Energy efficiency anomaly diagnosis method and device

Abstract

The invention provides an energy efficiency abnormity diagnosis method and device. According to the method, energy efficiency abnormity diagnosis of the target system is carried out based on the transfer entropy, and the energy efficiency abnormity of the system can be diagnosed more scientifically and reasonably. Besides, the transfer entropy is a statistic irrelevant to the model, so that the embodiment of the invention can be suitable for analyzing the causal relationship between subsystems in any industrial equipment system, and is used for diagnosing the subsystem causing the system energy efficiency abnormality.

Description

Technical Field

[0001] The present application relates to the technical field of data analysis and processing, and in particular to a method and device for diagnosing energy efficiency anomalies. Background Art

[0002] Climate change is a huge challenge facing human society. To this end, people need to reduce energy consumption to reduce carbon emissions. Improving energy efficiency is one of the ways to reduce energy consumption. China is an energy-intensive economy, and there is a lot of room for improvement in energy efficiency in some industrial fields. Based on information technology, improving energy efficiency by analyzing the operating status of industrial equipment is an effective way.

[0003] Energy efficiency anomaly (also referred to as energy efficiency anomaly in this article) refers to the phenomenon that the energy efficiency index is significantly higher than the normal operating state. Diagnosing the cause of energy efficiency anomaly, especially which part of the system equipment caused the anomaly, can provide directions and methods for improving energy efficiency. Traditional energy efficiency anomaly diagnosis usually relies on empirical knowledge, cannot accurately describe the cause and mechanism of the anomaly, and cannot be widely used, which has great limitations. Summary of the invention

[0004] At least one embodiment of the present application provides a method and device for diagnosing energy efficiency anomalies, which can scientifically and reasonably diagnose the causes of system energy efficiency anomalies.

[0005] According to one aspect of the present application, at least one embodiment provides an energy efficiency abnormality diagnosis method, including:

[0006] Periodically collecting energy input data, energy output data of the target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system;

[0007] Calculating the energy efficiency index of the target system using the energy input data and the energy output data;

[0008] Divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window;

[0009] Acquire an energy efficiency abnormal time window of the target system in the at least one time window;

[0010] According to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window, the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality is determined.

[0011] Optionally, the calculating, for each physical parameter indicator in each time window, respectively the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators includes:

[0012] Acquire a first time series consisting of physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window;

[0013] Delaying the second time series by the delay indicator to align with the first time series, and obtaining a first subsequence and a second subsequence according to the mutually aligned physical parameter indicators and energy efficiency indicators;

[0014] According to the first subsequence and the second subsequence, a transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated.

[0015] Optionally, the calculating the transfer entropy from the physical parameter indicator to the energy efficiency indicator under the delay indicator includes:

[0016] The transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated by an estimation algorithm based on Copula entropy.

[0017] Optionally, the energy input data includes the flow rate of input current or input fuel; and the energy output data includes the quantity of output energy-containing carriers.

[0018] Optionally, the energy efficiency index is the ratio of energy output data to energy input data collected at the same time.

[0019] Optionally, the physical parameter indicators used to characterize the operating status of each component of the target system include at least one of the following: temperature, pressure, humidity, fluid flow rate, current, and voltage.

[0020] Optionally, obtaining the energy efficiency abnormal time window of the target system in the at least one time window includes:

[0021] The energy efficiency abnormal time window of the target system in the at least one time window is detected by using a time series abnormality detection algorithm.

[0022] According to another aspect of the present application, at least one embodiment provides an energy efficiency abnormality diagnosis device, including:

[0023] A collection module, used to periodically collect energy input data, energy output data of a target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system;

[0024] A first calculation module, configured to calculate an energy efficiency index of the target system using the energy input data and the energy output data;

[0025] A second calculation module is used to divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window;

[0026] A first acquisition module, used for acquiring an energy efficiency abnormal time window of the target system in the at least one time window;

[0027] The first determination module is used to determine the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality according to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window.

