System, method and device for power supply and burn prevention of rotary kiln

Abstract

The present application discloses a system, method and device for power supply and fire prevention of rotary kiln, the system comprising: a multi-dimensional sensing unit for collecting multi-source data including temperature, vibration and current using a variety of sensors; an artificial intelligence driving unit for inputting multi-source data into an integrated model to generate vibration prediction values ​​and temperature prediction values; an adaptive magnetorheological buffer unit for buffering the vibration of the rotary kiln based on magnetorheological fluid, and adaptively adjusting the magnetic field strength according to the vibration prediction value; a composite cooling unit for combining phase change materials and heat pipes to control the temperature of the first target area, and adjusting the control parameters using the temperature prediction value; a nano-coating thermal protection unit for determining the multi-layer gradient structure of nano-materials based on the temperature prediction value to optimize the thermal stress distribution of the second target area. Through the scheme of the present application, the temperature can be automatically controlled while reducing the vibration of the rotary kiln.

Description

Technical Field

[0001] The present application relates to the field of control and regulation, and in particular to a system, method and equipment for power supply and burn prevention of a rotary kiln. Background Art

[0002] The rotary kiln is an important equipment widely used in the production of activated coke or the reactivation of activated coke. Its continuous and stable operation is crucial to production efficiency and product quality. When the rotary kiln is powered, a power supply slip ring device is usually used to power the rotary kiln body. The steam pipe installed on the outer wall of the rotary kiln body is used to pass water vapor into the rotary kiln body. As the rotary kiln body rotates, the steam pipe will fall off. The falling off of the steam pipe will cause the material that is carbonized at high temperature inside the rotary kiln body to leak from the hole gap of the steam pipe. The high-temperature material powder will put the electric steam valve, power cord and power supply equipment connected to the steam pipe in a harsh environment. Therefore, the rotary kiln often faces the risk of overheating or even burning of the power supply system during long-term high-temperature operation. Rotary kiln power supply burn-out prevention mainly involves protecting the power supply system components such as the electric steam valve and power cord to prevent them from being damaged by overheating. Effective power supply burn-out prevention can not only extend the life of the equipment, but also avoid production interruptions caused by power supply system failures, thereby reducing maintenance costs and improving production efficiency. At present, the main technologies for preventing rotary kiln power supply from burning include temperature monitoring, cooling system and overload protection. Temperature monitoring usually uses thermocouples or infrared thermometers to monitor the temperature of various components of the power supply system in real time; the cooling system reduces the temperature of the power supply system through air cooling or water cooling; overload protection prevents the power supply system from overloading through current and voltage monitoring. The working principle of these technologies is to maintain the power supply system within a safe temperature range through real-time monitoring and control. However, there are some problems with the existing technologies, such as limited temperature monitoring points, which makes it difficult to fully reflect the temperature distribution of the power supply system; the cooling system is inefficient and difficult to cope with sudden temperature increases; the overload protection system has a slow response speed and may not be able to cut off the power supply in time, resulting in equipment damage.

[0003] To solve the above problems, some improved methods have been developed. For example, distributed temperature sensing technology is used to arrange temperature sensors at multiple key points of the power supply system to obtain more comprehensive temperature distribution information; an intelligent cooling system is introduced to automatically adjust the cooling intensity according to real-time temperature data; a fast-response overload protection system is developed, and advanced algorithms are used to predict possible overload conditions. These methods have improved the effect of rotary kiln power supply anti-burning to a certain extent, but there are still some defects compared with the ideal rotary kiln power supply anti-burning system. First, most of these methods operate independently, lack systematic integration, and are difficult to achieve collaborative optimization; second, they mainly rely on traditional threshold judgments and simple control logic, which are difficult to cope with complex and changing operating environments; finally, these methods can usually only passively respond to temperature anomalies that have already occurred, and lack predictive and active protection capabilities.

[0004] Therefore, there is an urgent need for a technical solution that can automatically control the temperature while reducing the vibration of the rotary kiln. Summary of the invention

[0005] In order to solve the deficiencies of the prior art, the embodiments of the present application provide a system, method and device for preventing burning of rotary kiln power supply. The present application solves the technical problems of rotary kiln movement and high temperature material damage to electrical equipment in the prior art.

