Automated temperature measurement and fault analysis method and related system
Through automated temperature measurement and fault analysis methods, SVM and decision tree algorithms are used to identify abnormal data, generate fault types and optimize strategies, the problem of traditional temperature measurement systems being affected by noise errors is solved, and more accurate temperature measurement and fault warning are achieved. Improves the stability and operation efficiency of the equipment.
Patent Information
- Application Number
- CN202411513343.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2025-01-07
AI Technical Summary
During the measurement process, traditional temperature measurement systems are susceptible to environmental noise and errors of the equipment themselves, resulting in insufficient accuracy and reliability of the measurement data, and it is difficult to identify potential faults early. Usually, remedial measures can only be taken after the fault occurs, affecting the equipment. Safe and normal power generation.
Automatic temperature measurement and fault analysis methods are adopted, including preprocessing of temperature information, data feature extraction and trend prediction, abnormal data is identified through SVM algorithm model and decision tree algorithm, fault types are generated, and optimization strategies are generated to achieve early warning and fault diagnosis.
Through data preprocessing and trend prediction, the accuracy of temperature measurement and system robustness are improved, fault identification is early, equipment downtime or maintenance probability is reduced, operating efficiency and equipment stability are optimized, and equipment safety is ensured.
Smart Images
Figure CN119272133A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of temperature measurement and analysis in power generation enterprises, and in particular relates to an automated temperature measurement and fault analysis method and a related system. Background Art
[0002] With the continuous improvement of the degree of industrial automation, energy industries such as power generation companies have increasingly stringent requirements for the safety and stability of equipment operation. In the power generation process of power generation companies, temperature is one of the key factors affecting equipment performance and safety. Temperature measurement and analysis of power generation companies is an important means to monitor and control the temperature of key parts during the operation of power generation companies, aiming to ensure the safe and efficient operation of equipment. Temperature measurement and analysis of power generation companies is of great significance to ensure the safe and efficient operation of power generation company equipment. With the continuous development of my country's power industry, the temperature measurement and analysis technology of power generation companies will continue to improve, providing strong support for power production. Through accurate temperature measurement and analysis, it will help improve the operation and management level of power generation companies, reduce production costs, and promote the sustainable development of the power industry.
[0003] However, traditional temperature monitoring systems usually lack effective data processing and analysis capabilities, which makes them vulnerable to environmental noise and equipment errors during the measurement process, thus reducing the accuracy and reliability of the measurement data. At the same time, there are deficiencies in identifying potential faults and early warnings, and remedial measures can often only be taken after the fault occurs, which not only affects the normal power generation of the power plant, but may also cause equipment damage and safety accidents. Summary of the invention
[0004] The purpose of the present invention is to overcome the problem that the measurement process is easily affected by environmental noise and errors of the equipment itself, thereby reducing the accuracy and reliability of the measurement data, and to provide an automated temperature measurement and fault analysis method and related system.
[0005] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides an automated temperature measurement and fault analysis method, comprising the following steps: Obtain the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal; Analyze temperature digital information, extract required data features, identify operation modes, and make temperature trend predictions based on data features and operation modes; Compare the predicted temperature trend with the preset temperature trend, and re-compare when the comparison result is within the preset threshold range; otherwise, extract abnormal data in the temperature information according to the predicted temperature trend; According to the abnormal data in the temperature information, the fault type is generated, and the optimization strategy is obtained according to the fault type.
[0006] A further improvement of the present invention is that the specific method for preprocessing the temperature information is as follows: The analog signal of the temperature information is amplified, filtered and linearized, and the processed temperature information is converted into a digital signal.
[0007] A further improvement of the present invention is that when the comparison result is not within a preset threshold range, an audible and visual alarm is issued.
[0008] A further improvement of the present invention is that the specific method of analyzing the temperature digital information and extracting the required data features is as follows: Convert temperature digital information into feature vector; Establish an SVM algorithm model, use feature vectors to train the SVM algorithm model, and obtain an SVM algorithm model that can distinguish normal modes and abnormal modes of temperature data; The temperature digital information is input into the established SVM algorithm model to obtain the required data features.
[0009] A further improvement of the present invention is that the calculation method of a good SVM algorithm model is as follows:
[0010] in, is the Lagrange multiplier, is the number of data features, For the The category labels of the data features, is the kernel function.
[0011] A further improvement of the present invention is that, according to the abnormal data in the temperature information, a specific method for generating a fault type is as follows: The abnormal data are classified using a decision tree algorithm, and the classified abnormal data are recursively selected to obtain the abnormal data with the highest information gain. The abnormal data with the highest information gain are analyzed to obtain the fault type.
