Condition monitoring method, device, electronic device and readable storage medium

Abstract

The present application discloses a condition monitoring method, device, electronic device and readable storage medium. The method includes obtaining measurement data information of a target physical quantity collected by multiple homogeneous sensors through synchronous acquisition technology. Sensor association data is obtained by information association of each measurement data information; deviation data is obtained by deviation calculation of each measurement data; the consistency relationship between each two homogeneous sensors is determined according to the sensor association data and the deviation data. According to the consistency relationship between each homogeneous sensor, each measurement data information is fused; the fused data is used as the measurement data of the target physical quantity, and condition monitoring is performed based on the target physical quantity. The present application effectively improves the accuracy of mechanical equipment condition monitoring and can ensure the safe and stable operation of mechanical equipment.

Description

Technical Field

[0001] The present application relates to the field of mechanical technology, and in particular to a condition monitoring method, device, electronic device and readable storage medium. Background Art

[0002] Mechanical equipment generally consists of multiple parts such as drive devices, speed change devices, transmission devices, working devices, braking devices, protective devices, lubrication systems, cooling systems, etc., and each part includes multiple components. It is understandable that as the use time of mechanical equipment increases, the various components of the equipment will inevitably age, and these components will also be damaged when they are hit by external forces or improper use. For example, the transmission system, as an important component of the machinery, is composed of key components such as motors, couplings, gearboxes, drive shafts, and axle boxes, which are responsible for effectively converting the torque of the traction motor into torque. Due to the disturbance of external forces, a certain relative movement will occur between the various assemblies of the transmission system, resulting in the bearings of the traction motor output shaft, the bearings of the gearbox input shaft, i.e. the pinion shaft, and the coupling connecting the two shafts. They often suffer fatigue damage before their service life is up, affecting the safe operation of the machinery.

[0003] In order to ensure the stable and safe operation of mechanical equipment, it is necessary to monitor the operating status of mechanical equipment in real time. Related technologies will install sensors at the key components of mechanical equipment, and monitor the status information of key components of mechanical equipment through these sensors. However, the monitoring objects are mainly scattered components, and the monitoring of the entire system is far from enough. In addition, due to the single information data of the detection target of a single sensor, in the case of complex noise and unfocused targets, the monitoring performance cannot meet the actual requirements, the monitoring accuracy is low, the target information obtained is quite different from the actual information, and it cannot accurately reflect the actual operating status of the mechanical equipment. Taking the transmission system as an example, sensors are installed on the key components of the transmission system. Due to the limited number and types of sensors installed, it is impossible to accurately diagnose faults by relying solely on the multi-source information collected by these sensors, and the reliability of the transmission system is not high.

[0004] In view of this, how to improve the accuracy of status monitoring of mechanical equipment and ensure the safe and stable operation of mechanical equipment is a technical problem that technical personnel in the relevant field need to solve. Summary of the invention

[0005] The present application provides a condition monitoring method, device, electronic device and readable storage medium, which effectively improve the accuracy of mechanical equipment condition monitoring and can ensure the safe and stable operation of the mechanical equipment.

[0006] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0007] An embodiment of the present invention provides a state monitoring method, including:

[0008] Acquire measurement data information of target physical quantities collected by multiple homogeneous sensors through synchronous acquisition technology;

[0009] By correlating the information of each measurement data, sensor correlation data is obtained; by calculating the deviation of each measurement data, deviation data is obtained; and the consistency relationship between every two homogeneous sensors is determined according to the sensor correlation data and the deviation data;

[0010] According to the consistency relationship between homogeneous sensors, the measurement data information is fused;

[0011] The fused data is used as the measurement data of the target physical quantity to perform condition monitoring based on the target physical quantity.

[0012] Optionally, after acquiring the measurement data information of the target physical quantity collected by multiple homogeneous sensors through the synchronous collection technology, the method further includes:

[0013] Perform wavelet transform on the measurement data information of each homogeneous sensor to obtain multi-layer decomposition sub-signals;

[0014] Threshold processing is performed on the wavelet decomposition coefficients of each decomposed sub-signal to obtain estimated wavelet coefficients;

[0015] The estimated wavelet coefficients are used to perform wavelet reconstruction to obtain denoised measurement data information.

[0016] Optionally, performing threshold processing on the wavelet decomposition coefficients of each decomposed sub-signal to obtain estimated wavelet coefficients includes:

[0017] The value of the preset critical threshold is determined in advance according to a generation method of the preset critical threshold; the generation method includes a signal generation method and a noise generation method;

[0018] The estimated value calculation formula is called to calculate the estimated wavelet coefficients of each layer of decomposition sub-signal. The estimated value calculation formula is:

[0019]

[0020] In the formula, is the estimated wavelet coefficient of the k-th layer decomposition sub-signal, j is the total number of layers of decomposition sub-signals, ω j,k is the wavelet decomposition coefficient of the k-th layer decomposition sub-signal, λ is the preset critical threshold, and sgn(·) is the sign function.

