A signal analysis method for an electronically controlled single-cylinder diesel engine

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a signal analysis method for an electronically controlled single-cylinder diesel engine. The method includes: obtaining the vibration amplitude regularity and the vibration change amplitude at a moment; obtaining the abnormality degree of the vibration amplitude at each moment according to the difference between every two adjacent elements in the vibration change amplitude sequence at each moment and the vibration amplitude regularity at each moment; obtaining the optimized abnormality degree of the vibration amplitude at each moment according to the vibration amplitude corresponding to each moment in the judgment sequence of the vibration amplitude at each moment and the vibration amplitude regularity; obtaining the true vibration amplitude sequence of each vibration sensor; further obtaining the true sound pressure sequence of each sound level meter; and analyzing the true vibration amplitude sequence and the true sound pressure sequence of any vibration sensor and sound level meter to obtain the fault type of the single-cylinder diesel engine. The present invention can accurately eliminate noise and accurately obtain the fault type of the single-cylinder diesel engine.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a signal analysis method for an electronically controlled single-cylinder diesel engine. Background Art

[0002] As a power machine widely used in the fields of oil mines, railway traction, stationary power generation, construction machinery, and ships, diesel engines are increasingly developing towards large-scale, complex, and precise directions. As the most commonly used power equipment, once a certain part or link fails in a diesel engine, it will cause damage to key equipment and even result in huge economic losses. Therefore, by analyzing various signals collected by various vibration sensors during the operation of the diesel engine, discovering and diagnosing faults in a timely manner and taking effective measures can increase the safety and reliability during the operation of the diesel engine, reduce the maintenance cost of the diesel engine, reduce the losses caused thereby, and prevent sudden accidents.

[0003] However, when analyzing various signals collected by various vibration sensors, due to the interference of the complex operating environment of the diesel engine, there will be noise signals in the collected various signals. The noise signals will interfere with the subsequent analysis of various signals, making the analysis results inaccurate. The existing methods for removing noise signals are to filter the signals based on various filtering algorithms. However, since the filtering is performed on the entire signal, it is easy to filter out the normal signals therein, resulting in signal distortion, and further leading to inaccurate analysis results for the subsequent signals. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a signal analysis method for an electronically controlled single-cylinder diesel engine, and the specific technical solution adopted is as follows:

[0005] An embodiment of the present invention provides a signal analysis method for an electronically controlled single-cylinder diesel engine, and the method includes:

[0006] The vibration amplitudes collected by vibration sensors at different positions at the same moment and the distances between the corresponding vibration sensors and the vibration source form the vibration attenuation ratio sequence at this moment; the vibration amplitude regularity at this moment is obtained according to every three adjacent elements in the vibration attenuation ratio sequence; the vibration change amplitude at this moment is obtained according to the vibration amplitude at a moment collected by one vibration sensor, the vibration amplitudes at the previous moment and the next moment of this moment.

[0007] The vibration change amplitude sequences at at least two moments before a moment and at least two moments after this moment form the vibration change amplitude sequence at this moment; the abnormality degree of the vibration amplitude at each moment is obtained according to the difference between every two adjacent elements in the vibration change amplitude sequence at each moment and the vibration amplitude regularity at each moment.

[0008] Based on the position of the vibration amplitude at a moment within its period, obtain the moments at the same position within a preset number of periods adjacent to the front and back of this period, and form a judgment sequence of the vibration amplitude at this moment; according to the vibration amplitude corresponding to each moment in the judgment sequence of the vibration amplitude at each moment and the vibration amplitude regularity, the abnormal degree of the vibration amplitude at each moment is used to obtain the optimized abnormal degree of the vibration amplitude at each moment.

[0009] Based on the optimized abnormal degrees of the vibration amplitudes at different moments collected by a vibration sensor, screen the vibration amplitudes at different moments collected by a vibration sensor to obtain the true vibration amplitude sequence of this vibration sensor; further obtain the sound pressures at different moments collected by sound level meters at different positions, and screen to obtain the true sound pressure sequence of each sound level meter; analyze according to the true vibration amplitude sequence and true sound pressure sequence of any vibration sensor and sound level meter to obtain the fault type of the single-cylinder diesel engine.

