A yogurt cold-chain logistics temperature control tracing method and system based on the Internet of Things

Abstract

This invention belongs to the field of yogurt transportation technology, specifically relating to an IoT-based method and system for temperature control and traceability in yogurt cold chain logistics. This invention calculates the temperature control deviation of refrigeration equipment during historical heating and cooling processes, thereby determining temperature control parameters characterizing the operating characteristics of the refrigeration equipment. Finally, based on these parameters, an alarm temperature is calculated. By generating an alarm temperature that matches the current operating characteristics of the refrigeration equipment, early warning of potential faults is achieved, improving the predictability and reliability of temperature control traceability, and ultimately ensuring the safety and quality of yogurt.

Description

Technical Field

[0001] This invention belongs to the field of yogurt transportation technology, specifically relating to an Internet of Things-based method and system for temperature control and traceability of yogurt cold chain logistics. Background Technology

[0002] In modern supply chain systems, cold chain logistics plays a crucial role in ensuring the quality and safety of temperature-sensitive goods such as food and pharmaceuticals. This is especially true for dairy products like yogurt, which are highly sensitive to temperature changes. The environmental stability during transportation determines the final product's taste and safety, necessitating the development of a temperature control and traceability system to safeguard the integrity of the supply chain and product quality.

[0003] In the field of yogurt cold chain temperature control, existing control systems mostly employ simple threshold triggering. This means that once the temperature sensor reading exceeds a preset range, the refrigeration equipment is started or stopped. This reactive control method ignores the thermodynamic inertia within the cargo hold, making it prone to misjudgments due to short-term temperature fluctuations. This leads to frequent start-stop cycles of the refrigeration compressor, resulting in increased energy consumption and mechanical wear, as well as severe temperature fluctuations within the cargo hold. Furthermore, on-site sensor data must be uploaded to a remote server via mobile network for analysis and decision-making, and control commands are then transmitted back to the transport equipment. During transport when network signals are unstable or interrupted, the reliance on centralized computing architecture can cause delays or even loss of control commands. This results in a slow response to sudden temperature anomalies, hindering timely intervention and impacting yogurt quality.

[0004] To address the aforementioned issues, this invention provides a method and system for temperature control and traceability in yogurt cold chain logistics based on the Internet of Things. Summary of the Invention

[0005] The purpose of this invention is to provide a temperature control and traceability method and system for yogurt cold chain logistics based on the Internet of Things, so as to avoid the situation of yogurt failure after transportation is interrupted.

[0006] The present invention adopts the following technical solution: A method for temperature control and traceability in yogurt cold chain logistics based on the Internet of Things includes the following steps: Based on historical temperature data associated with the refrigeration equipment and the control status within the corresponding time period of the historical temperature data, temperature control parameters characterizing the operating characteristics of the refrigeration equipment are determined. Calculate and output the alarm temperature based on the temperature control parameters; Among them, the temperature control parameters that characterize the operating characteristics of refrigeration equipment include: Identify heating and cooling processes from historical temperature data, determine temperature control deviations based on these processes, and determine temperature control parameters based on multiple temperature control deviations determined within one or more statistical periods.

[0007] Preferably, the temperature control deviation is determined based on the heating and cooling processes, including: For the heating process, the heating deviation is determined based on the initial temperature at the start time and the final temperature at the end time. For the cooling process, the cooling deviation is determined based on the initial cooling temperature at the start time and the cooling end temperature at the end time. The temperature control deviation is determined based on all heating and cooling deviations obtained within a statistical period.

[0008] Preferably, identifying heating and cooling processes from historical temperature data includes: Historical temperature data is divided into multiple time sub-segments; Based on the direction of temperature change within each time sub-segment and the corresponding control status of the refrigeration equipment, the heating process and the cooling process are identified.

[0009] Preferably, the method further includes: Temperature nodes are obtained by collecting data from points deployed along the transportation route. Multiple temperature nodes that are associated with the refrigeration equipment over time are aggregated into historical temperature data.

[0010] Preferably, before determining the temperature control parameters characterizing the operating characteristics of the refrigeration equipment, the method further includes: Historical temperature data is defined as the area to be evaluated, and the regional attributes of the area to be evaluated are determined. When the regional attributes meet the preset analysis conditions, the step of determining the temperature control parameters is executed.

