Carbon emission monitoring equipment operation and maintenance method and system based on the Internet of Things

Abstract

This application relates to the field of carbon emission monitoring and discloses a carbon emission monitoring equipment operation and maintenance method and system based on the Internet of Things. The method includes: obtaining multiple time series acquisition results of acquisition equipment within a target area based on the Internet of Things, clustering the multiple time series acquisition results according to production scheduling characteristics, obtaining multiple time series acquisition result clusters and production scheduling characteristics corresponding to each time series acquisition result cluster, each time series acquisition result cluster including multiple time series acquisition results with similar production scheduling characteristics; determining the time series change characteristics of each time series acquisition result, and determining the distinguishing state characteristics of each time series acquisition result relative to the production scheduling characteristics of the time series acquisition result cluster to which it belongs; determining abnormal time series acquisition results based on the time series change characteristics and the distinguishing state characteristics through an anomaly detection model, and prompting the acquisition equipment corresponding to the abnormal time series acquisition results to be repaired. This application can efficiently monitor carbon emission activity level monitoring equipment.

Description

Technical Field

[0001] The present application relates to the field of carbon emission monitoring technology, and more specifically, to an operation and maintenance method and system for carbon emission monitoring equipment based on the Internet of Things. Background Art

[0002] Carbon emission activity monitoring equipment is widely used in various fields, including industrial production, transportation, and energy, to monitor and record carbon emissions data in real time. By utilizing sensors, data acquisition systems, and network transmission technologies, these equipment can accurately capture the activity levels of carbon emission sources and upload these data to a central carbon emissions management system, providing a scientific basis for quantitative carbon emissions analysis and the development of emission reduction strategies.

[0003] Although carbon emission activity level monitoring equipment plays an important role in carbon emission monitoring, its operation and maintenance process faces many challenges. The operating environment of carbon emission activity level monitoring equipment is often harsh, especially in environments with high temperature, high humidity, or corrosive gases. Sensors and data acquisition systems are easily damaged, resulting in data distortion or equipment failure. Due to the wide distribution of carbon emission monitoring equipment, operation and maintenance personnel need to conduct regular inspections and maintenance to ensure the normal operation of the equipment. Traditional manual inspections of carbon emission activity level monitoring equipment are inefficient and difficult to cover all equipment, which is prone to missed inspections or delayed maintenance. As carbon emission activity level monitoring equipment ages, hardware aging, and software updates are not timely, the performance of carbon emission activity level monitoring equipment and the accuracy of monitoring data can also be affected. Therefore, how to improve the operation and maintenance efficiency and reliability of carbon emission activity level monitoring equipment through intelligent means has become a key issue in current technology research and development and application. Summary of the Invention

[0004] The purpose of this application is to provide a carbon emission monitoring equipment operation and maintenance method and system based on the Internet of Things, which solves the technical problem of difficulty in efficiently monitoring carbon emission activity level monitoring equipment and achieves the technical effect of efficiently monitoring carbon emission activity level monitoring equipment.

[0005] An embodiment of the present application provides an operation and maintenance method for carbon emission monitoring equipment based on the Internet of Things, which includes: obtaining multiple time series acquisition results of a collection device in a target area based on the Internet of Things, clustering the multiple time series acquisition results according to production scheduling characteristics, and obtaining multiple time series acquisition result clusters and production scheduling characteristics corresponding to each time series acquisition result cluster, each time series acquisition result cluster including multiple time series acquisition results with similar production scheduling characteristics; wherein the collection device is used to collect carbon emission activity level data; determining the time series change characteristics of each time series acquisition result, and determining the distinguishing state characteristics of each time series acquisition result relative to the production scheduling characteristics of the time series acquisition result cluster to which it belongs; through an anomaly detection model, determining abnormal time series acquisition results according to the time series change characteristics and the distinguishing state characteristics, and prompting the collection device corresponding to the abnormal time series acquisition result to be repaired.

[0006] In one possible implementation, determining the distinguishing state characteristics of each time series acquisition result relative to the production scheduling characteristics of the time series acquisition result cluster to which it belongs includes: determining the scheduling mutation point and scheduling cycle of the production scheduling characteristics of the time series acquisition result cluster to which each time series acquisition result belongs, and determining the acquisition result mutation point and acquisition result cycle of each time series acquisition result, determining the mutation distinguishing characteristics based on the scheduling mutation point and the acquisition result mutation point, and determining the acquisition cycle distinguishing characteristics based on the scheduling cycle and the acquisition result cycle, and determining the distinguishing state characteristics based on the mutation distinguishing characteristics and the acquisition cycle distinguishing characteristics of each time series acquisition result.

[0007] In another possible implementation, the distinguishing state feature is determined based on the mutation distinguishing feature and the acquisition cycle distinguishing feature of each time series acquisition result, including: determining the global mutation amplitude mean of the scheduling mutation points of all time series acquisition results in all time series acquisition result clusters, the distinguishing mutation amplitude mean corresponding to the scheduling mutation points of all time series acquisition results of each time series acquisition result cluster, and determining the ratio of the distinguishing mutation amplitude mean to the global mutation amplitude mean as the mutation feature weight of each time series acquisition result cluster; determining the global scheduling cycle mean of the scheduling cycle of all time series acquisition results of all time series acquisition result clusters, the acquisition result cycle mean of all time series acquisition results of each time series acquisition result cluster, and determining the ratio of the global scheduling cycle mean to the acquisition result cycle mean as the acquisition cycle feature weight of each time series acquisition result cluster; determining the sum of the product of the mutation distinguishing feature and the mutation feature weight, and the product of the acquisition cycle distinguishing feature and the acquisition cycle feature weight as the distinguishing state feature.

