Fluidized bed equipment group operation and maintenance method and system for producing silicon-carbon negative electrode material

Abstract

The application provides a fluidized bed equipment group operation and maintenance method and system for production of silicon-carbon negative electrode materials, and relates to the field of intelligent operation and maintenance of equipment. The method comprises the following steps: fusing vibration data, temperature gradient data and internal pressure fluctuation data of the pretreated fluidized bed by a Kalman filtering algorithm and generating a state feature vector; inputting the state feature vector into a life prediction model to calculate the remaining life and maintenance degree, calculating the real-time repair rate based on a Bayesian updating algorithm, analyzing the repair rate fluctuation coefficient, and adjusting the real-time repair rate to a stable value through standardization operation when the repair rate fluctuation coefficient reaches a preset fluctuation coefficient threshold; constructing a total downtime cost function through an M / M / c queuing model, and solving the optimal number of maintenance personnel through the Lagrange multiplier method. The application can realize fine operation and maintenance and dynamic scheduling of the fluidized bed equipment group for production of silicon-carbon negative electrode materials, effectively improve the equipment group operation and maintenance efficiency, reduce downtime cost, and ensure the stability and reliability of the production process.

Description

Technical Field

[0001] This application relates to the field of intelligent operation and maintenance technology for equipment, specifically to a method and system for the operation and maintenance of fluidized bed equipment groups used in the production of silicon-carbon anode materials. Background Technology

[0002] Silicon-carbon anode materials, with their high specific capacity of 1500-2000 mAh / g, provide crucial support for improving the energy density of power batteries for new energy vehicles, and have become an essential material for upgrading the energy density of power batteries. With the global penetration rate of new energy vehicles exceeding 30%, the annual demand for silicon-carbon anode materials has climbed to 500,000 tons. Currently, the industry generally adopts 500 kg-class single-unit fluidized bed reactors and clustered layouts of hundreds of units to complete core processes such as high-temperature carbonization and graphite coating of silicon-carbon anodes. However, these reactors operate under extreme conditions of high-speed impact from silicon powder and silane decomposition corrosion, resulting in severe equipment wear and high maintenance pressure. The structural contradiction between maintenance technology and capacity expansion has become a key bottleneck restricting the large-scale development of the silicon-carbon anode industry.

[0003] Current fluidized bed equipment operation and maintenance largely rely on manual experience and fixed-cycle patterns. In terms of fault diagnosis, it primarily depends on maintenance personnel making judgments based on superficial indicators such as equipment operation sounds and temperatures, without establishing a dynamic correlation model between maintainability and repair rate. Regarding maintenance strategies, fixed-cycle maintenance or reactive maintenance methods are commonly used. While some patented technologies propose threshold alarms for parameters such as vibration and temperature, or timed shutdown maintenance schemes, they still rely on uniform thresholds and fixed cycles as the core execution logic. In terms of equipment group management, it mostly employs centralized maintenance at the end of the month and temporary scheduling after a fault, failing to achieve collaborative and optimized scheduling of multiple devices.

[0004] The existing operation and maintenance methods and related patented technologies have obvious defects: On the one hand, relying on experience-based judgment can easily lead to delayed fault warnings, frequent false alarms and missed alarms, and can easily cause safety accidents such as sealing failures and silane leaks, resulting in significant economic losses and order default risks; on the other hand, the disassembly and assembly of core components is complex, manual maintenance is inefficient, and the average repair time remains high, which seriously restricts the release of production capacity; at the same time, fixed-cycle maintenance does not take into account the differences in individual equipment wear and tear, which can easily lead to over-maintenance of healthy equipment and operation of faulty equipment with defects. Centralized maintenance of hundreds of equipment clusters can easily lead to resource conflicts, low system availability, long unplanned downtime, and overall adaptability that is difficult to meet the needs of large-scale, continuous, and high-reliability production of silicon-carbon anode materials. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this application provides a method and system for the operation and maintenance of fluidized bed equipment groups used in the production of silicon-carbon anode materials. This solves the problem that existing fluidized bed operation and maintenance relies on experience and fixed cycles, lacks adaptability, and cannot meet the needs of large-scale production of silicon-carbon anodes.

[0006] To achieve the above objectives, this application provides the following technical solution: In a first aspect, embodiments of this application provide a method for the operation and maintenance of a fluidized bed equipment group for the production of silicon-carbon anode materials. This method includes: Vibration data, temperature gradient data, and internal pressure fluctuation data of the fluidized bed are collected. After transmission via industrial Ethernet and low-pass filtering preprocessing, the preprocessed data are fused using a Kalman filter algorithm to generate a state feature vector. A life prediction model is constructed based on the Weibull distribution. The state feature vector is input into the life prediction model, and the shape and scale parameters of the model are corrected in real time. The remaining life and maintainability M(t) of the equipment are calculated. Based on the preset maintainability threshold, the corresponding level of early warning is triggered, and an early warning work order is generated. The real-time repair rate is calculated based on the Bayesian update algorithm. (t), analyze the repair rate fluctuation coefficient δ. When the repair rate fluctuation coefficient δ reaches the preset fluctuation coefficient threshold, the six-degree-of-freedom maintenance robot is dispatched to intervene and adjust the real-time repair rate to a stable value μ through preset standardized operations. const Based on the equipment group scheduling engine, the total downtime cost function is constructed by acquiring the M / M / c queuing model. The optimal number of maintenance personnel c* is solved by the Lagrange multiplier method. The maintenance resource allocation is optimized by prioritizing the maintenance degree M(t) of each fluidized bed equipment, and a dynamic scheduling scheme is output.

[0007] According to a first aspect of the embodiments of this application, the aforementioned calculation of the real-time repair rate based on the Bayesian update algorithm... (t), including: using the gamma distribution Γ(α0, β0) as the prior distribution of the repair rate μ(t); where α0 and β0 are initial parameters and are calibrated based on high-temperature operating condition maintenance data of the same model of equipment; Call the historical maintenance dataset D={t1,t2,…,t n The posterior parameters are calculated using the Bayesian update formula. , ;in, For the time required for a single repair, 1 ≤ i ≤ n; determine the posterior expectation. This represents the real-time repair rate.

