Hydraulic pump state monitoring system based on multi-modal information fusion and digital twinning

Abstract

The invention discloses a hydraulic pump state monitoring system based on multi-modal information fusion and digital twinning, and particularly relates to the technical field of hydraulic equipment state monitoring. Comprising a hydraulic pump multi-modal data acquisition module, a hydraulic pump multi-modal feature engineering module, a hydraulic pump state hierarchical fusion diagnosis module, a hydraulic pump health state and risk assessment module and a digital twinning and decision support module. The hydraulic pump multi-modal data acquisition module synchronously acquires key operation parameters of a hydraulic pump through a distributed sensor array, and pre-processes the key operation parameters to obtain a hydraulic pump multi-modal parameter set; the hydraulic pump state hierarchical fusion diagnosis module combines the advantages of RF, CNN, LSTM + Attention and other algorithms, a cavitation diagnosis sub-model, a bearing wear diagnosis sub-model and an internal leakage diagnosis sub-model are constructed respectively, diagnosis can be performed for different fault types, and automation and intelligence from feature extraction to fusion diagnosis are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hydraulic equipment state monitoring, in particular to a hydraulic pump state monitoring system based on multi-modal information fusion and digital twinning. BACKGROUND

[0002] In the modern industrial field, hydraulic pumps, as key power transmission and control components, are widely used in engineering machinery, metallurgy, mining, aerospace and many other industries. The stability and reliability of their operation state are directly related to the efficiency and safety of the entire production system.

[0003] Traditional hydraulic pump state monitoring methods include single parameter monitoring method, regular inspection and maintenance, and simple rule-based diagnostic system. The single parameter monitoring method triggers an alarm when the monitoring parameter exceeds the normal range by setting a fixed threshold. Regular inspection and maintenance involve manual inspection of the hydraulic pump, and the device is judged to be abnormal by observation, auscultation, and touch. The simple rule-based diagnostic method judges the fault according to the pre-set fault mode and the corresponding parameter change range. The above methods are used to monitor the state of the hydraulic pump.

[0004] Although the traditional hydraulic pump state monitoring method can monitor the state of the hydraulic pump, it also has limitations. For example, the single parameter monitoring method has a single fault mode and cannot accurately diagnose the fault state of the hydraulic pump. Regular inspection and maintenance rely on post-analysis or regular inspection, which cannot detect problems in the early stages of failure and has the risk of missed detection and misjudgment. The simple rule-based diagnostic method lacks quantitative indicators and can only give qualitative judgments of normal or abnormal, which cannot meet the needs of modern industrial production for fine management of equipment maintenance. Moreover, it lacks deep data mining and intelligent analysis capabilities, making it difficult to predict the future operating state and remaining useful life of the hydraulic pump. Therefore, it is of great significance to develop a system that can monitor the state of the hydraulic pump in real time, accurately and comprehensively, and predict its remaining useful life. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a hydraulic pump state monitoring system based on multi-modal information fusion and digital twinning to solve the problems raised in the background art.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a hydraulic pump state monitoring system based on multi-modal information fusion and digital twinning, comprising: A hydraulic pump multi-modal data acquisition module: synchronously acquires key operating parameters of the hydraulic pump through a distributed sensor array, and obtains a set of hydraulic pump multi-modal parameters after preprocessing; Hydraulic pump multi-modal feature engineering module: feature extraction is performed on the hydraulic pump multi-modal parameter set to obtain a hydraulic pump multi-modal feature data set, including basic parameter features, vibration signal features and motor and flow features; Hydraulic pump state hierarchical fusion diagnosis module: including a parallel expert model diagnosis unit and a fusion diagnosis unit, based on the hydraulic pump multi-modal feature data set, first performing parallel expert model diagnosis, and then performing fusion diagnosis to obtain a hydraulic pump state diagnosis result and transmit the result to the hydraulic pump health state and risk assessment module; Hydraulic pump health state and risk assessment module: based on the hydraulic pump state diagnosis result, a hydraulic pump health index is obtained through a mapping rule, a hydraulic pump risk index is obtained based on the hydraulic pump health index, and a remaining useful life prediction is performed to obtain a hydraulic pump health state and risk assessment result; Digital twin and decision support module: based on the hydraulic pump state diagnosis result, different maintenance strategy parameters are input, a digital twin model built in the hydraulic pump is used to virtually debug and optimize the maintenance strategy parameters, and optimal maintenance suggestions are obtained to the management end for human-computer interaction.

