A diesel generator overload monitoring method and system

Abstract

The present invention discloses a diesel generator overload monitoring method and system, which belongs to the technical field of diesel generators, and solves the problem that only based on the current data monitoring, it is impossible to give more accurate results, which will lead to the problem that subsequent maintenance personnel will be misled when repairing the diesel generator. It includes the following steps, continuously monitoring the vibration, temperature, noise, and exhaust color of the diesel generator; extracting the abnormal vibration time axis of the vibration change, extracting the abnormal temperature time axis of the temperature change, and judging whether the starting point of the abnormal temperature time axis is between the starting point and the end time of the abnormal vibration time axis, and if so, determining to output the abnormal vibration time axis as the filtering time axis. The present invention comprehensively judges the overload of the diesel generator by combining temperature and vibration external parameters, and improves the accuracy of fault judgment by analyzing the noise and exhaust gas color during abnormal periods, and assists operation and maintenance personnel in accurately troubleshooting faults.

Description

Technical Field

[0001] The present invention relates to the technical field of diesel generators, and in particular to a diesel generator overload monitoring method and system. Background Art

[0002] A diesel generator is a power generation device that uses diesel fuel as a power source. It generates mechanical energy through the combustion of diesel in an internal combustion engine, and then converts the mechanical energy into electrical energy through a generator. This type of generator has the characteristics of quick start-up, stable operation, and easy maintenance. It is widely used in emergency power supply, industrial production, construction and other fields, especially in places where the power grid is unstable or an independent power supply is required. Diesel generators can provide a continuous and stable power supply and are an indispensable part of the power system.

[0003] Diesel generator overload means that the diesel generator set is operated in excess of its rated load capacity, which may cause immeasurable losses to the equipment itself, the power system and even the entire social economy. Overload operation will increase engine wear and shorten its life, while increasing the risk of damage to the electrical system, and safety hazards will increase accordingly. In addition, overload will also lead to increased fuel consumption, worsening emissions, increased burden on the cooling system, and increased risk of overheating. In order to avoid these hazards, the capacity of the generator set should be reasonably configured, maintenance should be strengthened, overload protection devices should be installed, and the load should be arranged reasonably. Overload capacity is one of the important indicators for measuring the quality and performance of the generator, which determines the load size that the generator can withstand in a short period of time. The overload capacity of a diesel generator set is affected by factors such as engine power output, cooling system effect, and transmission reliability. In order to improve the overload capacity, an engine with appropriate power should be selected, the cooling system maintenance should be strengthened, and the reliability of the transmission should be checked regularly.

[0004] To determine whether a diesel generator is overloaded, you can monitor instrument readings such as ammeters, voltmeters, and power meters, observe the noise, vibration, and temperature changes of the generator, check the operating status of the load equipment, and check whether the protective devices are operating. If the ammeter reading exceeds the rated current, the voltmeter reading is lower than the normal value, the generator and load equipment have abnormal noise or vibration, the load equipment operates abnormally, or protective devices such as overload protectors and circuit breakers trip, these may be signs of generator overload. Combining this information, you can more accurately determine whether the generator is in an overload state and take appropriate measures to protect the generator.

[0005] However, diesel generators work continuously, and there is no situation where personnel are arranged to monitor them in real time, which will consume a lot of human resources. Therefore, the diesel generator is often monitored through a monitoring system, and then data is obtained to identify whether it is overloaded. Since the diesel generator makes a lot of noise when working, it is relatively difficult to extract abnormal noise. Therefore, the main data currently obtained is vibration and temperature changes. The two are judged to identify whether the diesel generator is overloaded. However, it is not accurate to judge based solely on the changes in the two. When the fuel system, air supply system, cooling system, and exhaust system are blocked, the diesel generator will also experience temperature overheating and vibration changes. Therefore, based solely on the current data monitoring, it is impossible to give a more accurate result, which will lead to the subsequent maintenance personnel being misled when repairing the diesel generator.