[0008] In another possible implementation, the method also includes: obtaining production schedule adjustment information corresponding to the collection devices in the target area based on the Internet of Things, determining the adjustment ratio of the production schedule adjustment in the collection devices corresponding to each time series collection result cluster, and determining the variance value of the production schedule adjustment of the collection devices corresponding to each time series collection result cluster; when the first adjustment ratio corresponding to the first time series collection result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series collection result cluster is greater than the preset variance value, the multiple time series collection results are re-clustered according to the production scheduling characteristics.

[0009] In another possible implementation, the method also includes: obtaining historical maintenance records of each collection device in the target area based on the Internet of Things, and determining the historical maintenance cycle of each collection device in the target area based on the historical maintenance records, and determining the average maintenance cycle of each collection device in the target area; determining the ratio of the historical maintenance cycle and the average maintenance cycle of each collection device as the maintenance factor of each collection device, and adjusting the distinguishing state feature by multiplying the maintenance factor by the distinguishing state feature.

[0010] In another possible implementation, the method also includes: when the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, the multiple time series acquisition results are re-clustered according to the production scheduling characteristics and maintenance factors.

[0011] In another possible implementation, the method also includes: obtaining the maintenance times of the acquisition equipment in the first time series acquisition result cluster within the historical time period, and determining the ratio of the maintenance times to the standard maintenance times as a maintenance times adjustment factor; multiplying the preset adjustment ratio corresponding to the first time series acquisition result cluster by the maintenance times adjustment factor to adjust the preset adjustment ratio corresponding to the first time series acquisition result cluster; and multiplying the preset variance value corresponding to the first time series acquisition result cluster by the maintenance times adjustment factor to adjust the preset variance value corresponding to the first time series acquisition result cluster.

[0012] In another possible implementation, the method further includes: determining a historical time period in which the acquisition equipment in the first time series acquisition result cluster was not maintained, and determining an average of the maintenance times of all time series acquisition result clusters in the historical time period as the standard maintenance times.

[0013] An embodiment of the present application also provides an Internet of Things-based carbon emission monitoring equipment operation and maintenance system, including a unit for executing any of the methods described above.

[0014] An embodiment of the present application also provides an Internet of Things-based carbon emission monitoring equipment operation and maintenance system, which implements any of the methods described above when the processor executes the computer program.

[0015] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in any one of the above items is implemented.

[0016] An embodiment of the present application further provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0017] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0018] An embodiment of the present application provides an operation and maintenance method for carbon emission monitoring equipment based on the Internet of Things, which includes: obtaining multiple time series acquisition results of a collection device in a target area based on the Internet of Things, clustering the multiple time series acquisition results according to production scheduling characteristics, and obtaining multiple time series acquisition result clusters and production scheduling characteristics corresponding to each time series acquisition result cluster, each time series acquisition result cluster including multiple time series acquisition results with similar production scheduling characteristics; wherein the collection device is used to collect carbon emission activity level data; determining the time series change characteristics of each time series acquisition result, and determining the distinguishing state characteristics of each time series acquisition result relative to the production scheduling characteristics of the time series acquisition result cluster to which it belongs; through an anomaly detection model, determining abnormal time series acquisition results according to the time series change characteristics and the distinguishing state characteristics, and prompting the collection device corresponding to the abnormal time series acquisition result to be repaired. The method in the embodiment of the present application can cluster multiple time series collection results according to production scheduling characteristics, and can determine abnormal time series collection results based on the time series change characteristics of the time series collection results and the distinguishing state characteristics of the time series collection results relative to the production scheduling characteristics of the time series collection result cluster to which they belong, thereby achieving accurate detection of abnormal time series collection results, improving the monitoring efficiency of carbon emission monitoring equipment, and enabling efficient monitoring of carbon emission monitoring equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A flowchart of an IoT-based carbon emission monitoring equipment operation and maintenance method provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a workflow of an IoT-based carbon emission monitoring equipment operation and maintenance method provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of a second method for operating and maintaining carbon emission monitoring equipment based on the Internet of Things provided in an embodiment of the present application;

[0023] Figure 4 A flowchart of a third method for operating and maintaining carbon emission monitoring equipment based on the Internet of Things provided in an embodiment of the present application;

[0024] Figure 5 A flowchart of a fourth method for operating and maintaining carbon emission monitoring equipment based on the Internet of Things provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of the logical structure of a carbon emission monitoring equipment operation and maintenance system based on the Internet of Things provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of the physical structure of a carbon emission monitoring equipment operation and maintenance system based on the Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0028] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0029] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0030] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0032] Traditional manual inspections of carbon emission activity monitoring equipment are inefficient and difficult to cover, leading to missed inspections or delayed maintenance. As carbon emission activity monitoring equipment ages, hardware aging, and untimely software updates can lead to a decline in the performance of the equipment and, consequently, the accuracy of the monitoring data.

