A method and system for analyzing the power data of a rapid temperature change test chamber

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a method and system for analyzing the power data of a rapid temperature change test chamber. The method includes: obtaining current data during the operation of the rapid temperature change test chamber; obtaining the fluctuation consistency of each current in the current data, and in response to the fluctuation consistency being greater than or equal to a threshold value, eliminating the corresponding current to obtain remaining current data; performing anomaly detection on the remaining current data to obtain abnormal currents and issuing an alarm. That is, the solution of the present invention can accurately analyze the power data of the rapid temperature change test chamber.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method and system for analyzing power data of a rapid temperature change test chamber. Background Art

[0002] A rapid temperature change test chamber (also known as a fast temperature change test chamber) is an environmental test device used to simulate the effects of rapid temperature changes on equipment or materials. It tests the performance stability of equipment or materials under different temperature conditions by rapidly changing the internal temperature. Its main applications are in the fields of electronics, electricity, machinery, automobiles, aerospace, etc., especially in product quality verification and environmental adaptability testing.

[0003] Since the rapid temperature change test chamber needs to frequently adjust the temperature, the power consumption of the equipment also fluctuates accordingly. And power data reflects the operating status and energy efficiency of the equipment, and is an important indicator for monitoring equipment performance, evaluating energy use efficiency, and diagnosing potential faults. Therefore, through in-depth analysis of power data, abnormal operation of the equipment can be detected in a timely manner, so as to take effective maintenance and repair measures to avoid equipment failure or damage.

[0004] In related technologies, such as a patent application document of an environmental simulation test chamber controller and control method disclosed with the publication number CN116165456A, it realizes real-time monitoring of the operating status of each component of the simulation test chamber, rapid fault location, and rapid protection after a fault occurs by embedding a controller.

[0005] When performing rapid fault location and rapid protection in the above solution, it is by comparing the collected data with the preset protection threshold value, and controlling the operation of the faulty component to stop and perform maintenance based on the comparison result. However, due to the particularity of the rapid temperature change test chamber (the power data changes with the temperature), there are normal fluctuations during the operation of the rapid temperature change test chamber. At this time, by directly comparing the collected data with the protection threshold value, the operating status of the rapid temperature change test chamber cannot be accurately analyzed.

[0006] Therefore, how to accurately analyze the power data of the rapid temperature change test chamber to detect whether the subsequent rapid temperature change test chamber is faulty is particularly important. Summary of the Invention

[0007] The object of the present invention is to propose a method and system for analyzing power data of a rapid temperature change test chamber to solve the problem that it is difficult to accurately analyze the power data of the rapid temperature change test chamber in the prior art and thus the detection of the rapid temperature change test chamber cannot be accurately performed; for this purpose, the present invention provides solutions in the following two aspects.

[0008] In a first aspect, a method for power data analysis of a rapid temperature change test chamber provided by the present invention includes:

[0009] Obtain the current data during the operation of the rapid temperature change test chamber;

[0010] Obtain the fluctuation consistency of each current in the current data. In response to the fluctuation consistency being greater than or equal to a threshold value, the corresponding current is excluded to obtain the remaining current data;

[0011] Perform anomaly detection on the remaining current data to obtain abnormal currents and issue an alarm;

[0012] The fluctuation consistency is the similarity between the fluctuation feature vector of the current and the fluctuation feature vector of the temperature at the same moment; the fluctuation feature vector is a two-dimensional vector composed of the change rate and relative prominence of the target data; the target data is any current or any temperature;

[0013] The relative prominence characterizes the differential change of the target data within the corresponding window; the size of the window is a set length with the target data as the end of the window.

[0014] The above solution obtains the fluctuation feature vectors of each data in the current data and temperature data of the rapid temperature change test chamber, calculates the fluctuation consistency of the two fluctuation feature vectors, and uses this fluctuation consistency as the fluctuation consistency of the corresponding current to determine whether the corresponding current is virtual abnormal data (these data do not represent equipment failures or anomalies, but are natural responses to temperature changes), and then excludes these virtual abnormal data, which can avoid misjudgments caused by these currents, thereby ensuring the accuracy of data analysis. That is, the present invention can reduce the interference of normal fluctuations on the subsequent abnormal analysis of current data, improve the accuracy of power data analysis of the rapid temperature change test chamber, avoid misjudgments, and reduce equipment maintenance costs.

