An industry chain early warning method and an energy service SaaS operation and maintenance management platform

Abstract

The application relates to an industry chain early warning method and an energy service SaaS operation and maintenance management platform. The method comprises the following steps: acquiring basic power consumption data groups of all terminals of an enterprise, each terminal corresponding to a basic power consumption data group; cleaning the basic power consumption data groups to obtain analysis power consumption data groups; constructing power consumption analysis curves by using the analysis power consumption data groups; acquiring behavior data of the terminals and segmenting the power consumption analysis curves according to the behavior data to obtain multiple sub-power consumption analysis curves; correlating and analyzing the sub-power consumption analysis curves and a comparison reference curve according to the behavior data to obtain analysis results; and giving a judgment result according to the analysis results, wherein the judgment result comprises normal power consumption behavior and abnormal power consumption behavior. The industry chain early warning method and the energy service SaaS operation and maintenance management platform disclosed by the application can discover the relationship between equipment operation behavior and power consumption by analyzing collected data, thereby providing data support for subsequent equipment maintenance and power consumption optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an industry chain early warning method and an energy service SaaS operation and maintenance management platform. BACKGROUND

[0002] Industrial electricity is an important part of the social electricity system, with characteristics such as high electricity consumption, concentrated load, continuous dependence and quality sensitivity. Under the business needs of energy saving management, environmental protection monitoring and industry chain early warning, some enterprises begin to install corresponding terminals to collect data and analyze electricity consumption, time-sharing load and abnormal electricity consumption to find electricity problems. A current implementation method is as follows:

[0003] Data collection: smart meters (with RS485 / 4G communication), Internet of Things sensors (monitoring equipment temperature, vibration), SCADA system (industrial equipment centralized monitoring);

[0004] Data processing: Python (Pandas / NumPy processing time series data), SQL (storing electricity and production data);

[0005] Analysis and visualization: Tableau / Power BI (load curve visualization);

[0006] Early warning system: real-time push of abnormal information through SMS / APP, linkage of PLC automatic shutdown (high-risk scene).

[0007] The above method can realize the automation of data collection and analysis, such as discovering abnormalities by comparing current data with historical data, determining by time period, equipment, process, etc. These judgment methods all have errors and cannot accurately reflect the relationship between equipment operation behavior and power consumption. SUMMARY

[0008] The present application provides an industry chain early warning method and an energy service SaaS operation and maintenance management platform, which discovers the relationship between equipment operation behavior and power consumption through analysis of collected data, thereby providing data support for subsequent equipment maintenance and power consumption optimization.

[0009] The above object of the present application is achieved by the following technical solution:

[0010] In a first aspect, the present application provides an industry chain early warning method, comprising:

[0011] obtaining basic electricity data sets of each terminal of an enterprise, each terminal corresponding to a basic electricity data set;

[0012] The basic power consumption data set is cleaned to obtain an analysis power consumption data set, and the cleaning includes removing abnormal data and filling missing data.

[0013] An analysis power consumption curve is constructed using the analysis power consumption data set.

[0014] Behavior data of the terminal is obtained, and the analysis power consumption curve is segmented according to the behavior data to obtain a plurality of sub-analysis power consumption curves, and the behavior data includes a behavior type, a start time and an end time.

[0015] The sub-analysis power consumption curves are associated and analyzed with a comparison reference curve according to the behavior data to obtain an analysis result.

[0016] A judgment result is given according to the analysis result, and the judgment result includes a normal power consumption behavior and an abnormal power consumption behavior.

[0017] In a possible implementation manner of the first aspect, after the analysis power consumption curve is constructed using the analysis power consumption data set, the method further includes:

[0018] An area value of the analysis power consumption curve is calculated, and a production behavior quantity corresponding to the analysis power consumption curve is obtained.

[0019] A production behavior mean value is calculated using the area value of the analysis power consumption curve and the production behavior quantity.

[0020] The production behavior mean value is compared with a production behavior standard value to determine a state of the production behavior mean value, and the state includes a normal value and an abnormal value.

[0021] In a possible implementation manner of the first aspect, when the behavior data is missing, the analysis power consumption curve is segmented using a feature of the analysis power consumption curve, and the feature of the analysis power consumption curve includes a slope change amount, a slope change time length, a stable interval amount and a stable time length.

