【正文】 This information is used to create temperature pensation described in AN840 Temperature Compensation Methods that can be found at . Sensors with internal pensation are also available,but at a higher cost. The benefit of lower overall system cost can be achieved by using a method where the internal temperature sensor of the S08 microcontroller is used as the reference to perform temperature pensation. Another benefit of using temperature pensation is extending the operating range of the end application. For example an application that requires accurate serial munications requires an accurate reference clock. If the reference clock loses accuracy at a hot temperature, the end application can not acplish the serial munications. Using temperature pensation to modify the serial munications at a hot temperature allows the end application to operate across a wider range. Both of the benefits listed above add value to the end application by using only the available on chip features. 6 Temperatue Compensation Methods The theory behind performing temperature pensation is straight forward. It involves 23 taking a temperature reading and changing the peripheral parameters based on a knowledge base of how the peripheral performs across temperature. Peripheral parameters are external or internal factors that affect the operation of the peripheral. In the case of an internal reference clock, such as the ICS internal reference clock on many S08 microcontrollers, the peripheral parameter that affects the output frequency is the TRIM register. Many system peripherals contain a trim register that allows pensation of the output of the peripheral. Another example of a peripheral parameter are equation variables. For example, if the peripheral is a sensor that outputs an analog voltage and the output contains an offset that is temperature dependant, then the peripheral parameter that must be changed at different temperatures are the equation variables that account for the offset voltage. To understand the peripheral parameters and how they must be changed, a knowledge base must be referenced. An example of a knowledge base is a specification. For example, the specification for the Freescale MPX10 series contains the parameters that define how the output of the pressure sensor changes across temperature ranges. A 。)。 plot(n,hardlim(n),39。 17 附錄： 附錄 1： 外文文獻(xiàn)原文 Mark Beale,Neural Network Toolbox: 1 Neuron Model Simple Neuron A neuron with a single scalar input and no bias appears on the left below. The scalar input p is transmitted through a connection that multiplies its strength by the scalar weight w, to form the product wp, again a scalar. Here the weighted input wp is the only argument of the transfer function f, which produces the scalar output a. The neuron on the right has a scalar bias, b. You may view the bias as simply being added to the product wp as shown by the summing junction or as shifting the function f to the left by an amount b. The bias is much like a weight, except that it has a constant input of transfer function input n, again a scalar, is the sum of the weighted input wp and the bias b. This sum is the argument of the transfer function f. (Chapter 7 discusses a different way to form the input n.) Here f is a transfer