A method and system for constructing a reduction motor control network and collecting data

Abstract

The present invention relates to a method and system for constructing and collecting data of a reduction motor control network, and belongs to the technical field of reduction motor control. The present invention constructs torque data characteristic change data based on a time series, introduces a dynamic Bayesian network, and inputs the torque data characteristic change data based on a time series into the dynamic Bayesian network for observation state update. By observing the state update, the updated torque data characteristic change data based on a time series is obtained, and the updated torque data characteristic change data based on a time series is subjected to torque state anomaly identification and analysis, and a relevant control strategy is generated based on the anomaly identification and analysis results. By constructing a reduction motor control network, the present invention can monitor multiple reduction motors, thereby timely discovering abnormal conditions of the reduction motors, and then timely controlling the reduction motors, avoiding abnormal use of the reduction motors, and improving the service life of the reduction motors.

Description

Technical Field

[0001] The present invention relates to the technical field of reduction motor control, and in particular to a reduction motor control network construction and data acquisition method and system. Background Art

[0002] A reduction motor is a combination of a reducer and an electric motor. This assembly is also commonly referred to as a gear motor or gear motor. It is typically assembled and supplied as a complete set by specialized reducer manufacturers. Gear motors are widely used in the steel and machinery industries, among others. The advantages of using a reduction motor include simplified design and space savings. With the continuous development of the reduction motor industry, a growing number of industries and businesses are utilizing reduction motors, and a number of companies have also entered the industry. The micro reduction motor and DC reduction motor industry, established in the 1950s, has evolved through stages of imitation, independent design, research and development, and large-scale manufacturing. It has now established an industry system with a comprehensive suite of product development, large-scale production, key components, key materials, specialized manufacturing equipment, and testing instruments, all supported by an increasingly internationalized system. However, during use, reduction motors can be affected by external factors, which can affect their torque. Failure to promptly detect torque anomalies can damage the reduction motor and reduce its service life. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method and system for constructing a reduction motor control network and collecting data.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides a method for constructing a reduction motor control network and collecting data, comprising the following steps:

[0006] Constructing a reduction motor control network, integrating the data of the reduction motors in the target area into the reduction motor control network, and initializing data acquisition parameters of the reduction motor control network;

[0007] Setting a data collection period, collecting torque data information of each reduction motor within a data collection period through the reduction motor control network, and analyzing and processing the torque data information of the reduction motor within the data collection period to obtain processed torque data information;

[0008] Constructing time-series torque data feature change data based on the processed torque data information, introducing a dynamic Bayesian network, and inputting the time-series torque data feature change data into the dynamic Bayesian network to update the observation state;

[0009] By observing the state update, the updated time-series-based torque data feature change data is obtained, and the updated time-series-based torque data feature change data is subjected to torque state anomaly identification and analysis, and a relevant control strategy is generated based on the anomaly identification and analysis results.

[0010] Furthermore, in the method for constructing a reduction motor control network and collecting data, the reduction motor control network is constructed, the data of the reduction motors in the target area are integrated into the reduction motor control network, and the data collection parameters of the reduction motor control network are initialized, specifically including:

[0011] Build a reduction motor control network, obtain the maximum information processing capacity of the reduction motor control network within a data acquisition cycle, the data size information of a single reduction motor during data acquisition, and obtain the number of reduction motors in the current target area;

[0012] Calculate the total estimated data processing volume under the number of reduction motors in the current target area based on the data size information of the single number reduction motors during data collection and the number of reduction motors in the current target area;

[0013] If the total estimated data processing capacity under the number information of the reduction motors in the current target area is greater than the maximum information processing capacity of the reduction motor control network within one data collection cycle, then reinitialize the number information of the reduction motors when performing data collection within one data collection cycle;

[0014] Until it is no more than the maximum information processing amount of the reduction motor control network within a data collection cycle, a data collection plan is constructed according to the number information of the reduction motors when performing data collection within a data collection cycle, and data collection planning is performed according to the data collection plan.