[0028] Optionally, the second computing module is further used to:

[0029] Acquire a first time series consisting of physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window;

[0030] Delaying the second time series by the delay indicator to align with the first time series, and obtaining a first subsequence and a second subsequence according to the mutually aligned physical parameter indicators and energy efficiency indicators;

[0031] According to the first subsequence and the second subsequence, a transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated.

[0032] Optionally, the second computing module is further used to:

[0033] The transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated by an estimation algorithm based on Copula entropy.

[0034] Optionally, the energy input data includes the flow rate of input current or input fuel; and the energy output data includes the quantity of output energy-containing carriers.

[0035] Optionally, the energy efficiency index is the ratio of energy output data to energy input data collected at the same time.

[0036] Optionally, the physical parameter indicators used to characterize the operating status of each component of the target system include at least one of the following: temperature, pressure, humidity, fluid flow rate, current, and voltage.

[0037] Optionally, the first acquisition module is further used to:

[0038] The energy efficiency abnormal time window of the target system in the at least one time window is detected by using a time series abnormality detection algorithm.

[0039] According to another aspect of the present application, at least one embodiment provides a computer-readable storage medium, on which a program is stored. When the program is executed by a processor, the steps of the method described above are implemented.

[0040] Compared with the prior art, the energy efficiency anomaly diagnosis method and device provided in the embodiment of the present application diagnoses the energy efficiency anomaly of the target system based on the transfer entropy, which can diagnose the energy efficiency anomaly of the system more scientifically and reasonably. In addition, the transfer entropy is a model-independent statistic, so the embodiment of the present application can be applied to the analysis of the causal relationship between subsystems in any industrial equipment system, and is used to diagnose the subsystem that causes the energy efficiency anomaly of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0042] Figure 1 A schematic diagram of a flow chart of an energy efficiency abnormality diagnosis method according to an embodiment of the present application;

[0043] Figure 2 An example diagram of a time series of an embodiment of the present application;

[0044] Figure 3 An example diagram of transfer entropy corresponding to each physical parameter indicator of an embodiment of the present application;

[0045] Figure 4 A schematic diagram of the structure of the energy efficiency abnormality diagnosis device according to an embodiment of the present application;

[0046] Figure 5 Another structural schematic diagram of the energy efficiency anomaly diagnosis device according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0048] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in one embodiment" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. "And / or" in the specification and claims represents at least one of the connected objects.

[0049] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0050] The following description provides examples and does not limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the functions and arrangements of the elements discussed without departing from the spirit and scope of the present disclosure. Various examples may appropriately omit, replace, or add various procedures or components. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0051] The embodiment of the present application provides a method for diagnosing energy efficiency anomalies. The method performs energy efficiency anomaly diagnosis based on transfer entropy, thereby diagnosing system energy efficiency anomalies in a more scientific and reasonable manner and can be widely used in various systems.

[0052] Transfer Entropy is a causal relationship measurement tool based on information theory. Using the transfer entropy method, we can analyze the internal causal relationship mechanism of system operation, and then apply it to the diagnosis of energy efficiency anomalies, and give the root system components that cause energy efficiency anomalies, thus providing a direction for improving energy efficiency.

[0053] The transfer entropy described in the embodiments of the present application is a measure of information flow transfer between time series based on the definition of information theory, and is used to estimate the causal relationship strength from the source variables of the physical parameter coordinates of each subsystem of the target system to the target variable of the energy efficiency index based on the data collected from the target system. The transfer entropy is a model-independent statistic, so it can be applied to the analysis of causal relationships between subsystems in any industrial equipment system or civil equipment system, and can diagnose the target subsystem that causes abnormal system energy efficiency.

[0054] The principles of the embodiments of the present application are first described below.

[0055] The transfer entropy estimation algorithm adopted in the embodiment of the present application is a transfer entropy estimation algorithm based on Copula entropy (Copula Entropy), and its principle is that the transfer entropy can be represented by multiple Copula entropies, so the transfer entropy is estimated by estimating multiple Copula entropies. The Copula entropy estimation algorithm adopted in the embodiment of the present application includes but is not limited to a direct estimation method based on the definition of Copula entropy and a non-parametric estimation method based on ordinal statistics and entropy estimation algorithm.

