An office environment management method based on data fusion

Abstract

The present application relates to the technical field of intelligent environment management, in particular to an office environment management method based on data fusion. The present application realizes fine perception of the problem of uneven heat distribution in the office area by constructing a two-dimensional thermal gradient mapping sequence containing specific direction and change amplitude, and is no longer limited to passive response to a single temperature value, then combines and quantizes the real-time energy consumption of the air supply equipment with the local temperature difference in the gradient sequence to generate a control load index and sort it, so as to establish the priority of equipment intervention according to the correlation degree of problem severity and energy consumption cost, and then accurately select the target equipment that can effectively solve the problem by matching the temperature gradient abnormal area and the equipment control action area, which changes the previous blind or global adjustment mode. Furthermore, by fitting and predicting the trend of the historical operation parameters of the target equipment, the passive response is changed to active intervention.

Description

Technical Field

[0001] This invention relates to the field of intelligent environmental management technology, and in particular to an office environment management method based on data fusion. Background Technology

[0002] The field of intelligent environmental management technology mainly involves controlling and adjusting various parameters of different environments through automation to achieve effective management of environmental quality.

[0003] Office environment management methods refer to controlling factors such as temperature, humidity, and lighting in the office environment by adjusting equipment such as air conditioners, lights, and curtains.

[0004] Existing technologies typically rely on macroscopic perception and unified control of the environment. Their control is often based on isolated or averaged environmental parameters. In actual office scenarios, when local areas experience abnormal temperatures due to uneven sunlight, personnel density, or equipment layout, this global adjustment method cannot accurately identify the specific location and severity of the problem. For example, if only the side of the office area near the window experiences localized high temperatures due to sunlight, a uniform cooling operation will indiscriminately deliver cold air to the entire space. This not only causes excessive cooling in areas far from the window, leading to discomfort for people, but also results in ineffective energy consumption due to the vague control target, failing to achieve a rapid and accurate response to specific heat accumulation problems. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a data fusion-based office environment management method.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an office environment management method based on data fusion, comprising the following steps:

[0007] S1: Obtain temperature data from the temperature sensors in each deployed node within the office area, and use the temperature data to construct a two-dimensional thermal gradient mapping sequence;

[0008] S2: Obtain the energy consumption values ​​of the air supply equipment in the office area at the corresponding deployment nodes, construct the correspondence between energy consumption data and temperature data based on the two-dimensional thermal gradient mapping sequence, and sort to generate a device control priority sequence;

[0009] S3: Match the distribution area of ​​temperature sensors in the two-dimensional thermal gradient mapping sequence with the control action area of ​​air supply equipment in the equipment control priority sequence, and filter the target equipment list with abnormal temperature gradients.

[0010] S4: Call the current operating parameters and previous cycle operating trend data of the target equipment list with abnormal temperature gradient, fit and predict the change trend of the current and previous cycle operating parameters, and form a reference table for the adjustment of abnormal equipment parameters.

[0011] S5: Based on the abnormal equipment parameter control reference table and the direction of temperature difference change in the corresponding region in the two-dimensional thermodynamic gradient mapping sequence, adjust the air supply temperature and wind speed parameters of the target equipment to obtain the equipment control instruction set.

[0012] The present invention is improved in that the two-dimensional thermal gradient mapping sequence includes a temperature gradient vector set, a group of temperature difference values ​​between adjacent nodes, and a temperature trend aggregation identifier; the equipment control priority sequence includes an equipment identification number sequence, a control load index sorting value, and equipment action area identification information; the target equipment list includes equipment numbers covering temperature fluctuation areas, equipment corresponding control area numbers, and a filter index item for equipment that meets the conditions; the abnormal equipment parameter control reference table includes predicted values ​​for supply air temperature, predicted values ​​for wind speed changes, and current change trend values; and the equipment control instruction set includes target supply air temperature values, target wind speed adjustment values, and supply air angle setting values.

[0013] The present invention is improved in that step S1 is specifically as follows:

[0014] S101: Acquire real-time temperature data from the temperature sensors in each deployed node within the office area, associate the collected temperature data of each node with the deployment location, and establish deployment node temperature data;

[0015] S102: Call the temperature data of the deployment nodes, identify spatially adjacent deployment nodes and calculate the temperature difference between adjacent deployment nodes, combine the difference with the directional relationship between the corresponding nodes, characterize the local heat change of each location in the office area, and generate a temperature gradient vector set.

[0016] S103: Based on the temperature gradient vector set, aggregate the vectors according to the consistency of their direction and the magnitude of their change to construct thermal trend segments, and splice each thermal trend segment according to the spatial order of the deployed nodes to obtain a two-dimensional thermal gradient mapping sequence.

[0017] An improvement of the present invention is that each deployment node in the office area includes a ceiling, a corner, and a ventilation terminal.

[0018] The present invention is improved in that step S2 is specifically as follows:

[0019] S201: Obtain the power and current operating parameters of the air supply equipment in the office area, and collect the real-time energy consumption value of the corresponding deployment node of the air supply equipment. Combine the operating parameters and energy consumption values ​​to generate equipment operating energy consumption data.