[0010] Preferably, obtain the vibration amplitude regularity at this moment according to every three adjacent elements in the vibration attenuation ratio sequence, including:

[0011] Obtain the absolute value of the difference between the first element and the second element, and the absolute value of the difference between the second element and the third element among every three adjacent elements in the vibration attenuation ratio sequence; obtain the absolute value of the result of subtracting the absolute value of the difference between the second element and the third element from the absolute value of the difference between the first element and the second element, and take the opposite of the absolute value of this result as the power exponent of the exponential function with the natural constant as the base, to obtain the function value of the exponential function with the natural constant as the base corresponding to every three adjacent elements; take the average of the function values of the exponential function with the natural constant as the base corresponding to every three adjacent elements in the vibration attenuation ratio sequence to obtain the vibration amplitude regularity.

[0012] Preferably, obtain the vibration change amplitude at this moment according to the vibration amplitude at a moment collected by a vibration sensor, the vibration amplitude at the previous moment and the vibration amplitude at the next moment of this moment, including: the absolute value of the difference between the vibration amplitude at a moment and the vibration amplitude at the previous moment of this moment, plus the absolute value of the difference between the vibration amplitude at a moment and the vibration amplitude at the next moment of this moment, to obtain the addition result; the ratio of the addition result to the absolute value of twice the vibration amplitude at this moment is the vibration change amplitude at this moment.

[0013] Preferably, the degree of abnormality of the vibration amplitude at each moment is obtained according to the difference between every two adjacent elements in the vibration change amplitude sequence at each moment and the regularity of the vibration amplitude at each moment, including: taking the opposite of the absolute value of the difference between every two adjacent elements in the vibration change amplitude sequence as the power exponent of the exponential function with the natural constant as the base to obtain the function value of the exponential function; averaging the difference between the function values corresponding to every two adjacent elements in the vibration change amplitude sequence at a moment and dividing it by the regularity of the vibration amplitude at this moment to obtain the degree of abnormality of the vibration amplitude at this moment.

[0014] Preferably, the optimized degree of abnormality of the vibration amplitude at each moment is:

[0015]

[0016] Among them, and respectively represent the optimized degree of abnormality and the degree of abnormality of the vibration amplitude at the Tth moment collected by a sensor; represents the number of moments in the judgment sequence of the vibration amplitude at the Tth moment; represents the vibration amplitude at the Tth moment; represents the vibration amplitude corresponding to the ith element in the judgment sequence of the vibration amplitude at the Tth moment; represents the regularity of the vibration amplitude at the Tth moment; represents the regularity of the vibration amplitude corresponding to the ith element in the judgment sequence of the vibration amplitude at the Tth moment; and the elements in the judgment sequence are moments; e represents the natural constant.

[0017] Preferably, based on the optimized degree of abnormality of the vibration amplitudes at different moments collected by a vibration sensor, the vibration amplitudes at different moments collected by a vibration sensor are screened to obtain the true vibration amplitude sequence of the vibration sensor, including: setting a judgment threshold, and removing the vibration amplitudes with an optimized degree of abnormality greater than the judgment threshold among the vibration amplitudes at different moments collected by a vibration sensor, and then forming the true vibration amplitude sequence of the vibration sensor.

[0018] Preferably, the fault type of the single-cylinder diesel engine is obtained by analyzing the true vibration amplitude sequence and the true sound pressure sequence of any vibration sensor and a sound level meter, including: obtaining historical vibration amplitude data and sound pressure data; obtaining the probability that the vibration amplitude at a moment in the true vibration amplitude sequence of any vibration sensor appears in the historical vibration amplitude data and the probability that the sound pressure at the same moment in the true sound pressure sequence of any sound level meter appears in the historical sound pressure data, which are the vibration historical probability and the sound pressure historical probability respectively;

[0019] Obtain the frequency of the vibration amplitude at this moment within a preset number of cycles adjacent to the cycle where the vibration amplitude at this moment is located. The ratio of the frequency to the number of elements in the judgment sequence at this moment is denoted as the first probability; obtain the frequency of the sound pressure at this moment within a preset number of cycles adjacent to the cycle where the sound pressure at this moment is located. The ratio of the frequency to the number of elements in the judgment sequence at this moment is denoted as the second probability;