[0056] The energy efficiency anomaly diagnosis method of the embodiment of the present application estimates a set of transfer entropies with different time delays in each time window. This is because the transfer of energy, matter and information in the system takes time, so there is a time delay in the causal effect from the subsystem to the energy efficiency index. The delay factor needs to be considered when calculating the causal strength from the subsystem to the energy efficiency index. The embodiment of the present application uses the maximum value of the transfer entropy corresponding to a set of estimated time delays as the causal strength from the subsystem to the system energy efficiency in the time window, and its basis is based on the following simulation experiment. In the simulation experiment, the inventor used the state space model to simulate the following system:

[0057] X i+1 =X i +ε

[0058] Y i+l =X i

[0059] Among them, X i is the system state at time i, Y i+lis the output of the system at time i+1, l represents the time delay from the system state to the system output, and ε represents noise. The simulation data of the system is obtained using this state space model, and the transfer entropy from X to Y under a set of different time delays is calculated. It is found that the transfer entropy corresponding to a delay of l is the maximum value of all transfer entropies. Therefore, the maximum value of the transfer entropy corresponding to a set of time delays can be used as the required causal relationship strength. Therefore, in the embodiment of the present application, the length of the time window needs to be greater than the length of the delay in the target system, and the calculated maximum delay index must also be greater than the delay in the target system and less than the length of each time window. Specifically, the delay in the target system can determine an approximate delay range based on empirical values ​​or through simulation.

[0060] The energy efficiency anomaly described in the embodiment of the present application refers to a situation where the energy efficiency index obviously deviates from the reference value under the normal operating state of the system, which can be a short-term anomaly, or a long-term anomaly or an intermittent anomaly. Specifically, a common time series anomaly detection algorithm can be used for anomaly detection, for example, a statistical-based algorithm, such as an autoregressive model (AR model), a moving average model (MA model), an autoregressive moving average model (ARMA model), a 3Sigma method, etc., a machine learning-based algorithm, such as K-Means, DBSCAN, LOF, etc., a neural network-based algorithm, such as MLP, CNN, ResNet, Wavenet, LSTM, GRU, AutoEncoder, etc., and other algorithms, such as Isolation Forest, One-Class SVM, XGBoost, etc.

[0061] Please refer to Figure 1 , an energy efficiency abnormality diagnosis method provided by an embodiment of the present application includes:

[0062] Step 11, periodically collect energy input data, energy output data of the target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system.

[0063] Here, the embodiment of the present application can collect energy input data, energy output data and physical parameter indicators used to characterize the operating status of each component of a target system (such as an industrial equipment system, a civil equipment system, etc.) within a certain period of time according to a preset sampling period. For example, the energy input data, energy output data and various physical parameter indicators within 3 days can be obtained by collecting data every 10 seconds.

[0064] Typically, an industrial equipment system / civilian equipment system includes multiple components (or multiple subsystems), and each component (subsystem) cooperates with each other to achieve energy conversion. The target system of the embodiment of the present application may be an industrial equipment system or a civilian equipment system, and the energy used by the target system includes but is not limited to electrical energy, thermal energy, kinetic energy, potential energy, etc. The target system typically includes multiple components / subsystems that work together to complete the energy form conversion process. The components / subsystems may be connected in series, in parallel, or in a mixed form of series and parallel.

[0065] Specifically, the energy input data may include data such as input current or input fuel flow, and the energy output data may include data such as the number of output energy-containing carriers (such as the volume, flow rate, and flow rate of output compressed air). In the embodiment of the present application, the physical parameter indicators used to characterize the operating status of each component of the target system are generally key operating parameters of the system related to energy form, including at least one of the following: temperature, pressure, humidity, current, voltage, fluid flow rate, etc.

[0066] Step 12: Calculate the energy efficiency index of the target system using the energy input data and the energy output data.

[0067] Here, the energy efficiency index refers to the ability of the target system to convert input energy into effective output energy. The energy efficiency index can be a ratio of energy output data and energy input data collected at the same time as an index, as shown in the following formula:

[0068]

[0069] In this way, through the above steps 11 and 12, multiple values ​​of the energy efficiency index and multiple values ​​of each physical parameter index within the target time period can be obtained.