[0015] Furthermore, in the construction and data acquisition method of the reduction motor control network, a data acquisition cycle is set, and the torque data information of each reduction motor within a data acquisition cycle is collected through the reduction motor control network, and the torque data information of the reduction motor within a data acquisition cycle is analyzed and processed to obtain the processed torque data information, specifically:

[0016] Setting a data collection period, collecting torque data information of each reduction motor within a data collection period through the reduction motor control network, introducing an outlier detection algorithm, and inputting the torque data information of each reduction motor within a data collection period into the outlier detection algorithm for outlier detection;

[0017] Obtaining outlier data from the torque data information of each reduction motor within a data collection cycle through outlier detection, and deleting the outlier data from the torque data information of each reduction motor within a data collection cycle;

[0018] After deletion, the sorted torque data information of each reduction motor within a data acquisition cycle is obtained and output as processed torque data information.

[0019] Furthermore, in the method for constructing and collecting data of the reduction motor control network, torque data characteristic change data based on time series is constructed based on the processed torque data information, a dynamic Bayesian network is introduced, and the torque data characteristic change data based on time series is input into the dynamic Bayesian network for observation state update, specifically:

[0020] Arrange and sort the processed torque data information according to the order of time points, construct torque data feature change data based on time series, and introduce dynamic Bayesian network;

[0021] Inputting the time series-based torque data feature change data into the dynamic Bayesian network, and treating the torque data information of each timestamp in the time series-based torque data feature change data as an observation state;

[0022] Calculate the state transition probability value of each observation state transferring to another observation state, set a state transition probability threshold, and determine whether the state transition probability value of each observation state transferring to another observation state is greater than the state transition probability threshold;

[0023] The observation state whose state transition probability value is greater than the state transition probability threshold is updated to another observation state, and the observation state whose state transition probability value is not greater than the state transition probability threshold is maintained unchanged.

[0024] Furthermore, in the construction and data acquisition method of the reduction motor control network, by observing the state update, the updated torque data characteristic change data based on the time series is obtained, and the torque state abnormality identification and analysis are performed on the updated torque data characteristic change data based on the time series, specifically including:

[0025] Obtain updated time-series-based torque data feature change data by observing the state update, set a torque data threshold, and determine whether there is torque data greater than the torque data threshold in the updated time-series-based torque data feature change data;

[0026] When there is torque data greater than a torque data threshold value in the updated time series-based torque data feature change data, the corresponding reduction motor is regarded as an abnormally operating reduction motor and an early warning is issued;

[0027] When there is no torque data greater than the torque data threshold value in the updated time series-based torque data characteristic change data, the output is a normal operation of the reduction motor.

[0028] Furthermore, in the construction of the reduction motor control network and the data acquisition method, relevant control strategies are generated based on the abnormality identification and analysis results, specifically including:

[0029] Acquire real-time torque data of the abnormal reduction motor in the abnormality identification and analysis results, and acquire estimated maximum torque data of the current abnormal reduction motor, and set a stop working torque threshold according to the estimated maximum torque data of the current abnormal reduction motor;

[0030] Determining whether the real-time torque data of the abnormal reduction motor in the abnormality identification and analysis result is greater than the stop working torque threshold;

[0031] When the real-time torque data of the abnormal reduction motor in the abnormal identification and analysis result is greater than the stop-work torque threshold, a stop-work instruction is issued, and the reduction motor is controlled according to the stop-work instruction;

[0032] When the real-time torque data of the abnormal reduction motor in the abnormality identification and analysis result is not greater than the stop-work torque threshold, the current abnormal reduction motor is continuously monitored and an early warning is issued.

[0033] The second aspect of the present invention provides a system for constructing and acquiring data of a reduction motor control network, comprising a memory and a processor, wherein the memory comprises a program for constructing and acquiring data of a reduction motor control network. When the program for constructing and acquiring data of a reduction motor control network is executed by the processor, the steps of any one of the methods for constructing and acquiring data of a reduction motor control network are implemented.

