A method and system for monitoring industrial Internet of Things equipment based on data analysis

Abstract

The present invention relates to the field of industrial Internet of Things equipment monitoring technology, and specifically discloses an industrial Internet of Things equipment monitoring method and system based on data analysis. The present invention relates to a method and device for improving the data processing capability and energy efficiency of an industrial Internet of Things monitoring system. In view of the problem that the existing monitoring system can only process a single type of data and the monitoring accuracy is not high, the present invention proposes a monitoring strategy that comprehensively considers multiple factors, which can effectively improve the accuracy of anomaly detection and the optimization capability of equipment operation status. By collecting multiple types of equipment data, a deep learning model is used to fuse the data, and anomaly detection and predictive maintenance are performed based on the fused data. The present invention can significantly improve the performance of the monitoring system, reduce energy consumption, and is suitable for remote monitoring and fault warning of various industrial equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things equipment monitoring, and in particular to an industrial Internet of Things equipment monitoring method and system based on data analysis. Background Art

[0002] With the development of industry, more and more factories have begun to adopt Industrial Internet of Things (IIoT) technology to improve production efficiency, reduce costs and improve product quality. The core of IIoT is to collect a large amount of real-time data through sensors and network connections, and use big data analysis technology to process these data to achieve intelligent management. Among them, the monitoring of equipment energy consumption and output is particularly important because it is directly related to production costs and efficiency. At present, most Industrial Internet of Things monitoring systems can only achieve basic data collection and simple statistical analysis, and cannot effectively identify abnormal changes in equipment operation status, especially abnormalities in energy efficiency, which makes it difficult to adjust production strategies in time to optimize overall operating efficiency.

[0003] Existing industrial Internet of Things monitoring systems mainly collect real-time data from equipment through sensors and use statistical methods or machine learning algorithms to analyze data to achieve basic monitoring of equipment status. However, these systems can usually only process a single type of data and lack the ability to comprehensively consider multiple factors. In addition, the monitoring accuracy of energy efficiency is not high, making it difficult to provide effective optimization suggestions to improve equipment operation status.

[0004] The present invention aims to solve the problems existing in the prior art and proposes a new data analysis industrial Internet of Things equipment monitoring method. The method obtains the energy consumption value and output data of the equipment, calculates the energy efficiency of the equipment, further analyzes its abnormal conditions, and finally obtains the optimal operating load of the equipment. Summary of the invention

[0005] The purpose of the present invention is to provide an industrial Internet of Things equipment monitoring method and system based on data analysis to solve the above-mentioned problems.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method and system for monitoring industrial Internet of Things equipment based on data analysis, comprising the following steps:

[0008] Obtain the energy consumption value and output data of the equipment, and obtain the mean and standard deviation of the energy efficiency of the equipment;

[0009] The mean and standard deviation of the energy efficiency of the equipment to obtain the anomaly score of energy efficiency;

[0010] Based on the anomaly score of energy efficiency, an energy efficiency anomaly signal and an energy efficiency no anomaly signal are generated;

[0011] Based on the energy efficiency abnormality signal, the operating load is analyzed to generate an operating load abnormality signal and an operating load normal signal;

[0012] Based on the abnormal operating load signal, analyze the energy efficiency under different operating loads to obtain the optimal operating load of the equipment;

[0013] Based on the optimal operating load of the equipment, the target speed of the equipment motor is obtained;

[0014] The energy efficiency of the equipment is regulated based on the target speed of the equipment motor.

[0015] As a further solution of the present invention: the process of obtaining the mean value and standard deviation of the energy efficiency of the equipment is:

[0016] Divide the monitoring cycle into a number of time sub-units of equal length, and obtain the energy consumption value and product output data of the equipment in each time sub-unit;

[0017] Calculate the ratio of product output data to energy consumption value to obtain the energy efficiency of the equipment within the time sub-unit;

[0018] Integrate the energy efficiency of all time sub-units to obtain the energy efficiency group of the equipment;

[0019] Based on the energy efficiency group, the mean energy efficiency of the equipment is obtained through the mean calculation formula;

[0020] Based on the mean value of the energy efficiency of the equipment, the energy efficiency group is processed using the standard deviation calculation formula to obtain the standard deviation of the energy efficiency of the equipment.

