Electric chain saw guide plate remote maintenance guidance method and system based on Internet of Things

Abstract

The invention provides an electric chain saw guide plate remote maintenance guidance method and system based on the Internet of Things, and relates to the technical field of data processing, and the method comprises the steps: connecting an Internet of Things database, and extracting target monitoring data; the target monitoring data is used for collecting time alignment, monitoring data analysis is carried out, an instant analysis result and a time sequence analysis result are obtained, the instant analysis result is an abnormal state existing in real time, and the time sequence analysis result is a predicted abnormal state obtained through time sequence analysis prediction; and analyzing the maintenance strategy according to the instant analysis result and the time sequence analysis result, performing instruction segmentation on the maintenance strategy according to the execution priority, generating maintenance guidance information, and performing remote maintenance guidance based on the maintenance guidance information. According to the method, the technical problems that an existing maintenance method cannot monitor and analyze equipment operation data in real time, so that maintenance hysteresis is high, and preventive maintenance is lacked are solved, and the technical effects of improving the maintenance efficiency of the electric chain saw guide plate and the equipment operation stability and safety are achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a remote maintenance guidance method and system for an electric chain saw guide bar based on the Internet of Things. Background Art

[0002] Electric chain saw is a common power tool, widely used in logging, gardening and construction. As one of the key components of electric chain saw, the guide bar is used to support and guide the operation of the chain, and its performance directly affects the working efficiency and service life of the electric chain saw. Since the guide bar of the electric chain saw is subjected to large friction and tension during operation, the guide bar will wear and deform, resulting in a decrease in its performance and even failure, which in turn affects the normal operation of the entire electric chain saw.

[0003] At present, the maintenance of electric chain saw guides mainly relies on regular manual inspections or empirical judgments. Common maintenance methods are visual inspections, manual detection of the degree of wear, repairs after failures, or regular replacements based on the use time of the equipment. On the one hand, relying on regular manual inspections is not only inefficient, but also difficult to detect potential wear or failures in a timely manner, resulting in delayed maintenance work. On the other hand, repairs after failures are often accompanied by unplanned downtime of equipment, which not only affects the progress of operations, but also increases maintenance costs. In addition, due to the lack of accurate data monitoring and analysis of operating parameters, maintenance decisions are overly dependent on manual experience, resulting in the formulation of maintenance strategies that are not accurate and scientific enough. Summary of the invention

[0004] The present application provides a remote maintenance guidance method and system for an electric chain saw guide bar based on the Internet of Things, which solves the technical problem that the existing maintenance methods are unable to monitor and analyze equipment operation data in real time, resulting in strong maintenance lags and lack of preventive maintenance, and achieves the technical effect of improving the maintenance efficiency of the electric chain saw guide bar and the stability and safety of equipment operation.

[0005] In view of the above problems, on the one hand, the present application provides a remote maintenance guidance method for an electric chain saw guide based on the Internet of Things, the method comprising: connecting to an Internet of Things database, extracting target monitoring data, the target monitoring data including at least one or more of temperature, vibration, tension, and wear data; using the target monitoring data to align the acquisition time, perform monitoring data analysis, and obtain instant analysis results and timing analysis results, the instant analysis results are real-time abnormal states, and the timing analysis results are predicted abnormal states obtained by timing analysis prediction; according to the instant analysis results and timing analysis results, the maintenance strategy is parsed, the maintenance strategy is divided into instructions according to the execution priority, maintenance guidance information is generated, and remote maintenance guidance is performed based on the maintenance guidance information.

[0006] On the other hand, the present application also provides an electric chain saw guide plate remote maintenance guidance system based on the Internet of Things, the system comprising: a monitoring data extraction module, the monitoring data extraction module is used to connect to the Internet of Things database and extract target monitoring data, the target monitoring data at least includes one or more of temperature, vibration, tension, and wear data; a monitoring data analysis module, the monitoring data analysis module is used to use the target monitoring data to perform acquisition time alignment, perform monitoring data analysis, and obtain instant analysis results and timing analysis results, the instant analysis results are real-time abnormal states, and the timing analysis results are predicted abnormal states obtained by timing analysis prediction; a maintenance guidance module, the maintenance guidance module is used to parse maintenance strategies according to the instant analysis results and timing analysis results, divide the maintenance strategies into instructions according to execution priority, generate maintenance guidance information, and perform remote maintenance guidance based on the maintenance guidance information.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By connecting to the Internet of Things database, the target monitoring data is extracted, and the foundation for data monitoring is established to provide accurate data support for subsequent analysis and maintenance, ensuring that the real-time status information of the electric chain saw guide can be obtained. The target monitoring data is used to align the acquisition time, perform monitoring data analysis, and obtain instant analysis results and timing analysis results. The instant analysis results help identify abnormal conditions that exist in real time, while the timing analysis results reveal potential abnormal conditions through predictive analysis, which not only improves the accuracy of problem identification, but also enhances the ability of predictive maintenance, thereby preventing potential failures in advance. The maintenance strategy is parsed according to the instant analysis results and timing analysis results, and the maintenance strategy is divided into instructions according to the execution priority, and maintenance guidance information is generated, which realizes the personalization and automation of maintenance activities and ensures the pertinence and effectiveness of maintenance activities. Remote maintenance guidance is carried out based on the maintenance guidance information, and equipment needs are quickly responded to, unplanned downtime is avoided, and maintenance efficiency and equipment operation stability are significantly improved.

[0008] To sum up, this application combines the Internet of Things technology to monitor the equipment status in real time, and through data analysis, provides a more objective basis for maintenance decision-making, can promptly detect and prevent potential failures, and provide remote maintenance guidance, thereby realizing active monitoring and predictive maintenance, reducing the unplanned downtime of equipment, and not only improving the maintenance efficiency of the electric chain saw guide bar, but also improving the reliability and service life of the equipment.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a flow chart of a remote maintenance guidance method for an electric chain saw guide plate based on the Internet of Things provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for generating maintenance guidance information in a remote maintenance guidance method for an electric chain saw guide plate based on the Internet of Things provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electric chain saw guide plate remote maintenance guidance system based on the Internet of Things provided in an embodiment of the present application.