[0021] Optionally, obtaining sensor associated data by associating information of each measurement data includes:

[0022] The information association relationship formula is called to calculate the association value between every two pieces of measurement data information, and the information association relationship formula is:

[0023]

[0024] A multidimensional correlation matrix is ​​determined according to the correlation value of each two pieces of measurement data information to serve as the sensor correlation data; the multidimensional correlation matrix P is:

[0025]

[0026] In the formula, p ij is the measurement data x of the i-th homogeneous sensor i and the measurement data x of the jth homogeneous sensor j The correlation value between is the measured data x i The mean of is the measured data x j The mean value of x i (h) is the measured data x i The hth data in x j (h) is the measured data x j The hth data in the measurement data, N is the total number of data contained in the measurement data; p nn is the correlation value between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors.

[0027] Optionally, the obtaining of deviation data by performing deviation calculation on each measurement data includes:

[0028] The confidence distance between the first measurement data and the second measurement data is calculated by calling the deviation calculation formula, wherein the deviation calculation formula is:

[0029]

[0030] A multidimensional confidence distance matrix is ​​determined according to the confidence distance between every two measurement data to serve as the deviation data; the multidimensional confidence distance matrix D is:

[0031]

[0032] Where, d ij is the measurement data x of the i-th homogeneous sensor i The measurement data x of the jth homogeneous sensor j The confidence distance, P i (x / x i ) is the one-dimensional confidence distance expression of the i-th homogeneous sensor, x is the integral variable parameter, d nnis the confidence distance between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors.

[0033] Optionally, determining the consistency relationship between every two homogeneous sensors according to the sensor association data and the deviation data includes:

[0034] The support degree calculation formula is called to calculate the support degree of the first homogeneous sensor to the second homogeneous sensor; the support degree calculation formula is:

[0035]

[0036] A multidimensional support matrix is ​​determined according to the support degree of each two homogeneous sensors; the multidimensional support matrix R is:

[0037]

[0038] In the formula, r ij is the support degree of the i-th homogeneous sensor to the j-th homogeneous sensor, r nn is the support degree of the nth homogeneous sensor to the nth homogeneous sensor.

[0039] Optionally, the fusing of the measurement data information according to the consistency relationship between the homogeneous sensors includes:

[0040] Determine a non-negative real number vector according to a consistency relationship matrix formed by consistency relationships between homogeneous sensors and its eigenvalue vector; the total number of elements of the non-negative real number vector is the same as the total number of homogeneous sensors, each element corresponds to a comprehensive support degree of a homogeneous sensor, and the comprehensive support degree is the support degree of all homogeneous sensors to the current homogeneous sensor;

[0041] Determining the comprehensive support level of each homogeneous sensor according to the non-negative real number vector;

[0042] The fused data is obtained according to the comprehensive support degree of each homogeneous sensor and the corresponding measurement data information.

[0043] Another aspect of the present invention provides a state monitoring device, including:

[0044] A data acquisition module is used to obtain measurement data information of target physical quantities collected by multiple homogeneous sensors through synchronous acquisition technology;

[0045] A data calculation module is used to obtain sensor-related data by performing information association on each measurement data; obtain deviation data by performing deviation calculation on each measurement data; and determine the consistency relationship between every two homogeneous sensors according to the sensor-related data and the deviation data;

[0046] A data fusion module is used to fuse the measurement data information according to the consistency relationship between the homogeneous sensors;

[0047] The state monitoring module is used to use the fused data as the measurement data of the target physical quantity to perform state monitoring based on the target physical quantity.

[0048] An embodiment of the present invention further provides an electronic device, comprising a processor, wherein the processor is configured to implement the steps of the state monitoring method as described in any of the preceding items when executing a computer program stored in a memory.

[0049] Finally, an embodiment of the present invention further provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the state monitoring method as described in any of the preceding items are implemented.

[0050] The advantage of the technical solution provided by the present application is that different sensors are used to measure the same physical quantity, and the data measured by these sensors are used to determine the consistency relationship between each homogeneous sensor through data association and measurement deviation. Finally, the data collected by each homogeneous sensor is automatically fused based on the consistency relationship, so that a more accurate, reliable and higher breadth of the measured signal can be obtained. And multiple sensors are coordinated with each other based on time synchronization. In the process of fusion, it is not necessary to know the prior knowledge of the measurement data. Fusion is performed according to data adaptation, so that the data fusion result is more accurate, effectively improving the accuracy of mechanical equipment status monitoring, improving the fault tolerance and credibility of status monitoring, and reducing the uncertainty of the system. Further, the system coverage is expanded, and the information of the measured object or environment can be obtained more accurately. When some sensors fail to operate normally, other sensors can still continue to monitor the target state, greatly expanding the coverage of the monitoring time, and can guarantee the safe and stable operation of mechanical equipment to the greatest extent.

