Equipment running state adjusting method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to an equipment operation state adjusting method and device, computer equipment and a storage medium, and the method comprises the steps: respectively inputting the working time period, real-time temperature and humidity and real-time energy consumption of to-be-tested equipment into a neural network model for analysis, and obtaining an energy consumption time period trend chart of the to-be-tested equipment; and adjusting the operation state of the to-be-tested equipment in combination with the real-time energy consumption and the real-time temperature and humidity to obtain a real-time adjustment mode. Therefore, the multi-dimensional information of the to-be-tested equipment is automatically analyzed to adjust the equipment so as to optimize the running state of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, device, computer device and storage medium for adjusting the operating state of a device. Background Art

[0002] In the field of intelligent management of industrial equipment, the technology of dynamically adjusting the operating state is the core link to realize the coordinated control of energy efficiency optimization and environmental safety.

[0003] Currently, most of the adjustments of the operating state of devices usually rely on single historical energy consumption data for prediction, or on the device energy consumption monitoring method based on time series analysis. By collecting historical energy consumption data to establish a linear regression model for energy consumption prediction, but these methods lack the comprehensive analysis ability of multi-dimensional data, resulting in insufficient prediction accuracy, single energy-saving strategy, single data dimension for analysis, limited prediction target, and the system cannot dynamically adjust according to the deviation between the actual energy consumption and the predicted value.

[0004] Therefore, how to automatically analyze the multi-dimensional information of the device to be tested and adjust the device to optimize the operating state of the device has become an urgent problem to be solved. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, computer device and storage medium for adjusting the operating state of a device to solve the problem of how to automatically analyze the multi-dimensional information of the device to be tested and adjust the device to optimize the operating state of the device.

[0006] In a first aspect, embodiments of the present invention provide a method for adjusting the operating state of a device, including: Obtaining the working period of the device to be tested operating in the working area and the real-time energy consumption and real-time temperature and humidity detected by sensors in real time when the device to be tested is operating; Respectively inputting the real-time energy consumption, the working period, and the real-time temperature and humidity into a preset trained neural network model for analysis to obtain an energy consumption period trend graph of the real-time energy consumption changing with the working period; According to the energy consumption period trend graph, obtaining the period predicted energy consumption of a preset working time in the working period, obtaining the current energy consumption corresponding to the preset working time according to the real-time energy consumption, analyzing whether the current energy consumption is higher than the period predicted energy consumption, and if it is higher than the period predicted energy consumption, adjusting the operating state of the device to be tested until the real-time energy consumption is not higher than the period predicted energy consumption, and obtaining the adjusted operating state as the energy consumption adjustment mode of the device to be tested; Based on the real-time temperature and humidity, calculate the real-time heat index, analyze whether the real-time heat index meets a preset index threshold. If it does not meet the index threshold, adjust the energy consumption adjustment mode until the real-time heat index meets the index threshold, and obtain the operating state of the device under test as the real-time adjustment mode.

[0007] In a second aspect, an embodiment of the present invention provides a device operating state adjustment device, including: An information detection module, configured to obtain the working period of the device under test operating in the working area, and the real-time energy consumption and real-time temperature and humidity detected by the sensor in real time when the device under test is operating; An information analysis module, configured to input the real-time energy consumption, the working period, and the real-time temperature and humidity into a preset and trained neural network model for analysis, and obtain an energy consumption period trend graph of the real-time energy consumption changing with the working period; An energy consumption analysis module, configured to obtain the predicted energy consumption of a preset working time period in the working period according to the energy consumption period trend graph, obtain the current energy consumption corresponding to the preset working time according to the real-time energy consumption, analyze whether the current energy consumption is higher than the predicted energy consumption of the period. If it is higher than the predicted energy consumption of the period, adjust the operating state of the device under test until the real-time energy consumption is not higher than the predicted energy consumption of the period, and obtain the adjusted operating state as the energy consumption adjustment mode of the device under test; A mode determination module, configured to calculate a real-time heat index according to the real-time temperature and humidity, analyze whether the real-time heat index meets a preset index threshold. If it does not meet the index threshold, adjust the energy consumption adjustment mode until the real-time heat index meets the index threshold, and obtain the operating state of the device under test as the real-time adjustment mode.

[0008] In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above device operating state adjustment method is implemented.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above device operating state adjustment method is implemented.