[0022] In a possible implementation manner of the first aspect, after the plurality of sub-analysis power consumption curves are obtained, the method further includes:

[0023] The sub-analysis power consumption curves are divided using a fixed time length to obtain sub-analysis power consumption curve segments.

[0024] The sub-analysis power consumption curve segments are analyzed to obtain stability data.

[0025] The comparison reference curve corresponding to the sub-analysis power consumption curve segments is analyzed to obtain reference stability data.

[0026] The stability data is compared with the reference stability data to determine a running state of the terminal, and the running state includes a stable running state and a non-stable running state.

[0027] In a possible implementation manner of the first aspect, the analyzing the sub-power consumption analysis curve segment and obtaining the stability data comprises:

[0028] obtaining a data point group corresponding to the sub-power consumption analysis curve segment and constructing an analysis reference curve using the data point group;

[0029] transforming the analysis reference curve into a time domain for decomposition, to obtain a continuous group and a discontinuous group;

[0030] calculating a ratio of the continuous group to the discontinuous group, denoted as the stability data, the ratio comprising a quantity ratio and an intensity ratio.

[0031] In a possible implementation manner of the first aspect, after comparing the stability data with the reference stability data, the method further comprises comparing a state distribution of the stability data with the reference stability data and giving a judgment result according to the state distribution, the judgment result comprising a same state and a different state.

[0032] In a possible implementation manner of the first aspect, the comparing the state distribution of the stability data with the reference stability data comprises:

[0033] obtaining a data point group corresponding to the sub-power consumption analysis curve segment and dividing the data point group according to a time length, to obtain a plurality of sub-data point groups;

[0034] determining a surrounding data density of data points in each sub-data point group and classifying the data points in the sub-data point group according to the surrounding data density;

[0035] statistically obtaining a distribution result of the different types of data points on a time sequence, denoted as a stability data distribution result;

[0036] obtaining a reference stability data distribution result using the same manner;

[0037] comparing the stability data distribution result with the reference stability data distribution result, to obtain a judgment result.

[0038] In a second aspect, the present application provides an industrial chain early warning device, comprising:

[0039] a data acquisition unit configured to acquire a basic power consumption data group of each terminal of an enterprise, each terminal corresponding to a basic power consumption data group;

[0040] a data cleaning unit configured to clean the basic power consumption data group to obtain an analysis power consumption data group, the cleaning comprising removing abnormal data and filling in missing data;

[0041] a first data processing unit configured to construct a power consumption analysis curve using the analysis power consumption data group;

[0042] The second data processing unit is configured to acquire behavior data of the terminal and segment the power consumption analysis curve according to the behavior data to obtain a plurality of sub power consumption analysis curves, wherein the behavior data comprises a behavior type, a start time and an end time.

[0043] The third data processing unit is configured to associate and analyze the sub power consumption analysis curve with the comparison reference curve according to the behavior data to obtain an analysis result.

[0044] The result judging unit is configured to give a judging result according to the analysis result, wherein the judging result comprises a normal power consumption behavior and an abnormal power consumption behavior.

[0045] In a third aspect, the present application provides an energy service SaaS operation and maintenance management platform, which comprises:

[0046] one or more memories configured to store instructions; and

[0047] one or more processors configured to invoke and run the instructions from the memories to perform the method as described in the first aspect and any possible implementation manner of the first aspect.

[0048] In a fourth aspect, the present application provides a computer readable storage medium, which comprises:

[0049] a program, when the program is run by a processor, the method as described in the first aspect and any possible implementation manner of the first aspect is performed.

[0050] In a fifth aspect, the present application provides a computer program product, which comprises program instructions, when the program instructions are run by a computing device, the method as described in the first aspect and any possible implementation manner of the first aspect is performed.

[0051] In a sixth aspect, the present application provides a chip system, which comprises a processor configured to implement the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above method.

[0052] The chip system can be composed of a chip, or can comprise a chip and other discrete devices.

[0053] In a possible design, the chip system further comprises a memory configured to save necessary program instructions and data. The processor and the memory can be decoupled and arranged on different devices, and connected through a wired or wireless manner, or the processor and the memory can be coupled on the same device.