[0012] A further improvement of the present invention is that the method of recursively selecting the classified abnormal data to obtain the abnormal data with the highest information gain is as follows:
[0013] in, is the information gain, is the entropy of category Y, It is the conditional entropy of category Y given feature X.
[0014] In a second aspect, the present invention provides an automated temperature measurement and fault analysis system, comprising: A data acquisition module is used to acquire the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal; The trend prediction module is used to analyze the temperature digital information, extract the required data features, and identify the operation mode, and perform temperature trend prediction based on the data features and operation mode; The data comparison module is used to compare the predicted temperature trend with the preset temperature trend. When the comparison result is within the preset threshold range, the comparison is repeated; otherwise, the abnormal data in the temperature information is extracted according to the predicted temperature trend. The fault analysis module is used to generate a fault type according to abnormal data in the temperature information, and obtain an optimization strategy according to the fault type.
[0015] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of an automated temperature measurement and fault analysis method when executing the computer program.
[0016] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of an automated temperature measurement and fault analysis method.
[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention effectively filters out environmental noise and the influence of the error of the device itself by preprocessing the temperature data, thereby obtaining more accurate temperature data. This data preprocessing can eliminate random noise in temperature measurement and improve measurement accuracy. The present invention can identify temperature anomalies early and predict potential faults by predicting temperature trends and extracting abnormal data. This trend prediction and comparison process helps to find problems before a fault occurs, achieves early intervention, and improves the efficiency of fault diagnosis. The optimization strategy generated based on the prediction results of the present invention can make corresponding adjustments before a fault occurs, reduce the probability of equipment shutdown or maintenance, thereby optimizing the overall operating efficiency of the system and reducing maintenance costs. When the temperature trend prediction result deviates from the preset trend comparison threshold, the present invention can dynamically re-compare and analyze to ensure the adaptability of the system. This feedback mechanism helps the device maintain stable temperature monitoring performance in a complex environment, increasing the robustness and reliability of the system. By extracting abnormal data and generating fault types, the present invention can more comprehensively analyze the operating status of the device, improve the stability and reliability of the device, and ensure the safety of the device in long-term operation. In summary, the present invention significantly overcomes the defect that the traditional measurement method is greatly interfered by the outside world, and can more accurately and effectively support the health management and operation optimization of the device. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 is a flow chart of the present invention; Figure 2 is a system diagram of the present invention; Figure 3 A system diagram of an embodiment. DETAILED DESCRIPTION
[0019] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.
[0020] Embodiment 1: See also Figure 1 , the automated temperature measurement and fault analysis method comprises the following steps: S1, obtain the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal.
[0021] S2, analyzes the temperature digital information, extracts the required data features, and identifies the operation mode, and predicts the temperature trend based on the data features and the operation mode.
[0022] S3, comparing the predicted temperature trend with the preset temperature trend, and re-comparing when the comparison result is within the preset threshold range; otherwise, extracting abnormal data in the temperature information according to the predicted temperature trend.
[0023] S4, generating a fault type according to the abnormal data in the temperature information, and obtaining an optimization strategy according to the fault type.
[0024] Embodiment 2: See also Figure 2 The present invention provides an automated temperature measurement and fault analysis system, comprising: A data acquisition module is used to acquire the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal; The trend prediction module is used to analyze the temperature digital information, extract the required data features, and identify the operation mode, and perform temperature trend prediction based on the data features and operation mode; The data comparison module is used to compare the predicted temperature trend with the preset temperature trend. When the comparison result is within the preset threshold range, the comparison is repeated; otherwise, the abnormal data in the temperature information is extracted according to the predicted temperature trend. The fault analysis module is used to generate a fault type according to abnormal data in the temperature information, and obtain an optimization strategy according to the fault type.
[0025] Embodiment 3: This embodiment provides an automated temperature measurement and fault analysis method for improving the accuracy of device temperature measurement, enhancing fault diagnosis capabilities, and optimizing device operating efficiency. Specifically, the following steps are included: Step 1: Get the temperature information of the target object, and process the analog signal of the temperature information through amplification, filtering and linearization to reduce noise and improve signal stability. Convert the processed temperature information into a digital signal to obtain clear temperature data, laying the foundation for subsequent analysis.
[0026] Step 2: Convert the temperature digital information into feature vectors, establish a support vector machine (SVM) algorithm model, and train the SVM model to identify and distinguish normal and abnormal patterns in temperature data.
