Factory operation state-based energy consumption simulation and prediction method, system, equipment and medium

Abstract

The invention relates to an energy consumption simulation and prediction method, system and device based on a factory operation state and a medium, and relates to the technical field of energy consumption simulation and prediction. The energy consumption simulation method based on the factory operation state comprises the steps that historical use time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment in a set time interval and historical energy consumption evaluation corresponding to the historical use time, the historical electricity consumption data and / or the historical gas consumption data of each set energy consumption device in a plurality of set energy consumption devices in the factory operation state are utilized; training a preset energy consumption simulation evaluation generation network to obtain a preset energy consumption simulation evaluation generator; and based on the preset energy consumption simulation evaluation generator, generating corresponding energy consumption simulation evaluation by using the current use time, the current power consumption data and / or the current gas consumption data corresponding to each set energy consumption device in the plurality of set energy consumption devices in the factory operation state. According to the embodiment of the invention, energy consumption simulation and prediction of the factory operation state can be realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of energy consumption simulation and prediction, and in particular to a method, system, device and medium for simulating and predicting energy consumption based on plant operation status. Background Art

[0002] From the perspective of energy utilization in a country's economic activities, unit energy consumption is the primary indicator reflecting energy consumption levels and energy conservation and consumption reduction. The ratio of total primary energy supply to GDP is an indicator of energy efficiency. Therefore, efficiency indicators illustrate the degree of energy utilization in a country's economic activities and reflect changes in its economic structure and energy efficiency.

[0003] For factories, unit energy consumption can also reflect the main indicators of energy consumption levels and energy conservation and consumption reduction. However, for energy-consuming equipment within a factory, the production value during its operation is generally fixed. However, as its usage time increases, energy-consuming equipment will age. As energy-consuming equipment ages, its energy consumption will increase to maintain its production value during operation. In addition, as energy-consuming equipment ages, the heat generated during operation will also increase, which will cause the refrigeration system to cool it or its environment. In the process of cooling it or its environment, the refrigeration system will also increase its energy consumption. However, the current energy consumption evaluation process does not consider the impact of the usage time of energy-consuming equipment on energy consumption evaluation. At the same time, multiple energy-consuming equipment needs to cooperate in the factory operation state, and it is difficult to establish a linear law (relationship) between the usage time of multiple energy-consuming equipment and the energy consumption of the factory operation state. Therefore, it is necessary to consider the impact of the usage time of energy-consuming equipment on energy consumption evaluation in order to realize energy consumption simulation and prediction of factory operation status. Summary of the Invention

[0004] The present disclosure proposes a technical solution for a method, system, equipment and medium for simulating and predicting energy consumption based on plant operating status.

[0005] According to one aspect of the present disclosure, a method for simulating energy consumption based on a plant operating state is provided, comprising:

[0006] The preset energy consumption simulation evaluation generation network is trained using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of the multiple set energy consumption devices in the factory operation state, and the corresponding historical energy consumption evaluation to obtain the preset energy consumption simulation evaluation generator; based on the preset energy consumption simulation evaluation generator, the corresponding energy consumption simulation evaluation is generated using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of the multiple set energy consumption devices in the factory operation state.

[0007] Preferably, the preset energy consumption simulation evaluation generation network is trained by utilizing the historical usage time, historical electricity consumption data and / or historical gas consumption data and their corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of the multiple set energy consumption devices in the factory operation state to obtain the preset energy consumption simulation evaluation generator, including: configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data as a classification feature vector; configuring the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or historical gas consumption data as a classification training label corresponding to the classification feature vector; using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; calculating the loss value corresponding to the training process energy consumption simulation evaluation and the classification training label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator.

[0008] Preferably, the method of calculating the loss value corresponding to the energy consumption simulation evaluation of the training process and the label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator, includes: if the loss value corresponding to the energy consumption simulation evaluation of the training process and the label is less than or equal to the preset loss value within the set number of training times, then the training of the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator is completed.

[0009] Preferably, before training the preset energy consumption simulation evaluation generation network, a connection to the host computer database is established through the industrial bus, and the industrial bus is used to obtain from the host computer database the historical usage time, historical electricity consumption data and / or historical gas consumption data and their corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of the multiple set energy consumption devices in the factory operation state.

[0010] Preferably, the use of the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation includes: obtaining random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data; configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise as a classification feature vector; configuring the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise as a classification training label corresponding to the classification feature vector; and using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation.

[0011] Preferably, before using the classification feature vector to train the preset energy consumption simulation evaluation generation network, the classification feature vector is standardized to obtain a standardized classification feature vector; and the preset energy consumption simulation evaluation generation network is trained using the standardized classification feature vector.

[0012] Preferably, the calculation of the energy consumption simulation evaluation of the training process and the loss value corresponding to the classification training label includes: based on a preset energy consumption simulation evaluation identification network, using the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation, to determine whether the energy consumption simulation evaluation is true or false; calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data and the second loss corresponding to determining whether the energy consumption simulation evaluation is true or false, and training the preset energy consumption simulation evaluation generation network.

[0013] Preferably, the preset energy consumption simulation evaluation and identification network is configured as one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.

[0014] Preferably, the energy consumption simulation evaluation and / or the energy consumption evaluation configuration is one of a high energy consumption level, a medium energy consumption level, a low energy consumption level and a normal energy consumption level.

[0015] Preferably, a corresponding electricity consumption detection sensor and / or gas consumption sensor is set in each of the set energy consumption devices; the corresponding historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are collected by using the corresponding electricity consumption detection sensor and / or gas consumption detection sensor set in each of the set energy consumption devices; and the collected historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are sent to the host computer database by using the industrial bus connected to the electricity consumption detection sensor and / or gas consumption detection sensor set in each of the set energy consumption devices, and the collected historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are stored in the host computer database.

[0016] Preferably, a timer is used to respectively time the usage time corresponding to each set energy-consuming device from being turned on to being turned off, so as to obtain the usage time corresponding to each set energy-consuming device; the usage time corresponding to each set energy-consuming device is sent to a host computer database through an industrial bus connected to the timer, and the usage time corresponding to each set energy-consuming device is stored using the host computer database.

[0017] Preferably, the preset energy consumption simulation evaluation generation network is configured as one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.;

[0018] The energy consumption simulation method based on the factory operation status also includes: using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in the set time interval of each set energy-consuming device in the factory operation status and the historical energy consumption evaluation corresponding to the second moment after the first moment, to train the preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator; based on the preset energy consumption simulation evaluation generator, using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each set energy-consuming device in the factory operation status, the energy consumption evaluation corresponding to the fourth moment after the third moment.

[0019] According to one aspect of the present disclosure, a method for predicting energy consumption based on a plant operating state is provided, comprising:

[0020] The preset energy consumption simulation evaluation generation network is trained using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment within a set time interval of each of the multiple set energy consumption devices in the factory operation state, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; based on the preset energy consumption simulation evaluation generator, the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each of the multiple set energy consumption devices in the factory operation state are used to predict the energy consumption evaluation corresponding to the fourth moment after the third moment.

[0021] Preferably, the preset energy consumption simulation evaluation generation network is trained using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in the set time interval of each of the multiple set energy consumption devices in the factory operation state, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator, including: configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data corresponding to the first moment as a prediction feature vector; configuring the historical energy consumption evaluation corresponding to the second moment after the first moment as a prediction training label corresponding to the prediction feature vector; using the prediction feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; calculating the loss value corresponding to the training process energy consumption simulation evaluation and the prediction training label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator.

[0022] Preferably, the method of calculating the loss value corresponding to the energy consumption simulation evaluation of the training process and the label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator, includes: if the loss value corresponding to the energy consumption simulation evaluation of the training process and the label is less than or equal to the preset loss value within the set number of training times, then the training of the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator is completed.

[0023] Preferably, before training the preset energy consumption simulation evaluation generation network, a connection to the host computer database is established through the industrial bus, and the industrial bus is used to obtain from the host computer database the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in the set time interval for each of the multiple set energy consumption devices in the factory operation state, as well as the historical energy consumption evaluation corresponding to the second moment after the first moment.

[0024] Preferably, the use of the predicted feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation includes: obtaining random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data corresponding to the first moment; configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise corresponding to the first moment as a predicted feature vector; configuring the energy consumption evaluation corresponding to the second moment as a predicted training label corresponding to the predicted feature vector; and using the predicted feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation.

[0025] Preferably, before using the predicted feature vector to train the preset energy consumption simulation evaluation generation network, it includes: standardizing the predicted feature vector to obtain a standardized predicted feature vector; and using the standardized predicted feature vector to train the preset energy consumption simulation evaluation generation network.

[0026] Preferably, the calculation of the energy consumption simulation evaluation of the training process and the loss value corresponding to the predicted training label includes: based on a preset energy consumption simulation evaluation identification network, using the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation, to determine whether the energy consumption simulation evaluation is true or false; calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data and the second loss corresponding to determining whether the energy consumption simulation evaluation is true or false, and training the preset energy consumption simulation evaluation generation network.

[0027] Preferably, the energy consumption simulation method based on the plant operating status is characterized in that the energy consumption simulation evaluation and / or the energy consumption evaluation is configured as one of a high energy consumption level, a medium energy consumption level, a low energy consumption level and a normal energy consumption level.

[0028] Preferably, a corresponding electricity consumption detection sensor and / or gas consumption sensor is set in each of the set energy consumption devices; the corresponding historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are collected by using the corresponding electricity consumption detection sensor and / or gas consumption detection sensor set in each of the set energy consumption devices; and the collected historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are sent to the host computer database by using the industrial bus connected to the electricity consumption detection sensor and / or gas consumption detection sensor set in each of the set energy consumption devices, and the collected historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are stored in the host computer database.