[0054] The present application has the following beneficial effects:

[0055] The industrial chain early warning method and the energy service SaaS operation and maintenance management platform provided by the application can discover the relationship between the device operation behavior and the power consumption by analyzing the collected data, and can discover normal power consumption behavior and abnormal power consumption behavior through analysis, and the results obtained by analysis can provide data support for subsequent device maintenance and power consumption optimization. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 is a step flowchart of an industrial chain early warning method provided by the application.

[0057] Figure 2 is a schematic diagram of constructing a power consumption analysis curve using an analysis power consumption data set provided by the application.

[0058] Figure 3 is a schematic diagram of segmenting a power consumption analysis curve according to behavior data provided by the application.

[0059] Figure 4 is a schematic diagram of determining the surrounding data density of the data points in each sub-data point set provided by the application.

[0060] Figure 5 is a comparison schematic diagram of a stability data distribution result and a reference stability data distribution result provided by the application.

[0061] Figure 6 is another comparison schematic diagram of a stability data distribution result and a reference stability data distribution result provided by the application. DETAILED DESCRIPTION

[0062] The technical solutions in the application will be further described in detail below with reference to the accompanying drawings.

[0063] The application discloses an industrial chain early warning method, please refer to Figure 1 In some examples, the industrial chain early warning method disclosed by the application includes the following contents:

[0064] S101, obtaining a basic power consumption data set of each terminal of an enterprise, each terminal corresponding to a basic power consumption data set;

[0065] S102, cleaning the basic power consumption data set to obtain an analysis power consumption data set, the cleaning including removing abnormal data and filling missing data;

[0066] S103, constructing a power consumption analysis curve using the analysis power consumption data set;

[0067] S104, obtaining behavior data of the terminal and segmenting the power consumption analysis curve according to the behavior data to obtain a plurality of sub-power consumption analysis curves, the behavior data including a behavior type, a start time and an end time.

[0068] S105, associating and analyzing the sub-power consumption analysis curve with the comparison reference curve according to the behavior data to obtain an analysis result;

[0069] S106, giving a judgment result according to the analysis result, the judgment result including normal power consumption behavior and abnormal power consumption behavior.

[0070] In step S101, first, the basic power consumption data set of each terminal of the enterprise is collected, where the terminal refers to the industrial production equipment participating in production in the enterprise, and the collection is performed in the manner described in the background art. In this application, the collected data includes voltage and current, and the basic power consumption data set has voltage and current. The basic power consumption data sets of the two types are processed in the same way, and the voltage and current can be collected simultaneously or selectively.

[0071] In step S102, the basic power consumption data set is cleaned to obtain an analysis power consumption data set. There are two cleaning methods, which are to remove abnormal data (data less than zero) and to fill in missing data (difference method or mean method).

[0072] The reason for producing data less than zero is:

[0073] When measuring, the "positive direction" of the current is preset (such as being defined as flowing into the device input as positive), and if the actual current flows in the opposite direction due to load characteristics or working condition changes (such as motor reversal or load becoming power feedback energy), the collected value will be negative.

[0074] The negative value of alternating current is a natural result of periodic change of sinusoidal waveform: in the negative half cycle of sinusoidal waveform, the current direction is opposite to that in the positive half cycle, and the collected value will show positive and negative alternation with the period (such as the current waveform of ordinary alternating current).

[0075] Power factor influence: when the load is capacitive or inductive and the power factor is low, the current may be opposite to the voltage, resulting in negative instantaneous current (but the effective value is still positive).

[0076] Collection module calibration problem: if the input range of ADC (analog-to-digital converter) is not correctly set (such as single polarity module misconnecting bipolar signal), the positive voltage may be misjudged as negative value.

[0077] The specific reasons for missing data are as follows:

[0078] Sensor failure: the internal coil of the current transformer (CT), voltage transformer (PT) or Hall sensor is disconnected or the magnetic core is saturated, resulting in failure to output effective signal, and the collection module has no data input.

[0079] Collection chip damage: ADC (analog-to-digital converter) chip overheating, virtual welding or pin oxidation, unable to complete the conversion of "analog signal to digital signal", directly losing the original data.

[0080] Module power supply instability: collection module power supply voltage fluctuation (such as below rated voltage), excessive ripple, resulting in periodic reset or stop working of the module, data collection interruption.

[0081] In step S103, the power consumption analysis curve is constructed using the power consumption data set, as shown in Figure 2 The specific way is to take the generation time of the data point in the power consumption data as the abscissa and the value as the ordinate to obtain discrete points, and then sequentially connect these discrete points together.