[0011] Preferably, determining the regional attributes of the area to be evaluated includes: Calculate the average temperature of the area to be evaluated. If the average temperature is lower than the preset upper temperature limit, the area to be evaluated is marked as an area to be confirmed. For the region to be confirmed, the region attribute is determined to be either steady state or floating state based on whether the absolute value of the temperature difference between adjacent temperature nodes in time is less than a first preset threshold.

[0012] Preferably, before determining the regional attributes of the area to be evaluated, the method further includes: The trend slope is obtained by performing linear regression analysis on the area to be evaluated. When the trend slope is positive, after a preset delay time, the data is reacquired and the average temperature used to determine the regional attributes is recalculated.

[0013] This invention also discloses an IoT-based temperature control and traceability system for yogurt cold chain logistics, comprising: The temperature acquisition module is used to collect temperature data through acquisition points deployed along the transportation path in order to obtain historical temperature data associated with the refrigeration equipment. The equipment performance evaluation module is configured to respond to historical temperature data and combine the control status of the refrigeration equipment within the corresponding time period of the historical temperature data to determine the temperature control parameters characterizing the operating characteristics of the refrigeration equipment. The alarm temperature generation module is configured to calculate and output the alarm temperature based on the temperature control parameters determined by the equipment performance evaluation module.

[0014] Preferably, the temperature control parameters determined by the equipment performance evaluation module include: Identify heating and cooling processes from historical temperature data; The temperature control deviation is determined based on the heating and cooling processes. Temperature control parameters are determined based on multiple temperature control deviations identified over one or more statistical periods.

[0015] Preferably, it further includes: The data quality assessment module is configured to determine the regional attributes of historical temperature data before the equipment performance assessment module performs its operations, and to trigger the equipment performance assessment module when the regional attributes meet the preset analysis conditions.

[0016] Beneficial effects 1. This invention calculates the temperature control deviation of the refrigeration equipment during historical heating and cooling processes, thereby determining the temperature control parameters that characterize the operating characteristics of the refrigeration equipment, and finally calculates the alarm temperature based on the temperature control parameters. By generating an alarm temperature that matches the current operating characteristics of the refrigeration equipment, it achieves early warning of potential faults, improves the predictability and reliability of temperature control traceability, and thus ensures the quality and safety of yogurt.

[0017] 2. This invention determines the operating status by acquiring the control status of the refrigeration equipment and combining it with the temperature change direction of historical temperature data. By associating the actual temperature change with the control status of the refrigeration equipment, it distinguishes between temperature fluctuations caused by changes in the control status and temperature changes caused by equipment failure, thus avoiding misjudging normal temperature fluctuations as abnormalities, reducing false alarm rate and improving the reliability of temperature control traceability.

[0018] 3. This invention aggregates multiple temperature nodes into an area to be evaluated to calculate the average temperature. Combining the temperature difference and trend slope, it determines whether the area attribute is steady-state or floating. Through data aggregation, internal stability testing and trend judgment processing, it filters out instantaneous noise and short-term fluctuations in the original temperature data, ensuring the stability of the data basis for subsequent analysis, thereby improving the robustness of the entire temperature control traceability process. Attached Figure Description

[0019] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely for explaining the invention and are not intended to limit the scope of protection of the invention.

[0021] Example 1 See Figure 1 This embodiment provides a temperature control and traceability method for yogurt cold chain logistics based on the Internet of Things, including the following steps: S1. Obtain the temperature node. The specific steps are as follows: By pre-deploying multiple collection points, the ambient temperature is periodically or event-triggered along the transportation route of the yogurt. Preferably, the collection points are wireless temperature sensors installed on the inner wall of the refrigerated compartment, on the surface of the cargo packaging box, or directly inserted into the simulated cargo. The simulated cargo refers to a gel block with similar thermodynamic properties to yogurt. Each acquisition generates a data pair containing a precise acquisition timestamp and a corresponding temperature value. This data pair is a temperature node. Multiple temperature nodes are arranged in chronological order and then aggregated to form the raw time series data for subsequent analysis.