[0008] According to a first aspect of the embodiments of this application, the aforementioned repair rate fluctuation coefficient δ satisfies the expression: , The standard deviation of the repair rate. The average repair rate; the M / M / c queuing model is a queuing model abstracted from the operating characteristics of multiple fluidized bed devices; the total downtime cost function satisfies the expression: C total =c·C labour + λ·W q ·Cdowntime In the formula, c represents the number of maintenance personnel, λ represents the fault arrival rate, and W... q C represents the average waiting time for faulty equipment. total For the total downtime cost, C labour For the labor cost per unit, C downtime Downtime losses per unit.

[0009] According to the first aspect of the embodiments of this application, the aforementioned operation and maintenance method for fluidized bed equipment group used in the production of silicon-carbon anode materials further includes: adopting a composite structure of neodymium iron boron permanent magnets and fluororubber sealing rings, and cooperating with a six-degree-of-freedom maintenance robot to complete the rapid disassembly and calibration of the target components of the fluidized bed, so as to ensure maintenance accuracy and efficiency; the neodymium iron boron permanent magnets are a ring array with a magnetic energy product greater than or equal to 50 MGOe, and the fluororubber sealing rings are lip-shaped structures with a temperature resistance range of -20℃ to 300℃.

[0010] According to a first aspect of the embodiments of this application, the aforementioned maintenance degree M(t) satisfies the expression: In the formula, t represents time, β is the shape parameter, and η is the scale parameter. The aforementioned remaining lifetime satisfies the expression: In the formula, T remain The remaining lifespan.

[0011] According to a first aspect of the embodiments of this application, vibration data is determined by a piezoelectric vibration sensor, which is installed on the gas distribution plate support and has a sampling frequency of 10kHz; temperature gradient data is determined by an infrared thermal imager, which is aligned with the heating unit and has a temperature accuracy of ±1℃; and internal pressure fluctuation data is determined by a differential pressure transmitter, which is installed on the inlet and outlet pipes of the reaction chamber and has a range of 0-2MPa.

[0012] According to a first aspect of the embodiments of this application, the early warning work order includes: fault location, estimated fault time and required spare parts model; a piezoelectric vibration sensor, an infrared thermal imager and a differential pressure transmitter constitute a multi-source sensing component; shape parameters and scale parameters are updated in real time through the maximum likelihood estimation method, and the update cycle is synchronized with the data acquisition cycle of the multi-source sensing component.

[0013] Secondly, this application provides an operation and maintenance system for a fluidized bed equipment group used in the production of silicon-carbon anode materials. The operation and maintenance system for the fluidized bed equipment group used in the production of silicon-carbon anode materials includes: a vector generation module, an early warning module, a scheduling and adjustment module, and a scheme output module.

[0014] Specifically, the vector generation module collects vibration data, temperature gradient data, and internal pressure fluctuation data of the fluidized bed. After industrial Ethernet transmission and low-pass filtering preprocessing, the preprocessed data is fused using the Kalman filter algorithm to generate a state feature vector. The early warning module constructs a life prediction model based on the Weibull distribution, inputs the state feature vector into the life prediction model, and corrects the model's shape and scale parameters in real time. It calculates the remaining life and maintainability M(t) of the equipment, triggers corresponding levels of early warning based on preset maintainability thresholds, and generates early warning work orders. The scheduling and adjustment module calculates the real-time repair rate based on the Bayesian update algorithm. (t), analyze the repair rate fluctuation coefficient δ. When the repair rate fluctuation coefficient δ reaches the preset fluctuation coefficient threshold, the six-degree-of-freedom maintenance robot is dispatched to intervene and adjust the real-time repair rate to a stable value μ through preset standardized operations. const The solution output module is used to construct the total downtime cost function based on the equipment group scheduling engine and the obtained M / M / c queuing model. It then solves for the optimal number of maintenance personnel c* using the Lagrange multiplier method, optimizes the allocation of maintenance resources by prioritizing the maintenance degree M(t) of each fluidized bed equipment, and outputs a dynamic scheduling solution.

[0015] Thirdly, embodiments of this application provide an electronic device, which includes: a processor, a memory, and a program stored in the memory and executable on the processor. When the program is executed by the processor, it implements the operation and maintenance method for a fluidized bed equipment group for the production of silicon-carbon anode materials as described in the first aspect.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program or instructions, which, when executed by a processor, implement the operation and maintenance method for a fluidized bed equipment group for silicon-carbon anode material production as described in the first aspect.

[0017] This application provides a method and system for the operation and maintenance of a fluidized bed equipment group for the production of silicon-carbon anode materials. Compared with the prior art, it has the following advantages: This application collects data from various dimensions of fluidized bed equipment, including vibration, temperature, and internal pressure fluctuations, and performs filtering preprocessing followed by Kalman filtering fusion to ensure the accuracy and reliability of equipment status perception. Based on the Weibull distribution, a lifespan prediction model is constructed and its parameters are corrected in real time, enabling precise calculation of remaining lifespan and maintainability, achieving tiered early warning and generating early warning work orders. This application employs a Bayesian update algorithm to calculate the real-time repair rate and analyze the fluctuation coefficient, driving a six-degree-of-freedom maintenance robot to adjust the repair rate to a stable value, improving the stability and standardization of the maintenance process. Furthermore, this application constructs a total downtime cost function using an M / M / c queuing model, utilizes the Lagrange multiplier method to solve for the optimal number of maintenance personnel, and optimizes maintenance resource allocation according to maintainability priority. This enables refined operation and dynamic scheduling of fluidized bed equipment groups used in silicon-carbon anode material production, effectively improving equipment group operation and maintenance efficiency, reducing downtime costs, and ensuring stable and reliable production processes. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic flowchart illustrating a method for the operation and maintenance of a fluidized bed equipment group for the production of silicon-carbon anode materials, provided in an embodiment of this application. Figure 2 This is a schematic diagram of the operation and maintenance system of a fluidized bed equipment group for the production of silicon-carbon anode materials provided in this application embodiment; Figure 3 This is an exemplary architecture diagram of an operation and maintenance system for a fluidized bed equipment group used in the production of silicon-carbon anode materials, provided in an embodiment of this application. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0022] This application provides a method and system for the operation and maintenance of fluidized bed equipment groups used in the production of silicon-carbon anode materials. It solves the problems of existing fluidized bed equipment operation and maintenance relying on manual experience and fixed cycles, lacking dynamic models of maintenance degree and repair rate and differentiated scheduling strategies, resulting in problems such as delayed early warning, false alarms and missed alarms, long average repair time, disordered equipment group scheduling, low system availability, and inability to adapt to the needs of large-scale continuous production of silicon-carbon anode materials.