[0082] In step S104, the behavior data of the terminal is obtained and the power consumption analysis curve is segmented according to the behavior data, as shown in Figure 3 The behavior data of the terminal includes starting, stopping, performing production actions, etc., which will directly affect the power consumption data set.

[0083] The behavior data includes three parameters: behavior type, start time and end time. Segmenting the power consumption analysis curve according to the behavior data will obtain multiple sub-power consumption analysis curves. The sub-power consumption analysis curve obtained here has a start time and an end time, and also has a label (behavior type).

[0084] In step S105, the sub-power consumption analysis curve is associated and analyzed with the comparison reference curve according to the behavior data, and the analysis result is obtained. The analysis result here includes normal and abnormal, but the analysis result at this time is only for a certain sub-power consumption analysis curve.

[0085] Finally, in step S106, the judgment result is given according to the analysis result. The judgment result includes normal power consumption behavior and abnormal power consumption behavior. The way to give the judgment result here is to determine the proportion of normal analysis results in all analysis results. For example, for some precision equipment, the tolerance for abnormal analysis results is low. The value referred to when the judgment result is given here is low, and vice versa.

[0086] This is because for power consumption behavior, the economy of comprehensive consideration and processing is also needed, because processing needs to involve production adjustment, personnel allocation, etc., which will directly feedback to the production output.

[0087] The way of determining the power consumption behavior through time reference, equipment reference, process reference and the like has a large error, when a behavior is abnormal, the abnormality is eliminated by the mean value calculation, but when the behavior analysis is performed, the problem position can be directly found because of the accuracy of the comparison sample. In addition, even if the problem can be found through the time reference, equipment reference, process reference and the like, the problem position cannot be directly determined.

[0088] In some examples, after the power consumption analysis curve is constructed using the power consumption data, the following steps are added:

[0089] S201, calculating the area value of the power consumption analysis curve and obtaining the number of production behaviors corresponding to the power consumption analysis curve;

[0090] S202, calculating the production behavior mean value using the area value of the power consumption analysis curve and the number of production behaviors;

[0091] S203, comparing the production behavior mean value and the production behavior standard value to determine the state of the production behavior mean value, the state including normal value and abnormal value.

[0092] In steps S201 to S203, whether an abnormal power consumption behavior occurs is judged according to the average power consumption of the production behavior, which can be used to preliminarily judge whether an obvious abnormal power consumption behavior occurs, for example, the power consumption (production behavior standard value) of a certain production behavior of a certain product is 1, if the calculated power consumption (production behavior mean value) is 1.1 at this time, it indicates that the production behavior is abnormal.

[0093] The above-mentioned way can be used for basic judgment, of course, after the basic judgment is performed, other steps need to be continuously performed, because the error will cause the natural inaccuracy of this judgment method, generally, in order to facilitate the judgment, the error is set to be large.

[0094] In some possible implementation manners, when the behavior data is missing, the power consumption analysis curve is segmented using the characteristics of the power consumption analysis curve, the characteristics of the power consumption analysis curve including the slope change amount, the slope change time length, the stable interval amount and the stable time length.

[0095] In some examples, after the plurality of sub-power consumption analysis curves are obtained, the following way is used for processing:

[0096] S301, dividing the sub-power consumption analysis curve using a fixed time length to obtain a sub-power consumption analysis curve segment;

[0097] S302, analyzing the sub-power consumption analysis curve segment to obtain stability data;

[0098] S303, analyze the contrast reference curve corresponding to the sub-power consumption analysis curve segment to obtain reference stability data;

[0099] S304, compare the stability data with the reference stability data to determine the running state of the terminal, and the running state includes a stable running state and a non-stable running state.

[0100] In steps S301 to S304, the sub-power consumption analysis curve is first segmented to obtain a plurality of sub-power consumption analysis curve segments, then the stability data of the sub-power consumption analysis curve segment is determined, then the contrast reference curve corresponding to the sub-power consumption analysis curve segment is analyzed to obtain the reference stability data.

[0101] The stability data of the sub-power consumption analysis curve segment and the reference stability data are obtained in the same way.

[0102] Finally, the stability data is compared with the reference stability data to determine the running state of the terminal, and the running state includes a stable running state and a non-stable running state.