[0006] Therefore, a diesel generator overload monitoring method and system are proposed to solve or alleviate the above problems. Summary of the invention

[0007] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a diesel generator overload monitoring method and system.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] A diesel generator overload monitoring method comprises the following steps:

[0010] Continuously monitor the vibration, temperature, noise, and exhaust color of diesel generators;

[0011] Extract the abnormal vibration time axis of the vibration change, extract the abnormal temperature time axis of the temperature change, and determine whether the starting point of the abnormal temperature time axis is between the starting point and the end time of the abnormal vibration time axis. If so, determine to output the abnormal vibration time axis as the filtering time axis. If not, determine to output the abnormal temperature time axis as the filtering time axis.

[0012] The noise of the diesel generator is filtered by filtering the time axis, and the noise of the diesel generator within the filtering time axis is intercepted;

[0013] In the noise of the diesel generator in the filtering time axis, the noise of the normally operating diesel generator is removed to obtain the abnormal noise, and the presence or absence of the abnormal noise is determined. If there is no abnormal noise, the output result is that there is no overload problem. If there is abnormal noise, proceed to the subsequent steps.

[0014] By filtering the time axis, the exhaust color of the diesel generator is intercepted and the color is judged. If the exhaust color is black smoke or white smoke, the output result is an overload problem. If the exhaust color is transparent or grayish white, the output result is not an overload problem.

[0015] Preferably, the method further comprises the following steps:

[0016] After determining that the output result is an overload problem, the abnormal noise content is matched with the known overload fault noises to analyze the specific overload fault.

[0017] Preferably, the continuous monitoring of the vibration, temperature, noise, and exhaust color of the diesel generator comprises the following steps:

[0018] The vibration condition of the diesel generator is collected through the vibration collection module, and the vibration condition of the diesel generator in normal operation and the change of the vibration condition of the diesel generator on a time axis are obtained;

[0019] The temperature condition of the diesel generator is collected through the temperature collection module, and the temperature change of the diesel generator over a period of time is obtained;

[0020] The noise condition of the diesel generator is collected through the noise collection module, and the noise condition of the diesel generator in normal operation and the noise condition of the diesel generator on a time axis are obtained;

[0021] The exhaust color of the diesel generator is collected through the visual acquisition module, and the exhaust video of the diesel generator on a time axis is obtained.

[0022] Preferably, the extracting of the abnormal vibration time axis of the vibration change and the extracting of the abnormal temperature time axis of the temperature change comprises the following steps:

[0023] The vibration acquisition module extracts the vibration changes of the diesel generator on a certain axis over a period of time. ,in, represents the vibration condition at time t, For the start time, For the end moment;

[0024] The data processing module calculates the mean value based on the vibration of the diesel generator running normally within the T time interval. ;

[0025] The data processing module sets the vibration over-limit threshold k. When the vibration of the diesel generator exceeds the mean value by k times, it is identified as abnormal vibration.

[0026] The data processing module sets a duration window to extract the abnormal vibration time axis of the vibration condition change, and the abnormal vibration time axis set Including time series , where the vibration value at each time point t is Above average k times of , and the time point sequence lasts for more than minutes, where n is the nth time point;

[0027] The temperature acquisition module extracts the temperature changes of the diesel generator over a period of time ,in, Represents the temperature at time t;

[0028] The data processing module calculates the mean value based on the temperature of the normally operating diesel generator within the T time interval. ;

[0029] The data processing module sets a temperature over-limit threshold w. When the temperature of the diesel generator exceeds the average value by w times, it is considered abnormal temperature.

[0030] The data processing module sets a duration window to extract the abnormal temperature time axis of temperature changes, and the abnormal temperature time axis set Including time series , where the temperature at each time point t is Temperature conditions exceeding normal diesel generator operation w times of .

[0031] Preferably, the step of removing the noise of the diesel generator in normal operation from the noise of the diesel generator in the filtering time axis to obtain the abnormal noise comprises the following steps:

[0032] The data processing module filters the noise of the diesel generator within the time axis Perform noise filtering, denoising, and normalization processing;

[0033] The data processing module takes the noise of the diesel generator in normal operation ;

[0034] The data processing module uses short-time Fourier transform to analyze the noise of a normally operating diesel generator. Analyze and obtain the time-frequency domain characteristics of the signal ,in, is the short-time Fourier transform spectrum at frequency f and time t;

[0035] The data processing module creates a noise template from the extracted features , noise template Used to represent the noise level of a diesel generator in normal operation;

[0036] The data processing module processes the noise of the diesel generator within the filtered time axis. Use short-time Fourier transform to obtain the time-frequency domain characteristics of the noise of the diesel generator in the filtered time axis ;

[0037] The data processing module measures the noise of the diesel generator within the filtering time axis by calculating the cosine similarity. Noise level compared to normal operation of a diesel generator The similarity of ,in, is the inner product, is the norm;

[0038] The data processing module removes the noise template After similar costs, the residual noise obtained is abnormal noise .