[0029] Preferably, a timer is used to respectively time the usage time corresponding to each set energy-consuming device from being turned on to being turned off, so as to obtain the usage time corresponding to each set energy-consuming device; the usage time corresponding to each set energy-consuming device is sent to a host computer database through an industrial bus connected to the timer, and the usage time corresponding to each set energy-consuming device is stored using the host computer database.

[0030] Preferably, the preset energy consumption simulation evaluation generation network is configured as one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.

[0031] Preferably, the energy consumption prediction method based on the plant operation status further comprises: using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of a plurality of set energy-consuming devices in the plant operation status and the corresponding historical energy consumption evaluation, to train a preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator;

[0032] Based on the preset energy consumption simulation evaluation generator, the corresponding energy consumption simulation evaluation is generated using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each set energy consumption equipment in the multiple set energy consumption equipment under the factory operation state.

[0033] According to one aspect of the present disclosure, an energy consumption simulation system based on the operation status of a factory is provided, comprising: a first training unit, for training a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data and the corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consumption devices in the operation status of the factory, to obtain the preset energy consumption simulation evaluation generator; a simulation evaluation unit, for generating a corresponding energy consumption simulation evaluation based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of a plurality of set energy consumption devices in the operation status of the factory.

[0034] According to one aspect of the present disclosure, a system for simulating energy consumption based on the operating status of a plant is provided, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call instructions stored in the memory to execute the above-mentioned energy consumption simulation method based on the operating status of the plant.

[0035] According to one aspect of the present disclosure, a system for simulating energy consumption based on the operating status of a plant is provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to implement the above-mentioned method for simulating energy consumption based on the operating status of the plant.

[0036] According to one aspect of the present disclosure, an energy consumption simulation system based on the plant operating status is provided, comprising: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption simulation method based on the plant operating status as described above is implemented.

[0037] According to one aspect of the present disclosure, an energy consumption simulation device based on the operation status of a factory is provided, comprising: a first training unit, for training a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data and the corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consumption devices in the operation status of the factory, to obtain the preset energy consumption simulation evaluation generator; a simulation evaluation unit, for generating a corresponding energy consumption simulation evaluation based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of a plurality of set energy consumption devices in the operation status of the factory.

[0038] According to one aspect of the present disclosure, an energy consumption simulation device based on the operating status of a factory is provided, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption simulation method based on the operating status of the factory.

[0039] According to one aspect of the present disclosure, an energy consumption simulation device based on the operating status of a plant is provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to implement the above-mentioned energy consumption simulation method based on the operating status of the plant.

[0040] According to one aspect of the present disclosure, there is provided an energy consumption simulation device based on the operating status of a plant, comprising: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption simulation method based on the operating status of the plant is implemented as described above.

[0041] According to one aspect of the present disclosure, an energy consumption prediction system based on the operation status of a factory is provided, comprising: a second training unit for training a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment within a set time interval of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the factory, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; an energy consumption evaluation prediction unit for predicting the energy consumption evaluation corresponding to the fourth moment after the third moment based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the factory.

[0042] According to one aspect of the present disclosure, a system for predicting energy consumption based on the operating status of a plant is provided, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the plant.

[0043] According to one aspect of the present disclosure, a system for predicting energy consumption based on the operating status of a plant is provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned method for predicting energy consumption based on the operating status of the plant.

[0044] According to one aspect of the present disclosure, there is provided an energy consumption prediction system based on the plant operating status, comprising: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption prediction method based on the plant operating status as described above is implemented.

[0045] According to one aspect of the present disclosure, an energy consumption prediction device based on the operation status of a factory is provided, comprising: a second training unit for training a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment within a set time interval of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the operation status of the factory, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; an energy consumption evaluation prediction unit for predicting the energy consumption evaluation corresponding to the fourth moment after the third moment based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each set energy consumption device in the operation status of the plurality of set energy consumption devices in the operation status of the factory.

[0046] According to one aspect of the present disclosure, an energy consumption prediction device based on the operating status of a plant is provided, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the plant.

[0047] According to one aspect of the present disclosure, an energy consumption prediction device based on the operating status of a plant is provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the plant.

[0048] According to one aspect of the present disclosure, an energy consumption prediction device based on the plant operating status is provided, including: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption prediction method based on the plant operating status as described above is implemented.

[0049] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-mentioned energy consumption simulation method based on the plant operating status is implemented.

[0050] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-mentioned energy consumption prediction method based on the plant operating status is implemented.

[0051] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the energy consumption simulation method based on the plant operating status and the energy consumption prediction method based on the plant operating status are implemented.

[0052] In the embodiments of the present disclosure, technical solutions corresponding to the energy consumption simulation and prediction method, system, equipment and medium based on the factory operating status are proposed to solve at least one technical problem that the current energy consumption simulation and prediction of the factory operating status does not take into account the impact of the usage time of energy-consuming equipment on energy consumption evaluation.

[0053] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0054] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0056] Figure 1 A flow chart showing a method for simulating energy consumption based on plant operating status according to an embodiment of the present disclosure is shown;

[0057] Figure 2 A schematic diagram of a method for predicting energy consumption based on plant operating status according to an embodiment of the present disclosure is shown;

[0058] Figure 3 A schematic diagram of an energy consumption simulation system based on a plant operating state according to an embodiment of the present disclosure is shown;

[0059] Figure 4 A schematic diagram of an energy consumption prediction system based on plant operating status according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0060] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0061] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0062] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent the existence of three situations: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0063] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0064] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, the present disclosure will not elaborate on them.

[0065] In addition, the present disclosure also provides an energy consumption simulation device based on the factory operating status and an energy consumption simulation prediction device or system based on the factory operating status, an electronic device, a computer-readable storage medium, and a program product. The above can all be used to implement any energy consumption simulation and prediction method based on the factory operating status provided by the present disclosure. The corresponding technical solutions and descriptions are referred to the corresponding records in the method section and will not be repeated here.

[0066] Figure 1 FIG. 1 is a flow chart showing a method for simulating energy consumption based on plant operation status according to an embodiment of the present disclosure. Figure 1 As shown, the energy consumption simulation method based on the plant operating status includes: step S101: using the historical usage time, historical electricity consumption data, and / or historical gas consumption data corresponding to at least one collection time within a set time interval for each of multiple set energy-consuming devices in the plant operating status, as well as the corresponding historical energy consumption evaluation, to train a preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator; step S102: based on the preset energy consumption simulation evaluation generator, using the current usage time, current electricity consumption data, and / or current gas consumption data corresponding to each of the multiple set energy-consuming devices in the plant operating status to generate a corresponding energy consumption simulation evaluation. This solves the technical problem that current energy consumption predictions for plant operating status do not consider the impact of the usage time of energy-consuming devices on energy consumption evaluations.

[0067] Step S101: Using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of the multiple set energy-consuming devices in the factory operation state and its corresponding historical energy consumption evaluation, the preset energy consumption simulation evaluation generation network is trained to obtain the preset energy consumption simulation evaluation generator.

[0068] In the embodiments of the present disclosure and other possible embodiments, those skilled in the art may configure multiple energy-consuming devices under the factory operation state according to actual needs. For example, production line production equipment and its corresponding drive motors, lighting equipment, air-conditioning equipment, etc., one or more. For example, factory circulating water equipment and its corresponding drive motors, lighting equipment, air-conditioning equipment, etc., one or more. For example, steel rolling production line equipment and its corresponding drive motors, lighting equipment, air-conditioning equipment, etc., one or more. For example, sewing machines, ironing machines and other equipment in a garment factory and their corresponding drive motors, lighting equipment, air-conditioning equipment, etc., one or more.

[0069] In the embodiments of the present disclosure and other possible embodiments, those skilled in the art may configure the set time interval according to actual needs. For example, the set time interval may be configured to be one week, 30 days, 6 months, or other time intervals.

[0070] In the embodiments of the present disclosure and other possible embodiments, the set time interval may include: one or more of: peak electricity and / or gas consumption times, low electricity and / or gas consumption times, and holiday electricity and / or gas consumption times.

[0071] In an embodiment of the present disclosure, the preset energy consumption simulation evaluation generation network is trained using the historical usage time, historical electricity consumption data and / or historical gas consumption data and their corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consumption devices in a factory operating state to obtain the preset energy consumption simulation evaluation generator, including: configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data as a classification feature vector; configuring the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or historical gas consumption data as a classification training label corresponding to the classification feature vector; using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; calculating the loss value corresponding to the training process energy consumption simulation evaluation and the classification training label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator.

[0072] In an embodiment of the present disclosure, the method of calculating the loss value corresponding to the energy consumption simulation evaluation of the training process and the label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator, includes: if the loss value corresponding to the energy consumption simulation evaluation of the training process and the label is less than or equal to the preset loss value within the set number of training times, then completing the training of the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator.

[0073] In an embodiment of the present disclosure, before training the preset energy consumption simulation evaluation generation network, a connection to a host computer database is established through an industrial bus, and the industrial bus is used to obtain from the host computer database the historical usage time, historical electricity consumption data and / or historical gas consumption data and their corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of the multiple set energy consumption devices in the factory operation state.

[0074] In an embodiment of the present disclosure, the energy consumption simulation evaluation and / or the energy consumption evaluation configuration is one of a high energy consumption level, a medium energy consumption level, a low energy consumption level, and a normal energy consumption level. Meanwhile, those skilled in the art may configure the energy consumption simulation evaluation and / or the energy consumption evaluation according to actual needs. For example, the energy consumption simulation evaluation and / or the energy consumption evaluation configuration is energy efficiency, and the energy efficiency levels are divided into energy efficiency levels A to G; wherein energy efficiency level A represents the highest energy efficiency level; conversely, energy efficiency level G represents the lowest energy efficiency level.