[0010] The beneficial effects of the present invention compared with the prior art are as follows: By obtaining the working period during which the device under test operates in the working area, the real-time energy consumption, and the real-time temperature and humidity detected by the sensor in real time when the device under test is running, the real-time energy consumption, the working period, and the real-time temperature and humidity are respectively input into a preset and trained neural network model for analysis to obtain an energy consumption period trend graph of the real-time energy consumption varying with the working period. According to the energy consumption period trend graph, the predicted energy consumption for a preset working time in the working period is obtained. According to the real-time energy consumption, the current energy consumption corresponding to the preset working time is obtained. Analyze whether the current energy consumption is higher than the predicted energy consumption for the period. If it is higher than the predicted energy consumption for the period, adjust the operating state of the device under test until the real-time energy consumption is not higher than the predicted energy consumption for the period, and obtain the adjusted operating state as the energy consumption adjustment mode of the device under test. According to the real-time temperature and humidity, the real-time heat index is calculated, and analyze whether the real-time heat index meets the preset index threshold. If it does not meet the index threshold, adjust the energy consumption adjustment mode until the real-time heat index meets the index threshold, and obtain the operating state of the device under test as the real-time adjustment mode. By respectively inputting the working period, the real-time temperature and humidity, and the real-time energy consumption of the device under test into the neural network model for analysis, an energy consumption period trend graph of the device under test is obtained, and the operating state of the device under test is adjusted by combining the real-time energy consumption and the real-time temperature and humidity to obtain the real-time adjustment mode. Thus, the multi-dimensional information of the device under test is automatically analyzed to adjust the device so as to optimize the operating state of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic diagram of the application environment of a method for adjusting the operating state of a device provided in Embodiment 1 of the present invention; Figure 2 It is a schematic flowchart of a method for adjusting the operating state of a device provided in Embodiment 2 of the present invention; Figure 3 It is a schematic flowchart of a method for adjusting the operating state of a device provided in Embodiment 3 of the present invention; Figure 4 It is a schematic flowchart of a method for adjusting the operating state of a device provided in Embodiment 4 of the present invention; Figure 5 It is a schematic flowchart of a method for adjusting the operating state of a device provided in Embodiment 5 of the present invention; Figure 6 It is a schematic structural diagram of a device for adjusting the operating state of a device provided in Embodiment 6 of the present invention; Figure 7 It is a schematic structural diagram of a computer device provided in the seventh embodiment of the present invention. Specific embodiments

[0013] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0014] As Figure 1 shown, it is a schematic diagram of the application environment of a device operation state adjustment method provided in the first embodiment of the present invention. Among them, the client and the server are connected for communication. The user can provide conditions, requirements, operation instructions, etc. for device operation state adjustment to the server by operating the client. The server is used to execute the device operation state adjustment method of the present invention according to the relevant content sent by the client. Among them, the client includes, but is not limited to, various computer devices such as personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The computer device corresponding to the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0015] As Figure 2 shown, it is a schematic flowchart of a device operation state adjustment method provided in the second embodiment of the present invention. Among them, the device operation state adjustment method is applied to the Figure 1 server in. The device operation state adjustment method may include the following steps: Step S201, obtain the working period of the device under test running in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor in real time when the device under test is running.

[0016] Among them, the working period refers to the time period when the device under test is in the running state in its working area. It can be determined by the start and stop records of the device, such as the operation log of the device, the time record of the control system, etc. For some devices with a timing function, the preset working period can also be directly obtained from the device settings. This time period can be fixed or irregular, depending on the usage mode and business requirements of the device. For example, a production device in a factory can start running at 8:00 am and stop running at 6:00 pm every day, then its working period is from 8:00 am to 6:00 pm; for the server of an e-commerce platform, it may run continuously for 24 hours during a promotion event, and the working period is the duration of the entire promotion event.

[0017] The working period helps to analyze the operation rules and energy consumption characteristics of the device at different times, because the device may face different workloads at different times, resulting in changes in energy consumption and other operation parameters.

[0018] Among them, the real-time energy consumption refers to the energy consumed by the device under test during operation, which is detected in real time by sensors. It is collected in real time through power sensors installed in the device circuit. These sensors can measure parameters such as current and voltage, and calculate the real-time power of the device according to the corresponding formula. In most cases, for power-driven devices, the real-time energy consumption is usually measured in power units (such as kilowatts), indicating the rate of electrical energy consumption of the device at a certain moment. By monitoring the real-time energy consumption, it is possible to promptly detect whether the device has an abnormally high energy consumption situation, so as to take corresponding adjustment measures. For example, when an intelligent air conditioner is running, the power sensor installed in its circuit will monitor the electrical power consumed by the air conditioner in real time. For instance, it shows that the current real-time energy consumption of the air conditioner is 1.5 kilowatts, which means that the air conditioner consumes 1.5 degrees of electricity per hour at this moment.

[0019] Among them, the real-time temperature and humidity refer to the temperature and humidity values of the working area where the device under test is located, which are detected in real time by temperature and humidity sensors. Detection can be carried out using temperature and humidity sensors. These sensors are usually installed near the device or at key positions in the working area, and can sense and record the temperature and humidity data of the environment in real time. Temperature is usually measured in degrees Celsius (°C), and humidity is generally expressed in relative humidity (%RH). Temperature and humidity have an important impact on the performance and lifespan of the device. Excessive temperature may cause the device to overheat, affecting its normal operation and even damaging the device; too high or too low humidity may also cause device failures. Therefore, real-time monitoring of temperature and humidity can provide a basis for adjusting the device operation status and improving the working environment. For example, in a data center, temperature and humidity sensors are installed, and the real-time monitoring shows that the current temperature in the computer room is 22°C and the relative humidity is 50%RH.

[0020] Step S202, input the real-time energy consumption, working period, and real-time temperature and humidity into a preset and trained neural network model for analysis, and obtain an energy consumption period trend graph showing the change of real-time energy consumption with the working period.

[0021] Among them, the real-time energy consumption, working period, and real-time temperature and humidity data are respectively input into a preset and trained neural network model. The model will perform a series of calculations and processes on these input data, and use the patterns and relationships learned internally to analyze the change trend of real-time energy consumption under different working periods. For example, during the working period from 10 am to 12 pm every day, as the temperature and humidity increase, the real-time energy consumption of the device shows an upward trend; while from 3 pm to 5 pm, even if the temperature and humidity remain relatively stable, due to the increase in workload, the real-time energy consumption will also increase.