[0034] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for the construction and data acquisition method of a reduction motor control network. When the program for the construction and data acquisition method of a reduction motor control network is executed by a processor, the steps of any one of the methods for construction and data acquisition of a reduction motor control network are implemented.

[0035] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0036] The present invention integrates the data of the reduction motors in the target area into the reduction motor control network by constructing a reduction motor control network, initializes the data acquisition parameters of the reduction motor control network, sets a data acquisition cycle, collects the torque data information of each reduction motor within a data acquisition cycle through the reduction motor control network, analyzes and processes the torque data information of the reduction motor within a data acquisition cycle, obtains the processed torque data information, constructs torque data feature change data based on a time series based on the processed torque data information, introduces a dynamic Bayesian network, and inputs the torque data feature change data based on the time series into the dynamic Bayesian network for observation state update, obtains updated torque data feature change data based on the time series through the observation state update, and performs torque state abnormality identification and analysis on the updated torque data feature change data based on the time series, and generates relevant control strategies based on the abnormality identification and analysis results. By constructing a reduction motor control network, the present invention can monitor multiple reduction motors, thereby timely discovering the abnormality of the reduction motors, and then timely controlling the reduction motors, avoiding abnormal use of the reduction motors, and improving the service life of the reduction motors. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0038] Figure 1 The overall flow chart of the construction of the reduction motor control network and the data acquisition method is shown;

[0039] Figure 2 A partial flow chart showing the construction of a reduction motor control network and a data acquisition method;

[0040] Figure 3 The system block diagram of the reduction motor control network and the data acquisition system is shown. DETAILED DESCRIPTION

[0041] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0043] like Figure 1 As shown, the first aspect of the present invention provides a method for constructing a reduction motor control network and collecting data, comprising the following steps:

[0044] S102: constructing a reduction motor control network, integrating the data of the reduction motors in the target area into the reduction motor control network, and initializing data acquisition parameters of the reduction motor control network;

[0045] S104: Setting a data collection period, collecting torque data information of each reduction motor within a data collection period through the reduction motor control network, and analyzing and processing the torque data information of the reduction motor within the data collection period to obtain processed torque data information;

[0046] S106: constructing time-series torque data feature change data based on the processed torque data information, introducing a dynamic Bayesian network, and inputting the time-series torque data feature change data into the dynamic Bayesian network to update the observation state;

[0047] S108: Obtain updated time-series-based torque data feature change data by observing state updates, perform torque state anomaly identification and analysis on the updated time-series-based torque data feature change data, and generate relevant control strategies based on the anomaly identification and analysis results.

[0048] It should be noted that the present invention can monitor multiple reduction motors by constructing a reduction motor control network, so as to promptly detect abnormal conditions of the reduction motors, and then promptly control the reduction motors to avoid abnormal use of the reduction motors and improve the service life of the reduction motors.

[0049] like Figure 2 As shown, further, in the method for constructing a reduction motor control network and collecting data, a reduction motor control network is constructed, data of the reduction motor in the target area is integrated into the reduction motor control network, and data collection parameters of the reduction motor control network are initialized, specifically including:

[0050] S202: Build a reduction motor control network, obtain the maximum information processing capacity of the reduction motor control network within a data acquisition cycle, and the data size information of a single reduction motor during data acquisition, and obtain the number of reduction motors in the current target area;

[0051] S204: Calculating a total estimated data processing volume under the number of reducer motors in the current target area based on the data size information of a single number of reducer motors during data collection and the number of reducer motors in the current target area;

[0052] S206: If the total estimated data processing capacity of the number of reduction motors in the current target area is greater than the maximum information processing capacity of the reduction motor control network within one data collection cycle, reinitialize the number of reduction motors during data collection within one data collection cycle;

[0053] S208: Until it is no more than the maximum information processing capacity of the reduction motor control network within a data collection cycle, a data collection plan is constructed according to the number information of the reduction motors when performing data collection within a data collection cycle, and data collection planning is performed according to the data collection plan.