[0075] In the embodiment of the present disclosure and other possible embodiments, determining the energy consumption evaluation includes: respectively obtaining the electricity consumption data and / or gas consumption data of a plurality of set energy-consuming devices and their corresponding production values; and determining the energy consumption evaluation based on the electricity consumption data and / or gas consumption data of the plurality of set energy-consuming devices and the production values. Determining the energy consumption evaluation based on the electricity consumption data and / or gas consumption data of the plurality of set energy-consuming devices and the production values ​​includes: obtaining a plurality of set ratios; calculating the ratio corresponding to the production value and the electricity consumption data and / or gas consumption data of the plurality of set energy-consuming devices; comparing the ratio with the plurality of set ratios to determine the energy consumption evaluation, and then configuring the energy consumption evaluation to be one of a high energy consumption level, a medium energy consumption level, a low energy consumption level, and a normal energy consumption level.

[0076] In the embodiments of the present disclosure and other possible embodiments, the comparison of the ratio and the multiple set ratios to determine the energy consumption evaluation, and then configuring the energy consumption evaluation to one of a high energy consumption level, a medium energy consumption level, a low energy consumption level and a normal energy consumption level, includes: obtaining a first set ratio corresponding to multiple set ratios, a second set ratio less than the first set ratio and a third set ratio less than the second set ratio; if the ratio is greater than or equal to the first set ratio, the energy consumption evaluation is configured as a high energy consumption level; if the ratio is less than the first set ratio and greater than or equal to the second set ratio, the energy consumption evaluation is configured as a medium energy consumption level; if the ratio is less than the second set ratio and greater than or equal to the third set ratio, the energy consumption evaluation is configured as a low energy consumption level; if the ratio is less than the third set ratio, the energy consumption evaluation is configured as a normal energy consumption level.

[0077] In an embodiment of the present disclosure, a corresponding electricity consumption detection sensor and / or gas consumption sensor is set for each of the set energy-consuming devices; the corresponding electricity consumption detection sensor and / or gas consumption detection sensor set for each of the set energy-consuming devices is used to collect corresponding historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data; and the collected historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are sent to a host computer database using an industrial bus connected to the electricity consumption detection sensor and / or gas consumption detection sensor set for each of the set energy-consuming devices, and the collected historical electricity consumption data and / or historical gas consumption data, current electricity consumption data and / or current gas consumption data are stored using the host computer database.

[0078] In an embodiment of the present disclosure, a timer is used to time the usage time corresponding to each set energy-consuming device from being turned on to being turned off, so as to obtain the usage time corresponding to each set energy-consuming device; the usage time corresponding to each set energy-consuming device is sent to a host computer database through an industrial bus connected to the timer, and the usage time corresponding to each set energy-consuming device is stored in the host computer database.

[0079] In an embodiment of the present disclosure, the preset energy consumption simulation evaluation generation network is configured as one or more of support vector regression (SVR), support vector machine (SVM), K-nearest neighbor algorithm (KNN), decision tree (XGBoost), random forest (RF), artificial neural network (ANN), deep neural network (DNN), etc.

[0080] In the embodiments of the present disclosure and other possible embodiments, the input layer and the output layer of the deep neural network (DNN) respectively include a first number of neurons and a second number of neurons, and each layer of the multiple intermediate hidden layers between the input layer and the output layer respectively includes a third number of neurons. In order to overcome the gradient vanishing problem and accelerate learning, in addition to the Sigmoid and Tanh activation functions, the ReLU activation function is also used to approximate the nonlinear function. Specifically, the ReLU activation function is configured after each neuron in the second layer and each neuron in the fourth layer in the intermediate hidden layer, and the Sigmoid activation function and the Tanh activation function are respectively configured after each neuron in the first layer and each neuron in the third layer of the intermediate hidden layer.

[0081] In an embodiment of the present disclosure, the preset energy consumption simulation evaluation generation network is trained using the classification feature vector to obtain a corresponding training process energy consumption simulation evaluation, including: obtaining random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data; configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise as a classification feature vector; configuring the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise as a classification training label corresponding to the classification feature vector; and using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain a corresponding training process energy consumption simulation evaluation.

[0082] In the embodiments of the present disclosure, before using the classification feature vector to train the preset energy consumption simulation evaluation generation network, the classification feature vector is standardized to obtain a standardized classification feature vector; and the preset energy consumption simulation evaluation generation network is trained using the standardized classification feature vector.

[0083] In an embodiment of the present disclosure, the calculation of the energy consumption simulation evaluation of the training process and the loss value corresponding to the classification training label includes: based on a preset energy consumption simulation evaluation identification network, using the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation, to determine whether the energy consumption simulation evaluation is true or false; calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data and the second loss corresponding to determining whether the energy consumption simulation evaluation is true or false, and training the preset energy consumption simulation evaluation generation network.

[0084] In the embodiments of the present disclosure and other possible embodiments, the calculation of the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data and the second loss corresponding to the judgment of whether the energy consumption simulation evaluation is true or false include: respectively constructing a first setting loss function corresponding to the first loss and a second setting loss function corresponding to the second loss; based on the first setting loss function, calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data; based on the second setting loss function, calculating the second loss corresponding to the random noise under the conditions of the historical electricity consumption data and / or gas consumption data for judging whether the energy consumption simulation evaluation is true or false.

[0085] In the embodiments of the present disclosure and other possible embodiments, constructing a first set loss function corresponding to the first loss includes: calculating the difference between a set value and an energy consumption simulation evaluation corresponding to random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data; taking the logarithm of the difference to obtain a logarithm of the difference; calculating a first expected value of the logarithm of the difference to construct a first set loss function corresponding to the first loss; wherein the set value is configured to be 1.

[0086] In the embodiments of the present disclosure and other possible embodiments, the construction of a first set loss function corresponding to the first loss includes: taking the logarithm of the probability value for discriminating whether the energy consumption simulation evaluation is true or false corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data, to obtain a discriminant logarithm value; calculating a second expected value of the logarithm value, and constructing a second set loss function corresponding to the second loss. Among them, the first loss of the energy consumption simulation evaluation corresponding to the random noise calculated under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data and the second loss corresponding to the true or false judgment of the energy consumption simulation evaluation are trained on the preset energy consumption simulation evaluation generation network to obtain a preset energy consumption simulation evaluation generator, including: based on the first set loss function corresponding to the first loss and the second set loss function corresponding to the second loss, constructing the objective function corresponding to the preset energy consumption simulation evaluation generation network and the preset energy consumption simulation evaluation identification network; maximizing the first expected value of the first set loss function corresponding to the first loss in the objective function and minimizing the second expected value of the second set loss function corresponding to the second loss in the objective function, training the preset energy consumption simulation evaluation generation network to obtain a preset energy consumption simulation evaluation generator.

[0087] In an embodiment of the present disclosure, the preset energy consumption simulation evaluation and identification network is configured as one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.

[0088] In the embodiments of the present disclosure and other possible embodiments, the collection period or collection frequency corresponding to the power consumption detection sensor and / or gas consumption sensor set for each set energy-consuming device is obtained; based on the collection period or collection frequency corresponding to the power consumption detection sensor and / or gas consumption sensor set for each set energy-consuming device, power consumption data and / or gas consumption data are collected for each set energy-consuming device, and the collected power consumption data and / or gas consumption data corresponding to each set energy-consuming device and the collection time are sent to the host computer database via the industrial bus.

[0089] In the embodiments of the present disclosure and other possible embodiments, the energy consumption simulation method based on the plant operating status includes: using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in a set time interval for each of the multiple set energy-consuming devices in the plant operating status, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to train a preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator; based on the preset energy consumption simulation evaluation generator, using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment for each of the multiple set energy-consuming devices in the plant operating status, to predict the energy consumption evaluation corresponding to the fourth moment after the third moment.

[0090] Step S102: Based on the preset energy consumption simulation evaluation generator, a corresponding energy consumption simulation evaluation is generated using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of the multiple set energy consumption devices in the factory operation state.

[0091] Figure 2 FIG. 1 shows a schematic diagram of an energy consumption prediction method based on a plant operation state according to an embodiment of the present disclosure. Figure 2As shown, the embodiment of the present disclosure also provides an energy consumption prediction method based on the operation status of a factory, comprising: step S201: using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in a set time interval of each of the multiple set energy-consuming devices in the operation status of the factory, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to train a preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator; step S202: based on the preset energy consumption simulation evaluation generator, using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each of the multiple set energy-consuming devices in the operation status of the factory, to predict the energy consumption evaluation corresponding to the fourth moment after the third moment. This solves the technical problem that the current energy consumption prediction of the operation status of the factory does not consider the impact of the usage time of the energy-consuming equipment on the energy consumption evaluation.

[0092] In an embodiment of the present disclosure, the preset energy consumption simulation evaluation generation network is trained by utilizing the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment within a set time interval of each of the multiple set energy consumption devices in the factory operation state, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator, including: configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data corresponding to the first moment as a prediction feature vector; configuring the historical energy consumption evaluation corresponding to the second moment after the first moment as a prediction training label corresponding to the prediction feature vector; using the prediction feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; calculating the loss value corresponding to the training process energy consumption simulation evaluation and the prediction training label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator.

[0093] In the embodiment of the present disclosure and other possible embodiments, the second moment can be configured as 72 hours after the first moment; similarly, the third moment can be configured as 72 hours after the fourth moment. Furthermore, based on the preset energy consumption simulation evaluation generator, the energy consumption evaluation corresponding to the fourth moment 72 hours after the third moment is predicted using the current usage time, current electricity consumption data, and / or current gas consumption data corresponding to each of the multiple set energy-consuming devices in the plant operating state at the third moment.

[0094] In an embodiment of the present disclosure, the method of calculating the loss value corresponding to the energy consumption simulation evaluation of the training process and the label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator, includes: if the loss value corresponding to the energy consumption simulation evaluation of the training process and the label is less than or equal to the preset loss value within the set number of training times, then completing the training of the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator.