[0020] Multiply the first probability at this moment by the difference between one and the vibration historical probability at this moment to obtain the vibration anomaly probability at this moment; multiply the second probability at this moment by the difference between one and the sound pressure historical probability at this moment to obtain the sound pressure anomaly probability at this moment; the product of the vibration anomaly probability and the sound pressure anomaly probability at this moment is the fault probability at this moment; set a first threshold. If the fault probability at this moment is greater than the first threshold, then this moment is a fault moment; obtain the vibration amplitude and sound pressure of all fault moments in the true vibration amplitude sequence and true sound pressure sequence of any vibration sensor and sound level meter to form a fault feature vector; input the fault feature vector into the diesel engine fault classification neural network to output the fault type of the diesel engine.

[0021] The embodiments of the present invention have at least the following beneficial effects: The present invention analyzes the ratio of the vibration amplitude at the same moment collected by vibration sensors at different positions to the distance ratio between the vibration sensors at different positions and the vibration source to obtain the vibration amplitude regularity at this moment. Based on this, it can be determined whether the vibration amplitude collected at each moment has regularity, which can help more accurately screen out the vibration amplitudes belonging to noise points in the subsequent process; further, analyze the difference between adjacent elements in the vibration change amplitude sequence corresponding to each moment and combine the vibration amplitude regularity at each moment to obtain the abnormal degree of the vibration amplitude at each moment. Combining the characteristics of the vibration amplitude belonging to the noise point in a cycle can more accurately screen out the noise points in all the vibration amplitudes collected by a vibration sensor; at the same time, optimize the obtained abnormal degree by combining the vibration amplitude and vibration amplitude regularity at the same position in different cycles to obtain a more accurate optimized abnormal degree. For the screening of the vibration amplitudes at different moments collected by each vibration sensor, remove the noise points in them, so that the subsequent analysis of the vibration amplitude can obtain a more accurate analysis result. At the same time, screen the sound pressures at different moments collected by sound level meters at different positions to remove the noise points in them, obtain the true sound pressure sequence of each sound pressure meter, and combine it with the true vibration amplitude sequence for analysis, which can more accurately judge the fault type of the single-cylinder diesel engine. Description of the Drawings

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 It is a method flowchart of a signal analysis method for an electronically controlled single-cylinder diesel engine provided by an embodiment of the present invention. Detailed implementation manners

[0024] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of a signal analysis method for an electronically controlled single-cylinder diesel engine according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0026] The following specifically describes the specific solution of a signal analysis method for an electronically controlled single-cylinder diesel engine provided by the present invention in conjunction with the drawings.

[0027] Embodiment:

[0028] The main application scenario of the present invention is as follows: In order to determine the fault category of a diesel engine, it is necessary to analyze the vibration signal and sound pressure signal during the operation of the diesel engine. However, when collecting the vibration signal and sound pressure signal, due to the complex working environment of the diesel engine and external interference, noise points will be generated. Therefore, it is necessary to screen out and eliminate the interference signals in the collected vibration signal and sound pressure signal to obtain the true vibration signal and sound pressure signal, making the subsequent analysis more accurate.

[0029] Please refer to Figure 1 , which shows a method flowchart of a signal analysis method for an electronically controlled single-cylinder diesel engine provided by an embodiment of the present invention. The method includes the following steps:

[0030] Step S1, the vibration amplitudes collected by vibration sensors at different positions at the same moment and the distances between the corresponding vibration sensors and the vibration source form the vibration attenuation ratio sequence at this moment; the vibration amplitude regularity at this moment is obtained according to every three adjacent elements in the vibration attenuation ratio sequence; the vibration change amplitude at this moment is obtained according to the vibration amplitude at a moment collected by a vibration sensor, the vibration amplitudes at the previous moment and the next moment of this moment.

[0031] In the embodiments of the present invention, signals of a diesel engine are collected by multiple sensors respectively, including vibration signals and sound pressure signals. A total of two sensors are used, namely vibration sensors and sound level meters. The installation positions of the two sensors should not affect the operating state of the diesel engine as much as possible, and at the same time can fully reflect the working information of the object to be measured. To ensure the acquisition accuracy, there are multiple sensors for each type of sensor. Among them, the vibration sensors collect the vibration signals of the diesel engine. Preferably, in this embodiment, the vibration amplitude ZD obtained from the vibration signals is analyzed. The sound signals of the diesel engine are collected by the sound level meters. Preferably, the sound signal in this embodiment is the sound pressure SY. At the same time, the power signal Y of the current diesel engine is obtained to ensure that the diesel engine is operating at the same power.