[0039] Preferably, intercepting the exhaust video of the diesel generator by filtering the time axis and judging the color comprises the following steps:

[0040] The data processing module converts each frame of the diesel generator exhaust video from the RGB color space to the HSV color space. , ;

[0041] The data processing module defines the exhaust position in the image as a region of interest ROI, and selects the region of interest ROI by detecting the exhaust position in the image through an object detection algorithm;

[0042] The data processing module calculates the average values ​​of hue H, saturation S, brightness V, and hue of the region of interest ROI. , the average value of saturation , the average brightness , where N is the number of pixels in the region of interest ROI;

[0043] The data processing module determines the exhaust color condition by the average values ​​of the hue H, saturation S, and brightness V of the region of interest ROI. The exhaust color condition includes normal condition and abnormal condition. The normal condition includes transparent gas and gray-white smoke, and the abnormal condition includes black smoke and white smoke.

[0044] Preferably, the data processing module determines the exhaust color by the average values ​​of the hue H, saturation S, and brightness V of the region of interest ROI, including the following steps:

[0045] Define normal as the average hue , Saturation average , average brightness ;

[0046] Define black smoke as the average hue , Saturation average , average brightness ;

[0047] Define white smoke as the average hue , Saturation average , average brightness ;

[0048] According to the above definition, the exhaust color is judged and the result is output.

[0049] Preferably, after the output result is determined to be an overload problem, the abnormal noise content is matched with the known overload fault noises to analyze the specific overload fault, including the following steps:

[0050] The data storage module records the noise characteristics of different fault types when the diesel generator is overloaded, and generates noise templates for multiple fault modes , where i is a different fault type;

[0051] The data processing module uses cosine similarity to compare Noise template with multiple failure modes The similarity of , determine whether a certain fault type exists based on the similarity value;

[0052] After the data processing module obtains a certain fault type, it outputs it as a specific overload fault.

[0053] The present invention also provides a diesel generator overload monitoring system for implementing the above-mentioned diesel generator overload monitoring method, comprising a vibration acquisition module, a temperature acquisition module, a noise acquisition module, a visual acquisition module, a data processing module, and a data storage module, wherein the vibration acquisition module is used to collect the vibration condition of the diesel generator, the temperature acquisition module is used to collect the temperature condition of the diesel generator, the noise acquisition module is used to collect the noise condition of the diesel generator, the visual acquisition module is used to collect the exhaust color condition of the diesel generator, the data storage module is used to record the noise characteristics of different fault types occurring when the diesel generator is overloaded, and the data processing module is used to adjust and identify according to different parameters, and output the results for reference.

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

[0055] The present invention can combine parameters other than temperature and vibration to further determine the overload situation of the diesel generator. In the present invention, the abnormal time period of the diesel generator is determined by the changes in temperature and vibration, and then the noise emitted by the diesel generator in this time period is extracted, and the noise emitted by the diesel generator under normal working conditions is used for filtering, thereby ensuring that the residual noise is the abnormal noise when the diesel generator is working abnormally, and at the same time, the color of the exhaust gas from the diesel generator is judged, so as to determine from multiple links and angles that the problem of the diesel generator at this time is clearly its overload situation, and then the processed abnormal noise can be matched by the means of noise matching, so as to provide reference opinions on the fault type to the operation and maintenance personnel when repairing the diesel generator, thereby improving the accuracy of the judgment of the operation and maintenance personnel on the problem of diesel generator overload, and can also accurately check small problems under the big problem of overload, with better accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 It is a flowchart of the present invention;

[0058] Figure 2 It is a structural block diagram of the present invention.

