Early warning method based on embedded system

Abstract

The invention relates to the technical field of communication early warning of embedded systems, and discloses an early warning method based on an embedded system, and the method comprises the steps: connecting the embedded system with a to-be-detected target device, obtaining the operation data of the target device, and building an initial operation model according to the operation data; and the embedded system is in communication connection with a database, historical fault data of the target equipment is obtained, and a fault judgment model is established according to the initial operation model and the historical fault data. And fault features and triggering factors in the fault judgment model are extracted, and a corresponding acquisition module is set according to the fault features to perform index data acquisition. The acquisition module is connected with the embedded system, the embedded system determines the early warning level of the target equipment according to the relationship between the index data acquired by the acquisition module and the fault characteristics, and the embedded system is connected with the target equipment, so that the equipment state can be comprehensively monitored and evaluated; therefore, potential fault risks can be timely identified and early warning can be automatically generated.

Description

Technical Field

[0001] The present invention relates to the technical field of communication early warning of embedded systems, and in particular to an early warning method based on embedded systems. Background Art

[0002] In the existing industry, equipment fault monitoring systems play a key role. By monitoring the operating status of equipment in real time, they can identify potential faults in advance and avoid sudden equipment downtime and production interruptions. Such systems not only improve equipment reliability and production efficiency, but also reduce the maintenance and replacement costs caused by faults.

[0003] However, at present, the equipment fault monitoring system mainly relies on manual periodic detection or fixed monitoring mode. This method not only consumes a lot of human resources, but also makes it difficult to ensure real-time monitoring results. Especially in complex industrial environments, the operating status of equipment is changeable, and it is difficult for existing systems to make accurate fault judgments based on real-time data. Problems are often only detected after the failure occurs, which leads to equipment downtime, increased maintenance costs, and may even cause safety accidents. At the same time, when the equipment is connected to the monitoring system, it needs to be adapted before it can be used. However, when it is found that the adaptation cannot be performed, additional technicians are required to make adjustments by changing the code, etc., which not only increases the complexity and maintenance difficulty of the equipment fault monitoring system during installation, but also further increases the cost of use.

[0004] Therefore, the existing equipment fault monitoring system has obvious deficiencies in real-time, accuracy and ease of use, and a more efficient and intelligent solution is urgently needed to improve the effectiveness of equipment monitoring. Summary of the invention

[0005] In view of this, the present invention proposes an early warning method based on an embedded system, aiming to solve the problem that the equipment fault monitoring system in the current technology has obvious deficiencies in real-time, accuracy and ease of use.

[0006] The present invention proposes an early warning method based on an embedded system, comprising:

[0007] Connecting the embedded system to the target device to be detected, acquiring the operation data of the target device, and establishing an initial operation model according to the operation data;

[0008] The embedded system is connected to a database for communication, the historical fault data of the target device is obtained, and a fault judgment model is established according to the initial operation model and the historical fault data;

[0009] Extracting fault characteristics and inducing factors in the fault judgment model, and setting corresponding acquisition modules to collect index data according to the fault characteristics;

[0010] The acquisition module is connected to the embedded system, and the embedded system determines the warning level of the target device according to the relationship between the indicator data collected by the acquisition module and the fault characteristics, wherein:

[0011] When the warning level is a low level, it is determined that no warning information notification is performed;

[0012] When the warning level is a medium level, the embedded system sends warning information to the operator through the communication unit according to a first preset interval;

[0013] When the warning level is high, the embedded system sends warning information to the operator through the communication unit according to a second preset interval;

[0014] Wherein, the first preset interval is greater than the second preset interval.

[0015] Furthermore, when establishing a fault judgment model based on the initial operation model and historical fault data, it includes:

[0016] Acquire the fault type, fault occurrence time, fault handling record and equipment maintenance record of each fault data in the historical fault data based on the embedded system;

[0017] According to the fault processing record, eliminating abnormal data in each of the fault data;

[0018] Establishing a relational expression for each of the fault data according to the fault type, fault occurrence time, fault handling record, and attribute information of the equipment maintenance record of each of the fault data after the abnormal data is removed;

[0019] The fault judgment model is established according to each of the fault data relationship expressions.