[0103] Here, the running state of the terminal is determined by comparing the stability data with the reference stability data, which is a sub-running state. After obtaining all the sub-running states, the proportion of normal sub-running states in all sub-running states is calculated. For example, the ratio is set to 0.8, and when the calculated proportion is greater than or equal to 0.8, it means that the running state of the terminal corresponding to the sub-power consumption analysis curve is normal, that is, the behavior data of the terminal corresponding to the sub-power consumption analysis curve is normal.

[0104] In some examples, the specific way of analyzing the sub-power consumption analysis curve segment and obtaining the stability data is as follows:

[0105] Obtain the data point group corresponding to the sub-power consumption analysis curve segment and use the data point group to construct an analysis reference curve;

[0106] Convert the analysis reference curve into the time domain for decomposition to obtain a continuous group and a discontinuous group;

[0107] Calculate the ratio of the continuous group to the discontinuous group, denoted as stability data, and the ratio includes a quantity ratio and an intensity ratio.

[0108] In the above manner, the stability data is determined by the proportion of continuous and discontinuous, and the stability data includes two data of quantity ratio and intensity ratio.

[0109] Here, the quantity refers to the number of curves after the analysis reference curve is converted into the time domain for decomposition, and the intensity refers to the intensity of the curve after the analysis reference curve is converted into the time domain for decomposition.

[0110] The quantity ratio and the intensity ratio are obtained by accumulation.

[0111] Here, continuous refers to the starting time and the ending time of the curve obtained by converting the analysis reference curve into the time domain for decomposition being the same as the starting time and the ending time of the analysis reference curve, and discontinuous refers to the starting time and / or the ending time of the curve obtained by converting the analysis reference curve into the time domain for decomposition being different from the starting time and the ending time of the corresponding analysis reference curve.

[0112] It should be understood that the current signal itself is a typical time-domain signal (amplitude curve changing over time), and the feature parameters extracted by time-domain decomposition can directly reflect the abnormal changes of the equipment operation state.

[0113] When the equipment is normally operated, the current curve usually presents stable time-domain characteristics (such as stable amplitude, regular fluctuation, and clear periodicity); and the electricity abnormality (such as mechanical jamming, component wear, and poor electrical contact) will break this rule, resulting in the abnormality of the current in the dimensions of amplitude, fluctuation frequency, duration, and pulse characteristics.

[0114] The sudden jump of the current (such as from 10A to 30A and lasting) may be a short circuit or a winding inter-turn fault; the frequent on-off of the current (such as periodically breaking for 0.5 seconds and then recovering) may be poor contact (such as loose wiring terminal) or intermittent shutdown of the equipment.

[0115] For example, the normal centrifugal pump current is stably at 25A±1A, if the time-domain decomposition finds that the current fluctuation range is expanded to 25A±5A, and the peak above 30A frequently appears, it may be caused by load instability due to impeller wear or pipeline blockage. In the long-term operation, if the window mean value gradually rises (such as the resistance increases due to the aging of the motor winding, and the current slowly rises), it may be a precursor of electrical performance degradation.

[0116] As can be seen from the above, when the equipment is abnormally operated, the corresponding current signal and / or voltage signal will change synchronously, and the corresponding energy consumption data will also change. Of course, these changes cannot be reflected by the time period reference, the equipment reference, and the process reference, but in the long-term operation process, these behaviors can cause the gradual deviation of the time period reference, the equipment reference, and the process reference.

[0117] In some examples, after comparing the stability data with the reference stability data, the state distribution of the stability data and the reference stability data is further compared, and a judgment result is given according to the state distribution, and the judgment result includes the same state and the different state.

[0118] The specific way of comparing the state distribution of the stability data and the reference stability data is as follows:

[0119] S401, obtain a data point group corresponding to a sub-power consumption analysis curve segment and divide the data point group according to a time length to obtain a plurality of sub-data point groups;

[0120] S402, determine a surrounding data density of data points in each sub-data point group and classify the data points in the sub-data point group according to the surrounding data density;

[0121] S403, statistically obtain a distribution result of different types of data points in a time sequence, denoted as a stability data distribution result;

[0122] S404, obtain a reference stability data distribution result using the same method;

[0123] S405, compare the stability data distribution result and the reference stability data distribution result to obtain a judgment result.