[0007] Technical effects and advantages of the present application: 1. The hydraulic pump multi-modal data acquisition module is used to comprehensively acquire mechanical, hydraulic, thermodynamic and electrical signals of the hydraulic pump; meanwhile, the hydraulic pump multi-modal feature engineering module is used to extract features from the hydraulic pump multi-modal parameter set, thereby providing a data basis for accurate diagnosis, improving the accuracy of fault diagnosis, and reducing the possibility of misdiagnosis and missed diagnosis; 2. The hydraulic pump state hierarchical fusion diagnosis module combines the advantages of RF, CNN, LSTM+Attention algorithms, respectively constructs a cavitation diagnosis sub-model, a bearing wear diagnosis sub-model and an internal leakage diagnosis sub-model, can diagnose different fault types, and realizes automation and intelligentization from feature extraction to fusion diagnosis; 3. The hydraulic pump health state and risk assessment module introduces health index HI and risk index RI, and realizes remaining useful life RUL prediction, so that maintenance is changed from 'after the event' to 'before the event', potential faults are identified in advance and corresponding maintenance measures are taken, and the system can effectively avoid unplanned shutdown, improve the reliability and efficiency of the production line. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 The figure is a schematic diagram of the overall process of the present application.

[0009] Figure 2 The figure is a schematic diagram of the hydraulic pump state hierarchical fusion diagnosis module of the present application. DETAILED DESCRIPTION

[0010] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of the present application.

[0011] Please refer to Figure 1 As shown in the drawings, the present application provides a hydraulic pump state monitoring system based on multi-modal information fusion and digital twinning, which comprises a hydraulic pump multi-modal data acquisition module, a hydraulic pump multi-modal feature engineering module, a hydraulic pump state hierarchical fusion diagnosis module, a hydraulic pump health state and risk assessment module, and a digital twinning and decision support module.

[0012] The hydraulic pump multi-modal data acquisition module is connected with the hydraulic pump multi-modal feature engineering module, the hydraulic pump state hierarchical fusion diagnosis module is connected with the hydraulic pump multi-modal feature engineering module and the hydraulic pump health state and risk assessment module respectively, and the digital twinning and decision support module is connected with the hydraulic pump health state and risk assessment module.

[0013] The hydraulic pump multi-modal data acquisition module synchronously acquires key operating parameters of the hydraulic pump through a distributed sensor array, and obtains a hydraulic pump multi-modal parameter set after preprocessing; The key operating parameters of the hydraulic pump include inlet vacuum degree, outlet pressure, three-dimensional vibration signal, flow, temperature, motor power and motor current; X / Y / Z axis vibration acceleration is collected according to the vibration signal; It needs to be specifically explained in this embodiment that the inlet vacuum degree: a vacuum pressure sensor is adopted, the sampling frequency is 1 kHz, and the acquisition range covers absolute pressure 0-1 atm; the outlet pressure: a high-frequency dynamic pressure sensor is adopted, the sampling frequency is 10 kHz, and FFT spectrum analysis is supported; the vibration signal: a three-axis acceleration sensor is adopted, the sampling frequency is 50 kHz, and three-dimensional direction vibration data are collected; the flow: a turbine or ultrasonic flowmeter is adopted, the sampling frequency is 100 Hz, and the measurement accuracy is ≤±1%; the temperature: a PT100 temperature sensor is adopted, the sampling frequency is 1 Hz, and the measurement range is -50℃-200℃; the motor power: a power sensor is adopted, the sampling frequency is 100 Hz, and active power and reactive power are collected; the motor current: a current sensor is adopted, the sampling frequency is 1 kHz, and stator current signals are collected for spectrum analysis.

[0014] The preprocessing includes denoising the operating parameters by a denoising technology (such as wavelet denoising), aligning the data of the operating parameters by a time stamp interpolation method (such as linear interpolation, spline interpolation, etc.), and obtaining the hydraulic pump multi-modal parameter set; This embodiment specifically explains the timestamp-based interpolation data alignment method, which ensures that multimodal data from different sensors remain consistent in the time dimension. This guarantees that the features extracted by subsequent feature engineering and the data used by the hierarchical fusion diagnostic model are all based on the same time reference, thereby improving the accuracy and reliability of fault diagnosis.