[0051] In addition, the embodiment of the present invention also provides a corresponding implementation device, an electronic device and a readable storage medium for the state monitoring method, which further makes the method more practical, and the device, the electronic device and the readable storage medium have corresponding advantages.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A schematic diagram of a flow chart of a state monitoring method provided by an embodiment of the present invention;

[0055] Figure 2 A schematic flow chart of another state monitoring method provided by an embodiment of the present invention;

[0056] Figure 3 A schematic flow chart of another state monitoring method provided by an embodiment of the present invention;

[0057] Figure 4 A structural diagram of a specific implementation of a state monitoring device provided by an embodiment of the present invention;

[0058] Figure 5 A structural diagram of a specific implementation of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0060] The terms "first", "second", "third", "fourth", etc. in the specification and claims of this application and the above drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may include steps or units that are not listed.

[0061] In the field of mechanical equipment status monitoring, the current data obtained by a single sensor is uncertain, incomplete, and inconsistent, resulting in inaccurate status monitoring. The embodiment of the present invention effectively fuses the measurement data of multiple sensors to obtain a more accurate measured signal, and performs status monitoring through the fused data, thereby improving the accuracy of mechanical equipment status monitoring. Various non-limiting implementations of the present application are described in detail below.

[0062] See first Figure 1 , Figure 1 A flow chart of a state monitoring method provided by an embodiment of the present invention, the embodiment of the present invention may include the following contents:

[0063] S101: Acquire measurement data information of target physical quantities collected by multiple homogeneous sensors through synchronous collection technology.

[0064] In this embodiment, homogeneous sensors refer to different sensors that measure the same physical quantity, that is, multiple groups of homogeneous sensors are installed in the mechanical equipment to be detected, and one group of homogeneous sensors is used to collect the measurement data of a physical quantity. Considering that the synchronous acquisition technology can transfer the time reference to other sensors, so that all sensors establish a unified high-precision time and work on a unified time reference, the data acquisition server uses high-precision time as a link to achieve time registration of multi-sensor data when processing data. In order to better integrate the subsequent measurement data information, this embodiment obtains the same physical quantity from homogeneous sensors through synchronous acquisition technology. The synchronous acquisition technology adopts time synchronization, uses high-precision time as a driving source, completes the time synchronization of the sensor, and the sensor receives the pulse and time signal of the timing, and completes the high-precision fusion of the collected data and time by itself. The collected data carries accurate time information, and synchronous acquisition is achieved. Thereby, it can solve the problem that conventional acquisition methods cannot achieve multi-data time registration, and the subsequent time registration algorithm, such as the least squares method, the curve fitting method, etc., has low time registration accuracy. There are multiple measurement data information in this step, that is, each homogeneous sensor corresponds to a measurement data information.

[0065] S102: obtaining sensor-associated data by associating information of each measurement data; obtaining deviation data by calculating deviations of each measurement data; and determining a consistency relationship between every two homogeneous sensors according to the sensor-associated data and the deviation data.

[0066] In this step, since the measurement data information of S101 is data corresponding to the same physical quantity, and the fused data to be obtained in the end is also one data, in order to better perform data fusion, the data collected by each homogeneous sensor can be firstly information-associated. The so-called information association is to calculate the correlation between the measurement data information collected by each homogeneous sensor. The greater the correlation between the measurement data collected by two homogeneous sensors, the greater the correlation between the measurement data collected by the two homogeneous sensors. Since different sensors are used for data collection, there are naturally deviations in each measurement data. In order to better perform data fusion, this embodiment also needs to calculate the deviation information between each measurement data before data fusion. The consistency relationship refers to the consistency support degree between different homogeneous sensors. The consistency information reflects the correlation and deviation between the measurement data information of each homogeneous sensor, thereby better reflecting the performance of each homogeneous sensor.

[0067] S103: fusing the measurement data information according to the consistency relationship between the homogeneous sensors.

[0068] When performing data fusion, the present application processes the measurement data information collected by S101 based on the performance information that can reflect each homogeneous sensor, that is, the consistency relationship, as a weight parameter to obtain the final fused data. The data obtained after fusion is the measured signal of the target physical quantity.

[0069] S104: Using the fused data as measurement data of the target physical quantity to perform condition monitoring based on the target physical quantity.

[0070] In the technical solution provided by the embodiment of the present invention, different sensors are used to measure the same physical quantity, and the data measured by these sensors are used to determine the consistency relationship between each homogeneous sensor through data association and measurement deviation. Finally, the data collected by each homogeneous sensor is automatically fused based on the consistency relationship, so that a more accurate, reliable and high-breadth measured signal can be obtained. And multiple sensors are coordinated with each other based on time synchronization. In the fusion process, it is not necessary to know the prior knowledge of the measurement data. Fusion is performed according to data adaptation, so that the data fusion result is more accurate, effectively improving the accuracy of mechanical equipment status monitoring, improving the fault tolerance and credibility of status monitoring, and reducing the uncertainty of the system. Further, the coverage of the system is expanded, and the information of the measured object or environment can be obtained more accurately. When some sensors fail to operate normally, other sensors can still continue to monitor the target state, which greatly expands the coverage of the monitoring time and can guarantee the safe and stable operation of mechanical equipment to the greatest extent.