[0095] In an embodiment of the present disclosure, the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in the set time interval of each of the multiple set energy-consuming devices in the factory operation state, and the historical energy consumption evaluation corresponding to the second moment after the first moment, before training the preset energy consumption simulation evaluation generation network, a connection with the host computer database is established through the industrial bus, and the industrial bus is used to obtain the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in the set time interval of each of the multiple set energy-consuming devices in the factory operation state, and the historical energy consumption evaluation corresponding to the second moment after the first moment from the host computer database.

[0096] In an embodiment of the present disclosure, the use of the predicted feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation includes: obtaining random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data corresponding to the first moment; configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise corresponding to the first moment as a predicted feature vector; configuring the energy consumption evaluation corresponding to the second moment as a predicted training label corresponding to the predicted feature vector; and using the predicted feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation.

[0097] In an embodiment of the present disclosure, before using the predicted feature vector to train the preset energy consumption simulation evaluation generation network, it includes: standardizing the predicted feature vector to obtain a standardized predicted feature vector; and using the standardized predicted feature vector to train the preset energy consumption simulation evaluation generation network.

[0098] In an embodiment of the present disclosure, the calculation of the energy consumption simulation evaluation of the training process and the loss value corresponding to the predicted training label includes: based on a preset energy consumption simulation evaluation identification network, using the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation, to determine whether the energy consumption simulation evaluation is true or false; calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data and the second loss corresponding to determining whether the energy consumption simulation evaluation is true or false, and training the preset energy consumption simulation evaluation generation network.

[0099] In an embodiment of the present disclosure, the energy consumption simulation evaluation and / or the energy consumption evaluation configuration is one of a high energy consumption level, a medium energy consumption level, a low energy consumption level, and a normal energy consumption level. Similarly, the preset energy consumption simulation evaluation identification network configuration is one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.

[0100] Similarly, in the embodiments of the present disclosure and other possible embodiments, the calculation of the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data and the second loss corresponding to the judgment of whether the energy consumption simulation evaluation is true or false include: respectively constructing a first setting loss function corresponding to the first loss and a second setting loss function corresponding to the second loss; based on the first setting loss function, calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data; based on the second setting loss function, calculating the second loss corresponding to the random noise under the conditions of the historical electricity consumption data and / or gas consumption data for judging whether the energy consumption simulation evaluation is true or false.

[0101] Similarly, in the embodiments of the present disclosure and other possible embodiments, the construction of the first set loss function corresponding to the first loss includes: calculating the difference between the set value and the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data; taking the logarithm of the difference to obtain the logarithm of the difference; calculating the first expected value of the logarithm of the difference to construct the first set loss function corresponding to the first loss; wherein, the set value is configured to be 1.

[0102] Similarly, in the embodiments of the present disclosure and other possible embodiments, the construction of the first set loss function corresponding to the first loss includes: taking the logarithm of the discrimination probability value for judging whether the energy consumption simulation evaluation is true or false corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data, to obtain a discrimination logarithm value; calculating a second expected value of the logarithm value, and constructing a second set loss function corresponding to the second loss. Among them, the first loss of the energy consumption simulation evaluation corresponding to the random noise calculated under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data and the second loss corresponding to the true or false judgment of the energy consumption simulation evaluation are trained on the preset energy consumption simulation evaluation generation network to obtain a preset energy consumption simulation evaluation generator, including: based on the first set loss function corresponding to the first loss and the second set loss function corresponding to the second loss, constructing the objective function corresponding to the preset energy consumption simulation evaluation generation network and the preset energy consumption simulation evaluation identification network; maximizing the first expected value of the first set loss function corresponding to the first loss in the objective function and minimizing the second expected value of the second set loss function corresponding to the second loss in the objective function, training the preset energy consumption simulation evaluation generation network to obtain a preset energy consumption simulation evaluation generator.

[0103] In the embodiments of the present disclosure and other possible embodiments, in order to solve the technical problem that traditional machine learning networks rely on a large amount of usage time, electricity consumption and / or gas consumption data, and are difficult to obtain the optimal energy consumption simulation evaluation and cannot accurately predict the energy consumption evaluation when the usage time, electricity consumption and / or gas consumption data are small and the energy consumption evaluation corresponding to the usage time, electricity consumption and / or gas consumption is unevenly distributed, a conditional generative adversarial network based on a preset energy consumption simulation evaluation generation network and a preset energy consumption simulation evaluation identification network is proposed.

[0104] In the embodiments of the present disclosure and other possible embodiments, the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or gas consumption data, the random noise under the conditions of the historical electricity consumption data and / or gas consumption data, the historical usage time, the historical electricity consumption data and / or gas consumption data, and the preset energy consumption simulation evaluation identification network are used to train the preset energy consumption simulation evaluation generation network to obtain a preset energy consumption simulation evaluation generator, including: based on the preset energy consumption simulation evaluation generation network, using the historical usage time, the historical electricity consumption data and / or gas consumption data and the historical An energy consumption simulation evaluation is generated by using random noise under the conditions of electricity consumption data and / or gas consumption data; based on the preset energy consumption simulation evaluation identification network, the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation are used to determine whether the energy consumption simulation evaluation is true or false; a first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data and a second loss corresponding to determining whether the energy consumption simulation evaluation is true or false is calculated, and the preset energy consumption simulation evaluation generation network is trained to obtain a preset energy consumption simulation evaluation generator.

[0105] In the embodiments of the present disclosure and other possible embodiments, the calculation of the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data and the second loss corresponding to the judgment of whether the energy consumption simulation evaluation is true or false include: respectively constructing a first setting loss function E[log(1-D(G(z|y)))] corresponding to the first loss and a second setting loss function E[logD(x|y)] corresponding to the second loss; based on the first setting loss function E[log(1-D(G(z|y)))], calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data; based on the second setting loss function E[logD(x|y)], calculating the second loss corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data for judging whether the energy consumption simulation evaluation is true or false. Among them, G represents the preset energy consumption simulation evaluation generation network, D represents the preset energy consumption simulation evaluation identification network, z represents random noise, D(G(z|y)) is the judgment probability corresponding to the generated energy consumption simulation evaluation; E represents expectation; the historical usage time, historical electricity consumption data and / or gas consumption data corresponding to the known condition y, and x represents the actual energy consumption evaluation corresponding to the energy consumption simulation evaluation.

[0106] In the embodiments of the present disclosure and other possible embodiments, constructing a first set loss function corresponding to the first loss includes: calculating the difference 1-D(G(z|y)) between the set value and the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data; taking the logarithm of the difference to obtain the difference logarithm log(1-D(G(z|y))); calculating the first expected value E[log(1-D(G(z|y)))] of the difference logarithm log(1-D(G(z|y))) to construct the first set loss function corresponding to the first loss; wherein, the set value is configured to be 1.

[0107] In the embodiments of the present disclosure and other possible embodiments, the construction of a first set loss function corresponding to the first loss includes: taking the logarithm of the discrimination probability value D(x|y) for discriminating whether the energy consumption simulation evaluation is true or false corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data, to obtain the discrimination logarithm value logD(x|y); calculating the second expected value E[logD(x|y)] of the logarithm value, and constructing a second set loss function corresponding to the second loss.

[0108] In the embodiment of the present disclosure and other possible embodiments, the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data and the second loss corresponding to the true or false judgment of the energy consumption simulation evaluation are calculated, and a preset energy consumption simulation evaluation generation network is trained to obtain a preset energy consumption simulation evaluation generator, including: constructing the objective function E[logD(x|y)]+E[log(1-D(G(z|y)))] corresponding to the preset energy consumption simulation evaluation generation network and the preset energy consumption simulation evaluation identification network based on a first setting loss function corresponding to the first loss and a second setting loss function corresponding to the second loss; maximizing the first expected value of the first setting loss function corresponding to the first loss in the objective function and minimizing the second expected value of the second setting loss function corresponding to the second loss in the objective function, that is:

[0109] m G inm D axE[logD(x|y)]+E[log(1-D(G(z|y)))], train the preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator.

[0110] In the embodiments of the present disclosure and other possible embodiments, known prior conditions corresponding to random noise under the conditions of the historical usage time, the historical electricity consumption data and / or the gas consumption data are added to control the generation process of the conditional generation adversarial network based on the preset energy consumption simulation evaluation generation network and the preset energy consumption simulation evaluation identification network.

[0111] In the embodiments of the present disclosure and other possible embodiments, the preset energy consumption simulation evaluation generation network includes: a first energy consumption evaluation shallow feature extraction module, an encoder connected to the shallow feature extraction module, and a decoder connected to the shallow feature extraction module and the encoder respectively; wherein the shallow feature extraction module is used to extract the first energy consumption evaluation shallow feature of the historical usage time, the historical electricity consumption data and / or gas consumption data, and the random noise under the conditions of the historical usage time, the historical electricity consumption data and / or gas consumption data; the encoder is used to extract the first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature corresponding to the first energy consumption evaluation shallow feature; the decoder is used to generate an energy consumption simulation evaluation based on the first energy consumption evaluation shallow feature and its corresponding first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature.

[0112] In the embodiment of the present disclosure and other possible embodiments, the shallow feature extraction module includes: a first set convolutional neural unit corresponding to the first energy consumption evaluation shallow feature for extracting the historical usage time, the historical electricity consumption data and / or gas consumption data, and random noise under the conditions of the historical electricity consumption data and / or gas consumption data. The first set convolutional neural unit includes at least one one-dimensional convolutional layer or multiple cascaded one-dimensional convolutional layers.

