A multi-sensor based equipment operation status monitoring system

Abstract

The present invention relates to the field of remote monitoring technology, and discloses a multi-sensor based equipment operation status monitoring system, including: a sensor module and a monitoring module; the sensor module includes a vibration sensor, a temperature sensor and a humidity sensor; the monitoring module includes a collection unit to collect the operation data of each sensor to establish a data group, and obtain the data fluctuation value of the sensor module according to the data group; the processing unit collects the historical normal operation data in the storage unit to obtain the data fluctuation threshold of the sensor module; the judgment unit filters the data fluctuation value according to the data fluctuation threshold, calculates the abnormal value of the filtered data, and determines the abnormal data according to the abnormal value; the early warning unit calculates the similarity between the abnormal data and the historical abnormal operation data according to the abnormal data, and issues an early warning to the monitored equipment according to the similarity. The present invention integrates vibration, temperature and humidity sensors, can comprehensively capture the operation status of the equipment, enhance the accuracy of early warning, and reduce maintenance costs.

Description

Technical Field

[0001] The present invention relates to the field of remote monitoring technology, and in particular to a multi-sensor based equipment operation status monitoring system. Background Art

[0002] In modern industrial and manufacturing environments, with the continuous improvement of factory automation and intelligence levels, the efficient operation of equipment in the factory is directly related to production efficiency, and equipment operation monitoring has become particularly important.

[0003] Traditional equipment operation status monitoring relies on periodic manual inspections and fixed monitoring points, which makes it difficult to reflect the dynamic changes in equipment operation in real time. With the expansion of factory scale and the complexity of production processes, the diversity of equipment operation and changes in environmental conditions have made monitoring increasingly difficult. Although sensors can now be used to monitor temperature, pressure, vibration and other multiple sensors for measurement. However, as the service life of the equipment increases, the data of the normal operation of the equipment itself will change, and the warning threshold of the sensor still needs to be manually adjusted, which increases the difficulty of monitoring and is prone to false alarms.

[0004] Therefore, it is necessary to design a multi-sensor based equipment operation status monitoring system to solve the problems existing in current technology. Summary of the invention

[0005] In view of this, the present invention proposes a multi-sensor based equipment operation status monitoring system, aiming to solve the problem that the current monitoring system relies on human control, which is time-consuming and labor-intensive, has low monitoring accuracy and is prone to false alarms.

[0006] The present invention proposes a multi-sensor based equipment operation status monitoring system, comprising:

[0007] Sensor modules and monitoring modules;

[0008] The sensor module includes a vibration sensor, a temperature sensor and a humidity sensor, and the sensor module is arranged in the device to be monitored;

[0009] The monitoring module is electrically connected to the sensor module, and the monitoring module includes a collection unit, a processing unit, a judgment unit, an early warning unit and a storage unit;

[0010] The acquisition unit is configured to acquire operation data of each sensor in the sensor module, establish a data group according to the operation data, the data group includes the operation data of each sensor in the sensor module at a current moment and the operation data of each sensor in the sensor module at a previous moment, and obtain the data fluctuation value of the sensor module according to the data group;

[0011] The processing unit is configured to collect historical normal operation data in the storage unit, and obtain a data fluctuation threshold of the sensor module according to the historical normal operation data;

[0012] The judgment unit is configured to filter the data fluctuation value according to the data fluctuation threshold, calculate the abnormal value of the filtered data based on the isolation forest model, and determine the abnormal data according to the abnormal value;

[0013] The early warning unit is configured to calculate the similarity between the abnormal data and the historical abnormal operation data in the storage unit according to the data type, data value and number of each type of abnormal data of the abnormal data, and to issue an early warning to the device to be monitored according to the similarity.

[0014] Further, when the processing unit obtains the data fluctuation threshold of the sensor module according to the historical normal operation data, it includes:

[0015]

[0016] Among them, Y represents the data fluctuation threshold, It represents the fluctuation mean of historical normal operation data. represents the standard deviation of fluctuations in historical normal operation data, and k represents the adjustment factor;

[0017]

[0018]

[0019]

[0020] Among them, Wt represents the data fluctuation value of historical normal operation data, represents the operating data of the sensor at time t, represents the operating data of the sensor at time t-1, and N represents the number of historical normal operating data.