[0020] S202: Call the two-dimensional thermal gradient mapping sequence, extract the corresponding temperature difference change value from the sequence, and obtain the energy consumption value of the air supply equipment from the equipment operation energy consumption data. Combine and quantify the extracted temperature difference change value and energy consumption value to generate the control load index.

[0021] S203: The control load index of each air supply device is uniformly sorted by value, the control order of each air supply device under the current thermal environment is determined, and a device control priority sequence is generated.

[0022] The present invention is improved in that step S3 is specifically as follows:

[0023] S301: Calculate the mean value of all temperature gradient changes in the two-dimensional thermodynamic gradient mapping sequence as a threshold, identify and mark sensor distribution areas where the gradient change value is continuously higher than the mean threshold, and generate temperature gradient abnormal areas.

[0024] S302: Match the distribution area of ​​temperature sensors in the abnormal temperature gradient area with the control area of ​​each air supply device in the device control priority sequence, determine whether the control area of ​​the air supply device covers the marked abnormal area, and establish device area coverage association information;

[0025] S303: Based on the equipment area coverage association information, filter the air supply equipment with established coverage relationships from the equipment control priority sequence, retain the air supply equipment number and the corresponding control load index, and generate a target equipment list with abnormal temperature gradient.

[0026] The present invention is improved in that step S4 is specifically as follows:

[0027] S401: Call the abnormal air supply equipment number in the target equipment list of the abnormal temperature gradient, obtain the air supply temperature, wind speed and current time series operating parameters of the corresponding abnormal air supply equipment in the current and previous cycles, and establish a set of equipment operation history parameters.

[0028] S402: Based on the parameter change trends in the historical parameter set of the equipment operation, the fitting logic of support vector regression is applied to process the parameters, predict the change trend of each operating parameter in the next cycle, and generate equipment parameter prediction results.

[0029] S403: Call the equipment parameter prediction results, match the temperature difference value at the corresponding position in the two-dimensional thermodynamic gradient mapping sequence with the control index in the equipment control priority sequence, combine each data item to form an abnormal equipment parameter control reference table.

[0030] The present invention is improved in that step S5 is specifically as follows:

[0031] S501: Call the abnormal equipment parameter control reference table, extract the temperature difference change direction of the area corresponding to the target air supply equipment from the two-dimensional thermal gradient mapping sequence, match the current air supply direction of the abnormal air supply equipment with the temperature difference change direction, and generate the equipment control direction determination result.

[0032] S502: Based on the determination result of the device control direction, if the direction is consistent, the adjustment range of wind speed and air supply temperature is directly set according to the reference table; if the direction is opposite, the air supply angle and speed are reset to align the direction, and a device parameter adjustment plan is established.

[0033] S503: Based on the wind speed adjustment range set in the equipment parameter adjustment plan, a maximum power coefficient limit is added, and the limited supply air temperature and wind speed parameters are integrated to obtain the equipment control instruction set.

[0034] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0035] In this invention, by constructing a two-dimensional thermodynamic gradient mapping sequence containing specific directions and amplitudes of change, a refined perception of uneven heat distribution in office areas is achieved, moving beyond passive responses to single temperature values. The real-time energy consumption of the air supply equipment is then combined and quantified with the local temperature differences in the gradient sequence to generate and rank control load indices. This establishes the priority of equipment intervention based on the correlation between problem severity and energy cost. Furthermore, by matching abnormal temperature gradient regions with equipment control areas, target equipment capable of effectively solving the problem is precisely selected, changing the previous blind or global adjustment methods. Moreover, by fitting and predicting the trends of historical operating parameters of target equipment, a forward-looking control reference can be formed, realizing a shift from passive response to proactive intervention. Finally, when issuing control commands, the matching degree between the direction of heat change and the direction of equipment air supply is comprehensively considered, and a power coefficient limit is added for safety verification, ensuring that every adjustment significantly improves energy efficiency and personnel comfort while guaranteeing equipment safety. Attached Figure Description

[0036] Figure 1 This is a flowchart of the method of the present invention;

[0037] Figure 2 This is a detailed flowchart of step S1 of the present invention;

[0038] Figure 3 This is a detailed flowchart of step S2 of the present invention;

[0039] Figure 4 This is a detailed flowchart of step S3 of the present invention;

[0040] Figure 5This is a detailed flowchart of step S4 of the present invention;

[0041] Figure 6 This is a detailed flowchart of step S5 of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0043] Please see Figure 1 This invention provides a technical solution: an office environment management method based on data fusion, comprising the following steps:

[0044] S1: Obtain temperature data from the temperature sensors in each deployed node within the office area, and use the temperature data to construct a two-dimensional thermal gradient mapping sequence;

[0045] S2: Obtain the energy consumption values ​​of the air supply equipment in the office area at the corresponding deployment nodes, construct the correspondence between energy consumption data and temperature data based on the two-dimensional thermodynamic gradient mapping sequence, and sort to generate a sequence of equipment control priorities;

[0046] S3: Match the distribution area of ​​temperature sensors in the two-dimensional thermal gradient mapping sequence with the control action area of ​​air supply equipment in the equipment control priority sequence, and filter the list of target equipment with abnormal temperature gradients.

[0047] S4: Call the current operating parameters and previous cycle operating trend data of the target equipment list with abnormal temperature gradient, fit and predict the change trend of the current and previous cycle operating parameters, and form a reference table for the adjustment of abnormal equipment parameters.