[0059] In the figure: 1. Vibration acquisition module; 2. Temperature acquisition module; 3. Noise acquisition module; 4. Visual acquisition module; 5. Data processing module; 6. Data storage module. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0061] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0063] In the description of the present invention, it should be understood that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the product of the invention is conventionally placed when in use, or are the orientations or positional relationships conventionally understood by those skilled in the art. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0064] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0065] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0066] A diesel generator overload monitoring system, such as Figure 2 As shown, it includes a vibration acquisition module 1, a temperature acquisition module 2, a noise acquisition module 3, a visual acquisition module 4, a data processing module 5, and a data storage module 6. The vibration acquisition module 1 is used to collect the vibration condition of the diesel generator, the temperature acquisition module 2 is used to collect the temperature condition of the diesel generator, the noise acquisition module 3 is used to collect the noise condition of the diesel generator, the visual acquisition module 4 is used to collect the exhaust color condition of the diesel generator, the data storage module 6 is used to record the noise characteristics of different fault types when the diesel generator is overloaded, and the data processing module 5 is used to adjust and identify according to different parameters, and output the results for reference.

[0067] A diesel generator overload monitoring method, such as Figure 1 As shown, the following steps are included:

[0068] Continuously monitor the vibration, temperature, noise, and exhaust color of the diesel generator. Continuously monitor the vibration, temperature, noise, and exhaust color of the diesel generator, including the following steps:

[0069] The vibration condition of the diesel generator is collected by the vibration collection module 1, and the vibration condition of the diesel generator in normal operation and the change of the vibration condition of the diesel generator on a time axis are obtained;

[0070] The temperature condition of the diesel generator is collected by the temperature collection module 2, and the temperature condition change of the diesel generator on a time axis is obtained;

[0071] The noise condition of the diesel generator is collected through the noise collection module 3, and the noise condition of the diesel generator in normal operation and the noise condition of the diesel generator on a time axis are obtained;

[0072] The exhaust color of the diesel generator is collected through the visual collection module 4, and the exhaust video of the diesel generator on a time axis is obtained;

[0073] Extract the abnormal vibration time axis of the vibration change, extract the abnormal temperature time axis of the temperature change, and determine whether the starting point of the abnormal temperature time axis is between the starting point and the end time of the abnormal vibration time axis. If so, determine to output the abnormal vibration time axis as the filtering time axis. If not, determine to output the abnormal temperature time axis as the filtering time axis.

[0074] Extracting the abnormal vibration time axis of the vibration change and extracting the abnormal temperature time axis of the temperature change include the following steps:

[0075] The vibration acquisition module 1 extracts the vibration changes of the diesel generator on a certain axis over a period of time. ,in, represents the vibration condition at time t, For the start time, For the end moment;

[0076] The data processing module 5 calculates the mean value according to the vibration of the diesel generator in normal operation within the T time interval. ;

[0077] The data processing module 5 sets a vibration exceeding limit threshold k. When the vibration of the diesel generator exceeds the mean value by k times, it is identified as abnormal vibration.

[0078] The data processing module 5 sets a duration window to extract the abnormal vibration time axis of the vibration condition change, and the abnormal vibration time axis set Including time series , where the vibration value at each time point t is Vibration conditions exceeding normal diesel generator operation k times of , and the time point sequence lasts for more than minutes, where n is the nth time point;

[0079] Temperature acquisition module 2 extracts the temperature changes of the diesel generator on a time axis ,in, Indicates the temperature at time t;

[0080] The data processing module 5 calculates the mean value according to the temperature of the normally operating diesel generator within the time interval T. ;

[0081] The data processing module 5 sets a temperature over-limit threshold w. When the temperature of the diesel generator exceeds the average value by w times, it is considered as abnormal temperature.

[0082] The data processing module 5 sets a duration window to extract the abnormal temperature time axis of the temperature change, and the abnormal temperature time axis set Including time series , where the temperature at each time point t is Temperature conditions exceeding normal diesel generator operation w times of ;

[0083] The noise of the diesel generator is filtered by filtering the time axis, and the noise of the diesel generator within the filtering time axis is intercepted;

[0084] In the noise of the diesel generator in the filtering time axis, the noise of the normally operating diesel generator is removed to obtain the abnormal noise, and the presence or absence of the abnormal noise is determined. If there is no abnormal noise, the output result is that there is no overload problem. If there is abnormal noise, proceed to the subsequent steps.

