A smart factory energy management system and management method

Abstract

The present invention discloses a smart factory energy management system and management method. The system comprises: a screen control center unit, a sensor monitoring unit, a real-time energy consumption alarm unit, an energy consumption management threshold unit, an equipment energy consumption statistics unit, an equipment stage energy consumption prediction unit, an energy comprehensive configuration unit, an equipment unified management unit, an energy consumption parameter control unit, an energy saving and emission reduction indication unit, an energy statistics unit, and a system control unit. The energy consumption of the equipment is collected through various intelligent sensors, and the energy consumption of the factory equipment is comprehensively calculated using a variety of algorithm models such as a double exponential empirical model, feature extraction, secondary nested judgment, an energy consumption demand prediction model, and an energy consumption management threshold. The system is combined with the system to supervise energy consumption issues. The system runs stably and has strong operability. The method is based on a certain existing theoretical foundation, is easy to understand, can help the factory to effectively manage energy consumption, has strong automation, and saves costs.

Description

Technical Field

[0001] The present invention relates to the field of energy management and algorithms, and in particular to a smart factory energy management system and management method. Background Art

[0002] In the process of factory management, many systems are involved, such as air conditioning system, cooling water system, exhaust system, power monitoring, etc. These systems consume a lot of energy and increase the operating costs of the factory, so they need to be optimized and managed to achieve the goal of reducing costs, increasing efficiency, saving energy and reducing emissions.

[0003] Publication number CN112232021A discloses an enterprise energy management data presentation system and method, including a user login module and a platform presentation interface. The platform presentation interface is entered through the user login module, and the platform presentation interface includes a menu selection column area, a data graphic information display area, and a user information area; the menu selection column area includes: a platform homepage module, a main system diagram module, an alarm analysis module, a power consumption monitoring module, a power consumption analysis module, a comprehensive energy module, a report management module, and a comprehensive report module; the data graphic information display area presents data according to the selection of the menu selection column area; the user information area includes a message alarm unit, a message announcement unit, and a user setting unit, and adopts a visual multi-screen projection method to achieve the effect of facilitating data display.

[0004] Publication number CN104956387A discloses an energy management method through energy management object modeling, which, based on the equipment included in the energy consumption facility and the process carried out through the above equipment, sets an energy cost center (ECC) for obtaining energy input to execute a specific process output product, sets an energy resource center (ERC) for bypassing and transmitting the energy supplied to the above energy consumption facility with the above set energy cost center (ECC), obtains the respective input and output values ​​measured at the input and output limits of the above set energy cost center (ECC) and the above set energy resource center (ERC), and provides the energy input and output and energy flow information of the above energy consumption facility to the user, an energy management method for a building, and an invention of a flexible energy management method for a factory.

[0005] However, the current existing methods do not establish a unified management model and method for the factory's energy-consuming equipment, which requires individual statistics and calculations for the equipment, which is time-consuming and labor-intensive, and the calculation and prediction accuracy of energy consumption is not high. Summary of the invention

[0006] In order to overcome the shortcomings and deficiencies of the prior art, the present invention provides a smart factory energy management system and management method.

[0007] The technical solution adopted by the present invention is a smart factory energy management system, which includes:

[0008] Screen control center unit, sensor monitoring unit, real-time energy consumption alarm unit, energy consumption management threshold unit, equipment energy consumption statistics unit, equipment stage energy consumption prediction unit, energy comprehensive configuration unit, equipment unified management unit, energy consumption parameter control unit, energy saving and emission reduction indication unit, energy statistics unit, system control unit;

[0009] The sensor monitoring unit, real-time energy consumption alarm unit, energy consumption management threshold unit, equipment energy consumption statistics unit, equipment stage energy consumption prediction unit, energy comprehensive configuration unit, equipment unified management unit, energy consumption parameter control unit, energy saving and emission reduction indication unit, energy statistics unit, and system control unit are connected to the screen control center unit, and the screen control center unit performs unified management of other units.