[0021] As a further solution of the present invention: the process of obtaining the abnormal score of energy efficiency is:

[0022] Calculate the difference between the energy efficiency of the equipment and the mean energy efficiency to obtain the difference between the energy efficiency and the mean energy efficiency;

[0023] The difference between the energy efficiency and the mean of the energy efficiency is ratioed with the standard deviation of the energy efficiency to obtain the abnormal score of the energy efficiency.

[0024] As a further solution of the present invention: the generation process of the energy efficiency abnormal signal and the energy efficiency normal signal is:

[0025] comparing the energy efficiency anomaly score to an energy efficiency anomaly score threshold;

[0026] If the energy efficiency anomaly score is greater than or equal to the energy efficiency anomaly score threshold, it means that the energy efficiency of the device is abnormal, and an energy efficiency anomaly signal is generated;

[0027] If the energy efficiency anomaly score is less than the energy efficiency anomaly score threshold, it means that the energy efficiency of the device is normal, and an energy efficiency normal signal is generated.

[0028] As a further solution of the present invention: the process of operating load analysis is:

[0029] Based on the abnormal operating load signal, the actual output power of the equipment when the time subunit is in the middle moment is obtained;

[0030] The actual output power of the device when the time sub-unit is in the middle moment is calculated by ratio with the theoretical maximum output power of the device to obtain the operating load of the device in the time sub-unit;

[0031] Integrate the operating loads in all time sub-units to obtain the equipment operating load group;

[0032] Use the mean value calculation formula to process the equipment's operating load group to obtain the average load of the equipment during the monitoring period;

[0033] Based on the average load of the equipment during the monitoring period, the operating load group of the equipment is processed using the standard deviation formula to obtain the standard deviation of the operating load of the equipment during the monitoring period.

[0034] As a further solution of the present invention: the generation process of the abnormal operation load signal and the normal operation load signal is as follows:

[0035] Based on the average load and operating load standard deviation of the equipment in the monitoring period, the operating load of the equipment in the time subunit and the average load of the equipment in the monitoring period are calculated to obtain the difference between the operating load and the average load;

[0036] The difference between the average load and the average load is calculated by the ratio with the standard deviation of the operating load to obtain the standard value of the operating load;

[0037] comparing the standard value of the operating load with a threshold value of the standard value of the operating load;

[0038] If the standard value of the operating load is greater than or equal to the threshold value of the standard value of the operating load, an operating load abnormality signal is generated;

[0039] If the standard value of the operating load is less than the threshold value of the standard value of the operating load, a normal operating load signal is generated.

[0040] As a further solution of the present invention: the analysis process of energy efficiency under different operating loads is:

[0041] Based on the abnormal signal of the equipment's operating load, the formula Obtain the coefficient b1 of energy efficiency and operating load, where FH is the operating load of the equipment in the time subunit, PX is the energy efficiency of the equipment in the time subunit, n is the number of time subunits, i is the number of time subunits, i=1,2,...,n;

[0042] Based on the coefficient b1, through the formula Obtain the coefficient b2 of energy efficiency and operating load;

[0043] The predicted value PXY of energy efficiency of the equipment under different operating loads is obtained through the formula PXY=b1+b2×FH.

[0044] As a further solution of the present invention: the process of obtaining the optimal operating load of the equipment is:

[0045] Based on the predicted values ​​of energy efficiency under different operating loads, a scatter plot of operating load and energy efficiency is drawn with operating load as the horizontal axis and energy efficiency as the vertical axis;

[0046] Based on the scatter plot of operating load and energy efficiency, the operating load with the highest energy efficiency is obtained by identifying the scatter plot, which is recorded as the optimal operating load of the equipment.

[0047] As a further solution of the present invention: an industrial Internet of Things equipment monitoring system based on data analysis, characterized in that it includes a data acquisition module, an energy efficiency analysis module, an operation load analysis module and an equipment control module;

[0048] The data acquisition module is used to obtain the energy consumption value and output data of the equipment, and obtain the mean value and standard deviation of the energy efficiency of the equipment;

[0049] The mean and standard deviation of the energy efficiency of the equipment to obtain the anomaly score of energy efficiency;

[0050] The energy efficiency analysis module generates energy efficiency abnormality signals and energy efficiency normal signals based on the abnormality scores of energy efficiency;

[0051] The operation load analysis module analyzes the operation load based on the energy efficiency abnormality signal and generates an operation load abnormality signal and an operation load normal signal;

[0052] Based on the abnormal operating load signal, analyze the energy efficiency under different operating loads to obtain the optimal operating load of the equipment;

[0053] The equipment control module obtains the target speed of the equipment motor based on the optimal operating load of the equipment and controls the equipment.