[0033] Based on the above reasons, an embodiment of the present application provides an operation and maintenance method for carbon emission monitoring equipment based on the Internet of Things. The method includes: obtaining multiple time series collection results of collection equipment in the target area based on the Internet of Things, clustering the multiple time series collection results according to production scheduling characteristics, and obtaining multiple time series collection result clusters and production scheduling characteristics corresponding to each time series collection result cluster, each time series collection result cluster includes multiple time series collection results with similar production scheduling characteristics; wherein, the collection equipment is used to collect carbon emission activity level data; determine the time series change characteristics of each time series collection result, and determine the distinguishing state characteristics of each time series collection result relative to the production scheduling characteristics of the time series collection result cluster to which it belongs; through the anomaly detection model, determine the abnormal time series collection result according to the time series change characteristics and the distinguishing state characteristics, and prompt the collection equipment corresponding to the abnormal time series collection result to be repaired. The method in the embodiment of the present application can cluster multiple time series collection results according to production scheduling characteristics, and can determine abnormal time series collection results based on the time series change characteristics of the time series collection results and the distinguishing state characteristics of the time series collection results relative to the production scheduling characteristics of the time series collection result cluster to which they belong, thereby achieving accurate detection of abnormal time series collection results, improving the monitoring efficiency of carbon emission monitoring equipment, and enabling efficient monitoring of carbon emission monitoring equipment.

[0034] In some scenarios, the carbon emission monitoring equipment operation and maintenance method based on the Internet of Things of an embodiment of the present application can be applied to the efficient monitoring equipment of carbon emission monitoring equipment in factories, enterprises, institutions, etc., thereby improving the monitoring accuracy and efficiency of carbon emission monitoring equipment.

[0035] The following is a detailed description of an IoT-based carbon emission monitoring equipment operation and maintenance method provided in an embodiment of the present application with reference to specific examples.

[0036] Figure 1 A flowchart of a carbon emission monitoring device operation and maintenance method based on the Internet of Things provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes S110 to S120, and S110 to S120 are described in detail below.

[0037] S110: Acquire multiple time series collection results from collection devices within a target area based on the Internet of Things, cluster the multiple time series collection results based on production scheduling characteristics, and obtain multiple time series collection result clusters and production scheduling characteristics corresponding to each time series collection result cluster, wherein each time series collection result cluster includes multiple time series collection results having similar production scheduling characteristics. The collection devices are used to collect carbon emission activity level data.

[0038] like Figure 1 As shown, in an embodiment of the present method, multiple time-series collection results of collection devices in the target area can be first obtained based on the Internet of Things. The collection devices are used to collect carbon emission activity level data in time series, and then the accuracy of the carbon emission detection equipment can be monitored based on the carbon emission activity level data.

[0039] For example, the collection device can be a gas sensor (such as a CO sensor, a methane sensor) to monitor the concentration of the emission gas, which can represent the activity level; the collection device can also be a flow meter, which is used to measure the flow of gas or liquid and calculate the emission amount, which can represent the activity level; the collection device can also be an energy consumption monitoring device, which is used to record the consumption of energy such as electricity and fuel, which can represent the activity level; the collection device can also be a GPS and Internet of Things device, which is used to track the emission activities of mobile sources (such as vehicles), which can represent the activity level. Through the above-mentioned collection devices, activity level data can be collected through the collection device, and then the status of the monitoring device can be monitored based on the activity level data.

[0040] For example, after acquiring the carbon emission activity level data, the collection device can upload the data to the management system through the data collection system and network transmission technology. The management system can process and analyze the data to obtain time series collection results.

[0041] After obtaining multiple time series acquisition results, the multiple time series acquisition results can be clustered according to the production scheduling characteristics, thereby obtaining multiple time series acquisition result clusters. Each time series acquisition result cluster includes multiple time series acquisition results with similar production scheduling characteristics, and each time series acquisition result cluster also has corresponding production scheduling characteristics.

[0042] Exemplarily, production scheduling features may include features such as the working mode and production time of the working equipment that needs to collect activity level data. Through clustering, time series collection results with similar production scheduling features can be classified into one category to form multiple time series collection result clusters.

[0043] S120: Determine the time series variation characteristics of each time series collection result, and determine the distinguishing status characteristics of each time series collection result relative to the production scheduling characteristics of the time series collection result cluster to which it belongs. Using the anomaly detection model, identify abnormal time series collection results based on the time series variation characteristics and distinguishing status characteristics, and prompt the collection equipment corresponding to the abnormal time series collection result to be repaired.

[0044] During detection, the time series variation characteristics of each time series acquisition result can be determined. The time series variation characteristics represent the variation characteristics of the time series acquisition result over time. Then, whether the time series acquisition result is abnormal in the time sequence can be judged based on the time series variation characteristics.

[0045] Exemplarily, the time series variation feature may include a fluctuation amplitude feature of the data.