[0023] The technical solution in this application is to solve the above-mentioned technical problems, and the general idea is as follows: Silicon-carbon anode materials are a core support for breakthroughs in the energy density of power batteries for new energy vehicles, and their global annual demand has climbed to 500,000 tons as the penetration rate of new energy vehicles has reached 30%. The current mainstream industry practice of using 500-kilogram-class single-unit fluidized bed batteries and clusters of 100 units, while undertaking the core processes of high-temperature carbonization and graphite coating of silicon-carbon anodes, is facing a structural mismatch between operation and maintenance technology and capacity expansion.

[0024] Silicon-carbon anodes, with their high specific capacity of 1500-2000 mAh / g (4-5 times that of traditional graphite anodes), have become an essential material for upgrading the energy density of power batteries. Their industrial production places extreme demands on the continuous and stable operation of fluidized beds—a one-hour shutdown of a single 500 kg fluidized bed will directly lead to a material shortage in the subsequent graphite coating process. However, the long-term operation of such equipment under the extreme conditions of silicon-carbon anode production results in a "double loss"—mechanical abrasion caused by high-speed collisions of silicon powder and chemical corrosion from silane decomposition products. This leads to an exponential increase in the risk of equipment failure, exposing three major operational pain points that restrict the industry's development: (1) Lack of maintainability quantification: Traditional operation and maintenance relies on the experience of maintenance personnel to "identify faults by sound" and "judge risks by temperature", without establishing a dynamic correlation model between maintainability and repair rate, resulting in delayed maintenance decisions.

[0025] (2) High Mean Time To Repair (MTTR): The core components of the 500 kg fluidized bed, such as the internal gas distribution plate and high-temperature sealing components, have precise structures. Manual disassembly and assembly requires the coordinated work of three skilled technicians, and the disassembly of components alone takes 4-6 hours. With the addition of troubleshooting and spare parts matching processes, the MTTR of a single fault generally exceeds 4 hours, and the repair cycle for complex faults such as heating unit leakage can reach 12 hours, which seriously restricts the release of production capacity.

[0026] (3) Disorderly scheduling of equipment group: The failures of the 100 equipment group are randomly distributed. The traditional “monthly centralized maintenance” mode is prone to causing triple resource conflicts of personnel, tools and spare parts. The temporary scheduling response after the failure is delayed by more than 30 minutes, resulting in long-term low availability of the equipment group system and long average annual unplanned downtime.

[0027] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0028] The following section first introduces a method for the operation and maintenance of a fluidized bed equipment group for the production of silicon-carbon anode materials, as provided in the embodiments of this application.

[0029] This application provides a schematic flowchart of an operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials. Figure 1 As shown, the operation and maintenance method of the fluidized bed equipment group for silicon-carbon anode material production may include the following steps S110-S140.

[0030] S110 collects vibration data, temperature gradient data, and internal pressure fluctuation data of the fluidized bed. After transmission via industrial Ethernet and low-pass filtering preprocessing, the preprocessed data is fused using the Kalman filter algorithm to generate a state feature vector.

[0031] Understandably, this application collects multi-dimensional data such as vibration, temperature gradient, and internal pressure fluctuation of the fluidized bed, and performs industrial Ethernet transmission, low-pass filtering preprocessing, and Kalman filtering algorithm data fusion, i.e. multi-source data perception fusion. This application can eliminate interference data, ensure the accuracy and reliability of equipment status perception, and generate a status feature vector that can accurately reflect the equipment operating status, providing a reliable data foundation for subsequent equipment status analysis.

[0032] S120. Construct a life prediction model based on the Weibull distribution, input the state feature vector into the life prediction model, and correct the shape and scale parameters of the model in real time; calculate the remaining life and maintenance degree M(t) of the equipment, and trigger the corresponding level of early warning in combination with the preset maintenance degree threshold to generate an early warning work order.

[0033] Understandably, a shape parameter greater than 1 indicates that the equipment has entered the wear and tear period, and the scale parameter can reflect the characteristic lifespan. This application constructs a lifespan prediction model based on the Weibull distribution and uses state feature vectors to correct the model parameters in real time, which can improve the accuracy of lifespan prediction, accurately calculate the remaining lifespan and maintenance degree M(t) of the equipment, realize level-based early warning and generate early warning work orders, and realize early prediction and standardized handling of equipment failures.

[0034] S130. Calculate the real-time repair rate based on the Bayesian update algorithm. (t), analyze the repair rate fluctuation coefficient δ. When the repair rate fluctuation coefficient δ reaches the preset fluctuation coefficient threshold, the six-degree-of-freedom maintenance robot is dispatched to intervene and adjust the real-time repair rate to a stable value μ through preset standardized operations. const .

[0035] Understandably, this application calculates the real-time repair rate and analyzes the fluctuation coefficient through the Bayesian update algorithm, which can monitor the stability of the repair process in real time. When the conditions are met, a six-degree-of-freedom repair robot is dispatched to intervene according to standardized operations, which can adjust the real-time repair rate to a stable value and improve the standardization, automation level and repair stability of the repair process.