[0048] S5: Based on the abnormal equipment parameter control reference table and the temperature difference change direction of the corresponding area in the two-dimensional thermodynamic gradient mapping sequence, adjust the air supply temperature and wind speed parameters of the target equipment to obtain the equipment control instruction set;

[0049] The two-dimensional thermal gradient mapping sequence includes a temperature gradient vector set, a group of temperature difference values ​​between adjacent nodes, and a temperature trend aggregation identifier. The equipment control priority sequence includes an equipment identification number sequence, a control load index sorting value, and equipment action area identifier information. The target equipment list includes the equipment number covering the temperature fluctuation area, the equipment corresponding control area number, and the index item for filtering equipment that meets the conditions. The abnormal equipment parameter control reference table includes the predicted value of the supply air temperature, the predicted value of the wind speed change, and the current change trend value. The equipment control instruction set includes the target supply air temperature value, the target wind speed adjustment value, and the supply air angle setting value.

[0050] Please see Figure 2Step S1 is as follows:

[0051] S101: Acquire real-time temperature data from temperature sensors in each deployed node within the office area. Each deployed node in the office area includes the ceiling, corners, and ventilation terminals. Associate the collected temperature data of each node with the deployment location to establish deployed node temperature data.

[0052] The system acquires real-time temperature data from temperature sensors deployed at each node within the office area. This operation is initiated at a pre-set sampling time based on the office schedule, such as 10:00 AM on weekdays, by sending a polling command to all temperature sensors in the office area via the central processing unit. These sensors are pre-deployed based on thermodynamic analysis at key locations representative of indoor temperature distribution, such as the center of the ceiling, the four corners, near windows, and the ends of air conditioning vents. The three-dimensional spatial coordinates of the sensors are precisely measured and stored during deployment. When a sensor deployed near a window receives the command, its internal thermistor element measures the current ambient temperature and transmits a specific temperature reading back via a wireless network. This transmitted temperature reading is strictly bound to the sensor's pre-stored spatial coordinates to form a complete data record containing precise location and real-time temperature. After completing this acquisition and binding process for all sensors in the area, all records are summarized to establish the temperature data for each deployed node.

[0053] S102: Call the temperature data of the deployment nodes, identify spatially adjacent deployment nodes and calculate the temperature difference between adjacent deployment nodes, combine the difference with the directional relationship between the corresponding nodes, characterize the local heat change of each location in the office area, and generate a temperature gradient vector set.

[0054] The system retrieves temperature data from deployed nodes and identifies physically adjacent pairs of nodes based on a pre-generated spatial adjacency table. This table, generated from the building information model of the office area, takes into account the straight-line distance between sensors and the presence of obstacles such as walls, ensuring that the identified adjacency relationships are meaningful for heat transfer. For each pair of identified adjacent nodes, the temperature difference between them is first calculated by subtracting the temperature reading of one node from the temperature reading of the other, resulting in a scalar value representing the temperature change. Then, based on the existing 3D coordinates of the two nodes, a unit direction vector is calculated from the lower-temperature node to the higher-temperature node. This vector clearly indicates the direction of heat flow. The straight-line distance between the two nodes is then calculated, and the aforementioned temperature difference is divided by this distance to obtain the gradient magnitude, which represents the degree of temperature change per unit distance. This magnitude and direction are combined to form a complete gradient vector. This process is repeated for all pairs of adjacent nodes to generate a set of temperature gradient vectors.

[0055] S103: Based on the temperature gradient vector set, thermal trend segments are constructed by aggregating the vectors according to the consistency of the vector direction and the magnitude of change. Each thermal trend segment is then spliced ​​together according to the spatial order of the deployed nodes to obtain a two-dimensional thermal gradient mapping sequence.

[0056] Based on the temperature gradient vector set, a criterion for vector aggregation is set. The criterion for directional consistency is that any two spatially continuous gradient vectors have an angle between their directions of less than 30 degrees. This angle value is set based on a large amount of experimental data showing that when heat forms a stable convection or conduction path, the deviation of heat flow direction at adjacent locations is usually small. 30 degrees is a threshold that balances capturing the mainstream trend and filtering out local disturbances. The criterion for amplitude is that the vector amplitude is greater than 0.4 degrees Celsius per meter. This value is set based on a distinction threshold determined after statistical analysis of historical temperature data. It can effectively distinguish significant heat accumulation or loss caused by equipment failure, sudden changes in the external environment, etc., from normal indoor temperature fluctuations. During operation, when a set of spatially continuous vectors is found to simultaneously meet the criteria of an angle between their directions of less than 30 degrees and an amplitude greater than 0.4 degrees Celsius per meter, they are aggregated to construct a thermal trend segment. Finally, according to the physical spatial arrangement order of the deployed nodes, all segments are sequentially spliced ​​together to obtain a two-dimensional thermal gradient mapping sequence.

[0057] Please see Figure 3 Step S2 is as follows:

[0058] S201: Obtain the power and current operating parameters of the air supply equipment in the office area, and collect the real-time energy consumption value of the corresponding deployment node of the air supply equipment. Combine the operating parameters and energy consumption values ​​to generate equipment operating energy consumption data.