[0021] Further, when the judgment unit screens the data fluctuation value according to the data fluctuation threshold, it includes:

[0022] Compare the data fluctuation value with the data fluctuation threshold value to eliminate small fluctuation data;

[0023] When the data fluctuation value is greater than the data fluctuation threshold, retaining the fluctuation data;

[0024] When the data fluctuation value is less than or equal to the data fluctuation threshold, the fluctuation data is determined to be small fluctuation data and is eliminated.

[0025] Furthermore, the judgment unit calculates the outlier value of the filtered data based on the isolation forest model, and determines the abnormal data according to the outlier value, including:

[0026] Calculate the outlier value of each filtered data based on the isolation forest model;

[0027]

[0028] Where s(a) represents the outlier of data a, E(h(a)) represents the average path length of data a in all isolated trees in the isolation forest, and c(n) represents the average path length used to standardize the path length;

[0029] When the abnormal value of the filtered data is greater than 0.8, the data is determined to be the abnormal data, and the sensor type corresponding to the abnormal data is identified.

[0030] Furthermore, when the early warning unit calculates the similarity between the abnormal data and the historical abnormal operation data in the storage unit according to the data type, data value and number of each type of abnormal data of the abnormal data, it includes:

[0031]

[0032] Among them, X represents the number of data types of abnormal data, Y represents the maximum data value in the abnormal data, Z represents the total number of abnormal data, Xi represents the number of data types of the i-th group of data in the historical abnormal operation data, Yi represents the maximum data value of the i-th group of data in the historical abnormal operation data, Zi represents the total number of the i-th group of data in the historical abnormal operation data, and Si represents the similarity between the abnormal data and the i-th group of data in the historical abnormal operation data.

[0033] Furthermore, when the early warning unit issues an early warning to the device to be monitored according to the similarity, it includes:

[0034] When there is data in the historical abnormal operation data whose similarity with the abnormal data is greater than a similarity threshold, the early warning unit issues an early warning according to the historical early warning level corresponding to the historical abnormal operation data; when there is no data in the historical abnormal operation data whose similarity with the abnormal data is greater than a similarity threshold, the early warning unit obtains the maximum data fluctuation value according to the abnormal data, determines the initial risk level according to the maximum data fluctuation value, and determines whether to adjust the initial risk level according to the distribution of the abnormal data to determine the final risk level.

[0035] Furthermore, when the warning unit issues a warning according to the historical warning level corresponding to the historical abnormal operation data, it includes:

[0036] When the historical abnormal operation data and the abnormal data have a similarity greater than a similarity threshold, the early warning unit uses the historical early warning level corresponding to the historical abnormal operation data as the final risk level to issue an early warning to the device to be monitored;

[0037] When the data whose similarity between the historical abnormal operation data and the abnormal data is greater than the similarity threshold is not unique, if the corresponding historical warning levels are the same, the warning unit will use the corresponding historical warning level as the final risk level to warn the equipment to be monitored; if the corresponding historical warning levels are different, the warning unit will use the highest historical warning level among the corresponding historical warning levels as the final risk level to warn the equipment to be monitored.

[0038] Furthermore, when the early warning unit determines the initial risk level according to the maximum data fluctuation value, it includes:

[0039] The early warning unit compares the maximum data fluctuation value with a first preset data fluctuation value and a second preset data fluctuation value respectively, and determines an initial risk level according to the comparison result; the first preset data fluctuation value is smaller than the second preset data fluctuation value;

[0040] When the maximum data fluctuation value is less than or equal to a first preset data fluctuation value, the early warning unit determines that the initial risk level is the third risk level; when the maximum data fluctuation value is greater than the first preset data fluctuation value and less than or equal to the second preset data fluctuation value, the early warning unit determines that the initial risk level is the second risk level; when the maximum data fluctuation value is greater than the second preset data fluctuation value, the early warning unit determines that the initial risk level is the first risk level; the first risk level is greater than the second risk level, and the second risk level is greater than the third risk level.