[0032] When the diesel engine is affected by external interference, due to the large amount of data collected, the collected data often has noise data, that is, noise points. Therefore, in the present invention, according to the regularity and periodicity between the multiple collected data, the analysis and identification of the data are completed to eliminate the interference of the noise data.

[0033] In the present invention, the continuous data collected by the same type of sensors are first analyzed. Here, taking the vibration amplitude ZD as an example, assuming that there are N vibration sensors collecting vibration amplitudes at different positions on the cylinder head, the vibration signal can be recorded as , represents the vibration amplitude collected by the i-th vibration sensor at the T moment.

[0034] Then, multiple vibration sensors can all obtain the vibration amplitudes at the same moment, forming a sequence expressed as , … , in addition, it should be noted that the number of vibration amplitudes and sound pressures collected by each vibration sensor and sound level meter is equal, and both the vibration signals and the sound signals change periodically. Even if a failure occurs, there will still be a certain periodicity.

[0035] Ideally, the vibration amplitudes collected by vibration sensors at the same distance from the vibration source at the same moment should be the same. However, during actual collection, due to different positions, that is, different distances from the vibration source, the data collected by the sensors may be interfered with, resulting in inconsistent detected data. Or when the vibration sensors are affected by external interference, the data detected by the sensors may also be inconsistent. In this case, noise appears.

[0036] Multiple vibration amplitudes at the same moment correspond to multiple vibration sensors. Obtain the coordinate information of the vibration source ( , , ), and the coordinate information of each vibration sensor ( , ), where ( , ) represents the coordinate information of the i-th vibration sensor.

[0037] Then the distance between the vibration sensor and the vibration source can be obtained :

[0038]

[0039] Among them, ( , ) is the coordinate information of the i-th vibration sensor, and ( , , ) is the coordinate information of the vibration source, represents the distance between the i-th vibration sensor and the vibration source, and at the same time, the vibration sensors are sorted according to the distance between the vibration sensors and the vibration source.

[0040] Thus, the ratio of the vibration amplitude corresponding to a vibration sensor to the distance between the vibration sensor and the vibration source among all the vibration amplitudes of vibration sensors at different positions at the same moment can be obtained. This ratio is the vibration attenuation ratio of the vibration sensor at this moment, and is expressed by the formula:

[0041]

[0042] Among them, represents the vibration amplitude collected by the i-th vibration sensor at time T; represents the distance between the i-th vibration sensor and the vibration source; represents the vibration attenuation ratio of the i-th vibration sensor at time T; The vibration attenuation ratios corresponding to time T form a vibration attenuation ratio sequence.

[0043] Further, the vibration amplitude regularity at the corresponding moment of the vibration attenuation ratio sequence is obtained based on the difference in the change amplitude between every three adjacent elements in the vibration attenuation ratio sequence. Specifically: obtain the absolute value of the difference between the first element and the second element among every three adjacent elements in the vibration attenuation ratio sequence, and the absolute value of the difference between the second element and the third element; take the opposite of the absolute value of the result of subtracting the absolute value of the difference between the second element and the third element from the absolute value of the difference between the first element and the second element as the power exponent of the exponential function with the natural constant as the base, and obtain the function value of the exponential function with the natural constant as the base corresponding to every three adjacent elements; average the function values of the exponential functions with the natural constant as the base corresponding to every three adjacent elements in the vibration attenuation ratio sequence to obtain the vibration amplitude regularity.

[0044] It is expressed by the formula as:

[0045]

[0046] Wherein, represents the vibration amplitude regularity corresponding to the T moment; represents the number of vibration sensors; , and respectively represent the i-th, (i + 1)-th, and (i + 2)-th elements in the vibration attenuation ratio sequence corresponding to the T moment; e represents the natural constant, represents the difference between the change amplitudes of the first element and the second element, and the second element and the third element among three adjacent elements. The smaller this value is, the greater the regularity of the vibration amplitude. The greater the vibration amplitude regularity , the smaller the possibility that the vibration amplitude collected at this moment is a noise point.