[0059] The power and current operating parameters of the ventilation equipment in the office area are obtained by sending a query command to a high-precision smart meter installed on the independent power supply line of each ventilation device. This smart meter can monitor and record detailed electrical parameters of the equipment in real time. Upon receiving the command, the meter will return the instantaneous active power consumption and root mean square value of the input current of the equipment at the current moment. At the same time, the meter will also provide a cumulative real-time energy consumption value since the last reset. This value directly reflects the total energy consumption of the equipment in the current working cycle. The two operating parameters of instantaneous power and current are correlated with the recorded cumulative real-time energy consumption value to form a complete data record that comprehensively describes the current operating status and energy consumption of the equipment. This process is performed on all ventilation equipment in the area to generate equipment operating energy consumption data.

[0060] S202: Call the two-dimensional thermal gradient mapping sequence, extract the corresponding temperature difference change value from the sequence, and obtain the energy consumption value of the air supply equipment from the equipment operation energy consumption data. Combine and quantify the extracted temperature difference change value and energy consumption value to generate the control load index.

[0061] The system invokes a two-dimensional thermal gradient mapping sequence and, based on the precise deployment coordinates of each air supply device recorded in the equipment operation energy consumption data, retrieves and extracts the temperature difference change value corresponding to that coordinate location from the mapping sequence. Simultaneously, it obtains the energy consumption value of the same air supply device within the current measurement cycle from the equipment operation energy consumption data. These two extracted values, namely the temperature difference change value and the energy consumption value, are combined and quantified. The specific quantification operation involves multiplying the absolute value of the temperature difference change value by the energy consumption value at a specified time after normalization. The result of this product is defined as the control load index, which quantifies the energy cost borne by the equipment to maintain or create the current local temperature difference. The higher the index, the closer the correlation between the equipment's operating energy consumption and the temperature imbalance problem in the area. This quantification calculation is performed on all air supply devices to generate the control load index.

[0062] S203: The control load index of each air supply device is uniformly sorted by value, the control order of each air supply device under the current thermal environment is determined, and the device control priority sequence is generated.

[0063] The control load indices generated by each air supply device in the previous steps are summarized. Then, a unified numerical sorting operation is performed on all these index values. The specific sorting rule is to adopt a strict descending order, that is, the air supply device with the highest control load index value is ranked first in the sequence, the next highest value is ranked second, and so on, until all devices are ranked according to their index size. The purpose of performing this sorting operation is to establish a clear control priority, which can ensure that limited control resources are used to address the devices with the most prominent energy consumption and temperature problems, thereby achieving the most efficient intervention. This sorted list of devices generates the device control priority sequence.

[0064] Please see Figure 4 Step S3 is as follows:

[0065] S301: Calculate the mean value of all temperature gradient changes in the two-dimensional thermodynamic gradient mapping sequence as a threshold, identify and mark sensor distribution areas where the gradient change value is continuously higher than the mean threshold, and generate temperature gradient anomaly areas.

[0066] The average value of all temperature gradient changes in the two-dimensional thermodynamic gradient mapping sequence is used as a dynamic threshold. The calculation process is as follows: First, the sequence is traversed to extract all independent, non-zero temperature gradient change values. Then, all these values ​​are summed and the sum is divided by the total number of values ​​to obtain an arithmetic mean. This mean is set as the average threshold for the current judgment period. The basis for setting this dynamic threshold is that it can adapt to the current overall thermal fluctuation level of the office area, avoiding misjudgments or omissions that may occur when using a fixed threshold under different seasons or weather conditions. After the threshold is set, the entire mapping sequence is traversed again, and the gradient change value at each location is compared with this average threshold. The spatial distribution areas formed by sensors whose values ​​are continuously higher than the average threshold are identified and marked to generate temperature gradient anomaly areas.

[0067] S302: Match the distribution area of ​​temperature sensors in the abnormal temperature gradient area with the control area of ​​each air supply device in the device control priority sequence, determine whether the control area of ​​the air supply device covers the marked abnormal area, and establish device area coverage association information;

[0068] The matching process involves matching the distribution area of ​​temperature sensors in the abnormal temperature gradient region with the control area of ​​each air supply device in the equipment control priority sequence. The control area of ​​each air supply device is pre-defined according to its manufacturer's performance specifications, which specify the effective air supply radius of the device under standard operating conditions, such as 5 meters, thus defining a circular control area centered on the device. The specific execution process of the matching judgment is to perform spatial geometric superposition analysis between the geometric range of the marked abnormal temperature gradient region and the circular control area of ​​each air supply device. By calculating the number of abnormal area sensors falling into the control area of ​​the air supply device and dividing it by the total number of sensors in the abnormal area, a coverage rate is obtained. When the calculated coverage rate is greater than 60%, the coverage relationship is determined to be valid. This percentage is set to ensure that the device has a dominant influence on the abnormal area, rather than accidental or marginal contact. The judgment results of all devices are recorded to establish device area coverage association information.

[0069] S303: Based on the equipment area coverage association information, filter the air supply equipment with established coverage relationships from the equipment control priority sequence, retain the air supply equipment number and the corresponding control load index, and generate a target equipment list with abnormal temperature gradient.

