Remaining Maintenance Time Prediction Method, Device and Electronic Equipment for Industrial Boiler System

Abstract

The present disclosure relates to the field of energy technologies. Embodiments of the present disclosure disclose a method, an apparatus, and an electronic device for predicting the remaining maintenance time of an industrial boiler system. A specific implementation of the method includes: obtaining a load prediction result, a load performance curve, parameters, historical data, and current operation data of the industrial boiler system; calculating the total operating income, the total operating cost, and the total operating achievement value of the industrial boiler system within a target time period based on the load prediction result and the load performance curve; obtaining a fitting function related to the operating achievement of the industrial boiler system based on the parameters; determining a reference value of the operating achievement of the industrial boiler system based on the historical data and the current operation data; and generating a predicted value of the remaining maintenance time of the industrial boiler system based on the fitting function related to the operating achievement, the reference value of the operating achievement, and a preset lower limit value of the operating achievement. This implementation provides maintenance personnel with an accurate predicted value of the remaining maintenance time, reduces the shutdown detection frequency, and saves labor and material resources.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of energy technologies, and particularly to a method, apparatus, and electronic device for predicting the remaining maintenance time of an industrial boiler system. Background Art

[0002] Currently, the operation and maintenance of most boilers rely on the professional capabilities of operators. During the operation of equipment, abnormal changes in parameters, equipment fault diagnosis, emergency treatment measures, etc. are generally judged by operators based on personal experience. Problem-solving is limited by personal capabilities, and equipment maintenance, defects, and fault handling are not timely. The setting of operators is generally tight, and coupled with the uneven professional levels of operators, preventive maintenance work is less. More often, when problems occur, professional manufacturers are called to rush to repair the problems. Non-preventive maintenance has a certain impact on the system operation efficiency and also shortens the service life of the equipment.

[0003] Currently, when performing predictive maintenance on an industrial boiler system, not only are there many required parameters, but on-site staff also need to constantly perform cumbersome tasks such as measuring different physical parameters, and the accuracy of the measured values is not high, resulting in poor predictive maintenance effects for the industrial boiler system. Summary of the Invention

[0004] In view of this, embodiments of the present disclosure provide a method, apparatus, and electronic device for predicting the remaining maintenance time of an industrial boiler system to solve the problem in the prior art of effectively monitoring the industrial boiler system and accurately predicting the remaining maintenance time to remind maintenance personnel to perform maintenance on the industrial boiler system.

[0005] In a first aspect of embodiments of the present disclosure, a method for predicting the remaining maintenance time of an industrial boiler system is provided, including: obtaining a load prediction result, a load performance curve, parameters, historical data, and current operation data of the industrial boiler system; calculating the total operating income, total operating cost, and total operating achievement value of the industrial boiler system within a target time period based on the load prediction result and the load performance curve; obtaining a fitting function related to the operating achievement of the industrial boiler system based on the parameters; determining a reference value of the operating achievement of the industrial boiler system based on the historical data and the current operation data; generating a predicted value of the remaining maintenance time of the industrial boiler system based on the fitting function related to the operating achievement, the reference value of the operating achievement, and a preset lower limit value of the operating achievement.

[0006] In the second aspect of the embodiments of the present disclosure, a device for predicting the remaining maintenance time of an industrial boiler system is provided. The device includes: an acquisition unit configured to acquire the load prediction result, load performance curve, parameters, historical data, and current operation data of the industrial boiler system; a calculation unit configured to calculate the total operation income, total operation cost, and total operation achievement value of the industrial boiler system within a target time period based on the load prediction result and the load performance curve; an operation achievement-related fitting function acquisition unit configured to acquire the operation achievement-related fitting function of the industrial boiler system based on the parameters; a determination unit configured to determine the operation achievement reference value of the industrial boiler system based on the historical data and the current operation data; and a generation unit configured to generate the predicted value of the remaining maintenance time of the industrial boiler system based on the operation achievement-related fitting function, the operation achievement reference value, and a preset lower limit value of the operation achievement.