[0054] It should be noted that, in fact, the data that needs to be collected by the reduction motor includes real-time speed information, real-time torque information, real-time voltage information, real-time current information, etc. The more data that needs to be collected, the larger the data size information of a single reduction motor during data collection will be. For example, the data size that needs to be processed once is 10 megabytes. In fact, the processing capacity of the computer system has an upper limit, that is, the reduction motor control network has a maximum information processing capacity within a data collection cycle. Through this method, the number information of the reduction motor during data collection within a data collection cycle can be optimized according to the maximum information processing capacity of the reduction motor control network within a data collection cycle, thereby improving the rationality of data collection.

[0055] It should be noted that obtaining the maximum information processing capacity of the reduction motor control network within a data acquisition cycle specifically includes:

[0056] By testing the reduction motor control network, a maximum information processing capacity change characteristic of the reduction motor control network within a data acquisition cycle under each storage capacity data is obtained;

[0057] Introducing a graph neural network, inputting the maximum information processing capacity change characteristics of the reduction motor control network under each storage capacity data within a data acquisition cycle into the graph neural network, and using the storage capacity data as the first node of the graph neural network;

[0058] Taking the maximum information processing amount feature as the second node of the graph neural network, constructing a directed description relationship, connecting the first node and the second node based on the directed description relationship, constructing a topological structure graph, and obtaining a related adjacency matrix based on the topological structure graph; constructing a knowledge graph, inputting the related adjacency matrix into the knowledge graph for storage, obtaining the real-time data storage capacity of the current reduction motor control network, and inputting the real-time data storage capacity of the current reduction motor control network into the knowledge graph for data matching;

[0059] Through data matching, the real-time data storage capacity of the current reduction motor control network below the current data storage capacity is obtained, and the maximum information processing capacity of the current reduction motor control network within a data acquisition cycle is updated according to the real-time data storage capacity of the reduction motor control network below the current data storage capacity.

[0060] It should be noted that due to the influence of data storage capacity, when the computer system is processing data, the larger the data storage capacity, the corresponding data processing capacity gradually decreases. Therefore, this method is used to update the maximum information processing capacity of the current reduction motor control network within a data acquisition cycle, thereby improving the rationality of the construction of the reduction motor control network.

[0061] Furthermore, in the construction and data acquisition method of the reduction motor control network, a data acquisition cycle is set, and the torque data information of each reduction motor within a data acquisition cycle is collected through the reduction motor control network, and the torque data information of the reduction motor within a data acquisition cycle is analyzed and processed to obtain the processed torque data information, specifically:

[0062] A data collection cycle is set, and the torque data information of each reduction motor within a data collection cycle is collected through the reduction motor control network. An outlier detection algorithm is introduced, and the torque data information of each reduction motor within a data collection cycle is input into the outlier detection algorithm for outlier detection;

[0063] Obtain outlier data from the torque data of each reduction motor within a data collection cycle through outlier detection, and delete the outlier data from the torque data of each reduction motor within a data collection cycle;

[0064] After deletion, the sorted torque data information of each reduction motor within a data acquisition cycle is obtained and output as processed torque data information.

[0065] It should be noted that since data collection involves collecting a number of data within a data collection cycle (such as 10 seconds, 20 seconds, 1 minute, etc.), the data collected within this data collection cycle may be abnormal. The outlier detection algorithm is used to delete abnormal data, making data collection more reasonable.

[0066] Furthermore, in the construction and data acquisition method of the reduction motor control network, the torque data characteristic change data based on the time series is constructed based on the processed torque data information, and the dynamic Bayesian network is introduced. The torque data characteristic change data based on the time series is input into the dynamic Bayesian network for observation state update, specifically:

[0067] The processed torque data information is sorted in the order of time points, and the torque data feature change data based on time series is constructed, and a dynamic Bayesian network is introduced;

[0068] Inputting the time series-based torque data feature change data into the dynamic Bayesian network, and taking the torque data information of each timestamp in the time series-based torque data feature change data as an observation state;

[0069] Calculate the state transition probability value of each observation state to another observation state, set the state transition probability threshold, and determine whether the state transition probability value of each observation state to another observation state is greater than the state transition probability threshold;

[0070] The observation state whose state transition probability value is greater than the state transition probability threshold is updated to another observation state, and the observation state whose state transition probability value is not greater than the state transition probability threshold is maintained unchanged.