[0041] Furthermore, when the early warning unit determines whether to adjust the initial risk level according to the abnormal data distribution, it includes:

[0042] The early warning unit determines the abnormal center point according to the location where the abnormal data appears, calculates the distance between each abnormal data in the abnormal data and the abnormal center point and determines the maximum distance; when the maximum distance is greater than a distance threshold, the early warning unit determines to adjust the initial risk level to obtain the final risk level; when the maximum distance is less than or equal to the distance threshold, the early warning unit determines not to adjust the initial risk level, and uses the initial risk level as the final risk level.

[0043] Furthermore, when the early warning unit determines to adjust the initial risk level to obtain the final risk level, it includes:

[0044] The early warning unit determines a distance difference according to the maximum distance and the distance threshold, the distance difference being the difference between the maximum distance and the distance threshold, the early warning unit compares the distance difference with the limited distance, and adjusts the initial risk level according to the comparison result to obtain the final risk level;

[0045] When the distance difference is less than or equal to the limited distance, the early warning unit increases the initial risk level by one level to obtain the final risk level; when the distance difference is greater than the limited distance, the early warning unit increases the initial risk level by two levels to obtain the final risk level.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: the sensor module integrates vibration, temperature and humidity sensors, which can fully capture the operating status of the equipment and ensure the monitoring accuracy under various environmental conditions. The monitoring module automatically analyzes the sensor data through the collection, processing and judgment units, and generates data fluctuation values ​​and fluctuation thresholds in real time. Automated data processing reduces manual intervention and reduces the false alarm rate. The isolation forest model effectively identifies abnormal data and provides an accurate basis for equipment failure warning. Finally, the abnormal data is compared with the historical data before the warning is issued, which further enhances the accuracy of the warning, reduces maintenance costs, and enhances the safety and reliability of the equipment. 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 This is a structural block diagram of a multi-sensor based equipment operation status monitoring system provided in 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] In modern industrial and manufacturing environments, with the continuous improvement of factory automation and intelligence, the efficient operation of equipment has become crucial. However, the current equipment operation status monitoring still mainly relies on periodic manual inspections and fixed monitoring points, which makes it difficult to reflect the dynamic changes of equipment in real time. With the expansion of factory scale and the complexity of production processes, the diversity of equipment operation and changes in environmental conditions have further increased the difficulty of monitoring. Although existing technologies can use sensors to monitor parameters such as temperature, pressure and vibration, the normal operation data of equipment will change after long-term use, resulting in frequent manual adjustment of the sensor's warning threshold. This not only increases the complexity of monitoring, but also increases the risk of false alarms, which may lead to delayed response to equipment failures. Therefore, it is particularly necessary to design an equipment operation status monitoring system based on multiple sensors to cope with the limitations of existing monitoring methods and ensure equipment safety and production efficiency.

[0051] In some embodiments of the present application, see Figure 1 As shown, a multi-sensor based equipment operation status monitoring system includes:

[0052] Sensor modules and monitoring modules;

[0053] The sensor module includes a vibration sensor, a temperature sensor and a humidity sensor, and the sensor module is arranged in the device to be monitored;

[0054] The monitoring module is electrically connected to the sensor module, and the monitoring module includes a collection unit, a processing unit, a judgment unit, an early warning unit and a storage unit;

[0055] The collecting unit is configured to collect the operation data of each sensor in the sensor module, establish a data group according to the operation data, the data group includes the operation data of each sensor in the sensor module at the current moment and the operation data of each sensor in the sensor module at the previous moment, and obtain the data fluctuation value of the sensor module according to the data group;

[0056] The processing unit is configured to collect historical normal operation data in the storage unit, and obtain a data fluctuation threshold of the sensor module according to the historical normal operation data;

[0057] The judgment unit is configured to filter the data fluctuation value according to the data fluctuation threshold, calculate the abnormal value of the filtered data based on the isolation forest model, and determine the abnormal data according to the abnormal value;

[0058] The early warning unit is configured to calculate the similarity between the abnormal data and the historical abnormal operation data in the storage unit according to the data type, data value and number of each type of abnormal data of the abnormal data, and issue an early warning to the monitored device according to the similarity.