[0085] The noise of the diesel generator in normal operation is removed from the noise of the diesel generator in the filtering time axis to obtain the abnormal noise, including the following steps:

[0086] Data processing module 5 obtains the noise of the diesel generator within the filtering time axis Perform noise filtering, denoising, and normalization processing;

[0087] Data processing module 5 obtains the noise of the normally operating diesel generator ;

[0088] Data processing module 5 uses short-time Fourier transform to analyze the noise of a normally operating diesel generator. Analyze and obtain the time-frequency domain characteristics of the signal ,in, is the short-time Fourier transform spectrum at frequency f and time t;

[0089] Data processing module 5 creates a noise template from the extracted features , noise template Used to represent the noise level of a diesel generator in normal operation;

[0090] The data processing module 5 processes the noise of the diesel generator within the filtered time axis. Use short-time Fourier transform to obtain the time-frequency domain characteristics of the noise of the diesel generator in the filtered time axis ;

[0091] Data processing module 5 measures the noise of the diesel generator within the filtering time axis by calculating the cosine similarity Noise level compared to normal operation of a diesel generator The similarity of ,in, is the inner product, is the norm;

[0092] Data processing module 5 removes the noise template After similar costs, the residual noise obtained is abnormal noise ;

[0093] By filtering the timeline, intercept the exhaust video of the diesel generator and judge the color. If the exhaust color is black smoke or white smoke, the output result is an overload problem. If the exhaust color is transparent or grayish white, the output result is not an overload problem.

[0094] By filtering the timeline to intercept the exhaust video of the diesel generator and determine the color, the following steps are included:

[0095] The data processing module 5 converts each frame of the exhaust video of the diesel generator captured by filtering the time axis from the RGB color space to the HSV color space. , ;

[0096] The data processing module 5 defines the exhaust position in the image as a region of interest ROI, and selects the region of interest ROI by detecting the exhaust position in the image through an object detection algorithm;

[0097] The data processing module 5 calculates the average values ​​of the hue H, saturation S, and brightness V of the region of interest ROI, and the average value of the hue , the average value of saturation , the average brightness , where N is the number of pixels in the region of interest ROI;

[0098] The data processing module 5 determines the exhaust color condition by the average value of the hue H, saturation S, and brightness V of the region of interest ROI. The exhaust color condition includes normal condition and abnormal condition. The normal condition includes transparent gas and gray-white smoke, and the abnormal condition includes black smoke and white smoke.

[0099] The data processing module 5 determines the exhaust color by the average values ​​of the hue H, saturation S, and brightness V of the region of interest ROI, including the following steps:

[0100] Define normal as the average hue , Saturation average , average brightness ;

[0101] Define black smoke as the average hue , Saturation average , average brightness ;

[0102] Define white smoke as the average hue , Saturation average , average brightness ;

[0103] According to the above definition, the exhaust color is judged and the result is output;

[0104] After determining that the output result is an overload problem, the abnormal noise content is matched with the known overload fault noises to analyze the specific overload fault;

[0105] After determining that the output result is an overload problem, the abnormal noise content is matched with the known overload fault noises to analyze the specific overload fault, including the following steps:

[0106] The data storage module 6 records the noise characteristics of different fault types when the diesel generator is overloaded, and generates noise templates for multiple fault modes. , where i is a different fault type;

[0107] Data processing module 5 uses cosine similarity to compare Noise template with multiple failure modes The similarity of , determine whether a certain fault type exists based on the similarity value;

[0108] After obtaining a certain fault type, the data processing module 5 outputs it as a specific overload fault.

[0109] The present invention makes an accurate diagnosis of the overload condition of the diesel generator by comprehensively analyzing multiple parameters. It not only considers temperature and vibration data, but also incorporates other key indicators to comprehensively evaluate the working status of the generator. First, the system monitors abnormal changes in temperature and vibration to identify specific periods when the generator may have problems. During these periods, the system collects noise data generated by the diesel generator and compares it with the noise pattern when the diesel generator is operating normally. Through this process, abnormal noise is screened out. In addition, the present invention also considers the color change of the exhaust gas emitted by the diesel generator as another important basis for judging overload problems.