[0071] It should be noted that the state transition probability value of each observation state to another observation state is calculated through the dynamic Bayesian network, and the state transition probability threshold is set. The observation state with a state transition probability value greater than the state transition probability threshold is updated to another observation state, and the observation state with a state transition probability value not greater than the state transition probability threshold is maintained unchanged. In this way, the torque data characteristic change data based on the time series can be updated in a timely manner to improve the rationality of monitoring.

[0072] Furthermore, in the construction and data acquisition method of the reduction motor control network, by observing the state update, the updated torque data characteristic change data based on the time series is obtained, and the torque state abnormality identification and analysis are performed on the updated torque data characteristic change data based on the time series, specifically including:

[0073] Obtain updated time-series-based torque data feature change data by observing the state update, set a torque data threshold, and determine whether there is torque data greater than the torque data threshold in the updated time-series-based torque data feature change data;

[0074] When there is torque data greater than a torque data threshold value in the updated time series-based torque data feature change data, the corresponding reduction motor is regarded as an abnormally operating reduction motor and an early warning is issued;

[0075] When there is no torque data greater than the torque data threshold value in the updated time series-based torque data feature change data, the output is a normal operation of the reduction motor.

[0076] It should be noted that in some special scenarios, such as abnormal external factors, the torque data of the reduction motor gradually increases within a predetermined time. When it increases to a certain limit, the reduction motor will cause abnormal operation. This method can identify abnormally operating reduction motors.

[0077] Furthermore, in the construction of the reduction motor control network and the data acquisition method, relevant control strategies are generated based on the abnormality identification and analysis results, specifically including:

[0078] Obtaining the real-time torque data of the abnormal reduction motor in the abnormality identification and analysis results, and obtaining the estimated maximum torque data of the current abnormal reduction motor, and setting the stop working torque threshold according to the estimated maximum torque data of the current abnormal reduction motor;

[0079] Determine whether the real-time torque data of the abnormal reduction motor in the abnormal identification analysis result is greater than the stop working torque threshold;

[0080] When the real-time torque data of the abnormal reduction motor in the abnormal identification and analysis results is greater than the stop-work torque threshold, a stop-work instruction is issued, and the reduction motor is controlled according to the stop-work instruction;

[0081] When the real-time torque data of the abnormal reduction motor in the abnormal identification and analysis results is not greater than the stop working torque threshold, the current abnormal reduction motor is continuously monitored and an early warning is issued.

[0082] It should be noted that, in fact, the motor has a maximum torque parameter under the extreme working parameters. Through this method, the stopping torque threshold can be set according to the estimated maximum torque data of the current abnormal reduction motor, thereby controlling the current abnormal reduction motor and improving the service life of the reduction motor.

[0083] In this method, the estimated maximum torque data of the current abnormal reduction motor is obtained, specifically including:

[0084] The maximum torque data variation characteristics of the reduction motor under various working environments are obtained through big data, and a prediction model for the maximum torque data variation characteristics of the reduction motor is constructed based on a deep neural network.

[0085] Inputting the maximum torque data variation characteristics of the reduction motor under each working environment into the reduction motor maximum torque data variation characteristic prediction model for training, thereby obtaining a trained reduction motor maximum torque data variation characteristic prediction model;

[0086] Obtaining the current abnormal working environment information of the reduction motor and the maximum torque data change characteristics within a preset time, and inputting the current abnormal working environment information of the reduction motor and the maximum torque data change characteristics within the preset time into the trained reduction motor maximum torque data change characteristic prediction model for prediction;

[0087] The estimated maximum torque data of the abnormal reduction motor at the current timestamp is obtained through prediction, and the estimated maximum torque data of the current abnormal reduction motor is updated according to the estimated maximum torque data of the abnormal reduction motor at the current timestamp.