[0036] S140. Based on the equipment group scheduling engine, the total downtime cost function is constructed by acquiring the M / M / c queuing model. The optimal number of maintenance personnel c* is solved by the Lagrange multiplier method. The maintenance resource allocation is optimized by prioritizing the maintenance degree M(t) of each fluidized bed equipment, and a dynamic scheduling scheme is output.

[0037] Understandably, this application constructs a total downtime cost function based on the M / M / c queuing model, uses the Lagrange multiplier method to obtain the optimal number of maintenance personnel, and combines the maintenance degree M(t) to prioritize and optimize resource allocation. This enables refined operation and maintenance and dynamic scheduling of fluidized bed equipment groups used in silicon-carbon anode material production, effectively improving the operation and maintenance efficiency of the equipment group, reducing downtime costs, and ensuring stable and reliable production processes.

[0038] It should be noted that this application focuses on the industrial mass production scenario of silicon-carbon anodes for lithium-ion batteries. Addressing the operational bottlenecks of 500 kg-class fluidized beds operating at high temperatures of 500-800℃, high pressures of 0.5-1.2 MPa, and in a silane corrosive atmosphere, it constructs an operation and maintenance method for fluidized bed equipment clusters used in silicon-carbon anode material production, integrating fault prediction, repair and control, and resource scheduling. The solution provided in this application, through multi-source sensing fusion, mathematical model prediction, and intelligent algorithm optimization, overcomes industry pain points such as high equipment failure rates, disordered maintenance processes, and unbalanced resource allocation, providing equipment support for continuous silicon-carbon anode production and helping to break through the production capacity constraints of core materials for new energy batteries.

[0039] In one example, the process of optimizing the dynamic repair rate of a single device includes the following steps: 1) Data Acquisition and Preprocessing: When the 500kg fluidized bed F1 was running for 48 hours, the vibration sensor detected a 5.2% shift in the resonant frequency of the gas distribution plate (safe threshold 3%). Simultaneously, the infrared thermal imager showed a temperature gradient of 8℃ / cm in the heating unit (threshold 5℃ / cm), and the differential pressure transmitter showed an internal pressure fluctuation of 0.15MPa (threshold 0.1MPa). After the three data streams were dynamically low-pass filtered (cutoff frequency 8Hz), the state feature vector was fused through Kalman filtering: X(t)=[5.2%, 8℃ / cm, 0.15MPa], with a data transmission delay of 45ms.

[0040] 2) Life Prediction and Early Warning: Input the state feature vector X(t) into the Weibull model, and obtain the shape parameter β=2.1 and the scale parameter η=120 hours through the maximum likelihood estimation method (convergence after 10 iterations). Calculate the remaining life as 36 hours and the maintenance degree M(t) as 0.67. The system automatically generates a first-level early warning work order, which specifies the fault location, estimated time and spare parts model, and pushes it to the maintenance management system.

[0041] 3) Repair execution: The maintenance personnel dispatched a six-degree-of-freedom robot to operate in a collaborative manner. The robot used a high-temperature gripper to remove the old component (1.2 minutes), and the new component was installed by positioning with a permanent magnet (0.8 minutes). The installation pressure was calibrated to 0.5MPa according to the standard specifications (pressure calibration was completed in accordance with GB / T 30099-2021).

[0042] In another example, the process of collaborative maintenance of a group of devices includes the following steps: 1) Initial Status Assessment: In a 72-hour production batch of 100 machines, the system monitored 20 machines with M(t) ≤ 0.7 (low risk) and 80 machines with M(t) ∈ [0.7, 0.9] (including 15 machines with M(t) ≥ 0.8, high risk), with an overall failure rate λ = 0.1h. - ¹·unit; when configured with 6 maintenance personnel, the M / M / c model calculates the system utilization ρ=0.83 (high load) and the failure wait time W q =1.2 hours, there was a time when 3 high-priority devices were waiting at the same time, which caused the failure of 1 device to escalate and increased the maintenance cost by 20,000 yuan.

[0043] 2) Optimization calculation: Substitute the parameters into the cost function and solve iteratively using the Lagrange multiplier method. When c=8, ρ=0.31, W q =0.3 hours, total downtime cost C total =2400 yuan / hour, which is the lowest cost, so the optimal configuration c*=8; In some embodiments, the aforementioned calculation of the real-time repair rate based on the Bayesian update algorithm (t), which may specifically include the following steps: S210. The gamma distribution Γ(α0, β0) is used as the prior distribution of the repair rate μ(t); where α0 and β0 are initial parameters and are calibrated based on maintenance data of the same model of equipment under high temperature conditions. S220, Call the historical maintenance dataset D={t1,t2,…,t n The posterior parameters are calculated using the Bayesian update formula. , ;in, The time taken for a single repair is 1 ≤ i ≤ n; S230, Determine the posterior expectation This represents the real-time repair rate.

[0044] In the embodiments of this application, it is understood that the application uses a gamma distribution as the prior distribution of the repair rate and calibrates the initial parameters based on maintenance data of the same model of equipment under high-temperature conditions, which can provide an initial distribution basis for the repair rate that fits the actual working conditions. Then, by calling historical maintenance datasets and using the Bayesian update formula to calculate posterior parameters, the prior distribution can be dynamically updated in combination with historical data, improving the accuracy and applicability of the parameters. This application determines the posterior expectation as the real-time repair rate, which can achieve accurate and real-time estimation of the repair rate and provide reliable data support for the stable control of the subsequent maintenance process.

[0045] In some embodiments, the recovery rate fluctuation coefficient δ satisfies the expression: , The standard deviation of the repair rate. This represents the average repair rate. The M / M / c queuing model is an abstract queuing model derived from the operating characteristics of multiple fluidized bed devices; the total downtime cost function satisfies the expression: C total =c·C labour + λ·W q ·C downtime ; In the formula, c represents the number of maintenance personnel, λ represents the fault arrival rate, and W... q C represents the average waiting time for faulty equipment. total For the total downtime cost, C labour For the labor cost per unit, C downtime Downtime losses per unit.