[0054] As a further solution of the present invention: a computer-readable medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the method as described in any one of claims 1-8 are executed.

[0055] Beneficial effects of the present invention:

[0056] (1) The present invention has made significant progress in data processing capabilities. By optimizing and innovating traditional data processing algorithms, the present invention can efficiently process large amounts of data from different sensors and accurately identify key information therein. This improvement not only speeds up data processing, but also greatly improves the accuracy of data, enabling the system to respond to various abnormal situations more quickly, reduce false alarm rates, and improve the timeliness and effectiveness of decision-making. For example, in the field of industrial automation, this high-precision data processing capability can help factories monitor the status of production lines in real time and quickly identify potential problems, thereby effectively avoiding production interruptions and ensuring production efficiency. In addition, in terms of energy consumption management, the present invention adopts advanced energy consumption management strategies, which can minimize energy consumption while ensuring the normal operation of the system. This low-power design not only helps to save energy and reduce emissions, but also reduces the cost of long-term operation. It is particularly important for application scenarios that require long-term uninterrupted work, such as data centers, intelligent building management systems, etc. By adopting technical means such as dynamic workload adjustment and intelligent power management, the present invention can automatically adjust the energy consumption level according to actual needs, ensuring the stability and reliability of the system while also achieving the goal of sustainable development.

[0057] (2) In terms of anomaly detection, the present invention can identify abnormal signals in complex patterns, thereby improving the accuracy and reliability of anomaly detection. The application of this technology not only reduces false alarms, but also can promptly detect possible problems and effectively prevent accidents. In addition, by introducing predictive maintenance functions, the present invention can detect potential failure risks in advance, thereby reducing unplanned downtime and reducing maintenance costs. This maintenance method changes the traditional regular inspection and maintenance mode and adopts a state-based maintenance strategy, which not only improves the availability of equipment, but also greatly reduces production losses caused by equipment failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present invention will be further described below in conjunction with the accompanying drawings.

[0059] Figure 1 It is a flow chart of an industrial Internet of Things equipment monitoring method based on data analysis of the present invention;

[0060] Figure 2It is a flow chart of generating energy efficiency abnormality signal and energy efficiency non-abnormality signal in an industrial Internet of Things equipment monitoring method based on data analysis of the present invention;

[0061] Figure 3 It is a flow chart of an industrial Internet of Things equipment monitoring system based on data analysis of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Example 1

[0064] See also Figure 1 As shown, the present invention is a method for monitoring industrial Internet of Things equipment based on data analysis, comprising the following steps:

[0065] Obtain the energy consumption value and output data of the equipment to obtain the energy efficiency group of the equipment;

[0066] Based on the energy efficiency group of the equipment, the mean and standard deviation of the energy efficiency of the equipment are obtained;

[0067] Based on the mean and standard deviation of the energy efficiency of the equipment, the energy efficiency anomaly score is obtained;

[0068] Based on the anomaly score of energy efficiency, an energy efficiency anomaly signal and an energy efficiency no anomaly signal are generated;

[0069] Based on the energy efficiency abnormality signal, the operating load is analyzed to generate an operating load abnormality signal and an operating load normal signal;

[0070] Based on the abnormal operating load signal, analyze the energy efficiency under different operating loads to obtain the optimal operating load of the equipment;

[0071] Based on the optimal operating load of the equipment, the target speed of the equipment motor is obtained and the equipment is regulated.

[0072] Example 2

[0073] See also Figure 2 As shown, the monitoring period is divided into a number of time sub-units of equal length, and the energy consumption value and product output data of the equipment in each time sub-unit are obtained;

[0074] By calculating the ratio of product output data to energy consumption value, the energy efficiency PX of the equipment in the time sub-unit is obtained;

[0075] Integrate the energy efficiencies of all time sub-units to obtain the energy efficiency group of the equipment;

[0076] The energy efficiency group is processed according to the mean calculation formula to obtain the mean energy efficiency PXj of the equipment;

[0077] The energy efficiency group is processed according to the standard deviation calculation formula to obtain the energy efficiency standard deviation PXs of the equipment;

[0078] By formula Get the anomaly score PXZ of energy efficiency;