[0010] A smart factory energy management method, the steps of the method are as follows:

[0011] Step S1: collecting raw data of energy-consuming equipment through various intelligent sensors, using a double exponential empirical model to describe the energy consumption of the equipment, and establishing an iterative equation of the double exponential empirical model according to the service life of the equipment;

[0012] Step S2: extracting features from the original data, establishing energy consumption characteristics per unit time, and using the energy consumption characteristics to perform error fitting on the double exponential empirical model of the equipment;

[0013] Step S3: Perform secondary nesting judgment based on whether the energy consumption demand of the equipment has changed, and establish an energy consumption demand prediction model;

[0014] Step S4: predicting equipment output efficiency based on production scheduling, maintenance plan and production planning model;

[0015] Step S5: Optimizing the start and stop schedule of the equipment through the energy consumption cost of the equipment and the start and stop optimization scheduling function;

[0016] Step S6: Calculate the energy consumption management threshold. Once the energy consumption management threshold is exceeded, the management system page will issue an alarm and push a message to the mobile phones of the on-duty personnel and on-site personnel for immediate processing.

[0017] Furthermore, the double exponential empirical model is expressed as:

[0018] A a =b a exp(c a a)+d a exp(e aa)

[0019] Among them, A a Indicates the energy consumption of the device per unit time, a indicates the operating time of the device per unit time, and b a Indicates the energy consumption coefficient of the low power consumption of the device, c a Indicates the average energy consumption of the device in low power operation state, d a Indicates the energy consumption coefficient of the equipment at full load, e a Indicates the average energy consumption of the equipment when it is running at full load;

[0020] The iterative equation is expressed as:

[0021]

[0022] Among them, A a-1 represents the energy consumption of the equipment in the previous unit time, η represents the covariance of the wear coefficient of the equipment at different times, ω represents the age of the equipment, K represents the designed life span of the equipment, and f a Represents the coefficient matrix of all other factors affecting the energy consumption of the equipment, η a Indicates the wear coefficient of the equipment per unit time, η a-1 Indicates the wear coefficient of the equipment in the previous unit time, f η Represents all other noise factors that affect the wear coefficient of the equipment, ω a Indicates the age of the equipment per unit time, ω a-1 Indicates the age of the equipment used to the previous unit of time, f ω Represents all other older noise factors that affect the use of the equipment.

[0023] Furthermore, the energy consumption characteristics per unit time are established, and the expression is:

[0024]

[0025] Among them, h(r) represents the energy consumption characteristic quantity per unit time, r represents the number of abnormal operation of the equipment, g1 represents the voltage characteristic when the equipment is operating normally, g2 represents the characteristic coefficient of abnormal operation of the equipment, and g3 represents the current characteristic when the equipment is operating normally;

[0026] The error fitting expression is:

[0027]

[0028] Among them, Q represents the hyperparameter formed by fitting, Q 2 The closer it is to 1, the higher the accuracy of the fitting. E represents the total number of times per unit time. A aIndicates the energy consumption of the device per unit time. It represents the fitting value of the energy consumption per unit time of the equipment, h r Represents the characteristic quantity of energy consumption per unit time, It represents the mean value of energy consumption characteristic quantity per unit time.

[0029] Furthermore, the secondary nested judgment is expressed as:

[0030]

[0031] Among them, ψ r (a) indicates whether the energy demand has changed, 1 indicates that the demand has changed, 0 indicates that the demand has not changed, Δr(a) indicates the change in energy demand per unit time, and ξ indicates the threshold value of the change in energy demand per unit time;

[0032] The energy consumption demand prediction model is expressed as:

[0033]

[0034] Among them, A C+1 It represents the energy consumption requirement of the equipment at the next unit time, and λr represents the iteration parameter of the energy consumption characteristic.

[0035] Furthermore, the output efficiency of the device is expressed as:

[0036] j = ∫[n(y a |A a-1 )n(b a |A a-1 )n(v a |A a-1 )]dA a-1

[0037] Among them, j represents the equipment output efficiency, y a represents production schedule, b a Indicates the maintenance plan, v a It represents the production plan, and n represents the number of times per unit time.

