the differences in each dimension and the distance between clustering centers, the similarity between data points can be measured more precisely, which helps to improve the accuracy of clustering and enables similar environmental data points to be effectively assigned to the same cluster.

[0012] Further, the importance satisfies the following relational expression: ; In the formula, is the importance of the th dimension, is the number of data points, is the The value of a data point in the th dimension, is the mean value of all data points in the th dimension, and is the standard normalization function.

[0013] The beneficial effects are as follows: By calculating the importance of different dimensions, we can better understand the structure and characteristics of the data, helping to identify the impact of dimensions on the overall data; By quantifying the importance, we can prioritize the attention and analysis of features with high importance, saving time and resources; By analyzing the dimensions with higher importance, it is easier to identify potential outliers or data points that do not meet expectations, ensuring the quality and reliability of the data.

[0014] Furthermore, the weighted Euclidean distance satisfies the following relationship: ; where is the weighted Euclidean distance between the th data point and the cluster center of the th cluster, is the number of dimensions, is the importance of the th dimension, is the Euclidean distance between the th data point and the cluster center of the th cluster in the th dimension.

[0015] The beneficial effects are as follows: By introducing the dimension importance, it can effectively reflect the relative importance of each dimension in distance calculation; The weighted Euclidean distance takes into account the importance of each dimension, can improve the accuracy of clustering, ensure more reasonable distance calculation, and thus obtain better clustering results; When the feature distribution of the dataset changes, the importance of dimensions can be dynamically adjusted, enabling the distance calculation to adapt to new data features and enhancing the flexibility and adaptability of the model.

[0016] Furthermore, the possibility satisfies the following relationship: ; where is the possibility that the th data point is assigned to the th cluster, is the mean similarity between the th data point and all data points within the th cluster, is the weighted Euclidean distance between the th data point and the cluster center of the th cluster, and is the standard normalization function.

[0017] The beneficial effects are as follows: By combining the average similarity between data points and clusters with the weighted Euclidean distance, the relationship between data points and clusters can be effectively measured, which helps to determine the clustering attribution of data points; through the standard normalization function, the possibility values can be compressed into a unified range, facilitating subsequent comparison and analysis and avoiding biases caused by data of different scales.

[0018] Further, obtaining the abnormality degree of each data point through the iterative self-organizing clustering algorithm includes: taking the normalization result of the Euclidean distance between each data point and the cluster center of its affiliated cluster in the final clustering result of the iterative self-organizing clustering algorithm as the abnormality degree of each data point, and the abnormality degree satisfies: ; In the formula, is the abnormality degree of the th data point, is the Euclidean distance between the th data point and the cluster center of its affiliated cluster in the final clustering result, is the standard normalization function.

[0019] Further, the realization of the industrial frequency control of the high-pressure fan based on data processing includes: controlling and adjusting the industrial frequency of the high-pressure fan according to the abnormality degree of the environmental data in the granary, and the adjustment amount of the adjusted working frequency satisfies: ; In the formula, is the adjustment amount of the adjusted working frequency, is the working frequency before adjustment, is the abnormality degree of the environmental data in the granary, is the preset abnormality threshold, is the hyperbolic tangent function.

[0020] In the second aspect, the present invention provides an industrial frequency control system for a high-pressure fan based on data processing, adopting the following technical solution: An industrial frequency control system for a high-pressure fan based on data processing includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned industrial frequency control method for a high-pressure fan based on data processing is realized.

[0021] By adopting the above technical solution, the above-mentioned industrial frequency control method for a high-pressure fan based on data processing is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0022] The present invention has the following technical effects: By analyzing the distance between each data point and the cluster centers of other clusters during each clustering in each iteration process, and then weightedly correcting the Euclidean distance between the data point and other cluster centers, the error accumulation during the clustering process is reduced, making the clustering result more accurate, and further improving the accuracy of the power frequency control of the high-pressure fan. Description of the Drawings

[0023] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals are for the same or corresponding parts.

[0024] Figure 1 is a flowchart of a method for power frequency control of a high-pressure fan based on data processing according to an embodiment of the present invention.