[0011] Description of the accompanying drawings: monitoring data extraction module 10, monitoring data analysis module 20, maintenance guidance module 30. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a remote maintenance guidance method and system for an electric chain saw guide bar based on the Internet of Things, thereby solving the technical problems that existing maintenance methods are unable to monitor and analyze equipment operation data in real time, resulting in strong maintenance lags and a lack of preventive maintenance. This achieves the technical effect of improving the maintenance efficiency of the electric chain saw guide bar and the stability and safety of equipment operation.

[0013] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a remote maintenance guidance method for an electric chain saw guide plate based on the Internet of Things, the method comprising: Connect to the Internet of Things database and extract target monitoring data, where the target monitoring data includes at least one or more of temperature, vibration, tension, and wear data.

[0014] Specifically, the IoT database is a system that collects, stores and manages a large amount of data generated by IoT devices. It can efficiently process and store real-time data from various sensors, providing a data basis for data analysis and application. The target monitoring data specifically refers to data closely related to the operating status of the electric chain saw, including but not limited to temperature, vibration, tension and wear. These data directly reflect the working status and health of the electric chain saw guide.

[0015] The IoT database collects key data about the operating status of the equipment in real time through a series of IoT devices installed on the electric chain saw, such as temperature sensors, vibration sensors, tension sensors, and wear monitoring sensors. Taking temperature monitoring as an example, the temperature sensor installed on the electric chain saw can monitor its operating temperature in real time, and the data is transmitted to the IoT database via a wireless network (such as Wi-Fi or 4G / 5G). Similarly, the vibration sensor can monitor the vibration of the electric chain saw during operation; the tension sensor is responsible for monitoring the tension state of the chain; the wear monitoring sensor assesses the degree of wear by detecting the surface condition, such as through capacitance changes or optical measurements.

[0016] Establish a network connection with the Internet of Things database, extract the required monitoring data from the database according to the preset parameters or query conditions, grasp the operating status of the electric chain saw in real time, and provide reliable data support for subsequent analysis and maintenance. Among them, temperature data can determine whether the equipment is overheated, vibration data can detect whether the equipment has signs of imbalance or damage; tension and wear data can evaluate the state of the chain and the degree of wear of the guide plate.

[0017] The target monitoring data is used to align the acquisition time and perform monitoring data analysis to obtain instant analysis results and time series analysis results. The instant analysis results are real-time abnormal states, and the time series analysis results are predicted abnormal states obtained by performing time series analysis prediction.

[0018] Specifically, during the operation of the electric chain saw, multiple sensors (temperature, vibration, tension, wear) may collect data at different frequencies, so the extracted monitoring data needs to be aligned in time. Alignment of acquisition time ensures the consistency of the data at the time point and provides an accurate time reference for subsequent analysis. Acquisition time alignment is usually completed through data preprocessing techniques, such as using timestamps to match and align data points. This process can be done with the help of the time series processing functions provided in Python's Pandas library, or using stream processing frameworks such as Apache Flink to process and align data in real time.

[0019] The aligned data is analyzed in real-time and in time series. The real-time analysis is based on the real-time data stream. The real-time stream processing framework is combined with threshold detection and anomaly detection algorithms to identify the current abnormal state, such as overheating, abnormal vibration, etc., to obtain the real-time analysis results. For example, when the temperature of the electric chain saw exceeds the preset threshold, the real-time analysis will trigger an alarm to prompt the user to take cooling measures. Time series analysis uses historical data to predict future abnormal states. By analyzing past temperature, vibration and other data, certain potential trends or patterns can be discovered. For example, if the temperature gradually rises after a certain period of time, it can be predicted that the equipment will be at risk of overheating in the future.

[0020] Through data alignment and monitoring data analysis, it is possible to quickly determine whether the current status of the equipment is normal, and proactively predict possible future failure risks, achieve immediate fault handling and preventive maintenance, thereby extending equipment life and reducing downtime.

[0021] The maintenance strategy is parsed according to the instant analysis result and the timing analysis result, the maintenance strategy is segmented into instructions according to the execution priority, maintenance guidance information is generated, and remote maintenance guidance is performed based on the maintenance guidance information.

[0022] Specifically, a series of specific maintenance strategies are derived based on the current and future equipment states of the chainsaw chain guide described by the instant analysis results and the timing analysis results. After the maintenance strategy is generated, the execution priority is assigned according to the urgency of the fault and the impact on the normal operation of the equipment, and the most important maintenance strategies are prioritized to ensure that the most urgent and important problems are resolved first. For example, excessive temperature may immediately cause equipment shutdown, so this problem has a higher priority than minor wear. Then, the specific tasks in the maintenance strategy are broken down into executable instructions, each of which clearly defines the specific maintenance steps. Maintenance guidance information is generated based on the segmented instructions. The maintenance guidance information is used to guide maintenance personnel or automated systems to perform maintenance operations. Based on the Internet of Things technology, maintenance information or instructions are transmitted remotely through the network to directly guide equipment operators to perform maintenance work, or to remotely trigger automated maintenance tasks.

[0023] For example, the analysis found that the chain tension of the electric chain saw was abnormal (instant analysis result) and the guide bar was expected to reach the wear threshold in one week (sequential analysis result). According to the urgency and impact, the chain tension adjustment strategy was given the highest priority, and the chain tension adjustment strategy was analyzed first, followed by the preventive maintenance strategy for guide bar wear. The chain tension adjustment strategy was subdivided into steps such as "check the chain tensioner" and "adjust the tension to the recommended value", and a detailed operation guide was generated, including instructions for the use of the adjustment tool and safe operation specifications. For the preventive maintenance of guide bar wear, instructions such as "check the guide bar wear" and "replace the guide bar if necessary" were generated. Through remote connection, guidance information for adjusting the chain tension instantly is sent to the on-site operator, with a schematic diagram and operation steps of the adjustment tool, or the device self-check or adjustment operation is remotely triggered through the Internet of Things system. At the same time, based on the guide bar wear prediction, a maintenance reminder is sent to the maintenance team one week in advance to ensure the smooth progress of maintenance work.

[0024] Through the above steps, maintenance strategies can be intelligently generated according to the immediate and future equipment status, and hierarchical instructions and remote guidance can be used to ensure that the maintenance of the electric chain saw guide bar is completed in a timely and effective manner, thereby reducing downtime and improving operating efficiency.