[0038] Furthermore, the start-stop optimization scheduling function is expressed as:

[0039]

[0040] Among them, W Y (N1, N2) represents the equipment start and stop scheduling function, N1 represents the equipment energy consumption cost matrix under different modes, and N2 represents the past equipment start and stop optimization scheduling matrix, T represents the transpose of the matrix, and Cov represents the covariance operation.

[0041] Furthermore, the energy consumption management threshold is expressed as:

[0042]

[0043] Among them, e represents the energy consumption management threshold of the device per unit time, A a Indicates the energy consumption of the device per unit time, c min Indicates the minimum energy consumption allowed by the device per unit time, c max Indicates the maximum energy consumption allowed by the device per unit time.

[0044] Beneficial effects:

[0045] The present invention proposes a smart factory energy management system and management method, collects energy consumption of equipment through various intelligent sensors, and uses a variety of algorithm models such as double exponential empirical model, feature extraction, secondary nested judgment, energy consumption demand prediction model, energy consumption management threshold, etc. to comprehensively calculate the energy consumption of factory equipment, and combines the system to supervise energy consumption issues. The system has stable operation and strong operability. The method is based on a certain existing theoretical foundation, is easy to understand, can help factories to effectively manage energy consumption, has strong automation, and saves costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a system architecture diagram of the present invention;

[0047] Figure 2 It is a flow chart of the overall steps of the present invention. DETAILED DESCRIPTION

[0048] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other. The present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0049] like Figure 1 As shown, a smart factory energy management system includes: a screen control center unit, a sensor monitoring unit, a real-time energy consumption alarm unit, an energy consumption management threshold unit, an equipment energy consumption statistics unit, an equipment stage energy consumption prediction unit, an energy comprehensive configuration unit, an equipment unified management unit, an energy consumption parameter control unit, an energy saving and emission reduction indication unit, an energy statistics unit, and a system control unit;

[0050] The sensor monitoring unit, real-time energy consumption alarm unit, energy consumption management threshold unit, equipment energy consumption statistics unit, equipment stage energy consumption prediction unit, energy comprehensive configuration unit, equipment unified management unit, energy consumption parameter control unit, energy saving and emission reduction indication unit, energy statistics unit, and system control unit are connected to the screen control center unit, and the screen control center unit performs unified management of other units.

[0051] Screen control center unit: In the eight-grid large screen display, the energy management system UI is designed to display 4 modules: power supply, gas supply, temperature, and operation and maintenance warning. Each module presents monitoring data in the form of charts. Power supply: The hyperbola chart shows the trend of power consumption, the comparison between the real-time value and the limit value; Gas supply: The hyperbola chart shows the trend of gas consumption, the comparison between the real-time value and the limit value; Temperature: Presents the temperature trend and intuitively shows whether it exceeds the limit; Operation and maintenance warning: Presents the operating status of different modules and system abnormality information.

[0052] Sensor monitoring unit: A collection of real-time monitoring of the energy consumption of equipment through a variety of different sensors, including voltage monitoring sensors, current monitoring sensors, natural gas monitoring sensors, etc. The data of the devices actually monitored and managed are bound to facilitate the presentation of real-time data to the system and management on the large screen. If there is an alarm, it will flash in the current interface in a timely manner.

[0053] Real-time energy consumption alarm unit: statistics the alarm information of the day, one of which is the alarm part and the other part is the real-time alarm list, presenting the alarm messages that have occurred.

[0054] Energy consumption management threshold unit: When a fault occurs, the energy management platform can analyze the early warning alarm information and send the alarm information to the relevant person in charge in a timely manner via SMS, email, voice, etc.

[0055] Equipment energy consumption statistics unit: The main contents of energy consumption status analysis include: electricity consumption and gas consumption. The analysis method requires the use of multiple analysis methods to conduct a comprehensive, systematic, quantitative and qualitative analysis and research, analysis and summary of energy usage. Commonly used methods include: comparative analysis method; statistical grouping method, structural analysis method, dynamic analysis method, and factor analysis method. By using different analysis methods, we hope to find loopholes and unreasonable places in the energy use process, so as to adjust the energy allocation strategy and reduce waste in the energy use process.