[0071] In order to further improve the accuracy of subsequent data fusion and the accuracy of state monitoring of mechanical equipment, after obtaining the measurement data information of the target physical quantity collected by multiple homogeneous sensors through synchronous acquisition technology in S101, signal denoising processing can also be performed on the obtained measurement data information, such as Figure 2 As shown, it may include:

[0072] The measurement data information of each homogeneous sensor is subjected to wavelet transform to obtain multi-layer decomposition sub-signals; the wavelet decomposition coefficients of each decomposition sub-signal are subjected to threshold processing to obtain estimated wavelet coefficients; and wavelet reconstruction is performed using each estimated wavelet coefficient to obtain denoised measurement data information.

[0073] Among them, the measurement data information of each homogeneous sensor is a noisy signal. The noisy signal f(t) is subjected to wavelet transform, where t represents time. The noisy signal can be decomposed into multiple layers, and the corresponding coefficient of each layer is ω j,k . Wherein, j represents the total number of decomposition layers, k represents the corresponding number of layers, k = 1, 2, ..., j. Threshold processing is also called threshold denoising, which performs denoising based on the fact that the amplitude of the wavelet coefficient corresponding to the energy of the real data itself is too large, while the amplitude of the wavelet coefficient of the interference noise is too small. Any threshold function can be used to perform threshold processing. As an optional implementation, the calculation process of estimating the wavelet coefficient may include the following steps:

[0074] The value of the preset critical threshold is determined in advance according to the generation method of the preset critical threshold; the generation method includes a signal generation method and a noise generation method; the estimated value calculation relationship is called to calculate the estimated wavelet coefficients of each layer of decomposition sub-signal, and the estimated value calculation relationship is:

[0075]

[0076] In the formula, is the estimated wavelet coefficient of the k-th layer decomposition sub-signal, j is the total number of layers of decomposition sub-signals, ω j,k is the wavelet decomposition coefficient of the k-th layer decomposition sub-signal, λ is the preset critical threshold, and sgn(·) is the sign function.

[0077] In this embodiment, the threshold function adopts a soft threshold function, which is calculated by j,k Perform threshold processing to obtain the estimated wavelet coefficients make As small as possible. The selection of the preset critical threshold is determined according to the actual situation. j,k When |>λ, the preset critical threshold is mainly generated by the signal; otherwise, the preset critical threshold is mainly generated by the noise.

[0078] From the above, we can see that the use of wavelet threshold denoising can achieve good signal retention effect, the data has good robustness, and reduces the impact of sudden changes in the surrounding environment on the system monitoring performance. It has strong adaptability to environmental changes and good robustness.

[0079] In the above embodiment, there is no limitation on how to perform step S102. In this embodiment, an optional implementation method of information association, deviation calculation and consistency relationship determination is provided, such as: Figure 3 As shown, it may include:

[0080] For homogeneous sensors, that is, different sensors measure the same physical quantity, and the physical quantities measured by these sensors are correlated. The Pearson correlation coefficient is used to measure the measurement data x of the i-th homogeneous sensor. i and the measurement data x of the jth homogeneous sensor j The correlation between them can be calculated by calling the information correlation formula to calculate the correlation value between each two measurement data information. The information correlation formula can be expressed as:

[0081]

[0082] The multidimensional correlation matrix is ​​determined according to the correlation value of each two measurement data information. That is, for multiple homogeneous sensors measuring the same physical feature, the correlation between the homogeneous sensors can form an n×n correlation matrix P as sensor correlation data; the multidimensional correlation matrix P can be expressed as:

[0083]

[0084] In the formula, p ij is the measurement data x of the i-th homogeneous sensor i and the measurement data x of the jth homogeneous sensor j The correlation value between ij The value of p is between -1 and 1. ij The larger the absolute value of the variable x is, the i (h) and x j The higher the correlation of (h); ij The smaller the absolute value of the variable x is, the i (h) and x j The lower the correlation of (h). is the measured data x i The mean of is the measured data x j The mean of x i (h) is the measured data x i The hth data in x j(h) is the measured data x j The hth data in the measurement data, N is the total number of data contained in the measurement data; p nn is the correlation value between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors.