[0007] In the third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0008] In the fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] One of the embodiments of the above various embodiments of the present disclosure has the following beneficial effects: First, acquire the load prediction result, load performance curve, parameters, historical data, and current operation data of the industrial boiler system; then, calculate the total operation income, total operation cost, and total operation achievement value within the target time period based on the load prediction result and the load performance curve; then, acquire the operation achievement-related fitting function based on the parameters; after that, determine the operation achievement reference value based on the historical data and the current operation data; then, generate the predicted value of the remaining maintenance time of the industrial boiler system based on the operation achievement-related fitting function, the operation achievement reference value, and a preset lower limit value of the achievement; finally, transmit the predicted value of the remaining maintenance time to a target device with access permission, and control the target device to display the predicted value of the remaining maintenance time. The method provided by the present disclosure provides an accurate predicted value of the remaining maintenance time for maintenance personnel, which helps maintenance personnel make a plan in advance for the maintenance work of the industrial boiler system, avoiding equipment damage caused by untimely maintenance or the phenomenon of increased costs caused by excessive maintenance. Furthermore, the influence of the operation efficiency on the industrial boiler system is greatly reduced, and the normal operation achievement value of the industrial boiler system is maintained. By monitoring the change of the total operation achievement of the industrial boiler system in a fast and efficient manner, the shutdown detection frequency is reduced, and labor and material resources are saved. Description of the Drawings

[0010] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the accompanying drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0011] Figure 1 is a schematic diagram of an application scenario of a method for predicting the remaining maintenance time of an industrial boiler system according to some embodiments of the present disclosure;

[0012] Figure 2 is a schematic flowchart of some embodiments of a method for predicting the remaining maintenance time of an industrial boiler system according to the present disclosure;

[0013] Figure 3 is a schematic structural diagram of some embodiments of a device for predicting the remaining maintenance time of an industrial boiler system according to the present disclosure;

[0014] Figure 4 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Description of the Embodiments

[0015] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art should understand that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary details.

[0016] The following will describe in detail a method, a device, and an electronic device for predicting the remaining maintenance time of an industrial boiler system according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0017] Figure 1 is a schematic diagram of an application scenario of a method for predicting the remaining maintenance time of an industrial boiler system according to some embodiments of the present disclosure.

[0018] In Figure 1In the application scenario, first, the computing device 101 can obtain the load prediction result 102, the load performance curve 103, the parameters 104, the historical data 105, and the current operation data 106 of the industrial boiler system. Then, based on the above load prediction result 102 and the above load performance curve 103, the computing device 101 can calculate the total operating income 107, the total operating cost 108, and the total operating achievement value 109 (e.g., the total net profit of the operation) of the industrial boiler system within the target time period. Then, based on the above parameters 104, the computing device 101 can obtain the fitting function 110 related to the operating achievement of the industrial boiler system (e.g., the net profit fitting function of the operation). After that, based on the above historical data 105 and the above current operation data 106, the computing device 101 can determine the reference value 111 of the operating achievement of the industrial boiler system (e.g., the reference value of the net profit of the operation). Finally, based on the above fitting function 110 related to the operating achievement, the above reference value 111 of the operating achievement, and the preset lower limit value 112 of the operating achievement, the predicted remaining maintenance time value 113 of the industrial boiler system is generated.

[0019] It should be noted that the above computing device 101 can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the above-listed hardware devices. It can be implemented as, for example, multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0020] It should be understood that Figure 1 the number of computing devices in

[0021] Figure 2 is a schematic flowchart of the method for predicting the remaining maintenance time of the industrial boiler system provided by the embodiments of the present disclosure. Figure 2 The method for predicting the remaining maintenance time of the industrial boiler system in Figure 1 can be executed by the Figure 2 computing device 101. As

[0022] shown, the method for predicting the remaining maintenance time of the industrial boiler system includes the following steps:

[0023] In some embodiments, the execution subject of the method for predicting the remaining maintenance time of the industrial boiler system (such as Figure 1The computing device 101 shown can obtain the load prediction result, load performance curve, parameters, historical data, and current operation data of the industrial boiler system through a wired connection or a wireless connection. Here, the above load prediction result can be the predicted value of the load prediction of the industrial boiler system at a certain moment. The above load performance curve at least includes a time item, a load value item, and a load demand item, and the above load performance curve is mainly used to represent the functional relationship between the above time item, the above load value item, and the above load demand item. The above parameters can be the equipment-related parameters of the industrial boiler system. The above historical data can be classified according to the time dimension, and the data generated during the historical startup operation of the industrial boiler system is the above historical data, and the data generated during the current startup operation is the above current operation data. As an example, the above historical data and the above current operation data can at least include: feed water pH value, feed water conductivity, feed water dissolved oxygen content, feed water hardness, feed water phosphate content, feed water total alkalinity, and feed water chloride content, etc.