[0056] Equipment stage energy consumption forecasting unit: Under current technology, electric energy cannot be stored in large quantities. The significance of energy consumption load forecasting is to maintain the supply and demand balance of the power system at peak times and provide reliable and standard electric energy to various users as economically as possible to meet their load needs. In the system, the previous energy consumption data can be analyzed in multiple dimensions to fully and deeply understand the working principle of energy consumption equipment, thereby calculating the load information of the enterprise in terms of energy consumption.

[0057] Energy comprehensive configuration unit: Use the energy management system to provide relevant information to the dispatch center, prompting the dispatch center to give correct commands in a timely manner, realize rational energy dispatch, and strengthen decentralized or centralized control of energy.

[0058] Unified equipment management unit: Enterprises need to manage their energy-consuming equipment in a unified manner, classify energy-consuming equipment, and clearly mark them. They use the marks as a link to manage energy-consuming equipment, build a framework for energy-consuming equipment management, and realize the management of records, maintenance, defects, and changes. When enterprises manage energy-consuming equipment in real time, they can understand the specific operating status and efficiency of the equipment, and promptly repair or eliminate equipment with high energy consumption or failures to avoid safety accidents caused by equipment failures.

[0059] Energy consumption parameter control unit: Analyze the company's annual and quarterly energy consumption data to understand the energy consumption of a single product, the energy consumption of the entire factory, and the energy consumption of the product production process. Analyze the company's energy consumption from multiple dimensions, understand the gap between the company itself and other companies in the same industry, optimize the company's production process, and transform and upgrade equipment.

[0060] Energy conservation and emission reduction indication unit: Strengthen the management of the company's production processes, clarify the energy indicators required for different processes, build a management system for energy indicators based on the company's own resource conditions, optimize the energy consumption status of different production processes, compare production equipment, select equipment with lower energy consumption, and effectively implement the company's energy management work.

[0061] Energy Statistics Unit: Collect enterprise energy consumption data, audit the enterprise's energy consumption, understand the enterprise's shortcomings in energy conservation, formulate enterprise energy transformation goals, and submit the target data to the audit department to ensure that the enterprise can work hard to achieve the goal of energy transformation.

[0062] System control unit: System configuration mainly includes functions such as user management, role management, authority management, alarm strategy configuration, and system parameter maintenance, which facilitates users to maintain system data, configure user permissions, alarm strategies, etc.

[0063] like Figure 2 As shown, a smart factory energy management method, the steps of the method are as follows:

[0064] Step S1: collecting raw data of energy-consuming equipment through various intelligent sensors, using a double exponential empirical model to describe the energy consumption of the equipment, and establishing an iterative equation of the double exponential empirical model according to the service life of the equipment;

[0065] The double exponential empirical model is a statistic of the energy consumption of the equipment. The double exponential empirical model can be used to effectively and accurately describe the energy consumption of the equipment. The double exponential empirical model statistics the energy consumption of the equipment per unit time. The use effect of the double exponential empirical model takes into account the aging and wear of the equipment. The energy consumption of the equipment is different in different time periods. Therefore, it is necessary to establish an iterative equation of the double exponential empirical model according to the service life of the equipment, and use the iterative equation of the double exponential empirical model to ensure the accuracy of equipment energy consumption monitoring.

[0066] Step S2: extracting features from the original data, establishing energy consumption characteristics per unit time, and using the energy consumption characteristics to perform error fitting on the double exponential empirical model of the equipment;

[0067] The energy consumption characteristics are related to the number of times the equipment operates, the current and voltage consumed by the equipment. Error fitting is a description of the error generated by the double exponential empirical model. The error fitting is related to the energy consumption characteristic quantity per unit time, which represents the mean of the energy consumption characteristic quantity per unit time. Because all models cannot describe the original data with 100% accuracy, error fitting is used to explain the error situation of the double exponential empirical model in detail.