[0059] Specifically, the operating status data of the monitored equipment is collected in real time by integrating multiple sensors (vibration, temperature and humidity). The sensor module is directly installed inside the equipment to ensure direct monitoring of the operating environment. The monitoring module is responsible for processing and analyzing the collected data to identify potential faults in a timely manner. The acquisition unit is responsible for collecting sensor data in real time and establishing a data group. The data group contains not only the sensor data at the current moment, but also the data at the previous moment, so that the system can calculate the fluctuation value of the data. The processing unit determines the threshold of data fluctuation based on the historical normal operation data. The judgment unit compares the data fluctuation value with the data fluctuation threshold, preliminarily screens out the data with large fluctuations, and uses the isolation forest model to detect outliers on the screened data. The isolation forest model can effectively identify abnormal fluctuations in the data, thereby helping to judge the operating status of the equipment. The early warning unit calculates the similarity between the abnormal data and the historical abnormal data based on the type, value and number of abnormal data, and finally determines the early warning status of the monitored equipment according to the similarity.

[0060] It is understandable that the multi-sensor-based equipment operation status monitoring system improves the real-time and accuracy of equipment monitoring. Through multi-dimensional data collection and analysis, the system can provide timely warnings before the equipment becomes abnormal, reduce the risk of failure, and improve production efficiency. At the same time, the system's automation characteristics reduce the need for manual intervention and reduce the probability of false alarms, thereby ensuring the safe and stable operation of the equipment.

[0061] In some embodiments of the present application, when the processing unit obtains the data fluctuation threshold of the sensor module according to the historical normal operation data, it includes:

[0062]

[0063] Among them, Y represents the data fluctuation threshold, It represents the fluctuation mean of historical normal operation data. represents the standard deviation of fluctuations in historical normal operation data, and k represents the adjustment factor;

[0064]

[0065]

[0066]

[0067] Among them, Wt represents the data fluctuation value of historical normal operation data, represents the operating data of the sensor at time t, represents the operating data of the sensor at time t-1, and N represents the number of historical normal operating data.

[0068] It can be understood that the data fluctuation threshold (Y) is a key indicator used in the monitoring system to determine whether the data is abnormal. The fluctuation mean (μ) represents the average fluctuation level of the historical normal operation data, reflecting the state of the equipment under normal working conditions. This value provides a benchmark for threshold setting. The fluctuation standard deviation (σ) quantifies the fluctuation amplitude of the historical data, indicating the range of variation of the data during normal operation. The larger the standard deviation, the more drastic the fluctuation, and vice versa. The adjustment factor (k) is used to flexibly adjust the sensitivity of the fluctuation threshold to facilitate the needs of different equipment and operating environments. By changing the value of k, the looseness of the threshold can be controlled, thereby affecting the sensitivity of the warning. The specific k value setting can be set according to the actual monitoring needs, and the preferred k value is [0.8-1.2]. By quantifying the fluctuation characteristics of historical data and reasonably setting the standard for abnormal detection, the system can dynamically adapt to changes in the status of the equipment. At the same time, the introduction of the adjustment factor allows the threshold to be flexibly adjusted according to actual conditions, enhancing the adaptability and reliability of the system.

[0069] It is understandable that by setting dynamic thresholds based on historical data, the system can more effectively identify real abnormal signals and reduce the probability of false alarms and missed alarms. In addition, flexible adjustment factors allow the monitoring solution to be optimized for different equipment and operating environments, thereby achieving higher adaptability and accuracy, ensuring the safe and stable operation of the equipment.

[0070] In some embodiments of the present application, when the judgment unit screens the data fluctuation value according to the data fluctuation threshold, it includes: comparing the data fluctuation value with the data fluctuation threshold to eliminate small fluctuation data;

[0071] Specifically, when the data fluctuation value is greater than the data fluctuation threshold, the fluctuation data is retained; when the data fluctuation value is less than or equal to the data fluctuation threshold, the fluctuation data is determined to be small fluctuation data and is eliminated.

[0072] In some embodiments of the present application, the judgment unit calculates the outlier value of the filtered data based on the isolation forest model, and determines the abnormal data according to the outlier value, including:

[0073] Calculate the outlier value of each filtered data based on the isolation forest model;

[0074]

[0075] Where s(a) represents the outlier of data a, E(h(a)) represents the average path length of data a in all isolated trees in the isolation forest, and c(n) represents the average path length used to standardize the path length;

[0076] When the outlier value of the filtered data is greater than 0.8, the data is determined to be abnormal data, and the sensor type corresponding to the abnormal data is identified.