[0015] Hydraulic pump multimodal feature engineering module: Extracts features from the multimodal parameter set of hydraulic pump to obtain a multimodal feature dataset of hydraulic pump, including basic parameter features, vibration signal features, and motor and flow characteristics; The basic parameter characteristics are based on the inlet vacuum degree P. in and export pressure P out The ratio of the inlet vacuum pressure difference R is calculated. p Within the set sliding window, the maximum value P of the outlet pressure is collected respectively. out，max Minimum value P out，min and mean P out，avg Calculate the outlet pressure deviation rate DR p DR p =(P out，max -P out，min ) / P out，avg ; The vibration signal characteristics are as follows: Based on the vibration signal, three-dimensional vibration signals are collected, including three-dimensional vibration signals of the hydraulic pump and bearings; Fourier transform is performed on the vibration signals to obtain the power spectral density S(f) of each dimension of the hydraulic pump, and the 500-1000Hz broadband power P of each dimension is obtained. 500-1000 , The vibration-averaged broadband power P is obtained by averaging the three-dimensional broadband power. 500-1000 avg For each dimension of the bearing vibration signal, calculate the fault characteristic frequency f of the outer ring, inner ring, and ball bearing respectively. o f i and f b , Where n is the motor speed, z is the number of balls, d is the ball diameter, D is the pitch circle diameter, and θ is the contact angle. , In most cases, when referring to the contact angle, it usually means the contact angle between the inner ring and the ball, because the inner ring usually rotates with the shaft, while the outer ring is fixed in the bearing housing; however, in specially designed bearings, the contact angle may also refer to the angle between the outer ring and the ball. The embodiment needs to be specifically explained that the vibration signal power spectral density S(f) can be obtained by the existing formula of Welch power spectral density, for each dimension of vibration acceleration signal a(t), remove the signal lamp DC offset, divide the long time domain signal a(t) into n1 shorter, overlapping segments, multiply each segment of data by a window function w(n) (such as Hanning window), obtain each windowed signal x k (n), and perform fast Fourier transform to obtain its discrete Fourier transform X k (f), calculate the signal power spectrum of the segment, and average the signal power spectra of the K segments to obtain the vibration signal power spectral density S(f) of each dimension.