[0015] Optionally, the fluctuation consistency is:

[0016] ;

[0017] In the formula, is the fluctuation feature vector of the th current in the current data, is the fluctuation feature vector of the th temperature in the temperature data corresponding to the current data, is the modulus of the vector.

[0018] The above solution provides a method for accurately calculating the fluctuation consistency.

[0019] Optionally, the fluctuation consistency is the cosine similarity between the current fluctuation eigenvector and the temperature fluctuation eigenvector at the same moment.

[0020] Optionally, when the target data is any current, the relative prominence is:

[0021] ;

[0022] In the formula, is the th current in the current data, is the maximum value in the window corresponding to the th current in the current data, is the minimum value in the window corresponding to the th current in the current data.

[0023] The relative prominence calculated by the above scheme can measure the abnormality of a certain data point relative to other data points.

[0024] Optionally, when the target data is any current, the relative prominence is:

[0025] ; where is the th current in the current data, is the average value of the current in the window corresponding to the th current in the current data, and L is the set length of the window.

[0026] Optionally, when the target data is any current, the change rate is:

[0027] ; is the th current in the current data, is the th current in the current data.

[0028] The above change rate can intuitively reflect the dynamic change characteristics of the current.

[0029] Optionally, the CBLOF algorithm is used to perform anomaly detection on the remaining current data.

[0030] The CBLOF algorithm can accurately perform anomaly detection on the remaining current data.

[0031] In the second aspect, a power data analysis system for a rapid temperature change test chamber includes:

[0032] A processor;

[0033] A memory that stores computer instructions for power data analysis of a rapid temperature change test chamber. When the computer instructions are run by the processor, the system performs the above-mentioned power data analysis method for a rapid temperature change test chamber.

[0034] The beneficial effects of the present invention are as follows:

[0035] The solution of the present invention eliminates virtual abnormal data before identifying abnormal power data to ensure that real abnormal power data is screened out. Furthermore, the abnormal power data is identified to timely detect the abnormal operation of the equipment, so as to take effective maintenance and repair measures to avoid equipment failure or damage. Description of the Drawings

[0036] By referring to the following detailed description with reference to the drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become easily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0037] Figure 1 Schematically shows a flowchart of the steps of a power data analysis method for a rapid temperature change test chamber in this embodiment;

[0038] Figure 2 Schematically shows a structural block diagram of a power data analysis system for a rapid temperature change test chamber in this embodiment. Detailed Embodiments

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0040] The working principle of the rapid temperature change test chamber is to change the temperature inside the chamber through a heating or cooling system. In this process, the temperature change will directly affect the power consumption of the rapid temperature change test chamber. That is, when the rapid temperature change test chamber needs to be heated, devices such as electric heaters will consume more power, resulting in an upward trend in power data.

[0041] The present invention analyzes and processes the power data during the operation of the rapid temperature change test chamber to detect the operation state of the rapid temperature change test chamber.

[0042] Specifically, as Figure 1 shown, a power data analysis method for a rapid temperature change test chamber in this embodiment includes the following steps:

[0043] Step S1, obtain the current data during the operation of the rapid temperature change test chamber.

[0044] Specifically, in one embodiment, an electric current sensor is installed outside the rapid temperature change test chamber to obtain the current data during the operation of the rapid temperature change test chamber. At this time, the current data is the supply current of the rapid temperature change test chamber, and the acquisition frequency is 1 Hz. Specifically, the current data within 10 minutes or 30 minutes can be acquired.

[0045] In another embodiment, the current data can also be the current data of each component (such as the monitored compressor, fan, electric heater, etc.) inside the rapid temperature change test chamber.

[0046] It should be noted that the reason for using the current data during the operation of the rapid temperature change test chamber as the power data is as follows: The working principle of the rapid temperature change test chamber usually depends on the refrigeration and heating systems (such as refrigeration units, heaters, etc.). The power consumption of these systems will change with the change of temperature. When the temperature inside the test chamber changes rapidly, the load and current of the equipment will fluctuate accordingly. Therefore, by detecting the current fluctuations, the working state of the rapid temperature change test chamber can be preliminarily understood.

[0047] Of course, as other implementation manners, the power data can also be voltage data or power data.

[0048] Step S2, obtain the fluctuation consistency of each current in the current data. In response to the fluctuation consistency being greater than or equal to the threshold, the corresponding current is removed to obtain the remaining current data.