[0070] Based on the equipment area coverage association information, the items in the equipment control priority sequence are filtered. The filtering operation is strictly performed in descending order of equipment priority in the sequence. Specifically, the air supply equipment with the highest current priority is taken out, and its judgment result recorded in the equipment area coverage association information is queried. If the result shows that the coverage relationship is established, the number of this air supply equipment and its corresponding control load index value are retained and added to a new target list. If the result shows that the coverage relationship is not established, the equipment is directly discarded, and the next priority equipment is processed. After processing all the equipment in the equipment control priority sequence one by one according to this rule, the final list containing only the retained equipment is smaller in scale and more targeted, which is the target equipment list of temperature gradient anomalies.

[0071] Please see Figure 5 Step S4 is as follows:

[0072] S401: Call the abnormal air supply equipment number in the target equipment list of abnormal temperature gradient, obtain the time series operating parameters of the corresponding abnormal air supply equipment in the current and previous cycles, and establish a set of equipment operating history parameters.

[0073] The system retrieves the air supply equipment numbers from the target equipment list for temperature gradient anomalies and uses these numbers as unique identifiers to initiate a precise query request to the database storing historical operating data. The query time range is set to the current moment plus a complete period equal to the control cycle, such as the past 15 minutes. The query parameters explicitly include air supply temperature, wind speed, and equipment operating current. The data is returned in a format with high-precision timestamps, ensuring the temporal continuity and accuracy of the data. These queried time-series data are then classified and organized according to the equipment numbers, creating a dedicated, structured historical parameter data archive for each target air supply equipment in the list, thus establishing a set of historical operating parameters for the equipment.

[0074] S402: Based on the parameter change trends in the historical parameter set of the equipment operation, the fitting logic of support vector regression is applied to process the data, predict the change trend of each operating parameter in the next cycle, and generate equipment parameter prediction results.

[0075] Based on the parameter change trends in the historical parameter set of the equipment, support vector regression is applied to predict the change trend of each operating parameter in the next period. The core prediction process is achieved through a unified weighted time series prediction formula, which is applied to each independent time series parameter such as supply air temperature, wind speed, and current to generate their respective predicted values. The specific calculation formula is as follows:

[0076] ;

[0077] Where P represents a specific time series parameter collected by the abnormal air supply equipment. For example, when the goal is to predict the air supply temperature in the next cycle, P specifically refers to "air supply temperature"; when predicting wind speed, P specifically refers to "wind speed"; and when predicting current, P specifically refers to "current". t represents the current time period, that is, the starting time of the prediction, which corresponds to the latest data point in the collected time series data. This represents the next cycle immediately following the current time cycle, i.e., the predicted target time point. Therefore, The full meaning is "the predicted value of the target operating parameter in the next period," which is the final result that the formula aims to calculate. (Sum symbol) This indicates an accumulation operation that iterates through the data from the current time (…). From the furthest point within the historical window ( All data points in the summation operation. `i` is a counting index that starts at 0 and increments by 1 each time, until... So far, it has been used to access each data point in the historical time series sequentially. This represents the actual measured value of the target operating parameter at a certain point in the past, derived from the equipment's historical operating parameter set, and is used as the current index. When it is 0, That is, the measurement value of the current period; under the index When it is 1, This refers to the measurement value from the previous cycle, and so on. It represents the historical data input used for prediction. 'n' represents the total number of historical data points used for this prediction, i.e., the length of the time window. This value is set based on striking a balance between the stability of the prediction and sensitivity to recent changes. Through analysis experiments on historical data from the building automation system, a suitable value is selected that contains enough information to reflect the parameter change patterns while avoiding interference from outdated data. For example, if the control cycle is 5 minutes and data from the past 15 minutes is used, then the value of 'n' is 4 (including the current time). Represents a historical data point The corresponding weighting coefficients are derived by training a support vector regression model on a large amount of historical operating data covering various working conditions. The basic principle behind their setting is that measurements closer to the current moment have a greater impact on future trends. Therefore, the weighting coefficients typically assign higher weights to recent data (e.g., recent data). , The weight of the data is greater than that of the data from the distant past, which ensures that the prediction model can more sensitively capture and respond to recent trends. b represents a bias constant term, which is also obtained through training the regression model. Its function is to correct the fixed deviation between the prediction result and the true value caused by the inherent properties of the device or systematic factors (such as the inherent measurement bias of the sensor), thereby improving the overall accuracy of the prediction.

[0078] The entire formula's calculation logic is: to calculate each measurement value within the historical window ( ) are all multiplied by their corresponding weighting coefficients ( Then, the results of all these products are summed, and finally, the bias constant term (b) is added to obtain the final prediction of the parameter value for the next period. By applying this formula independently, but using the historical data and weights of the corresponding parameters, to the three time series of air supply temperature, wind speed and current respectively, the changing trend of each parameter in the next period can be calculated. The predicted values ​​of all parameters of all target equipment are summarized to generate the equipment parameter prediction results.

[0079] Suppose we retrieve the wind speed time series operating parameters of FCU-03 at the current time (t) and over the past three periods from the equipment's historical operating parameter set. Assuming the control period is 5 minutes, we collect data from the past 15 minutes and set the number of historical data points used for prediction. The obtained wind speed sequence data is as follows: Current wind speed ( ): 5.0 m / s, wind speed 5 minutes ago ( ): 4.9 m / s, wind speed 10 minutes ago ( ): 4.8 m / s, wind speed 15 minutes ago ( ): 4.5 m / s.