[0046] During detection, the timing change characteristics of each timing acquisition result can be determined, and the distinguishing state characteristics of each timing acquisition result relative to the production scheduling characteristics of the timing acquisition result cluster to which it belongs can be determined. The distinguishing state characteristics reflect the difference between a certain timing acquisition result and other timing acquisition results in the timing acquisition result cluster where the timing acquisition result is located. Abnormal timing acquisition results can then be identified based on the distinguishing state characteristics.

[0047] Figure 2 A schematic diagram of a work flow of a carbon emission monitoring equipment operation and maintenance method based on the Internet of Things provided in an embodiment of the present application is shown as follows: Figure 2 As shown, after obtaining the time series change characteristics and the distinguishing state characteristics, the abnormal time series acquisition results can be determined according to the time series change characteristics and the distinguishing state characteristics through the abnormality detection model, and the acquisition equipment corresponding to the abnormal time series acquisition results can be prompted to be repaired to realize the detection of the working status of the acquisition equipment.

[0048] For example, when the method in the embodiment of the present application is working and detecting in a certain industrial production scenario, if the timing collection results of a certain collection device show that the carbon emission level of the timing collection results suddenly increases significantly in time series, and this change is significantly different from the collection results of other collection devices in the timing collection result cluster where the timing collection results are located, then the collection device may have a fault or abnormality, and the system will prompt the operation and maintenance personnel to inspect the device.

[0049] For example, the anomaly detection model can be based on a machine learning algorithm and can be implemented by learning the characteristics of normal and abnormal states through training data, so that abnormal time series acquisition results can be identified in practical applications.

[0050] The beneficial effect of the above-mentioned implementation method is that compared with the traditional manual inspection method, the method of the present application realizes real-time monitoring and intelligent operation and maintenance of carbon emission monitoring equipment through Internet of Things technology. By clustering and detecting anomalies in the time series collection results, it can timely discover abnormal conditions of the collection equipment and prompt the operation and maintenance personnel to carry out maintenance, thereby improving the operation and maintenance efficiency and the reliability of the collection equipment.

[0051] The beneficial effect of the above-mentioned implementation method is that, when performing anomaly detection on the time series acquisition results, it is possible to judge whether the time series acquisition results are abnormal time series acquisition results based on the changing characteristics of the carbon emission levels in the time series of the time series acquisition results and the distinguishing characteristics of the time series acquisition results of other acquisition devices in the time series acquisition result cluster where the time series acquisition results are located, thereby improving the accuracy of the judgment on whether the time series acquisition results are abnormal.

[0052] In some implementations, in the above-mentioned S120, determining the distinguishing status characteristics of each time series acquisition result relative to the production scheduling characteristics of the time series acquisition result cluster to which it belongs includes: determining the scheduling mutation point and scheduling cycle of the production scheduling characteristics of the time series acquisition result cluster to which each time series acquisition result belongs, and determining the acquisition result mutation point and acquisition result cycle of each time series acquisition result, determining the mutation distinguishing characteristics based on the scheduling mutation point and the acquisition result mutation point, and determining the acquisition cycle distinguishing characteristics based on the scheduling cycle and the acquisition result cycle, and determining the distinguishing status characteristics based on the mutation distinguishing characteristics and acquisition cycle distinguishing characteristics of each time series acquisition result.

[0053] In order to determine the distinguishing state features, the distinguishing state features can be determined from the mutation features of the activity level changes and the periodic features of the activity level changes in the time series acquisition results, thereby improving the accuracy of the distinguishing state features.

[0054] When determining the distinguishing state characteristics, we can first determine the scheduling mutation point and scheduling cycle of the production scheduling characteristics of the timing collection result cluster to which each timing collection result belongs. The scheduling mutation point is the mutation time of the timing collection result cluster to which the timing collection result belongs, and the scheduling cycle is the production scheduling cycle of the timing collection result cluster.

[0055] When determining the distinguishing state features, we can first determine the acquisition result mutation point and acquisition result cycle of each time series acquisition result. The acquisition result mutation point represents the mutation time of the time series acquisition result, and the acquisition result cycle is the period in which the time series acquisition result changes.

[0056] When determining the distinguishing state features subsequently, the mutation distinguishing features can be determined based on the scheduling mutation point and the collection result mutation point. The mutation distinguishing features represent the difference between the mutation time of the time series collection result cluster where the time series collection result is located and the mutation time of the time series collection result.

[0057] When determining the distinguishing state features subsequently, the collection cycle distinguishing features may be determined based on the scheduling cycle and the collection result cycle. The scheduling cycle is the difference between the production scheduling cycle of the time series collection result cluster and the cycle in which the time series collection results change.

[0058] For example, the mutation points and periodic characteristics of the production schedule can be identified by using time series analysis methods, such as sliding window analysis, Fourier transform, etc.; similar methods can be used to analyze the mutation points and periodic characteristics of the collection results; by comparing these characteristics, the differences between the production schedule and the collection results can be identified, and these differences are used to determine the distinguishing state characteristics.

[0059] After obtaining the mutation distinguishing features and the acquisition cycle distinguishing features, the distinguishing state features can be determined based on the mutation distinguishing features and the acquisition cycle distinguishing features of each time series acquisition result. The distinguishing state features characterize the mutation features and the cycle features of the time series acquisition results, thereby improving the detection accuracy of abnormal time series acquisition results.