[0077] Specifically, the judgment unit first compares the data fluctuation value with the preset data fluctuation threshold to ensure that only significant fluctuations are focused on. When the data fluctuation value is greater than the threshold, it is considered that the fluctuation reflects the actual state change of the device, so the data is retained; otherwise, the small fluctuation data is eliminated. This process effectively filters out noise and improves the effectiveness of subsequent analysis. Using the isolation forest model, the judgment unit can detect outliers on the filtered data. The isolation forest measures the degree of isolation of data points by constructing multiple random trees, and the average path length (E(h(a)) is used as a metric. The shorter the data point, the more abnormal it is. The standardized path length (c(n)) is used to standardize the path length to ensure comparability between data sets of different sizes. By setting a reasonable fluctuation threshold, the system can actively eliminate irrelevant small fluctuations, thereby focusing on potential abnormal signals. The isolation forest model provides an anomaly detection method based on the path length of the data point in the tree, which adapts to the diversity and complexity of the data in equipment monitoring. This method improves the accuracy of anomaly identification and reduces the complexity of calculation.

[0078] It is understandable that by screening data fluctuations and combining the intelligent analysis of the isolation forest model, the system can accurately identify real abnormal signals and reduce the risk of false positives and false negatives. It ensures the safety and reliability of the equipment and makes the production process smoother. In addition, the sensor type corresponding to the abnormal data is clearly identified to facilitate subsequent maintenance and processing.

[0079] In some embodiments of the present application, when the early warning unit calculates the similarity between the abnormal data and the historical abnormal operation data in the storage unit according to the data type, data value and number of each type of abnormal data of the abnormal data, it includes:

[0080]

[0081] Among them, X represents the number of data types of abnormal data, Y represents the maximum data value in the abnormal data, Z represents the total number of abnormal data, Xi represents the number of data types of the i-th group of data in the historical abnormal operation data, Yi represents the maximum data value of the i-th group of data in the historical abnormal operation data, Zi represents the total number of the i-th group of data in the historical abnormal operation data, and Si represents the similarity between the abnormal data and the i-th group of data in the historical abnormal operation data.

[0082] In some embodiments of the present application, when the early warning unit issues an early warning to the monitored equipment based on the similarity, it includes: when there is data in the historical abnormal operation data whose similarity with the abnormal data is greater than the similarity threshold, the early warning unit issues an early warning based on the historical early warning level corresponding to the historical abnormal operation data; when there is no data in the historical abnormal operation data whose similarity with the abnormal data is greater than the similarity threshold, the early warning unit obtains the maximum data fluctuation value based on the abnormal data, determines the initial risk level based on the maximum data fluctuation value, and determines whether to adjust the initial risk level based on the distribution of the abnormal data to determine the final risk level.

[0083] Specifically, when the detected similarity is greater than the similarity threshold, the system considers that the current abnormal situation is strongly associated with the historical abnormality, and issues an early warning based on the early warning level corresponding to the historical data. If there is no data with a similarity greater than the threshold, the system will determine the initial risk level based on the maximum fluctuation value of the abnormal data. The system will also analyze the distribution characteristics of the data to determine whether the risk level needs to be adjusted, thereby deriving the final risk level.

[0084] It is understandable that the risk of the current equipment status can be determined by analyzing the similarity between abnormal data and historical data. This similarity calculation enables the system to respond more intelligently to possible fault conditions and avoid false alarms caused by simple threshold trigger mechanisms. By comprehensively considering historical abnormal conditions, the early warning unit can improve the accuracy of early warnings and reduce the false alarm rate.

[0085] In some embodiments of the present application, when the early warning unit issues an early warning based on the historical early warning level corresponding to the historical abnormal operation data, it includes: when the data whose similarity between the historical abnormal operation data and the abnormal data is greater than the similarity threshold is unique, the early warning unit uses the historical early warning level corresponding to the historical abnormal operation data as the final risk level to issue an early warning to the monitored equipment; when the data whose similarity between the historical abnormal operation data and the abnormal data is greater than the similarity threshold is not unique, if the corresponding historical warning levels are the same, the early warning unit uses the corresponding historical warning level as the final risk level to issue an early warning to the monitored equipment; if the corresponding historical warning levels are different, the early warning unit uses the highest level of the corresponding historical warning levels as the final risk level to issue an early warning to the monitored equipment.