[0080] The weighting coefficients in the formula ( The bias constant (b) and the bias coefficient (b) were obtained by offline training of the support vector regression model using historical operating data from all equipment in the office area over several months. This training process aimed to learn the inherent patterns of parameter changes under different operating conditions. For the wind speed parameter, the model parameters were set as follows: Weight coefficient vector (w): Based on the principle that "recent data has a greater impact," the weights obtained during training were assigned as follows: (correspond (Weight): 0.5 (correspond (Weight): 0.3 (correspond (Weight): 0.15 (correspond The weights (b) are 0.05, and the bias constant (b) is 0.05, which is the bias term obtained during training to correct systematic bias.

[0081] The historical data and model parameters obtained above are completely substituted into the prediction formula defined in S402 for calculation. The prediction formula is as follows:

[0082] ;

[0083] Expanding the summation notation, the formula becomes a weighted summation over each historical data point:

[0084] ;

[0085] Accumulate and add the bias term: Add the above calculation result to the bias term to obtain the final predicted value:

[0086] ;

[0087] The calculated wind speed prediction for the next cycle is 4.965 m / s.

[0088] This calculation shows that, based on the wind speed change trend over the past 15 minutes and considering the greater influence of recent data, the wind speed predicted by the FCU-03 device in the next 5 minutes will be approximately 4.97 m / s (usually rounded to the effective precision of the physical quantity).

[0089] The same calculation process, using different weighting coefficients and bias terms (also derived from model training), will be independently applied to the time series data of the supply air temperature and current of FCU-03 to obtain the predicted values ​​for these two parameters. All these predicted values ​​(predicted wind speed 4.97 m / s, predicted supply air temperature, and predicted current) will be aggregated to form the predicted equipment parameters for FCU-03, serving as a key input for generating the abnormal equipment parameter control reference table in step S403.

[0090] S403: Call the equipment parameter prediction results, match the temperature difference value at the corresponding position in the two-dimensional thermodynamic gradient mapping sequence with the control index in the equipment control priority sequence, combine each data item to form an abnormal equipment parameter control reference table;

[0091] The system retrieves the predicted equipment parameters and integrates them with data from other steps. Specifically, for a single device in the target device list, it first retrieves the predicted equipment parameters generated in the previous step, including information such as predicted wind speed and predicted temperature. Then, based on the device's precise deployment location, it searches for and matches the real-time temperature difference value corresponding to that location from the two-dimensional thermal gradient mapping sequence. Finally, it retrieves the initially calculated control index for that device from the device control priority sequence. These three parts of data, which have different sources but describe the same object—predictions for the future, descriptions of the current environment, and assessments of historical performance—are combined and aligned to form a comprehensive structured data entry. After completing this data fusion operation for all target devices, an abnormal equipment parameter control reference table is generated.

[0092] Please see Figure 6 Step S5 is as follows:

[0093] S501: Call the abnormal equipment parameter control reference table, extract the temperature difference change direction of the corresponding area of ​​the target air supply equipment from the two-dimensional thermal gradient mapping sequence, match the current air supply direction of the abnormal air supply equipment with the temperature difference change direction, and generate the equipment control direction determination result.

[0094] The system calls the abnormal equipment parameter control reference table and extracts the direction of temperature difference change in the area corresponding to the target air supply equipment. This direction information is a core attribute of the gradient vector in the two-dimensional thermodynamic gradient mapping sequence, uniquely determined by the physical law of heat flowing from the low-temperature zone to the high-temperature zone. Simultaneously, by sending a status query command to the equipment controller, the system obtains the current actual air supply direction of the air supply equipment. This direction is determined by the real-time set angle of its physical air guide plate. Then, these two directions are matched and judged. The specific process involves calculating the spatial angle between these two direction vectors and determining their relationship based on the size of the angle: an angle less than 30 degrees is defined as being in the same direction, ensuring that the airflow direction and heat flow direction are basically consistent and can work synergistically; an angle greater than 150 degrees is defined as being in opposite directions, ensuring that the airflow direction and heat flow direction are basically opposed and have a direct antagonistic effect; other angles indicate deviation. This judgment is recorded to generate the equipment control direction judgment result.

[0095] S502: Based on the equipment control direction determination result, if the direction is consistent, the adjustment range of wind speed and air supply temperature is directly set according to the reference table; if the direction is opposite, the air supply angle and speed are reset to align with the direction, and an equipment parameter adjustment plan is established.

[0096] Based on the determination of the equipment control direction, a differentiated preliminary parameter adjustment plan is formulated for each target device. The specific adjustment logic is as follows: if the determination result is in the same direction, the current air supply direction is considered reasonable, and the plan directly adopts the predicted wind speed and air supply temperature from the abnormal equipment parameter control reference table as the adjustment target; if the determination result is in the opposite direction, the current air supply direction is considered to exacerbate the problem, and the first operation of the plan is to send a command to the equipment controller to adjust its air guide plate angle to be completely consistent with the direction of temperature difference change, that is, first correct the direction, and then set the wind speed and temperature with the predicted values ​​in the reference table as the target; for other deviations, it is also regarded as an inefficient air supply method, and the handling method is the same as the opposite situation, that is, first adjust the direction and then set the parameters. These adjustment plans, which include specific actions and set values, are summarized based on different determination results to establish an equipment parameter adjustment plan.