[0060] The beneficial effect of the above-mentioned implementation method is that the distinguishing state characteristics are determined according to the mutation distinguishing characteristics and acquisition cycle distinguishing characteristics of each time series acquisition result, which can improve the detection accuracy of abnormal time series acquisition results, better adapt to complex production environments, reduce missed detections and false detections, and improve equipment maintenance efficiency and data accuracy.

[0061] Figure 3 A flow chart of a second method for operating and maintaining carbon emission monitoring equipment based on the Internet of Things provided in an embodiment of the present application is shown in FIG. Figure 3As shown, in the above S120, the distinguishing state feature can be determined according to the mutation distinguishing feature and the acquisition cycle distinguishing feature of each time series acquisition result, including S121 to S122. S121 to S122 are described in detail below.

[0062] S121. Determine the global average of the scheduling mutation points of all time series acquisition results in all time series acquisition result clusters, the average of the distinctive mutation amplitudes corresponding to the scheduling mutation points of all time series acquisition results in each time series acquisition result cluster, and determine the ratio of the distinctive mutation amplitude average to the global average of the mutation amplitude as the mutation feature weight of each time series acquisition result cluster. Determine the global scheduling cycle average of the scheduling cycles of all time series acquisition results in all time series acquisition result clusters, the collection result cycle average of all time series acquisition results in each time series acquisition result cluster, and determine the ratio of the global scheduling cycle average to the collection result cycle average as the collection cycle feature weight of each time series acquisition result cluster.

[0063] In order to further improve the accuracy of determining the distinguishing state characteristics, the global mutation amplitude mean of the scheduling mutation points of all time series acquisition results in all time series acquisition result clusters and the distinguishing mutation amplitude mean corresponding to the scheduling mutation points of all time series acquisition results in each time series acquisition result cluster can be determined. The global mutation amplitude mean represents the mutation amplitude of the activity level in the scheduling of all time series acquisition results in all time series acquisition result clusters, and the distinguishing mutation amplitude mean represents the mutation amplitude of the activity level of all time series acquisition results in each time series acquisition result cluster.

[0064] After obtaining the mean value of the distinct mutation amplitude and the mean value of the global mutation amplitude, the ratio of the mean value of the distinct mutation amplitude to the mean value of the global mutation amplitude can be determined as the mutation feature weight of each time series acquisition result cluster. The mutation feature weight represents the ratio of the mutation amplitude of each time series acquisition result cluster to the mutation amplitude of all time series acquisition result clusters. Then, the weight corresponding to the activity level mutation amplitude of the time series acquisition results within the time series acquisition result cluster can be determined based on the mutation feature weight.

[0065] In order to further improve the accuracy of determining the distinguishing state characteristics, the global scheduling cycle mean of the scheduling cycles of all timing acquisition results of all timing acquisition result clusters and the acquisition result cycle mean of all timing acquisition results of each timing acquisition result cluster can be determined. The global scheduling cycle mean represents the cycle mean of the activity level changes of the timing acquisition results of all timing acquisition result clusters, and the acquisition result cycle mean represents the cycle mean of the activity level changes of all timing acquisition results in each timing acquisition result cluster.

[0066] After obtaining the global scheduling cycle mean and the collection result cycle mean, the ratio of the global scheduling cycle mean to the collection result cycle mean can be determined as the collection cycle feature weight of each time series collection result cluster. Then, the weight of the cycle of each time series collection result cluster relative to the global activity level change can be determined based on the collection cycle feature weight.

[0067] S122: Determine the sum of the product of the mutation distinguishing feature and the mutation feature weight, and the product of the acquisition cycle distinguishing feature and the acquisition cycle feature weight as the distinguishing state feature.

[0068] After obtaining the mutation feature weight and the acquisition cycle feature weight, the sum of the product of the mutation distinguishing feature and the mutation feature weight, and the sum of the product of the acquisition cycle distinguishing feature and the acquisition cycle feature weight can be determined as the distinguishing state feature. The distinguishing state feature combines the weight corresponding to the activity level mutation amplitude of the time series acquisition results within each time series acquisition result cluster and the weight of the cycle of activity level change of each time series acquisition result cluster relative to the global one to determine the distinguishing state feature, thereby improving the scientific nature and reliability of the distinguishing state feature.

[0069] The beneficial effect of the above-mentioned implementation method is that the weight corresponding to the activity level mutation amplitude of the time series acquisition results within each time series acquisition result cluster and the weight of the period of activity level change of each time series acquisition result cluster relative to the global one are combined to determine the distinguishing state characteristics, thereby improving the scientificity and reliability of determining the distinguishing state characteristics, being able to more accurately reflect the changing characteristics and periodic characteristics of the time series acquisition results, and improving the accuracy and reliability of anomaly detection.

[0070] Figure 4 A flow chart of a third method for operating and maintaining carbon emission monitoring equipment based on the Internet of Things provided in the embodiment of the present application is shown as follows: Figure 4 As shown, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0071] S210. Obtain production schedule adjustment information corresponding to each collection device in the target area based on the Internet of Things, determine an adjustment ratio for production schedule adjustment in the collection device corresponding to each time series collection result cluster, and determine a variance value for production schedule adjustment in the collection device corresponding to each time series collection result cluster.