[0024] In some optional implementation manners of some embodiments, the above load prediction result and the above load performance curve can be obtained according to the following steps: First step, the above execution subject can collect the historical operation data related to the load and load influencing factors of the industrial boiler system; Second step, the above execution subject can use the above historical operation data as a training sample set to train an initial neural network model to obtain a load prediction neural network model; Third step, the above execution subject can obtain weather forecast data, predicted date, and production plan on the energy consumption side as the input of the above load prediction neural network model to obtain the above load prediction result and the above load performance curve. Here, the above historical operation data related to the load at least includes: historical operation data of heat load, historical operation data of steam load, and historical operation data of electric load. The above historical operation data related to the load influencing factors at least includes: historical operation data of outdoor temperature, outdoor relative humidity, wind speed, wind direction, and illuminance.

[0025] In some optional implementation manners of some embodiments, to maintain the prediction accuracy of the load prediction neural network model, the training method of the load prediction neural network model is set to a rolling mode, and newly added historical data is continuously added to reflect the recent load situation of the industrial boiler system in real time. The specific steps further include: setting a prediction period, and using the rolling mode to add the real load data in the previous historical period to the historical data to update the above load prediction neural network model. Then, use the updated load prediction neural network model to predict the load of the industrial boiler system in the next period.

[0026] In some alternative implementation manners of some embodiments, the above historical data may be obtained according to the following steps: First, the above execution entity may obtain the original historical data of the above industrial boiler system within a preset historical time period through a wired connection method or a wireless connection method; then, the above execution entity may perform data cleaning and data aggregation on the above original historical data to obtain the above historical data. The selection of the above preset historical time period may be randomly selected, and may be a historical time period in hours, a historical time period in seconds, or a historical time period in minutes.

[0027] Optionally, the above data cleaning is mainly used to remove the original historical data of the above industrial boiler system when the equipment is shut down, and is not only used to remove the original historical data when the equipment is shut down. The above data aggregation is mainly used to aggregate the selected hourly original historical data and calculate the average daily operation result value of the above industrial boiler system, and can also aggregate and calculate the second-level and minute-level original historical data.

[0028] As an example, here we adopt a historical time period in hours and select the hourly original historical data. The above data cleaning is mainly used to remove the original historical data of the above industrial boiler system when the equipment is shut down. The above data aggregation is mainly used to aggregate the selected hourly original historical data and calculate the average daily operation result value of the above industrial boiler system.

[0029] It should be noted that the above wireless connection method may include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future-developed wireless connection methods.

[0030] Step S202: Calculate the total operating income, total operating cost, and total operating result value of the above industrial boiler system within the target time period based on the above load prediction result and the above load performance curve.

[0031] In some embodiments, the above execution entity may calculate the total operating income, total operating cost, and total operating result value of the above industrial boiler system within the target time period based on the above load prediction result and the above load performance curve through the following steps:

[0032] First step, the above-mentioned execution entity can obtain the value-related indicators of the above-mentioned industrial boiler system. Here, the value-related indicators at least include: heating value-related indicators, energy consumption value-related indicators, water consumption value-related indicators, electricity consumption value-related indicators, chemical drug value-related indicators, and labor value-related indicators. For example, the above-mentioned value-related indicators may include: heating price, energy consumption price, water consumption price, electricity consumption price, chemical drug price, and labor price.

[0033] Second step, the above-mentioned execution entity can build a corresponding digital mechanism model based on the physical mechanism of the above-mentioned industrial boiler system. Here, the above-mentioned digital mechanism model can be an ordinary mathematical model built according to the various parameters of the above-mentioned industrial boiler system for understanding the performance of the industrial boiler system.

[0034] Third step, the above-mentioned execution entity can use the above-mentioned digital mechanism model to simulate and calculate the performance, state parameters, and energy efficiency prediction values of the above-mentioned industrial boiler system. As an example, the above-mentioned execution entity can simulate and calculate the performance of the above-mentioned industrial boiler system and the state parameters of each connection point to obtain performance parameters. The above-mentioned execution entity can calculate the income status of the above-mentioned industrial boiler system under different working conditions based on the above-mentioned value-related indicators to obtain the energy efficiency prediction value. As an example, the above-mentioned execution entity can determine the value representing the above-mentioned income status as the above-mentioned energy efficiency prediction value.