[0022] S2. Determine the temperature control node. The specific steps are as follows: Obtain a preset baseline time period, which serves as the basic unit for defining the analysis window. Preferably, the baseline time period can be set to 5 minutes. All temperature nodes whose timestamps fall within the same baseline time period are aggregated to form the region to be evaluated. Preliminary trend analysis is then performed on this region to determine its overall temperature change trend, avoiding immediate but potentially erroneous judgments about ongoing and unstable temperature changes. Specifically: By performing linear regression analysis on all temperature nodes within the evaluation area, a trend fitting line and its trend slope are obtained; where the acquisition time is the horizontal axis and the temperature value is the vertical axis. If the trend slope is positive, the overall temperature change trend of the area to be evaluated is determined to be positive. This indicates that the temperature may be rising continuously. In order to ensure that the subsequent decision is based on a relatively stable state, after waiting for a preset delay time, such as waiting for 2 minutes, the acquisition and aggregation of temperature nodes will be re-executed to form a new area to be evaluated, and the data of the new area to be evaluated will be used for subsequent calculations. If the trend slope is not positive, i.e., zero or negative, then the overall temperature change trend of the area to be evaluated is determined to be a non-positive trend, and the initial area to be evaluated is directly used for subsequent calculations. Calculate the arithmetic mean of the temperature values ​​of all temperature nodes within the region to be evaluated to obtain the average temperature. Based on the average temperature, determine the region's attributes. The determination process includes: Obtain the preset upper limit of temperature as a critical safety indicator set according to the shelf life requirements of yogurt, and compare the average temperature with the upper limit of temperature; if the average temperature is not lower than the upper limit of temperature, the area attribute of the area to be evaluated is directly determined as an over-temperature state and it is used as a temperature control node; if the average temperature is lower than the upper limit of temperature, the area to be evaluated is marked as an area to be confirmed, and its internal temperature fluctuation is further analyzed. Specifically, the temperature difference between each pair of adjacent temperature nodes in the region to be confirmed is calculated in chronological order, and the absolute value of all these temperature differences is obtained. Then, a first preset threshold for measuring temperature stability is obtained, preferably 0.2 degrees Celsius. If the absolute value of all calculated temperature differences is less than the first preset threshold, it indicates that the temperature in the region is stable, and the region attribute of the region to be confirmed is determined to be steady state. If the absolute value of at least one temperature difference is not less than the first preset threshold, it indicates that the temperature in the region fluctuates significantly, and its region attribute is determined to be floating. The region to be evaluated with the region attribute determined, whether it is steady state, floating, or the aforementioned over-temperature state, is determined as a temperature control node for use in subsequent steps.

[0023] S3. Obtain the running status. The specific steps are as follows: For each defined temperature control node, the specific refrigeration equipment that provides cooling services to the environment where the temperature control node is located during the corresponding time period is identified. Then, the cooling nodes directly associated with the refrigeration equipment are identified. The cooling nodes are monitoring points used to measure the working efficiency of the refrigeration equipment itself, such as sensors installed at the air outlet of the refrigeration equipment. The historical temperature data of the cooling nodes in the past historical period and the control status of the refrigeration equipment in the same historical period, such as log records of the status of power-on, power-off, defrosting, etc., are obtained.

[0024] Based on the correspondence between historical temperature data and control status, the operating status of the refrigeration equipment is analyzed and extracted using preset matching rules. The analysis process is as follows: Historical temperature data is divided into multiple consecutive time segments. For each time segment, the direction of temperature change is determined by comparing the temperature values ​​at its start and end times. The direction of temperature change includes increasing, decreasing, or remaining unchanged. Obtain the corresponding refrigeration equipment control status during this period, and determine the refrigeration equipment's operating status as an effective or ineffective operating status based on the combination of temperature change direction and control status within this time sub-segment. The preset matching rules are a calculation model used to determine whether the operation of the refrigeration equipment is effective based on its control status and the actual temperature changes it generates. The specific definitions are as follows:

[0025] This is an indicator function; its value is 1 when the logical condition within the parentheses is true, and 0 otherwise. In the formula: This indicates the operating status of the equipment, which describes the judgment result of whether the equipment operation has achieved the expected effect. 1 represents an effective operating status and 0 represents an invalid operating status. Indicates the direction of temperature change, which describes the macroscopic trend of temperature change within a time sub-segment. -1 represents decreasing temperature, 0 represents constant temperature, and 1 represents increasing temperature. This indicates the control status of the equipment, which describes the command status of the refrigeration equipment within the corresponding time sub-segment. 1 represents power-on, and 0 represents power-off or non-refrigeration mode.