[0006] The embodiment of the present application provides a system for power supply and burning prevention of a rotary kiln, comprising: a multidimensional sensing unit, an artificial intelligence driving unit, an adaptive magnetorheological buffer unit, a composite cooling unit and a nano-coating thermal protection unit; wherein the multidimensional sensing unit is used to collect multi-source data including temperature, vibration and current using a variety of sensors; the artificial intelligence driving unit is used to input the multi-source data into an integrated model to generate vibration prediction values ​​and temperature prediction values; the adaptive magnetorheological buffer unit is used to buffer the movement of the rotary kiln based on magnetorheological fluid, and adaptively adjust the magnetic field strength according to the vibration prediction value; the composite cooling unit is used to control the temperature of the first target area in combination with phase change materials and heat pipes, and adjust the control parameters using the temperature prediction value; the nano-coating thermal protection unit is used to determine the multi-layer gradient structure of the nano-material based on the temperature prediction value to optimize the thermal stress distribution of the second target area.

[0007] In a possible implementation, multi-source data is input into an integrated model to generate vibration prediction values ​​and temperature prediction values, including: performing multi-scale decomposition of the time series of the multi-source data based on wavelet transform, and simultaneously inputting the sequences of each scale after decomposition into multiple time series prediction models to obtain a first-level vibration prediction sequence and a first-level temperature prediction sequence; based on a fractal integration function, model fusion is performed on the outputs of the first-level vibration prediction sequence and the first-level temperature prediction sequence in different time series prediction models at the same scale to obtain a second-level vibration prediction sequence and a second-level temperature prediction sequence; cross-scale fusion is performed on the second-level vibration prediction sequence and the second-level temperature prediction sequence to obtain vibration prediction values ​​and temperature prediction values.

[0008] In a possible implementation, multi-source data is input into an integrated model to generate vibration prediction values ​​and temperature prediction values, including: performing multi-scale decomposition on the time series of the multi-source data based on wavelet transform, and inputting the sequence of each scale after decomposition into the corresponding time series prediction model; fusing the output of the time series prediction model based on the fractal characteristics of each scale sequence to obtain the vibration prediction value and the temperature prediction value; including:

[0009] in, represents the fusion prediction result, including vibration prediction value or temperature prediction value, g represents the nonlinear combination function, w i represents the time-varying weight function of the i-th scale, f i () represents the prediction model corresponding to the i-th scale, X i represents the input sequence of the i-th scale, D i represents the current fractal dimension of the i-th scale, D i，avg represents the average fractal dimension of the i-th scale, α j represents the weight of the j-th ensemble model, represents the prediction result of the jth integrated model, n represents the number of layers of wavelet decomposition, and M represents the number of time series prediction models in the integrated model.

[0010] In a possible implementation, based on the fractal integration function, the outputs of the same scale in different time series prediction models in the first-level vibration prediction sequence and the first-level temperature prediction sequence are respectively fused to obtain the second-level vibration prediction sequence and the second-level temperature prediction sequence, including:

[0011] Among them, F j represents the integration result of the jth scale, y nj It represents the vibration prediction value or temperature prediction value of the nth model at the jth scale, D j represents the fractal dimension of the jth scale, H jRepresents the Hurst exponent of the jth scale, (R / S) j represents the rescaled range of the jth scale, (T) j represents the time span of the jth scale, α ij represents the weight of the i-th model at the j-th scale, β ij represents the optimization coefficient that can be learned by the i-th model at the j-th scale.

[0012] In a possible implementation, cross-scale fusion is performed on the secondary vibration prediction sequence and the secondary temperature prediction sequence respectively to obtain a vibration prediction value and a temperature prediction value, including: in, represents the cross-scale integrated prediction results, including vibration prediction values ​​or temperature prediction values, m represents the total number of time scales, j represents the index of the time scale, and F j represents the integration result of the jth scale, w j represents the weight of the jth time scale, μ represents the mean value of the logarithmic scale, σ represents the standard deviation of the logarithmic scale, and ρ ij Represents the absolute value of the correlation coefficient between scales i and j.

[0013] In a possible implementation, the vibration of the rotary kiln is buffered based on magnetorheological fluid, and the magnetic field strength is adaptively adjusted according to the vibration prediction value, including: installing magnetorheological buffers at one or more preset positions and establishing a magnetorheological fluid damping force model; calculating the required damping force according to the vibration prediction value to adaptively adjust the magnetic field strength.