[0085] This embodiment uses confidence distance to distinguish between true measurement data and outlier data. The confidence distance measurement method uses the "confidence distance" between two probability distribution curves as a measure of the degree of deviation between sensor information and determines the correctness of the data obtained by the sensor. In one-dimensional case, the measurement data of homogeneous sensor i and homogeneous sensor j are x i and x j , the deviation calculation formula can be called to calculate the confidence distance between the first measurement data and the second measurement data. The first measurement data is the measurement data information collected by the homogeneous sensor i, and the second measurement data is the measurement data information collected by the homogeneous sensor j. The deviation calculation formula can be expressed as:

[0086]

[0087] The confidence distance between the second measurement data and the first measurement data is calculated by calling the deviation calculation formula:

[0088] The multidimensional confidence distance matrix is ​​determined according to the confidence distance between every two measurement data. That is, for n homogeneous sensors measuring the same physical feature, each confidence distance constitutes an n×n confidence distance matrix D as deviation data; the multidimensional confidence distance matrix D can be expressed as:

[0089]

[0090] Where, d ij is the measurement data x of the i-th homogeneous sensor i The measurement data x of the jth homogeneous sensor j The confidence distance, d ji For x j x i The confidence distance of i (x / x i ) is the one-dimensional confidence distance expression of the i-th homogeneous sensor or the probability density function, P j (x / x j ) is the probability density function of the homogeneous sensor j, x is the integral variable parameter, d nnis the confidence distance between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors. The value of the confidence distance reflects the mutual support distance between two homogeneous sensors. ij = 0.8, the surface is assumed to be based on the measurement data x of homogeneous sensor i i As an estimate, the measurement value x of the homogeneous sensor j is j The confidence distance under probability distribution is 80%. The larger the confidence distance, the greater the deviation of the data, and the smaller the confidence distance, the better the consistency of the two data in reflecting the same thing.

[0091] After determining the correlation and deviation between the measurement data, the confidence distance matrix is ​​a mathematical description of the consistency support between different homogeneous sensors. The support function can be expressed by inverse trigonometric functions, that is, the support calculation formula can be used to calculate the support of the first homogeneous sensor to the second homogeneous sensor; the support calculation formula can be expressed as:

[0092]

[0093] After determining the multidimensional confidence distance matrix, the support degree of a homogeneous sensor for another homogeneous sensor can be obtained. The multidimensional support matrix can be determined according to the support degree of every two homogeneous sensors. The multidimensional support matrix R can be expressed as:

[0094]

[0095] In the formula, r ij is the support degree of the i-th homogeneous sensor to the j-th homogeneous sensor, and the confidence distance d between two homogeneous sensors ij The larger the confidence distance d, the smaller the support between them. ij The smaller it is, the greater the support. nn is the support degree of the nth homogeneous sensor to the nth homogeneous sensor.

[0096] As can be seen from the above, this embodiment performs a series of processing on the measurement data, and multiple homogeneous sensors cooperate with each other, which is conducive to obtaining feature information with higher accuracy, reliability and breadth.

[0097] In the above embodiment, there is no limitation on how to execute step S103. In this embodiment, an optional implementation of data fusion is provided, which may include:

[0098] A non-negative real number vector is determined according to a consistency relationship matrix formed by consistency relationships among homogeneous sensors and its eigenvalue vector; the total number of elements of the non-negative real number vector is the same as the total number of homogeneous sensors, and each element corresponds to a comprehensive support degree of a homogeneous sensor, and the comprehensive support degree is the support degree of all homogeneous sensors to the current homogeneous sensor;

[0099] Determine the comprehensive support level of each homogeneous sensor according to a non-negative real number vector;

[0100] The fused data is obtained according to the comprehensive support degree of each homogeneous sensor and the corresponding measurement data information.

[0101] In this embodiment, the consistency relationship matrix takes a multidimensional support matrix as an example. i is the comprehensive support degree of all sensors for the measurement data information of the ith sensor. The larger the value, the higher the degree to which the measurement data information of the ith sensor is recognized by the entire homogeneous sensor network. The smaller the value, the less credible the measurement data information of the ith sensor is. i The sum is 1, which can form the matrix A = (a1, a2, ..., a n ) T According to the matrix definition, there exists a non-negative real vector Y=(y1,y2,…,y n ) T , so that A = RY. Since the multidimensional support matrix R is a non-negative symmetric matrix, according to its properties, it has a largest eigenvalue vector λ, so that RY = λY, and the vector Y can be obtained, that is, the non-negative real vector is determined. After determining the non-negative real vector, through the relationship Each element in the matrix A can be obtained. In this embodiment, X=a1x1+a2x2+…+a n x n Calculate the fused data. x1,x2,…,x n It is the measurement data information collected by different homogeneous sensors at the same time, and X is the fused data.

[0102] As can be seen from the above, the above method can realize the adaptive fusion of the measurement data information collected by each homogeneous sensor, and improve the accuracy of the measured signal. Of course, technicians in the relevant field can also use the weighted average fusion method for data fusion, but this method cannot be adaptively fused, and when the sensor is abnormal, it will cause fusion errors.

[0103] It should be noted that there is no strict order of execution between the steps in this application. As long as they comply with the logical order, these steps can be executed simultaneously or in a certain preset order. Figure 1-Figure 3 This is just a schematic and does not mean that this is the only execution order.

[0104] The embodiment of the present invention also provides a corresponding device for the state monitoring method, which further makes the method more practical. The device can be described from the perspective of functional modules and hardware. The state monitoring device provided by the embodiment of the present invention is introduced below. The state monitoring device described below and the state monitoring method described above can be referred to each other.