[0035] Fourth step, the above-mentioned execution entity can determine the above-mentioned total operating income, the above-mentioned total operating cost, and the above-mentioned total operating result value based on the above-mentioned value-related indicators and the above-mentioned energy efficiency prediction value. As an example, the above-mentioned execution entity can determine the sum of the fuel cost, electricity consumption cost, water consumption cost, material cost, and labor cost as the operating cost, and determine the cumulative value of the operating cost as the total operating cost. As an example, the above-mentioned execution entity can determine the cumulative value of the product of the heating value-related indicator and the heating quantity as the total operating income. As an example, the above-mentioned execution entity can calculate the difference between the total operating income and the total operating cost to obtain the total operating result value.

[0036] Step S203, based on the above parameters, obtain the fitting function related to the operating results of the above-mentioned industrial boiler system.

[0037] In some embodiments, based on the above parameters, the above-mentioned execution entity can obtain the fitting function related to the operating results through the following steps:

[0038] In the first step, the above-mentioned execution entity can input the above-mentioned parameters into a pre-trained parameter and thermodynamic model to obtain a model related to the operation results of the above-mentioned industrial boiler system. As an example, the above-mentioned parameter and thermodynamic model can be a thermodynamic model including the principle of Maxwell relations. Here, the above-mentioned model related to the operation results mainly includes the following operation methods: subtracting the total operation cost from the total operation income to obtain the total operation result value; determining the cumulative value of the product of the heat supply value-related index and the heat supply amount as the total operation income; determining the cumulative value of the operation cost as the total operation cost; and determining the sum of the fuel cost, power consumption cost, water consumption cost, material cost, and labor cost as the operation cost.

[0039] The fuel cost described above can be obtained by multiplying the total fuel consumption value by the fuel value-related information (e.g., fuel unit price). The above-mentioned power consumption cost can be obtained by multiplying the total power consumption value by the plant power value-related information (e.g., power unit price). The above-mentioned water consumption cost can be obtained by multiplying the total water consumption by the water value-related information (e.g., water unit price). The above-mentioned material cost can be obtained by multiplying the total consumption value of environmental protection and chemical materials by the material value-related information (e.g., material unit price).

[0040] In the second step, based on the above-mentioned model related to the operation results, the above-mentioned execution entity can obtain an initial fitting function related to the operation results. Here, the Taylor formula is used in the above-mentioned initial fitting function related to the operation results.

[0041] The Taylor formula described above is a method of approximating a function f(x) that has an nth-order derivative at x = x0 using an nth-degree polynomial about (x - x0). It is applied in the fields of mathematics and physics and is a formula for describing the values of a function in the vicinity using the information of the function at a certain point. If the function is smooth enough, given the values of the derivatives of the function at a certain point, the Taylor formula can use these derivative values as coefficients to construct a polynomial to approximate the values of the function in the neighborhood of this point. The Taylor formula also gives the deviation between this polynomial and the actual function value.

[0042] The Taylor expansion formula has a wide range of applications in mathematical analysis, such as in limit calculation, estimation of the order of infinitesimals, construction of inequalities, and equation solving. Determining a set of data and seeking an approximate expression y = f(x) of a function, where the approximate expression is required to reflect the basic trend of the data without necessarily passing through all the points (xi, yi), this is the curve fitting problem. The approximate expression y = f(x) of the function is called the fitting curve.

[0043] In the third step, the above-mentioned execution entity can perform curve fitting on the above-mentioned fitting function related to the initial operation result and the above-mentioned historical data to obtain the fitting function related to the operation result. Here, the fitting function related to the operation result is mainly used to represent the functional relationship between the operation result of the above-mentioned industrial boiler system and the cumulative operation time. At the same time, the cumulative operation time and the operation result are in a direct proportional relationship. Specifically, the above-mentioned execution entity can use the least squares method (also known as the method of least squares) to perform curve fitting on the above-mentioned fitting function related to the initial operation result and the above-mentioned historical data to obtain the fitting function related to the operation result. The least squares method can find the best function match for the data by minimizing the sum of the squares of the errors. Using the least squares method, unknown data can be easily obtained, and the sum of the squares of the errors between the obtained data and the actual data is minimized. The least squares method can also be used for curve fitting. Some other optimization problems can also be expressed using the least squares method by minimizing energy or maximizing entropy.