[0020] Furthermore, when establishing the fault judgment model according to each of the fault data relationship equations, it includes:

[0021] According to the fault type, aggregating the fault data relational expressions;

[0022] Obtaining a distance measurement between the fault relational expressions under the fault types after aggregation;

[0023] Establishing the distance matrix according to the distance measurement between the fault relational expressions under the fault type, and recursively merging the fault relational expressions under the fault type according to the distance matrix;

[0024] Obtain the fault characteristics of each fault type after recursive merging, and establish the fault judgment model.

[0025] Furthermore, when the embedded system determines the warning level of the target device according to the relationship between the indicator data collected by the collection module and the fault characteristics, it includes:

[0026] The relationship between the indicator data and the fault characteristics is associated through a preset mathematical model, and the preset mathematical model is based on a weighted analysis of the target device operating parameters, and the warning level is determined according to the weighted analysis result.

[0027] Furthermore, when determining the warning level according to the weighted analysis result, it also includes:

[0028] Normalizing the collected indicator data;

[0029] Obtaining a risk score for each fault feature according to the preset mathematical model;

[0030] The risk scores are weighted and aggregated to determine a warning score, and the warning level is determined based on the warning score.

[0031] Furthermore, the risk scores are weighted and summarized to determine the early warning score, including:

[0032] Obtaining the weight coefficient of each fault feature, each indicator data and the total number of fault features;

[0033] Substitute the weight coefficient of each fault feature, each indicator data and the total number of fault features into a formula to determine the early warning score. The formula is as follows:

[0034]

[0035] Among them, P represents the early warning score, wi is the weight corresponding to the fault feature i, xi is the i-th indicator data collected, f(xi) is the fault feature function corresponding to the data, and n is the total number of fault features.

[0036] Furthermore, when determining the warning level according to the warning score P, it includes:

[0037] Pre-configuring a first preset early warning score and a second preset early warning score, and determining the early warning level according to the relationship between the early warning score P and the first preset early warning score and the second preset early warning score;

[0038] When the warning score P is less than the first preset warning score, the warning level is determined to be a low level;

[0039] When the warning score P is greater than or equal to the first preset warning score, and the warning score P is less than the second preset warning score, the warning level is determined to be medium;

[0040] When the warning score P is greater than or equal to the second preset warning score, the warning level is determined to be a high level;

[0041] Among them, the first preset warning score is less than the second preset warning score, and the low level is less than the medium level and less than the high level.

[0042] Furthermore, the fault characteristic function f(xi) is dynamically adjusted according to the operating status and historical data of the equipment, wherein the fault characteristic function f(xi) can be in the form of a linear function, an exponential function or other nonlinear functions.

[0043] Furthermore, when it is determined that the embedded system sends warning information to the operator by the communication unit, it also includes:

[0044] Acquiring the operator's response time to the warning information, and determining the operator's response interval according to the response time;

[0045] The warning information, the response time and the response interval are used to establish fault data, and the fault data is sent to the database through the communication unit based on the embedded system for storage.