[0016] The motor and flow characteristics: based on the measured power P me , the measured flow Q (unit: L / min), the outlet pressure P out (unit: bar) to obtain the theoretical power P th (unit: kW, bar×L / min=kW), P th =Q×P out / 600η, η is the theoretical volumetric efficiency of the hydraulic pump (for example, 0.95), based on the measured power P me and the theoretical power P th , the power efficiency deviation ΔP is obtained; based on the rated flow Q ra of the hydraulic pump, the flow attenuation rate DR Q is calculated, DR Q =(Q-Q ra ) / Q ra ; Please refer to Figure 2 , the hydraulic pump state hierarchical fusion diagnosis module: including parallel expert model diagnosis unit and fusion diagnosis unit, based on the multi-modal feature data set of the hydraulic pump, first parallel expert model diagnosis, then fusion diagnosis, get the hydraulic pump state diagnosis result and transmit to the hydraulic pump health state and risk assessment module; The parallel expert model diagnosis unit: including cavitation diagnosis sub-model, bearing wear diagnosis sub-model, internal leakage diagnosis sub-model; The cavitation diagnosis sub-model: based on the multi-modal feature data set of the hydraulic pump, the vibration average broadband power P 500-1000 avg , the inlet vacuum P in and the outlet pressure deviation rate DR p are constructed into a multi-source feature vector as the input feature vector X cav of the preset random forest model (RF), X cav =[P 500-1000 avg , P in , DRp Suppose that the random forest consists of K decision trees {h} k (x)} k=1 K For the input feature vector X cav Each decision tree outputs the probability p of cavitation occurring. k，cav p k，cav =h k (X cav Next, the cavitation confidence level C is obtained by averaging the outputs of the K decision trees. cav , Finally, based on the cavitation confidence level, the cavitation severity level L is classified. cav , Cavitation refers to the vaporization of a liquid into bubbles during the operation of a hydraulic pump, caused by a local pressure drop below the liquid's vaporization pressure. It is typically identified by monitoring vibration and pressure change parameters. The output of the cavitation diagnostic sub-model includes the cavitation confidence level C. cav Cavitation severity level L cav ; The bearing wear diagnostic sub-model includes: A1: Constructing Input Features: Based on the multimodal feature dataset of hydraulic pumps, extract the three-dimensional vibration time-series data X of bearings. vib ∈R 3×T T represents the time step, 3 represents the three-dimensional vibration direction, and the characteristic frequencies f of the outer ring, inner ring, and ball bearing faults are extracted. o f i f b Based on the power spectral density S(f) of the vibration signal, the average power values ​​Sf in the three-dimensional vibration directions of the outer ring, inner ring, and balls at the characteristic frequency of bearing failure are obtained respectively. o，avg (f0), S i，avg (f i ), S b，avg (f b ), construct the input feature vector X of the pre-defined 1D convolutional neural network (1D-CNN) in X in =[X vib ;S o，avg (f0), S i，avg (f i ), S b，avg (f b )]; A2: Local temporal feature extraction: First, perform convolutional layer 1, y1=ReLU(X in *w1+b1), where * represents the convolution operation, w1 is the convolution kernel, and w1∈R. k1×c1, k1=32 is the kernel size, c1=16 is the output channel number, b1 is the bias term, ReLu activation function, extracts local features such as impact, periodic pulse in the vibration signal, such as periodic vibration generated by bearing wear; then the pooling layer 1, y p1 =MaxPooling(y1, s1=2), the pooling window step s1 is 2, and the output y p1 ∈R c1×T / 2 , MaxPooling is a pooling operation; A3: Fusion feature frequency: first, the convolution layer 2, y2=ReLu(y p1 *w2+b2), w2 is the convolution kernel, w2∈R k2×c2 , k2=16, c2=32, b2 is the bias term, further fusion of local time sequence features and feature frequency power, and strengthening of fault frequency correlation features; then the pooling layer 2, y p2 =MaxPooling(y2, s2=2), the output y p2 ∈R c1×T / 2 ; the pooling output is flattened into a vector y flat ∈R N , N is the dimension after flattening, and the full connection layer y fc1 =ReLu(W3×y flat +b3) is obtained, W3 is the weight matrix of the full connection layer y fc1 , b3 is the corresponding bias term; the probability distribution P of three types of faults is output through the Softmax function, P=Softmax(W4×y fc1 +b4), W3 is the weight matrix of the output layer, and b4 is the corresponding bias term; A4: Output result: including inner ring fault probability P in , outer ring fault probability P out , ball fault probability P ball and bearing wear confidence C bear , , β is the weight (for example, 0.6), C bear ∈[0, 1], the higher the value, the more reliable the diagnosis result is, if C bear ≥ the corresponding threshold (for example, 0.6), it is determined that the corresponding fault type is taken, otherwise it is determined that there is no bearing fault; The inner leakage diagnosis sub-model: first, a multivariate time series X le is constructed, the time series length is tt, X le =[Q(t), T(t), P out (t), P me (t), ΔP(t), DR Q (t)], Q(t), T(t), P out(t), P me (t), ΔP(t) and DR Q (t) are respectively the measured flow rate, temperature, outlet pressure, power, power efficiency deviation and flow rate decay rate; then the multivariate time series X le is processed through an LSTM layer (Long Short Term Memory network) to obtain a hidden state sequence {h t} t=1 tt , h t is the hidden state at time t; then the attention weight a t , , e t =W h ×h t +b h , W h and b h are respectively the weight matrix and bias term of the hidden state sequence, a t is the attention weight of the hidden state at time t; then the hidden state is weighted and fused to obtain a fused feature h att , ; then the fused feature h att is input to a fully connected layer to obtain the internal leakage rate R le through a Sigmoid function Sigmoid(W fc ×h att +b fc ), W fc and b fc are respectively the weight matrix and bias term of the fully connected layer; finally, the prediction error MAE of the LSTM+Attention model and the feature consistency CV are combined to obtain the internal leakage confidence C le , C le =(1-MAE)×γ+(1-CV)×(1-γ), MAE is the average absolute error of the model predicted leakage rate R le and the true value R le，0 , CV is the coefficient of variation of the power efficiency deviation ΔP and the flow rate decay rate DR Q , the coefficient of variation CV is the ratio of the standard deviation (σ(ΔP), σ(DRQ)) after combination of the two variables to the mean (μ(ΔP), μ(DRQ)) after combination; in internal leakage diagnosis, ΔP (power efficiency deviation) and DRQ (flow rate decay rate) are strongly related features in physics, by measuring the change synchronism of the two variables, the physical explainability of the internal leakage diagnosis confidence is enhanced; the internal leakage diagnosis submodel output results including the internal leakage rate R le and the internal leakage confidence C le are obtained; The embodiment needs to be specifically explained that the LSTM is prior art, and the hidden state is updated through the forgetting gate, the input gate, the cell state and the output gate to obtain a hidden state sequence {h t} t=1 tt .