[0070] Step 13, divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and take the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window.

[0071] Here, in step 13, the target time period is divided into at least one time window to determine a time period containing energy efficiency anomalies. The length of the time window can be set according to the characteristics of the detected anomaly type, while also taking into account the accuracy and reliability of the subsequent estimation of transfer entropy.

[0072] Specifically, a first time series consisting of the physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window may be first obtained. Then, the second time series is delayed by the delay indicator and aligned with the first time series, and a first subsequence and a second subsequence are obtained according to the aligned physical parameter indicators and energy efficiency indicators.

[0073] Figure 2 An example of obtaining a first subsequence and a second subsequence is provided, in which the time window includes 180 sampling point data, that is, the first time series (physical parameter index 1) and the second time series (energy efficiency index) both include 180 data, which are t=1, t=2, ..., t=180, a total of 180 sampling point data. When the delay index τ is 3, the second time series is delayed by 3 sampling points, and then the first subsequence and the second subsequence are obtained according to the sampling point data aligned with the first time series and the second time series, wherein the first subsequence is the data of t=4, t=5, ..., t=180, a total of 177 sampling points in the first time series, and the second subsequence is the data of t=1, t=2, ..., t=177, a total of 177 sampling points in the second time series.

[0074] Then, according to the first subsequence and the second subsequence, the transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated. Here, the transfer entropy from the physical parameter index to the energy efficiency index under the delay index can be calculated by an estimation algorithm based on Copula entropy. The estimation algorithm based on Copula entropy includes but is not limited to a direct estimation method based on the definition of Copula entropy and a non-parametric estimation method based on ordinal statistics and entropy estimation algorithm. The input of the transfer entropy estimation algorithm is the time series of the source variable (such as the first subsequence) and the time series of the target variable (such as the second subsequence), and the parameter is the delay value from the source variable to the target variable. The specific algorithm can refer to the relevant prior art, and the embodiments of the present application will not be repeated here.

[0075] In this way, for each physical parameter indicator, the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators can be calculated, and then the maximum transfer entropy is used as the transfer entropy of the physical parameter indicator in the time window, so that the transfer entropy of each physical parameter indicator in the time window can be obtained. Repeat the above steps for each time window, so as to obtain the transfer entropy of each physical parameter indicator in each time window.

[0076] Step 14: Obtain an energy efficiency abnormal time window of the target system in the at least one time window.

[0077] Here, the energy efficiency abnormal time window of the target system in the at least one time window is detected by a time series abnormality detection algorithm. The time series abnormality detection algorithm includes but is not limited to a statistical-based algorithm, a machine learning-based algorithm, a neural network-based algorithm, and other algorithms. In step 14, if the time window of energy efficiency abnormality is not detected, the process can be terminated. If the time window of energy efficiency abnormality is detected, step 15 is entered.

[0078] Step 15, determining the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality according to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window.

[0079] Here, the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality is determined according to the order of the transfer entropy values ​​of each physical parameter indicator in the energy efficiency abnormality time window from large to small. For example, in the energy efficiency abnormality time window, the transfer entropy values ​​of physical parameter indicators 1, 2, and 3 are 50, 60, and 120, respectively, where physical parameter indicator 1 is the physical parameter indicator of component 1 in the target system, physical parameter indicator 2 is the physical parameter indicator of component 2 in the target system, and physical parameter indicator 3 is the physical parameter indicator of component 3 in the target system. It can be determined that component 3 has the largest contribution to the energy efficiency abnormality, followed by component 2, and component 1 has the smallest contribution to the energy efficiency abnormality. Based on the above diagnostic results, optimization directions and methods can be provided for improving the energy utilization efficiency of the target system.

[0080] Through the above steps, the embodiment of the present application performs energy efficiency anomaly diagnosis of the target system based on transfer entropy, which can diagnose system energy efficiency anomaly in a more scientific and reasonable manner. In addition, since transfer entropy is a model-independent statistic, it can be applied to the analysis of causal relationships between subsystems in any industrial equipment system, and used to diagnose subsystems that cause system energy efficiency anomalies.