[0079] Compare the outlier score PXZ of energy efficiency with the outlier threshold;

[0080] If the energy efficiency anomaly score PXZ is greater than or equal to the anomaly threshold, it means that the energy efficiency of the device is abnormal, and an energy efficiency anomaly signal is generated;

[0081] If the energy efficiency anomaly score PXZ is less than the anomaly threshold, it means that the energy efficiency of the device is normal, and an energy efficiency normal signal is generated;

[0082] It should be noted that the abnormal energy efficiency signal means that the energy efficiency of the equipment is low during operation. The low energy efficiency of industrial equipment will lead to a series of problems such as increased production costs, weakened corporate competitiveness, and increased environmental pollution. These problems not only have a negative impact on the company itself, but also impose a burden on the equipment and the environment.

[0083] Example 3

[0084] Based on the energy efficiency abnormality signal of the equipment generated above, since the abnormal operation load of the equipment will lead to the abnormal energy efficiency of the equipment, it is analyzed and judged whether the operation load of the equipment is related to the abnormal energy efficiency of the equipment. If there is a relationship of the operation load, it is convenient to adjust the operation load in time during the subsequent operation of the equipment to reduce the impact of the operation load of the equipment on the energy efficiency, effectively improve the energy efficiency of the equipment, and then improve the energy utilization rate of the equipment. Specifically:

[0085] Obtain the theoretical maximum output power of the device and the actual output power of the device when the time subunit is in the middle moment;

[0086] Calculate the ratio of the actual output power of the equipment when the time sub-unit is in the middle moment to the theoretical maximum output power of the equipment to obtain the operating load FH of the equipment in the time sub-unit;

[0087] Integrate all operating loads within the monitoring period to obtain the equipment operating load group;

[0088] The equipment's operating load group is processed according to the mean calculation formula to obtain the equipment's average load FHP during the monitoring period;

[0089] The equipment's operating load group is processed according to the standard deviation formula to obtain the standard deviation FHC of the equipment's operating load during the monitoring period;

[0090] Based on the average load FHP and standard deviation FHC of the operating load, the formula Calculate the standard value FZB of the operating load;

[0091] Compare the standard value FZB of the operating load of the equipment during the monitoring period with the threshold value of the operating load;

[0092] If the standard value FZB of the equipment's operating load during the monitoring period is greater than or equal to the threshold value of the operating load, it means that the operating load exceeds the normal range, and an abnormal operating load signal is generated;

[0093] If the standard value FZB of the operating load of the equipment during the monitoring period is less than the threshold value of the operating load, it means that the operating load is within the normal range, and a normal operating load signal is generated.

[0094] Example 4

[0095] Based on the above-mentioned abnormal load signals, by analyzing the energy efficiency under different loads, more refined load management can be achieved and energy can be ensured to be used effectively, which can bring significant cost savings and productivity improvements to enterprises while reducing environmental pollution and resource consumption;

[0096] Analyze the energy efficiency under different operating loads, specifically:

[0097] Based on the energy efficiency group of the equipment and the operating load group of the equipment, the formula Obtain the coefficient b1 of energy efficiency and operating load, where n is the number of time subunits, i is the number of time subunits, i=1,2,...,n;

[0098] Based on the coefficient b1, through the formula Obtain the coefficient b2 of energy efficiency and operating load;

[0099] The energy efficiency prediction value PXY of the equipment under different operating loads is obtained through the formula PXY=b1+b2×FH;

[0100] Based on the predicted value PXY of energy efficiency under different operating loads, a scatter plot of operating load and energy efficiency is drawn with operating load as the horizontal axis and energy efficiency as the vertical axis;

[0101] Based on the scatter plot of operating load and energy efficiency, find out the operating load with the highest energy efficiency FHyou and the operating load with the lowest energy efficiency FHcha;

[0102] Based on the most energy-efficient operating load FHyou, obtain the theoretical maximum speed ZSmax of the equipment motor;

[0103] The target speed of the equipment motor is calculated by the formula ZS=FHyou×ZSmax;

[0104] It should be noted that there is a direct relationship between motor speed and operating load. When the motor speed increases, the output power of the equipment will usually increase, thereby increasing the operating load. Conversely, reducing the motor speed will reduce the output power of the equipment, thereby reducing the operating load. By adjusting the speed of the equipment motor to the target speed, the operating load of the equipment can be adjusted to the optimal operating load, thereby achieving the purpose of optimizing the energy efficiency of the equipment.