[0022] Among them, based on the analysis results of the neural network model, the system will generate an energy consumption period trend graph showing the change of real-time energy consumption over working periods. This trend graph uses the working period as the horizontal axis and the real-time energy consumption as the vertical axis, intuitively showing the change of equipment energy consumption in different working periods. The energy consumption period trend graph can help equipment management and maintenance personnel intuitively understand the energy consumption law of the equipment and find the peak and trough periods of energy consumption. For example, by observing the trend graph and finding that the energy consumption of the equipment is abnormally high during a specific period, it is possible to further investigate the reasons, whether it is caused by equipment failure, excessive workload, or environmental factors, and then take corresponding measures to optimize the operation status of the equipment and reduce energy consumption.

[0023] Step S203: According to the energy consumption period trend graph, obtain the predicted energy consumption for the preset working time period during the working period. According to the real-time energy consumption, obtain the current energy consumption corresponding to the preset working time. Analyze whether the current energy consumption is higher than the predicted energy consumption for the period. If it is higher than the predicted energy consumption for the period, adjust the operation status of the device to be tested until the real-time energy consumption is not higher than the predicted energy consumption for the period, and obtain the adjusted operation status as the energy consumption adjustment mode of the device to be tested.

[0024] Among them, it is based on the energy consumption period trend graph obtained in step S202. This trend graph shows the law of the device's real-time energy consumption changing with the working period, reflecting the general level and change trend of the device's energy consumption under different working periods. From the energy consumption period trend graph, find the energy consumption value corresponding to the preset working time. This energy consumption value is the predicted energy consumption for the preset working time. For example, if the preset working time is from 9 am to 10 am, by checking the energy consumption period trend graph, it can be known that the predicted energy consumption for this period is 50 kilowatts.

[0025] According to the real-time energy consumption data detected by the sensor in step S201, within the preset working time, extract the real-time energy consumption value corresponding to the current moment as the current energy consumption for the preset working time. For example, within the preset working time from 9 am to 10 am, if the real-time energy consumption detected by the sensor at the current moment (such as 9:30 am) is 60 kilowatts, then the current energy consumption is 60 kilowatts.

[0026] Among them, when the analysis result shows that the current energy consumption is higher than the predicted energy consumption for the period, it means that the current energy consumption of the equipment exceeds the reasonable range predicted according to historical laws, and the operation status of the equipment needs to be adjusted. The adjustment methods will vary depending on the type of equipment. For industrial production equipment, the operating power of the equipment will be reduced and the production rhythm will be adjusted; for air conditioning equipment, the set temperature will be increased and the wind speed will be reduced, etc.

[0027] After adjusting the operating state of the device, continuously monitor the real-time energy consumption, and continuously repeat the process of comparing the current energy consumption with the predicted energy consumption for a period until the real-time energy consumption is no longer higher than the predicted energy consumption for the period. When the real-time energy consumption is not higher than the predicted energy consumption for the period, the operating state of the device at this time is the state that can make the energy consumption at a reasonable level after adjustment, and it is determined as the energy consumption adjustment mode of the device under test. This mode can be used as a reference for the subsequent operation of the device to maintain the stability and reasonableness of the device energy consumption.

[0028] Step S204: Calculate the real-time heat index based on the real-time temperature and humidity, and analyze whether the real-time heat index meets the preset index threshold. If it does not meet the index threshold, adjust the energy consumption adjustment mode until the real-time heat index meets the index threshold, and obtain the operating state of the device under test as the real-time adjustment mode.

[0029] Among them, in step S201, we have obtained the real-time temperature and humidity data in the working area during the operation of the device under test through sensors. These two data are the key indicators reflecting the thermal environment status around the device.

[0030] The real-time heat index is an index that comprehensively considers the thermal effects of temperature and humidity on the human body or the device, and it can more accurately reflect the actual thermal environment perception. Calculating the real-time heat index usually uses a specific formula, which combines the real-time temperature and humidity data for operation. For example, in some standard formulas, the higher the temperature and the higher the humidity, the higher the calculated heat index. When the real-time temperature is 30°C and the relative humidity is 80%, the real-time heat index calculated through the corresponding formula may show a relatively high value, indicating that the thermal environment is relatively stuffy at this time.

[0031] Among them, the preset index threshold is a heat index range preset according to the normal operation requirements and safety standards of the device. Different types of devices have different adaptability to the thermal environment, so different threshold settings will be available. For example, for some precision electronic devices, in order to ensure their stable performance and service life, the heat index threshold will be set relatively low to ensure that the device operates in a relatively cool environment.

[0032] Compare the calculated real-time heat index with the preset index threshold. If the real-time heat index is within the preset threshold range, it means that the current thermal environment is suitable for the device to operate; if the real-time heat index exceeds the preset threshold, whether it is too high or too low, it indicates that the current thermal environment does not belong to the comfortable temperature felt by the human body, and thus adjust the power of the device under test.

[0033] Optionally, if the real-time heat index meets the preset index threshold, use the energy consumption adjustment mode as the operating state of the device under test.