[0046] Compared with the prior art, the beneficial effect of the present invention is that by connecting the embedded system to the target device to be detected, the function of obtaining the device operation data in real time is realized. Compared with the traditional passive fault monitoring method, the present invention can capture the state change of the device in time and dynamically establish the initial operation model. This model can not only reflect the current operation state of the device, but also be updated as the data changes during the operation of the device, ensuring the real-time and accuracy of the early warning model. Secondly, through the communication connection with the database, the present invention can retrieve the historical fault data of the device and establish a fault judgment model in combination with the initial operation model. This method effectively utilizes the combination of historical data and current data, and provides a sufficient basis for the accurate prediction of equipment failures. Through the fault features and their inducing factors extracted by the fault judgment model, the acquisition module can be set in a targeted manner to ensure that the collected data is highly correlated with the fault features, avoid the collection of invalid data, and improve the efficiency and accuracy of monitoring. Further, the embedded system determines the early warning level of the target device according to the relationship between the indicator data and the fault features obtained by the acquisition module. This early warning mechanism based on the relationship between features and data enables the system to effectively distinguish the severity of the fault. For low-level warnings, the system avoids unnecessary notifications and reduces interference with operators; for medium-level and high-level warnings, different notification frequencies are set to ensure that operators can respond quickly in the event of a fault escalation to avoid accidents. In particular, high-level warnings with shorter preset intervals can promptly remind relevant personnel when a major equipment failure is about to occur, providing higher security. Finally, through the flexible adjustment of the first and second preset intervals, the system can set different response times according to different fault levels, making the entire warning process more intelligent and efficient. This interval setting can reasonably balance the timeliness of the warning and the degree of interference of the operator, and optimize the workflow of equipment management and monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0048] Figure 1 A flowchart of an early warning method based on an embedded system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0050] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides an early warning method based on an embedded system, including:

[0051] Step S100: Connect the embedded system to the target device to be detected, obtain the operating data of the target device, and establish an initial operating model according to the operating data.

[0052] Step S200: connect the embedded system to the database for communication, obtain historical fault data of the target device, and establish a fault judgment model based on the initial operation model and the historical fault data.

[0053] Specifically, when establishing a fault judgment model based on the initial operation model and historical fault data, it includes: obtaining the fault type, fault occurrence time, fault handling record and equipment maintenance record of each fault data in the historical fault data based on the embedded system. According to the fault handling record, the abnormal data in each fault data is eliminated. According to the attribute information between the fault type, fault occurrence time, fault handling record and equipment maintenance record of each fault data after eliminating the abnormal data, the relationship between each fault data is established. According to the relationship between each fault data, a fault judgment model is established.

[0054] Specifically, when establishing a fault judgment model based on each fault data relational expression, the method includes: aggregating each fault data relational expression based on the fault type. Obtaining the distance measurement between each fault relational expression under each fault type after aggregation. Establishing a distance matrix based on the distance measurement between each fault relational expression under the fault type, and recursively merging each fault relational expression under the fault type based on the distance matrix. Obtaining the fault characteristics of each fault type after recursive merging, and establishing a fault judgment model.

[0055] It can be seen that by processing these data, abnormal data are removed to ensure the accuracy of the data. Subsequently, the relationship between the fault data is established based on the attributes such as the fault type, fault occurrence time, processing record and maintenance record after removing the abnormal data, and the distance measurement between each fault relationship is calculated by aggregating the data of different fault types. Based on the distance measurement, a distance matrix is ​​established, and the fault characteristics of the fault type are obtained by recursive merging. Finally, a fault judgment model is constructed through these features, so that the system can more accurately predict and judge possible future fault conditions. This technical principle utilizes data aggregation, distance measurement and recursive algorithm to effectively improve the accuracy and reliability of the fault judgment model.

[0056] It is understandable that the process of acquiring historical fault data through the embedded system is the basis for building a fault judgment model. These data include information such as various fault types, fault occurrence time, fault handling records, and equipment maintenance records. By collecting and integrating this information, the embedded system can fully understand the historical fault conditions of the equipment and provide important basic data for subsequent analysis. In addition, these historical data provide a rich basis for pattern recognition and trend analysis of equipment failures, making the establishment of a fault judgment model more targeted and scientific. Next, when processing the acquired fault data, the step of removing abnormal data is particularly important. Abnormal data is usually caused by equipment failure, data collection errors, or human operation errors. These abnormal data may interfere with the construction of the model and reduce its prediction accuracy. By identifying and removing these abnormal data, the system can improve the quality of the data set, making the subsequent fault judgment model more representative and reliable. This process not only helps to clearly define the fault characteristics, but also provides a cleaner and more accurate data set for subsequent analysis. Subsequently, by establishing a relationship between the fault data, the embedded system can capture the potential connection between different fault types. This process involves analyzing the attribute information of various types of fault data and extracting fault relationships with similar characteristics. At this point, by aggregating the fault types, the embedded system can group related fault data so that the model can take into account the mutual influence between faults when processing. The calculation of distance metrics provides a quantitative basis for analyzing fault characteristics, helps identify the similarities and differences between different faults, and lays a solid foundation for further model building. Finally, in the process of calculating the distance matrix, the embedded system quantifies the distance between fault relations to form a structured representation, which is convenient for subsequent recursive merging. The recursive merging process can not only optimize the representation of fault relations, but also improve the overall performance of the fault judgment model. This process enables the model to dynamically adjust its structure, gradually focus on the most representative fault characteristics, and form a fault judgment model on this basis.