[0113] In the embodiments of the present disclosure and other possible embodiments, the encoder includes: a first dense feature extraction module and a second dense feature extraction module connected to the first dense feature extraction module; wherein the first dense feature extraction module includes: a second set convolution neural unit, a third set convolution neural unit connected to the second set convolution neural unit, the first set batch normalization unit connected to the third set convolution neural unit, and a first set activation function connected to the first set batch normalization unit; wherein the input of the second set convolution neural unit is configured as the first energy consumption evaluation shallow feature, and the output of the first set activation function is configured as the first energy consumption evaluation deep feature; the second dense feature extraction module includes: a fourth set convolution neural unit, a fifth set convolution neural unit connected to the fourth set convolution neural unit, and a fifth set activation function connected to the fifth set convolution neural unit. The second set batch normalization unit connected to the set convolution neural unit and the second set activation function connected to the second set batch normalization unit are set; a first jump connection unit is configured between the input of the fourth set convolution neural unit, the input of the second set convolution neural unit, and the output of the third set convolution neural unit; the first jump connection unit is used to splice the first energy consumption evaluation shallow feature and the processing feature output by the third set convolution neural unit to obtain a first splicing feature; the first splicing feature is configured as the input of the fourth set convolution neural unit, and the output of the second set activation function is configured as the second energy consumption evaluation deep feature; wherein the second set convolution neural unit, the third set convolution neural unit, the fourth set convolution neural unit, and the fifth set convolution neural unit include at least one one-dimensional convolution layer or multiple cascaded one-dimensional convolution layers.

[0114] In the embodiments of the present disclosure and other possible embodiments, a second jump connection unit is configured between the input of the second set convolutional neural unit and the input of the third set convolutional neural unit; wherein the second jump connection unit is used to splice the first energy consumption evaluation shallow feature and the processing feature output by the second set convolutional neural unit to obtain a second splicing feature; the second splicing feature is configured as the input of the third set convolutional neural unit.

[0115] In the embodiments of the present disclosure and other possible embodiments, a third jump connection unit is configured between the input of the fourth setting convolutional neural unit and the input of the fifth setting convolutional neural unit; wherein the third jump connection unit is used to splice the splicing feature with the processing feature output by the fourth setting convolutional neural unit to obtain a third splicing feature; the third splicing feature is configured as the input of the fifth setting convolutional neural unit.

[0116] In the embodiments of the present disclosure and other possible embodiments, the decoder includes: a sixth set convolutional neural unit, a feature self-attention module connected to the sixth set convolutional neural unit, and a linear layer connected to the feature self-attention module; wherein the sixth set convolutional neural unit is used to perform convolution processing on the shallow features of the first energy consumption evaluation to obtain the shallow features of the second energy consumption evaluation; the feature self-attention module is used to perform self-attention processing on the shallow features of the second energy consumption evaluation, the deep features of the first energy consumption evaluation, and the deep features of the second energy consumption evaluation to obtain self-attention features; the linear layer is used to perform linear processing on the self-attention features to generate the energy consumption simulation evaluation; wherein the sixth set convolutional neural unit includes at least one one-dimensional convolutional layer or multiple cascaded one-dimensional convolutional layers.

[0117] In the embodiments of the present disclosure and other possible embodiments, the feature self-attention module includes: a channel attention module and a spatial attention module connected to the channel attention module; wherein the channel attention module is used to perform channel attention processing on the second energy consumption evaluation shallow features, the first energy consumption evaluation deep features and the second energy consumption evaluation deep features to obtain channel attention features; the spatial attention module is used to perform spatial attention processing on the spatial attention features to obtain self-attention features.

[0118] In the embodiments of the present disclosure and other possible embodiments, before the channel attention module is used to perform channel attention processing on the second energy consumption evaluation shallow features, the first energy consumption evaluation deep features and the second energy consumption evaluation deep features, the second energy consumption evaluation shallow features, the first energy consumption evaluation deep features and the second energy consumption evaluation deep features are spliced ​​to obtain spliced ​​features to be processed; the channel attention module is used to perform channel attention processing on the spliced ​​features to be processed to obtain channel attention features.

[0119] In the embodiment of the present disclosure and other possible embodiments, the channel attention module includes: a first pooling unit and a second pooling unit different from the first pooling unit, a shared multi-layer perceptron connected to the first pooling unit and the second pooling unit respectively, an adder connected to the shared multi-layer perceptron, a third set activation function connected to the adder and a first multiplier; wherein the first pooling unit and the second pooling unit respectively perform pooling operations on the unprocessed splicing features corresponding to the second energy consumption evaluation shallow features, the first energy consumption evaluation deep features and the second energy consumption evaluation deep features, to obtain the first pooling features and the second pooling features. feature; the shared multi-layer perceptron is used to perform weight processing on the first pooling feature and the second pooling feature respectively to obtain a first weight feature and a second weight feature; the adder is used to perform addition processing on the first weight feature and the second weight feature to obtain an addition feature; the third set activation function is used to perform nonlinear processing on the addition feature to obtain a channel attention weight; the first multiplier is used to perform multiplication processing on the channel attention weight and the splicing feature to be processed to obtain a channel attention feature; wherein, the first pooling unit is configured as a maximum pooling layer, and the second pooling unit is configured as a mean pooling layer.

[0120] In the embodiments of the present disclosure and other possible embodiments, the spatial attention module includes: a third pooling unit, a fourth pooling unit connected to the third pooling unit and a convolution layer connected to the fourth pooling unit, a fourth set activation function connected to the convolution layer and a second multiplier; wherein, the third pooling unit and the fourth pooling unit are used in sequence to perform pooling processing on the channel attention features to obtain third pooling features; the convolution layer is used to perform convolution processing on the third pooling features to obtain convolution features; the fourth set activation function is used to perform nonlinear processing on the convolution features to obtain spatial attention weights; the second multiplier is used to perform multiplication processing on the channel attention features and the spatial attention weights to obtain self-attention features; wherein, the third pooling unit is configured as a maximum pooling layer, and the fourth pooling unit is configured as a mean pooling layer.

[0121] In the embodiments of the present disclosure and other possible embodiments, the linear layer connected to the feature self-attention module includes: a first linear layer and a second linear layer connected to the first linear layer; wherein the second linear layer is used to perform linear processing on the linear features of the self-attention features based on the first linear layer, and then perform linear processing to generate the energy consumption simulation evaluation.

[0122] In the embodiments of the present disclosure and other possible embodiments, the preset energy consumption simulation evaluation identification network includes: at least one convolutional correlation weight module or multiple cascaded convolutional correlation weight modules; wherein, the convolutional correlation weight module is used to use the historical usage time, the historical electricity consumption data and / or gas consumption data, the random noise under the conditions of the historical electricity consumption data and / or gas consumption data, and the energy consumption evaluation corresponding to the historical electricity consumption data and / or gas consumption data to train the preset energy consumption simulation evaluation generation network; wherein, the number of the multiple cascaded convolutional correlation weight modules can be configured to be 3.

[0123] In the embodiment of the present disclosure and other possible embodiments, each of the convolutional correlation weight modules includes: a seventh setting convolutional neural unit, a feature self-attention unit connected to the seventh setting convolutional neural unit, a third setting batch normalization unit connected to the feature self-attention unit, and a fifth setting activation function connected to the third setting batch normalization unit; wherein the seventh setting convolutional neural unit is used to perform an activation function on the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption evaluation and reservoir quality pseudo-evaluation corresponding to the historical usage time and the historical electricity consumption data and / or gas consumption data, or the correlation weight feature output by the previous level convolutional correlation weight module Convolution processing; obtaining convolution features to be judged; the feature self-attention unit is used to perform self-attention processing on the convolution features to be judged, and obtain self-attention features to be judged; the third setting batch normalization unit is used to perform batch normalization processing on the self-attention features to be judged, and obtain batch normalized features to be judged; the fifth setting activation function is used to perform nonlinear processing on the batch normalized features to be judged, and obtain the discrimination result corresponding to each of the convolution correlation weight modules; wherein, the seventh setting convolution neural unit includes at least one one-dimensional convolution layer or multiple cascaded one-dimensional convolution layers; wherein, the discrimination result is configured as true or false corresponding to the energy consumption simulation evaluation and / or the energy consumption evaluation.

[0124] In the embodiments of the present disclosure and other possible embodiments, a jump connection unit is provided between the inputs of each of the convolutional correlation weight modules; wherein the jump connection unit is used to splice the discrimination result corresponding to the output of the previous-level convolutional correlation weight module with the input features of the previous-level convolutional correlation weight module to obtain the correlation weight splicing features of the next-level convolutional correlation weight module.

[0125] In the embodiments of the present disclosure and other possible embodiments, feature extraction of the historical usage time, the historical electricity consumption data and / or gas consumption data, and the random noise under the conditions of the historical electricity consumption data and / or gas consumption data is better achieved. Among them, the shallow features of energy consumption evaluation are first obtained by using the first set convolutional neural unit, and then the shallow features of energy consumption evaluation are input into the dense feature extraction module to enhance the feature learning ability of limited data, obtain the deep features of energy consumption evaluation, and realize the encoding of input features. Then, the shallow features of energy consumption evaluation and the deep features of energy consumption evaluation are fused through the hybrid attention module. The fused features will be used to generate predictions of energy consumption through two linear network layers to realize the decoding of input features. Secondly, the input data is feature learned using 3 layers of set convolutional neural units and feature self-attention mechanism, and the original data and the extracted features are then spliced. After that, it is judged through 2 linear layers whether the input data comes from the preset energy consumption simulation evaluation generator or real data. Finally, through the continuous confrontation between the preset energy consumption simulation evaluation generator and the preset energy consumption simulation evaluation identification network model, the preset energy consumption simulation evaluation generator has a better data generation capability, so that the preset energy consumption simulation evaluation generator model can be used to implement the quality evaluation of unknown energy consumption. Among them, the preset energy consumption simulation evaluation identification network judges the actual energy consumption evaluation as true and judges the generated energy consumption simulation evaluation that is inconsistent with the actual energy consumption evaluation as false.