[0026] Furthermore, if the temperature change direction of a time sub-segment is monotonically decreasing and the corresponding control state is "on", then the expected cooling effect is achieved, and its operating state is determined to be an effective operating state. If the temperature change direction is monotonically increasing or unchanged and the corresponding control state is "on", or if the temperature change direction is monotonically decreasing and the corresponding control state is "off", it indicates that the equipment operation has not achieved the expected effect or the status record does not match the actual physical performance, and its operating state is determined to be an invalid operating state.

[0027] S4. Analyze the temperature control deviation. The specific steps are as follows: Based on the determined effective operating status, all cooling processes that are determined to be effective are screened from historical temperature data. Within a preset statistical period, such as the past 24 hours, all effective cooling processes are identified. For each effective cooling process, the temperature value at its start time is defined as the initial cooling temperature, and the temperature value at its end time is defined as the final cooling temperature. The duration of the process is also recorded. The cooling rate of the process is determined by the following formula: Cooling rate = (Initial cooling temperature - Ending cooling temperature) / Duration of cooling process; The cooling rate is the cooling deviation that quantifies the performance of the cooling process. All cooling deviation values ​​calculated within the statistical period are collected to form a temperature control deviation dataset that reflects the recent performance of the equipment. Based on multiple temperature control deviation datasets determined within one or more statistical periods, their arithmetic mean is calculated to obtain the average temperature control deviation that can represent the average cooling capacity of the refrigeration equipment under the current operating conditions.

[0028] S5. Construct temperature control parameters. The specific steps are as follows: Based on the calculated average temperature control deviation, a temperature control adjustment amount is constructed. The temperature control adjustment amount is set to be equal to the average temperature control deviation, which represents the expected cooling capacity of the refrigeration equipment per unit time. The adjustment time is obtained through a preset query mechanism, which dynamically determines the adjustment time based on the regional attributes of the current temperature control node and the difference between the current average temperature and the upper limit temperature. For example, this query mechanism can be based on a two-dimensional mapping table, where one dimension is the regional attribute and the other dimension is the temperature difference range. In a floating state with a small temperature difference, a shorter adjustment time will be mapped to allow for rapid intervention; while in a steady state with a large temperature difference, a longer adjustment time may be mapped to. The core temperature control parameter, i.e. the expected cooling range, is determined by multiplying the temperature control adjustment amount by the determined adjustment time. This expected cooling range represents the amount of cooling that the refrigeration equipment is expected to achieve within the future adjustment time.

[0029] S6. Alarm temperature assessment, the specific steps are as follows: The temperature control parameters determined above are set as the reference parameters. The alarm temperature is calculated and output based on the reference parameters. The calculation method is: alarm temperature = upper limit of temperature - expected temperature drop. The alarm temperature forms a dynamic safety buffer zone. Once the temperature value collected in real time reaches or exceeds the alarm temperature, even if the final upper limit of temperature has not yet been reached, an early warning signal will be generated immediately to realize closed-loop management of temperature control. This effectively moves the timing of regulation forward to avoid irreversible quality damage caused by equipment response delays or sudden changes in external conditions.

[0030] The warning signal can be used to notify managers or to send control commands to the refrigeration equipment to start it ahead of time or increase its power.

[0031] Example 2 See Figure 2 This embodiment provides an IoT-based temperature control and traceability system for yogurt cold chain logistics, including: The temperature acquisition module is configured to collect temperature data through acquisition points deployed along the transportation route to obtain historical temperature data associated with the refrigeration equipment. Furthermore, the acquisition points are preferably multiple IoT temperature sensors deployed inside the refrigerated compartment, at air outlets, at air inlets, and within cargo stacks.

[0032] Temperature values ​​are periodically acquired from the collection points, and each temperature value and its corresponding timestamp, device identifier, and other information are recorded as a temperature node. Multiple temperature nodes that are continuous in time and associated with the same refrigeration device are aggregated to form a historical temperature data for subsequent modules to analyze.

[0033] Furthermore, the temperature acquisition module is also used to synchronously acquire the control status of the refrigeration equipment within the corresponding time period of historical temperature data, such as whether the compressor is in the cooling state or in the shutdown state.