[0124] In steps S401 to S405, the surrounding data density of data points in each sub-data point group is first determined, then the data points in the sub-data point group are classified according to the surrounding data density, then the distribution result of different types of data points in a time sequence is statistically obtained, and finally the stability data distribution result and the reference stability data distribution result are compared.

[0125] In the above method, the purpose of dividing the data point group according to the time length is to reduce the number of data points in the sub-data point group, and generally the time length corresponding to one sub-data point group is 3-5 seconds.

[0126] Specifically, as shown in Figure 4 , the specific method of determining the surrounding data density of data points in each sub-data point group is to first select an arbitrary data point in a sub-data point group, then create a circle with the data point and statistically obtain the number of other data points existing in the circle, which can directly reflect the distribution density of the data points.

[0127] Then, the data points are arranged according to the distribution density, and every ten or every twenty in a sequential sequence is a group, of course, this is only an example.

[0128] Statistically obtaining the distribution result of different types of data points in a time sequence means that the data points are sorted according to the generation time, at which time all the data points are in a straight line, and then the distribution result of data points of the same type is statistically obtained, as shown in Figure 5 , at which time the distribution of data points of the same type in the straight line is statistically obtained, mainly investigating whether there is an aggregation behavior.

[0129] The reference stability data distribution result is processed using the same method.

[0130] ComparisonFigure 5 and Figure 6 Comparing the stability data distribution result with the reference stability data distribution result refers to whether the distribution manners of the same type of data points in the stability data distribution result and the reference stability data distribution result are the same (completely the same or requiring the same number of proportion groups), if the same, it indicates that the sub-power consumption analysis curve segment and the corresponding comparison reference curve are the same, otherwise it indicates that they are different, at this time, the sub-power consumption analysis curve segment has an abnormal power consumption behavior.

[0131] The application also provides an industry chain early warning device, comprising:

[0132] a data acquisition unit, configured to acquire basic power consumption data sets of each terminal of an enterprise, each terminal corresponding to a basic power consumption data set;

[0133] a data cleaning unit, configured to clean the basic power consumption data sets to obtain analysis power consumption data sets, the cleaning including removing abnormal data and filling missing data;

[0134] a first data processing unit, configured to construct a power consumption analysis curve using the analysis power consumption data sets;

[0135] a second data processing unit, configured to acquire behavior data of the terminal and segment the power consumption analysis curve according to the behavior data to obtain a plurality of sub-power consumption analysis curves, the behavior data including a behavior type, a start time and an end time;

[0136] a third data processing unit, configured to associate and analyze the sub-power consumption analysis curve with a comparison reference curve according to the behavior data to obtain an analysis result;

[0137] a result judging unit, configured to give a judgment result according to the analysis result, the judgment result including a normal power consumption behavior and an abnormal power consumption behavior.

[0138] Further, after constructing the power consumption analysis curve using the analysis power consumption data sets, the method further comprises:

[0139] calculating an area value of the power consumption analysis curve and acquiring a production behavior quantity corresponding to the power consumption analysis curve;

[0140] calculating a production behavior mean value using the area value of the power consumption analysis curve and the production behavior quantity;

[0141] comparing the production behavior mean value with a production behavior standard value to determine a state of the production behavior mean value, the state including a normal value and an abnormal value.

[0142] Further, when the behavior data is missing, the power consumption analysis curve is segmented using a feature of the power consumption analysis curve, the feature of the power consumption analysis curve including a slope change amount, a slope change time length, a stability interval amount and a stability time length.

[0143] Further, after obtaining the plurality of sub-power consumption analysis curves, the method further comprises:

[0144] dividing the sub-power consumption analysis curve using a fixed time length to obtain a sub-power consumption analysis curve segment;

[0145] analyzing the sub-power consumption analysis curve segment to obtain stability data;

[0146] analyzing a comparison reference curve corresponding to the sub-power consumption analysis curve segment to obtain reference stability data;

[0147] comparing the stability data and the reference stability data to determine a running state of the terminal, the running state comprising a stable running state and a non-stable running state.

[0148] Further, analyzing the sub-power consumption analysis curve segment and obtaining the stability data comprises:

[0149] obtaining a data point group corresponding to the sub-power consumption analysis curve segment and constructing an analysis reference curve using the data point group;

[0150] transforming the analysis reference curve into a time domain for decomposition to obtain a continuous group and a discontinuous group;

[0151] calculating a ratio of the continuous group and the discontinuous group, denoted as the stability data, the ratio comprising a quantity ratio and an intensity ratio.