[0126] In the embodiments of the present disclosure and other possible embodiments, during the training process, the preset energy consumption simulation evaluation generator and the preset energy consumption simulation evaluation identification network need to be optimized and trained at the same time, and the two promote each other and improve together through adversarial games. Specifically, the goal of the preset energy consumption simulation evaluation generator is to continuously optimize network parameters and improve the quality of the generated energy consumption simulation evaluation, so that the preset energy consumption simulation evaluation identification network cannot judge whether it is true or false, that is, it is hoped that the preset energy consumption simulation evaluation identification network will maximize the probability of judging the generated energy consumption simulation evaluation as true. The preset energy consumption simulation evaluation identification network needs to continuously minimize the classification error rate of the input data, that is, maximize the difference between its probability of distinguishing the true energy consumption evaluation and the probability of distinguishing the generated data.

[0127] In the embodiments of the present disclosure and other possible embodiments, by jointly optimizing the objective functions of the preset energy consumption simulation evaluation generator and the preset energy consumption simulation evaluation identification network, the training goal is to find a Nash equilibrium point of the preset energy consumption simulation evaluation generator and the preset energy consumption simulation evaluation identification network, so that the energy consumption simulation evaluation generated by the preset energy consumption simulation evaluation generator is sufficiently realistic, and the preset energy consumption simulation evaluation identification network cannot distinguish between the real energy consumption evaluation and the generated energy consumption simulation evaluation.

[0128] In the embodiments of the present disclosure and other possible embodiments, during the training process, the preset energy consumption simulation evaluation generator and the preset energy consumption simulation evaluation identification network are updated alternately. First, the preset energy consumption simulation evaluation identification network is trained using real data and generated data, and the preset energy consumption simulation evaluation identification network parameters are updated so that the preset energy consumption simulation evaluation identification network can better distinguish between real energy consumption evaluations and generated energy consumption simulation evaluations. Secondly, the preset energy consumption simulation evaluation identification network parameters are fixed, and the preset energy consumption simulation evaluation generator parameters are updated so that the preset energy consumption simulation evaluation generator generates a more realistic energy consumption evaluation, and the probability that the preset energy consumption simulation evaluation identification network determines that the generated data is real is increased. Finally, through continuous alternating updates and optimizations, the recognition error rate of the preset energy consumption simulation evaluation identification network is increased, the preset energy consumption simulation evaluation generator can estimate the distribution of energy consumption simulation evaluations, and the generated energy consumption simulation evaluations are more realistic.

[0129] In the embodiments of the present disclosure and other possible embodiments, a conditional generative adversarial network (CGN) can effectively utilize given conditional constraint information, transforming the probabilities of a GAN into conditional probabilities. During the implementation using the CGN, the historical usage time, electricity consumption data, and / or gas consumption data corresponding to the conditions in the conditional probabilities are output as energy consumption estimates.

[0130] In the embodiments of the present disclosure and other possible embodiments, in order to better apply the conditional generative adversarial network directly to the energy consumption evaluation process, that is, under the conditions of historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of multiple set energy-consuming devices in a given factory operating state, the model can give an energy consumption evaluation under the corresponding conditions.

[0131] In the embodiments of the present disclosure and other possible embodiments, the preset energy consumption simulation evaluation generation network includes: an encoder and a decoder to complete the dense extraction of features. Among them, the dense feature extraction preset energy consumption simulation evaluation generator model takes potential noise and the historical usage time, historical electricity consumption data and / or gas consumption data as conditional constraints as input. For the historical usage time, the historical electricity consumption data and / or gas consumption data and the random noise under the conditions of the historical electricity consumption data and / or gas consumption data, a layer of set convolutional neural units (the first set convolutional neural unit) is used to obtain the first energy consumption evaluation shallow feature of the input data that is not encoded, and then the first energy consumption evaluation shallow feature is input into the designed dense feature extraction module to obtain the encoded first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature, thereby realizing the encoding of the input feature. Afterwards, the unencoded shallow features of the first energy consumption evaluation are again extracted by a set convolutional neural unit and fused with the deep features of the first energy consumption evaluation and the deep features of the second energy consumption evaluation through an attention module. The fused features will continue to be generated and predicted through the first linear layer and the second linear layer corresponding to the two cascaded linear network layers to realize the decoding of the input features and obtain the energy consumption simulation evaluation.

[0132] In the embodiment of the present disclosure and other possible embodiments, the entire encoder is mainly composed of two cascaded energy consumption evaluation dense feature modules. Each energy consumption evaluation dense feature module includes: the second set convolution neural unit and the third set convolution neural unit corresponding to the two layers of set convolution neural units, or the fourth set convolution neural unit and the fifth set convolution neural unit, the first set batch normalization unit or the second set batch normalization unit, and the first set activation function ReLU or the second set activation function ReLU corresponding to the set activation function layer. In order to effectively realize the dense extraction between data and enhance the feature extraction effect, the module establishes the second jump connection unit or the third jump connection unit corresponding to the residual link between the two layers of set convolution neural units, and splices the input features and the output features of the second set convolution neural unit or the fourth set convolution neural unit corresponding to the first layer of set convolution neural units in the channel dimension, and together serve as the input of the dense module to the third set convolution neural unit or the fifth set convolution neural unit corresponding to the second layer of set convolution neural units. After being processed by the third set convolutional neural unit or the fifth set convolutional neural unit corresponding to the set convolutional neural unit, the features will sequentially pass through the first set batch normalization unit or the second set batch normalization unit corresponding to the BN layer and the first set activation function or the second set activation function corresponding to the ReLU layer. The first set batch normalization unit or the second set batch normalization unit corresponding to the BN layer) normalizes the feature distribution. Finally, the output result of the single energy consumption evaluation intensive feature module is obtained.

[0133] In the embodiments of the present disclosure and other possible embodiments, in order to further realize intensive feature extraction, data transmission is also realized in the same way in the two intensive modules. The output features of the previous energy consumption evaluation intensive feature module will be used together with the input data as the input of the next energy consumption evaluation intensive feature module through feature splicing (a second jump connection unit is configured between the input of the second setting convolution neural unit and the input of the third setting convolution neural unit; wherein, the second jump connection unit is used to splice the first energy consumption evaluation shallow feature and the processing feature output by the second setting convolution neural unit to obtain a second splicing feature; the second splicing feature is configured as the input of the third setting convolution neural unit). Through such cascaded feature transfer, the subsequent modules can directly use the feature information extracted by the previous modules, which significantly improves the utilization rate of the features and can also realize the fusion of multi-level features, so that the network can simultaneously utilize shallow local features and deep global features. Finally, the outputs of the two energy consumption evaluation intensive feature modules are spliced ​​together to provide part of the input for the subsequent decoder (a first jump connection unit is configured between the input of the fourth setting convolutional neural unit, the input of the second setting convolutional neural unit, and the output of the third setting convolutional neural unit; the first jump connection unit is used to splice the first energy consumption evaluation shallow feature and the processing feature output of the third setting convolutional neural unit to obtain a first spliced ​​feature; the first spliced ​​feature is configured as the input of the fourth setting convolutional neural unit).

[0134] In the embodiments of the present disclosure and other possible embodiments, for the decoder, the first shallow feature of energy consumption evaluation extracted by the first set convolutional neural unit corresponding to the set convolutional neural unit is input into the encoder and the decoder. The shallow feature of the first energy consumption evaluation is further extracted by the sixth set convolutional neural unit corresponding to a layer of set convolutional neural units to obtain the shallow feature of the second energy consumption evaluation. Afterwards, the extracted shallow feature of the second energy consumption evaluation and the first deep feature of energy consumption evaluation and the second deep feature of energy consumption evaluation from the encoder are fused together through the convolutional attention mechanism module to improve the model's ability to pay attention to features at different levels and achieve effective fusion of features. Finally, the fused features are sequentially input into the first linear layer and the second linear layer corresponding to the two-layer linear network layer to achieve the generation prediction of the preset energy consumption simulation evaluation and obtain the energy consumption simulation evaluation.

[0135] In the embodiments of the present disclosure and other possible embodiments, the convolutional attention mechanism module performs attention mechanism operations on the channel and spatial dimensions, so that the network pays more attention to important channel features and spatial position features, suppresses unnecessary channel and spatial position features, and increases the network's ability to capture input features.

[0136] In the embodiments of the present disclosure and other possible embodiments, channel attention is a method that compresses the spatial dimension through a pooling layer and focuses on the importance of each feature map channel, aiming to enhance the feature expression capability between different channels. First, the channel attention weight is calculated by the maximum pooling operation corresponding to the first pooling unit and the average pooling operation corresponding to the second pooling unit on each channel, respectively, to calculate the maximum feature corresponding to the first pooling feature and the average feature corresponding to the second pooling feature. Secondly, the obtained feature vector is passed through a shared multi-layer perceptron to learn the first weight feature and the second weight feature corresponding to the weight parameter of each channel. Finally, the channel attention weight is obtained by normalizing it with a third set activation function σ (such as Sigmoid), and multiplying it with the unprocessed splicing feature obtained by splicing the second energy consumption evaluation shallow feature, the first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature to achieve weight adjustment of different channels.

[0137] In the embodiments of the present disclosure and other possible embodiments, spatial attention is an important method for enhancing the representation ability of the network in the spatial dimension. It mainly identifies important features in each spatial position, making up for the limitations of channel attention in spatial position. First, the channel attention features are compressed by the average pooling corresponding to the fourth pooling unit and the maximum pooling corresponding to the third pooling unit to obtain the third pooling features and the fourth pooling features. Then, the third pooling features and the fourth pooling features obtained by the average pooling and the maximum pooling are spliced ​​through a splicing operation to obtain the third pooling features, or the third pooling unit and the fourth pooling unit are used in turn to perform pooling processing on the channel attention features to obtain the third pooling features; the channel information is fused using the 7*7 convolution kernel corresponding to the convolution layer to obtain the convolution features.