[0014] In one possible implementation, the temperature of the first target area is controlled by combining phase change materials and heat pipes, and the control parameters are adjusted using temperature prediction values, including: setting a phase change material layer between the rotary kiln and the power transmission structure, and embedding a heat pipe network; establishing a heat conduction model and a phase change material melting / solidification process model to adjust the control parameters of the heat pipe working fluid flow rate according to the temperature prediction values.

[0015] In one possible implementation, a multilayer gradient structure of nanomaterials is determined based on a temperature prediction value to optimize the thermal stress distribution in a second target area, including: establishing a multilayer nanomaterial coating gradient structure model to calculate the thermal stress distribution; using the temperature prediction value to solve the interlayer parameters through multi-objective optimization to adjust the thickness of each layer of nanomaterials on the surface of the transmission structure.

[0016] The embodiment of the present application also provides a method for power supply and fire prevention of a rotary kiln, comprising: using a variety of sensors to collect multi-source data including temperature, vibration and current; inputting the multi-source data into an integrated model to generate vibration prediction values ​​and temperature prediction values; buffering the vibration of the rotary kiln based on magnetorheological fluid, and adaptively adjusting the magnetic field strength according to the vibration prediction value; combining phase change materials and heat pipes to control the temperature of the first target area, and adjusting the control parameters using the temperature prediction value; determining the multilayer gradient structure of the nanomaterial based on the temperature prediction value to optimize the thermal stress distribution of the second target area.

[0017] An embodiment of the present application also provides a device for power supply and burn prevention of a rotary kiln, characterized in that it includes: a processor, a memory, and a system bus; wherein the processor and the memory are connected via the system bus; the memory is used to store one or more programs, and the one or more programs include instructions, and when the instructions are executed by the processor, the processor executes the method described in the above embodiment.

[0018] In the system, method and equipment for rotary kiln power supply and burn prevention provided above, the embodiment of the present application establishes a digital twin model of the rotary kiln power supply system through artificial intelligence and big data technology, which can realize comprehensive perception and accurate prediction of the operating status of the power supply system, and automatically control the temperature while reducing the vibration of the rotary kiln. Secondly, by introducing predictive maintenance and active protection capabilities, the equipment failure rate can be reduced by more than 50%, extending the equipment life and reducing maintenance costs. Thirdly, the improvement of intelligence and automation will significantly reduce manual intervention, reduce operational risks, and improve production safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A schematic block diagram of a rotary kiln power supply and burn prevention system provided in an embodiment of the present application;

[0021] Figure 2 A flowchart of an artificial intelligence driven method provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of another artificial intelligence driven method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0024] Those skilled in the art will appreciate that the terms "first", "second" and the like in the embodiments of the present application are only used to distinguish different steps, devices or modules, etc., and do not represent any specific technical meaning, nor do they represent the necessary logical order between them. It should also be understood that in the embodiments of the present application, "multiple" may refer to two or more, and "at least one" may refer to one, two or more. It should also be understood that for any component, data or structure mentioned in the embodiments of the present application, in the absence of explicit limitation or contrary revelation given in the context, it can generally be understood as one or more. In addition, the term "and / or" in the present application is only a kind of association relationship describing the associated objects, indicating that there can be three kinds of relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present application generally indicates that the associated objects before and after are an "or" relationship. It should also be understood that the description of each embodiment in the present application emphasizes the differences between the embodiments, and the same or similar parts can refer to each other. For the sake of brevity, they will not be repeated one by one.

[0025] At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use. The techniques, methods and devices known to ordinary technicians in the relevant fields may not be discussed in detail, but where appropriate, the techniques, methods and devices should be considered as part of the specification. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] Figure 1A schematic block diagram of a rotary kiln power supply and anti-burning system provided in an embodiment of the present application. It should be understood that the system shown in the figure is exemplary and not restrictive. This means that the system architecture involved is not limited to a specific form or design, but is presented as an example. In other words, the architecture shown in the figure can be regarded as a way of expression to clearly describe related concepts and relationships, and does not exclude other forms of architecture. Therefore, when interpreting the architecture in the picture, it should be understood that the model is flexible and diverse, and its purpose is to provide an exemplary description rather than a restrictive provision on a specific form.