[0046] In the embodiments of this application, it is understood that by constructing a repair rate fluctuation coefficient δ using the average repair rate and the standard deviation of the repair rate, this application can intuitively and quantitatively reflect the degree of fluctuation in the repair rate, providing an objective basis for judging the stability of the maintenance process. Based on the operational characteristics of multiple fluidized bed devices, this application abstracts an M / M / c queuing model, which can accurately match the operation and maintenance scheduling scenarios of equipment groups. By combining the number of maintenance personnel, fault arrival rate, average waiting time of faulty equipment, single-unit labor cost, and unit downtime loss to construct a total downtime cost function, this application can comprehensively quantify the overall cost of equipment group operation and maintenance, providing an evaluation basis for subsequent optimization and dynamic scheduling of maintenance resources.

[0047] In one example, the maintenance degree M(t) satisfies the expression: ; In the formula, t represents time, β is the shape parameter, and η is the scale parameter; The remaining lifetime satisfies the expression: In the formula, T remain The remaining lifespan.

[0048] Understandably, this application analyzes the maintainability based on a comprehensive consideration of time, shape parameters, and scale parameters, which can quantify the maintenance status of equipment at different times and provide a standardized and unified quantitative basis for equipment status assessment and graded early warning. By calculating the remaining lifespan, this application can determine the remaining usable time of fluidized bed equipment, providing support for judging maintenance timing and scheduling maintenance resources, and improving the accuracy of operation and maintenance decisions.

[0049] In some embodiments, the aforementioned operation and maintenance method for fluidized bed equipment clusters used in the production of silicon-carbon anode materials may further include: employing a composite structure of neodymium iron boron permanent magnets and fluororubber sealing rings, in conjunction with a six-degree-of-freedom maintenance robot, to complete the rapid disassembly, assembly, and calibration of target components in the fluidized bed, thereby ensuring maintenance accuracy and efficiency. The neodymium iron boron permanent magnets are a ring array with a magnetic energy product greater than or equal to 50 MGOe, and the fluororubber sealing rings are lip-shaped structures with a temperature resistance range of -20℃ to 300℃.

[0050] In this application embodiment, it should be noted that, addressing the inefficient disassembly and assembly of traditional sealing components, this application designs a composite structure of neodymium iron boron permanent magnets and fluororubber sealing rings. The neodymium iron boron permanent magnets employ a ring array with a magnetic energy product ≥50MGOe, enabling boltless rapid positioning of components. The fluororubber sealing ring has a lip-shaped structure, is temperature resistant from -20℃ to 300℃, and shows no corrosion failure after immersion in a 5% silane atmosphere for 720 hours. This component has a disassembly time ≤2 minutes and a repeatability accuracy error ≤0.1mm, significantly improving maintenance efficiency.

[0051] Based on this, this application adopts a composite structure of neodymium iron boron permanent magnets and fluororubber sealing rings, and uses a six-degree-of-freedom maintenance robot to achieve rapid disassembly, assembly, and calibration of target components in fluidized beds, which is beneficial to improving maintenance accuracy and efficiency. The neodymium iron boron permanent magnets are set as a ring array with a magnetic energy product of not less than 50 MGOe, which can ensure the reliability and stability of adsorption positioning. The fluororubber sealing ring adopts a lip structure and has a temperature resistance range covering -20℃ to 300℃, which can adapt to the high-temperature working environment of fluidized beds, improve the sealing effect and service life, and ensure the operational reliability of the equipment after maintenance.

[0052] In some embodiments, vibration data is determined by a piezoelectric vibration sensor, which is mounted on the gas distribution plate support and has a sampling frequency of 10kHz; temperature gradient data is determined by an infrared thermal imager, which is aligned with the heating unit and has a temperature accuracy of ±1℃; and internal pressure fluctuation data is determined by a differential pressure transmitter, which is installed on the inlet and outlet pipes of the reaction chamber and has a range of 0-2MPa.

[0053] In the embodiments of this application, it can be understood that, in view of the characteristics of the high-incidence area of ​​fluidized bed failure, this application has customized and deployed three types of sensors resistant to harsh environments: a piezoelectric vibration sensor with a sampling frequency of 10kHz (encapsulated in high-temperature ceramic, with a temperature resistance of 500-800℃) is installed on the gas distribution plate support base, and is rigidly connected to the equipment support base with ceramic insulating gaskets, with a calibration error ≤0.1Hz; an infrared thermal imager is deployed in front of the heating unit to capture abnormal temperature field gradients in real time; and differential pressure transmitters are installed on the inlet and outlet pipes of the reaction chamber to dynamically monitor pressure fluctuations in the chamber.

[0054] Based on this, this application uses a piezoelectric vibration sensor to collect vibration data, which can ensure that the collected vibration signal is accurate, stable and responds quickly; this application uses an infrared thermal imager to collect temperature gradient data, which can achieve accurate acquisition of temperature changes and improve the reliability of temperature gradient data; this application uses a differential pressure transmitter to collect internal pressure fluctuation data, which is installed in the inlet and outlet pipes of the reaction chamber with a range of 0-2MPa, which can be adapted to the working pressure range of the fluidized bed, ensuring the accuracy and applicability of internal pressure data acquisition, and providing high-precision and high-stability raw data for equipment status monitoring and subsequent data processing.

[0055] In some embodiments, the early warning work order includes: fault location, estimated fault time and required spare parts model; piezoelectric vibration sensor, infrared thermal imager and differential pressure transmitter constitute a multi-source sensing component; shape parameters and scale parameters are updated in real time through maximum likelihood estimation, and the update cycle is synchronized with the data acquisition cycle of the multi-source sensing component.

[0056] In this application embodiment, it is understood that the early warning work order includes the fault location, estimated fault time, and required spare parts model, providing clear and complete guidance information for maintenance operations and improving the pertinence and efficiency of maintenance handling. This application uses a multi-source sensing component consisting of a piezoelectric vibration sensor, an infrared thermal imager, and a differential pressure transmitter to achieve comprehensive and multi-dimensional monitoring of equipment operating status, improving the completeness of status perception. This application updates shape and scale parameters in real time using the maximum likelihood estimation method, and the update cycle is synchronized with the data acquisition cycle of the multi-source sensing component, ensuring the timeliness and consistency of model parameter updates.