[0081] To help better understand the above method, the method of the embodiment of the present application is described below in conjunction with an application example on an air compressor system.

[0082] In this example, it is assumed that a system consisting of three air compressors (referred to as air compressors) provides compressed air as power for the factory production line. The three air compressors work in parallel, and the air compressors are clustered and controlled with stable air pressure output as the control target. The compressed air at the outlet of each air compressor is collected together through a pipeline to a main outlet, so there is a system response delay from the air compressor to the main outlet. Depending on the power demand of the production line, one or more of the three air compressors will be manually started to respond.

[0083] This example assumes that the data sampling frequency is 0.1 samples / second, that is, one sample is collected every 10 seconds, and the collection period is 4 consecutive working days. During the data collection period, 1 to 3 air compressors are working.

[0084] In this example, the working current data I of each air compressor is first collected. i , i=1,2,3, as physical parameter indicators to characterize its working state, voltage data U is collected at the same time, and the instantaneous power of each air compressor is calculated based on current and voltage as energy input data. This example also collects compressed air flow rate L data at the total air outlet. Since the compressed air pressure is relatively stable, the air flow rate can be used as a physical quantity to characterize the energy output data.

[0085] Based on the above data, the energy efficiency index of the system can be calculated from the instantaneous power of the input current (P = UI) and the flow rate of the output compressed air. The calculation formula is as follows:

[0086]

[0087] Then, the transfer entropy nonparametric estimation method based on Copula entropy is used to calculate each I i The transfer entropy from E to E. Divide all the time data into equal time windows, and set the length of each time window to half an hour (180 samples). Calculate the transfer entropy of a set of delay indicators in each time window. The delay window length is 6 minutes (36 samples), that is, the delay indicators are from 1 sample length to 36 sample lengths. In this way, each air compressor obtains 36 transfer entropy estimates for the 36 delay indicators in each time window, and then takes the maximum value to obtain the contribution of the air compressor to the energy efficiency index in the time window, such as Figure 3 As shown, the three curves correspond to three air compressors respectively.

[0088] By using the abnormal diagnosis algorithm, it can be determined that there is an energy efficiency anomaly in a certain time window. According to the transfer entropy calculation results corresponding to the time window, it can be known how much each air compressor contributes to the energy efficiency anomaly in the time window. A large transfer entropy value indicates a large contribution to the abnormal situation, and vice versa.

[0089] Based on the above method embodiments, the present application embodiment also provides an energy efficiency abnormality diagnosis device, please refer to Figure 4 , the device comprises:

[0090] A collection module 41 is used to periodically collect energy input data, energy output data of a target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system;

[0091] A first calculation module 42, configured to calculate an energy efficiency index of the target system using the energy input data and the energy output data;

[0092] A second calculation module 43 is used to divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window;

[0093] A first acquisition module 44 is used to acquire an energy efficiency abnormal time window of the target system in the at least one time window;

[0094] The first determination module 45 is used to determine the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality according to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window.

[0095] Through the above modules, the embodiment of the present application can scientifically and reasonably diagnose the causes of abnormal system energy efficiency.

[0096] Optionally, the second calculation module 43 is further used for:

[0097] Acquire a first time series consisting of physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window;

[0098] Delaying the second time series by the delay indicator to align with the first time series, and obtaining a first subsequence and a second subsequence according to the mutually aligned physical parameter indicators and energy efficiency indicators;

[0099] According to the first subsequence and the second subsequence, a transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated.

[0100] Optionally, the second calculation module 43 is further used for:

[0101] The transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated by an estimation algorithm based on Copula entropy.

[0102] Optionally, the energy input data includes the flow rate of input current or input fuel; and the energy output data includes the quantity of output energy-containing carriers.

[0103] Optionally, the energy efficiency index is the ratio of energy output data to energy input data collected at the same time.

[0104] Optionally, the physical parameter indicators used to characterize the operating status of each component of the target system include at least one of the following: temperature, pressure, humidity, fluid flow rate, current, and voltage.