[0027] The SVM algorithm model is optimized by the following objective function:
[0028] in, is the Lagrange multiplier, is the number of data features, For the The category labels of the data features, is the kernel function. The trained SVM model can identify normal and abnormal temperature features.
[0029] Step 3: According to the extracted data features, the temperature trend is predicted and the predicted temperature trend is compared with the preset normal temperature trend. If the comparison result is within the preset threshold range, the next comparison process will be started; if it is not within the threshold range, the sound and light alarm will be activated to indicate possible abnormal conditions.
[0030] Step 4: When the result of temperature trend prediction deviates from the preset threshold, the fault type is generated according to the abnormal data in the temperature information. The specific method is to use the decision tree algorithm to classify the abnormal data and recursively select the abnormal data with the highest information gain to ensure the accuracy of classification.
[0031] Information gain (IG) is calculated as follows:
[0032] in, is the information gain, is the entropy of category Y, is the conditional entropy of category Y given feature X. By analyzing the abnormal data with the highest information gain, the fault type of the equipment can be accurately determined.
[0033] Step 5: Based on the identified fault type, the system generates a corresponding optimization strategy. This strategy can be used to adjust the operation of the equipment, reduce the possibility of similar faults in the future, and thus improve the operating efficiency and reliability of the equipment.
[0034] In summary, this method realizes the accurate collection and processing of temperature information. It uses the SVM model and decision tree algorithm to effectively identify temperature anomalies and diagnose fault types. Its further alarm function and recursive information gain analysis mechanism contribute to reliable fault detection and equipment maintenance optimization in complex environments.
[0035] Embodiment 4: This embodiment introduces specific data and parameters to demonstrate the effectiveness of the method in a more practical manner. This embodiment uses an automated temperature measurement and fault analysis system for real-time monitoring and abnormal diagnosis of industrial equipment temperature.
[0036] Step 1: temperature information acquisition and preprocessing; The target device is set to be an industrial motor with a normal operating temperature range of 40°C to 80°C.
[0037] The temperature analog signal obtained by the sensor is in the range of 0°C to 100°C. The signal is amplified 20 times by an amplifier to enhance the recognition of slight temperature changes; it is then filtered out by a low-pass filter to remove noise signals with a frequency higher than 10 Hz to avoid the influence of high-frequency noise caused by environmental vibration and other factors.
[0038] The amplified and filtered analog signal is converted into a digital signal through a 12-bit ADC (Analog-to-Digital Converter). Assuming that 10 data points are collected per second, each data point represents the average temperature value of the time period for subsequent analysis.
[0039] Step 2: temperature digital information analysis; Feature extraction: Convert the digital temperature signal sequence into a feature vector. For example, a feature vector is formed by a set of average temperature, standard deviation, maximum value, and minimum value within 10 consecutive seconds: [mean, std, max, min].
[0040] SVM model training: The support vector machine (SVM) model is trained using historical data from previous periods. The data set includes normal operating temperatures (40°C to 80°C) and abnormal operating temperatures (>80°C or <40°C).
[0041] Objective function:
[0042] Among them, the number of samples n = 1000; Lagrange multipliers ; Kernel Function =Gaussian kernel, set the parameters to = 0.5.
[0043] The trained SVM model classifies the real-time temperature data into normal mode or abnormal mode.
[0044] Step 3: Temperature trend prediction and comparison; The slope of the temperature trend (increase / decrease rate) is calculated every minute, and the predicted result is compared with the preset temperature trend slope (normally the slope should be 0 to 0.5°C / min). When the predicted result slope exceeds 0.5°C / min and the trend exceeds the safety threshold of 80°C, an audible and visual alarm is activated to alert maintenance personnel.
[0045] Step 4: abnormal data extraction and fault type generation; Decision tree classification: After the alarm, the system inputs the current abnormal data into the decision tree algorithm and uses the historical abnormal temperature data as a benchmark. The decision tree recursively selects the abnormal data with the highest information gain.
[0046] Information gain calculation:
[0047] For example, the entropy of temperature anomaly data = 0.8, while the conditional entropy under the characteristic (such as the temperature rise rate) =0.4, then the information gain is =0.4.
[0048] The system analyzes the abnormal data with the highest information gain to determine the type of fault. For example, a sharp increase in temperature may indicate a cooling fault or excessive motor load.
[0049] Step 5: Optimization strategy generation; Depending on the type of fault, the system generates an optimization strategy. If a heat dissipation fault is detected, the system will recommend increasing the power of the ventilation equipment or adjusting the operating frequency of the equipment to prevent the temperature from rising further.