[0086] Specifically, when the similarity between historical abnormal operation data and current abnormal data is greater than a threshold, the early warning unit first determines the uniqueness of these data. If the data with high similarity corresponds to only one piece of historical abnormal data, the corresponding historical warning level is directly used as the final risk level for early warning. If there are multiple pieces of historical abnormal data with high similarity, further analysis is required. If the warning levels of these historical data are the same, the system directly uses the warning level as the final risk level. If the corresponding historical warning levels are inconsistent, the early warning unit will select the highest warning level as the final risk level for early warning. This ensures that in the case of different risk assessments, the most stringent standards can be used to respond, thereby improving safety.

[0087] It is understandable that by analyzing the similarity between historical abnormal data and current abnormal data, the accuracy and pertinence of the early warning can be ensured. By judging the uniqueness of the data and the similarity of the early warning level, the system can dynamically adjust the risk assessment to make the early warning more scientific and reasonable. It avoids the uncertainty caused by data diversity and ensures that it can still respond quickly and effectively when facing complex situations.

[0088] In some embodiments of the present application, when the early warning unit determines the initial risk level according to the maximum data fluctuation value, it includes: the early warning unit compares the maximum data fluctuation value with a first preset data fluctuation value and a second preset data fluctuation value respectively, and determines the initial risk level according to the comparison result; the first preset data fluctuation value is less than the second preset data fluctuation value;

[0089] Specifically, when the maximum data fluctuation value is less than or equal to the first preset data fluctuation value, the early warning unit determines that the initial risk level is the third risk level; when the maximum data fluctuation value is greater than the first preset data fluctuation value and less than or equal to the second preset data fluctuation value, the early warning unit determines that the initial risk level is the second risk level; when the maximum data fluctuation value is greater than the second preset data fluctuation value, the early warning unit determines that the initial risk level is the first risk level; the first risk level is greater than the second risk level, and the second risk level is greater than the third risk level.

[0090] It is understandable that by setting different fluctuation thresholds, a hierarchical risk assessment system is formed. This enables the system to dynamically adjust the risk level based on real-time data, thereby responding promptly to changes in equipment status. Clearly classified risk levels can effectively guide subsequent decisions and actions, ensuring that potential failures are discovered in a timely manner.

[0091] In some embodiments of the present application, when the early warning unit determines whether to adjust the initial risk level based on the distribution of abnormal data, it includes: the early warning unit determines the abnormal center point according to the location where the abnormal data appears, calculates the distance between each abnormal data in the abnormal data and the abnormal center point and determines the maximum distance; when the maximum distance is greater than the distance threshold, the early warning unit determines to adjust the initial risk level to obtain the final risk level; when the maximum distance is less than or equal to the distance threshold, the early warning unit determines not to adjust the initial risk level, and uses the initial risk level as the final risk level. It can be understood that the distance threshold can be set according to the actual monitoring sensitivity requirements. The preferred value of the distance threshold is 1 / 3 of the length or width of the equipment.

[0092] In some embodiments of the present application, when the early warning unit determines to adjust the initial risk level to obtain the final risk level, the early warning unit determines the distance difference according to the maximum distance and the distance threshold, the distance difference is the difference between the maximum distance and the distance threshold, the early warning unit compares the distance difference with the limited distance, and adjusts the initial risk level according to the comparison result to obtain the final risk level;

[0093] Specifically, the limited distance can be set according to the size of the equipment itself. When the distance difference is less than or equal to the limited distance, the early warning unit will increase the initial risk level by one level to obtain the final risk level; when the distance difference is greater than the limited distance, the early warning unit will increase the initial risk level by two levels to obtain the final risk level.

[0094] Specifically, the early warning unit first determines an abnormal center point based on the location where the abnormal data appears. This point usually represents the gathering center of the abnormal data. Subsequently, the system calculates the distance between all abnormal data and the center point, and finds the maximum distance, which is used as the basis for evaluating the distribution of abnormal data. When the maximum distance is greater than the distance threshold, the early warning unit determines that the distribution of abnormal data is relatively scattered and the distribution area of ​​abnormal data is large, indicating that there is a problem with a large area of ​​the equipment. Therefore, the initial risk level is adjusted significantly to obtain the final risk level. When the maximum distance is less than or equal to the distance threshold, it means that the distribution of abnormal data is relatively concentrated and the abnormal area of ​​the equipment is small. The early warning unit makes a small adjustment to maintain the initial risk level.