[0057] In some embodiments, this application provides an operation and maintenance system 300 for a fluidized bed equipment group used in the production of silicon-carbon anode materials, such as... Figure 2 As shown, the operation and maintenance system 300 for the fluidized bed equipment group used in the production of silicon-carbon anode materials may include the following modules: The vector generation module 310 is used to collect vibration data, temperature gradient data, and internal pressure fluctuation data of the fluidized bed. After transmission via industrial Ethernet and low-pass filtering preprocessing, the preprocessed data is fused using the Kalman filtering algorithm to generate a state feature vector. The early warning module 320 is used to construct a life prediction model based on the Weibull distribution, input the state feature vector into the life prediction model, and correct the shape and scale parameters of the model in real time; calculate the remaining life and maintenance degree M(t) of the equipment, and trigger the corresponding level of early warning in combination with the preset maintenance degree threshold to generate an early warning work order; The scheduling and adjustment module 330 is used to calculate the real-time repair rate based on the Bayesian update algorithm. (t), analyze the repair rate fluctuation coefficient δ. When the repair rate fluctuation coefficient δ reaches the preset fluctuation coefficient threshold, the six-degree-of-freedom maintenance robot is dispatched to intervene and adjust the real-time repair rate to a stable value μ through preset standardized operations. const ; The solution output module 340 is used to construct the total downtime cost function based on the equipment group scheduling engine and the obtained M / M / c queuing model, solve the optimal number of maintenance personnel c* by using the Lagrange multiplier method, optimize the allocation of maintenance resources by combining the maintenance degree M(t) priority ranking of each fluidized bed equipment, and output a dynamic scheduling solution.

[0058] According to embodiments of this application, any and multiple modules among the vector generation module 310, early warning module 320, scheduling adjustment module 330, and scheme output module 340 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module.

[0059] Figure 2 Each module in the system shown has the function of implementing each step in the aforementioned operation and maintenance method of fluidized bed equipment group for silicon-carbon anode material production, and can achieve the corresponding technical effect. For the sake of brevity, it will not be elaborated here.

[0060] It should be noted that each module adopts a joint architecture of edge preprocessing and cloud deep optimization: multi-source data is filtered and denoised at the edge node (reducing transmission bandwidth by 90%), the core algorithm model is deployed in the cloud (supporting parallel computing of 100 devices), and real-time linkage is achieved through industrial Ethernet (1Gbps transmission rate) and 5G network (end-to-end latency ≤20ms).

[0061] In some embodiments, this application also provides an exemplary architecture diagram of an operation and maintenance system for a fluidized bed equipment group used in the production of silicon-carbon anode materials, such as... Figure 3 As shown, the perception layer collects raw data through three types of sensors. After being aggregated by the data acquisition unit, the data is preprocessed and uploaded by the edge gateway, realizing the data entry function. The algorithm layer integrates three core algorithms through the algorithm integration unit to analyze, optimize, and schedule the data uploaded by the perception layer. The execution layer executes specific operations by the maintenance robot in conjunction with modular components according to the instructions of the algorithm layer. The hybrid network built by industrial Ethernet and 5G provides reliable support for real-time data interaction between the layers, ensuring the efficiency and stability of the architecture.

[0062] In some embodiments, to verify the high-temperature stability, early warning accuracy, repair and optimization effect, and scheduling economy of the operation and maintenance system for fluidized bed equipment groups used in the production of silicon-carbon anode materials, and to provide data support for industrial applications, this application conducted experimental verification, the specific contents of which are as follows: (1) Experimental background The experiment followed the IEC 62506:2023 standard for quantitative accelerated testing of industrial systems (Category B). The test cycle was shortened by increasing stress conditions (temperature 750℃, pressure 0.9MPa). An acceleration factor AF of 5 was calculated using the Arrhenius model, ensuring that 2000 hours of accelerated testing is equivalent to 10,000 hours of normal operating data. Data was acquired at a frequency of 10Hz, with dual backup storage at the edge and in the cloud, and transmitted using AES-256 encryption to guarantee data integrity and security.

[0063] (2) Experimental basis and environment 2.1 Experimental Standards: IEC 62506:2023 Quantitative Accelerated Testing (Class B), GB / T 30099-2021 "Industrial Robot Maintenance Specification", GB / T 26808-2011 "General Technical Conditions for Industrial Sensors"; Acceleration factor AF=5, 2000 hours of accelerated testing is equivalent to 10000 hours of normal operating conditions; 2.2 Experimental subjects: 3 500kg fluidized beds from the same batch (model LFB-500, Changzhou Lima Drying, initial 1000 hours of operation, no major malfunctions); 100 digital twin systems of equipment (built with Unity3D 2022.1, twin accuracy ±0.1mm). 2.3 Experimental conditions: Simulating extreme production environment - reaction chamber temperature 750±5℃ (PID temperature control), pressure 0.9±0.3MPa (pressure regulating valve control), nitrogen gas containing 5% silane (purity 99.999%, flow rate 50m³ / h) is introduced, the material is a mixture of silicon powder and graphite powder (D50=5μm, mass ratio 1:4), and the loading amount is 500kg / unit; 2.4. Control group setup: Control group (traditional experience maintenance): 3 skilled technicians conduct on-site inspections every 2 hours, with 3 days of downtime maintenance at the end of the month; Experimental group (system of this invention): 3 technicians with the same skills + 2 maintenance robots; The equipment, working conditions, and tasks of the two groups are the same, and the experimental period is 2000 hours (accelerated time).