[0025] Furthermore, the embodiment of the present application is connected to the Internet of Things database, which includes: Construct a multi-level sensor module, including a first-level temperature sensor, a vibration sensor module, a second-level tension sensor module, and a third-level wear sensor module, wherein each level of the sensor module has an adaptive activation function. When the adaptive activation function is satisfied, the higher-level sensor module is awakened to achieve step-by-step triggering; establish a data acquisition channel for the multi-level sensor module, send the sensor acquisition data through the data acquisition channel, and generate an acquisition timestamp at the same time to obtain monitoring data at each level; establish a mapping association between the monitoring data at each level and the multi-level sensor module, and construct a multi-level Internet of Things database.

[0026] Specifically, the multi-level sensor module is a system composed of different sensors, which are divided into multiple levels according to the function or importance of the sensor, and each level of sensor monitors different types of data. In the embodiment of the present application, the multi-level sensor module includes a first-level temperature sensor, a vibration sensor module, a second-level tension sensor module, and a third-level wear sensor module. An adaptive activation function is set between each level of sensor modules, which automatically determines whether a higher level of monitoring needs to be enabled.

[0027] Among them, the first-level temperature sensing and vibration sensing module is composed of several temperature sensors and vibration sensors, which are used to monitor the basic operating status of the electric chain saw, including temperature and vibration, and identify overheating, friction, and abnormal mechanical movement problems. When an abnormality is found in the first-level monitoring, such as when the temperature or vibration data reaches the abnormal threshold, the second-level tension sensing module is automatically activated through the adaptive activation function. The second-level tension sensing module is composed of several tension sensors, which are used to monitor the tension state of the chain and identify the problem of the chain being too loose or too tight. When the second-level tension sensing module detects abnormal chain tension or the data of the first-level sensor module is continuously abnormal, the adaptive activation function activates the third-level wear sensing module. The third-level wear sensing module is composed of several wear sensors, which are used to monitor the wear of the guide plate and chain and provide more detailed fault information. This step-by-step activation design helps save system resources. The high-level sensor module will only be activated when the low-level sensor detects an abnormality. If everything is normal, only the first-level sensor needs to be run to reduce energy consumption and data processing burden.

[0028] Using IoT communication protocols such as MQTT or AMQP, a data collection channel for multi-level sensor modules is established. Sensor modules at all levels send their collected data through the data collection channel and generate a timestamp to record the time of data collection. The role of the timestamp is to ensure that all data can be arranged in chronological order, ensuring that even if the data comes from sensors at different levels, it can be analyzed on the same time dimension.

[0029] In order to manage and analyze these data, it is necessary to map and associate the monitoring data at each level with the corresponding sensor modules and establish the corresponding relationship between data and sensor modules. Through this mapping, we can clearly understand the source of the data, that is, which sensor module each piece of data is generated by, so as to improve the accuracy of data analysis.

[0030] Through the monitoring data generated by the multi-level sensor modules and the corresponding relationship between the data and the sensor modules, a multi-level IoT database corresponding to the multi-level architecture of the sensor is established to store and retrieve different types of data. The IoT database can be built using NoSQL databases such as MongoDB, Cassandra, or Hadoop distributed file systems to support the storage and fast access of large-scale data.

[0031] Through this structured, layered sensor and database design, it is possible to respond to the operating status of the electric chain saw, gradually trigger sensor monitoring, capture anomalies in a timely manner, and provide real-time, accurate equipment monitoring and remote maintenance support.

[0032] Furthermore, the method described in the embodiment of the present application also includes: Taking temperature, vibration, tension and wear as variables respectively, fitting the abnormal states of the variables is performed through historical abnormal data to determine the abnormal state threshold of each variable, wherein the abnormal state threshold is a relationship coefficient including the load amount; extracting top abnormal events according to the historical abnormal data, performing correlation evaluation on the temperature, vibration, tension and wear respectively, and determining the associated influence relationship between the top abnormal events and the temperature, vibration, tension and wear; configuring activation selection conditions according to the abnormal state threshold and the associated influence relationship, and establishing the adaptive activation function, wherein the activation selection conditions are independent conditions of the abnormal state threshold or union conditions of the abnormal state threshold and the associated influence relationship.

[0033] Specifically, we use temperature, vibration, tension and wear as variables to analyze the historical abnormal data recorded in the past. Through statistical and fitting methods, we find out the typical performance of each variable when it is in an abnormal state, and determine the abnormal state threshold of each variable according to the load. For example, the normal upper limit of the temperature of an electric chain saw under light load may be 80°C, but it may be allowed to reach 90°C under heavy load. This method of adjusting the threshold according to the load ensures the accuracy of abnormal detection.

[0034] The variable abnormal state fitting can be completed by regression analysis, and the appropriate regression model can be selected, including linear regression, polynomial regression, logistic regression, etc. When establishing the regression model, special consideration is given to the impact of changes in load on abnormal states, and load is introduced as an independent variable in the model. The regression model is trained using historical data, and the accuracy and generalization ability of the model are evaluated through methods such as cross-validation.

[0035] Next, extract the top abnormal events from the historical data, that is, those events in the historical data that cause the equipment to stop running or seriously affect the performance, such as guide plate overheating, severe vibration, chain breakage, etc., extract the temperature, vibration, tension, and wear values ​​when the top events occur, and record the variable status at that time. Use correlation analysis methods, such as Pearson correlation coefficient or multivariate regression, to evaluate the correlation and influence relationship between these top events and temperature, vibration, tension, and wear. These correlation relationships help to understand the interaction between multiple variables. Through correlation analysis, calculate the correlation coefficient between each pair of variables, such as temperature and vibration, vibration and tension, to determine the interaction strength of these variables in the top abnormal events. For example, the analysis found that when the temperature rises in the top abnormal event, the vibration intensifies, indicating that there is a strong correlation between temperature and vibration; analyze the chain tension and vibration data, and find that the vibration abnormality is related to the chain tension deviation; by analyzing the relationship between the chain tension and wear data, it is found that when the tension is too loose or too tight, the wear rate of the guide plate is significantly accelerated, indicating that there is a correlation between the two.