[0095] It is understandable that by calculating the distance between the abnormal data and the center point, the severity and dispersion of the abnormal situation can be effectively judged. By setting the distance threshold and the limited distance, a risk adjustment mechanism is formed, so that the early warning system can respond dynamically according to the actual data situation, ensuring timely detection and response to potential risks.

[0096] In the above embodiment, the sensor module integrates vibration, temperature and humidity sensors, which can fully capture the operating status of the equipment and ensure the monitoring accuracy under various environmental conditions. The monitoring module automatically analyzes the sensor data through the acquisition, processing and judgment units, and generates data fluctuation values ​​and fluctuation thresholds in real time. Automated data processing reduces manual intervention and reduces the false alarm rate. The isolation forest model effectively identifies abnormal data and provides an accurate basis for equipment failure warning. Finally, the abnormal data is compared with the historical data before the warning is issued, which further enhances the accuracy of the warning, reduces maintenance costs, and enhances the safety and reliability of the equipment.

[0097] 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 take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take 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.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the 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 produce 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.

[0099] 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.

[0100] 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 A step that specifies a function in one or more boxes.

[0101] 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. A multi-sensor based equipment operation status monitoring system, characterized in that: include: Sensor modules and monitoring modules; The sensor module includes a vibration sensor, a temperature sensor and a humidity sensor, and the sensor module is arranged in the device to be monitored; The monitoring module is electrically connected to the sensor module, and the monitoring module includes a collection unit, a processing unit, a judgment unit, an early warning unit and a storage unit; The acquisition unit is configured to acquire operation data of each sensor in the sensor module, establish a data group according to the operation data, the data group includes the operation data of each sensor in the sensor module at a current moment and the operation data of each sensor in the sensor module at a previous moment, and obtain the data fluctuation value of the sensor module according to the data group; The processing unit is configured to collect historical normal operation data in the storage unit, and obtain a data fluctuation threshold of the sensor module according to the historical normal operation data; The judgment unit is configured to filter the data fluctuation value according to the data fluctuation threshold, calculate the abnormal value of the filtered data based on the isolation forest model, and determine the abnormal data according to the abnormal value; The early warning unit is configured to calculate the similarity between the abnormal data and the historical abnormal operation data in the storage unit according to the data type, data value and number of each type of abnormal data of the abnormal data, and issue an early warning to the device to be monitored according to the similarity; When the early warning unit calculates the similarity between the abnormal data and the historical abnormal operation data in the storage unit according to the data type, data value and number of each type of abnormal data of the abnormal data, it includes: Wherein, X represents the number of data types of abnormal data, Y represents the maximum data value in the abnormal data, Z represents the total number of abnormal data, Xi represents the number of data types of the i-th group of data in the historical abnormal operation data, Yi represents the maximum data value of the i-th group of data in the historical abnormal operation data, Zi represents the total number of the i-th group of data in the historical abnormal operation data, and Si represents the similarity between the abnormal data and the i-th group of data in the historical abnormal operation data; When the early warning unit issues an early warning to the device to be monitored according to the similarity, it includes: When there is data in the historical abnormal operation data whose similarity with the abnormal data is greater than the similarity threshold, the early warning unit issues an early warning according to the historical early warning level corresponding to the historical abnormal operation data; when there is no data in the historical abnormal operation data whose similarity with the abnormal data is greater than the similarity threshold, the early warning unit obtains the maximum data fluctuation value according to the abnormal data, determines the initial risk level according to the maximum data fluctuation value, and determines whether to adjust the initial risk level according to the abnormal data distribution to determine the final risk level; When the early warning unit issues an early warning according to the historical early warning level corresponding to the historical abnormal operation data, it includes: When the historical abnormal operation data and the abnormal data have a similarity greater than a similarity threshold, the early warning unit uses the historical early warning level corresponding to the historical abnormal operation data as the final risk level to issue an early warning to the device to be monitored; When the data whose similarity between the historical abnormal operation data and the abnormal data is greater than the similarity threshold is not unique, if the corresponding historical warning levels are the same, the warning unit will use the corresponding historical warning level as the final risk level to warn the equipment to be monitored; if the corresponding historical warning levels are different, the warning unit will use the highest historical warning level among the corresponding historical warning levels as the final risk level to warn the equipment to be monitored.