[0105] Example 5

[0106] See also Figure 3 As shown, an industrial Internet of Things equipment monitoring system based on data analysis is characterized by comprising a data acquisition module, an energy efficiency analysis module, an operation load analysis module and an equipment control module;

[0107] The data acquisition module is used to obtain the energy consumption value and output data of the equipment, and obtain the mean value and standard deviation of the energy efficiency of the equipment;

[0108] The mean and standard deviation of the energy efficiency of the equipment to obtain the anomaly score of energy efficiency;

[0109] The energy efficiency analysis module generates energy efficiency abnormality signals and energy efficiency normal signals based on the abnormality scores of energy efficiency;

[0110] The operation load analysis module analyzes the operation load based on the energy efficiency abnormality signal and generates an operation load abnormality signal and an operation load normal signal;

[0111] Based on the abnormal operating load signal, analyze the energy efficiency under different operating loads to obtain the optimal operating load of the equipment;

[0112] The equipment control module obtains the target speed of the equipment motor based on the optimal operating load of the equipment and controls the equipment.

[0113] Example 6

[0114] A computer-readable medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the method described in any one of Examples 1-4 are executed.

[0115] Working principle of the present invention: The present invention has made significant progress in data processing capabilities. By optimizing and innovating traditional data processing algorithms, the present invention can efficiently process a large amount of data from different sensors and accurately identify key information therein. This improvement not only speeds up the data processing speed, but also greatly improves the accuracy of the data, so that the system can respond to various abnormal situations more quickly, reduce the false alarm rate, and improve the timeliness and effectiveness of decision-making. For example, in the field of industrial automation, this high-precision data processing capability can help factories monitor the status of production lines in real time and quickly identify potential problems, thereby effectively avoiding production interruptions and ensuring production efficiency. In addition, in terms of energy consumption management, the present invention adopts advanced energy consumption management strategies, which can minimize energy consumption while ensuring the normal operation of the system. This low-power design not only helps to save energy and reduce emissions, but also reduces the cost of long-term operation. It is particularly important for application scenarios that require long-term uninterrupted work, such as data centers, intelligent building management systems, etc. By adopting technical means such as dynamic adjustment of workloads and intelligent power management, the present invention can automatically adjust the energy consumption level according to actual needs, ensuring the stability and reliability of the system while also achieving the goal of sustainable development;

[0116] In terms of anomaly detection, the present invention can identify abnormal signals in complex patterns, thereby improving the accuracy and reliability of anomaly detection. The application of this technology not only reduces false alarms, but also can promptly discover possible problems and effectively prevent accidents. In addition, by introducing predictive maintenance functions, the present invention can detect potential failure risks in advance, thereby reducing unplanned downtime and reducing maintenance costs. This maintenance method changes the traditional regular inspection and maintenance mode and adopts a state-based maintenance strategy, which not only improves the availability of equipment, but also greatly reduces production losses caused by equipment failures.