[0057] Step S300: extract fault characteristics and inducing factors in the fault judgment model, and set corresponding collection modules according to the fault characteristics to collect index data.

[0058] Step S400: Connect the acquisition module to the embedded system, and the embedded system determines the warning level of the target device according to the relationship between the indicator data collected by the acquisition module and the fault characteristics.

[0059] Specifically, when the embedded system determines the warning level of the target device based on the relationship between the indicator data collected by the acquisition module and the fault characteristics, it includes: the relationship between the indicator data and the fault characteristics is associated through a preset mathematical model, the preset mathematical model is based on a weighted analysis of the operating parameters of the target device, and the warning level is determined based on the weighted analysis results.

[0060] Specifically, when determining the warning level based on the weighted analysis results, it also includes: normalizing the collected indicator data. Obtaining the risk score of each fault feature according to a preset mathematical model. Weighting and summarizing the risk scores to determine the warning score, and determining the warning level based on the warning score.

[0061] Specifically, the weighted summary of each risk score to determine the early warning score includes: obtaining the weight coefficient of each fault feature, each indicator data, and the total number of fault features. Substitute the weight coefficient of each fault feature, each indicator data, and the total number of fault features into the formula to determine the early warning score, and the formula is as follows:

[0062]

[0063] Among them, P represents the early warning score, wi is the weight corresponding to the fault feature i, xi is the i-th indicator data collected, f(xi) is the fault feature function corresponding to the data, and n is the total number of fault features.

[0064] Specifically, when determining the warning level according to the warning score P, it includes: pre-configuring a first preset warning score and a second preset warning score, and determining the warning level according to the relationship between the warning score P and the first preset warning score and the second preset warning score. When the warning score P is less than the first preset warning score, the warning level is determined to be a low level. When the warning score P is greater than or equal to the first preset warning score, and the warning score P is less than the second preset warning score, the warning level is determined to be a medium level. When the warning score P is greater than or equal to the second preset warning score, the warning level is determined to be a high level. Among them, the first preset warning score is less than the second preset warning score, and the low level < medium level < high level.

[0065] It can be seen that the collected data of each indicator are normalized to ensure that the data are comparable and of uniform magnitude. Subsequently, the preset mathematical model calculates the risk score of each fault feature based on the weighted analysis of the equipment operating parameters. These risk scores are weighted and summarized according to the preset weight coefficients to obtain an overall warning score (P), which reflects the current degree of fault risk of the equipment. Further, according to the pre-configured first and second preset warning scores, the system determines the final warning level according to the relationship between the warning score (P) and the two preset values. When the warning score is lower than the first preset value, the warning level is set to a low level, and no warning information is required; when the score is between the first and second preset values, it is set to a medium level, and the system sends timely warning information to the operator; and when the score reaches or exceeds the second preset value, it is set to a high level, and the operator needs to be notified immediately to take emergency measures.