[0034] The data quality assessment module is configured to pre-assess the quality of historical temperature data before the equipment performance assessment module performs its operations, ensuring that the data used for analysis is valid and representative; it is also used to receive historical temperature data generated by the temperature acquisition module and define it as the area to be assessed.

[0035] A preliminary trend analysis is performed on the area to be evaluated. Specifically, linear regression analysis is performed on the temperature nodes within the area to be evaluated to obtain the trend slope. If the trend slope shows a significant positive value, it indicates an abnormal continuous temperature rise event, such as a car door not being closed tightly. In this case, the analysis will be paused, and after waiting for a preset delay time, the temperature acquisition module will be instructed to reacquire data to form a new area to be evaluated, thereby avoiding incorrect performance evaluation based on abnormal operating condition data.

[0036] After confirming that the data is not in a continuous upward trend, we begin to determine the regional attributes of the area to be evaluated, as follows: Calculate the average temperature of the area. If the average temperature is higher than the preset upper limit of temperature set for the quality and safety of yogurt, the data segment is considered invalid. If the average temperature is within the acceptable range, the area is marked as an area to be confirmed. For the region to be confirmed, calculate the absolute value of the temperature difference between each temperature node that is adjacent in time within it. If the absolute value of the vast majority or all of the temperature differences is less than the first preset threshold, it indicates that the temperature fluctuation is gentle. Then the region is determined to be in a steady state and meets the preset analysis conditions. Conversely, if the temperature fluctuates drastically, the regional attribute is determined to be floating. Only when the regional attribute is determined to meet the analysis conditions, that is, when the regional attribute is determined to be in a steady state, will this high-quality historical temperature data be transmitted to the equipment performance evaluation module.

[0037] The equipment performance evaluation module is configured to respond to historical temperature data and combine it with the corresponding control status to determine the temperature control parameters that characterize the operating characteristics of the refrigeration equipment.

[0038] Furthermore, after receiving the historical temperature data and its corresponding control status information filtered by the data quality assessment module, process identification is performed. The historical temperature data is divided into multiple time sub-segments. Within each time sub-segment, a joint judgment is made based on the direction of temperature change within that segment and the control status of the refrigeration equipment at that time, thereby accurately identifying the heating and cooling processes from the data. The heating process includes, for example, the temperature rise naturally during equipment shutdown due to the intrusion of external heat or the respiration heat of the goods, while the cooling process includes, for example, the temperature drop caused by the operation of the refrigeration system during equipment startup.

[0039] After identifying the heating and cooling processes, the temperature control deviation is determined. For each identified heating process, the initial temperature at the start time and the end temperature at the end time are extracted, and the heating deviation is calculated based on the two. Similarly, for each cooling process, the initial temperature at the start time and the end temperature at the end time are extracted, and a cooling deviation is calculated. Within a preset statistical period, such as a complete cooling start-stop cycle or within an hour, all obtained temperature rise and temperature drop deviations are comprehensively statistically analyzed to determine the temperature control deviation that can represent the overall temperature fluctuation of the equipment within that period.

[0040] Multiple temperature control deviations are collected and analyzed within one or more statistical periods. By analyzing the trends or performing statistical calculations on these historical temperature control deviations, temperature control parameters that can stably characterize the current operating characteristics of the refrigeration equipment are determined. These temperature control parameters objectively reflect the comprehensive performance of the equipment, such as its insulation performance, refrigeration efficiency, and control accuracy.

[0041] The alarm temperature generation module is configured to calculate and output the alarm temperature based on the temperature control parameters determined by the equipment performance evaluation module.

[0042] Adjustments are made based on the actual performance of the equipment. The temperature control parameters, which quantify the temperature fluctuation range of the equipment under normal operation, are received from the equipment performance evaluation module. Based on these temperature control parameters, a new alarm temperature is calculated. The preferred calculation method is to subtract the fluctuation range represented by the temperature control parameters from the upper limit of the temperature.

[0043] Because the temperature rise process that the equipment needs to go through from normal fluctuation to actual over-temperature state is taken into account, an early warning signal is generated when the real-time temperature reaches the dynamically calculated alarm temperature, giving managers valuable time to take intervention measures.