[0105] From the perspective of functional modules, see Figure 4 , Figure 4 A structural diagram of a state monitoring device provided in an embodiment of the present invention in a specific implementation manner, the device may include:

[0106] The data acquisition module 401 is used to obtain measurement data information of target physical quantities acquired by multiple homogeneous sensors through synchronous acquisition technology.

[0107] The data calculation module 402 is used to obtain sensor-related data by associating information on each measurement data; obtain deviation data by performing deviation calculation on each measurement data; and determine the consistency relationship between every two homogeneous sensors based on the sensor-related data and the deviation data.

[0108] The data fusion module 403 is used to fuse the measurement data information according to the consistency relationship between the homogeneous sensors.

[0109] The state monitoring module 404 is used to use the fused data as measurement data of the target physical quantity to perform state monitoring based on the target physical quantity.

[0110] Optionally, in some implementations of the present embodiment, the above-mentioned device may also include a filtering module, for example, for performing wavelet transform on the measurement data information of each homogeneous sensor after acquiring the measurement data information of the target physical quantity collected by multiple homogeneous sensors through synchronous acquisition technology to obtain a multi-layer decomposition sub-signal; performing threshold processing on the wavelet decomposition coefficients of each decomposition sub-signal to obtain estimated wavelet coefficients; and performing wavelet reconstruction using each estimated wavelet coefficient to obtain denoised measurement data information.

[0111] As an optional implementation of the above embodiment, the above filtering module can be further used to: determine the value of the preset critical threshold in advance according to the generation method of the preset critical threshold; the generation method includes a signal generation method and a noise generation method; call the estimated value calculation relationship to calculate the estimated wavelet coefficients of each layer of decomposition sub-signal, and the estimated value calculation relationship is:

[0112]

[0113] In the formula, is the estimated wavelet coefficient of the k-th layer decomposition sub-signal, j is the total number of layers of decomposition sub-signals, ω j,k is the wavelet decomposition coefficient of the k-th layer decomposition sub-signal, λ is the preset critical threshold, and sgn(·) is the sign function.

[0114] Optionally, in some other implementations of this embodiment, the data calculation module 402 may be used to: call an information association relationship formula to calculate the association value between every two pieces of measurement data information, where the information association relationship formula is:

[0115]

[0116] A multidimensional correlation matrix is ​​determined according to the correlation value of each two measurement data information to serve as sensor correlation data; the multidimensional correlation matrix P is:

[0117]

[0118] In the formula, p ij is the measurement data x of the i-th homogeneous sensor i and the measurement data x of the jth homogeneous sensor j The correlation value between is the measured data x i The mean of is the measured data x j The mean value of x i (h) is the measured data x i The hth data in x j (h) is the measured data x j The hth data in the measurement data, N is the total number of data contained in the measurement data; p nn is the correlation value between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors.

[0119] As an optional implementation of this embodiment, the data calculation module 402 may be further used to: call a deviation calculation formula to calculate the confidence distance between the first measurement data and the second measurement data, and the deviation calculation formula is:

[0120]

[0121] The multidimensional confidence distance matrix is ​​determined according to the confidence distance between every two measurement data as deviation data; the multidimensional confidence distance matrix D is:

[0122]

[0123] Where, d ij is the measurement data x of the i-th homogeneous sensor i The measurement data x of the jth homogeneous sensorj The confidence distance, P i (x / x i ) is the one-dimensional confidence distance expression of the i-th homogeneous sensor, x is the integral variable parameter, d nn is the confidence distance between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors.

[0124] As another optional implementation of this embodiment, the data calculation module 402 may be further used to: call a support degree calculation formula to calculate the support degree of the first homogeneous sensor to the second homogeneous sensor; the support degree calculation formula is:

[0125]

[0126] The multidimensional support matrix is ​​determined according to the support degree of each two homogeneous sensors; the multidimensional support matrix R is:

[0127]

[0128] In the formula, r ij is the support degree of the i-th homogeneous sensor to the j-th homogeneous sensor, r nn is the support degree of the nth homogeneous sensor to the nth homogeneous sensor.

[0129] Optionally, in some other implementations of the present embodiment, the data fusion module 403 may be further used to: determine a non-negative real vector based on a consistency relationship matrix formed by consistency relationships between homogeneous sensors and its eigenvalue vector; the total number of elements of the non-negative real vector is the same as the total number of homogeneous sensors, each element corresponds to a comprehensive support degree of a homogeneous sensor, and the comprehensive support degree is the support degree of all homogeneous sensors to the current homogeneous sensor; determine the comprehensive support degree of each homogeneous sensor based on the non-negative real vector; and obtain fused data based on the comprehensive support degree of each homogeneous sensor and the corresponding measurement data information.

[0130] The functions of the functional modules of the state monitoring device described in the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0131] It can be seen from the above that the embodiments of the present invention effectively improve the accuracy of mechanical equipment status monitoring and can ensure the safe and stable operation of the mechanical equipment.