[0028] The rotary kiln is the core equipment in the production of activated carbon. Its continuous rotation characteristics and internal high temperature environment pose a huge challenge to the safety of the power supply system. Traditional anti-burning methods are often unable to cope with the dynamic working environment of the rotary kiln, resulting in frequent overheating and burning of the power supply system. This technical solution aims to comprehensively solve the problem of rotary kiln power supply anti-burning through an innovative intelligent sensor network and an adaptive cooling system, thereby improving the safety and stability of equipment operation. The embodiment of the present application includes a multidimensional sensing unit 101, an artificial intelligence drive unit 102, an adaptive magnetorheological buffer unit 103, a composite cooling unit 104, and a nano-coating thermal protection unit 105.

[0029] The multi-dimensional sensing unit 101 is used to collect multi-source data including temperature, vibration and current using a variety of sensors. Through an intelligent network composed of a variety of sensors, all-round monitoring of key parts of the rotary kiln is achieved. The sensor layout includes but is not limited to infrared thermal imaging sensors: installed on the outside of the rotary kiln, in the area where the slip ring power supply equipment is connected to the steam pipe, used to monitor in real time the temperature distribution around the steam pipe and the power supply equipment when the steam pipe connected to the slip ring line slides during the rotation of the rotary kiln body. Thermocouple array: embedded in the inner wall of the rotary kiln to monitor internal temperature changes. Vibration sensor: installed on the rotary kiln support structure to monitor the vibration of the kiln body. Current sensor: installed in the slip ring power supply system to monitor current changes.

[0030] The artificial intelligence driving unit 102 is used to input multi-source data into the integrated model to generate vibration prediction values ​​and temperature prediction values.

[0031] In one embodiment (such as Figure 2 The specific method will be shown in Figure 2The invention further describes the method and the like, comprising: performing multi-scale decomposition of the time series of multi-source data based on wavelet transform, and simultaneously inputting the sequence of each scale after decomposition into multiple time series prediction models to obtain a first-level vibration prediction sequence and a first-level temperature prediction sequence; performing model fusion on the outputs of the first-level vibration prediction sequence and the first-level temperature prediction sequence in different time series prediction models at the same scale based on the fractal integration function to obtain a second-level vibration prediction sequence and a second-level temperature prediction sequence; performing cross-scale fusion on the second-level vibration prediction sequence and the second-level temperature prediction sequence to obtain a vibration prediction value and a temperature prediction value.

[0032] In another embodiment (such as Figure 3 The specific method will be shown in Figure 3 The method comprises: performing multi-scale decomposition of the time series of multi-source data based on wavelet transform, and inputting the sequence of each scale after decomposition into the corresponding time series prediction model; fusing the output of the time series prediction model based on the fractal characteristics of each scale sequence to obtain vibration prediction values ​​and temperature prediction values.

[0033] The adaptive magnetorheological buffer unit 103 is used to buffer the vibration of the rotary kiln based on the magnetorheological fluid, and adaptively adjust the magnetic field strength according to the vibration prediction value. This includes: installing the magnetorheological buffer at one or more preset positions and establishing a magnetorheological fluid damping force model; calculating the required damping force according to the vibration prediction value to adaptively adjust the magnetic field strength.

[0034] Specifically, a magnetorheological buffer with one end connected to the collector and the other end connected to the brush can be installed on the collector platform, which includes magnetorheological fluid, electromagnetic coil, piston rod, etc. The magnetorheological fluid-based adaptive buffer system can effectively reduce the vibration of the rotary kiln and improve the stability of the power supply system.

[0035] Magnetorheological fluid selection: A magnetorheological fluid with high magnetorheological effect can be selected. The relationship between its shear stress τ and magnetic field intensity H can be expressed as: Among them, τ y (H) is the yield stress, η is the plastic viscosity, is the shear rate.

[0036] Next, the magnetorheological fluid damping force model is established: F d =F c +C v v+F f , where F d is the total damping force, F c is the controllable yield strength, C v is the viscosity coefficient, v is the piston speed, F f is the friction force. Calculate the required damping force based on the vibration prediction value: F required =m·apredicted , where m is the mass of the rotary kiln, a predicted is the acceleration component in the vibration prediction value. Then, the magnetic field strength is adaptively adjusted: H = k·(F required -F current )+H0, where H is the adjusted magnetic field strength, k is the proportionality coefficient, F current is the current damping force, and H0 is the initial magnetic field strength.