[0025] Figure 2 is a flowchart during each iteration of the iterative self-organizing clustering algorithm for a method for power frequency control of a high-pressure fan based on data processing according to an embodiment of the present invention. Detailed Embodiments

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be understood that when the claims, specifications, and drawings of the present invention use terms such as "first" and "second", they are only used to distinguish different objects and not to describe a specific order. The terms "including" and "comprising" used in the specifications and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0028] An embodiment of the present invention discloses a method for power frequency control of a high-pressure fan based on data processing. Refer to Figure 1 , including steps S1 - S3: S1: Obtain the data of each dimension of each data point in the environmental data of the grain depot.

[0029] It should be noted that by monitoring the environmental data in the grain depot and combining with an intelligent management system, automatic control of the environment in the grain depot can be realized. By timely adjusting the storage environment, it is ensured that the grain is stored in the best state, reducing spoilage and losses.

[0030] Specifically, the data of each dimension includes: temperature dimension data, humidity dimension data, and oxygen concentration dimension data.

[0031] By evenly dividing the area in the granary and arranging temperature sensors, humidity sensors, and oxygen concentration measuring instruments in each area, the temperature, humidity, and oxygen content in the area are collected. The preset collection frequency during collection is 1 min / time, and the implementer can adjust the collection frequency according to the specific implementation situation. The temperature data value, humidity data value, and oxygen content data value collected at the same moment in the same area are used as the values of different dimensions of a data point.

[0032] S2: Obtain the anomaly degree of each data point through the iterative self-organizing clustering algorithm.

[0033] Specifically, obtaining the anomaly degree of each data point through the iterative self-organizing clustering algorithm includes: Taking the normalization result of the Euclidean distance between each data point and the clustering center of its affiliated clustering cluster in the final clustering result of the iterative self-organizing clustering algorithm as the anomaly degree of each data point, and the anomaly degree satisfies: ; where is the anomaly degree of the th data point, is the Euclidean distance between the th data point and the clustering center of its affiliated clustering cluster in the final clustering result, is the standard normalization function.

[0034] During each round of iteration of the iterative self-organizing clustering algorithm, referring to Figure 2 , step S2 includes steps S201 - S205, specifically as follows: S201: For each clustering in each round of iteration, calculate the similarity between data points based on the difference in the values of each dimension between any two data points and the Euclidean distance between the clustering centers of the clustering clusters to which the two data points belong up to this clustering.

[0035] It should be noted that the iterative self-organizing clustering algorithm is a clustering method based on self-organizing characteristics and iterative optimization ideas. This algorithm optimizes the clustering results by randomly selecting initial clustering centers and iterating repeatedly. In each iteration, the algorithm assigns data points to the nearest clustering center and updates the positions of the clustering centers according to the assignment results until the clustering centers no longer change, thereby effectively clustering environmental data. However, since the data in each dimension of the granary environmental data is gradually changing, there will be multiple clustering clusters with relatively close Euclidean distances to the same data point. Violently assigning the data point to the nearest clustering center will ignore the local change characteristics of the data, resulting in errors in the clustering process and continuous accumulation of errors in the continuous clustering process, thus making the clustering results inaccurate. Therefore, the present invention calculates the similarity degree between two data points to facilitate subsequent correction of the clustering results of each round according to the similarity degree and reduce errors.

[0036] Specifically, the similarity satisfies the following relational expression: ; In the formula, is the similarity between the th data point and the th data point, is the number of dimensions, is the value of the th data point in the th dimension, is the value of the th data point in the th dimension, is the number of clustering times up to this clustering, is the th clustering, and is the Euclidean distance between the clustering centers of the clustering clusters to which the th and is a hyperparameter, is the natural exponential function.

[0037] Implementers can set the hyperparameter according to the specific implementation situation. For example, 0.1. The existence of the hyperparameter is to prevent from occurring and making the calculation result meaningless.

[0038] Among them, represents the difference in data values of the th and th data points in each dimension. The smaller its value, the higher the similarity degree between these two data points; It represents the Euclidean distance between the cluster centers to which these two data points belong during the clustering process. The smaller its value, the closer the clusters to which these two data points belong, that is, the higher the similarity degree of these two data points.

[0039] S202: For any dimension, calculate the importance degree of this dimension based on the difference between the value of each data point in this dimension and the mean value of the data points within this dimension.

[0040] It should be noted that since the distribution situations of data in different dimensions are different, and the distribution situations in different dimensions reflect the importance degrees of different dimensions. When the traditional iterative self-organizing clustering algorithm assigns multi-dimensional data points to clusters, it uses the same weight to calculate the Euclidean distance for all dimensions, which cannot reflect the distribution situations of different dimensions, thus making the calculation result inaccurate. Therefore, the present invention calculates the importance degree of each dimension according to the data fluctuation degree of different dimensions, which is convenient for subsequent weighted calculation of the Euclidean distance.