[0105] Optionally, the first acquisition module 44 is further configured to:

[0106] The energy efficiency abnormal time window of the target system in the at least one time window is detected by using a time series abnormality detection algorithm.

[0107] It should be noted that the various systems provided in the above embodiments are devices corresponding to the above energy efficiency abnormality diagnosis method, and the implementation methods in the above embodiments are applicable to the embodiments of the device, and can also achieve the same technical effects. The above device provided in the embodiment of the present application can implement all the method steps implemented in the above method embodiment, and can achieve the same technical effects, and the parts and beneficial effects that are the same as those in the method embodiment will not be specifically described here.

[0108] Please refer to Figure 5 , a schematic diagram of the structure of another energy efficiency abnormality diagnosis device provided in an embodiment of the present application, the device includes: a processor 501, a transceiver 502, a memory 503, a user interface 504 and a bus interface.

[0109] In the embodiment of the present application, the device further includes: a program stored in the memory 503 and executable on the processor 501 .

[0110] The transceiver 502 is used to send and receive data under the control of the processor;

[0111] The processor 501 is configured to read the computer program in the memory and perform the following operations:

[0112] Periodically collecting energy input data, energy output data of the target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system;

[0113] Calculating the energy efficiency index of the target system using the energy input data and the energy output data;

[0114] Divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window;

[0115] Acquire an energy efficiency abnormal time window of the target system in the at least one time window;

[0116] According to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window, the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality is determined.

[0117] It can be understood that in the embodiment of the present application, when the computer program is executed by the processor 501, each process of the above-mentioned energy efficiency abnormality diagnosis method embodiment can be implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0118] exist Figure 5 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 501 and memory represented by memory 503. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 502 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface 504 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0119] The processor 501 is responsible for managing the bus architecture and general processing, and the memory 503 can store data used by the processor 501 when performing operations.

[0120] Optionally, the processor 501 is further configured to read the computer program in the memory and perform the following operations:

[0121] Acquire a first time series consisting of physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window;

[0122] Delaying the second time series by the delay indicator to align with the first time series, and obtaining a first subsequence and a second subsequence according to the mutually aligned physical parameter indicators and energy efficiency indicators;

[0123] According to the first subsequence and the second subsequence, a transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated.

[0124] Optionally, the processor 501 is further used to read the computer program in the memory and perform the following operations: calculating the transfer entropy from the physical parameter index to the energy efficiency index under the delay index through an estimation algorithm based on Copula entropy.

[0125] Optionally, the energy input data includes the flow rate of input current or input fuel; and the energy output data includes the quantity of output energy-containing carriers.

[0126] Optionally, the energy efficiency index is the ratio of energy output data to energy input data collected at the same time.

[0127] Optionally, the physical parameter indicators used to characterize the operating status of each component of the target system include at least one of the following: temperature, pressure, humidity, fluid flow rate, current, and voltage.

[0128] Optionally, the processor 501 is further configured to read the computer program in the memory and perform the following operations: detecting an energy efficiency abnormal time window of the target system in the at least one time window by using a time series anomaly detection algorithm.

[0129] It should be noted that the device in this embodiment is a device corresponding to the above-mentioned energy efficiency abnormality diagnosis method, and the implementation methods in the above-mentioned embodiments are all applicable to the embodiments of the device, and can also achieve the same technical effect. In the device, the transceiver 502 and the memory 503, as well as the transceiver 502 and the processor 501 can be connected through the bus interface communication, and the function of the processor 501 can also be implemented by the transceiver 502, and the function of the transceiver 502 can also be implemented by the processor 501. It should be noted that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect, and the parts and beneficial effects that are the same as the method embodiment in this embodiment will not be specifically repeated here.

[0130] In some embodiments of the present application, a computer-readable storage medium is further provided, on which a program is stored, and when the program is executed by a processor, the following steps are implemented:

[0131] Periodically collecting energy input data, energy output data of the target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system;

[0132] Calculating the energy efficiency index of the target system using the energy input data and the energy output data;

[0133] Divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window;

[0134] Acquire an energy efficiency abnormal time window of the target system in the at least one time window;

[0135] According to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window, the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality is determined.