[0036] According to the abnormal state thresholds and associated impact relationships obtained through analysis, activation selection conditions are configured. These activation selection conditions can be thresholds of a single variable, such as activating a high-level sensor only when the temperature exceeds the threshold, or they can be joint conditions of multiple variables, such as activating the next layer of sensors only when both the temperature and vibration exceed the threshold. Based on these activation selection conditions, an adaptive activation function is established through a programming language. This function determines whether to activate a higher-level monitoring system by judging the current device status in real time.

[0037] For example, taking the secondary tension sensor module as an example, when the activation selection condition is a threshold of a single variable, that is, the secondary tension sensor module is activated only when the temperature exceeds the threshold or the vibration exceeds the threshold, the adaptive activation function can be set to: , where T and V represent the real-time data of temperature, vibration, tension and wear, respectively, and T´ and V´ represent the abnormal thresholds of temperature and vibration, respectively.

[0038] When the activation selection condition is the union condition of the associated influence relationship, that is, the secondary tension sensing module will be activated only when the temperature and vibration exceed the threshold at the same time, the adaptive activation function can be set to: , where T and V represent the real-time data of temperature, vibration, tension and wear, respectively, and T´ and V´ represent the abnormal thresholds of temperature and vibration, respectively.

[0039] The adaptive activation function can also be constructed by combining independent conditions and union conditions. When any variable of temperature or vibration exceeds the threshold or when both temperature and vibration exceed the threshold, the secondary tension sensor module is activated. At this time, the adaptive activation function can be set to: , where T and V represent the real-time data of temperature, vibration, tension and wear, respectively, and T´ and V´ represent the abnormal thresholds of temperature and vibration, respectively.

[0040] Through detailed analysis of historical abnormal data, we can configure activation selection conditions and establish adaptive activation functions based on abnormal status and related impacts, ensuring that the adaptive activation function can automatically activate the higher-level sensor module at the appropriate time to achieve intelligent and accurate monitoring of data collection.

[0041] Furthermore, the embodiment of the present application utilizes the target monitoring data to perform acquisition time alignment, performs monitoring data analysis, and obtains instant analysis results and time series analysis results, including: Generate the collection time according to the activation time of the sensor module, and perform time alignment with the earliest collection time in the target monitoring data as the starting point to obtain a timing matrix of the target monitoring data, wherein the horizontal elements of the timing matrix are data of different monitoring variables at the same collection time, and the vertical elements are data of different collection times for the same monitoring variable; perform horizontal data analysis and evaluation based on the timing matrix to obtain the instant analysis result; perform vertical data analysis and prediction based on the timing matrix to obtain the timing analysis result.

[0042] Specifically, a collection timestamp list is generated based on the activation time of different sensor modules, the earliest collection time is selected as the benchmark, and then the subsequent sensor data are arranged according to this benchmark time, and the data collected by different sensors at different time points are placed in the same time frame to construct a timing matrix. The timing matrix is ​​a two-dimensional data structure used to store monitoring data from different sensors at different time points. The horizontal axis represents the values ​​collected by different sensors at the same time, and the vertical axis represents the data collected by the same sensor at different times. For example, at a certain time point, the temperature is 70°C, the vibration is 3g, the tension is 12N, and the wear is 0.5mm. These data will be placed in the same row. The collected values ​​of temperature at different times are 70°C, 72°C, and 75°C, which are arranged in the same column.

[0043] Using this time series matrix, we first conduct horizontal data analysis, that is, analyze the data of different sensors at the same time to determine the current operating status of the equipment. For example, if a sudden increase in temperature and abnormal increase in vibration are detected at the same time, it may be determined that the current equipment is faulty. This analysis will generate instant analysis results, indicating whether there is a problem that needs to be solved immediately.

[0044] Then, longitudinal data analysis is performed, that is, analyzing the trend of changes in the same variable over time. For example, by analyzing the trend of temperature changes in the past few hours, future temperature changes can be predicted. The results of longitudinal analysis can reveal potential problems, such as whether the temperature rises faster than normal and may exceed the safety threshold at a certain point in the future. The time series analysis results generated by this analysis are used to predict the status of future equipment, thereby achieving preventive maintenance.

[0045] This analysis method based on the timing matrix can more comprehensively grasp the status of the equipment. It can not only detect problems at the current moment, but also provide early warnings to help formulate long-term maintenance strategies.

[0046] Furthermore, the embodiment of the present application performs horizontal data analysis and evaluation according to the time series matrix to obtain the instant analysis result, including: According to the correlation and influence relationship between the top abnormal event and the temperature, vibration, tension and wear, a discriminator is generated based on historical abnormal data training, and the temperature, vibration, tension and wear monitoring data in the lateral data are used as input variables of the discriminator. The top abnormal event is discriminated by the discriminator, and the identified abnormal event is output as the instant analysis result. At the same time, the instant analysis result is compared with the abnormal warning threshold. When the abnormal warning threshold is reached, maintenance warning information is sent, and the maintenance warning information contains the abnormal event.

[0047] Specifically, a discriminator is trained based on historical abnormal data. The trained discriminator is a machine learning model, such as logistic regression, support vector machine or neural network. The discriminator learns the correlation and influence relationship between top abnormal events and temperature, vibration, tension and wear monitoring data to determine whether top abnormal events occur.

[0048] After the training is completed, the current monitoring data of temperature, vibration, tension and wear in the lateral data of the time series matrix are input into the discriminator as input variables. For each time point, the discriminator will receive a set of temperature, vibration, tension and wear data points as input. The discriminator will analyze these input data to determine whether the current equipment status meets the characteristics of the top abnormal events that have occurred in history, and output an instant analysis result to indicate whether there is an abnormality in the current status.

[0049] Then, the instant analysis results are compared with the pre-set abnormal warning threshold. This abnormal warning threshold is a preset standard used to judge the severity of the abnormality. If the abnormal event output by the discriminator reaches or exceeds the abnormal warning threshold, a maintenance warning message is immediately issued. The warning message often contains detailed information about the abnormal event, such as the abnormality type, occurrence time, etc.