[0037] The composite cooling unit 104 is used to control the temperature of the first target area by combining the phase change material and the heat pipe, and to adjust the control parameters using the temperature prediction value. This includes: setting a phase change material layer between the rotary kiln and the power transmission structure, and embedding the heat pipe network; establishing a heat conduction model and a phase change material melting / solidification process model to adjust the control parameters of the heat pipe working fluid flow according to the temperature prediction value.

[0038] In one embodiment, a phase change material layer can be provided on the outer wall of the rotary kiln at the area where the power supply equipment is connected to the steam pipe, and a heat pipe network can be embedded to form a composite cooling system. The composite cooling device combining phase change material (PCM) and heat pipe can achieve efficient heat dissipation and temperature control.

[0039] Phase change material selection can be selected from organic phase change materials with moderate melting point and large latent heat, such as octadecane. Its heat absorption process can be expressed as: Q = m[c s (T m -T i )+L+c l (T f -T m )], where m is the PCM quality, c s and c l are the solid and liquid specific heat capacities, T m is the melting point, T i and T f are the initial and final temperatures respectively, and L is the latent heat of phase change. The heat pipe can be a high thermal conductivity copper-water heat pipe, and its effective thermal conductivity can be expressed as: Among them, Q max is the maximum heat transfer, L is the length of the heat pipe, A is the cross-sectional area, and ΔT is the temperature difference.

[0040] Then, establish the heat conduction model: Where T is temperature, t is time, α is thermal diffusion coefficient, q v is the volume heat source, ρ is the density, c p is the specific heat capacity. Modeling of the melting / solidification process of phase change materials: Among them, L is the latent heat of phase change, f is the liquid phase fraction, and k is the thermal conductivity.

[0041] Next, adjust the control parameters based on the temperature prediction value: T set =T base +ΔT predicted , where T set is the set temperature, T base is the reference temperature, ΔT predicted is the temperature change component in the temperature prediction value. Heat pipe working fluid flow regulation: in, is the mass flow rate of the working fluid, Q predicted is the heat load in the temperature prediction value, and ΔT is the temperature difference between the two ends of the heat pipe.

[0042] The nano coating thermal protection unit 105 is used to determine the multi-layer gradient structure of the nano material based on the temperature prediction value to optimize the thermal stress distribution of the second target area. This includes: establishing a multi-layer nano material coating gradient structure model to calculate the thermal stress distribution; using the temperature prediction value to solve the interlayer parameters through multi-objective optimization to adjust the thickness of each layer of nano material on the surface of the power transmission structure.

[0043] First, a multi-layer gradient structure model is established: suppose n layers of nanomaterial coating, each layer has a thickness of d i , the thermal conductivity is k i . Furthermore, the application of micro-nano coatings on the surfaces of key components of the power supply system can improve their high temperature resistance and heat dissipation efficiency. The coating material design can use alumina and zirconia composite nanomaterials, and its thermal conductivity k can be expressed as: 1 / k = f1 / k1 + f2 / k2, where f1 and f2 are the volume fractions of the two materials, and k1 and k2 are the thermal conductivities of the two materials.

[0044] For multilayer gradient structures, the thermal stress distribution is optimized and the interlayer stress σ can be expressed as: Where E is the elastic modulus, α1 and α2 are the thermal expansion coefficients of adjacent layers, ΔT is the temperature difference, and ν is the Poisson's ratio. Subsequently, the interlayer parameters are optimized based on the temperature prediction value: i =k0exp(-β i x i ), where k0 is the thermal conductivity of the substrate, β i is the optimization coefficient, x i is the distance from the base, β i =f(T predicted ,σ predicted ), where T predicted and σ predicted are the temperature and stress components in the temperature prediction value, respectively.

[0045] Next, multi-objective optimization is performed:

[0046] minF(x)=[f1(x),f2(x),…,f m (x)];

[0047]

[0048] Among them, F(x) is the objective function vector, including minimizing thermal stress, maximizing thermal insulation performance, etc., g j (x) and h k (x) is the constraint condition. Finally, the coating structure is adaptively adjusted, and the thickness of each layer of nanomaterial is determined according to the optimization results to achieve the optimization of thermal stress distribution.

[0049] Figure 2 A flowchart of an artificial intelligence driven method provided in an embodiment of the present application. In step S201, the time series of multi-source data is decomposed into multiple scales based on wavelet transform, and the sequence of each scale after decomposition is simultaneously input into multiple time series prediction models to obtain a first-level vibration prediction sequence and a first-level temperature prediction sequence.