[0072] When detecting abnormal time series collection results through time series collection result clusters, the production schedule adjustment information corresponding to the collection devices in the target area can be obtained based on the Internet of Things. The production schedule adjustment information represents the production schedule adjustment of the activity level collected by the collection devices; at the same time, the adjustment ratio of the production schedule adjustment in the collection devices corresponding to each time series collection result cluster can be determined. The adjustment ratio of the production schedule adjustment represents the quantitative ratio of the production schedule adjustment, and the variance value of the production schedule adjustment of the collection devices corresponding to each time series collection result cluster can be determined. The variance value of the production schedule adjustment represents the dispersion amplitude of the production schedule adjustment of the collection devices corresponding to the time series collection result cluster. Then, according to the quantitative ratio of the production schedule adjustment and the dispersion amplitude of the production schedule adjustment, it can be determined whether the time series collection result clusters need to be re-clustered.

[0073] S220 , when the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, re-clustering the multiple time series acquisition results according to the production scheduling characteristics.

[0074] After obtaining the adjustment ratio corresponding to the time series acquisition result cluster and the variance value corresponding to the time series acquisition result cluster, when the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, it means that the adjustment ratio of the number of acquisition devices in the time series acquisition result cluster is high, and the dispersion of the adjustment of the production schedule of the acquisition devices in the time series acquisition result cluster is too large. Therefore, the multiple time series acquisition results can be re-clustered according to the production scheduling characteristics to ensure the accuracy of the subsequent determination of the abnormal time series acquisition results in the acquisition result cluster.

[0075] For example, in the above method, when determining whether the time series acquisition results need to be re-clustered, it can be achieved through the following steps: 1. The adjustment of the production schedule can be monitored in real time through sensors installed on the production equipment, and the data can be transmitted to the control system for analysis. 2. By performing statistical analysis on the collected production scheduling data, the variance value corresponding to each cluster of time series acquisition results is calculated to evaluate the stability of the production schedule. 3. When it is detected that the adjustment ratio and variance value exceed the preset threshold, the control system automatically triggers the re-clustering process and re-clusters the time series acquisition results according to the latest production scheduling characteristics.

[0076] The beneficial effect of the above implementation method is that when it is detected that the adjustment ratio and variance value of a certain time series acquisition result cluster exceeds the preset threshold, the system will re-cluster the time series acquisition results according to the latest production scheduling characteristics. This dynamic adjustment mechanism can promptly reflect changes in production scheduling and improve the accuracy and effectiveness of the time series acquisition results.

[0077] Figure 5 A flowchart of a fourth method for operating and maintaining carbon emission monitoring equipment based on the Internet of Things is provided in an embodiment of the present application, as shown in FIG. Figure 5 As shown, the above method further includes S310 to S320, and S310 to S320 are described in detail below.

[0078] S310: Obtain historical maintenance records of each collection device in the target area based on the Internet of Things, determine historical maintenance cycles of each collection device in the target area based on the historical maintenance records, and determine an average maintenance cycle of each collection device in the target area.

[0079] When determining whether it is necessary to re-cluster all collection devices to obtain a time series collection result cluster, the historical maintenance records of each collection device in the target area can be obtained based on the Internet of Things, and the historical maintenance cycle of each collection device in the target area can be determined based on the historical maintenance records. The historical maintenance cycle represents the time period for maintenance and repair of each collection device in the target area.

[0080] After obtaining the maintenance and overhaul time period of each collection device in the target area, the average maintenance period of each collection device in the target area can be determined. The average maintenance period represents the mean of the maintenance periods of each collection device in the target area.

[0081] For example, the maintenance information of each device can be collected and recorded in real time through the Internet of Things technology and stored in a cloud database. By performing statistical analysis on this data, the historical maintenance cycle and average maintenance cycle of each device can be calculated.

[0082] S320: Determine the ratio of the historical maintenance cycle to the average maintenance cycle of each collection device as the maintenance factor of each collection device, and adjust the distinguishing state feature by multiplying the maintenance factor by the distinguishing state feature.

[0083] After obtaining the average maintenance cycle, the ratio of the historical maintenance cycle of each collection device to the average maintenance cycle can be determined as the maintenance factor of each collection device. The maintenance factor represents the maintenance frequency of each collection device in the historical time period.

[0084] After obtaining the maintenance factor, the distinguishing state feature can be multiplied by the maintenance factor to adjust the distinguishing state feature, and then the distinguishing state feature can be adjusted by the maintenance factor, so that the distinguishing state feature increases when the maintenance frequency of the acquisition device is higher, and decreases when the maintenance frequency of the acquisition device is lower.

[0085] For example, the calculation of the maintenance factor can be achieved by writing a corresponding algorithm and applying it to the adjustment process of distinguishing status characteristics, which can more accurately assess the health status of the equipment, timely detect and handle abnormal situations, and improve the operation and maintenance efficiency and reliability of the equipment.