[0050] By training the discriminator, the current health status of the equipment can be analyzed through real-time monitoring data, and anomalies can be quickly and accurately identified. At the same time, the abnormal warning threshold mechanism ensures that warnings are issued only when there is a real risk of equipment, avoiding unnecessary maintenance interference and improving the efficiency and safety of equipment management.

[0051] Furthermore, the embodiment of the present application performs longitudinal data analysis and prediction according to the time series matrix to obtain the time series analysis result, including: According to the changing trend of the variable fitted by the longitudinal data, the changing trend coefficient is obtained; based on the changing trend coefficient, the state change is predicted according to the time series relationship to obtain the predicted time series variable; the predicted time series variable is used as the input variable to perform top abnormal event discrimination through the discriminator, and the predicted abnormal event is output as the time series analysis result, and the time series analysis result includes the predicted abnormal state and its predicted time.

[0052] Specifically, according to the longitudinal data in the time series matrix, the changes of temperature, vibration, tension, and wear at different time points are analyzed respectively. By fitting these data, the change trend coefficient of each variable is determined. This coefficient is a mathematical quantity that reflects the trend and rate of change of the monitored variable over time. For example, by fitting the temperature data, it is found that the temperature is rising at a rate of 2°C per hour. This rate is the change trend coefficient. The change trend coefficient can be obtained by fitting through time series analysis, regression analysis, etc. For example, linear regression is used to fit the change trend of temperature over time. Taking time as the independent variable and temperature as the dependent variable, a linear regression model is established to observe the rate of temperature rise or fall and predict whether overheating will occur in the future.

[0053] Using the calculated change trend coefficient, the values ​​of the monitoring variables (temperature, vibration, tension, wear) at future time points are predicted to obtain the predicted time series variables. The predicted time series variables are input into the previously trained discriminator to determine whether the top abnormal event may occur at the predicted time point. If the prediction result indicates that an abnormality may occur, the predicted abnormal state and its predicted occurrence time are recorded as the output of the time series analysis result.

[0054] For example, the temperature monitoring data of the electric chain saw is longitudinally analyzed, and the ARIMA model is used to fit the temperature change trend and calculate the change trend coefficient. Assume that the model predicts that the temperature will rise from 60°C to 65°C in the next 2 hours, close to the abnormal warning threshold of 63°C. The predicted temperature value (65°C) is input into the discriminator for abnormal event prediction. If the result output by the discriminator indicates that the top abnormal event (such as equipment overheating) may occur in 2 hours, the time series analysis result is generated: "It is predicted that the equipment may have an overheating abnormality in 2 hours."

[0055] Through longitudinal data analysis and prediction, it is possible to provide early warning of impending failures, greatly reducing sudden failures and downtime of equipment.

[0056] Further, such as Figure 2 As shown, the embodiment of the present application parses the maintenance strategy according to the instant analysis result and the timing analysis result, divides the maintenance strategy into instructions according to the execution priority, and generates maintenance guidance information, including: According to the instant analysis results and the timing analysis results, the abnormal events and their abnormal state times are obtained; a mapping relationship between the abnormal events and maintenance means is established, including the compensation efficiency of the maintenance means, the maintenance compensation time limit is obtained according to the abnormal state time, and the maintenance strategy is determined using the maintenance compensation time limit and the compensation efficiency; a synchronization analysis is performed on the maintenance strategy, and when the synchronization condition is met, the maintenance guidance information is generated according to the maintenance strategy; when the maintenance strategy does not meet the synchronization condition, the maintenance strategy is prioritized to determine the strategy priority, and the strategy priority represents the risk level of the abnormal event; the maintenance strategy is sorted according to the priority, instructions are segmented according to the sorting result, and the maintenance guidance information is generated.

[0057] Specifically, based on the results of the instant analysis and the timing analysis, abnormal events are identified and the exact time when these abnormal events may occur is determined. The maintenance plan entered in advance by the operator is extracted to establish a mapping relationship between abnormal events and maintenance methods. This mapping relationship indicates the maintenance methods that can be used for specific abnormal events (such as excessive temperature and excessive vibration). For example, excessive temperature may require equipment cooling or replacement of coolant, and excessive vibration may require equipment calibration. For each maintenance method, its compensation efficiency is evaluated. Compensation efficiency refers to the efficiency of the maintenance method in effectively repairing or improving the abnormal state within a certain period of time. This efficiency can be determined based on historical data or equipment specifications. For example, the efficiency of lubricating oil in reducing temperature within 10 minutes may be 60%.

[0058] According to the compensation efficiency of the maintenance means and the abnormal state time, the maintenance compensation time limit for each abnormal state is determined. This time limit is the acceptable maintenance time window for the equipment after the abnormal state occurs to avoid further damage or failure. For example, if the tension is predicted to exceed the standard after 2 hours, then the maintenance compensation time limit is within 2 hours. The maintenance strategy is generated by comprehensively determining the compensation efficiency and maintenance compensation time limit. There can be one or more maintenance strategies, and each maintenance strategy corresponds to an abnormal state.

[0059] Then, the maintenance strategies are analyzed for synchronization to determine whether there is interference and sequence between multiple maintenance strategies and whether they can be executed simultaneously. If the synchronization condition is met, that is, multiple maintenance strategies can be executed simultaneously, maintenance guidance information is generated according to the synchronized maintenance strategies to remind the operator or the automatic operating system to execute these maintenance strategies step by step.

[0060] If the synchronization condition is not met, priority analysis is required. By analyzing the risk level of each abnormal event, determine which tasks are executed first. For example, excessive temperature may be more urgent than minor wear, so the temperature problem will be handled first. Priority analysis is used to determine the strategy priority, sort the maintenance strategies according to the priority, and divide the instructions according to the sorting results to generate maintenance guidance information.

[0061] For example, the instant analysis results indicate temperature abnormalities, and the timing analysis results predict future vibration abnormalities. The maintenance means and maintenance compensation time limit are determined based on the analysis results. If the current temperature is abnormal, it is necessary to cool down immediately; if vibration abnormalities are predicted, it is necessary to check and tighten the connection parts in advance. The acceptable maintenance time window for electric chain saws is 1 hour to avoid production stoppages. The corresponding maintenance strategies are determined to be "start the cooling system immediately" and "check and tighten the equipment after 1.5 hours." Since cooling and inspection cannot be synchronized, the priority needs to be analyzed. The temperature abnormality is more urgent, so cooling is given priority; the vibration abnormality has a lower risk and is checked later. Finally, the maintenance guidance information of "start the cooling system immediately" and "check the equipment connection parts after 1.5 hours" is generated.