[0152] Further, after comparing the stability data and the reference stability data, the method further comprises comparing a state distribution of the stability data and the reference stability data and giving a judgment result according to the state distribution, the judgment result comprising a same state and a different state.

[0153] Further, comparing the state distribution of the stability data and the reference stability data comprises:

[0154] obtaining a data point group corresponding to the sub-power consumption analysis curve segment and dividing the data point group according to a time length to obtain a plurality of sub-data point groups;

[0155] determining a surrounding data density of data points in each sub-data point group and classifying the data points in the sub-data point group according to the surrounding data density;

[0156] statistically obtaining a distribution result of different types of data points in a time sequence, denoted as a stability data distribution result;

[0157] obtaining a reference stability data distribution result using the same method;

[0158] comparing the stability data distribution result and the reference stability data distribution result to obtain a judgment result.

[0159] In an example, the units in any of the above apparatuses can be one or more integrated circuits, configured to implement one or more of the above methods, e.g., one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0160] For another example, when the units in the apparatuses can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor that can invoke a program. For another example, these units can be integrated together in the form of a system-on-a-chip (SOC).

[0161] In the present application, various objects such as messages / information / devices / network elements / systems / apparatuses / actions / operations / processes / concepts, etc. that can occur are named. It can be understood that these specific names do not constitute a limitation on the related objects, and the names can be changed according to scenes, contexts or usage habits, etc. The technical meaning of the technical terms in the present application should be mainly determined according to the functions and technical effects embodied / implemented in the technical solutions.

[0162] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, apparatus and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0163] In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0164] 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, i.e., they may be located in one place, or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0165] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0166] It should also be understood that in various embodiments of the present application, first, second, etc. are only to represent that a plurality of objects are different. For example, the first time window and the second time window are only to represent different time windows. The above first, second, etc. should not have any effect on the time window itself, and should not limit the embodiments of the present application.

[0167] It should also be understood that in various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0168] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the technical solutions that essentially contribute to the prior art can be embodied in the form of software products, which are stored in a computer readable storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned computer readable storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, and various media that can store program codes.

[0169] The present application also provides an energy service SaaS operation and maintenance management platform, the platform comprising:

[0170] One or more memories for storing instructions; and

[0171] one or more processors to invoke and run the instructions from the memory to perform the method as recited in the above description.

[0172] The present application also provides a computer program product including instructions, which when executed, cause the terminal device and the network device to perform the operations of the terminal device and the network device corresponding to the above method.

[0173] The present application also provides a chip system including a processor to implement the functions involved in the above description, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0174] The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0175] The processor mentioned in any of the above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the above-mentioned feedback information transmission method.

[0176] In a possible design, the chip system further includes a memory, which is configured to store necessary program instructions and data. The processor and the memory can be decoupled and arranged on different devices, and connected through wired or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can be coupled on the same device.

[0177] Optionally, the computer instructions are stored in the memory.

[0178] Optionally, the memory is a storage unit in the chip, such as a register, a cache, etc. The memory can also be a storage unit in the terminal located outside the chip, such as a ROM or other type of static storage device that can store static information and instructions, a RAM, etc.

[0179] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0180] The non-volatile memory can be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory.

[0181] The volatile memory can be a RAM used as an external cache. RAM has many different types, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synch link DRAM (SLDRAM), and direct Rambus RAM.