[0017] The fusion diagnosis unit comprises: B1: defining an identification framework: based on D-S evidence theory fusion, defining an identification framework Θ, Θ={normal, cavitation, bearing wear, internal leakage, compound failure}, the compound failure is the case of simultaneously existing two or more than two single faults, and the bearing wear includes inner ring failure probability, outer ring failure probability and ball failure; B2: basic probability assignment: based on the output results of the cavitation diagnosis sub-model, including cavitation confidence C cav and cavitation severity level L cav , the basic probability assignment function m1(A) of the cavitation diagnosis sub-model is constructed through the function f1, which satisfies m1(A1)+m1(Θ)=1, m1(A1) and m1(Θ) are basic probability assignment results, ; the basic probability assignment function m2(A) of the bearing wear diagnosis sub-model is constructed through the function g1, and the basic probability assignment function m3(A) of the internal leakage diagnosis sub-model is constructed through the function h1, which is logically the same as the basic probability assignment function m1(A) of the cavitation diagnosis sub-model, , P max is the maximum value of the inner ring failure probability P in , the outer ring failure probability P out and the ball failure probability P ball , the bearing wear confidence C bear , , the internal leakage rate R le and the internal leakage confidence C le ; A in m2(A) is {bearing wear}, and A in m3(A) is {internal leakage}; B3: evidence combination: the basic probability assignment m(A) after the combination of the three sub-models is: , the numerator represents the sum of the products of the corresponding subset basic probabilities of A1, A2 and A3 in the basic probability assignment from each sub-model when the intersection of the subsets is A, and the denominator represents the intersection of the subsets is empty, which is normalized by subtracting the conflict measure from 1; B4: hydraulic pump state diagnosis result: based on the combined basic probability assignment m(A), the comprehensive health state HS of the hydraulic pump is obtained, HS=argmax A∈Θ m(A), for example, if m{cavitation} is the largest in all m(A), the comprehensive health state is determined as cavitation failure; The hydraulic pump health state and risk assessment module: based on the hydraulic pump state diagnosis result, the hydraulic pump health index is obtained through the mapping rule, the hydraulic pump risk index is obtained based on the hydraulic pump health index, and the remaining useful life prediction is carried out, and the hydraulic pump health state and risk assessment result is obtained; The hydraulic pump health index: based on the hydraulic pump state diagnosis result HS, it is multiplied by 100 to map to 1-100 points, including the normal hydraulic pump health index HI score range, the cavitation HI score range, the bearing wear HI score range, the internal leakage HI score range, and the composite fault HI score range; the volume efficiency attenuation coefficient kη is introduced to correct HI, and finally the corrected HI is obtained th , HI th =HI×kη, kη is the ratio of the current efficiency η me of the hydraulic pump to the theoretical efficiency η, and the ratio of the current efficiency output power to the input power of the hydraulic pump; The embodiment needs to be specifically described that the HI score is, for example, the normal HI score range is 95-100, the cavitation HI score range is 80-95 for level 1, 60-80 for level 2, the internal leakage HI score range is 50-70, and the composite fault HI score range is <50.

[0018] The hydraulic pump risk index: the fault severity weight S is defined in advance (for example, slight leakage S=1.0, which is obtained by analyzing historical fault cases and assigning fixed weight values to different fault types), the risk index RI is calculated, RI=(100-HI)×S / 10; then the risk level is divided: if RI belongs to the preset high risk level (for example, 7.5), the immediate shutdown maintenance suggestion is triggered, if RI belongs to the medium risk level (for example, 5 The remaining useful life prediction: a pre-trained LSTM model is used to predict n2 future time points, the HI sequence [HI TT-m1+1 ,..., HI TT ] of the last m1 time points is input, TT is the current time, the next time HI TT+1 is predicted, [HI TT-m1+2 ,..., HI TT , HI TT ] is taken as new input, HI TT+2 is predicted, and so on, to obtain the HI degradation curve prediction result HI(TT1), TT1>TT; set the time threshold HI fail (for example, 20), solve the minimum time t fail that satisfies HI(TT1)≤HI fail , and the remaining useful life is RUL=tfail -t me , t me The current moment; Digital Twin and Decision Support Module: Based on the hydraulic pump status diagnosis results, different maintenance strategy parameters are input, and the maintenance strategy parameters are virtually debugged and optimized using the built-in digital twin model of the hydraulic pump to obtain the optimal maintenance suggestions for human-computer interaction at the management end, including the following steps; C1: Based on the hydraulic pump condition diagnosis results, input different maintenance strategy parameters θ into the built-in digital twin model of the hydraulic pump, θ=[θ1, θ2, ..., θ...]. M ], θ M The parameters for the Mth maintenance strategy are (e.g., hydraulic pump speed, system set pressure, etc.); then, based on the remaining useful life (RUL), the RUL after implementing the maintenance strategy θ is obtained. θ RUL θ =RUL0+ΔRUL(θ), where ΔRUL(θ) is the lifetime extension time; C2: Strategy Benefit Calculation: Benefit value B(θ) is the output value RUL brought about by the lifespan extension. θ ×C pr Total maintenance cost C ma The ratio of (θ) is obtained, C pr The output value per unit time is calculated based on the economic value produced by the hydraulic pump, with the unit being yuan / s. The total maintenance cost is also in yuan, referring to the cost of all maintenance strategies converted into yuan according to preset rules. Based on the benefit value B(θ) of virtual debugging, the maintenance strategy with the greatest benefit is selected. This embodiment needs to specifically explain the maintenance strategy costs, such as the energy cost of adjusting pressure and the time cost of downtime maintenance. The preset rules are: for example, the energy cost of adjusting pressure multiplied by the electricity price is the cost in yuan, and the downtime maintenance time multiplied by the output value per unit time is the cost in yuan.