[0136] When the program is executed by the processor, it can implement all the implementation methods of the above-mentioned energy efficiency abnormality diagnosis method and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0137] Those of ordinary skill 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 to be beyond the scope of this application.

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0139] In the embodiments provided in the present 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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.

[0140] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0141] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0142] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0143] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for diagnosing abnormal energy efficiency, characterized in that: include: Periodically collecting energy input data, energy output data of the target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system; Calculating the energy efficiency index of the target system using the energy input data and the energy output data; Divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window; Acquire an energy efficiency abnormal time window of the target system in the at least one time window; According to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window, the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality is determined.

2. The method according to claim 1, characterized in that The step of calculating, for each physical parameter indicator in each time window, the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators includes: Acquire a first time series consisting of physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window; Delaying the second time series by the delay indicator to align with the first time series, and obtaining a first subsequence and a second subsequence according to the mutually aligned physical parameter indicators and energy efficiency indicators; According to the first subsequence and the second subsequence, a transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated.

3. The method according to claim 2, characterized in that The calculating the transfer entropy from the physical parameter indicator to the energy efficiency indicator under the delay indicator includes: The transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated by an estimation algorithm based on Copula entropy.

4. The method according to claim 1, characterized in that The energy input data includes the flow rate of input current or input fuel; the energy output data includes the quantity of output energy-containing carriers.

5. The method according to claim 1, characterized in that The energy efficiency index is the ratio of energy output data to energy input data collected at the same time.

6. The method according to claim 1, characterized in that The physical parameter indicators used to characterize the operating status of each component of the target system include at least one of the following: temperature, pressure, humidity, fluid flow rate, current, and voltage.

7. The method according to claim 1, characterized in that The obtaining of the energy efficiency abnormal time window of the target system in the at least one time window includes: The energy efficiency abnormal time window of the target system in the at least one time window is detected by using a time series abnormality detection algorithm.

8. An energy efficiency abnormality diagnosis device, characterized in that: include: A collection module, used to periodically collect energy input data, energy output data of a target system within a target time period, and physical parameter indicators used to characterize the operating status of each component of the target system; A first calculation module, configured to calculate an energy efficiency index of the target system using the energy input data and the energy output data; A second calculation module is used to divide the target time period into at least one time window, and in each time window, for each physical parameter indicator, respectively calculate the transfer entropy from the physical parameter indicator to the energy efficiency indicator under different lengths of delay indicators, and use the maximum transfer entropy as the transfer entropy of the physical parameter indicator in the time window; A first acquisition module, used for acquiring an energy efficiency abnormal time window of the target system in the at least one time window; The first determination module is used to determine the contribution of each component corresponding to each physical parameter indicator to the energy efficiency abnormality according to the transfer entropy of each physical parameter indicator within the energy efficiency abnormality time window.

9. The device according to claim 8, characterized in that The second computing module is further used for: Acquire a first time series consisting of physical parameter indicators within the time window and a second time series consisting of the energy efficiency indicators within the time window; Delaying the second time series by the delay indicator to align with the first time series, and obtaining a first subsequence and a second subsequence according to the mutually aligned physical parameter indicators and energy efficiency indicators; According to the first subsequence and the second subsequence, a transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated.

10. The device according to claim 9, characterized in that The second computing module is further used for: The transfer entropy from the physical parameter index to the energy efficiency index under the delay index is calculated by an estimation algorithm based on Copula entropy.

11. The device according to claim 8, characterized in that The energy input data includes the flow rate of input current or input fuel; the energy output data includes the quantity of output energy-containing carriers.

12. The device according to claim 8, characterized in that The energy efficiency index is the ratio of energy output data to energy input data collected at the same time.

13. The device according to claim 8, characterized in that The physical parameter indicators used to characterize the operating status of each component of the target system include at least one of the following: temperature, pressure, humidity, fluid flow rate, current, and voltage.

14. The device according to claim 8, characterized in that The first acquisition module is further used for: The energy efficiency abnormal time window of the target system in the at least one time window is detected by using a time series abnormality detection algorithm.

Images