[0044] Optionally, in addition to the least squares method, a linear regression model, a piecewise linear regression model, a polynomial regression model, a quadratic spline model, and a cubic spline model can also be used to perform curve fitting on the above-mentioned fitting function related to the initial operation result and the above-mentioned historical data.

[0045] Step S204: Determine the reference value of the operation result of the above-mentioned industrial boiler system based on the above-mentioned historical data and the above-mentioned current operation data.

[0046] In some embodiments, based on the above-mentioned historical data and the above-mentioned current operation data, the above-mentioned execution entity can determine the reference value of the operation result of the above-mentioned industrial boiler system through the following steps:

[0047] In the first step, the above-mentioned execution entity can use the autoregressive integrated moving average model to fit the above-mentioned historical data to obtain the predicted value of the operation result of the above-mentioned industrial boiler system at the target time. Here, the autoregressive integrated moving average model (ARIMA) mainly transforms a non-stationary time series into a stationary time series, and then establishes a model by regressing the dependent variable only on its lag values and the present and lag values of the random error term.

[0048] Optionally, due to the large volatility of historical data, it can be considered that the current value of the operation result obtained from the current operation data is a perturbation of the total operation result value of the industrial boiler system. The operation result of the industrial boiler system can be predicted by using the time series prediction method. The time series model here is not limited to the above-mentioned autoregressive integrated moving average model, and can also be an ETS (Error Trend Seasonality) model and an STL model. The ETS model family can be a series of models based on the simple exponential smoothing method (weighted moving average method). The STL (Seasonal and Trend decomposition using Loess) method can be a time series decomposition method with robust locally weighted regression as the smoothing method, and the STL model can be a regression neural network model using the STL method.

[0049] In the second step, based on the above-mentioned current operation data, the above-mentioned execution entity can obtain the current value of the operation result of the above-mentioned industrial boiler system at the above-mentioned target time.

[0050] In the third step, the above-mentioned execution entity can perform weighted summation on the above-mentioned predicted value of the operation result and the above-mentioned current value of the operation result to obtain a value as the above-mentioned reference value of the operation result.

[0051] Optionally, the above-mentioned execution entity can calculate the average value of the above-mentioned predicted value of the operation result and the above-mentioned current value of the operation result to obtain a value as the above-mentioned reference value of the operation result.

[0052] Step S205: Generate a predicted value of the remaining maintenance time of the above-mentioned industrial boiler system based on the above-mentioned fitting function related to the operation result, the above-mentioned reference value of the operation result, and the preset lower limit value of the operation result.

[0053] In some embodiments, based on the above-mentioned fitting function related to the operation result, the above-mentioned reference value of the operation result, and the above-mentioned preset lower limit value of the operation result, the above-mentioned execution entity can generate the predicted value of the remaining maintenance time of the above-mentioned industrial boiler system through the following steps:

[0054] In the first step, based on the above-mentioned fitting function related to the operation result and the above-mentioned preset lower limit value of the operation result, the above-mentioned execution entity can determine the theoretical maintenance time of the above-mentioned industrial boiler system. As an example, the above-mentioned execution entity can construct a function curve related to the total operation result value and time based on the above-mentioned fitting function related to the operation result. The above-mentioned execution entity can determine the above-mentioned preset lower limit value of the operation result as the abscissa and the time corresponding to the corresponding ordinate as the above-mentioned theoretical maintenance time.

[0055] In the second step, based on the above-mentioned fitting function related to the operation result and the above-mentioned reference value of the operation result, the above-mentioned execution entity can determine the current cumulative operation time of the above-mentioned industrial boiler system.

[0056] In the third step, the above-mentioned execution entity can calculate the difference between the above-mentioned theoretical maintenance time and the above-mentioned current cumulative operation time to obtain the difference as the predicted value of the remaining maintenance time.

[0057] In some optional implementation manners of some embodiments, the above-mentioned execution entity can transmit the predicted value of the remaining maintenance time to a target device with access permission, and control the target device to display the predicted value of the remaining maintenance time.

[0058] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or posterior. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0059] It should be understood that the scope of application of this predictive maintenance method is relatively wide, not limited to industrial boiler systems, and can also be applied to other energy conversion equipment in poly-generation stations. There is no limitation here.