[0064] (3) Experimental modules and test indicators 3.1 Verification of Multi-Sensor Sensing Accuracy The measurement accuracy of the multi-source sensing module is the foundation for subsequent modeling and early warning, directly determining the reliability of the early warning results. This experiment uses high-precision standard instruments as a benchmark for systematic calibration: a standard vibration table (model: Brüel & Kjær 4808) with vibration accuracy of ±0.1Hz, a constant temperature chamber (model: Thermo Scientific HERAcell150i) with temperature accuracy of ±0.2℃, and a pressure calibrator (model: Fluke 729) with pressure accuracy of ±0.01MPa. Calibration is performed once daily at 8:00 AM. The specific steps are as follows: 1) Install the vibration sensor on the standard vibration table, set the vibration frequency to 50Hz, and record the measured value and the standard value; 2) Aim the infrared thermal imager at the observation window of the constant temperature chamber, set the temperature to 750℃, and record the average temperature field value and the standard value; 3) Connect the differential pressure transmitter to the pressure calibrator, set the pressure to 1.0MPa, and record the measured value and the standard value. One hundred sets of data were continuously collected under different operating conditions (covering temperatures of 500-800℃ and pressures of 0.5-1.2MPa). The absolute and relative errors between the measured values ​​and the standard values ​​were calculated to evaluate the stability of the sensor under extreme conditions. Experimental statistics regarding sensor type, average error, maximum error, and accuracy compliance rate are shown in Table 1. Table 1 Conclusion: Under the conditions of 750℃ high temperature and 5% silane corrosion, the accuracy compliance rates of the vibration sensor (±0.3Hz), infrared thermal imager (±0.5℃), and differential pressure transmitter (±0.01MPa) were all 100%. The differential pressure transmitter had the smallest error and high confidence (95% confidence interval [0.009, 0.011]). After Kalman filtering, the amplitude fluctuation of the multi-source data was reduced by more than 30%, providing a high-confidence input for accurate estimation of Weibull model parameters and fault early warning.

[0065] 3.2 Fault Early Warning Accuracy Statistics Twenty typical faults (including aging of sealing rings, blockage of gas distribution plates, etc.) were artificially implanted in the experiment. Each fault was tested five times, and the warning response time and judgment accuracy of the two groups of systems were recorded. A Level 1 warning (M(t)≥0.6) was a preventative alert, while a Level 2 warning (M(t)≥0.8) triggered mandatory maintenance. Statistical information regarding warning levels, indicators, intelligent maintenance groups, traditional maintenance groups, and improvement effects is shown in Table 2. Table 2 3.3 Repair Rate and MTTR Optimization Effect Record the number of equipment failures, single repair time, and repair rate fluctuations for both groups over 2000 hours. The experimental group utilized Bayesian optimization and modular maintenance components, with maintenance personnel operating according to standard procedures; the control group used a traditional manual method, relying on experience and paper manuals. Both groups had personnel of similar skill levels. Statistical information on each indicator, the intelligent maintenance group, the traditional maintenance group, and the optimization range is shown in Table 3. Table 3 Note: The modular components played a significant role in the experimental group. The replacement time for vulnerable parts such as sealing rings was ≤2 minutes, greatly improving maintenance efficiency and fully achieving the design specifications.

[0066] 3.4 Comparison of the benefits of equipment group scheduling Simulate the continuous operation of 100 devices in a digital twin system, setting the cost parameter as: C. labour =50 yuan / hour per person, C downtime =500 yuan / hour·unit, comparing the total downtime cost of the two systems under different maintenance personnel configurations. Statistical information regarding the number of maintenance personnel, cost of the intelligent group, cost of the traditional group, and cost-benefit comparison is shown in Table 4: Table 4 Conclusion: With an optimal configuration of 8 people, the intelligent group saves an average of 336,000 yuan per month (an optimization of 58.3%), with an annualized benefit of over 4.03 million yuan. Combined with the additional benefit of reduced failures, the total annual benefit of a group of 100 devices exceeds 8 million yuan, fully verifying the economy and optimality of the scheduling strategy.

[0067] (4) Experimental conclusions 4.1 The multi-sensor fusion module achieves the required measurement accuracy, and the data stability after Kalman filtering is excellent, providing a reliable foundation for equipment status modeling under high temperature and strong corrosion environments; 4.2 The early warning and repair rate control mechanism based on Weibull distribution and Bayesian optimization has outstanding performance, with a fault early warning accuracy of over 96.3% and a secondary early warning accuracy of 100%. At the same time, it shortens the MTTR by 50% and reduces the repair rate fluctuation coefficient from 0.68 to 0.22, achieving accurate fault prediction and efficient repair. 4.3 The modular maintenance module significantly improves efficiency, greatly enhancing maintenance operation efficiency and reducing the operation error rate from 12.3% to 0.8%. It significantly reduces the interference of human operation uncertainty on maintenance quality and efficiency, meeting the stringent requirements of industrial applications. 4.4 The queuing theory-based equipment group scheduling strategy minimizes the total downtime cost, increases the availability of a 100-equipment group system from 75% to 92%, and improves annual economic benefits by more than 8 million yuan, fully verifying the feasibility, stability and economic value of the technical solution of this invention.

[0068] In some embodiments, this application provides an electronic device, the structural schematic of which is shown below. Figure 4 As shown.

[0069] The electronic device may include a processor 410 and a memory 420 storing computer program instructions.

[0070] Specifically, the processor 410 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0071] Memory 420 may include mass storage for data or instructions. For example, and not limitingly, memory 420 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 420 may include removable or non-removable (or fixed) media. Where appropriate, memory 420 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 420 is non-volatile solid-state memory.

[0072] Memory 420 may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory 420 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the fluidized bed equipment group operation and maintenance methods for silicon-carbon anode material production in the above embodiments.

[0073] The processor 410 reads and executes computer program instructions stored in the memory 420 to implement any of the operation and maintenance methods for fluidized bed equipment groups used in the production of silicon-carbon anode materials in the above embodiments.

[0074] In one example, the electronic device may also include a communication interface 430 and a bus 400. For example, Figure 4 As shown, the processor 410, memory 420, and communication interface 430 are connected via bus 400 and communicate with each other.

[0075] The communication interface 430 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0076] Bus 400 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 400 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0077] Furthermore, in conjunction with the operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any one of the operation and maintenance methods for a fluidized bed equipment group used in the production of silicon-carbon anode materials described in the above embodiments.