[0034] Among them, in the previous steps (such as step S203), according to the energy consumption situation of the device, the operating parameters of the device are adjusted through a certain algorithm or strategy to obtain an operating mode that can keep the device energy consumption at a relatively reasonable level. This mode involves adjusting parameters such as the power, operating frequency, and switch state of the device to achieve the purpose of reducing energy consumption. When the real-time heat index meets the preset index threshold, it indicates that the current thermal environment has no adverse impact on the operation of the device, and the device can operate normally under the existing energy consumption adjustment mode. At this time, there is no need to make additional adjustments to the operating mode of the device to improve the thermal environment, so as to avoid increasing unnecessary energy consumption or affecting the normal operation of the device.

[0035] In the embodiment of the present application, by obtaining the working period when the device to be measured operates in the working area, the real-time energy consumption, and the real-time temperature and humidity detected by the sensor in real time when the device to be measured operates, the real-time energy consumption, the working period, and the real-time temperature and humidity are respectively input into the preset trained neural network model for analysis to obtain an energy consumption period trend chart of the real-time energy consumption changing with the working period. According to the energy consumption period trend chart, the predicted energy consumption of the period of the preset working time in the working period is obtained. According to the real-time energy consumption, the current energy consumption corresponding to the preset working time is obtained, and it is analyzed whether the current energy consumption is higher than the predicted energy consumption of the period. If it is higher than the predicted energy consumption of the period, the operating state of the device to be measured is adjusted until the real-time energy consumption is not higher than the predicted energy consumption of the period, and the adjusted operating state is used as the energy consumption adjustment mode of the device to be measured. According to the real-time temperature and humidity, the real-time heat index is calculated, and it is analyzed whether the real-time heat index meets the preset index threshold. If it does not meet the index threshold, the energy consumption adjustment mode is adjusted until the real-time heat index meets the index threshold, and the operating state of the device to be measured is obtained as the real-time adjustment mode. By respectively inputting the working period, the real-time temperature and humidity, and the real-time energy consumption of the device to be measured into the neural network model for analysis, an energy consumption period trend chart of the device to be measured is obtained, and the operating state of the device to be measured is adjusted by combining the real-time energy consumption and the real-time temperature and humidity to obtain the real-time adjustment mode. Thus, the multi-dimensional information of the device to be measured is automatically analyzed to adjust the device to optimize the operating state of the device.

[0036] As Figure 3 shown, it is a schematic flowchart of a method for adjusting the operating state of a device provided in Embodiment III of the present invention. The training process of the trained neural network model in step S202 may include the following steps: Step S301, obtain a training set. The training set includes training information of at least one device to be measured. The training information includes the working period, the real-time energy consumption, the real-time temperature and humidity of the device to be measured, and the annotation result; Step S302: Input the working period, real-time energy consumption, and real-time temperature and humidity in each device to be tested into a preset neural network model for feature extraction, obtaining a first vector corresponding to the working period, a second vector corresponding to the real-time energy consumption, and a third vector corresponding to the real-time temperature and humidity. Step S303: Calculate the weight assignment loss based on the first vector, second vector, third vector, and annotation results. Step S304: Update the parameters in the preset neural network model according to the weight assignment loss to obtain an updated neural network model. Step S305: Use the updated neural network model as the preset neural network model, and return to execute the step of inputting the working period, real-time energy consumption, and real-time temperature and humidity in each device to be tested into the preset neural network model for feature extraction until the weight assignment loss meets the preset conditions, and the obtained updated neural network model is the trained neural network model.

[0037] Among them, the training set is a set of data used to train the model, the training information is the relevant data collected for at least one device to be tested, the working period represents the time period when the device is in the running state, reflecting the time law of the device operation. The real-time energy consumption represents the energy consumed by the device in real time during operation, reflecting the energy consumption characteristics of the device. The real-time temperature and humidity represent the real-time temperature and humidity of the device operation environment, which will affect the performance and energy consumption of the device. The annotation result can be understood as the correct result that the expected model should output under the given working period, real-time energy consumption, and real-time temperature and humidity conditions. For example, judging whether the device is in an efficient operation state based on these data.

[0038] Among them, the model with the structure and initial parameters predefined before the training starts. Input the working period, real-time energy consumption, and real-time temperature and humidity of each device to be tested into the preset neural network model respectively. The model will perform a series of calculations and conversions on these input data and map them into corresponding vectors. The first vector is the vector corresponding to the working period, which extracts the key features in the working period data, and these features are related to the operation mode of the device at different time periods. The second vector is the vector corresponding to the real-time energy consumption, containing the features of the real-time energy consumption data, which helps the model understand the change law of energy consumption. The third vector is the vector corresponding to the real-time temperature and humidity, reflecting the characteristics of the real-time temperature and humidity data, which can be used to analyze the impact of environmental factors on the device.

[0039] Among them, based on the feature information contained in the first vector, the second vector, and the third vector, the model will make predictions. The prediction result of the model is compared with the annotation result, and the difference between the two is calculated through a specific loss function. This difference is the weight allocation loss. The larger the loss value, the greater the deviation between the prediction result of the model and the actual situation. According to the calculated weight allocation loss, the parameters in the preset neural network model are adjusted to make the prediction result of the model closer to the annotation result, thereby improving the performance of the model. An optimization algorithm (such as stochastic gradient descent, etc.) is used to update the parameters in the model according to the magnitude and direction of the weight allocation loss. For example, some weight values are reduced or some bias values are increased to adjust the decision boundary and output result of the model.