[0049] In this embodiment, the process of obtaining the fluctuation consistency is as follows:

[0050] Step S21, obtain the change rate and relative prominence degree of any current in the current data of the rapid temperature change test chamber, and construct a fluctuation feature vector corresponding to the current.

[0051] In one embodiment, the change rate is the degree of change of the current of the rapid temperature change test chamber at the current moment compared to the current at the previous moment.

[0052] Specifically, for the th current in the current data of the rapid temperature change test chamber, the change rate is expressed as: ;

[0053] In the formula, is the th current in the current data, is the th current in the current data. Among them, is the th current compared to the The degree of change of a current, the greater the degree of change, the higher the change rate of the th current.

[0054] In this embodiment, the relative prominence of each current in the current data of the rapid temperature change test chamber within its corresponding window is also obtained. Taking any current as the target data, the window of the target data is a local segment of the collected current data, and the data corresponding to the end of this local segment is the target data.

[0055] In this embodiment, the length of the window is L. Specifically, the value of L can be 11, that is, the window is 1×11; of course, the size of the window can also be determined according to the actual situation.

[0056] In one embodiment, the relative differences between each current in the rapid temperature change test chamber and the maximum and minimum values within the corresponding window are used as the relative prominence of the corresponding current in the current data of the rapid temperature change test chamber.

[0057] Specifically, the relative prominence of the th current in the current data is expressed as:

[0058] ;

[0059] In the formula, is the th current in the current data, is the maximum value in the window corresponding to the th current in the current data, is the minimum value in the window corresponding to the th current in the current data.

[0060] In the formula, is the comprehensive difference between the th current and the maximum and minimum values of the corresponding window, is the difference between the maximum and minimum values in the window corresponding to the th current; when the comprehensive difference is larger and the difference is smaller, the relative prominence of the th current is higher.

[0061] In another embodiment, the relative prominence of the th current in the current data can also be expressed as: the relative difference between the th current and the mean value of all currents within the corresponding window.

[0062] Specifically, the relative prominence of the th current can also be expressed as: ;

[0063] where, is the th current in the current data, is the average current within the window corresponding to the th current in the current data.

[0064] Furthermore, the fluctuation feature vector of the th current is expressed as:

[0065] ;

[0066] In the formula, is the relative prominence of the th current, is the change rate of the th current, is the fluctuation feature vector of the th current.

[0067] In this embodiment, the change rate of the current is used to measure how fast the data changes in a short period of time; in the power data of the rapid temperature change test chamber, the change rate can intuitively reflect the dynamic change characteristics of parameters such as power load or current. When the test chamber is in a state of rapid temperature change, the change rate of its power data will also increase accordingly. The relative prominence is used to measure the abnormality of a certain data point relative to other data points; in the power data, some data points may show significant abnormalities due to equipment failures, operation errors, or external interferences, etc. Therefore, in this embodiment, the fluctuation degree of the current is comprehensively described according to the change rate and relative prominence of each current in the current data of the rapid temperature change test chamber.

[0068] Step S22: Obtain the temperature data corresponding to the current data, calculate the change rate and relative prominence of the temperature corresponding to each current, and construct the fluctuation feature vector of the temperature.

[0069] In this embodiment, the temperature data during the operation of the rapid temperature change test chamber is obtained through the temperature sensors installed inside the rapid temperature change test chamber; the acquisition frequency of the temperature sensors is the same as that of the current sensors. In the temperature data of this embodiment, the acquisition moments of the temperature and the current in the current data are the same.

[0070] In one embodiment, the change rate of the th temperature is expressed as: ;

[0071] In the formula, is the th temperature in the temperature data, is the th temperature in the temperature data.

[0072] In this embodiment, the relative prominence of each temperature in the temperature data of the rapid temperature change test chamber within its corresponding window is also obtained; the window size is L, and this window takes each temperature as the window end and has a size of length L.

[0073] In one embodiment, the relative prominence of the th temperature in the temperature data is expressed as:

[0074] ;

[0075] In the formula, is the th temperature in the temperature data, is the maximum value in the window corresponding to the th temperature in the temperature data, is the minimum value in the window corresponding to the th temperature in the temperature data.

[0076] In another embodiment, the relative prominence of the th temperature in the temperature data can also be expressed as: the relative difference of the th temperature compared to the average value of all temperatures within its corresponding window.