[0088] It should be noted that the maximum torque data change characteristics of the reduction motor under different working environments (such as temperature, humidity, load conditions, etc.) are different. Through this method, the estimated maximum torque data of the current abnormal reduction motor can be updated, further improving the rationality of monitoring.

[0089] like Figure 3 As shown, the second aspect of the present invention provides a system 4 for constructing a reduction motor control network and collecting data, including a memory 41 and a processor 42. The memory 41 includes a program for constructing a reduction motor control network and collecting data. When the program for constructing a reduction motor control network and collecting data is executed by the processor 42, the following steps are implemented:

[0090] Construct a reduction motor control network, integrate the data of the reduction motors in the target area into the reduction motor control network, and initialize the data acquisition parameters of the reduction motor control network;

[0091] Setting a data collection cycle, collecting torque data information of each reduction motor within a data collection cycle through the reduction motor control network, and analyzing and processing the torque data information of the reduction motor within the data collection cycle to obtain processed torque data information;

[0092] Based on the processed torque data information, the torque data feature change data based on the time series is constructed, the dynamic Bayesian network is introduced, and the torque data feature change data based on the time series is input into the dynamic Bayesian network to update the observation state;

[0093] By observing the state update, the updated time-series-based torque data feature change data is obtained, and the updated time-series-based torque data feature change data is used to identify and analyze torque state anomalies, and relevant control strategies are generated based on the anomaly identification and analysis results.

[0094] Furthermore, in this system, a reduction motor control network is constructed, the data of the reduction motors in the target area are integrated into the reduction motor control network, and the data acquisition parameters of the reduction motor control network are initialized, specifically including:

[0095] Build a reduction motor control network, obtain the maximum information processing capacity of the reduction motor control network within a data acquisition cycle, the data size information of a single reduction motor during data acquisition, and obtain the number of reduction motors in the current target area;

[0096] Calculate the total estimated data processing volume under the number of reducer motors in the current target area based on the data size information of a single number of reducer motors during data collection and the number of reducer motors in the current target area;

[0097] If the total estimated data processing capacity under the number information of the reduction motors in the current target area is greater than the maximum information processing capacity of the reduction motor control network within one data collection cycle, the number information of the reduction motors during data collection within one data collection cycle is reinitialized;

[0098] Until it is no more than the maximum information processing capacity of the reduction motor control network within a data collection cycle, a data collection plan is constructed according to the quantity information of the reduction motors when performing data collection within a data collection cycle, and data collection planning is carried out according to the data collection plan.

[0099] Furthermore, in this system, a data collection cycle is set, and the torque data information of each reduction motor within a data collection cycle is collected through the reduction motor control network, and the torque data information of the reduction motor within a data collection cycle is analyzed and processed to obtain the processed torque data information, specifically:

[0100] A data collection cycle is set, and the torque data information of each reduction motor within a data collection cycle is collected through the reduction motor control network. An outlier detection algorithm is introduced, and the torque data information of each reduction motor within a data collection cycle is input into the outlier detection algorithm for outlier detection;

[0101] Obtain outlier data from the torque data of each reduction motor within a data collection cycle through outlier detection, and delete the outlier data from the torque data of each reduction motor within a data collection cycle;

[0102] After deletion, the sorted torque data information of each reduction motor within a data acquisition cycle is obtained and output as processed torque data information.

[0103] Furthermore, in this system, the torque data feature change data based on the time series is constructed based on the processed torque data information, and the dynamic Bayesian network is introduced. The torque data feature change data based on the time series is input into the dynamic Bayesian network for observation state update, specifically:

[0104] The processed torque data information is sorted in the order of time points, and the torque data feature change data based on time series is constructed, and a dynamic Bayesian network is introduced;

[0105] Inputting the time series-based torque data feature change data into the dynamic Bayesian network, and taking the torque data information of each timestamp in the time series-based torque data feature change data as an observation state;

[0106] Calculate the state transition probability value of each observation state to another observation state, set the state transition probability threshold, and determine whether the state transition probability value of each observation state to another observation state is greater than the state transition probability threshold;

[0107] The observation state whose state transition probability value is greater than the state transition probability threshold is updated to another observation state, and the observation state whose state transition probability value is not greater than the state transition probability threshold is maintained unchanged.