[0047] Finally, it is also necessary to calculate the change amplitude of the vibration amplitude at a moment for analysis to obtain the vibration change amplitude at a moment. Specifically: the absolute value of the difference between the vibration amplitude at the T moment and the vibration amplitude at the previous moment of this moment, plus the absolute value of the difference between the vibration amplitude at the T moment and the vibration amplitude at the next moment of this moment, to obtain the added result; the ratio of the added result to the absolute value of twice the vibration amplitude at the T moment is the vibration change amplitude at this moment; it is expressed by the formula as:

[0048]

[0049] Wherein, represents the vibration change amplitude of the vibration amplitude collected by any vibration sensor at the T moment, that is, the vibration change amplitude at the T moment; , and respectively represent the vibration amplitudes at time T-1, time T, and time T+1 collected by a vibration sensor.

[0050] Step S2: The vibration change amplitudes at at least two moments before a certain moment and at least two moments after this moment form the vibration change amplitude sequence at this moment; the abnormality degree of the vibration amplitude at each moment is obtained according to the difference between every two adjacent elements in the vibration change amplitude sequence at each moment and the regularity of the vibration amplitude at each moment.

[0051] When determining whether the vibration amplitude at each moment collected by a vibration sensor is noise data, it is necessary to consider the vibration change amplitudes at at least two moments within a certain period before this moment and the vibration change amplitudes at at least two moments within a certain period after this moment. Specifically, obtain the vibration change amplitudes at at least two moments within a preset period before time T of a vibration sensor and the vibration change amplitudes at at least two moments within a preset period after time T of a vibration sensor, and form the vibration change amplitude sequence at time T, denoted as { … … }, representing the vibration change amplitude at the th moment of a vibration sensor.

[0052] According to the vibration change amplitude sequence at time T and the regularity of the vibration amplitude at time T calculate the abnormality degree of the vibration amplitude at time T of a vibration sensor. Specifically: Take the opposite of the absolute value of the difference between every two adjacent elements in the vibration change amplitude sequence at time T as the power exponent of the exponential function with the natural constant as the base to obtain the function value of the exponential function; calculate the average value of the differences between the function values corresponding to every two adjacent elements in the vibration change amplitude sequence at time T of a certain moment and divide it by the regularity of the vibration amplitude at time T to obtain the abnormality degree of the vibration amplitude at time T; it is expressed by the formula:

[0053]

[0054] where, represents the abnormality degree of the vibration amplitude at time T of a vibration sensor; represents the Tth moment; and represent the vibration change amplitudes of the vibration amplitudes collected at time T and time T+1 of any vibration sensor; represents the vibration amplitude regularity corresponding to time T; the larger YC is, the more likely the vibration amplitude at this moment is a noise signal; e represents the natural constant.

[0055] Step S3: Based on the position of the vibration amplitude at a moment within its period, obtain the moments at the same position within a preset number of periods adjacent to the front and back of this period, and form a judgment sequence of the vibration amplitude at this moment; according to the vibration amplitude corresponding to each moment in the judgment sequence of the vibration amplitude at each moment and the vibration amplitude regularity, the optimized abnormal degree of the vibration amplitude at each moment is obtained for the abnormal degree of the vibration amplitude at each moment.

[0056] Since this embodiment analyzes the vibration amplitude at a moment, and the vibration amplitude at a moment is within a period, it is necessary to further analyze by combining the vibration amplitudes within a preset number of periods adjacent to the front and back of this period to optimize the abnormal degree of the vibration amplitude at a moment; based on the position of the vibration amplitude at a moment within its period, obtain the moments at the same position within a preset number of periods adjacent to the front and back of this period, and form a judgment sequence of the vibration amplitude at this moment. The elements in the judgment sequence are all moments, and the number of elements in the judgment sequence is M. For example, if the T moment is the third moment within its corresponding period, then take the third moment in each of the first three periods of the period corresponding to the T moment, and take the third moment in each of the last three periods of the period corresponding to the T moment to form the judgment sequence, then the number of elements M in the judgment sequence is 6; in addition, it should be noted that the value of M can be adjusted by the implementer according to the specific situation.