[0097] S503: Based on the wind speed adjustment range set in the equipment parameter adjustment plan, a maximum power coefficient limit is added to obtain the equipment control instruction set;

[0098] Based on the wind speed adjustment range set for each target device in the equipment parameter adjustment plan, a power verification step is added before the final instruction is generated. This step involves adding a maximum power coefficient limit to the device. This step aims to ensure that the control instruction can meet the needs of improving the thermal environment without causing the equipment to operate under overload. The final, verified adjustment power of the air supply equipment issued to the equipment is determined by the following formula:

[0099] ;

[0100] in, Representing the physical quantity "power", the unit is watt; indicating that this is the final power command value that can be safely issued to physical devices after safety and energy efficiency verification has been performed. A function is a mathematical operator that selects the minimum value from the multiple values ​​enclosed within its parentheses. In this scenario, it acts as a safety limiter or "power ceiling," ensuring that the final output command never exceeds the preset upper limit by comparing the planned power requirement with the device's maximum safe power allowance, thereby guaranteeing device safety. The representative plans to adjust power. Among them, This also represents "power"; the process of obtaining this value is as follows: First, the target air supply velocity set to improve the thermal environment is extracted. Then, this velocity value is substituted into the inherent performance curve function of the air supply equipment (a function describing the non-linear relationship between wind speed and power consumption, pre-stored in the equipment information database) to calculate the theoretical instantaneous power. For example, if the plan is to adjust the wind speed of a certain device to 5.1 meters per second, by consulting its performance curve, the corresponding theoretical instantaneous power is calculated to be 950 watts. That is, 950 watts. This represents the rated maximum power of the equipment. This represents "power"; it indicates the maximum power value that the equipment is designed to operate safely for a long period of time, as specified by the equipment manufacturer in its technical specifications or equipment nameplate. This is a fixed parameter, which can be retrieved from the equipment information database after the target equipment list is determined in step S303. For example, the rated maximum power of a target equipment is 1000 watts. This represents the maximum power factor. In engineering, this coefficient is typically used to represent a factor or constant, indicating that it is specifically used to limit power. This coefficient is specifically set to 0.9, based on the following: according to extensive equipment operation experiments and energy efficiency analyses, most wind turbines achieve their highest overall energy efficiency ratio when operating at slightly below their rated maximum power (e.g., 90%). Furthermore, setting this coefficient provides a 10% safety margin for normal fluctuations or surges in grid voltage, preventing equipment from tripping or being damaged due to instantaneous overload, thereby extending the equipment's lifespan.

[0101] In the actual verification process, the upper limit of power is first calculated. Then, the theoretical power required for the plan will be calculated. Compare with this upper limit value. If If it is 950 watts, then the formula is calculated as follows: ,get The calculated power is 900 watts, indicating that the originally planned power has exceeded the safe range and must be adjusted. Therefore, 900 watts is taken as the final command power. The equipment performance curve is then consulted to find the maximum wind speed capable of outputting this power, and this wind speed is taken as the final command wind speed. If the calculated... If it is 850 watts, then ,get The 850 watt rating indicates that the original plan was within a safe range, and its wind speed and power were directly adopted. Finally, the supply air temperature and wind speed parameters, verified by this power limit and ultimately determined, were integrated to obtain a set of equipment control commands that can be executed safely and efficiently.

[0102] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A data fusion-based office environment management method, characterized in that, Includes the following steps: S1: Obtain temperature data from the temperature sensors in each deployed node within the office area, and use the temperature data to construct a two-dimensional thermal gradient mapping sequence; S2: Obtain the energy consumption values ​​of the air supply equipment in the office area at the corresponding deployment nodes, construct the correspondence between energy consumption data and temperature data based on the two-dimensional thermal gradient mapping sequence, and sort to generate a device control priority sequence; S3: Match the distribution area of ​​temperature sensors in the two-dimensional thermal gradient mapping sequence with the control action area of ​​air supply equipment in the equipment control priority sequence, and filter the target equipment list with abnormal temperature gradients. S4: Call the current operating parameters and previous cycle operating trend data of the target equipment list with abnormal temperature gradient, fit and predict the change trend of the current and previous cycle operating parameters, and form a reference table for the adjustment of abnormal equipment parameters. S5: Based on the abnormal equipment parameter control reference table and the temperature difference change direction of the corresponding region in the two-dimensional thermodynamic gradient mapping sequence, adjust the air supply temperature and wind speed parameters of the target equipment to obtain the equipment control instruction set; Step S1 is as follows: S101: Acquire real-time temperature data from the temperature sensors in each deployed node within the office area, associate the collected temperature data of each node with the deployment location, and establish deployment node temperature data; S102: Call the temperature data of the deployment nodes, identify spatially adjacent deployment nodes and calculate the temperature difference between adjacent deployment nodes, combine the difference with the directional relationship between the corresponding nodes, characterize the local heat change of each location in the office area, and generate a temperature gradient vector set. S103: Based on the temperature gradient vector set, aggregate the vectors according to the consistency of their direction and the magnitude of their change to construct thermal trend segments, and splice each thermal trend segment according to the spatial order of the deployed nodes to obtain a two-dimensional thermal gradient mapping sequence.