[0050] Multi-scale decomposition can use wavelet transform to decompose the original time series into three scales. For example, Daubechies wavelet is used to decompose the original time series into three scales. Suppose the original time series is X(t), t=1,2,…,N, and after wavelet decomposition, we get: X(t)=A3(t)+D3(t)+D2(t)+D1(t), where A3(t) is the third-level approximation, and D3(t), D2(t), and D1(t) are the third-, second-, and first-level details, respectively.

[0051] Let f ARIMA ,f LSTM ,f Prophet Represent the prediction functions of the three models respectively. For each decomposed scale sequence i (i = 1, 2, 3, 4, where 4 represents A3), apply all prediction models (such as ARIMA, LSTM and Prophet): y ARIMA,i (t) = f ARIMA (X i (t)),y LSTM,i (t) = f LSTM (X i (t)),y Prophet,i (t) = f Prophet (X i (t)).

[0052] Then, at each scale, the prediction results of these models are combined using a fractal integration function. The core idea of ​​fractal integration is to nonlinearly combine the prediction results of each model according to the fractal characteristics of each scale. At step S202, based on the fractal integration function, the outputs of different time series prediction models at the same scale in the first-level vibration prediction sequence and the first-level temperature prediction sequence are respectively fused to obtain a second-level vibration prediction sequence and a second-level temperature prediction sequence, including:

[0053]

[0054] Among them, F j represents the integration result of the jth scale, y nj It represents the vibration prediction value or temperature prediction value of the nth model at the jth scale, D j represents the fractal dimension of the jth scale, H j represents the Hurst index of the jth scale, 0 <H<1,(R / s) j represents the rescaled range of the jth scale, (T) j represents the time span of the jth scale, α ij represents the weight of the i-th model at the j-th scale, β ij represents the optimization coefficient that can be learned by the i-th model at the j-th scale, β kj represents the optimization coefficient that can be learned by the k-th model at the j-th scale.

[0055] At step S203, the integrated results of different scales are combined again. The secondary vibration prediction sequence and the secondary temperature prediction sequence are cross-scale fused to obtain vibration prediction values ​​and temperature prediction values, including:

[0056]

[0057] in, represents the cross-scale integrated prediction results, including vibration prediction values ​​or temperature prediction values, m represents the total number of time scales, j represents the index of the time scale, and F j represents the integration result of the jth scale, w j represents the weight of the jth time scale, defined as μ represents the mean on a logarithmic scale, σ represents the standard deviation on a logarithmic scale, ρ ij represents the absolute value of the correlation coefficient between scales i and j, cov(F i , F j ) represents the covariance between the prediction results of scales i and j, Represents the standard deviation of the prediction results at scales i and j.

[0058] The cross-scale integration of the embodiment of the present application comprehensively considers scale weights, scale distribution, inter-scale correlations and nonlinear relationships, and provides a comprehensive framework to integrate prediction results at different time scales.

[0059] Figure 3 A flow chart of another artificial intelligence driven method provided for an embodiment of the present application. The advantage of the method described in the above embodiment is that it fully utilizes the prediction ability of each model at each scale, but the computational complexity is high. In order to make the computation more efficient and each model can focus on a specific frequency range, the following method can be used.

[0060] At step S301, the time series of multi-source data is decomposed at multiple scales based on wavelet transform, and the sequence of each scale after decomposition is respectively input into the corresponding time series prediction model. As described in the previous embodiment, multi-scale decomposition is also performed first. However, in this embodiment, a specific prediction model is assigned to each scale. For example: ARIMA is used to predict the lowest frequency approximate sequence, LSTM is used to predict the medium frequency detail sequence, and Prophet is used to predict the high frequency detail sequence.

[0061] Then, at step S302, the prediction results of these different scales are directly combined. The output of the time series prediction model is fused based on the fractal characteristics of each scale sequence to obtain the vibration prediction value and the temperature prediction value, including:

[0062]

[0063] in, represents the fusion prediction result, including vibration prediction value or temperature prediction value, g represents the nonlinear combination function, w i represents the time-varying weight function of the i-th scale, f i () represents the prediction model corresponding to the i-th scale, X i represents the input sequence of the i-th scale, D i represents the current fractal dimension of the i-th scale, D i，avg represents the average fractal dimension of the i-th scale, α j represents the weight of the j-th ensemble model, represents the prediction result of the jth integrated model, n represents the number of layers of wavelet decomposition, and M represents the number of time series prediction models in the integrated model.