[0057] Combine the judgment sequence to optimize the abnormal degree of the vibration amplitude at each moment, and obtain the optimized abnormal degree of the vibration amplitude at each moment:

[0058]

[0059] Among them, and respectively represent the optimized abnormal degree and the abnormal degree of the vibration amplitude at the T moment collected by a sensor; represents the number of moments in the judgment sequence of the vibration amplitude at the T moment; represents the vibration amplitude at the T moment; represents the vibration amplitude corresponding to the i-th element in the judgment sequence of the vibration amplitude at the T moment; represents the vibration amplitude regularity at the T moment; represents the vibration amplitude regularity corresponding to the i-th element in the judgment sequence of the vibration amplitude at the T moment; e represents the natural constant.

[0060] and The larger the value, the higher the degree of abnormality in the optimization of the vibration amplitude at that moment, indicating that the vibration amplitude at that moment is more likely to be noise and needs to be filtered out more. Based on the data corresponding to each element in the sequence, the degree of abnormality is optimized to obtain a more accurate degree of abnormal optimization, making the subsequent removal of the vibration amplitude more accurate.

[0061] Step S4: Based on the degree of abnormal optimization of the vibration amplitudes at different moments collected by a vibration sensor, screen the vibration amplitudes at different moments collected by the vibration sensor to obtain the true vibration amplitude sequence of the vibration sensor; furthermore, obtain the sound pressures at different moments collected by sound level meters at different positions, and screen to obtain the true sound pressure sequence of each sound level meter; analyze the true vibration amplitude sequence and true sound pressure sequence of any vibration sensor and sound level meter to obtain the fault type of the single-cylinder diesel engine.

[0062] First, based on the degree of abnormal optimization of the vibration amplitudes at different moments collected by a vibration sensor, screen the vibration amplitudes at different moments collected by the vibration sensor to obtain the true vibration amplitude sequence of the vibration sensor. Specifically: set a judgment threshold, and after removing the vibration amplitudes with an abnormal optimization degree greater than the judgment threshold among the vibration amplitudes at different moments collected by a vibration sensor, form the true vibration amplitude sequence of the vibration sensor. Therefore, each vibration sensor will obtain a true vibration amplitude sequence. In step S1, the sound pressures at different moments are also collected by different sound level meters, and the same processing is performed on the collected sound pressures at different moments using the method of processing vibration amplitudes to screen out the sound pressure data belonging to noise, and the true sound pressure sequence of each sound level meter can be obtained. At this time, the true vibration amplitude sequences of each vibration sensor and the true sound pressure sequences of each sound level meter have removed the data belonging to noise, and more accurate analysis results can be obtained in the subsequent analysis process.

[0063] Furthermore, analyze the true vibration amplitude sequence and true sound pressure sequence of any vibration sensor and sound level meter to obtain the fault type of the single-cylinder diesel engine. Specifically: obtain the historical vibration amplitude data and sound pressure data. It should be noted that obtaining the historical vibration amplitude data and sound pressure data is a well-known technology and will not be elaborated here.

[0064] Obtain the probability that the vibration amplitude at a certain moment in the true vibration amplitude sequence of any vibration sensor appears in the historical vibration amplitude data and the probability that the sound pressure at the same moment in the true sound pressure sequence of any sound level meter appears in the historical sound pressure data, which are the vibration historical probability and the sound pressure historical probability ; Obtain the frequency count of the vibration amplitude at this moment within a preset number of cycles adjacent to the cycle where the vibration amplitude at this moment is located. The ratio of the frequency count to the number of elements in the judgment sequence at this moment is denoted as the first probability. ; Obtain the frequency count of the sound pressure at this moment within a preset number of cycles adjacent to the cycle where the sound pressure at this moment is located. The ratio of the frequency count to the number of elements in the judgment sequence at this moment is denoted as the second probability. ; Multiply the first probability at this moment by the difference between 1 and the vibration historical probability at this moment to obtain the vibration anomaly probability at this moment. It is expressed by the formula:

[0065]

[0066] Wherein, represents the vibration anomaly probability at this moment of a certain moment; represents the first probability corresponding to this moment, represents the vibration historical probability corresponding to this moment. When the larger the value, it indicates that the frequency of occurrence of the vibration amplitude at this moment in the adjacent cycles is higher. At the same time, when the frequency of occurrence of the vibration amplitude at this moment in the historical data is lower, it indicates that the possibility of the vibration amplitude at this moment being noise data is greater.