[0066] It is understandable that the embedded system obtains the index data of the equipment through the acquisition module, which is the basis of the entire early warning process. The collected data includes a variety of operating parameters, such as temperature, pressure, vibration, etc. These data provide important information about the current operating status of the equipment, laying the foundation for subsequent fault analysis and early warning evaluation. In this process, the accuracy and timeliness of the acquisition module are crucial to ensure that the real-time equipment status changes can be captured, thereby providing the most accurate input for the model. Secondly, normalizing the collected index data is one of the key steps. The purpose of normalization is to convert data of different dimensions and ranges to a unified scale so that each indicator is comparable in the subsequent weighted analysis. This process effectively eliminates the impact caused by different data magnitudes and ensures that each indicator can fairly reflect its contribution to the fault risk. In addition, normalization processing also helps to improve the convergence of the model and reduce the numerical instability problems that may occur during the training process. Next, the embedded system uses a preset mathematical model to score the fault characteristics. The model is based on the weighted analysis of the equipment operating parameters and comprehensively considers the impact of each indicator on the fault. By combining the normalized index data with the fault feature function, the system can calculate the risk score of each fault feature. This score reflects the probability of a specific fault feature occurring under the current operating state of the equipment, and provides basic data for the subsequent early warning score. When weighting and summarizing the risk scores of each fault feature, the embedded system introduces a weight coefficient, which reflects the importance of each fault feature in the overall fault judgment. By using the formula for calculation, the embedded system can comprehensively evaluate the impact of multiple fault features on the overall fault risk of the equipment. This weighted summary not only improves the accuracy of fault judgment, but also enables the model to flexibly adapt to the needs of different equipment and environments. Finally, based on the relationship between the calculated early warning score (P) and the pre-set first and second early warning scores, the embedded system can effectively determine the early warning level. When the early warning score is lower than the first preset value, the embedded system determines that the equipment is in a safe operating state and no alarm is required; when the score is between the two, the embedded system issues a medium-level early warning to remind the operator to pay attention to potential risks; and when the score reaches or exceeds the second preset value, the embedded system immediately issues a high-level alarm and requires emergency measures. Such a graded warning mechanism can not only optimize information transmission and reduce the possibility of false alarms and missed alarms, but also ensure that operators take appropriate measures when facing different risk levels, effectively improving the safety and operating efficiency of equipment.

[0067] Specifically, when sending warning information according to the warning level, it includes: when the warning level is a low level, it is determined that no warning information notification is performed. When the warning level is a medium level, the embedded system sends warning information to the operator through the communication unit according to the first preset interval. When the warning level is a high level, the embedded system sends warning information to the operator through the communication unit according to the second preset interval. The first preset interval is greater than the second preset interval.

[0068] It is understandable that the embedded system adopts differentiated warning information sending strategies according to different warning levels to optimize the efficiency and effectiveness of information transmission. When the warning level is low, the system determines that the equipment is in a safe operating state, so it does not send any warning information to avoid unnecessary interference; when the warning level is medium, the system will regularly send warning information to the operator according to the set first preset interval to remind him to pay attention to the potential risks of the equipment and ensure that the operator can remain alert; in the case of high-level warnings, the system will send information more frequently according to the second preset interval, so that the operator can quickly take emergency measures to reduce the risk of failure. In this way, the embedded system not only achieves flexible response to different risk levels, but also improves the pertinence and timeliness of warning information, ensuring that operators can effectively deal with the risk of equipment failure, thereby improving the safety and reliability of the equipment.

[0069] Specifically, the fault characteristic function f(xi) is dynamically adjusted according to the operating status and historical data of the equipment, wherein the fault characteristic function f(xi) can be in the form of a linear function, an exponential function or other nonlinear functions.

[0070] It can be understood that by updating its function form in real time based on the operating status and historical data of the equipment to adapt to different working conditions. This dynamic adjustment mechanism allows the function to maintain efficient response capabilities to fault characteristics when facing complex equipment behaviors and environmental changes. The fault characteristic function can take the form of a linear function, an exponential function, or other nonlinear functions, which reflects the flexible modeling of the relationship between fault characteristics and indicator data, and can more accurately reflect the failure risk of the equipment under specific conditions. For example, linear functions are suitable for situations where there is a linear relationship between fault risk and indicator data, while exponential functions and nonlinear functions can capture more complex dynamic behaviors. When the operating status of the equipment changes or the historical data is updated, the system can quickly adjust the form of the fault characteristic function, thereby optimizing the calculation of the risk score and improving the accuracy and timeliness of fault prediction.