[0060] One embodiment in each of the above embodiments of the present disclosure has the following beneficial effects: First, obtain the load prediction result, load performance curve, parameters, historical data, and current operation data of the industrial boiler system; then, based on the above load prediction result and the above load performance curve, calculate the total operation income, total operation cost, and total operation achievement value within the target time period; then, based on the above parameters, obtain the fitting function related to the operation achievement; after that, based on the above historical data and the above current operation data, determine the operation achievement reference value; then, based on the above fitting function related to the operation achievement, the above operation achievement reference value, and the preset achievement lower limit value, generate the predicted value of the reputation maintenance time of the above industrial boiler system; finally, transmit the predicted value of the remaining maintenance time to a target device with access permission, and control the target device to display the predicted value of the remaining maintenance time. The method provided by the present disclosure provides an accurate predicted value of the remaining maintenance time for maintenance personnel, which helps maintenance personnel make a plan in advance for the maintenance work of the industrial boiler system, avoid equipment damage caused by untimely maintenance, or the phenomenon of increased costs caused by excessive maintenance. Furthermore, the impact of the operation efficiency on the industrial boiler system is greatly reduced, and the normal total operation achievement value of the industrial boiler system is maintained. By means of a fast and efficient way, the change of the total operation achievement of the industrial boiler system is monitored in real time, the shutdown detection frequency is reduced, and labor and materials are saved. In addition, for the optimization of the traditional physical model, the workload of measuring data is greatly reduced, and the accuracy of prediction is improved.

[0061] All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be elaborated here one by one.

[0062] The following are embodiments of the disclosed device, which can be used to implement the method embodiments of the present disclosure. For details not disclosed in the device embodiments of the present disclosure, please refer to the method embodiments of the present disclosure.

[0063] Figure 3 It is a schematic diagram of a remaining maintenance time prediction device for an industrial boiler system provided by an embodiment of the present disclosure. As Figure 3 shown, the remaining maintenance time prediction device 300 for the industrial boiler system includes:

[0064] An acquisition unit 301, configured to acquire a load prediction result, a load performance curve, parameters, historical data, and current operation data of the industrial boiler system;

[0065] A calculation unit 302, configured to calculate the total operating income, total operating cost, and total operating achievement value of the industrial boiler system within a target time period based on the above load prediction result and the above load performance curve;

[0066] An operating achievement-related fitting function acquisition unit 303, configured to acquire an operating achievement-related fitting function of the industrial boiler system based on the above parameters;

[0067] A determination unit 304, configured to determine an operating achievement reference value of the industrial boiler system based on the above historical data and the above current operation data;

[0068] A generation unit 305, configured to generate a predicted value of the remaining maintenance time of the industrial boiler system based on the above operating achievement-related fitting function, the above operating achievement reference value, and a preset lower limit value of the operating achievement.

[0069] In some optional implementation manners of some embodiments, the load prediction result and the load performance curve of the industrial boiler system are obtained according to the following steps: collecting historical operation data related to the load and load influencing factors of the industrial boiler system; using the above historical operation data as a training sample set to train an initial neural network model to obtain a load prediction neural network model; obtaining meteorological forecast data, a predicted date, and an energy consumption side production plan as inputs of the above load prediction neural network model to obtain the above load prediction result and the above load performance curve.

[0070] In some alternative implementation manners of some embodiments, the calculation unit 302 of the remaining maintenance time prediction device 300 of the industrial boiler system is further configured to: obtain the value-related indicators of the industrial boiler system; build a corresponding digital mechanism model based on the physical mechanism of the industrial boiler system; use the digital mechanism model to simulate and calculate the performance, state parameters, and energy efficiency prediction values of the industrial boiler system; and determine the total operating income, the total operating cost, and the total operating achievement value based on the value-related indicators and the energy efficiency prediction values.

[0071] In some alternative implementation manners of some embodiments, the operation achievement-related fitting function obtaining unit 303 of the remaining maintenance time prediction device 300 of the industrial boiler system is further configured to: input the parameters into a pre-trained parameter and thermodynamic model to obtain the operation achievement-related model of the industrial boiler system; obtain an initial operation achievement-related fitting function based on the operation achievement-related model; and perform curve fitting on the initial operation achievement-related fitting function and the historical data to obtain the operation achievement-related fitting function.

[0072] In some alternative implementation manners of some embodiments, the historical data is obtained according to the following steps: obtain the original historical data of the industrial boiler system within a preset historical time period; and perform data cleaning and data aggregation on the original historical data to obtain the historical data.