[0041] Specifically, the importance degree satisfies the following relational expression: ; In the formula, is the importance degree of the th dimension, is the number of data points, is the th data point's value in the th dimension, is the mean value of all data points in the th dimension, is the standard normalization function.

[0042] Among them, represents the difference between the data values of all data points in the th dimension and the average level of this dimension. The larger its value, the greater the data change in this dimension, the greater its influence on clustering, that is, the higher the importance degree of this dimension; then by dividing by the standard deviation of this dimension, the influence brought by the order of magnitude of the data values in different dimensions is eliminated.

[0043] S203: Use the importance degree as the weight to weight the Euclidean distance from each data point to each cluster center, and obtain the weighted Euclidean distance from each data point to each cluster center; pre-assign each data to the cluster with the smallest weighted Euclidean distance according to the weighted Euclidean distance.

[0044] It should be noted that in the traditional iterative self-organizing clustering algorithm, during the clustering process, data points are violently assigned to the clustering cluster with the smallest Euclidean distance, without considering the distribution of different dimensions and the connections between data points. Therefore, in the present invention, the weighted Euclidean distance between any data point and any clustering center is calculated according to the similarity degree between any data point and other data points and the importance degree of each dimension.

[0045] Specifically, the weighted Euclidean distance satisfies the following relational expression: ; In the formula, is the weighted Euclidean distance between the th data point and the clustering center of the th clustering cluster, is the number of dimensions, is the importance degree of the th dimension, is the Euclidean distance between the th data point and the clustering center of the th clustering cluster in the th dimension.

[0046] Among them, if the importance degree of the th dimension is higher, the proportion of the Euclidean distance of this dimension is larger.

[0047] S204: Calculate the possibility of each data point being assigned to each clustering cluster based on the ratio of the similarity mean value between each data point and all data points in each clustering cluster and the weighted Euclidean distance.

[0048] Specifically, the possibility satisfies the following relational expression: ; In the formula, is the possibility that the th data point is assigned to the th clustering cluster, is the similarity mean value between the th data point and all data points in the th clustering cluster, is the weighted Euclidean distance between the th data point and the clustering center of the th clustering cluster, is the standard normalization function.

[0049] Among them, if is larger, it indicates that the th data point and all data points in the th clustering cluster are more similar, then the th data point is assigned to the The greater the possibility in a clustering cluster; Denote the th data point and the th clustering center of the clustering cluster. The smaller its value, the greater the possibility of assigning the th data point to the th clustering cluster.

[0050] S205: Assign each data point to the clustering cluster with the greatest possibility according to the possibility, and complete this clustering.

[0051] S206: In response to the clustering clusters to which the data points belong no longer changing, the clustering ends and enters the next round of iteration.

[0052] In response to the clustering cluster to which the data point belongs being different from the clustering cluster to which it belonged when the previous clustering was completed in this round of iteration, enter the next clustering until the clustering clusters to which the data points belong no longer change, that is, when the clustering clusters to which the data points belong are the same as those to which they belonged when the previous clustering was completed in this round of iteration, the clustering ends and enters the next round of iteration.

[0053] S3: Take the mean value of the abnormality degrees of all data points as the abnormality degree of the environmental data of the granary to implement the industrial frequency control of the high-pressure fan based on data processing.

[0054] Specifically, the implementation of the industrial frequency control of the high-pressure fan based on data processing includes: Control and adjust the industrial frequency of the high-pressure fan according to the abnormality degree of the environmental data in the granary. The adjustment amount of the adjusted working frequency satisfies: ; In the formula, is the adjustment amount of the adjusted working frequency, is the working frequency before adjustment, is the abnormality degree of the environmental data in the granary, is the preset abnormality threshold, is the hyperbolic tangent function.

[0055] Implementers can set the abnormality threshold according to the specific implementation situation to ensure that the abnormality threshold is fine, for example, 0.5.

[0056] Among them, if the abnormality degree of the environmental data in the granary is low, appropriately lower the industrial frequency of the high-pressure fan to avoid excessive resource consumption; if the abnormality degree of the environmental data in the granary is high, increase the industrial frequency of the high-pressure fan to achieve rapid adjustment of the environmental data in the granary.