[0019] C3: Optimal Maintenance Recommendation: This includes determining the latest maintenance time t based on the Remaining Useful Life (RUL) predicted by the LSTM model and the production schedule. ma Maintenance recommendations are determined based on the hydraulic pump risk index. Based on the benefit value B(θ) of virtual commissioning, the maintenance strategy with the greatest benefit is selected. At the same time, the hydraulic pump health index HI, hydraulic pump risk index RI, and remaining useful life RUL are displayed. Finally, the optimal maintenance recommendation is sent to the management terminal for human-computer interaction.

[0020] This embodiment specifically explains that the built-in digital twin model of the hydraulic pump integrates physical models such as the hydraulic pump flow continuity equation and Bernoulli equation with the data-driven model of the hydraulic pump state diagnosis output to realize real-time mapping of the hydraulic pump operating state, thereby constructing a digital twin model of the hydraulic pump.

[0021] Secondly: the drawings of the disclosed embodiments only involve the structures involved in the disclosed embodiments, other structures can be referred to the general design, and in the case of no conflict, the same embodiments and different embodiments of the present application can be combined with each other; Finally: the above only describes the preferred embodiments of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A hydraulic pump condition monitoring system based on multimodal information fusion and digital twin, characterized in that: include: Hydraulic pump multimodal data acquisition module: Synchronously acquires key operating parameters of the hydraulic pump through a distributed sensor array, and obtains the hydraulic pump multimodal parameter set after preprocessing; Hydraulic pump multimodal feature engineering module: Extracts features from the multimodal parameter set of hydraulic pump to obtain a multimodal feature dataset of hydraulic pump, including basic parameter features, vibration signal features, and motor and flow characteristics; Hydraulic pump status hierarchical fusion diagnosis module: includes a parallel expert model diagnosis unit and a fusion diagnosis unit. Based on the hydraulic pump multimodal feature dataset, it first performs parallel expert model diagnosis, then performs fusion diagnosis, obtains hydraulic pump status diagnosis results, and transmits them to the hydraulic pump health status and risk assessment module. Hydraulic pump health status and risk assessment module: Based on the hydraulic pump status diagnosis results, the hydraulic pump health index is obtained through mapping rules, the hydraulic pump risk index is obtained based on the hydraulic pump health index, and the remaining useful life is predicted to obtain the hydraulic pump health status and risk assessment results. Digital Twin and Decision Support Module: Based on the hydraulic pump status diagnosis results, different maintenance strategy parameters are input, and the built-in digital twin model of the hydraulic pump is used to virtually debug and optimize the maintenance strategy parameters to obtain the optimal maintenance suggestions for human-computer interaction at the management end.

2. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin as described in claim 1, characterized in that: The cavitation diagnosis sub-model in the parallel expert model diagnosis unit: based on the multimodal feature dataset of the hydraulic pump, the vibration average broadband power P 500-1000 avg Imported vacuum degree P in and export pressure deviation rate DR p The multi-source feature vectors formed are used as the input feature vector X of the pre-defined random forest model. cav X cav =[P 500-1000 avg P in DR p Suppose that the random forest consists of K decision trees {h} k (x)} k=1 K For the input feature vector X cav Each decision tree outputs the probability p of cavitation occurring. k，cav p k，cav =h k (X cav Next, the cavitation confidence level C is obtained by averaging the outputs of the K decision trees. cav Finally, based on the cavitation confidence level, the cavitation severity level L is classified. cav ; The output of the cavitation diagnosis sub-model is obtained, including the cavitation confidence level C. cav Cavitation severity level L cav .

3. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin as described in claim 1, characterized in that: The bearing wear diagnosis sub-model in the parallel expert model diagnosis unit includes: A1: Constructing Input Features: Based on the multimodal feature dataset of hydraulic pumps, extract the three-dimensional vibration time-series data X of bearings. vib ∈R 3 ×T T represents the time step, 3 represents the three-dimensional vibration direction, and the characteristic frequencies f of the outer ring, inner ring, and ball bearing faults are extracted. o f i f b Based on the power spectral density S(f) of the vibration signal, the average power values ​​Sf in the three-dimensional vibration directions of the outer ring, inner ring, and balls at the characteristic frequency of bearing failure are obtained respectively. o，avg (f0), S i，avg (f i ), S b，avg (f b ), construct the input feature vector X of the pre-defined 1D convolutional neural network. in X in =[X vib ;S o，avg (f0), S i，avg (f i ), S b，avg (f b )]; A2: Local temporal feature extraction: First, perform convolutional layer 1, y1=ReLU(X in *w1+b1), where * represents the convolution operation, w1 is the convolution kernel, and w1∈R. k1×c1 k1=32 is the kernel size, c1=16 is the number of output channels, b1 is the bias term, and ReLU activation function is used; then pooling layer 1 is performed, y p1 =MaxPooling(y1, s1=2), the pooling window stride s1 is 2, and the output is y1. p1 ∈R c1×T / 2 MaxPooling is a pooling operation.

4. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin as described in claim 1, characterized in that: The bearing wear diagnosis sub-model in the parallel expert model diagnosis unit also includes: A3: fusing feature frequencies: first, performing convolutional layer 2, y2=ReLU(y p1 *w2+b2), where w2 is the convolution kernel, and w2∈R k2×c2 k2=16, c2=32, b2 is a bias term, which further integrates local temporal features with characteristic frequency power to enhance fault frequency correlation features; then pooling layer 2 is performed, y p2 =MaxPooling(y2, s2=2), outputs y p2 ∈R c1×T / 2 Flatten the pooling output into a vector y. flat ∈R N N is the dimension after flattening, resulting in the fully connected layer y. fc1 =ReLu(W3×y flat +b3), W3 is a fully connected layer y fc1 The weight matrix is ​​given by b3, where b3 is the corresponding bias term; the probability distribution P of the three types of faults is output through the Softmax function, P = Softmax(W4 × y fc1 +b4), W3 is the weight matrix of the output layer, and b4 is the corresponding bias term; A4: Output results: including the inner ring failure probability P in outer ring failure probability P out and the probability of ball bearing failure P ball and bearing wear confidence level C bear C bear ∈[0,1], if C bear If the value is greater than or equal to the corresponding threshold, it is determined to be the corresponding fault type, and the item with the highest probability is selected; otherwise, it is determined to be a bearingless fault.

5. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin as described in claim 1, characterized in that: The internal leakage diagnosis sub-model in the parallel expert model diagnosis unit: First, a multivariate time series X is constructed. le The time series length is t, X le =[Q(t), T(t), P out (t), P me (t), ΔP(t), DR Q [(t)], Q(t), T(t), P out (t), P me (t), ΔP(t) and DR Q (t) represents the measured flow rate, temperature, outlet pressure, power, power efficiency deviation, and flow rate decay rate, respectively; then, the multivariate time series X is processed through an LSTM layer. le Processing yields the hidden state sequence {h} t } t=1 tt h t Let be the hidden state at time t; then, the attention weight 'a' is calculated using an attention mechanism. t a t Let h be the attention weights of the hidden state at time t; then, the hidden states are weighted and fused to obtain the fused feature h. att , Next, the feature h is fused. att The input is fed into a fully connected layer and passes through the Sigmoid function (Sigmoid(W)). fc ×h att +b fc The internal leakage rate R is obtained. le W fc and b fc These are the weight matrix and bias term of the fully connected layer, respectively; finally, the prediction error (MAE) and feature consistency (CV) of the LSTM+Attention model are combined to obtain the inner leakage confidence C. le C le =(1-MAE)×γ+(1-CV)×(1-γ), where MAE is the model-predicted leakage rate R. le Compared with the true value R le，0 The mean absolute error, CV, is the power efficiency deviation ΔP and the flow rate attenuation rate DR. Q coefficient of variation; The output of the internal leakage diagnostic sub-model is obtained, including the internal leakage rate R. le and internal leakage confidence level C le .

6. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin according to claim 1, characterized in that: The fusion diagnostic unit includes: B1: Define the identification framework: Based on the DS evidence theory fusion, define the identification framework Θ, Θ={normal, cavitation, bearing wear, internal leakage, composite fault}, composite fault is the situation where two or more of the above single faults exist at the same time, bearing wear includes inner ring fault probability, outer ring fault probability and ball fault. B2: Basic probability allocation: Based on the output of the cavitation diagnosis sub-model, including the cavitation confidence level C. cav Cavitation severity level L cav The basic probability allocation function m1(A) of the cavitation diagnostic sub-model is constructed using function f1, satisfying m1(A) i )+m1(Θ)=1, m1(A1) and m1(Θ) are the basic probability allocation result and the frame Θ probability allocation result, respectively; then the basic probability allocation function m2(A) of the bearing wear diagnosis sub-model is constructed through function g1 and the basic probability allocation function m3(A) of the internal leakage diagnosis sub-model is constructed through function h1, which are logically the same as the basic probability allocation function m1(A) of the cavitation diagnosis sub-model. B3: Evidence Combination: The basic probability assignment m(A) after combining the three sub-models is: The numerator represents the sum of the products of the basic probabilities of the corresponding subsets of each submodel when the intersection of the subsets A1, A2 and A3 from the basic probability assignments of each submodel is A. The denominator represents the fact that the intersection of the subsets is empty, and the conflict measure is subtracted from 1 for normalization. B4: Hydraulic pump condition diagnosis result: The comprehensive health status HS of the hydraulic pump is obtained based on the combined basic probability allocation m(A), HS=argmax A∈Θ m(A).

7. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin as described in claim 1, characterized in that: The hydraulic pump health index is based on the hydraulic pump condition diagnosis result HS, which is multiplied by 100 and mapped to a score of 1-100. It includes the normal hydraulic pump health index HI score range, the HI score range for cavitation, the HI score range for bearing wear, the HI score range for internal leakage, and the HI score range for compound faults. By introducing a volumetric efficiency attenuation coefficient kη to correct HI, the corrected HI is finally obtained. th HI th =HI×kη, where kη is the current efficiency η of the hydraulic pump. me The ratio of the theoretical efficiency η to the current efficiency of the hydraulic pump, which is the ratio of the output power to the input power. The risk index of the hydraulic pump is calculated by pre-defining the failure severity weight S and calculating the risk index RI, where RI = (100 - HI) × S / 10. Then, risk levels are classified: if RI is at the preset high-risk level, an immediate shutdown maintenance recommendation is triggered; if RI is at the medium-risk level, a planned maintenance recommendation is triggered; if RI is at the low-risk level, a continuous monitoring recommendation is triggered. The remaining useful life prediction: A pre-trained LSTM model is used to predict the next n2 time steps, with the HI sequence [HI] of the most recent m1 time steps as input. TT-m1+1 , ..., HI TT ], TT represents the current time, and the next time HI is predicted. TT+1 Then [HI] TT-m1+2 , ..., HI TT HI TT As a new input, predict HI TT+2 By analogy, the predicted HI decay curve result HI(TT1) is obtained, where TT1 > TT; a time threshold HI is set. fail Solve for HI(TT1)≤HI fail The minimum time t fail Then the remaining useful lifetime is RUL=t fail -t me , t me This refers to the current moment.

8. The hydraulic pump condition monitoring system based on multimodal information fusion and digital twin as described in claim 1, characterized in that: The digital twin and decision support module includes: C1: Based on the hydraulic pump condition diagnosis results, inputting different maintenance strategy parameters θ into the built-in digital twin model of the hydraulic pump, θ=[θ1, θ2, ..., θ...]. M ], θ M Let θ be the parameter of the Mth maintenance strategy; then, based on the remaining useful life (RUL), the RUL after implementing the maintenance strategy θ is obtained. θ RUL θ =RUL0+ΔRUL(θ), where ΔRUL(θ) is the lifetime extension time; C2: Strategy Benefit Calculation: Benefit value B(θ) is the output value RUL brought about by the lifespan extension. θ ×C pr Total maintenance cost C ma The ratio of (θ) is obtained, C pr The output value per unit time is calculated based on the economic value produced by the hydraulic pump, with the unit being yuan / s. The total maintenance cost is also in yuan, referring to the cost of all maintenance strategies converted into yuan according to preset rules. Based on the benefit value B(θ) of virtual debugging, the maintenance strategy with the greatest benefit is selected. C3: Optimal Maintenance Recommendation: This includes determining the latest maintenance time t based on the Remaining Useful Life (RUL) predicted by the LSTM model and the production schedule. ma Maintenance recommendations are determined based on the hydraulic pump risk index. Based on the benefit value B(θ) of virtual commissioning, the maintenance strategy with the greatest benefit is selected. At the same time, the hydraulic pump health index HI, hydraulic pump risk index RI, and remaining useful life RUL are displayed. Finally, the optimal maintenance recommendation is sent to the management terminal for human-computer interaction.

Images