[0068] Step S3: Perform secondary nesting judgment based on whether the energy consumption demand of the equipment has changed, and establish an energy consumption demand prediction model;

[0069] The secondary nesting judgment is a description of the change in the energy consumption of the equipment, which is related to the change in the energy consumption demand of the equipment per unit time and the threshold of the change in the energy consumption demand per unit time. The secondary nesting judgment provides a reliable basis for the establishment of the subsequent energy consumption demand prediction model. The first layer of the secondary nesting is to judge whether the energy consumption demand has changed, and the second layer of the secondary nesting is to calculate the change in the energy consumption demand per unit time. The energy consumption demand prediction model is related to the iterative parameters of the energy consumption demand and the energy consumption characteristic quantity at the next unit moment. The energy consumption demand prediction model predicts the energy consumption demand of the equipment per unit time.

[0070] Step S4: predicting equipment output efficiency based on production scheduling, maintenance plan and production planning model;

[0071] The output efficiency of equipment is closely related to production scheduling, maintenance plan and production plan. Production scheduling is determined based on the factory's order volume. The maintenance plan is related to the equipment's maintenance and overhaul arrangements. The equipment cannot be in operation all year round. When a certain production task is completed, the equipment needs to be maintained, repaired and installed. The production plan is also related to the equipment's order volume, but not all orders will be generated. When unexpected situations occur, such as a decrease in demand or funds not in place, the order volume changes and the production plan also changes accordingly.

[0072] Step S5: Optimizing the start and stop schedule of the equipment through the energy consumption cost of the equipment and the start and stop optimization scheduling function;

[0073] The start-stop optimization scheduling function is related to the equipment energy consumption cost matrix under different modes and the past equipment start-stop optimization scheduling matrix. When the equipment is operating at full load, half load, and overload, the energy consumption required is different, which constitutes a 3×3 coefficient matrix. The size of the values ​​in the matrix is ​​related to the equipment usage time and equipment model. The past equipment start-stop optimization scheduling matrix is ​​related to the operation or stop of the equipment in all past time periods.

[0074] Step S6: Calculate the energy consumption management threshold. Once the energy consumption management threshold is exceeded, the management system page will issue an alarm and push a message to the mobile phones of the on-duty personnel and on-site personnel for immediate processing.

[0075] The energy consumption management threshold is a description of the peak energy consumption of the equipment. When the management threshold is exceeded, it means that the equipment may be operating abnormally or damaged. In this case, it is extremely dangerous for the equipment to continue to operate, so an alarm needs to be issued and sent to the staff to minimize the loss. The establishment of energy consumption management thresholds is also a way to monitor the equipment, which can ensure the normal operation of the equipment from the perspective of energy consumption.

[0076] Double exponential empirical model, the expression is:

[0077] A a =b a exp(c a a)+d a exp(e a a)

[0078] Among them, A a Indicates the energy consumption of the device per unit time, a indicates the operating time of the device per unit time, and b a Indicates the energy consumption coefficient of the low power consumption of the device, c a Indicates the average energy consumption of the device in low power operation state, d a Indicates the energy consumption coefficient of the equipment at full load, e a Indicates the average energy consumption of the equipment when it is running at full load;

[0079] The iterative equation is expressed as:

[0080]

[0081] Among them, A a-1 represents the energy consumption of the equipment in the previous unit time, η represents the covariance of the wear coefficient of the equipment at different times, ω represents the age of the equipment, K represents the designed life span of the equipment, and fa Represents the coefficient matrix of all other factors affecting the energy consumption of the equipment, η a Indicates the wear coefficient of the equipment per unit time, η a-1 Indicates the wear coefficient of the equipment in the previous unit time, f η Represents all other noise factors that affect the wear coefficient of the equipment, ω a Indicates the age of the equipment per unit time, ω a-1 Indicates the age of the equipment used to the previous unit of time, f ω Represents all other older noise factors that affect the use of the equipment.