[0110] Through this multi-angle analysis method, the present invention can clearly point out whether the problem of the diesel generator is overload. Furthermore, the system can also perform a detailed analysis of the abnormal noise through noise matching technology, and provide maintenance personnel with a specific fault type reference, thereby greatly improving the diagnostic accuracy of overload problems. This method not only improves the accuracy of fault judgment, but also helps operation and maintenance personnel to accurately identify and solve various minor problems related to overload, optimizes the maintenance process of the diesel generator, and ensures the stable operation and efficiency of the generator.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A diesel generator overload monitoring method, characterized in that: The following steps are included: Continuously monitor the vibration, temperature, noise, and exhaust color of diesel generators; Extract the abnormal vibration time axis of the vibration change, extract the abnormal temperature time axis of the temperature change, and determine whether the starting point of the abnormal temperature time axis is between the starting point and the end time of the abnormal vibration time axis. If so, determine to output the abnormal vibration time axis as the filtering time axis. If not, determine to output the abnormal temperature time axis as the filtering time axis. The noise of the diesel generator is filtered by filtering the time axis, and the noise of the diesel generator within the filtering time axis is intercepted; In the noise of the diesel generator in the filtering time axis, the noise of the normally operating diesel generator is removed to obtain the abnormal noise, and the presence or absence of the abnormal noise is determined. If there is no abnormal noise, the output result is that there is no overload problem. If there is abnormal noise, proceed to the subsequent steps. By filtering the timeline to intercept the exhaust video of the diesel generator and judge the color, if the exhaust color is black smoke or white smoke, the output result is an overload problem, if the exhaust color is transparent or grayish white, the output result is not an overload problem.

2. A diesel generator overload monitoring method according to claim 1, characterized in that: It also includes the following steps, After determining that the output result is an overload problem, the abnormal noise content is matched with the known overload fault noises to analyze the specific overload fault.

3. A diesel generator overload monitoring method according to claim 1, characterized in that: The continuous monitoring of the vibration, temperature, noise, and exhaust color of the diesel generator includes the following steps: The vibration condition of the diesel generator is collected by a vibration collection module (1), and the vibration condition of the diesel generator in normal operation and the change of the vibration condition of the diesel generator over a period of time are obtained; The temperature condition of the diesel generator is collected by the temperature collection module (2), and the temperature condition change of the diesel generator on a time axis is obtained; The noise condition of the diesel generator is collected through the noise collection module (3), and the noise condition of the diesel generator in normal operation and the noise condition of the diesel generator over a period of time are obtained; The visual acquisition module (4) is used to collect the exhaust color of the diesel generator and obtain the exhaust video of the diesel generator on a time axis.

4. A diesel generator overload monitoring method according to claim 3, characterized in that: The method of extracting the abnormal vibration time axis of the vibration change and the abnormal temperature time axis of the temperature change comprises the following steps: The vibration acquisition module (1) extracts the vibration changes of the diesel generator on a certain axis over a period of time. ,in, represents the vibration condition at time t, For the start time, For the end moment; The data processing module (5) calculates the mean value according to the vibration condition of the diesel generator in normal operation within the time interval T. ; The data processing module (5) sets a vibration exceeding limit threshold k, and when the vibration of the diesel generator exceeds the mean value by k times, it is identified as abnormal vibration; The data processing module (5) sets a duration window to extract the abnormal vibration time axis of the vibration condition change, and the abnormal vibration time axis set Including time series , where the vibration value at each time point t is Above average k times of , and the time point sequence lasts for more than minutes, where n is the nth time point; The temperature acquisition module (2) extracts the temperature changes of the diesel generator over a period of time. ,in, Indicates the temperature at time t; The data processing module (5) calculates the mean value according to the temperature of the normally operating diesel generator within the time interval T. ; The data processing module (5) sets a temperature over-limit threshold w. When the temperature of the diesel generator exceeds the average value by w times, it is considered as abnormal temperature. The data processing module (5) sets a duration window to extract the abnormal temperature time axis of the temperature change, and the abnormal temperature time axis set Including time series , where the temperature at each time point t is Temperature conditions exceeding normal diesel generator operation w times of .