[0108] Furthermore, in this system, by observing the state update, the updated torque data characteristic change data based on the time series is obtained, and the torque state abnormality identification and analysis are performed on the updated torque data characteristic change data based on the time series, specifically including:

[0109] Obtain updated time-series-based torque data feature change data by observing the state update, set a torque data threshold, and determine whether there is torque data greater than the torque data threshold in the updated time-series-based torque data feature change data;

[0110] When there is torque data greater than a torque data threshold value in the updated time series-based torque data feature change data, the corresponding reduction motor is regarded as an abnormally operating reduction motor and an early warning is issued;

[0111] When there is no torque data greater than the torque data threshold value in the updated time series-based torque data feature change data, the output is a normal operation of the reduction motor.

[0112] Furthermore, in this system, relevant control strategies are generated based on the abnormality identification and analysis results, including:

[0113] Obtaining the real-time torque data of the abnormal reduction motor in the abnormality identification and analysis results, and obtaining the estimated maximum torque data of the current abnormal reduction motor, and setting the stop working torque threshold according to the estimated maximum torque data of the current abnormal reduction motor;

[0114] Determine whether the real-time torque data of the abnormal reduction motor in the abnormal identification analysis result is greater than the stop working torque threshold;

[0115] When the real-time torque data of the abnormal reduction motor in the abnormal identification and analysis results is greater than the stop-work torque threshold, a stop-work instruction is issued, and the reduction motor is controlled according to the stop-work instruction;

[0116] When the real-time torque data of the abnormal reduction motor in the abnormal identification and analysis results is not greater than the stop working torque threshold, the current abnormal reduction motor is continuously monitored and an early warning is issued.

[0117] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for the construction and data acquisition method of a reduction motor control network. When the program for the construction and data acquisition method of a reduction motor control network is executed by a processor, any step of the construction and data acquisition method of a reduction motor control network is implemented.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0119] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0120] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0121] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0122] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods of the various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0123] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for constructing a reduction motor control network and collecting data, characterized in that: The following steps are involved: Constructing a reduction motor control network, integrating the data of the reduction motors in the target area into the reduction motor control network, and initializing data acquisition parameters of the reduction motor control network; Setting a data collection period, collecting torque data information of each reduction motor within a data collection period through the reduction motor control network, and analyzing and processing the torque data information of the reduction motor within the data collection period to obtain processed torque data information; Constructing time-series torque data feature change data based on the processed torque data information, introducing a dynamic Bayesian network, and inputting the time-series torque data feature change data into the dynamic Bayesian network to update the observation state; Obtain updated time-series-based torque data feature change data by observing state updates, perform torque state anomaly identification and analysis on the updated time-series-based torque data feature change data, and generate relevant control strategies based on the anomaly identification and analysis results; Constructing a reduction motor control network, integrating the data of the reduction motors in the target area into the reduction motor control network, and initializing the data acquisition parameters of the reduction motor control network, specifically including: Build a reduction motor control network, obtain the maximum information processing capacity of the reduction motor control network within a data acquisition cycle, the data size information of a single reduction motor during data acquisition, and obtain the number of reduction motors in the current target area; Calculate the total estimated data processing volume under the number of reduction motors in the current target area based on the data size information of the single number reduction motors during data collection and the number of reduction motors in the current target area; If the total estimated data processing capacity under the number information of the reduction motors in the current target area is greater than the maximum information processing capacity of the reduction motor control network within one data collection cycle, then reinitialize the number information of the reduction motors when performing data collection within one data collection cycle; Until it is no more than the maximum information processing amount of the reduction motor control network within a data collection cycle, a data collection plan is constructed according to the number information of the reduction motors when performing data collection within a data collection cycle, and data collection planning is performed according to the data collection plan.