[0071] In some embodiments of the present application, when determining that the embedded system sends warning information to the operator through the communication unit, it also includes: obtaining the operator's response time to the warning information, and determining the operator's response interval based on the response time. The warning information, the response time, and the response interval are used to establish fault data, and the fault data is sent to the database through the communication unit based on the embedded system for storage.

[0072] It can be seen that the embedded system analyzes the operator's response time to the warning information and dynamically determines its response interval, thereby optimizing the transmission efficiency of the warning information and the timeliness of subsequent operations. Specifically, after sending the warning information, the embedded system will monitor the operator's response time in real time. This information not only reflects the operator's sensitivity to the warning, but also provides a basis for the subsequent response strategy. According to the collected response time, the embedded system can intelligently adjust the operator's response interval to achieve more effective information interaction in future warnings. At the same time, the embedded system integrates the warning information, response time and response interval into fault data, and sends this data to the database for storage through the communication unit. This process ensures the systematic recording of all relevant information and provides a basis for subsequent data analysis and fault feature modeling. By analyzing the historical response data, the embedded system can continuously optimize the warning strategy and enhance the ability to predict equipment failures. The implementation of this feedback mechanism enables the entire warning system to not only have real-time response capabilities, but also to continuously improve and evolve in a data-driven manner to improve the safety and reliability of the equipment.

[0073] In the above embodiment, by connecting the embedded system to the target device to be detected, the function of obtaining the device operation data in real time is realized. Compared with the traditional passive fault monitoring method, the present invention can capture the state change of the device in time and dynamically establish the initial operation model. This model can not only reflect the current operation state of the device, but also be updated as the data changes during the operation of the device, ensuring the real-time and accuracy of the early warning model. Secondly, through the communication connection with the database, the present invention can retrieve the historical fault data of the device and establish a fault judgment model in combination with the initial operation model. This method effectively utilizes the combination of historical data and current data, and provides a sufficient basis for the accurate prediction of equipment failures. Through the fault features and their inducing factors extracted by the fault judgment model, the acquisition module can be set in a targeted manner to ensure that the collected data is highly correlated with the fault features, avoid the collection of invalid data, and improve the efficiency and accuracy of monitoring. Further, the embedded system determines the early warning level of the target device according to the relationship between the indicator data and the fault features obtained by the acquisition module. This early warning mechanism based on the relationship between features and data enables the system to effectively distinguish the severity of the fault. For low-level early warnings, the system avoids unnecessary notifications and reduces interference with operators. For medium-level and high-level warnings, different notification frequencies are set to ensure that operators can respond quickly to escalating faults and avoid accidents. In particular, high-level warnings with shorter preset intervals can promptly remind relevant personnel when a major equipment failure is about to occur, providing higher security. Finally, through the flexible adjustment of the first and second preset intervals, the system can set different response times according to different fault levels, making the entire warning process more intelligent and efficient. This interval setting can reasonably balance the timeliness of the warning and the degree of interference of the operator, and optimize the workflow of equipment management and monitoring.

[0074] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0075] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An early warning method based on an embedded system, characterized in that: include: Connecting the embedded system to the target device to be detected, acquiring the operation data of the target device, and establishing an initial operation model according to the operation data; The embedded system is connected to a database for communication, the historical fault data of the target device is obtained, and a fault judgment model is established according to the initial operation model and the historical fault data; Extracting fault characteristics and inducing factors in the fault judgment model, and setting corresponding acquisition modules to collect index data according to the fault characteristics; The acquisition module is connected to the embedded system, and the embedded system determines the warning level of the target device according to the relationship between the indicator data collected by the acquisition module and the fault characteristics, wherein: When the warning level is a low level, it is determined that no warning information notification is performed; When the warning level is a medium level, the embedded system sends warning information to the operator through the communication unit according to a first preset interval; When the warning level is high, the embedded system sends warning information to the operator through the communication unit according to a second preset interval; Wherein, the first preset interval is greater than the second preset interval.