[0062] Through the above steps, maintenance strategies can be formulated and implemented efficiently and orderly based on real-time monitoring and predictive analysis to ensure the normal operation and production efficiency of equipment and reduce the risk of sudden failures.

[0063] Furthermore, the embodiment of the present application sorts the maintenance strategies according to the priorities, and performs instruction segmentation according to the sorting results, and also includes: Determine whether the maintenance strategy has a shutdown strategy. If so, parse the compensation strategy of the corresponding abnormal event based on the timing relationship of the corresponding abnormal event; use the compensation strategy to match maintenance strategies of other priorities. When the match is successful, configure the matching maintenance strategy with the highest priority. At the same time, use the maximum amount of the maintenance strategy and the compensation strategy as the execution strategy to reset the priority.

[0064] Specifically, before sorting maintenance strategies and dividing instructions, it is necessary to first determine whether there is a shutdown strategy. Since shutdown means a complete interruption of production, it usually brings huge production losses, delay costs, and additional restart time costs. Therefore, shutdown is usually the last choice with the lowest priority, and it is only chosen when serious failures cannot be avoided through other maintenance means.

[0065] Analyze whether there is a strategy that requires equipment shutdown in the maintenance strategy. If there is a shutdown strategy, further analyze the compensation strategy of the strategy. Compensation strategy refers to measures taken to reduce downtime or reduce the impact of abnormal events. For example, the equipment needs to be shut down within 2 hours to repair tension, but the equipment operation time can be extended through short-term cooling. Cooling is a compensation strategy.

[0066] Match the compensation strategy with maintenance strategies of other priorities to find a matching maintenance strategy that can be coordinated or executed synchronously. If the match is successful, configure the matching maintenance strategy as the highest priority to ensure that the equipment abnormality is handled without downtime. At the same time, the largest amount of the maintenance strategy and the compensation strategy is used as the execution strategy, that is, the strategy that can solve the problem to the greatest extent is selected, and the priority of the maintenance strategy is reordered to ensure that the compensation strategy can be executed in a timely manner.

[0067] For example, there is a shutdown strategy of "wear exceeds limit, replace guide plate" in the maintenance strategy. Analysis finds that "lubrication" can reduce wear, so "lubrication" is used as a compensation strategy and matched with other priority maintenance strategies. It is found that "lubrication" and "tension adjustment" can be performed at the same time, so "lubrication" and "tension adjustment" are used as matching maintenance strategies, set to the highest priority, and set the lubrication amount to the maximum.

[0068] If the match is not successful, that is, there is no maintenance strategy that can be executed simultaneously with the current compensation strategy, a new compensation strategy needs to be added. The introduction of compensation strategy is to delay the occurrence of problems or reduce the impact of problems. For example, if there is a risk of excessive tension in the equipment, but it cannot be stopped immediately for repair, the process of equipment damage can be delayed by temporarily reducing the load, adjusting the operating speed, or adjusting the tension parameters in the short term.

[0069] After adding the compensation strategy, you need to re-evaluate the priorities of all strategies and reset the priorities of the maintenance strategies to ensure that the compensation strategies can be executed in a timely manner. Based on the reset priorities, evaluate whether the current maintenance strategy meets the maintenance requirements of all abnormal events, including whether each abnormal event has corresponding handling measures, whether the handling time is reasonable, and whether it has minimal impact on production. If the evaluation results show that a strategy fails to meet maintenance requirements or production goals, it is necessary to add additional maintenance steps, adjust the maintenance schedule, or optimize the compensation strategy.

[0070] Through compensation strategies and priority resetting, it is possible to ensure that equipment can operate normally in the short term, minimize downtime, and ensure production continuity.

[0071] In summary, the electric chain saw guide plate remote maintenance guidance method based on the Internet of Things provided in the embodiment of the present application has the following technical effects: Construct a multi-level sensor module and an Internet of Things database that are triggered step by step to monitor the operating status of the equipment in real time and accurately while reducing resource consumption; connect to the Internet of Things database, extract target monitoring data, establish a basis for data monitoring, provide accurate data support for subsequent analysis and maintenance, and ensure that the real-time status information of the electric chain saw guide can be obtained. Use the target monitoring data to align the acquisition time, obtain the timing matrix for monitoring data analysis, train the discriminator through historical data, obtain instant analysis results and timing analysis results, the instant analysis results help identify the abnormal state that exists in real time, and the timing analysis results reveal the potential abnormal state through predictive analysis, which not only improves the accuracy of problem identification, but also enhances the ability of predictive maintenance, thereby preventing potential failures in advance. According to the instant analysis results and timing analysis results, the maintenance strategy is parsed, the maintenance strategy is divided into instructions according to the execution priority, and maintenance guidance information is generated, which realizes the personalization and automation of maintenance activities and ensures the pertinence and effectiveness of maintenance activities. Based on the maintenance guidance information, remote maintenance guidance is carried out to quickly respond to equipment needs, avoid unplanned downtime, and significantly improve maintenance efficiency and equipment operation stability.

[0072] Overall, the embodiment of the present application combines the Internet of Things technology to monitor the equipment status in real time, and through data analysis, provides a more objective basis for maintenance decision-making, can promptly detect and prevent potential failures, and provide remote maintenance guidance, thereby realizing active monitoring and predictive maintenance, reducing the unplanned downtime of equipment, and not only improving the maintenance efficiency of the electric chain saw guide bar, but also improving the reliability and service life of the equipment.

[0073] Embodiment 2, as Figure 3 As shown, the embodiment of the present application provides a remote maintenance guidance system for an electric chain saw guide plate based on the Internet of Things, and the system includes: The monitoring data extraction module 10 is used to connect to the Internet of Things database to extract target monitoring data, and the target monitoring data includes at least one or more of temperature, vibration, tension, and wear data. The monitoring data analysis module 20 is used to use the target monitoring data to align the acquisition time, perform monitoring data analysis, and obtain instant analysis results and time series analysis results. The instant analysis results are real-time abnormal states, and the time series analysis results are predicted abnormal states obtained by performing time series analysis prediction.