2. The office environment management method based on data fusion according to claim 1, characterized in that: The two-dimensional thermal gradient mapping sequence includes a temperature gradient vector set, a group of temperature difference values ​​between adjacent nodes, and a temperature trend aggregation identifier. The temperature trend aggregation identifier is a thermal trend segment of continuous vector aggregation selected according to the judgment criteria of vector aggregation. The equipment control priority sequence includes an equipment identification number sequence, a control load index sorting value, and equipment action area identification information. The target equipment list includes the equipment number covering the temperature fluctuation area, the control area number corresponding to the equipment, and the index item of the equipment that meets the selection criteria. The abnormal equipment parameter control reference table includes the predicted value of the supply air temperature, the predicted value of the wind speed change, and the current change trend value. The equipment control instruction set includes the target supply air temperature value, the target wind speed adjustment value, and the supply air angle setting value.

3. The office environment management method based on data fusion according to claim 1, characterized in that: Each deployment node within the office area includes the ceiling, corners, and ventilation terminals.

4. The office environment management method based on data fusion according to claim 1, characterized in that: Step S2 is as follows: S201: Obtain the power and current operating parameters of the air supply equipment in the office area, and collect the real-time energy consumption value of the corresponding deployment node of the air supply equipment. Combine the operating parameters and energy consumption values ​​to generate equipment operating energy consumption data. S202: Call the two-dimensional thermal gradient mapping sequence, extract the corresponding temperature difference change value from the sequence, and obtain the energy consumption value of the air supply equipment from the equipment operation energy consumption data. Combine and quantify the extracted temperature difference change value and energy consumption value to generate the control load index. S203: The control load index of each air supply device is uniformly sorted by value, the control order of each air supply device under the current thermal environment is determined, and a device control priority sequence is generated.

5. The office environment management method based on data fusion according to claim 1, characterized in that: Step S3 is as follows: S301: Calculate the mean value of all temperature gradient changes in the two-dimensional thermodynamic gradient mapping sequence as a threshold, identify and mark sensor distribution areas where the gradient change value is continuously higher than the mean threshold, and generate temperature gradient abnormal areas. S302: Match the distribution area of ​​temperature sensors in the abnormal temperature gradient area with the control area of ​​each air supply device in the device control priority sequence, determine whether the control area of ​​the air supply device covers the marked abnormal area, and establish device area coverage association information; S303: Based on the equipment area coverage association information, filter the air supply equipment with established coverage relationships from the equipment control priority sequence, retain the air supply equipment number and the corresponding control load index, and generate a target equipment list with abnormal temperature gradient.

6. The office environment management method based on data fusion according to claim 1, characterized in that: Step S4 is as follows: S401: Call the abnormal air supply equipment number in the target equipment list of the abnormal temperature gradient, obtain the air supply temperature, wind speed and current time series operating parameters of the corresponding abnormal air supply equipment in the current and previous cycles, and establish a set of equipment operation history parameters. S402: Based on the parameter change trends in the historical parameter set of the equipment operation, the fitting logic of support vector regression is applied to process the parameters, predict the change trend of each operating parameter in the next cycle, and generate equipment parameter prediction results. S403: Call the equipment parameter prediction results, match the temperature difference value at the corresponding position in the two-dimensional thermodynamic gradient mapping sequence with the control index in the equipment control priority sequence, combine each data item to form an abnormal equipment parameter control reference table.

7. The office environment management method based on data fusion according to claim 6, characterized in that: To predict the trend of each operating parameter in the next cycle, the following formula is used: ； Where P represents the operating parameters collected by the abnormal air supply equipment, including air supply temperature, air velocity, and current. is the predicted value of the target operating parameter in the next period, and i is the data point index of the operating parameter. This represents the actual measured values ​​of the target's operating parameters at historical moments, where n represents the total number of historical data points. Representatives and historical data points The corresponding weighting coefficient, b represents a bias constant term.

8. The office environment management method based on data fusion according to claim 1, characterized in that: Step S5 is as follows: S501: Call the abnormal equipment parameter control reference table, extract the temperature difference change direction of the area corresponding to the target air supply equipment from the two-dimensional thermal gradient mapping sequence, match the current air supply direction of the abnormal air supply equipment with the temperature difference change direction, and generate the equipment control direction determination result. S502: Based on the determination result of the device control direction, if the direction is consistent, the adjustment range of wind speed and air supply temperature is directly set according to the reference table; if the direction is opposite, the air supply angle and speed are reset to align the direction, and a device parameter adjustment plan is established. S503: Based on the wind speed adjustment range set in the equipment parameter adjustment plan, a maximum power coefficient limit is added, and the limited supply air temperature and wind speed parameters are integrated to obtain the equipment control instruction set.

9. The office environment management method based on data fusion according to claim 8, characterized in that: To add a maximum power factor limit, the formula is: ； Calculate and send power adjustment to the air supply equipment ; Where P represents power, This indicates that the minimum value is selected from the multiple values ​​contained within the parentheses. The representative plans to adjust the power. This represents the rated maximum power of the equipment. This represents the maximum power factor.

Images