[0040] Among them, through multiple iterations of training, the parameters of the model are continuously optimized so that the model can better learn the rules in the data until the performance of the model meets the preset requirements. The updated neural network model is used as the new preset model, and step S302 is executed again, that is, the working period, real-time energy consumption, and real-time temperature and humidity data are re-input for feature extraction, and then steps S303 and S304 are repeated to calculate the new weight allocation loss and update the model parameters. When the weight allocation loss meets the preset conditions, for example, the loss value is less than a certain pre-set threshold, or the loss value no longer decreases significantly after multiple iterations, at this time, it is considered that the model has converged, and the obtained updated neural network model is the trained neural network model, which can be used for subsequent actual applications, such as the analysis of real-time data in step S202.

[0041] In this embodiment, by adjusting the model parameters multiple times, the model can accurately learn the relationship between the working period, real-time energy consumption, real-time temperature and humidity and the annotation result, so as to have the ability to accurately predict and analyze new data.

[0042] As Figure 4 shown, it is a schematic flowchart of a method for adjusting the operating state of a device provided in Embodiment 4 of the present invention. After obtaining the working period of the device to be tested operating in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor during the operation of the device to be tested in step S201, the method for adjusting the operating state of the device may further include the following steps: Step S401: Obtain the historical operation information library of the device to be tested, and extract the historical period energy consumption and the period air temperature corresponding to the historical period energy consumption in the preset time period in the historical operation information library.

[0043] Step S402: Input the historical period energy consumption and the period air temperature into a preset time series model for processing to obtain the time zone energy consumption value of the preset time period.

[0044] Step S403: Generate a maintenance strategy for the device under test based on the energy consumption values in different time zones.

[0045] Among them, the historical operation information database stores various operation data of the device under test over a past period of time, which is accumulated through the built-in recording system of the device or a dedicated data acquisition system. Data within a specific preset time period (such as the past month, the past year, etc.) is screened out from the historical operation information database. Among them, the historical time period energy consumption refers to the energy consumed by the device at different times within the preset time period, and the time period temperature is the weather temperature corresponding to these energy consumption time periods. The weather temperature will affect the energy consumption of the device. For example, in hot weather, the refrigeration device may consume more energy.

[0046] Among them, the time series model is a statistical model specifically used to process data arranged in chronological order. Common ones include ARIMA (Autoregressive Integrated Moving Average Model), LSTM (Long Short-Term Memory Network), etc. These models can capture features such as trends, seasonality, and periodicity of data changing over time. The extracted historical time period energy consumption and time period temperature are respectively used as input data and fed into a preset time series model. The model will analyze and learn these data, identify the patterns and regularities in them, and then predict the energy consumption values in each time zone (i.e., different time periods) within the preset time period based on these regularities. For example, the model may find that when the temperature rises in summer every year, the energy consumption of the device will increase accordingly, and thus predict the energy consumption situation in each time period of summer based on the current temperature data.

[0047] Among them, the energy consumption values in different time zones can show the energy consumption distribution of the device in different time periods. For example, judge which time periods have excessive energy consumption, which may indicate problems such as device abnormalities or low operating efficiency. According to the energy consumption analysis results, formulate corresponding maintenance strategies. For time periods with excessive energy consumption, preventive maintenance can be arranged for the device during these time periods to check whether the device has faults and whether performance optimization is required. For example, clean and maintain the refrigeration device to improve its refrigeration efficiency and reduce energy consumption. For time periods with relatively stable energy consumption, the maintenance plan can be appropriately adjusted to reduce unnecessary maintenance work and lower the maintenance cost. At the same time, according to the energy consumption prediction results, the operation time and load of the device can be reasonably arranged to further optimize the energy utilization efficiency of the device.

[0048] Optionally, collect the real-time energy consumption of the device under test in the real-time adjustment mode; Analyze whether there are abnormal values in the real-time energy consumption according to the historical operation information database to obtain an analysis result, and optimize the operation state of the device under test according to the analysis result.

[0049] Among them, when the device is in the real-time adjustment mode, with the help of various energy consumption monitoring devices or systems, continuously and dynamically collect the energy data currently consumed by the device to be measured. The real-time adjustment mode means that the operating parameters of the device (such as power, speed, etc.) will be continuously adjusted according to factors such as the current working conditions and environmental conditions to achieve an optimization goal (such as energy conservation, efficient operation, etc.). Collecting real-time energy consumption data is to obtain the latest situation of the energy actually consumed by the device during this dynamic adjustment process.

[0050] Among them, if there are outliers in the real-time energy consumption: it is necessary to deeply analyze the reasons for the outliers. If the outliers are caused by equipment failures, it is necessary to arrange maintenance personnel to repair the equipment; if the outliers are due to unreasonable operating parameter settings, it is necessary to readjust the parameters to bring them back to the normal energy consumption level. If the real-time energy consumption is normal, the energy consumption data can be further analyzed to find potential energy-saving space. For example, based on the comprehensive analysis of historical data and real-time data, optimize the operating strategy of the device, adjust the start and stop times or operating power of the device to achieve more efficient energy utilization.