[0182] The embodiments of the present disclosure are all the preferred embodiments of the present application, and are not intended to limit the protection scope of the present application, so that: any equivalent changes made according to the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A supply chain early warning method, characterized in that, include: Obtain basic power consumption data sets for each terminal of the enterprise; each terminal corresponds to one basic power consumption data set. The basic electricity consumption data set is cleaned to obtain the analysis electricity consumption data set. The cleaning process includes removing abnormal data and filling in missing data. Use the power consumption data set to construct a power consumption analysis curve; The terminal's behavior data is acquired and the power consumption analysis curve is segmented based on the behavior data to obtain multiple sub-power consumption analysis curves. The behavior data includes behavior type, start time, and end time. The power consumption analysis curve is correlated and analyzed with the comparison reference curve based on the behavioral data to obtain the analysis results; Based on the analysis results, a judgment is given, which includes normal electricity consumption behavior and abnormal electricity consumption behavior. After obtaining multiple sub-power consumption analysis curves, the following is also included: The sub-power consumption analysis curve is divided into segments using a fixed time length; By analyzing the power consumption curve segment, stability data can be obtained. By analyzing the power consumption analysis curve segment and the corresponding comparative reference curve, reference stability data is obtained. By comparing stability data with reference stability data, the operating status of the terminal is determined, including stable operating status and unstable operating status. The analysis of the power consumption curve segment and the resulting stability data include: Obtain the data point set corresponding to the sub-power consumption analysis curve segment and use the data point set to construct the analysis reference curve; The analysis reference curve is transferred to the time domain for decomposition, resulting in a continuous group and a discontinuous group; Calculate the ratio of continuous groups to discontinuous groups, and record it as stability data. The ratio includes the quantity ratio and the intensity ratio.

2. The supply chain early warning method according to claim 1, characterized in that, After constructing the power consumption analysis curve using the power consumption data set, it also includes: Calculate the area value of the power consumption analysis curve and obtain the production behavior quantity corresponding to the power consumption analysis curve; The average value of production activities is calculated using the area under the power consumption analysis curve and the quantity of production activities. By comparing the mean value of production behavior with the standard value of production behavior, the state of the mean value of production behavior is determined, including normal values ​​and abnormal values.

3. The supply chain early warning method according to claim 1, characterized in that, When behavioral data is missing, the power consumption analysis curve is segmented using its features, which include the slope change, slope change duration, stable interval, and stable duration.

4. The supply chain early warning method according to claim 1, characterized in that, After comparing the stability data with the reference stability data, the process also includes comparing the state distribution of the stability data and the reference stability data and giving a judgment result based on the state distribution. The judgment result includes whether the states are the same or different.

5. The supply chain early warning method according to claim 4, characterized in that, The state distributions of the comparative stability data and the reference stability data include: The data point groups corresponding to the sub-power consumption analysis curve segments are obtained, and the data point groups are divided according to the time length to obtain multiple sub-data point groups; Determine the surrounding data density of data points in each subgroup of data points and classify the data points in the subgroup of data points according to the surrounding data density; The distribution results of different types of data points in a time series are statistically analyzed and denoted as the stability data distribution results. The reference stability data distribution results were obtained using the same method; By comparing the stability data distribution results with the reference stability data distribution results, a judgment result is obtained.

6. A supply chain early warning device, characterized in that, include: The data acquisition unit is used to acquire basic power consumption data sets for each terminal of the enterprise, with each terminal corresponding to one basic power consumption data set; The data cleaning unit is used to clean the basic electricity consumption data set to obtain the analysis electricity consumption data set. The cleaning includes removing abnormal data and filling in missing data. The first data processing unit is used to construct power consumption analysis curves using the power consumption data set; The second data processing unit is used to acquire the terminal's behavior data and segment the power consumption analysis curve according to the behavior data to obtain multiple sub-power consumption analysis curves. The behavior data includes behavior type, start time and end time. The third data processing unit is used to correlate and analyze the sub-power consumption analysis curve with the comparison reference curve based on the behavioral data to obtain the analysis results; The result judgment unit is used to give a judgment result based on the analysis results. The judgment result includes normal power consumption behavior and abnormal power consumption behavior. After obtaining multiple sub-power consumption analysis curves, the following is also included: The sub-power consumption analysis curve is divided into segments using a fixed time length; By analyzing the power consumption curve segment, stability data can be obtained. By analyzing the power consumption analysis curve segment and the corresponding comparative reference curve, reference stability data is obtained. By comparing stability data with reference stability data, the operating status of the terminal is determined, including stable operating status and unstable operating status. The analysis of the power consumption curve segment and the resulting stability data include: Obtain the data point set corresponding to the sub-power consumption analysis curve segment and use the data point set to construct the analysis reference curve; The analysis reference curve is transferred to the time domain for decomposition, resulting in a continuous group and a discontinuous group; Calculate the ratio of continuous groups to discontinuous groups, and record it as stability data. The ratio includes the quantity ratio and the intensity ratio.

7. An energy service SaaS operation and maintenance management platform, characterized in that, The platform includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by a processor, executes the method as described in any one of claims 1 to 5.

Images