[0074] The maintenance guidance module 30 is used to analyze the maintenance strategy according to the instant analysis results and the timing analysis results, divide the maintenance strategy into instructions according to the execution priority, generate maintenance guidance information, and perform remote maintenance guidance based on the maintenance guidance information.

[0075] Furthermore, the system described in the embodiment of the present application is also used to perform the following steps: Construct a multi-level sensor module, including a first-level temperature sensor, a vibration sensor module, a second-level tension sensor module, and a third-level wear sensor module, wherein each level of the sensor module has an adaptive activation function. When the adaptive activation function is satisfied, the higher-level sensor module is awakened to achieve step-by-step triggering; establish a data acquisition channel for the multi-level sensor module, send the sensor acquisition data through the data acquisition channel, and generate an acquisition timestamp at the same time to obtain monitoring data at each level; establish a mapping association between the monitoring data at each level and the multi-level sensor module, and construct a multi-level Internet of Things database.

[0076] Furthermore, the system described in the embodiment of the present application is also used to perform the following steps: Taking temperature, vibration, tension and wear as variables respectively, fitting the abnormal states of the variables is performed through historical abnormal data to determine the abnormal state threshold of each variable, wherein the abnormal state threshold is a relationship coefficient including the load amount; extracting top abnormal events according to the historical abnormal data, performing correlation evaluation on the temperature, vibration, tension and wear respectively, and determining the associated influence relationship between the top abnormal events and the temperature, vibration, tension and wear; configuring activation selection conditions according to the abnormal state threshold and the associated influence relationship, and establishing the adaptive activation function, wherein the activation selection conditions are independent conditions of the abnormal state threshold or union conditions of the abnormal state threshold and the associated influence relationship.

[0077] Furthermore, the monitoring data analysis module 20 of the embodiment of the present application is also used to perform the following steps: Generate the collection time according to the activation time of the sensor module, and perform time alignment with the earliest collection time in the target monitoring data as the starting point to obtain a timing matrix of the target monitoring data, wherein the horizontal elements of the timing matrix are data of different monitoring variables at the same collection time, and the vertical elements are data of different collection times for the same monitoring variable; perform horizontal data analysis and evaluation based on the timing matrix to obtain the instant analysis result; perform vertical data analysis and prediction based on the timing matrix to obtain the timing analysis result.

[0078] Furthermore, the monitoring data analysis module 20 of the embodiment of the present application is also used to perform the following steps: According to the correlation and influence relationship between the top abnormal event and the temperature, vibration, tension and wear, a discriminator is generated based on historical abnormal data training, and the temperature, vibration, tension and wear monitoring data in the lateral data are used as input variables of the discriminator. The top abnormal event is discriminated by the discriminator, and the identified abnormal event is output as the instant analysis result. At the same time, the instant analysis result is compared with the abnormal warning threshold. When the abnormal warning threshold is reached, maintenance warning information is sent, and the maintenance warning information contains the abnormal event.

[0079] Furthermore, the monitoring data analysis module 20 of the embodiment of the present application is also used to perform the following steps: According to the changing trend of the variable fitted by the longitudinal data, the changing trend coefficient is obtained; based on the changing trend coefficient, the state change is predicted according to the time series relationship to obtain the predicted time series variable; the predicted time series variable is used as the input variable to perform top abnormal event discrimination through the discriminator, and the predicted abnormal event is output as the time series analysis result, and the time series analysis result includes the predicted abnormal state and its predicted time.

[0080] Furthermore, the maintenance guidance module 30 of the embodiment of the present application is also used to perform the following steps: According to the instant analysis results and the timing analysis results, the abnormal events and their abnormal state times are obtained; a mapping relationship between the abnormal events and maintenance means is established, including the compensation efficiency of the maintenance means, the maintenance compensation time limit is obtained according to the abnormal state time, and the maintenance strategy is determined using the maintenance compensation time limit and the compensation efficiency; a synchronization analysis is performed on the maintenance strategy, and when the synchronization condition is met, the maintenance guidance information is generated according to the maintenance strategy; when the maintenance strategy does not meet the synchronization condition, the maintenance strategy is prioritized to determine the strategy priority, and the strategy priority represents the risk level of the abnormal event; the maintenance strategy is sorted according to the priority, instructions are segmented according to the sorting result, and the maintenance guidance information is generated.

[0081] Furthermore, the maintenance guidance module 30 of the embodiment of the present application is also used to perform the following steps: Determine whether the maintenance strategy has a shutdown strategy. If so, parse the compensation strategy of the corresponding abnormal event based on the timing relationship of the corresponding abnormal event; use the compensation strategy to match maintenance strategies of other priorities. When the match is successful, configure the matching maintenance strategy with the highest priority. At the same time, use the maximum amount of the maintenance strategy and the compensation strategy as the execution strategy to reset the priority.

[0082] Through the above-mentioned detailed description of the remote maintenance guidance method for the electric chain saw guide plate based on the Internet of Things in this specification, those skilled in the art can clearly understand the remote maintenance guidance system for the electric chain saw guide plate based on the Internet of Things in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant parts can be referred to the description of the method part.

[0083] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A remote maintenance guidance method for an electric chain saw guide plate based on the Internet of Things, characterized in that: include: Connecting to an Internet of Things database to extract target monitoring data, wherein the target monitoring data includes at least one or more of temperature, vibration, tension, and wear data; Using the target monitoring data to perform acquisition time alignment, perform monitoring data analysis, and obtain instant analysis results and time series analysis results, wherein the instant analysis results are abnormal states existing in real time, and the time series analysis results are predicted abnormal states obtained by performing time series analysis prediction; The maintenance strategy is parsed according to the instant analysis result and the timing analysis result, the maintenance strategy is segmented into instructions according to the execution priority, maintenance guidance information is generated, and remote maintenance guidance is performed based on the maintenance guidance information.