Claims

1. A method for temperature control and traceability in yogurt cold chain logistics based on the Internet of Things, characterized in that, Includes the following steps: Based on historical temperature data associated with the refrigeration equipment and the control status within the corresponding time period of the historical temperature data, temperature control parameters characterizing the operating characteristics of the refrigeration equipment are determined. Calculate and output the alarm temperature based on the temperature control parameters; Among them, the temperature control parameters that characterize the operating characteristics of refrigeration equipment include: Identify heating and cooling processes from historical temperature data, determine temperature control deviations based on these processes, and determine temperature control parameters based on multiple temperature control deviations determined within one or more statistical periods.

2. The method for temperature control and traceability of yogurt cold chain logistics based on the Internet of Things according to claim 1, characterized in that, Based on the heating and cooling processes, the temperature control deviation is determined to include: For the heating process, the heating deviation is determined based on the initial temperature at the start time and the final temperature at the end time. For the cooling process, the cooling deviation is determined based on the initial cooling temperature at the start time and the cooling end temperature at the end time. The temperature control deviation is determined based on all heating and cooling deviations obtained within a statistical period.

3. The method for temperature control and traceability of yogurt cold chain logistics based on the Internet of Things according to claim 1, characterized in that, Identifying warming and cooling processes from historical temperature data includes: Historical temperature data is divided into multiple time sub-segments; Based on the direction of temperature change within each time sub-segment and the corresponding control status of the refrigeration equipment, the heating process and the cooling process are identified.

4. The method for temperature control and traceability of yogurt cold chain logistics based on the Internet of Things according to claim 1, characterized in that, The method further includes: Temperature nodes are obtained by collecting data from points deployed along the transportation route. Multiple temperature nodes that are associated with the refrigeration equipment over time are aggregated into historical temperature data.

5. The method for temperature control and traceability of yogurt cold chain logistics based on the Internet of Things according to claim 1, characterized in that, Before determining the temperature control parameters characterizing the operating characteristics of the refrigeration equipment, the method also includes: Historical temperature data is defined as the area to be evaluated, and the regional attributes of the area to be evaluated are determined. When the regional attributes meet the preset analysis conditions, the step of determining the temperature control parameters is executed.

6. The method for temperature control and traceability of yogurt cold chain logistics based on the Internet of Things according to claim 5, characterized in that, The regional attributes of the area to be evaluated include: Calculate the average temperature of the area to be evaluated. If the average temperature is lower than the preset upper temperature limit, the area to be evaluated is marked as an area to be confirmed. For the region to be confirmed, the region attribute is determined to be either steady state or floating state based on whether the absolute value of the temperature difference between adjacent temperature nodes in time is less than a first preset threshold.

7. The method for temperature control and traceability of yogurt cold chain logistics based on the Internet of Things according to claim 5, characterized in that, Before determining the regional attributes of the area to be evaluated, the method also includes: The trend slope is obtained by performing linear regression analysis on the area to be evaluated. When the trend slope is positive, after a preset delay time, the data is reacquired and the average temperature used to determine the regional attributes is recalculated.

8. A temperature control and traceability system for yogurt cold chain logistics based on the Internet of Things, characterized in that, include: The temperature acquisition module is used to collect temperature data through acquisition points deployed along the transportation path in order to obtain historical temperature data associated with the refrigeration equipment. The equipment performance evaluation module is configured to respond to historical temperature data and combine the control status of the refrigeration equipment within the corresponding time period of the historical temperature data to determine the temperature control parameters characterizing the operating characteristics of the refrigeration equipment. The alarm temperature generation module is configured to calculate and output the alarm temperature based on the temperature control parameters determined by the equipment performance evaluation module.

9. A temperature control and traceability system for yogurt cold chain logistics based on the Internet of Things as described in claim 8, characterized in that, The temperature control parameters determined by the equipment performance evaluation module include: Identify heating and cooling processes from historical temperature data; The temperature control deviation is determined based on the heating and cooling processes. Temperature control parameters are determined based on multiple temperature control deviations identified over one or more statistical periods.

10. A temperature control and traceability system for yogurt cold chain logistics based on the Internet of Things as described in claim 8, characterized in that, Also includes: The data quality assessment module is configured to determine the regional attributes of historical temperature data before the equipment performance assessment module performs its operations, and to trigger the equipment performance assessment module when the regional attributes meet the preset analysis conditions.

Images