[0078] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0079] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0080] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0081] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0082] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for the operation and maintenance of a fluidized bed equipment group for the production of silicon-carbon anode materials, characterized in that, include: Vibration data, temperature gradient data, and internal pressure fluctuation data of the fluidized bed are collected, transmitted via industrial Ethernet and preprocessed by low-pass filtering, and then fused using the Kalman filtering algorithm to generate a state feature vector. A lifetime prediction model is constructed based on the Weibull distribution. The state feature vector is input into the lifetime prediction model, and the shape and scale parameters of the model are corrected in real time. Calculate the remaining lifespan and maintainability M(t) of the equipment, and trigger the corresponding level of early warning based on the preset maintainability threshold, generating an early warning work order; Real-time repair rate calculated based on Bayesian update algorithm (t), analyze the repair rate fluctuation coefficient δ. When the repair rate fluctuation coefficient δ reaches the preset fluctuation coefficient threshold, the six-degree-of-freedom maintenance robot is dispatched to intervene and adjust the real-time repair rate to a stable value μ through preset standardized operations. const ; Based on the equipment group scheduling engine, the total downtime cost function is constructed by acquiring the M / M / c queuing model. The optimal number of maintenance personnel c* is solved by the Lagrange multiplier method. The maintenance resource allocation is optimized by prioritizing the maintenance degree M(t) of each fluidized bed equipment, and a dynamic scheduling scheme is output.

2. The operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials as described in claim 1, characterized in that, The real-time repair rate is calculated based on the Bayesian update algorithm. (t), including: The gamma distribution Γ(α0, β0) is used as the prior distribution of the repair rate μ(t); where α0 and β0 are initial parameters and are calibrated based on maintenance data of the same model of equipment under high temperature conditions. Call the historical maintenance dataset D={t1,t2,…,t n The posterior parameters are calculated using the Bayesian update formula. , ;in, The time taken for a single repair is 1 ≤ i ≤ n; Determine the posterior expectation This represents the real-time repair rate.

3. The operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials as described in claim 2, characterized in that, The recovery rate fluctuation coefficient δ satisfies the expression: , The standard deviation of the repair rate. This represents the average repair rate. The M / M / c queuing model is an abstraction of the operating characteristics of multiple fluidized bed devices; the total downtime cost function satisfies the expression: C total = c · C labour + λ · W q · C downtime ; In the formula, c represents the number of maintenance personnel, λ represents the fault arrival rate, and W... q C represents the average waiting time for faulty equipment. total For the total downtime cost, C labour For the labor cost per unit, C downtime Losses due to downtime.

4. The operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials as described in any one of claims 1-3, characterized in that, It also includes: using a composite structure of neodymium iron boron permanent magnets and fluororubber sealing rings, combined with a six-degree-of-freedom maintenance robot to complete the rapid disassembly, assembly and calibration of target components in fluidized beds, so as to ensure maintenance accuracy and efficiency; The neodymium iron boron permanent magnet is a ring array with a magnetic energy product greater than or equal to 50 MGOe, and the fluororubber sealing ring has a lip-shaped structure and a temperature resistance range of -20℃ to 300℃.

5. The operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials as described in any one of claims 1-3, characterized in that, The maintainability M(t) satisfies the expression: ； In the formula, t represents time, β is the shape parameter, and η is the scale parameter; The remaining lifetime satisfies the expression: In the formula, T remain The remaining lifespan.

6. The operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials as described in any one of claims 1-3, characterized in that, The vibration data is acquired and determined by a piezoelectric vibration sensor, which is installed on the gas distribution plate support and has a sampling frequency of 10kHz. The temperature gradient data is determined by an infrared thermal imager, which is aligned with the heating unit and has a temperature accuracy of ±1℃. The internal pressure fluctuation data is acquired and determined by a differential pressure transmitter, which is installed on the inlet and outlet pipelines of the reaction chamber and has a range of 0-2MPa.

7. The operation and maintenance method for a fluidized bed equipment group used in the production of silicon-carbon anode materials as described in claim 6, characterized in that, The early warning work order includes: fault location, estimated fault time and required spare parts model; the piezoelectric vibration sensor, the infrared thermal imager and the differential pressure transmitter constitute a multi-source sensing component; the shape parameters and the scale parameters are updated in real time through the maximum likelihood estimation method, and the update cycle is synchronized with the data acquisition cycle of the multi-source sensing component.

8. A fluidized bed equipment group operation and maintenance system for silicon-carbon anode material production, characterized in that, include: The vector generation module is used to collect vibration data, temperature gradient data, and internal pressure fluctuation data of the fluidized bed. After transmission via industrial Ethernet and low-pass filtering preprocessing, the preprocessed data is fused using the Kalman filter algorithm to generate state feature vectors. The early warning module is used to construct a lifetime prediction model based on the Weibull distribution, input the state feature vector into the lifetime prediction model, and correct the shape parameters and scale parameters of the model in real time. Calculate the remaining lifespan and maintainability M(t) of the equipment, and trigger the corresponding level of early warning based on the preset maintainability threshold, generating an early warning work order; The scheduling and adjustment module is used to calculate the real-time repair rate based on the Bayesian update algorithm. (t), analyze the repair rate fluctuation coefficient δ. When the repair rate fluctuation coefficient δ reaches the preset fluctuation coefficient threshold, the six-degree-of-freedom maintenance robot is dispatched to intervene and adjust the real-time repair rate to a stable value μ through preset standardized operations. const ; The solution output module is used to construct the total downtime cost function based on the equipment group scheduling engine and the obtained M / M / c queuing model, solve for the optimal number of maintenance personnel c* using the Lagrange multiplier method, optimize the allocation of maintenance resources by combining the maintenance degree M(t) priority ranking of each fluidized bed equipment, and output a dynamic scheduling solution.

9. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the operation and maintenance method for a fluidized bed equipment group for the production of silicon-carbon anode materials as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that, when executed by a processor, implement the operation and maintenance method for a fluidized bed equipment group for the production of silicon-carbon anode materials as described in any one of claims 1 to 7.

Images