[0117] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A data analysis industrial Internet of Things equipment monitoring method, characterized in that: The following steps are involved: Obtain the energy consumption value and output data of the equipment, and obtain the mean and standard deviation of the energy efficiency of the equipment; Based on the mean and standard deviation of the energy efficiency of the equipment, the energy efficiency anomaly score is obtained; The abnormal scores of energy efficiency are processed to obtain energy efficiency abnormal signals and energy efficiency normal signals; Based on the energy efficiency abnormality signal, the operating load is analyzed to generate an operating load abnormality signal and an operating load normal signal; Based on the abnormal operating load signal, analyze the energy efficiency under different operating loads to obtain the optimal operating load of the equipment; According to the optimal operating load of the equipment, the target speed of the equipment motor is obtained to complete the regulation of the energy efficiency of the equipment. The process of obtaining the mean and standard deviation of the energy efficiency of the equipment is as follows: Divide the monitoring cycle into a number of time sub-units of equal length, and obtain the energy consumption value and product output data of the equipment in each time sub-unit; Calculate the ratio of product output data to energy consumption value to obtain the energy efficiency of the equipment within the time sub-unit; Integrate the energy efficiency of all time sub-units to obtain the energy efficiency group of the equipment; Based on the energy efficiency group, the mean energy efficiency of the equipment is obtained through the mean calculation formula; The energy efficiency group is processed by the standard deviation calculation formula to obtain the energy efficiency standard deviation of the equipment; The process of obtaining the anomaly score of energy efficiency is: Calculate the difference between the energy efficiency of the equipment and the mean energy efficiency to obtain the difference between the energy efficiency and the mean energy efficiency; The energy efficiency anomaly score is calculated by multiplying the difference between the energy efficiency and the mean of the energy efficiency with the standard deviation of the energy efficiency; The process for running a load analysis is: Obtain the actual output power of the device when the time subunit is in the middle moment; The actual output power of the device when the time sub-unit is in the middle moment is calculated by ratio with the theoretical maximum output power of the device to obtain the operating load of the device in the time sub-unit; Integrate the operating loads in all time sub-units to obtain the equipment operating load group; Use the mean value calculation formula to process the equipment's operating load group to obtain the average load of the equipment during the monitoring period; Based on the average load of the equipment during the monitoring period, the standard deviation formula is used to process the equipment's operating load group to obtain the standard deviation of the equipment's operating load during the monitoring period; The generation process of the abnormal operation load signal and the normal operation load signal is as follows: Based on the average load and operating load standard deviation of the equipment in the monitoring period, the operating load of the equipment in the time subunit and the average load of the equipment in the monitoring period are calculated to obtain the difference between the operating load and the average load; The difference between the average load and the average load is multiplied by the standard deviation of the operating load to obtain the standard value of the operating load; comparing the standard value of the operating load with a threshold value of the standard value of the operating load; If the standard value of the operating load is greater than or equal to the threshold value of the standard value of the operating load, an operating load abnormality signal is generated; If the standard value of the operating load is less than the threshold value of the standard value of the operating load, a normal operating load signal is generated; The analysis process of energy efficiency under different operating loads is as follows: Based on the abnormal signal of the equipment's operating load, the formula Obtain the coefficient b1 of energy efficiency and operating load, where FH is the operating load of the equipment in the time subunit, PX is the energy efficiency of the equipment in the time subunit, n is the number of time subunits, i is the number of time subunits, i = 1, 2, ..., n; Based on the coefficient b1, through the formula Obtain the coefficient b2 of energy efficiency and operating load; The energy efficiency prediction value PXY of the equipment under different operating loads is obtained through the formula PXY=b1+b2×FH; The process of obtaining the optimal operating load of the equipment is: Based on the predicted values ​​of energy efficiency under different operating loads, a scatter plot of operating load and energy efficiency is drawn with operating load as the horizontal axis and energy efficiency as the vertical axis; Based on the scatter plot of operating load and energy efficiency, the operating load with the highest energy efficiency is obtained by identifying the scatter plot, which is recorded as the optimal operating load of the equipment.

2. According to the data analysis industrial Internet of Things equipment monitoring method of claim 1, it is characterized in that: The generation process of energy efficiency abnormal signal and energy efficiency normal signal is as follows: comparing the energy efficiency anomaly score to an energy efficiency anomaly score threshold; If the energy efficiency anomaly score is greater than or equal to the energy efficiency anomaly score threshold, it means that the energy efficiency of the device is abnormal, and an energy efficiency anomaly signal is generated; If the energy efficiency anomaly score is less than the energy efficiency anomaly score threshold, it means that the energy efficiency of the device is normal, and an energy efficiency normal signal is generated.

3. A data analysis industrial Internet of Things equipment monitoring system, characterized in that: The system is used to execute the method described in any one of claims 1 to 2 above, and the system includes a data acquisition module, an energy efficiency analysis module, an operation load analysis module and an equipment control module; The data acquisition module is used to obtain the energy consumption value and output data of the equipment, and obtain the mean value and standard deviation of the energy efficiency of the equipment; The mean and standard deviation of the energy efficiency of the equipment to obtain the anomaly score of energy efficiency; The energy efficiency analysis module generates energy efficiency abnormality signals and energy efficiency normal signals based on the abnormality scores of energy efficiency; The operation load analysis module analyzes the operation load based on the energy efficiency abnormality signal and generates an operation load abnormality signal and an operation load normal signal; Based on the abnormal operating load signal, analyze the energy efficiency under different operating loads to obtain the optimal operating load of the equipment; The equipment control module obtains the target speed of the equipment motor based on the optimal operating load of the equipment and controls the equipment.

4. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 2 are executed.

Images