2. The early warning method based on embedded system as claimed in claim 1, characterized in that: When establishing a fault judgment model based on the initial operation model and historical fault data, it includes: Acquire the fault type, fault occurrence time, fault handling record and equipment maintenance record of each fault data in the historical fault data based on the embedded system; According to the fault processing record, eliminating abnormal data in each of the fault data; Establishing a relational expression for each of the fault data according to the fault type, fault occurrence time, fault handling record, and attribute information of the equipment maintenance record of each of the fault data after the abnormal data is removed; The fault judgment model is established according to each of the fault data relationship expressions.

3. The early warning method based on embedded system as claimed in claim 2, characterized in that: When establishing the fault judgment model according to each of the fault data relationship equations, it includes: According to the fault type, aggregating the fault data relational expressions; Obtaining a distance metric between the fault relational expressions under the fault types after aggregation; Establishing the distance matrix according to the distance measurement between the fault relational expressions under the fault type, and recursively merging the fault relational expressions under the fault type according to the distance matrix; Obtain the fault characteristics of each fault type after recursive merging, and establish the fault judgment model.

4. The early warning method based on embedded system as claimed in claim 1, characterized in that: When the embedded system determines the warning level of the target device according to the relationship between the indicator data collected by the collection module and the fault characteristics, it includes: The relationship between the indicator data and the fault characteristics is associated through a preset mathematical model, and the preset mathematical model is based on a weighted analysis of the target device operating parameters, and the warning level is determined according to the weighted analysis result.

5. The early warning method based on embedded system as claimed in claim 4, characterized in that: According to the weighted analysis results, the warning level is determined, which also includes: Normalizing the collected indicator data; Obtaining a risk score for each fault feature according to the preset mathematical model; The risk scores are weighted and aggregated to determine a warning score, and the warning level is determined based on the warning score.

6. The early warning method based on embedded system as claimed in claim 5, characterized in that: The risk scores are weighted and aggregated to determine the early warning score, including: Obtaining the weight coefficient of each fault feature, each indicator data and the total number of fault features; Substitute the weight coefficient of each fault feature, each indicator data and the total number of fault features into a formula to determine the early warning score. The formula is as follows: Among them, P represents the early warning score, wi is the weight corresponding to the fault feature i, xi is the i-th indicator data collected, f(xi) is the fault feature function corresponding to the data, and n is the total number of fault features.

7. The early warning method based on embedded system as claimed in claim 6, characterized in that: When determining the warning level according to the warning score P, it includes: Pre-configuring a first preset early warning score and a second preset early warning score, and determining the early warning level according to the relationship between the early warning score P and the first preset early warning score and the second preset early warning score; When the warning score P is less than the first preset warning score, the warning level is determined to be a low level; When the warning score P is greater than or equal to the first preset warning score, and the warning score P is less than the second preset warning score, the warning level is determined to be medium; When the warning score P is greater than or equal to the second preset warning score, the warning level is determined to be a high level; Among them, the first preset warning score is less than the second preset warning score, and the low level is less than the medium level and less than the high level.

8. The early warning method based on embedded system as claimed in claim 6, characterized in that: The fault characteristic function f(xi) is dynamically adjusted according to the operating status and historical data of the equipment, wherein the fault characteristic function f(xi) can be in the form of a linear function, an exponential function or other nonlinear functions.

9. The early warning method based on embedded system as claimed in claim 1, characterized in that: When it is determined that the embedded system sends warning information to the operator by the communication unit, the method further includes: Acquiring the operator's response time to the warning information, and determining the operator's response interval according to the response time; The warning information, the response time and the response interval are used to establish fault data, and the fault data is sent to the database through the communication unit based on the embedded system for storage.

Images