[0073] In some alternative implementation manners of some embodiments, the determination unit 304 of the remaining maintenance time prediction device 300 of the industrial boiler system is further configured to: use an autoregressive integrated moving average model with exogenous inputs to fit the historical data to obtain the operation achievement prediction value of the industrial boiler system at the target time; obtain the current operation achievement value of the industrial boiler system at the target time based on the current operation data; and perform weighted summation on the operation achievement prediction value and the current operation achievement value to obtain a value as the operation achievement reference value.

[0074] In some alternative implementation manners of some embodiments, the generation unit 305 of the remaining maintenance time prediction device 300 of the industrial boiler system is further configured to: determine the theoretical maintenance time of the industrial boiler system based on the operation achievement-related fitting function and the preset lower limit value of the operation achievement; determine the current cumulative operation time of the industrial boiler system based on the operation achievement-related fitting function and the operation achievement reference value; and calculate the difference between the theoretical maintenance time and the current cumulative operation time to obtain a difference as the remaining maintenance time prediction value.

[0075] In some alternative implementations of some embodiments, the remaining maintenance time prediction device 300 of the industrial boiler system is further configured to: transmit the remaining maintenance time prediction value to a target device with access rights, and control the target device to display the remaining maintenance time prediction value.

[0076] It can be understood that the various units described in the device 300 correspond to the respective steps in the method described with reference to Figure 2 Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 300 and the units included therein, and will not be repeated here.

[0077] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

[0078] Figure 4 is a schematic diagram of the computer device 4 provided by the embodiments of the present disclosure. As Figure 4 shown, the computer device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above various method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the various modules / units in the above device embodiments are implemented.

[0079] Exemplarily, the computer program 403 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 403 in the computer device 4.

[0080] The computer device 4 can be a desktop computer, a notebook, a palm computer, a cloud server, and other computer devices. The computer device 4 can include, but is not limited to, the processor 401 and the memory 402. Those skilled in the art can understand that Figure 4 merely an example of the computer device 4 does not constitute a limitation to the computer device 4, and may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the computer device may further include input / output devices, network access devices, a bus, etc.

[0081] The processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0082] The memory 402 can be an internal storage unit of the computer device 4. For example, the hard disk or memory of the computer device 4. The memory 402 can also be an external storage device of the computer device 4. For example, a plug-in hard disk equipped on the computer device 4, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 402 can also include both the internal storage unit and the external storage device of the computer device 4. The memory 402 is used to store computer programs and other programs and data required by the computer device. The memory 402 can also be used to temporarily store data that has been output or is to be output.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0084] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0085] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this disclosure.

[0086] In the embodiments provided by this disclosure, it should be understood that the disclosed device / computer equipment and method can be implemented in other ways. For example, the device / computer equipment embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0087] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, the functional units in each embodiment of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0089] When an integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods, the present disclosure may also be accomplished by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. The computer program may include computer program code, and the computer program code may be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0090] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present disclosure, and should all be included within the protection scope of the present disclosure.

Claims

1. A method for predicting the remaining maintenance time of an industrial boiler system, characterized in that, it includes: Obtain the load prediction result, load performance curve, equipment-related parameters, historical data and current operation data of the industrial boiler system; The load prediction result is the load prediction value of the industrial boiler system at a certain moment, and the load performance curve is used to represent the functional relationship between the time item, load value item and load demand item; the historical data includes the average daily operation result of the industrial boiler system; Based on the load prediction result and the load performance curve, calculate the total operating income, total operating cost and total operating result value of the industrial boiler system within the target time period; Based on the equipment-related parameters, obtain the operation result-related model of the above industrial boiler system, and based on the operation result-related model, obtain the operation result-related fitting function of the industrial boiler system; wherein, the operation result-related model includes the operation methods of the total operating income, total operating cost and total operating result value of the industrial boiler system, and the operation result-related fitting function is used to represent the functional relationship between the operation result of the industrial boiler system and the cumulative operation time; Based on the historical data and the current operation data, determine the operation result reference value of the industrial boiler system; Based on the operation result-related fitting function, the operation result reference value and the preset lower limit value of the operation result, generate the predicted value of the remaining maintenance time of the industrial boiler system, which includes: Based on the operation result-related fitting function and the preset lower limit value of the operation result, determine the theoretical maintenance time of the industrial boiler system; Based on the operation result-related fitting function and the operation result reference value, determine the current cumulative operation time of the industrial boiler system; Take the difference between the theoretical maintenance time and the current cumulative operation time to obtain the difference as the predicted value of the remaining maintenance time.