[0050] Optimization strategies are automatically recorded and added to the system’s fault prevention database for improved monitoring of future equipment.
[0051] Through this method, the device can achieve real-time monitoring and early warning of the temperature range of 40℃ to 80℃; the alarm is activated when the temperature exceeds 80℃ or the trend slope exceeds 0.5℃ / min. At the same time, the use of SVM and decision tree algorithms increases the accuracy of equipment anomaly detection to more than 95%.
[0052] Embodiment 5: See also Figure 3 As shown, the present invention also provides an electronic device 100 for automated temperature measurement and fault analysis method; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.
[0053] The memory 101 can be used to store the computer program 103, and the processor 102 implements the steps of the automated temperature measurement and fault analysis method described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
[0054] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.
[0055] The memory 101 in the electronic device 100 stores a plurality of instructions to implement an automated temperature measurement and fault analysis method, and the processor 102 can execute the plurality of instructions to implement: Obtain the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal; Analyze temperature digital information, extract required data features, identify operation modes, and make temperature trend predictions based on data features and operation modes; Compare the predicted temperature trend with the preset temperature trend, and re-compare when the comparison result is within the preset threshold range; otherwise, extract abnormal data in the temperature information according to the predicted temperature trend; According to the abnormal data in the temperature information, the fault type is generated, and the optimization strategy is obtained according to the fault type.
[0056] Embodiment 6: If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).
[0057] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0058] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0059] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. Automated temperature measurement and fault analysis method, characterized in that: The following steps are involved: Acquire the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal; Analyze temperature digital information, extract required data features, identify operation modes, and make temperature trend predictions based on data features and operation modes; Compare the predicted temperature trend with the preset temperature trend, and re-compare when the comparison result is within the preset threshold range; Otherwise, extract abnormal data from the temperature information based on the predicted temperature trend; According to the abnormal data in the temperature information, the fault type is generated, and the optimization strategy is obtained according to the fault type.
2. The automated temperature measurement and fault analysis method according to claim 1, characterized in that: The specific method for preprocessing temperature information is as follows: The analog signal of the temperature information is amplified, filtered and linearized, and the processed temperature information is converted into a digital signal.
3. The automated temperature measurement and fault analysis method according to claim 1, characterized in that: When the comparison result is not within the preset threshold range, an audible and visual alarm will be issued.
4. The automated temperature measurement and fault analysis method according to claim 1, characterized in that: The specific method for analyzing temperature digital information and extracting the required data features is as follows: Convert temperature digital information into feature vector; Establish an SVM algorithm model, use feature vectors to train the SVM algorithm model, and obtain an SVM algorithm model that can distinguish normal modes and abnormal modes of temperature data; The temperature digital information is input into the established SVM algorithm model to obtain the required data features.
5. The automated temperature measurement and fault analysis method according to claim 4, characterized in that: The calculation method of a good SVM algorithm model is as follows: in, is the Lagrange multiplier, is the number of data features, For the The category labels of the data features, is the kernel function.
6. The automated temperature measurement and fault analysis method according to claim 1, characterized in that: The specific method of generating the fault type according to the abnormal data in the temperature information is as follows: The abnormal data are classified using a decision tree algorithm, and the classified abnormal data are recursively selected to obtain the abnormal data with the highest information gain. The abnormal data with the highest information gain are analyzed to obtain the fault type.
7. The automated temperature measurement and fault analysis method according to claim 6, characterized in that: The method of recursively selecting the classified abnormal data to obtain the abnormal data with the highest information gain is as follows: in, is the information gain, is the entropy of category Y, It is the conditional entropy of category Y given feature X. 8.Automated temperature measurement and fault analysis system, characterized in that: include: A data acquisition module is used to acquire the temperature information of the target object, pre-process the temperature information, and obtain the required temperature digital signal; The trend prediction module is used to analyze the temperature digital information, extract the required data features, and identify the operation mode, and perform temperature trend prediction based on the data features and operation mode; A data comparison module is used to compare the predicted temperature trend with the preset temperature trend, and re-compare when the comparison result is within the preset threshold range; Otherwise, extract abnormal data from the temperature information based on the predicted temperature trend; The fault analysis module is used to generate a fault type according to abnormal data in the temperature information, and obtain an optimization strategy according to the fault type.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the automated temperature measurement and fault analysis method according to any one of claims 1 to 7 are implemented.
10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automated temperature measurement and fault analysis method according to any one of claims 1 to 7 are implemented.