[0051] Optionally, obtain a preset floating threshold, and according to the real-time energy consumption, obtain the first energy consumption within the preset time period; Calculate the difference between the first energy consumption and the historical period energy consumption to obtain an outlier. According to whether the outlier meets the preset floating threshold, if it does not meet the preset floating threshold, optimize the operating state of the device to be measured.

[0052] Among them, the preset floating threshold is a preset energy consumption fluctuation range. It takes into account that the device's energy consumption will fluctuate due to various factors (such as ambient temperature, usage frequency, etc.) under normal circumstances, rather than being fixed. This threshold stipulates the boundaries within which the energy consumption can float up and down within a reasonable range, and is usually determined comprehensively based on the device's historical operation data, industry standards, and the device's design parameters, etc. The real-time energy consumption is the energy consumed by the device at the current moment. The preset time period is a preset time interval, such as one hour, one day, etc. According to the real-time energy consumption data, the total energy consumption of the device within this preset time period is calculated to obtain the first energy consumption. This may require processing such as integrating or accumulating the real-time energy consumption data, and the specific method depends on the acquisition method and characteristics of the energy consumption data. The historical period energy consumption is the energy consumption data within the preset time period extracted from the historical operation information database. Subtracting the historical period energy consumption from the first energy consumption, the obtained difference is the outlier. This outlier reflects the degree of difference between the device's energy consumption in the current preset time period and the energy consumption in the same historical period. The calculated outlier is compared with the preset floating threshold. If the outlier exceeds the range of the floating threshold, that is, it does not conform to the preset floating threshold, it indicates that there is a large deviation between the device's current energy consumption situation and the historical normal situation, and there may be problems such as device failures, unreasonable operation parameter settings, or being affected by external abnormal factors, etc. At this time, it is necessary to optimize the operation state of the device to be measured.

[0053] In this embodiment, by mining the historical operation data of the device, using a time series model for energy consumption prediction, and formulating a maintenance strategy based on the prediction results, it helps to improve the operation efficiency of the device, reduce energy consumption and maintenance costs, and realize the intelligent management and maintenance of the device.

[0054] As Figure 5 shown, it is a schematic flowchart of a method for adjusting the operation state of a device provided in Embodiment 5 of the present invention. Before obtaining the working period during which the device to be measured operates in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor when the device to be measured operates in step S201, this method for adjusting the operation state of the device may further include the following steps: Step S501, obtaining the historical operation information database of the device to be measured to obtain the energy consumption change of the device to be measured.

[0055] Step S502, analyzing the energy consumption change to determine the time factors and environmental factors that affect the energy consumption of the device to be measured.

[0056] Among them, the energy consumption change data obtained in step S501 is studied in more detail. Using statistical methods and data analysis techniques, characteristics such as the trend, periodicity, and abnormal points of energy consumption change are found. For example, regression analysis is used to determine the relationship between energy consumption and time, or the energy consumption data is classified into different categories through cluster analysis to better understand the pattern of energy consumption change.

[0057] Time factors include the time period when the device operates (such as day or night, working day or rest day), seasonal changes, etc. Through the correlation analysis of energy consumption data and time information, the energy consumption differences of the device at different time points can be found. For example, the energy consumption of some devices may be higher during the day than at night, which may be because the device has a higher usage frequency or a higher environmental temperature during the day.

[0058] Environmental factors mainly refer to the temperature, humidity, light intensity, air pressure, etc. of the device operating environment. Changes in environmental conditions will directly or indirectly affect the energy consumption of the device. For example, in a high-temperature and high-humidity environment, the temperature and humidity felt by the human body are not suitable, and more energy needs to be consumed to enhance the output of the device so as to reduce the temperature and humidity in the working area. By analyzing the correlation between energy consumption data and environmental data, the specific impact degree of environmental factors on the device's energy consumption can be determined.

[0059] In this embodiment, by mining the historical operation data of the device to be tested, analyzing the energy consumption change and the time and environmental factors behind it, it provides an important reference basis for subsequent obtaining data such as the working period, real-time energy consumption, and real-time temperature and humidity of the device, and further adjusting the device operation state, which helps to manage the operation of the device more scientifically and reasonably and reduce energy consumption.

[0060] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0061] As Figure 6 shown, it is a schematic diagram of a device operation state adjustment device provided in Embodiment VII of the present invention. The device operation state adjustment device corresponds one-to-one to the device operation state adjustment method in the above embodiment. The device operation state adjustment device includes an information detection module 61, an information analysis module 62, an energy consumption analysis module 63, and a mode determination module 64. The detailed description of each functional module is as follows: The information detection module 61 is used to obtain the working period when the device to be tested operates in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor in real time when the device to be tested operates; An information analysis module 62 is configured to input the real-time energy consumption, working period, and real-time temperature and humidity into a pre-trained neural network model for analysis respectively, so as to obtain an energy consumption period trend graph of the real-time energy consumption varying with the working period; An energy consumption analysis module 63 is configured to obtain a predicted energy consumption for a preset working time period in the working period according to the energy consumption period trend graph, obtain the current energy consumption corresponding to the preset working time according to the real-time energy consumption, analyze whether the current energy consumption is higher than the predicted energy consumption for the period. If it is higher than the predicted energy consumption for the period, adjust the operating state of the device under test until the real-time energy consumption is not higher than the predicted energy consumption for the period, and obtain the adjusted operating state as the energy consumption adjustment mode of the device under test; A mode determination module 64 is configured to calculate a real-time heat index according to the real-time temperature and humidity, analyze whether the real-time heat index meets a preset index threshold. If it does not meet the index threshold, adjust the energy consumption adjustment mode until the real-time heat index meets the index threshold, and obtain the operating state of the device under test as the real-time adjustment mode.