[0077] Specifically, the relative prominence of the th temperature can also be expressed as:

[0078] ; where is the th temperature in the temperature data, is the average value of the temperatures within the window corresponding to the th temperature in the temperature data.

[0079] Furthermore, the fluctuation feature vector of the th temperature is expressed as:

[0080] ; in the formula, is the relative prominence of the th temperature, is the change rate of the th temperature, is the fluctuation feature vector of the th temperature.

[0081] The reason for introducing the temperature fluctuation characteristic vector is that the rapid temperature change test chamber, as an environmental testing device, will simulate different ambient temperatures, and the temperature change itself may cause a sudden change in power consumption, which may in turn affect the change in current; therefore, if the temperature change in the rapid temperature change test chamber is not considered, these sudden changes may be misjudged as abnormal data. In fact, they are just normal reactions to environmental changes, and the data of the normal reaction is virtual abnormal data. Therefore, further verification is required through the temperature fluctuation characteristic vector.

[0082] Step S23, calculating the fluctuation consistency of the current data of the rapid temperature change test chamber, eliminating the current whose fluctuation consistency is greater than or equal to a threshold, and obtaining the remaining current data.

[0083] In one embodiment, The consistency of the fluctuation of the current and the corresponding temperature It is expressed as: ; For the The fluctuation characteristic vector of the current, For the The temperature fluctuation characteristic vector, is the cosine similarity.

[0084] Among them, The current and the corresponding temperature data The higher the cosine similarity between the temperature fluctuation feature vectors, the higher the consistency between the two.

[0085] In another embodiment, The current and the corresponding temperature data The consistency of temperature fluctuations It can also be expressed as: ;

[0086] In the formula, The current data The fluctuation characteristic vector of the current, is the temperature data corresponding to the current data The temperature fluctuation characteristic vector, is the magnitude of the vector.

[0087] in, Indicates The current and The smaller the difference, the higher the consistency. 0.1 is the preset hyperparameter to avoid the result being 0.

[0088] In this embodiment, after obtaining the fluctuation consistency of each current in the current data of the rapid temperature change test chamber, the virtual abnormal data in the current data of the rapid temperature change test chamber is eliminated by comparing the fluctuation consistency with a threshold value.

[0089] Specifically, a threshold value a is set. When the fluctuation consistency of each current in the current data of the rapid temperature change test chamber is greater than or equal to this threshold value, it can be considered that the current in the current data of the rapid temperature change test chamber has a high consistency with the temperature in the corresponding temperature data, that is, the fluctuation shown by the current of this rapid temperature change test chamber is caused by the external adjustment of the temperature in the test chamber (due to the sudden change of the current data caused by the rapid temperature change test chamber, resulting in the virtual abnormal performance of the current at this moment). The fluctuation it shows is a normal fluctuation, and the corresponding current belongs to the virtual abnormal data; at this time, if the abnormal detection is still carried out on this part of the virtual abnormal data, it may lead to misjudgment and waste of equipment maintenance resources. Therefore, it is necessary to eliminate it to reduce the interference of subsequent abnormal detection.

[0090] The value of the above threshold value a is 0.3. Of course, it can also be determined according to the actual situation.

[0091] By analyzing the fluctuation consistency of each current in the current data of the rapid temperature change test chamber with the temperature in the corresponding temperature data, it is possible to determine whether each current in the current data of the rapid temperature change test chamber is virtual abnormal data. Before performing abnormal detection on the current data of the rapid temperature change test chamber, this part of the virtual abnormal data is eliminated first, and the remaining current data is subjected to abnormal detection, which can avoid the problem of inaccurate abnormal detection, thereby improving the accuracy of the abnormal data recognition result.

[0092] Step S3: Perform abnormal detection on each remaining current data to obtain abnormal currents and give an alarm.

[0093] The abnormal detection in this embodiment can adopt the CBLOF algorithm or the LOF algorithm.

[0094] Taking the CBLOF algorithm as an example, the CBLOF algorithm (Cluster-Based Local Outlier Factor, clustering-based local outlier factor detection algorithm) is a method for abnormal detection, which combines the ideas of clustering and local outlier factor (LOF). The basic steps of the CBLOF algorithm include data clustering, distinguishing large clusters and small clusters, calculating the abnormal score, and finally judging the abnormal points according to the abnormal score.

[0095] In this embodiment, the CBLOF algorithm is used to perform abnormal detection on the remaining current data. When abnormal data is identified, an alarm can be issued to remind relevant staff to perform maintenance processing. The specific detection process of the CBLOF algorithm is well-known technology and will not be elaborated here.