[0138] In the embodiments of the present disclosure and other possible embodiments, in the attention module, the first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature from the encoder and the second energy consumption evaluation shallow feature extracted from the decoder are used as input (i.e., the second energy consumption evaluation shallow feature, the first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature are spliced ​​together to obtain the unprocessed spliced ​​feature). The channel attention is first used to calculate the different channel weights to obtain the channel attention weights, which are then multiplied by the input features to obtain the channel attention features. Then, using this as input, the weights of different spatial positions are calculated to obtain the spatial attention weights, which are then multiplied by the unprocessed spliced ​​features to complete the final self-attention features. The use of the attention module can achieve the effective fusion of the second energy consumption evaluation shallow feature and the first energy consumption evaluation deep feature and the second energy consumption evaluation deep feature, complete the extraction of the importance of features at different levels, and extract information at different spatial positions, enhance the overall representation capability of the preset energy consumption simulation evaluation preset energy consumption simulation evaluation generation network, and achieve the generation of high-quality energy consumption simulation evaluation, thereby achieving accurate evaluation of energy consumption.

[0139] In the embodiments of the present disclosure and other possible embodiments, a preset energy consumption simulation evaluation network includes: one layer of set convolutional neural units and two layers of linear connection layers configured in a convolutional correlation weight module, that is, at least one convolutional correlation weight module or multiple cascaded convolutional correlation weight modules are followed by at least one linear layer. For example, at least one convolutional correlation weight module or multiple cascaded convolutional correlation weight modules are followed by two linear layers, respectively configured as a third linear layer and a fourth linear layer connected to the third linear layer. In the convolutional correlation weight module, after the seventh set convolutional neural unit corresponding to each layer of the set convolutional neural unit, the feature self-attention module corresponding to the feature self-attention unit, the third set batch normalization unit, and the ReLU set activation function (the fifth set activation function) are sequentially added. The feature self-attention unit enhances the expressive power of important features by calculating the correlation weights between features; the third set batch normalization unit is used to stabilize the feature distribution and accelerate convergence; the fifth set activation function introduces nonlinear transformation capabilities.

[0140] In the embodiments of the present disclosure and other possible embodiments, the preset energy consumption simulation evaluation and identification network adopts a dual-input design. The first input is configured as a first joint feature obtained by concatenating the actual energy consumption evaluation with the historical usage time, historical electricity consumption data and / or gas consumption data corresponding to the known conditions, and the energy consumption evaluation corresponding to the historical electricity consumption data and / or gas consumption data. The other input is a second joint feature obtained by concatenating the energy consumption simulation evaluation generated by the preset energy consumption simulation evaluation generator with the historical usage time, historical electricity consumption data and / or gas consumption data corresponding to the known conditions, and the energy consumption simulation evaluation corresponding to the historical electricity consumption data and / or gas consumption data. During the training process, after the first joint feature passes through the preset energy consumption simulation evaluation and identification network, a binary cross-entropy loss function is used to calculate the probability of it being identified as a real sample. Simultaneously, the second joint feature is also processed by the same preset energy consumption simulation evaluation and identification network, and the cross-entropy loss function is used to calculate the probability of it being identified as a generated sample. This adversarial training mechanism forces the preset energy consumption simulation evaluation and identification network to continuously improve its discrimination ability, while also promoting the preset energy consumption simulation evaluation and preset energy consumption simulation evaluation generation network to improve its generation quality.

[0141] In the embodiments of the present disclosure and other possible embodiments, no strict distinction is made between the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment within a set time interval and their corresponding historical energy consumption evaluation, and the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment within the set time interval and their corresponding historical energy consumption evaluation corresponding to the second moment after the first moment. However, the process of training the preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator in the energy consumption simulation method based on the plant operating status and the energy consumption prediction method based on the plant operating status corresponding to the embodiments of the present disclosure is the same.

[0142] In the embodiments of the present disclosure and other possible embodiments, the energy consumption prediction method based on the plant operating status also includes: using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of the multiple set energy-consuming devices in the plant operating status and its corresponding historical energy consumption evaluation to train the preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator; based on the preset energy consumption simulation evaluation generator, using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of the multiple set energy-consuming devices in the plant operating status to generate a corresponding energy consumption simulation evaluation.

[0143] The execution subject of the energy consumption simulation and prediction method based on the plant operation status may be an energy consumption simulation and prediction device or system based on the plant operation status. For example, the energy consumption simulation and prediction method based on the plant operation status may be executed by a terminal device, a server, or other processing device, wherein the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the energy consumption simulation and prediction method based on the plant operation status may be implemented by a processor calling computer-readable instructions stored in a memory.

[0144] Those skilled in the art will understand that in the above-mentioned energy consumption simulation and prediction method based on the plant operating status in the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0145] Figure 3 FIG. 1 shows a schematic diagram of an energy consumption simulation system based on a factory operation state according to an embodiment of the present disclosure. Figure 3 As shown, an embodiment of the present disclosure further provides an energy consumption simulation system based on the operation status of a factory, including: a first training unit 101, used to train a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data and its corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consumption devices in the operation status of the factory, to obtain the preset energy consumption simulation evaluation generator; 102 simulation evaluation unit, used to generate a corresponding energy consumption simulation evaluation based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of a plurality of set energy consumption devices in the operation status of the factory.

[0146] An embodiment of the present disclosure also provides an energy consumption simulation system based on the operating status of a factory, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption simulation method based on the operating status of the factory.

[0147] An embodiment of the present disclosure also provides an energy consumption simulation system based on the operating status of a plant, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to call the instructions stored in the memory to implement the above-mentioned energy consumption simulation method based on the operating status of the plant.

[0148] An embodiment of the present disclosure also provides an energy consumption simulation system based on the plant operating status, including: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption simulation method based on the plant operating status as described above is implemented.

[0149] An embodiment of the present disclosure also provides an energy consumption simulation device based on the operating status of a factory, including: a first training unit, used to train a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data and its corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consumption devices in the operating status of the factory, to obtain the preset energy consumption simulation evaluation generator; a simulation evaluation unit, used to generate a corresponding energy consumption simulation evaluation based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of a plurality of set energy consumption devices in the operating status of the factory.

[0150] An embodiment of the present disclosure also provides an energy consumption simulation device based on the operating status of a factory, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption simulation method based on the operating status of the factory.

[0151] An embodiment of the present disclosure also provides an energy consumption simulation device based on the operating status of a factory, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to implement the above-mentioned energy consumption simulation method based on the operating status of the factory.

[0152] An embodiment of the present disclosure further provides an energy consumption simulation device based on the operating status of a plant, comprising: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption simulation method based on the operating status of a plant as described above is implemented.

[0153] Figure 4 FIG. 1 shows a schematic diagram of an energy consumption prediction system based on factory operation status according to an embodiment of the present disclosure. Figure 4As shown, an embodiment of the present disclosure also provides an energy consumption prediction system based on the operation status of a factory, including: a second training unit 201, used to train a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in a set time interval of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the factory, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; an energy consumption evaluation prediction unit 202, used to predict the energy consumption evaluation corresponding to the fourth moment after the third moment based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the factory.

[0154] An embodiment of the present disclosure also provides an energy consumption prediction system based on the operating status of a factory, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the factory.

[0155] An embodiment of the present disclosure also provides an energy consumption prediction system based on the operating status of a plant, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the plant.

[0156] An embodiment of the present disclosure also provides an energy consumption prediction system based on the plant operating status, including: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption prediction method based on the plant operating status as described above is implemented.

[0157] An embodiment of the present disclosure also provides an energy consumption prediction device based on the operation status of a factory, including: a second training unit, used to train a preset energy consumption simulation evaluation generation network by using the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in a set time interval of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the factory, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; an energy consumption evaluation prediction unit, used to predict the energy consumption evaluation corresponding to the fourth moment after the third moment based on the preset energy consumption simulation evaluation generator by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to the third moment of each set energy consumption device in the operation status of a plurality of set energy consumption devices in the factory.

[0158] An embodiment of the present disclosure also provides an energy consumption prediction device based on the operating status of a factory, comprising: an electronic device configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the factory.

[0159] An embodiment of the present disclosure also provides an energy consumption prediction device based on the operating status of a plant, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned energy consumption prediction method based on the operating status of the plant.

[0160] An embodiment of the present disclosure also provides an energy consumption prediction device based on the operating status of a plant, comprising: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption prediction method based on the operating status of the plant as described above is implemented.

[0161] An embodiment of the present disclosure further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the above-mentioned energy consumption simulation method based on the plant operating status.

[0162] An embodiment of the present disclosure further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the above-mentioned energy consumption prediction method based on the plant operating status.

[0163] An embodiment of the present disclosure further provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the above-mentioned energy consumption simulation method based on the plant operating status and the above-mentioned energy consumption prediction method based on the plant operating status.

[0164] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the energy consumption simulation and prediction method based on the factory operating status described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0165] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0166] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions. The electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0167] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0168] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0169] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for simulating energy consumption based on plant operation status, characterized in that: include: The preset energy consumption simulation evaluation generator is obtained by training a preset energy consumption simulation evaluation generation network using historical usage time, historical electricity consumption data, and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consumption devices in a factory operating state, and the corresponding historical energy consumption evaluation; Based on the preset energy consumption simulation evaluation generator, the corresponding energy consumption simulation evaluation is generated using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each set energy consumption equipment in the multiple set energy consumption equipment under the factory operation state.