[0057] An embodiment of the present invention also discloses a high-voltage fan power-frequency control system based on data processing, which includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a high-voltage fan power-frequency control method according to the present invention is implemented.

[0058] The above system further includes a communication bus, a communication interface and other components well-known to those skilled in the art. Their settings and functions are known in the art, so they will not be described in detail here.

[0059] In the present invention, the foregoing memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device or apparatus. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, or any other medium that can be used to store the required information and can be accessed by an application program, module or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0060] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

[0061] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A method for controlling the power frequency of a high-pressure fan based on data processing, characterized in that: include: Obtain data of each dimension of each data point in the environmental data of the granary; obtain the abnormality of each data point through an iterative self-organizing clustering algorithm, and use the mean of the abnormality of all data points as the abnormality of the environmental data of the granary to achieve power frequency control of the high-pressure fan based on data processing; In each round of iteration of the iterative self-organizing clustering algorithm, in response to the clusters to which each data point belongs no longer changing, clustering ends and enters the next round of iteration, including: for each clustering in each round of iteration, based on the difference in the values ​​of any two data points in each dimension and the Euclidean distance between the cluster centers of the clusters to which the above two data points belong in each clustering up to this clustering, the similarity between the data points is calculated; for any dimension, based on the difference between the value of each data point in the dimension and the average value of the data points in the dimension, the importance of the dimension is calculated; using the importance as a weight, the Euclidean distance from each data point to each cluster center is weighted to obtain the weighted Euclidean distance from each data point to each cluster center; pre-allocating each data point to the cluster with the smallest weighted Euclidean distance according to the weighted Euclidean distance; calculating the possibility of each data point being allocated to each cluster based on the average similarity between each data point and all data points in each cluster and the ratio of the weighted Euclidean distance; and allocating each data point to the cluster with the greatest possibility according to the possibility to complete this clustering.

2. A method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1, characterized in that: The dimensional data include: temperature dimensional data, humidity dimensional data and oxygen concentration dimensional data.

3. The method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1 is characterized in that: The similarity satisfies the following relationship: ； In the formula, For the data points and The similarity between data points, is the number of dimensions, For the The data point in The value of the dimension, For the The data point in The value of the dimension, is the number of clusterings up to this clustering, For the The second clustering and The Euclidean distance between the cluster centers of the clusters to which the data points belong. is a hyperparameter, is a natural exponential function.

4. The method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1 is characterized in that: The importance satisfies the following relationship: ； In the formula, For the The importance of the dimension, is the number of data points, For the The data point in The value of the dimension, For all data points in The mean of the dimensions, is the standard normalization function.

5. The method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1 is characterized in that: The weighted Euclidean distance satisfies the following relationship: ； In the formula, For the Data points to The weighted Euclidean distance between the cluster centers of clusters, is the number of dimensions, For the The importance of the dimension, For the Data points to The cluster center of the cluster is in Euclidean distance in dimensions.

6. A method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1, characterized in that: The possibility satisfies the following relationship: ； In the formula, For the Data points are assigned to The probability of clusters, For the data points and The mean similarity between all data points in a cluster, For the Data points to The weighted Euclidean distance between the cluster centers of clusters, is the standard normalization function.

7. The method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1 is characterized in that: The method of obtaining the abnormality of each data point by iterative self-organizing clustering algorithm includes: The normalized result of the Euclidean distance between each data point and the cluster center of the cluster to which it belongs in the final clustering result of the iterative self-organizing clustering algorithm is used as the abnormality of each data point. The abnormality satisfies: ; In the formula, For the The abnormality of a data point, In the final clustering result The Euclidean distance between a data point and the cluster center of the cluster to which it belongs, is the standard normalization function.

8. The method for controlling the power frequency of a high-pressure blower based on data processing according to claim 1 is characterized in that: The method for realizing the power frequency control of the high-pressure fan based on data processing includes: The power frequency of the high-pressure fan is controlled and adjusted according to the abnormality of the environmental data in the granary. The adjustment amount of the adjusted working frequency satisfies: ; In the formula, is the adjustment amount of the adjusted operating frequency, is the working frequency before adjustment, is the abnormality of the environmental data in the granary, To preset the abnormal threshold, is the hyperbolic tangent function.

9. A high-pressure fan power frequency control system based on data processing, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a high-pressure fan power frequency control method based on data processing according to any one of claims 1 to 8 is implemented.

Images