[0096] Exemplarily, when an abnormal current is detected in a certain component, overcurrent protection needs to be activated; and the staff should be reminded to conduct inspections and repairs.

[0097] It should be noted that since the current data of the rapid temperature change test chamber usually has a certain degree of aggregation and periodicity, the CBLOF algorithm is adopted in this embodiment, which can effectively identify abnormal points based on the clustering characteristics of the data, and can also accurately screen out real abnormal data points by combining the local characteristics and clustering structure of the data.

[0098] Before identifying abnormal data in the current data of the rapid temperature change test chamber, the solution of the present invention can screen out virtual abnormal data according to the consistency between the current data and the temperature data changes during the operation of the rapid temperature change test chamber, and then eliminate the virtual abnormal data, that is, eliminate the data with fluctuating characteristics and whose fluctuations are synchronized with the temperature fluctuations, so as to avoid the problem of identifying the corresponding data as abnormal data when using the CBLOF algorithm for anomaly detection.

[0099] Since the power data of the rapid temperature change test chamber is usually used to monitor the operating state of the equipment, through a power data analysis method for a rapid temperature change test chamber of the present invention, it is possible to more intelligently determine the source of power fluctuations (whether it is caused by environmental factors or by equipment failures), and thus avoid unnecessary maintenance operations caused by environmental factor interference.

[0100] The present invention also provides a power data analysis system for a rapid temperature change test chamber. As Figure 2 shown, the system includes a processor and a memory, and the memory stores computer program instructions, which when executed by the processor implement a power data analysis method for a rapid temperature change test chamber according to the above of the present invention.

[0101] The system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be elaborated here.

[0102] In the present invention, the foregoing memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented by computer-readable / executable instructions stored or otherwise held by such a computer-readable medium.

[0103] In the description of this specification, the meaning of "a plurality of" is at least two, such as two, three, or more, etc., unless otherwise specifically defined.

[0104] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in the practice of the present invention.

Claims

1. A method for analyzing the power data of a rapid temperature change test chamber, characterized in that, Comprising: Obtaining current data during the operation of a rapid temperature change test chamber and temperature data corresponding to the current data; Obtaining the Fluctuation Consistency of the Current Data of a Rapid Temperature Change Test Chamber : ； In the formula, is the fluctuation feature vector of the th current in the current data, is the fluctuation feature vector of the th temperature in the temperature data corresponding to the current data, is the modulus of the vector; In response to the fluctuation consistency being greater than or equal to a threshold value, the corresponding current is removed to obtain remaining current data; Performing anomaly detection on the remaining current data to obtain abnormal current and giving an alarm; The fluctuation consistency is the similarity between the fluctuation feature vector of the current and the fluctuation feature vector of the temperature at the same moment; the fluctuation feature vector is a two-dimensional vector composed of the change rate and relative prominence of the target data; the target data is any current or any temperature; The relative prominence characterizes the differential change of the target data within the corresponding window, specifically: ； Wherein, is the th current in the current data, is the maximum value in the window corresponding to the th current in the current data, is the minimum value in the window corresponding to the th current in the current data; the size of the window is a set length with the target data as the end of the window.

2. The power data analysis method of a rapid temperature change test chamber according to claim 1, characterized in that The fluctuation consistency is the cosine similarity between the fluctuation feature vector of the current and the fluctuation feature vector of the temperature at the same moment.

3. The power data analysis method of a rapid temperature change test chamber according to claim 1 or 2, characterized in that, When the target data is any current, the relative prominence is as follows: ; among them, is the th current in the current data, is the average current within the window corresponding to the th current in the current data, and L is the set length of the window.

4. A method for analyzing the power data of a rapid temperature change test chamber according to claim 1, characterized in that, When the target data is any current, the rate of change is as follows: ; is the th current in the current data, is the th current.

5. A method for analyzing the power data of a rapid temperature change test chamber according to claim 1, characterized in that, The anomaly detection of the remaining current data is performed using the CBLOF algorithm.

6. A power data analysis system for a rapid temperature change test chamber, characterized in that, Comprising: A processor; A memory storing computer instructions for power data analysis of a rapid temperature change test chamber, and when the computer instructions are run by the processor, enabling the system to execute the power data analysis method of a rapid temperature change test chamber according to claim 1.

Images