5. A diesel generator overload monitoring method according to claim 3, characterized in that: The method of removing the noise of the diesel generator in normal operation from the noise of the diesel generator in the filtering time axis to obtain the abnormal noise includes the following steps: The data processing module (5) obtains the noise of the diesel generator within the filtering time axis Perform noise filtering, denoising, and normalization processing; The data processing module (5) obtains the noise of the normally operating diesel generator. ; The data processing module (5) uses short-time Fourier transform to analyze the noise of a normally operating diesel generator. Analyze and obtain the time-frequency domain characteristics of the signal ,in, is the short-time Fourier transform spectrum at frequency f and time t; The data processing module (5) creates a noise template from the extracted features , noise template Used to represent the noise level of a diesel generator in normal operation; The data processing module (5) processes the noise of the diesel generator within the filtered time axis. Use short-time Fourier transform to obtain the time-frequency domain characteristics of the noise of the diesel generator in the filtered time axis ; The data processing module (5) measures the noise of the diesel generator within the filtering time axis by calculating the cosine similarity. Noise level compared to normal operation of a diesel generator The similarity of ,in, is the inner product, is the norm; The data processing module (5) removes the noise template After similar costs, the residual noise obtained is abnormal noise .

6. A diesel generator overload monitoring method according to claim 3, characterized in that: The method of intercepting the exhaust video of the diesel generator by filtering the time axis and judging the color includes the following steps: The data processing module (5) converts each frame of the exhaust video of the diesel generator captured by filtering the time axis from the RGB color space to the HSV color space. , ; The data processing module (5) defines the exhaust position in the image as a region of interest (ROI), and selects the region of interest (ROI) by detecting the exhaust position in the image through an object detection algorithm; The data processing module (5) calculates the average values ​​of hue H, saturation S, brightness V, and hue of the region of interest ROI. , the average value of saturation , the average brightness , where N is the number of pixels in the region of interest ROI; The data processing module (5) determines the exhaust color condition by the average values ​​of the hue H, saturation S, and brightness V of the region of interest (ROI). The exhaust color condition includes a normal condition and an abnormal condition. The normal condition includes transparent gas and grayish white smoke, and the abnormal condition includes black smoke and white smoke.

7. A diesel generator overload monitoring method according to claim 6, characterized in that: The data processing module (5) determines the exhaust color condition by the average value of the hue H, saturation S, and brightness V of the region of interest ROI, including the following steps: Define normal as the average hue , Saturation average , average brightness ; Define black smoke as the average hue , Saturation average , average brightness ; Define white smoke as the average hue , Saturation average , average brightness ; According to the above definition, the exhaust color is judged and the result is output.

8. A diesel generator overload monitoring method according to claim 2, characterized in that: After the output result is determined to be an overload problem, the abnormal noise content is matched with the known overload fault noises to analyze the specific overload fault, including the following steps: The data storage module (6) records the noise characteristics of different fault types when the diesel generator is overloaded, and generates noise templates of multiple fault modes. , where i is a different fault type; The data processing module (5) uses cosine similarity to compare Noise template with multiple failure modes The similarity of , determine whether a certain fault type exists based on the similarity value; After obtaining a certain fault type, the data processing module (5) outputs it as a specific overload fault.

9. A diesel generator overload monitoring system, used to implement the diesel generator overload monitoring method according to any one of claims 1 to 8, characterized in that: The invention comprises a vibration collection module (1), a temperature collection module (2), a noise collection module (3), a visual collection module (4), a data processing module (5), and a data storage module (6), wherein the vibration collection module (1) is used to collect vibration conditions of the diesel generator, the temperature collection module (2) is used to collect temperature conditions of the diesel generator, the noise collection module (3) is used to collect noise conditions of the diesel generator, the visual collection module (4) is used to collect exhaust color conditions of the diesel generator, the data storage module (6) is used to record noise characteristics of different fault types when the diesel generator is overloaded, and the data processing module (5) is used to adjust and identify according to different parameters, and output the results for reference.

Images