[0082] Establish the energy consumption characteristics per unit time, the expression is:

[0083]

[0084] Among them, h(r) represents the energy consumption characteristic quantity per unit time, r represents the number of abnormal operation of the equipment, g1 represents the voltage characteristic when the equipment is operating normally, g2 represents the characteristic coefficient of abnormal operation of the equipment, and g3 represents the current characteristic when the equipment is operating normally;

[0085] Error fitting, the expression is:

[0086]

[0087] Among them, Q represents the hyperparameter formed by fitting, Q 2 The closer it is to 1, the higher the accuracy of the fitting. E represents the total number of times per unit time. A a Indicates the energy consumption of the device per unit time. It represents the fitting value of the energy consumption per unit time of the equipment, h r Represents the characteristic quantity of energy consumption per unit time, It represents the mean value of energy consumption characteristic quantity per unit time.

[0088] Secondary nested judgment, the expression is:

[0089]

[0090] Among them, ψ r (a) indicates whether the energy demand has changed, 1 indicates that the demand has changed, 0 indicates that the demand has not changed, Δr(a) indicates the change in energy demand per unit time, and ξ indicates the threshold value of the change in energy demand per unit time;

[0091] Energy consumption demand prediction model, the expression is:

[0092]

[0093] Among them, A C+1 Indicates the energy consumption demand of the equipment at the next unit time, λ r Represents the iteration parameter of the energy consumption characteristic.

[0094] Equipment output efficiency, expressed as:

[0095] j = ∫[n(y a |A a-1 )n(b a |A a-1 )n(v a |A a-1 )]dA a-1

[0096] Among them, j represents the equipment output efficiency, y a represents production schedule, b a Indicates the maintenance plan, v a It represents the production plan, and n represents the number of times per unit time.

[0097] Start and stop optimization scheduling function, the expression is:

[0098]

[0099] Among them, W Y (N1, N2) represents the equipment start and stop scheduling function, N1 represents the equipment energy consumption cost matrix under different modes, and N2 represents the past equipment start and stop optimization scheduling matrix, T represents the transpose of the matrix, and Cov represents the covariance operation.

[0100] The threshold of energy consumption management is expressed as:

[0101]

[0102] Among them, e represents the energy consumption management threshold of the device per unit time, A a Indicates the energy consumption of the device per unit time, c min Indicates the minimum energy consumption allowed by the device per unit time, c max Indicates the maximum energy consumption allowed by the device per unit time.

[0103] The present invention proposes a smart factory energy management system and management method, collects energy consumption of equipment through various intelligent sensors, and uses a variety of algorithm models such as double exponential empirical model, feature extraction, secondary nested judgment, energy consumption demand prediction model, energy consumption management threshold, etc. to comprehensively calculate the energy consumption of factory equipment, and combines the system to supervise energy consumption issues. The system has stable operation and strong operability. The method is based on a certain existing theoretical foundation, is easy to understand, can help factories to effectively manage energy consumption, has strong automation, and saves costs.