[0132] The status monitoring device mentioned above is described from the perspective of functional modules. Furthermore, the present application also provides an electronic device, which is described from the perspective of hardware. Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application in one implementation manner. Figure 5 As shown, the electronic device includes a memory 50 for storing a computer program; and a processor 51 for implementing the steps of the state monitoring method mentioned in any of the above embodiments when executing the computer program.

[0133] Among them, the processor 51 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the processor 51 may also be a controller, a microcontroller, a microprocessor or other data processing chip. The processor 51 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 51 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 51 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 51 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0134] The memory 50 may include one or more computer-readable storage media, which may be non-transitory. The memory 50 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. The memory 50 may be an internal storage unit of an electronic device in some embodiments, such as a hard disk of a server. The memory 50 may also be an external storage device of an electronic device in other embodiments, such as a plug-in hard disk equipped on a server, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. Further, the memory 50 may also include both an internal storage unit of an electronic device and an external storage device. The memory 50 may not only be used to store application software and various types of data installed in the electronic device, such as: the code of the program for executing the vulnerability processing method, etc., but may also be used to temporarily store data that has been output or is to be output. In this embodiment, the memory 50 is at least used to store the following computer program 501, wherein, after the computer program is loaded and executed by the processor 51, the relevant steps of the state monitoring method disclosed in any of the aforementioned embodiments can be implemented. In addition, the resources stored in the memory 50 may also include an operating system 502 and data 503, etc., and the storage method may be temporary storage or permanent storage. The operating system 502 may include Windows, Unix, Linux, etc. The data 503 may include but is not limited to data corresponding to the status monitoring results, etc.

[0135] In some embodiments, the electronic device may further include a display screen 52, an input / output interface 53, a communication interface 54 or a network interface, a power supply 55 and a communication bus 56. Among them, the display screen 52 and the input / output interface 53 such as a keyboard belong to the user interface, and the optional user interface may also include a standard wired interface, a wireless interface, etc. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, etc. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface. The communication interface 54 may optionally include a wired interface and / or a wireless interface, such as a WI-FI interface, a Bluetooth interface, etc., which is usually used to establish a communication connection between the electronic device and other electronic devices. The communication bus 56 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0136] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than those shown in the figure, for example, it may also include a sensor 57 for realizing various functions.

[0137] The functions of the functional modules of the electronic device described in the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment. The specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0138] It can be seen from the above that the embodiments of the present invention effectively improve the accuracy of mechanical equipment status monitoring and can ensure the safe and stable operation of the mechanical equipment.

[0139] It is understandable that if the state monitoring method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electrically erasable programmable ROM, register, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, removable disk, CD-ROM, disk or optical disk and other media that can store program code.

[0140] Based on this, an embodiment of the present invention further provides a readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the state monitoring method described in any of the above embodiments are performed.

[0141] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the hardware disclosed in the embodiments, including devices and electronic devices, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0142] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0143] The above is a detailed introduction to a condition monitoring method, device, electronic device and readable storage medium provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A condition monitoring method, characterized in that: include: Acquire measurement data information of target physical quantities collected by multiple homogeneous sensors through synchronous acquisition technology; By correlating the information of each measurement data, sensor correlation data is obtained; by calculating the deviation of each measurement data, deviation data is obtained; and the consistency relationship between every two homogeneous sensors is determined according to the sensor correlation data and the deviation data; According to the consistency relationship between homogeneous sensors, the measurement data information is fused; using the fused data as measurement data of the target physical quantity to perform condition monitoring based on the target physical quantity; The deviation data is obtained by performing deviation calculation on each measurement data, including: The information association relationship formula is called to calculate the association value between every two pieces of measurement data information, and the information association relationship formula is: A multidimensional correlation matrix is ​​determined according to the correlation value of each two pieces of measurement data information to serve as the sensor correlation data; the multidimensional correlation matrix P is: The confidence distance between the first measurement data and the second measurement data is calculated by calling the deviation calculation formula, wherein the deviation calculation formula is: Wherein, determining the consistency relationship between every two homogeneous sensors according to the sensor association data and the deviation data includes: The support degree calculation formula is called to calculate the support degree of the first homogeneous sensor to the second homogeneous sensor; the support degree calculation formula is: In the formula, p ij is the measurement data x of the i-th homogeneous sensor i The correlation value between the measurement data xj of the jth homogeneous sensor, is the measured data x i The mean of is the mean of the measured data xj, x i (h) is the measured data x i The hth data in x j (h) is the hth data in the measurement data xj, N is the total number of data contained in the measurement data; p nn is the correlation value between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, n is the total number of homogeneous sensors, d ij is the measurement data x of the i-th homogeneous sensor i The confidence distance of the measurement data xj of the jth homogeneous sensor, P i (x / x i ) is the one-dimensional confidence distance expression of the i-th homogeneous sensor, x is the integral variable parameter, r ij is the support degree of the i-th homogeneous sensor to the j-th homogeneous sensor.