[0062] Optionally, the above information analysis module 62 includes: A training set determination unit is configured to obtain a training set, where the training set includes training information of at least one device under test, and the training information includes the working period, real-time energy consumption, real-time temperature and humidity of the device under test, and an annotation result; A feature extraction unit is configured to input the working period, real-time energy consumption, and real-time temperature and humidity in each device under test into a preset neural network model for feature extraction respectively, so as to obtain a first vector corresponding to the working period, a second vector corresponding to the real-time energy consumption, and a third vector corresponding to the real-time temperature and humidity; A loss calculation unit is configured to calculate a weight distribution loss according to the first vector, the second vector, the third vector, and the annotation result; A parameter update unit is configured to update the parameters in the preset neural network model according to the weight distribution loss, so as to obtain an updated neural network model; A return execution unit is configured to use the updated neural network model as the preset neural network model, and return to execute the step of inputting the working period, real-time energy consumption, and real-time temperature and humidity in each device under test into the preset neural network model for feature extraction respectively, until the updated neural network model obtained when the weight distribution loss meets a preset condition is the trained neural network model.

[0063] Optionally, the device operating state adjustment device further includes: An air temperature extraction module, which is used to obtain the historical operation information library of the device under test after acquiring the working period of the device under test running in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor during the operation of the device under test, and extract the historical period energy consumption within a preset time period in the historical operation information library and the period air temperature of the weather air temperature corresponding to the historical period energy consumption; A time zone energy consumption value determination module, which is used to input the historical period energy consumption and the period air temperature into a preset time series model for processing respectively to obtain the time zone energy consumption value of a preset time period; A strategy generation unit, which is used to generate a maintenance strategy for the device under test according to the time zone energy consumption value.

[0064] Optionally, the device operation state adjustment device further includes: A threshold compliance module, which is used to, after analyzing whether the real-time heat index complies with a preset index threshold, if the real-time heat index complies with the preset index threshold, use the energy consumption adjustment mode as the operation state of the device under test.

[0065] Optionally, the device operation state adjustment device further includes: A historical energy consumption acquisition module, which is used to obtain the historical operation information library of the device under test and obtain the energy consumption change of the device under test before acquiring the working period of the device under test running in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor during the operation of the device under test; An influencing factor determination module, which is used to analyze the energy consumption change and determine the time factor and environmental factor that affect the energy consumption of the device under test.

[0066] A real-time energy consumption collection module, which is used to collect the real-time energy consumption of the device under test in the real-time adjustment mode after obtaining the energy consumption period trend graph of the real-time energy consumption changing with the working period; An anomaly analysis module, which is used to analyze whether there is an abnormal value in the real-time energy consumption according to the historical operation information library to obtain an analysis result, and optimize the operation state of the device under test according to the analysis result.

[0067] Optionally, the above anomaly analysis module includes: A first energy consumption acquisition unit, which is used to obtain a preset floating threshold and obtain the first energy consumption within a corresponding preset time period according to the real-time energy consumption; An optimization unit, which is used to calculate the difference between the first energy consumption and the historical period energy consumption to obtain an abnormal value, and optimize the operation state of the device under test according to whether the abnormal value complies with the preset floating threshold, if it does not comply with the preset floating threshold.

[0068] For the specific limitations of the device operation state adjustment device, reference can be made to the limitations of the device operation state adjustment method in the foregoing text, which will not be elaborated here. Each module in the above device operation state adjustment device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0069] As Figure 7 shown, it is a schematic structural diagram of a computer device provided in the seventh embodiment of the present invention. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a device operation state adjustment method.

[0070] In an embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the device operation state adjustment method in the above embodiment. For example Figures 2 to 5 shown, to avoid repetition, it will not be elaborated here. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the device operation state adjustment device. For example Figure 6 shown, the functions of the information detection module 61, the information analysis module 62, the energy consumption analysis module 63, and the mode determination module 64 will not be elaborated here to avoid repetition.

[0071] In an embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, it implements the device operation state adjustment method in the above embodiment. As Figures 2 to 5 shown, to avoid repetition, it will not be elaborated here. Alternatively, when the computer program is executed by the processor, it implements the functions of each module / unit in this embodiment of the above device operation state adjustment device. For example Figure 6 shown, the functions of the information detection module 61, the information analysis module 62, the energy consumption analysis module 63, and the mode determination module 64 will not be elaborated here to avoid repetition. The computer-readable storage medium can be non-volatile or volatile.