[0086] The beneficial effect of the above-mentioned implementation method is that by determining the ratio of the historical maintenance cycle and the average maintenance cycle of each collection device as a maintenance factor, and adjusting the distinguishing state characteristics through the maintenance factor, the distinguishing state characteristics are increased when the maintenance frequency of the collection device is higher, and the distinguishing state characteristics are reduced when the maintenance frequency of the collection device is lower.

[0087] In some implementations, the above method also includes: when the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, the multiple time series acquisition results are re-clustered according to the production scheduling characteristics and maintenance factors.

[0088] When determining whether multiple time series acquisition results need to be re-clustered, when the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, the multiple time series acquisition results can be re-clustered according to the production scheduling characteristics and maintenance factors, and the acquisition equipment with similar maintenance history can be maintained in combination with the maintenance factors.

[0089] For example, the re-clustering process can be implemented in a variety of ways. A clustering method based on the K-means algorithm can be used to classify the time series acquisition results according to new features; or a hierarchical clustering method can be used to reclassify by calculating the similarity between the acquisition results.

[0090] The beneficial effect of the above-mentioned implementation method is that by introducing maintenance factors and re-clustering methods, it effectively solves the problem of abnormal timing collection results caused by production schedule adjustments and equipment maintenance. This technical solution can more accurately reflect the actual production and maintenance status, and can improve the operation and maintenance efficiency and data accuracy of carbon emission monitoring equipment.

[0091] In some implementations, the above method further includes S410 to S420, and S410 to S420 are described in detail below.

[0092] S410: Obtain the maintenance times of the collection devices in the first time series collection result cluster within a historical time period, and determine a ratio of the maintenance times to the standard maintenance times as a maintenance times adjustment factor.

[0093] When it is determined that multiple time series acquisition results need to be re-clustered, the maintenance times of the acquisition devices in the first time series acquisition result cluster within the historical time period can be obtained, and the ratio of the maintenance times to the standard maintenance times can be determined as the maintenance times adjustment factor. The maintenance times adjustment factor represents the ratio of the maintenance times of all acquisition devices in the time series acquisition result cluster to the standard maintenance times.

[0094] For example, the data acquisition module in the Internet of Things system can be used to regularly record the maintenance times of each acquisition device and store them in the management system. The data processing module can analyze the historical maintenance data and calculate the maintenance times adjustment factor of each time series acquisition result cluster.

[0095] S420: Multiply the preset adjustment ratio corresponding to the first time series acquisition result cluster by the maintenance times adjustment factor to adjust the preset adjustment ratio corresponding to the first time series acquisition result cluster. Furthermore, multiply the preset variance value corresponding to the first time series acquisition result cluster by the maintenance times adjustment factor to adjust the preset variance value corresponding to the first time series acquisition result cluster.

[0096] After obtaining the maintenance times adjustment factors of all timing acquisition result clusters, the preset adjustment ratio corresponding to the first timing acquisition result cluster can be multiplied by the maintenance times adjustment factor to adjust the preset adjustment ratio corresponding to the first timing acquisition result cluster, and then the maintenance times adjustment factor can be combined to determine whether the timing acquisition result clusters need to be re-clustered.

[0097] After obtaining the maintenance times adjustment factors of all timing acquisition result clusters, the preset variance value corresponding to the first timing acquisition result cluster can be multiplied by the maintenance times adjustment factor to adjust the preset variance value corresponding to the first timing acquisition result cluster, and then the maintenance times adjustment factor can be combined to determine whether the timing acquisition result cluster needs to be re-clustered.

[0098] For example, the calculated adjustment factor may be automatically applied to a preset adjustment ratio and a preset variance value, thereby dynamically adjusting these parameters to accommodate different maintenance frequencies.

[0099] The beneficial effect of the above implementation is that, by introducing the maintenance times adjustment factor, the actual maintenance status of the time series acquisition result cluster can be more accurately reflected, thereby improving the accuracy of determining whether the time series acquisition result cluster needs to be re-clustered.

[0100] In some implementations, the method further includes: determining a historical time period in which the acquisition equipment in the first time series acquisition result cluster was not maintained, and determining an average of the maintenance times of all time series acquisition result clusters in the historical time period as the standard maintenance times.

[0101] When determining the standard maintenance number, a historical time period in which the acquisition equipment in the first time series acquisition result cluster has not been overhauled can be determined, and the average of the maintenance times of all time series acquisition result clusters within the historical time period can be determined as the standard maintenance number, so that the maintenance times of the acquisition equipment within the historical time period eliminate the interference of the maintenance times of the acquisition equipment in the first time series acquisition result cluster, and the maintenance frequency of the acquisition equipment in the first time series acquisition result cluster can be more accurately evaluated, thereby improving the accuracy of the relative frequency of maintenance of the acquisition equipment in the first time series acquisition result cluster.

[0102] The beneficial effect of the above-mentioned implementation method is that it eliminates the interference of the maintenance times of the acquisition equipment in the first time series acquisition result cluster, can improve the accuracy of the relative frequency of maintenance of the acquisition equipment in the first time series acquisition result cluster, and improves the accuracy and reliability of determining whether the first time series acquisition result cluster needs to be re-clustered.