2. The condition monitoring method according to claim 1, characterized in that: After obtaining the measurement data information of the target physical quantity collected by multiple homogeneous sensors through the synchronous collection technology, it also includes: Perform wavelet transform on the measurement data information of each homogeneous sensor to obtain multi-layer decomposition sub-signals; Threshold processing is performed on the wavelet decomposition coefficients of each decomposed sub-signal to obtain estimated wavelet coefficients; The estimated wavelet coefficients are used to perform wavelet reconstruction to obtain denoised measurement data information.

3. The condition monitoring method according to claim 2, characterized in that: The step of performing threshold processing on the wavelet decomposition coefficients of each decomposed sub-signal to obtain estimated wavelet coefficients includes: The value of the preset critical threshold is determined in advance according to a generation method of the preset critical threshold; the generation method includes a signal generation method and a noise generation method; The estimated value calculation formula is called to calculate the estimated wavelet coefficients of each layer of decomposition sub-signal. The estimated value calculation formula is: In the formula, is the estimated wavelet coefficient of the k-th layer decomposition sub-signal, j is the total number of layers of decomposition sub-signals, ω j,k is the wavelet decomposition coefficient of the k-th layer decomposition sub-signal, λ is the preset critical threshold, and sgn(·) is the sign function.

4. The condition monitoring method according to claim 1, characterized in that: The deviation data is obtained by performing deviation calculation on each measurement data, including: A multidimensional confidence distance matrix is ​​determined according to the confidence distance between every two measurement data to serve as the deviation data; the multidimensional confidence distance matrix D is: Where, d nn is the confidence distance between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, and n is the total number of homogeneous sensors.

5. The condition monitoring method according to claim 4, characterized in that: The determining the consistency relationship between every two homogeneous sensors according to the sensor association data and the deviation data comprises: A multidimensional support matrix is ​​determined according to the support degree of each two homogeneous sensors; the multidimensional support matrix R is: In the formula, r nn is the support degree of the nth homogeneous sensor to the nth homogeneous sensor.

6. The condition monitoring method according to any one of claims 1 to 5, characterized in that: The fusing of the measurement data information according to the consistency relationship between the homogeneous sensors includes: Determine a non-negative real number vector according to a consistency relationship matrix formed by consistency relationships between homogeneous sensors and its eigenvalue vector; the total number of elements of the non-negative real number vector is the same as the total number of homogeneous sensors, each element corresponds to a comprehensive support degree of a homogeneous sensor, and the comprehensive support degree is the support degree of all homogeneous sensors to the current homogeneous sensor; Determining the comprehensive support level of each homogeneous sensor according to the non-negative real number vector; The fused data is obtained according to the comprehensive support degree of each homogeneous sensor and the corresponding measurement data information.

7. A condition monitoring device, characterized in that: include: A data acquisition module is used to obtain measurement data information of target physical quantities collected by multiple homogeneous sensors through synchronous acquisition technology; A data calculation module is used to obtain sensor-related data by performing information association on each measurement data; obtain deviation data by performing deviation calculation on each measurement data; and determine the consistency relationship between every two homogeneous sensors according to the sensor-related data and the deviation data; A data fusion module is used to fuse the measurement data information according to the consistency relationship between the homogeneous sensors; A state monitoring module, used for using the fused data as measurement data of the target physical quantity to perform state monitoring based on the target physical quantity; Wherein, the data calculation module is further used for: The information association relationship formula is called to calculate the association value between every two pieces of measurement data information, and the information association relationship formula is: A multidimensional correlation matrix is ​​determined according to the correlation value of each two pieces of measurement data information to serve as the sensor correlation data; the multidimensional correlation matrix P is: The information association relationship formula is called to calculate the association value between every two pieces of measurement data information, and the information association relationship formula is: The confidence distance between the first measurement data and the second measurement data is calculated by calling the deviation calculation formula, wherein the deviation calculation formula is: Wherein, the data fusion module is further used for: The support degree calculation formula is called to calculate the support degree of the first homogeneous sensor to the second homogeneous sensor; the support degree calculation formula is: In the formula, p ij is the measurement data x of the i-th homogeneous sensor i and the correlation value between the measurement data xj of the jth homogeneous sensor, Xi is the measurement data x i The mean value of X j is the mean of the measured data xj, x i (h) is the measured data x i The hth data in x j (h) is the hth data in the measurement data xj, N is the total number of data contained in the measurement data; p nn is the correlation value between the measurement data of the nth homogeneous sensor and the measurement data of the nth homogeneous sensor, n is the total number of homogeneous sensors, d ij is the measurement data x of the i-th homogeneous sensor i The confidence distance of the measurement data xj of the jth homogeneous sensor, P i (x / x i ) is the one-dimensional confidence distance expression of the i-th homogeneous sensor, x is the integral variable parameter, r ij is the support degree of the i-th homogeneous sensor to the j-th homogeneous sensor.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is used to implement the steps of the condition monitoring method according to any one of claims 1 to 6 when executing a computer program stored in the memory.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the condition monitoring method according to any one of claims 1 to 6 are implemented.

Images