[0067] Multiply the second probability at this moment by the difference between 1 and the sound pressure historical probability at this moment to obtain the sound pressure anomaly probability at this moment; it is expressed by the formula:

[0068]

[0069] Wherein, represents the sound pressure anomaly probability at this moment of a certain moment; represents the second probability corresponding to this moment, represents the sound pressure historical probability corresponding to this moment.

[0070] The product of the vibration anomaly probability and the sound pressure anomaly probability at a certain moment is the fault probability at this moment. It is expressed by the formula:

[0071]

[0072] Wherein, represents the vibration anomaly probability at a certain moment; represents the sound pressure anomaly probability at a certain moment; represents the fault probability at this moment. The greater the fault probability, the greater the likelihood of a fault occurring at this moment. Set a first threshold. If the fault probability at this moment is greater than the first threshold, then this moment is a fault moment. Preferably, in the embodiments of the present invention, the value of the first threshold is 0.87, and the implementer can adjust the value of the first threshold according to the actual situation.

[0073] Finally, obtain the vibration amplitude and sound pressure at all fault moments in the true vibration amplitude sequence and true sound pressure sequence of any vibration sensor and sound level meter to form a fault feature vector; input the fault feature vector into the diesel engine fault classification neural network, and output the fault type of the diesel engine. The training process of the diesel engine fault classification neural network is a well-known technology and will not be elaborated here. Since it is used for classification, the loss function of this neural network is the cross-entropy loss function.

[0074] According to the above steps, the diesel engine signals are collected by sensors, the signals are preprocessed to obtain corresponding fault feature vectors, the faults are identified according to the diesel engine fault classification neural network, and relevant repairs are carried out according to the faults.

[0075] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0076] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0077] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the scope of the present invention shall be included in the protection scope of the present invention.

Claims

1. A signal analysis method for an electronically controlled single-cylinder diesel engine, characterized in that, The method includes: The vibration amplitudes collected by vibration sensors at different positions at the same moment, and the distances between the corresponding vibration sensors and the vibration source form the vibration attenuation ratio sequence at this moment; the vibration amplitude regularity at this moment is obtained according to every three adjacent elements in the vibration attenuation ratio sequence; the vibration change amplitude at this moment is obtained according to the vibration amplitude at a moment collected by a vibration sensor, the vibration amplitudes at the previous moment and the next moment of this moment. The vibration change amplitude sequences at at least two moments before a moment and at least two moments after this moment form the vibration change amplitude sequence at this moment; the abnormality degree of the vibration amplitude at each moment is obtained according to the difference between every two adjacent elements in the vibration change amplitude sequence at each moment and the vibration amplitude regularity at each moment. Based on the position of the vibration amplitude at a moment within its period, the moments at the same position within the preset number of periods adjacent to the front and back of this period are obtained, forming the judgment sequence of the vibration amplitude at this moment; according to the vibration amplitude corresponding to each moment in the judgment sequence of the vibration amplitude at each moment and the vibration amplitude regularity, and the abnormality degree of the vibration amplitude at each moment, the optimized abnormality degree of the vibration amplitude at each moment is obtained. Based on the optimized abnormality degrees of the vibration amplitudes at different moments collected by a vibration sensor, the vibration amplitudes at different moments collected by a vibration sensor are screened to obtain the true vibration amplitude sequence of this vibration sensor; furthermore, the sound pressures at different moments collected by sound level meters at different positions are obtained, and the true sound pressure sequences of each sound level meter are screened. Obtain historical vibration amplitude data and sound pressure data; obtain the probability that the vibration amplitude at a moment in the true vibration amplitude sequence of any vibration sensor appears in the historical vibration amplitude data and the probability that the sound pressure at the same moment in the true sound pressure sequence of any sound level meter appears in the historical sound pressure data, which are the vibration historical probability and the sound pressure historical probability respectively. Obtain the frequency of the vibration amplitude at this moment within the preset number of periods adjacent to the front and back of the period where the vibration amplitude at this moment is located, and the ratio of the frequency to the number of elements in the judgment sequence at this moment is denoted as the first probability; obtain the frequency of the sound pressure at this moment within the preset number of periods adjacent to the front and back of the period where the sound pressure at this moment is located, and the ratio of the frequency to the number of elements in the judgment sequence at this moment is denoted as the second probability. Multiply the first probability at this moment by the difference between 1 and the vibration historical probability to obtain the vibration abnormality probability at this moment; multiply the second probability at this moment by the difference between 1 and the sound pressure historical probability to obtain the sound pressure abnormality probability at this moment; the product of the vibration abnormality probability and the sound pressure abnormality probability at this moment is the fault probability at this moment; set a first threshold, if the fault probability at this moment is greater than the first threshold, then this moment is a fault moment; obtain the vibration amplitudes and sound pressures at all fault moments in the true vibration amplitude sequences and true sound pressure sequences of any vibration sensor and sound level meter to form a fault feature vector; input the fault feature vector into the diesel engine fault classification neural network, and output the fault type of the diesel engine.