2. The method according to claim 1, characterized in that, The load prediction result and the load performance curve of the industrial boiler system are obtained according to the following steps: Collect the historical operation data related to the load and load influencing factors of the industrial boiler system; Use the historical operation data related to the load and load influencing factors as the training sample set to train the initial neural network model to obtain the load prediction neural network model; Obtain the meteorological forecast data, prediction date and production plan on the energy consumption side as the input of the load prediction neural network model to obtain the load prediction result and the load performance curve.

3. The method according to claim 1, characterized in that, The calculation of the total operating income, total operating cost and total operating result value of the industrial boiler system within the target time period based on the load prediction result and the load performance curve includes: Based on the load prediction result and the load performance curve, obtain the value-related indicators of the industrial boiler system; Based on the physical mechanism of the industrial boiler system, build a corresponding digital mechanism model; Use the digital mechanism model to simulate and calculate the performance, state parameters and energy efficiency prediction values of the industrial boiler system. Determine the total operating revenue, the total operating cost, and the total operating achievement value based on the value-related indicators and the estimated energy efficiency.

4. The method according to claim 1, wherein, the obtaining of the operation achievement related model of the industrial boiler system based on the equipment related parameters, and the obtaining of the operation achievement related fitting function of the industrial boiler system based on the operation achievement related model include: Input the equipment related parameters into a pre-trained parameter and thermodynamic model to obtain the operation achievement related model of the industrial boiler system; Based on the operation achievement related model, obtain an initial operation achievement related fitting function; Perform curve fitting on the initial operation achievement related fitting function and the historical data to obtain the operation achievement related fitting function.

5. The method according to claim 1, wherein, the historical data is obtained according to the following steps: Obtain the original historical data of the industrial boiler system within a preset historical time period; Perform data cleaning and data aggregation on the original historical data to obtain the historical data.

6. The method according to claim 1, wherein, the determining of the operation achievement reference value of the industrial boiler system based on the historical data and the current operation data includes: Use an autoregressive integrated moving average model to fit the historical data to obtain the predicted operation achievement value of the industrial boiler system at the target time; Based on the current operation data, obtain the current operation achievement value of the industrial boiler system at the target time; Perform weighted summation on the predicted operation achievement value and the current operation achievement value to obtain the value used as the operation achievement reference value.

7. The method according to claim 1, wherein, the method further includes: Transmit the predicted remaining maintenance time value to a target device with access rights, and control the target device to display the predicted remaining maintenance time value.

8. A device for predicting the remaining maintenance time of an industrial boiler system, wherein, it includes: An obtaining unit configured to obtain the load prediction result, the load performance curve, the equipment related parameters, the historical data, and the current operation data of the industrial boiler system; The load prediction result is the predicted load value of the industrial boiler system at a certain moment, and the load performance curve is used to represent the functional relationship between the time item, the load value item, and the load demand item; the historical data includes the average daily operation achievement of the industrial boiler system; A calculation unit configured to calculate the total operating revenue, the total operating cost, and the total operating achievement value of the industrial boiler system within a target time period based on the load prediction result and the load performance curve. The operation result-related fitting function acquisition unit is configured to obtain an operation result-related model of the industrial boiler system based on the device-related parameters, and obtain an operation result-related fitting function of the industrial boiler system based on the operation result-related model; wherein, the operation result-related model includes the operation methods of the total operation income, the total operation cost, and the total operation result value of the industrial boiler system, and the operation result-related fitting function is used to represent the functional relationship between the operation result of the industrial boiler system and the cumulative operation time; The determination unit is configured to determine an operation result reference value of the industrial boiler system based on the historical data and the current operation data; The generation unit is configured to generate a predicted remaining maintenance time of the industrial boiler system based on the operation result-related fitting function, the operation result reference value, and a preset lower limit value of the operation result; Specifically, the generation unit is configured to: determine the theoretical maintenance time of the industrial boiler system based on the operation result-related fitting function and the preset lower limit value of the operation result; determine the current cumulative operation time of the industrial boiler system based on the operation result-related fitting function and the operation result reference value; and calculate the difference between the theoretical maintenance time and the current cumulative operation time to obtain a difference value as the predicted remaining maintenance time.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images