2. The multi-sensor based equipment operation status monitoring system according to claim 1, characterized in that: When the processing unit obtains the data fluctuation threshold of the sensor module according to the historical normal operation data, it includes: Y=μW+k·σW; Among them, Y represents the data fluctuation threshold, μW represents the fluctuation mean of the historical normal operation data, σW represents the fluctuation standard deviation of the historical normal operation data, and k represents the adjustment factor; Wt=|X t -X t-1 |; Among them, Wt represents the data fluctuation value of historical normal operation data, X t represents the operating data of the sensor at time t, X t-1 represents the operating data of the sensor at time t-1, and N represents the number of historical normal operating data.

3. The multi-sensor based equipment operation status monitoring system according to claim 1, characterized in that: When the judgment unit screens the data fluctuation value according to the data fluctuation threshold, it includes: Compare the data fluctuation value with the data fluctuation threshold value to eliminate small fluctuation data; When the data fluctuation value is greater than the data fluctuation threshold, retaining the fluctuation data; When the data fluctuation value is less than or equal to the data fluctuation threshold, the fluctuation data is determined to be small fluctuation data and is eliminated.

4. The multi-sensor based equipment operation status monitoring system according to claim 3 is characterized in that: The judging unit calculates the outlier value of the filtered data based on the isolation forest model, and determines the abnormal data according to the outlier value, including: Calculate the outlier value of each filtered data based on the isolation forest model; Where s(a) represents the outlier of data a, E(h(a)) represents the average path length of data a in all isolated trees in the isolation forest, and c(n) represents the average path length used to standardize the path length; When the abnormal value of the filtered data is greater than 0.8, the data is determined to be the abnormal data, and the sensor type corresponding to the abnormal data is identified.

5. The multi-sensor based equipment operation status monitoring system according to claim 1, characterized in that: When the early warning unit determines the initial risk level according to the maximum data fluctuation value, it includes: The early warning unit compares the maximum data fluctuation value with a first preset data fluctuation value and a second preset data fluctuation value respectively, and determines an initial risk level according to the comparison result; the first preset data fluctuation value is smaller than the second preset data fluctuation value; When the maximum data fluctuation value is less than or equal to a first preset data fluctuation value, the early warning unit determines that the initial risk level is the third risk level; when the maximum data fluctuation value is greater than the first preset data fluctuation value and less than or equal to the second preset data fluctuation value, the early warning unit determines that the initial risk level is the second risk level; when the maximum data fluctuation value is greater than the second preset data fluctuation value, the early warning unit determines that the initial risk level is the first risk level; the first risk level is greater than the second risk level, and the second risk level is greater than the third risk level.

6. The multi-sensor based equipment operation status monitoring system according to claim 5, characterized in that: When the early warning unit determines whether to adjust the initial risk level according to the abnormal data distribution, it includes: The early warning unit determines the abnormal center point according to the location where the abnormal data appears, calculates the distance between each abnormal data in the abnormal data and the abnormal center point and determines the maximum distance; when the maximum distance is greater than a distance threshold, the early warning unit determines to adjust the initial risk level to obtain the final risk level; when the maximum distance is less than or equal to the distance threshold, the early warning unit determines not to adjust the initial risk level, and uses the initial risk level as the final risk level.

7. The multi-sensor based equipment operation status monitoring system according to claim 6, characterized in that: When the early warning unit determines to adjust the initial risk level to obtain the final risk level, it includes: The early warning unit determines a distance difference according to the maximum distance and the distance threshold, the distance difference being the difference between the maximum distance and the distance threshold, the early warning unit compares the distance difference with the limited distance, and adjusts the initial risk level according to the comparison result to obtain the final risk level; When the distance difference is less than or equal to the limited distance, the early warning unit increases the initial risk level by one level to obtain the final risk level; when the distance difference is greater than the limited distance, the early warning unit increases the initial risk level by two levels to obtain the final risk level.

Images