2. The signal analysis method for an electronically controlled single-cylinder diesel engine according to claim 1, characterized in that Obtaining the vibration amplitude regularity at this moment according to every three adjacent elements in the vibration attenuation ratio sequence includes: Obtaining the absolute value of the difference between the first element and the second element, and the absolute value of the difference between the second element and the third element among every three adjacent elements in the vibration attenuation ratio sequence; obtaining the absolute value of the result of subtracting the absolute value of the difference between the second element and the third element from the absolute value of the difference between the first element and the second element, and taking the opposite of the absolute value of the result as the power exponent of the exponential function with the natural constant as the base, to obtain the function value of the exponential function corresponding to every three adjacent elements; averaging the function values of the exponential functions with the natural constant as the base corresponding to every three adjacent elements in the vibration attenuation ratio sequence to obtain the vibration amplitude regularity.

3. A signal analysis method for an electronically controlled single-cylinder diesel engine according to claim 1, characterized in that, Obtaining the vibration change amplitude at this moment according to the vibration amplitude at a moment collected by a vibration sensor, the vibration amplitudes at the previous moment and the next moment of this moment includes: obtaining the absolute value of the sum of the absolute value of the difference between the vibration amplitude at a moment and the vibration amplitude at the previous moment of this moment, and the absolute value of the difference between the vibration amplitude at a moment and the vibration amplitude at the next moment of this moment; the ratio of the sum result to twice the absolute value of the vibration amplitude at this moment is the vibration change amplitude at this moment.

4. A signal analysis method for an electronically controlled single-cylinder diesel engine according to claim 1, characterized in that Obtaining the abnormality degree of the vibration amplitude at each moment according to the difference between every two adjacent elements in the vibration change amplitude sequence at each moment and the vibration amplitude regularity at each moment includes: taking the opposite of the absolute value of the difference between every two adjacent elements in the vibration change amplitude sequence as the power exponent of the exponential function with the natural constant as the base to obtain the function value of the exponential function; averaging the difference between the function value corresponding to every two adjacent elements in the vibration change amplitude sequence at a moment and 1, and dividing it by the vibration amplitude regularity at this moment to obtain the abnormality degree of the vibration amplitude at this moment.

5. A signal analysis method for an electronically controlled single-cylinder diesel engine according to claim 1, characterized in that, The optimized abnormality degree of the vibration amplitude at each moment is: Among them, and respectively represent the optimized abnormality degree and the abnormality degree of the vibration amplitude at time T collected by a sensor; represents the number of moments in the judgment sequence of the vibration amplitude at time T; represents the vibration amplitude at time T; represents the vibration amplitude corresponding to the i-th element in the judgment sequence of the vibration amplitude at time T; represents the vibration amplitude regularity at time T; represents the vibration amplitude regularity corresponding to the i-th element in the judgment sequence of the vibration amplitude at time T; and the elements in the judgment sequence are moments; e represents the natural constant.

6. A signal analysis method for an electronically controlled single-cylinder diesel engine according to claim 1, characterized in that Screening the vibration amplitudes at different moments collected by a vibration sensor based on the optimized abnormality degree of the vibration amplitudes at different moments collected by a vibration sensor to obtain the true vibration amplitude sequence of this vibration sensor includes: setting a judgment threshold, and removing the vibration amplitudes with an optimized abnormality degree greater than the judgment threshold among the vibration amplitudes at different moments collected by a vibration sensor, and then forming the true vibration amplitude sequence of this vibration sensor.

Images