[0064] It should be noted that when i=n+1, X n+1 (t) = A n (t) (lowest frequency approximate sequence); when 1≤i≤n, X i (t) = D i(t)(Detail sequence).

[0065] In summary, the method you choose depends on the following factors: Computing resources: If computing resources are sufficient, Figure 2 The method of the embodiment can provide more comprehensive results. Data characteristics: If the data characteristics of different scales are significantly different, Figure 3 The method of the embodiment described above is suitable for data scenarios. Model characteristics: If some models perform better at a specific scale, Figure 3 The method of the embodiment described above is more advantageous. Prediction target: The method is selected based on whether it is necessary to analyze different frequency components separately.

[0066] In practical applications, experiments are needed to determine which method is more suitable for a specific problem. You can even consider a mixture of the two methods, such as using multiple models on certain key scales and only one model on other scales.

[0067] Furthermore, an embodiment of the present application also provides a device for power supply and burn prevention of a rotary kiln, comprising: a processor, a memory, and a system bus; the processor and the memory are connected via the system bus; the memory is used to store one or more programs, and the one or more programs include instructions, which, when executed by the processor, enable the processor to execute any of the above methods.

[0068] Furthermore, an embodiment of the present application also provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any one of the above-mentioned processing methods.

[0069] It can be known from the description of the above implementation mode that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0070] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0071] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0072] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A system for power supply and burning prevention of rotary kiln, characterized in that: include: Multi-dimensional sensing unit, artificial intelligence driving unit, adaptive magnetorheological buffer unit, composite cooling unit and nano-coating thermal protection unit; among them, The multi-dimensional sensing unit is used to collect multi-source data including temperature, vibration and current using multiple sensors; The artificial intelligence driving unit is used to input multi-source data into the integrated model to generate vibration prediction values ​​and temperature prediction values; The adaptive magnetorheological buffer unit is used to buffer the vibration of the rotary kiln based on the magnetorheological fluid, and to adaptively adjust the magnetic field strength according to the vibration prediction value; The composite cooling unit is used to control the temperature of the first target area by combining the phase change material and the heat pipe, and to adjust the control parameter by using the temperature prediction value; The nano-coating thermal protection unit is used to determine the multi-layer gradient structure of the nano-material based on the temperature prediction value to optimize the thermal stress distribution of the second target area; Among them, multi-source data is input into the integrated model to generate vibration prediction values ​​and temperature prediction values, including: Based on wavelet transform, the time series of multi-source data is decomposed into multiple scales, and the sequences of each scale after decomposition are simultaneously input into multiple time series prediction models to obtain the first-level vibration prediction sequence and the first-level temperature prediction sequence; based on the fractal integration function, the outputs of the same scale in different time series prediction models in the first-level vibration prediction sequence and the first-level temperature prediction sequence are respectively fused to obtain the second-level vibration prediction sequence and the second-level temperature prediction sequence; the second-level vibration prediction sequence and the second-level temperature prediction sequence are respectively fused across scales to obtain the vibration prediction value and the temperature prediction value; or, Based on wavelet transform, the time series of multi-source data is decomposed into multiple scales, and the decomposed series of each scale is input into the corresponding time series prediction model; based on the fractal characteristics of each scale sequence, the output of the time series prediction model is fused to obtain vibration prediction values ​​and temperature prediction values; including: ,in, Indicates the fusion prediction results, including vibration prediction values ​​or temperature prediction values, represents a nonlinear combination function, Indicates The time-varying weight function of the scale, Indicates The prediction model corresponding to each scale is Indicates The input sequence of scales, Indicates The current fractal dimension of the scale, Indicates The average fractal dimension of the scales, Indicates The weight of the ensemble model, Indicates The prediction results of the integrated model are represents the number of wavelet decomposition layers, Indicates the number of time series forecasting models in the ensemble model.

2. The system according to claim 1, characterized in that in, Based on the fractal integration function, the outputs of the same scale in different time series prediction models in the first-level vibration prediction sequence and the first-level temperature prediction sequence are fused to obtain the second-level vibration prediction sequence and the second-level temperature prediction sequence, including: ， in, Indicates The integration results of the scales are Indicates that it is The model in Vibration prediction value or temperature prediction value on a scale, Indicates The fractal dimension of the scale, Indicates The Hurst index of the scale, Indicates The rescaling range of each scale is Indicates The time span of the scale, Indicates The model in The weights on the scale, Indicates The model in The optimization coefficients that can be learned at each scale.