2. The method for remote maintenance guidance of an electric chain saw guide plate based on the Internet of Things as claimed in claim 1, characterized in that: The connection to the Internet of Things database previously includes: Construct a multi-level sensor module, including a first-level temperature sensor and a vibration sensor module, a second-level tension sensor module, and a third-level wear sensor module, wherein each level of the sensor module has an adaptive activation function, and when the adaptive activation function is satisfied, the higher-level sensor module is awakened to achieve step-by-step triggering; Establish a data acquisition channel for multi-level sensor modules, send sensor acquisition data through the data acquisition channel and generate acquisition timestamps at the same time, and obtain monitoring data at each level; Establish mapping associations between monitoring data at each level and multi-level sensor modules, and build a multi-level Internet of Things database.

3. The remote maintenance guidance method for electric chain saw guide plate based on Internet of Things as claimed in claim 2, characterized in that: include: Taking temperature, vibration, tension and wear as variables respectively, fitting the abnormal state of the variables is performed through historical abnormal data to determine the abnormal state threshold of each variable, wherein the abnormal state threshold is a relationship coefficient including the load amount; Extracting top abnormal events according to the historical abnormal data, respectively evaluating the correlation of the temperature, vibration, tension, and wear, and determining the correlation and influence relationship between the top abnormal events and the temperature, vibration, tension, and wear; An activation selection condition is configured according to the abnormal state threshold and the associated influence relationship to establish the adaptive activation function, wherein the activation selection condition is an independent condition of the abnormal state threshold or a union condition of the abnormal state threshold and the associated influence relationship.

4. The method for remote maintenance guidance of an electric chain saw guide plate based on the Internet of Things as claimed in claim 3, characterized in that: The target monitoring data is used to align the acquisition time, perform monitoring data analysis, and obtain instant analysis results and time series analysis results, including: Generate the acquisition time according to the activation time of the sensor module, and perform time alignment with the earliest acquisition time in the target monitoring data as the starting point to obtain a time series matrix of the target monitoring data, wherein the horizontal elements of the time series matrix are data of different monitoring variables at the same acquisition time, and the vertical elements are data of different acquisition times of the same monitoring variable; According to the time series matrix, horizontal data analysis and evaluation are performed to obtain the instant analysis results; The longitudinal data analysis and prediction are performed according to the time series matrix to obtain the time series analysis result.

5. The method for remote maintenance guidance of an electric chain saw guide plate based on the Internet of Things as claimed in claim 4, characterized in that: According to the time series matrix, horizontal data analysis and evaluation are performed to obtain the instant analysis results, including: According to the correlation and influence relationship between the top abnormal event and the temperature, vibration, tension and wear, a discriminator is generated based on historical abnormal data training, and the temperature, vibration, tension and wear monitoring data in the lateral data are used as input variables of the discriminator. The top abnormal event is discriminated by the discriminator, and the identified abnormal event is output as the instant analysis result. At the same time, the instant analysis result is compared with the abnormal warning threshold. When the abnormal warning threshold is reached, maintenance warning information is sent, and the maintenance warning information contains the abnormal event.

6. The method for remote maintenance guidance of an electric chain saw guide plate based on the Internet of Things as claimed in claim 5, characterized in that: Performing longitudinal data analysis and prediction according to the time series matrix to obtain the time series analysis result includes: Fitting the changing trend of the variable according to the longitudinal data to obtain the changing trend coefficient; Based on the change trend coefficient, a state change prediction is performed according to a time series relationship to obtain a predicted time series variable; The predicted time series variable is used as an input variable to perform top abnormal event discrimination through the discriminator, and the predicted abnormal event is output as the time series analysis result, and the time series analysis result includes the predicted abnormal state and its predicted time.

7. The method for remote maintenance guidance of an electric chain saw guide plate based on the Internet of Things as claimed in claim 1, characterized in that: The maintenance strategy is parsed according to the instant analysis result and the timing analysis result, and the maintenance strategy is divided into instructions according to the execution priority to generate maintenance guidance information, including: Obtaining abnormal events and their abnormal state time according to the instant analysis results and the time series analysis results; Establishing a mapping relationship between the abnormal event and the maintenance means, including the compensation efficiency of the maintenance means, obtaining a maintenance compensation time limit according to the abnormal state time, and determining the maintenance strategy using the maintenance compensation time limit and the compensation efficiency; Performing synchronization analysis on the maintenance strategy, and when a synchronization condition is met, generating the maintenance guidance information according to the maintenance strategy; When the maintenance strategy does not meet the synchronization condition, the maintenance strategy is prioritized to determine the strategy priority, wherein the strategy priority represents the risk level of the abnormal event; The maintenance strategies are sorted according to the priorities, instructions are segmented according to the sorting results, and the maintenance guidance information is generated.

8. The method for remote maintenance guidance of an electric chain saw guide plate based on the Internet of Things as claimed in claim 7, characterized in that: The maintenance strategies are sorted according to the priorities, and instructions are segmented according to the sorting results, and the method also includes: Determine whether the maintenance strategy has a shutdown strategy, and if so, analyze the compensation strategy of the corresponding abnormal event based on the time sequence relationship of the corresponding abnormal event; The compensation strategy is used to match maintenance strategies of other priorities. When the match is successful, the matching maintenance strategy is configured with the highest priority, and the maximum amount of the maintenance strategy and the compensation strategy is used as the execution strategy to reset the priority.

9. The electric chain saw guide plate remote maintenance guidance system based on the Internet of Things is characterized by: The system is used to execute the remote maintenance guidance method for an electric chain saw guide bar based on the Internet of Things according to any one of claims 1 to 8, comprising: A monitoring data extraction module, wherein the monitoring data extraction module is used to connect to the Internet of Things database to extract target monitoring data, wherein the target monitoring data includes at least one or more of temperature, vibration, tension, and wear data; A monitoring data analysis module, wherein the monitoring data analysis module is used to use the target monitoring data to perform acquisition time alignment, perform monitoring data analysis, and obtain instant analysis results and time series analysis results, wherein the instant analysis results are abnormal states existing in real time, and the time series analysis results are predicted abnormal states obtained by performing time series analysis prediction; A maintenance guidance module is used to analyze the maintenance strategy according to the instant analysis results and the timing analysis results, divide the maintenance strategy into instructions according to the execution priority, generate maintenance guidance information, and perform remote maintenance guidance based on the maintenance guidance information.

Images