2. The method for constructing a reduction motor control network and collecting data according to claim 1, characterized in that: A data collection cycle is set, and torque data information of each reduction motor within a data collection cycle is collected through the reduction motor control network. The torque data information of the reduction motor within a data collection cycle is analyzed and processed to obtain the processed torque data information, specifically: Setting a data collection period, collecting torque data information of each reduction motor within a data collection period through the reduction motor control network, introducing an outlier detection algorithm, and inputting the torque data information of each reduction motor within a data collection period into the outlier detection algorithm for outlier detection; Obtaining outlier data from the torque data information of each reduction motor within a data collection cycle through outlier detection, and deleting the outlier data from the torque data information of each reduction motor within a data collection cycle; After deletion, the sorted torque data information of each reduction motor within a data acquisition cycle is obtained and output as processed torque data information.

3. The method for constructing a reduction motor control network and collecting data according to claim 1, characterized in that: Based on the processed torque data information, torque data feature change data based on time series is constructed, a dynamic Bayesian network is introduced, and the torque data feature change data based on time series is input into the dynamic Bayesian network to update the observation state, specifically: Arrange and sort the processed torque data information according to the order of time points, construct torque data feature change data based on time series, and introduce dynamic Bayesian network; Inputting the time series-based torque data feature change data into the dynamic Bayesian network, and treating the torque data information of each timestamp in the time series-based torque data feature change data as an observation state; Calculate the state transition probability value of each observation state transferring to another observation state, set a state transition probability threshold, and determine whether the state transition probability value of each observation state transferring to another observation state is greater than the state transition probability threshold; The observation state whose state transition probability value is greater than the state transition probability threshold is updated to another observation state, and the observation state whose state transition probability value is not greater than the state transition probability threshold is maintained unchanged.

4. The method for constructing a reduction motor control network and collecting data according to claim 1, characterized in that: By observing the state update, obtaining updated time-series-based torque data feature change data, and performing torque state abnormality identification and analysis on the updated time-series-based torque data feature change data, specifically including: Obtain updated time-series-based torque data feature change data by observing the state update, set a torque data threshold, and determine whether there is torque data greater than the torque data threshold in the updated time-series-based torque data feature change data; When there is torque data greater than a torque data threshold value in the updated time series-based torque data feature change data, the corresponding reduction motor is regarded as an abnormally operating reduction motor and an early warning is issued; When there is no torque data greater than the torque data threshold value in the updated time series-based torque data characteristic change data, the output is a normal operation of the reduction motor.

5. The method for constructing a reduction motor control network and collecting data according to claim 1, characterized in that: Generate relevant control strategies based on the abnormality identification and analysis results, including: Acquire real-time torque data of the abnormal reduction motor in the abnormality identification and analysis results, and acquire estimated maximum torque data of the current abnormal reduction motor, and set a stop working torque threshold according to the estimated maximum torque data of the current abnormal reduction motor; Determining whether the real-time torque data of the abnormal reduction motor in the abnormality identification and analysis result is greater than the stop working torque threshold; When the real-time torque data of the abnormal reduction motor in the abnormal identification and analysis result is greater than the stop-work torque threshold, a stop-work instruction is issued, and the reduction motor is controlled according to the stop-work instruction; When the real-time torque data of the abnormal reduction motor in the abnormality identification and analysis result is not greater than the stop-work torque threshold, the current abnormal reduction motor is continuously monitored and an early warning is issued.

6. A reduction motor control network construction and data acquisition system, characterized in that: It includes a memory and a processor, wherein the memory includes a method program for constructing a reduction motor control network and collecting data. When the method program for constructing a reduction motor control network and collecting data is executed by the processor, the steps of the method for constructing a reduction motor control network and collecting data as described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a method program for constructing a reduction motor control network and collecting data. When the method program for constructing a reduction motor control network and collecting data is executed by a processor, the steps of the method for constructing a reduction motor control network and collecting data as described in any one of claims 1 to 5 are implemented.

Images