[0103] An embodiment of the present application also provides an Internet of Things-based carbon emission monitoring equipment operation and maintenance system, including a unit for executing any of the methods described above.

[0104] Figure 6 A logical structure diagram of a carbon emission monitoring equipment operation and maintenance system based on the Internet of Things is provided in one embodiment of the present application, such as Figure 6 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0105] An embodiment of the present application also provides an Internet of Things-based carbon emission monitoring equipment operation and maintenance system, which implements any of the methods described above when the processor executes the computer program.

[0106] Figure 7 A schematic diagram of the physical structure of a carbon emission monitoring equipment operation and maintenance system based on the Internet of Things provided in one embodiment of the present application is shown as follows: Figure 7 As shown, the system 2 of this embodiment includes: at least one processor 20 ( Figure 7 Only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps of any of the above-mentioned method embodiments are implemented. The beneficial effects of the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0107] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0109] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0110] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process of the above-mentioned method embodiment by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can at least include: any entity or device capable of carrying computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, mobile hard drive, magnetic disk, or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0112] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0113] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0114] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0116] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A carbon emission monitoring equipment operation and maintenance method based on the Internet of Things, characterized in that: The method comprises: Based on the Internet of Things, multiple time series collection results from collection devices within a target area are obtained, and the multiple time series collection results are clustered according to production scheduling characteristics to obtain multiple time series collection result clusters and production scheduling characteristics corresponding to each time series collection result cluster. Each time series collection result cluster includes multiple time series collection results with similar production scheduling characteristics. The collection devices are used to collect carbon emission activity level data. Determine the timing change characteristics of each timing collection result, and determine the distinguishing state characteristics of each timing collection result relative to the production scheduling characteristics of the timing collection result cluster to which it belongs; through the anomaly detection model, determine the abnormal timing collection results based on the timing change characteristics and distinguishing state characteristics, and prompt the collection equipment corresponding to the abnormal timing collection results to be repaired.

2. The method according to claim 1, wherein Determine the distinguishing status characteristics of each time series acquisition result relative to the production scheduling characteristics of the time series acquisition result cluster to which it belongs, including: Determine the scheduling mutation point and scheduling cycle of the production scheduling characteristics of the timing collection result cluster to which each timing collection result belongs, and determine the collection result mutation point and collection result cycle of each timing collection result, determine the mutation distinguishing characteristics based on the scheduling mutation point and the collection result mutation point, and determine the collection cycle distinguishing characteristics based on the scheduling cycle and the collection result cycle, and determine the distinguishing state characteristics based on the mutation distinguishing characteristics and collection cycle distinguishing characteristics of each timing collection result.

3. The method according to claim 2, wherein Determine the distinguishing state features based on the mutation distinguishing features and acquisition cycle distinguishing features of each time series acquisition result, including: Determine the global mutation amplitude mean of the scheduling mutation points of all time series acquisition results in all time series acquisition result clusters, the distinguishing mutation amplitude mean corresponding to the scheduling mutation points of all time series acquisition results of each time series acquisition result cluster, and determine the ratio of the distinguishing mutation amplitude mean to the global mutation amplitude mean as the mutation feature weight of each time series acquisition result cluster; determine the global scheduling cycle mean of the scheduling cycles of all time series acquisition results in all time series acquisition result clusters, the acquisition result cycle mean of all time series acquisition results of each time series acquisition result cluster, and determine the ratio of the global scheduling cycle mean to the acquisition result cycle mean as the acquisition cycle feature weight of each time series acquisition result cluster; The sum of the product of the mutation distinguishing feature and the mutation feature weight, and the product of the acquisition cycle distinguishing feature and the acquisition cycle feature weight is determined as the distinguishing state feature.

4. The method according to claim 3, wherein The method further comprises: Based on the Internet of Things, the production schedule adjustment information corresponding to each collection device in the target area is obtained, the adjustment ratio of the production schedule adjustment in the collection device corresponding to each time series collection result cluster is determined, and the variance value of the production schedule adjustment of the collection device corresponding to each time series collection result cluster is determined; When the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, the multiple time series acquisition results are re-clustered according to the production scheduling characteristics.

5. The method according to claim 4, wherein The method further comprises: Obtain the historical maintenance records of each collection device in the target area based on the Internet of Things, determine the historical maintenance cycle of each collection device in the target area based on the historical maintenance records, and determine the average maintenance cycle of each collection device in the target area; The ratio of the historical maintenance period to the average maintenance period of each acquisition device is determined as the maintenance factor of each acquisition device, and the distinguishing state feature is multiplied by the maintenance factor to adjust the distinguishing state feature.

6. The method according to claim 5, wherein The method further comprises: When the first adjustment ratio corresponding to the first time series acquisition result cluster is greater than the preset adjustment ratio, and the first variance value corresponding to the first time series acquisition result cluster is greater than the preset variance value, the multiple time series acquisition results are re-clustered according to the production scheduling characteristics and the maintenance factors.

7. A carbon emission monitoring equipment operation and maintenance system based on the Internet of Things, characterized in that: Comprising means for performing the method according to any one of claims 1 to 6.

8. A carbon emission monitoring equipment operation and maintenance system based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images