3. The system according to claim 1, characterized in that in, The second-level vibration prediction sequence and the second-level temperature prediction sequence are cross-scale fused to obtain vibration prediction values ​​and temperature prediction values, including: ， in, represents the cross-scale integrated prediction results, including vibration prediction values ​​or temperature prediction values, represents the total number of time scales, represents the index of the time scale, Indicates The integration results of the scales are Indicates The weight of the time scale, represents the mean on a logarithmic scale, represents the standard deviation on a logarithmic scale, Representation scale and The absolute value of the correlation coefficient between them.

4. The system according to claim 1, characterized in that in, The vibration of the rotary kiln is buffered based on magnetorheological fluid, and the magnetic field strength is adaptively adjusted according to the vibration prediction value, including: installing a magnetorheological buffer at one or more preset positions and establishing a magnetorheological fluid damping force model; The required damping force is calculated according to the vibration prediction value to adaptively adjust the magnetic field strength.

5. The system according to claim 1, characterized in that in, The temperature of the first target area is controlled by combining phase change materials and heat pipes, and the control parameters are adjusted using the temperature prediction value, including: A phase change material layer is provided between the rotary kiln and the power transmission structure, and a heat pipe network is embedded; A heat conduction model and a phase change material melting / solidification process model are established to adjust the control parameters of the heat pipe working fluid flow rate according to the temperature prediction value.

6. The system according to claim 1, characterized in that in, Determining a multilayer gradient structure of the nanomaterial based on the temperature prediction value to optimize the thermal stress distribution of the second target area includes: Establish a gradient structure model of multilayer nanomaterial coating to calculate the thermal stress distribution; The temperature prediction value is used to solve the interlayer parameters through multi-objective optimization to adjust the thickness of each layer of nanomaterials on the surface of the transmission structure.

7. A method for preventing burning of rotary kiln power supply, characterized in that: include: Use multiple sensors to collect multi-source data including temperature, vibration and current; Input multi-source data into the integrated model to generate vibration predictions and temperature predictions; The vibration of the rotary kiln is buffered based on magnetorheological fluid, and the magnetic field strength is adaptively adjusted according to the vibration prediction value; Combining phase change materials and heat pipes to control the temperature of the first target area, and using the temperature prediction value to adjust the control parameters; determining a multilayer gradient structure of the nanomaterial based on the temperature prediction value to optimize the thermal stress distribution in the second target area; Among them, multi-source data is input into the integrated model to generate vibration prediction values ​​and temperature prediction values, including: Based on wavelet transform, the time series of multi-source data is decomposed into multiple scales, and the sequences of each scale after decomposition are simultaneously input into multiple time series prediction models to obtain the first-level vibration prediction sequence and the first-level temperature prediction sequence; based on the fractal integration function, the outputs of the same scale in different time series prediction models in the first-level vibration prediction sequence and the first-level temperature prediction sequence are respectively fused to obtain the second-level vibration prediction sequence and the second-level temperature prediction sequence; the second-level vibration prediction sequence and the second-level temperature prediction sequence are respectively fused across scales to obtain the vibration prediction value and the temperature prediction value; or, Based on wavelet transform, the time series of multi-source data is decomposed into multiple scales, and the decomposed series of each scale is input into the corresponding time series prediction model; based on the fractal characteristics of each scale sequence, the output of the time series prediction model is fused to obtain vibration prediction values ​​and temperature prediction values; including: ,in, Indicates the fusion prediction results, including vibration prediction values ​​or temperature prediction values, represents a nonlinear combination function, Indicates The time-varying weight function of the scale, Indicates The prediction model corresponding to each scale is Indicates The input sequence of scales, Indicates The current fractal dimension of the scale, Indicates The average fractal dimension of the scales, Indicates The weight of the ensemble model, Indicates The prediction results of the integrated model are represents the number of wavelet decomposition layers, Indicates the number of time series forecasting models in the ensemble model.

8. A device for power supply and burning prevention of rotary kiln, characterized in that: include: A processor, a memory, and a system bus; wherein the processor and the memory are connected via the system bus; The memory is used to store one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by the processor, the processor is caused to perform the method of claim 7.

Images