2. The energy consumption simulation method based on the plant operation status according to claim 1 is characterized in that: The method utilizes the historical usage time, historical electricity consumption data and / or historical gas consumption data and the corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval of each of the multiple set energy consumption devices in the factory operation state to train the preset energy consumption simulation evaluation generation network to obtain the preset energy consumption simulation evaluation generator, including: configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data as a classification feature vector; configuring the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or historical gas consumption data as a classification training label corresponding to the classification feature vector; using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; calculating the loss value corresponding to the training process energy consumption simulation evaluation and the classification training label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator; and / or, The method of calculating the loss value corresponding to the energy consumption simulation evaluation of the training process and the label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator, includes: if the loss value corresponding to the energy consumption simulation evaluation of the training process and the label is less than or equal to the preset loss value within a set number of training times, then completing the training of the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator; and / or, Before training the preset energy consumption simulation evaluation generation network, a connection to a host computer database is established through an industrial bus, and the industrial bus is used to obtain from the host computer database the historical usage time, historical electricity consumption data and / or historical gas consumption data and the corresponding historical energy consumption evaluation corresponding to at least one collection moment within a set time interval for each of the multiple set energy consumption devices in the factory operation state.

3. The energy consumption simulation method based on plant operation status according to claim 2 is characterized in that: The method of using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation includes: obtaining random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data; configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise as a classification feature vector; configuring the energy consumption evaluation corresponding to the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise as a classification training label corresponding to the classification feature vector; using the classification feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; and / or, Before using the classification feature vector to train the preset energy consumption simulation evaluation generation network, the classification feature vector is standardized to obtain a standardized classification feature vector; the preset energy consumption simulation evaluation generation network is trained using the standardized classification feature vector; and / or, The calculation of the loss value corresponding to the energy consumption simulation evaluation of the training process and the classification training label includes: based on a preset energy consumption simulation evaluation identification network, using the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation, to determine whether the energy consumption simulation evaluation is true or false; calculating a first loss of the energy consumption simulation evaluation corresponding to random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data and a second loss corresponding to determining whether the energy consumption simulation evaluation is true or false, and training the preset energy consumption simulation evaluation generation network; and / or, The preset energy consumption simulation evaluation and identification network configuration is one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.

4. A method for predicting energy consumption based on plant operation status, characterized in that: include: The preset energy consumption simulation evaluation generation network is trained using the historical usage time, historical electricity consumption data, and / or historical gas consumption data corresponding to the first moment in a set time interval for each of the multiple set energy consumption devices in the factory operation state, and the historical energy consumption evaluation corresponding to the second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; Based on the preset energy consumption simulation evaluation generator, the energy consumption evaluation corresponding to the fourth moment after the third moment is predicted by using the current usage time, current electricity consumption data and / or current gas consumption data corresponding to each of the multiple set energy consumption devices in the factory operation state at the third moment.

5. The energy consumption simulation method based on plant operation status according to claim 4 is characterized in that: The preset energy consumption simulation evaluation generator is obtained by training a preset energy consumption simulation evaluation generation network using historical usage time, historical electricity consumption data, and / or historical gas consumption data corresponding to a first moment in a set time interval for each of a plurality of set energy consumption devices in a factory operating state, and a historical energy consumption evaluation corresponding to a second moment after the first moment, including: The historical usage time, the historical electricity consumption data and / or the historical gas consumption data corresponding to the first moment are configured as a prediction feature vector; the historical energy consumption evaluation corresponding to the second moment after the first moment is configured as a prediction training label corresponding to the prediction feature vector; the preset energy consumption simulation evaluation generation network is trained using the prediction feature vector to obtain the corresponding training process energy consumption simulation evaluation; the loss value corresponding to the training process energy consumption simulation evaluation and the prediction training label is calculated, and then the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator is trained.

6. The energy consumption simulation method based on plant operation status according to claim 4 or 5, characterized in that: The method of calculating the loss value corresponding to the energy consumption simulation evaluation of the training process and the label, and then training the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator, includes: if the loss value corresponding to the energy consumption simulation evaluation of the training process and the label is less than or equal to the preset loss value within a set number of training times, then completing the training of the preset energy consumption simulation evaluation generation network corresponding to the preset energy consumption simulation evaluation generator; and / or, Before training the preset energy consumption simulation evaluation generation network, a connection is established between an upper computer database and an industrial bus, and the industrial bus is used to obtain from the upper computer database the historical usage time, historical electricity consumption data and / or historical gas consumption data corresponding to the first moment in the set time interval for each of the multiple set energy consuming devices in the factory operation state, as well as the historical energy consumption evaluation corresponding to the second moment after the first moment; and / or, The use of the predicted feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation includes: obtaining random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data corresponding to the first moment; configuring the historical usage time, the historical electricity consumption data and / or historical gas consumption data, and the random noise corresponding to the first moment as a predicted feature vector; configuring the energy consumption evaluation corresponding to the second moment as a predicted training label corresponding to the predicted feature vector; using the predicted feature vector to train the preset energy consumption simulation evaluation generation network to obtain the corresponding training process energy consumption simulation evaluation; and / or, Before using the predicted feature vector to train the preset energy consumption simulation evaluation generation network, the method includes: normalizing the predicted feature vector to obtain a standardized predicted feature vector; using the standardized predicted feature vector to train the preset energy consumption simulation evaluation generation network; and / or, The calculation of the energy consumption simulation evaluation of the training process and the loss value corresponding to the predicted training label includes: based on a preset energy consumption simulation evaluation identification network, using the historical usage time, the historical electricity consumption data and / or gas consumption data, the energy consumption simulation evaluation and the energy consumption evaluation, to determine whether the energy consumption simulation evaluation is true or false; calculating the first loss of the energy consumption simulation evaluation corresponding to the random noise under the conditions of the historical electricity consumption data and / or historical gas consumption data and the second loss corresponding to determining whether the energy consumption simulation evaluation is true or false, and training the preset energy consumption simulation evaluation generation network.

7. The energy consumption simulation method based on the plant operation status according to any one of claims 1 to 3 or the energy consumption simulation method based on the plant operation status according to any one of claims 4 to 6, characterized in that: The energy consumption simulation evaluation and / or the energy consumption evaluation configuration is one of a high energy consumption level, a medium energy consumption level, a low energy consumption level and a normal energy consumption level; and / or, Setting a corresponding power consumption detection sensor and / or gas consumption sensor on each of the set energy consumption devices; using the corresponding power consumption detection sensor and / or gas consumption detection sensor set on each of the set energy consumption devices to collect corresponding historical power consumption data and / or historical gas consumption data, current power consumption data and / or current gas consumption data; and utilizing an industrial bus connected to a power consumption detection sensor and / or a gas consumption detection sensor provided for each of the set energy-consuming devices to send the collected historical power consumption data and / or historical gas consumption data, current power consumption data and / or current gas consumption data to a host computer database, and utilizing the host computer database to store the collected historical power consumption data and / or historical gas consumption data, current power consumption data and / or current gas consumption data; and / or, Using a timer, respectively timing the usage time corresponding to each set energy-consuming device from being turned on to being turned off, to obtain the usage time corresponding to each set energy-consuming device; The usage time corresponding to each set energy-consuming device is sent to a host computer database via an industrial bus connected to the timer, and the host computer database is used to store the usage time corresponding to each set energy-consuming device; and / or, The preset energy consumption simulation evaluation generation network configuration is one or more of support vector regression, support vector machine, K-nearest neighbor algorithm, random forest, artificial neural network, deep neural network, etc.

8. An energy consumption simulation system or energy consumption simulation device based on factory operation status, characterized in that: include: A first training unit is configured to train a preset energy consumption simulation evaluation generation network using historical usage time, historical electricity consumption data, and / or historical gas consumption data corresponding to at least one collection moment within a set time interval for each of a plurality of set energy consuming devices in a factory operating state, and their corresponding historical energy consumption evaluations, to obtain the preset energy consumption simulation evaluation generator; a simulation evaluation unit configured to generate a corresponding energy consumption simulation evaluation based on the preset energy consumption simulation evaluation generator and using the current usage time, current electricity consumption data, and / or current gas consumption data corresponding to each of the plurality of set energy consumption devices in the factory operation state; or The device comprises an electronic device, the electronic device being configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the energy consumption simulation method based on the plant operation status according to any one of claims 1 to 3 and 7; or Comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to call the instructions stored in the memory to execute the energy consumption simulation method based on the plant operation status according to any one of claims 1-3 and 7; or, The invention comprises: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption simulation method based on the plant operation status as claimed in any one of claims 1-3 and 7 is implemented.

9. An energy consumption prediction system or energy consumption prediction device based on factory operation status, characterized in that: include: A second training unit is configured to train a preset energy consumption simulation evaluation generation network using historical usage time, historical electricity consumption data, and / or historical gas consumption data corresponding to a first moment in a set time interval for each of a plurality of set energy consumption devices in a factory operating state, and a historical energy consumption evaluation corresponding to a second moment after the first moment, to obtain the preset energy consumption simulation evaluation generator; an energy consumption evaluation prediction unit, configured to predict, based on the preset energy consumption simulation evaluation generator, an energy consumption evaluation corresponding to a fourth moment after the third moment by using the current usage time, current electricity consumption data, and / or current gas consumption data corresponding to the third moment for each of the plurality of set energy consuming devices in the plant operating state; or The invention comprises: an electronic device, the electronic device being configured with a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the energy consumption prediction method based on the plant operation status according to any one of claims 4 to 7; or, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to call the instructions stored in the memory to execute the energy consumption prediction method based on the plant operation status according to any one of claims 4 to 7; or, The invention comprises: a computer program product, wherein the computer program product is provided with a computer program / instruction, and when the computer program / instruction is executed by a processor, the energy consumption prediction method based on the plant operation status as described in any one of claims 4 to 7 is implemented.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by the processor, they implement the energy consumption simulation method based on the plant operating status as described in any one of claims 1-3 and 7; and / or, when the computer program instructions are executed by the processor, they implement the energy consumption prediction method based on the plant operating status as described in any one of claims 4-7.

Images