function, typically a step function or a sigmoid function, which takes the argument n and produces the output a. Examples of various transfer functions are given in the next section. Note that w and b are both adjustable scalar parameters of the neuron. The central idea of neural works is that such parameters can be adjusted so that the work exhibits some desired or interesting behavior. Thus, we can train the work to do a particular job by adjusting the weight or bias parameters, or perhaps the work itself will adjust these parameters to achieve some desired end. 18 All of the neurons in this toolbox have provision for a bias, and a bias is used in many of our examples and will be assumed in most of this toolbox. However, you may omit a bias in a neuron if you want. As previously noted, the bias b is an adjustable (scalar) parameter of the neuron. It is not an input. However, the constant 1 that drives the bias is an input and must be treated as such when considering the linear dependence of input vectors in Chapter 4, “Linear Filters.” 2 Transfer Functions Many transfer functions are included in this toolbox. A plete list of them can be found in “Transfer Function Graphs” in Chapter 14. Three of the most monly used functions are shown below. The hardlimit transfer function shown above limits the output of the neuron to either 0, if the input argument n is less than 0。這段時(shí)間里老師給我的啟迪及所學(xué)到的內(nèi)容，相信，學(xué)到的學(xué)習(xí)方法也同樣會(huì)影響我今后的學(xué)習(xí)。 在論文的過程中每一次遇到不懂的問題趙老師都會(huì)認(rèn)真和耐心的為我講解，并且老師會(huì)經(jīng)常檢查論文的進(jìn)度情況，對(duì)論文中存在的問題及時(shí)指出，為我的修改提供建議。 通過上面的實(shí)驗(yàn)分析，因此在實(shí)際應(yīng)用中我們應(yīng)該根據(jù)實(shí)際的的需要選擇適當(dāng)?shù)难a(bǔ)償方法來實(shí)現(xiàn)溫度的補(bǔ)償過程。 結(jié)論 通過實(shí)驗(yàn)對(duì)比插值算法的實(shí)現(xiàn)的溫度補(bǔ)償與實(shí)際的輸出特性誤差比較大； BP 和RBF 神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)的溫度補(bǔ)償精度較高，但在應(yīng)用中，二者的區(qū)別有： ?與 BP 神經(jīng)網(wǎng)絡(luò)相比 RBF 神經(jīng)網(wǎng)絡(luò)的輸出是隱單元輸出的線性加權(quán)和，學(xué)習(xí)速度加快； ?BP 神經(jīng)網(wǎng)絡(luò)使用 sigmoid（）函數(shù)作為激活函數(shù)，這樣是的神經(jīng)元有很大的輸入輸入可見區(qū)域；而 RBF 神經(jīng)網(wǎng)絡(luò)使用徑向函數(shù)（一般使用高斯函數(shù)）作為激活函數(shù)，神經(jīng)元輸入空間很小，因此需要更多的徑向基神經(jīng)元； ?RBF 神經(jīng)網(wǎng)絡(luò)具有比 BP 神經(jīng)網(wǎng)絡(luò)更強(qiáng)的逼近能力和更快的收斂速度 ,且不存在局部極小問題 ,通過訓(xùn)練 RBF 神經(jīng)網(wǎng)絡(luò)能夠逼近任意非線性。將帶遺忘 因子的梯度下降算法應(yīng)用于 RBF 神經(jīng)網(wǎng)絡(luò)的參數(shù)調(diào)整 ,該算法具有良好的非線性映射能力、自學(xué)習(xí)和泛化能力 ,收斂較快 ,特別適用于傳感器數(shù)學(xué)模型的建立。 另外 BP神經(jīng)網(wǎng)絡(luò)在控制領(lǐng)域的缺點(diǎn)還有是它的權(quán)值和偏置值矩陣占用的內(nèi)存太大，所以對(duì)單片機(jī)的內(nèi)存要求也高，成本相應(yīng)的也要增加。 （ 4）網(wǎng)絡(luò)隱層節(jié)點(diǎn)的個(gè)數(shù)的選擇尚無理論指導(dǎo)，一般是根據(jù)經(jīng)驗(yàn)選取的。 若初始權(quán)值離極小點(diǎn)很近，則收斂速度較快；若初始值權(quán)值遠(yuǎn)離極小點(diǎn)，則收斂速度極慢。 （ 3）網(wǎng)絡(luò)對(duì)初始值很敏感。因?yàn)?BP 算法是以階梯下降法為基礎(chǔ)的，只具有先行收斂速度，雖通過引入“勢態(tài)項(xiàng)”增加了一定程度的二階信息，但對(duì)算法的性質(zhì)并無根本的改變。采用 BP神經(jīng)網(wǎng)絡(luò)對(duì)壓力傳感器進(jìn)行溫度補(bǔ)償，由于神經(jīng)網(wǎng)絡(luò)具有非線性特 性、自適應(yīng)和學(xué)習(xí)能力 ,只要能獲取傳感器的輸入和輸出數(shù)據(jù) ,通過適當(dāng)?shù)挠?xùn)練學(xué)習(xí) ,可以逼近其輸入輸出特性。 (二 )BP神經(jīng)網(wǎng)絡(luò)算法準(zhǔn)確度高，它基本消除了溫度對(duì)壓力傳感器輸出信號(hào)的影響，實(shí)現(xiàn)了壓力傳感器的溫度補(bǔ)償，提高了壓力傳感器的精確度和可靠性。 3 仿真研究與實(shí)驗(yàn)結(jié)果 由前面所述的 RBF 神經(jīng)網(wǎng)絡(luò)模型，在基于 RBF 神經(jīng)網(wǎng)絡(luò)的溫度補(bǔ)償實(shí)驗(yàn) 中，為了實(shí)現(xiàn)實(shí)驗(yàn)的對(duì)