[0104] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", "connect", and "fix" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0105] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart factory energy management system, characterized in that , the system includes: Screen control center unit, sensor monitoring unit, real-time energy consumption alarm unit, energy consumption management threshold unit, equipment energy consumption statistics unit, equipment stage energy consumption prediction unit, energy comprehensive configuration unit, equipment unified management unit, energy consumption parameter control unit, energy saving and emission reduction indication unit, energy statistics unit, system control unit; The sensor monitoring unit, real-time energy consumption alarm unit, energy consumption management threshold unit, equipment energy consumption statistics unit, equipment stage energy consumption prediction unit, energy comprehensive configuration unit, equipment unified management unit, energy consumption parameter control unit, energy saving and emission reduction indication unit, energy statistics unit, and system control unit are connected to the screen control center unit, and the screen control center unit performs unified management on other units; The system is implemented by a smart factory energy management method, the steps of which are as follows: Step S1: collecting raw data of energy-consuming equipment through various intelligent sensors, using a double exponential empirical model to describe the energy consumption of the equipment, and establishing an iterative equation of the double exponential empirical model according to the service life of the equipment; Step S2: extracting features from the original data, establishing energy consumption characteristics per unit time, and using the energy consumption characteristics to perform error fitting on the double exponential empirical model of the equipment; Step S3: Perform secondary nesting judgment based on whether the energy consumption demand of the equipment has changed, and establish an energy consumption demand prediction model; Step S4: predicting equipment output efficiency based on production scheduling, maintenance plan and production planning model; Step S5: Optimizing the start and stop schedule of the equipment through the energy consumption cost of the equipment and the start and stop optimization scheduling function; Step S6: Calculate the energy consumption management threshold. Once the energy consumption management threshold is exceeded, the management system page will issue an alarm, and a push message will be sent to the mobile phones of the on-duty personnel and on-site personnel for immediate processing; The double exponential empirical model is expressed as: A a =b a exp(c a a)+d a exp(e a a) Among them, A a Indicates the energy consumption of the device per unit time, a indicates the operating time of the device per unit time, and b a Indicates the energy consumption coefficient of the low power consumption of the device, c a Indicates the average energy consumption of the device in low power operation state, d a Indicates the energy consumption coefficient of the equipment at full load, e a Indicates the average energy consumption of the equipment when it is running at full load; The iterative equation is expressed as: Among them, A a-1 represents the energy consumption of the equipment in the previous unit time, η represents the covariance of the wear coefficient of the equipment at different times, ω represents the age of the equipment, K represents the designed life span of the equipment, and f a Represents the coefficient matrix of all other factors affecting the energy consumption of the equipment, η a Indicates the wear coefficient of the equipment per unit time, η a-1 Indicates the wear coefficient of the equipment in the previous unit time, f η Represents all other noise factors that affect the wear coefficient of the equipment, ω a Indicates the age of the equipment per unit time, ω a-1 Indicates the age of the equipment used to the previous unit of time, f ω Indicates all other older noise factors that affect the use of the equipment; The energy consumption characteristics per unit time are established, and the expression is: Among them, h(r) represents the energy consumption characteristic quantity per unit time, r represents the number of abnormal operation of the equipment, g1 represents the voltage characteristic when the equipment is operating normally, g2 represents the characteristic coefficient of abnormal operation of the equipment, and g3 represents the current characteristic when the equipment is operating normally; The error fitting expression is: Among them, Q represents the hyperparameter formed by fitting, Q 2 The closer it is to 1, the higher the accuracy of the fitting. E represents the total number of times per unit time. A a Indicates the energy consumption of the device per unit time. It represents the fitting value of the energy consumption per unit time of the equipment, h r Represents the characteristic quantity of energy consumption per unit time, Represents the mean value of energy consumption characteristic quantity per unit time; The secondary nested judgment is expressed as: Among them, ψ r (a) indicates whether the energy demand has changed, 1 indicates that the demand has changed, 0 indicates that the demand has not changed, Δr(a) indicates the change in energy demand per unit time, and ξ indicates the threshold value of the change in energy demand per unit time; The energy consumption demand prediction model is expressed as: Among them, A C+1 Indicates the energy consumption demand of the equipment at the next unit time, λ r Iteration parameter representing the energy consumption characteristic quantity; The output efficiency of the equipment is expressed as: Among them, j represents the equipment output efficiency, y a represents production schedule, v a represents the production plan, and n represents the number of times per unit time; The start-stop optimization scheduling function is expressed as: Among them, W Y (N1, N2) represents the equipment start-stop scheduling function, N1 represents the equipment energy consumption cost matrix under different modes and N2 represents the past equipment start-stop optimization scheduling matrix, T represents the transpose of the matrix, and Cov represents the covariance operation; The energy consumption management threshold is expressed as: Among them, e represents the energy consumption management threshold of the device per unit time, A a Indicates the energy consumption of the device per unit time, c min Indicates the minimum energy consumption allowed by the device per unit time, c max Indicates the maximum energy consumption allowed by the device per unit time.

Images