[0072] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0073] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0074] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A method for adjusting the operation status of equipment, characterized in that: include: Obtain the working period of the device under test in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor when the device under test is running; The real-time energy consumption, the working period, and the real-time temperature and humidity are respectively input into a preset trained neural network model for analysis to obtain an energy consumption period trend graph showing the real-time energy consumption changing with the working period; According to the energy consumption period trend graph, the predicted energy consumption of the preset working time in the working period is obtained, and according to the real-time energy consumption, the current energy consumption corresponding to the preset working time is obtained, and it is analyzed whether the current energy consumption is higher than the predicted energy consumption of the period. If it is higher than the predicted energy consumption of the period, the operating state of the device under test is adjusted until the real-time energy consumption is not higher than the predicted energy consumption of the period, and the adjusted operating state is the energy consumption regulation mode of the device under test; According to the real-time temperature and humidity, the real-time thermal index is calculated, and it is analyzed whether the real-time thermal index meets the preset index threshold. If it does not meet the index threshold, the energy consumption adjustment mode is adjusted until the real-time thermal index meets the index threshold, and the operating state of the device under test is obtained as the real-time adjustment mode.

2. The device operation status adjustment method according to claim 1, characterized in that: The training process of the trained neural network model is as follows: Acquire a training set, wherein the training set includes training information of at least one device to be tested, wherein the training information includes a working period, real-time energy consumption, real-time temperature and humidity, and a labeling result of the device to be tested; The working period, the real-time energy consumption, and the real-time temperature and humidity in each device under test are respectively input into a preset neural network model for feature extraction to obtain a first vector corresponding to the working period, a second vector corresponding to the real-time energy consumption, and a third vector corresponding to the real-time temperature and humidity; Calculate a weight distribution loss according to the first vector, the second vector, the third vector, and the labeling result; According to the weight distribution loss, updating the parameters in the preset neural network model to obtain an updated neural network model; The updated neural network model is used as the preset neural network model, and the step of inputting the working period, the real-time energy consumption, and the real-time temperature and humidity in each device to be tested into the preset neural network model for feature extraction is returned to execute, until the updated neural network model obtained when the weight distribution loss meets the preset conditions is a trained neural network model.

3. The device operation status adjustment method according to claim 1, characterized in that: After obtaining the working period of the device under test in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor when the device under test is running, the method further includes: Obtain a historical operation information database of the device under test, extract the historical time period energy consumption within a preset time period from the historical operation information database and the time period temperature of the weather temperature corresponding to the historical time period energy consumption; Inputting the energy consumption in the historical period and the temperature in the period into a preset time series model for processing, respectively, to obtain the time zone energy consumption value of the preset time period; A maintenance strategy is generated for the device under test according to the time zone energy consumption value.

4. The method for adjusting the equipment operation status according to claim 1, characterized in that: After analyzing whether the real-time thermal index meets a preset index threshold, the method further includes: If the real-time thermal index meets the preset index threshold, the energy consumption adjustment mode is used as the operating state of the device under test.

5. The method for adjusting the equipment operation status according to claim 1, characterized in that: Before obtaining the working period of the device under test in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor when the device under test is running, the method further includes: Obtaining a historical operation information database of the device under test to obtain energy consumption changes of the device under test; The energy consumption changes are analyzed to determine time factors and environmental factors that affect the energy consumption of the device under test.

6. The method for adjusting the equipment operation status according to claim 3, characterized in that: After obtaining the energy consumption period trend graph showing the real-time energy consumption changing with the working period, the method further includes: Collecting the real-time energy consumption of the device under test in the real-time adjustment mode; According to the historical operation information database, the real-time energy consumption is analyzed to see whether there is an abnormal value, an analysis result is obtained, and according to the analysis result, the operation state of the device under test is optimized.

7. The method for adjusting the equipment operation status according to claim 6, characterized in that: Analyzing whether the real-time energy consumption has an abnormal value according to the historical operation information database, obtaining an analysis result, and optimizing the operation state of the device under test, including: Obtaining a preset floating threshold, and obtaining a first energy consumption corresponding to the preset time period according to the real-time energy consumption; The difference between the first energy consumption and the energy consumption in the historical period is calculated to obtain an abnormal value, and the operating state of the device under test is optimized according to whether the abnormal value meets the preset floating threshold. If it does not meet the preset floating threshold, the operating state of the device under test is optimized.

8. A device for adjusting the operation status of equipment, characterized in that: include: An information detection module is used to obtain the working period of the device under test in the working area and the real-time energy consumption and real-time temperature and humidity detected by the sensor when the device under test is running; An information analysis module, for inputting the real-time energy consumption, the working period, and the real-time temperature and humidity into a preset trained neural network model for analysis, and obtaining an energy consumption period trend graph showing the real-time energy consumption changing with the working period; An energy consumption analysis module, used to obtain the predicted energy consumption of the preset working time in the working period according to the energy consumption period trend graph, obtain the current energy consumption corresponding to the preset working time according to the real-time energy consumption, analyze whether the current energy consumption is higher than the predicted energy consumption of the period, and if it is higher than the predicted energy consumption of the period, adjust the operating state of the device under test until the real-time energy consumption is no higher than the predicted energy consumption of the period, and the adjusted operating state is the energy consumption regulation mode of the device under test; A mode determination module is used to calculate a real-time thermal index based on the real-time temperature and humidity, analyze whether the real-time thermal index meets a preset index threshold, and if it does not meet the index threshold, adjust the energy consumption adjustment mode until the real-time thermal index meets the index threshold, thereby obtaining the operating state of the device under test as the real-time adjustment mode.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the device operating status adjustment method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the device operating status adjustment method according to any one of claims 1 to 7 is implemented.

Images